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.1698129108.rhmmedcatt-proliant-ml350-gen10 b/.summary/0/events.out.tfevents.1698129108.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..7107d71e87bdf0fe27911f42d0633c428f471195 --- /dev/null +++ b/.summary/0/events.out.tfevents.1698129108.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51c2957ebf722ad6311fa781c16b4d8f3c6500f7405434a3f70269b4acb28fd8 +size 87326717 diff --git a/.summary/1/events.out.tfevents.1698129108.rhmmedcatt-proliant-ml350-gen10 b/.summary/1/events.out.tfevents.1698129108.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..7a2f7a070591629c9fdc8d13609181f3102fb14f --- /dev/null +++ b/.summary/1/events.out.tfevents.1698129108.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8597951e4d296a921251cb69251174a6a7837e00462ffb324b83b5ce0f1cdfc +size 45889523 diff --git a/README.md b/README.md index 2529060c02b3fd1e4de01f1e3ea72f536883bc11..abb402bd4535c5b59fc4ebef9317718c02f43172 100644 --- a/README.md +++ b/README.md @@ -15,35 +15,39 @@ model-index: type: atari_berzerk metrics: - type: mean_reward - value: 2047.00 +/- 696.72 + value: 46256.00 +/- 17678.86 name: mean_reward verified: false --- -A(n) **APPO** model trained on the **atari_berzerk** 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_berzerk -``` +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_berzerk** 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_berzerk +``` + + ## Using the model To run the model after download, use the `enjoy` script corresponding to this environment: diff --git a/checkpoint_p0/best_001875680_480174080_reward_34.260.pth b/checkpoint_p0/best_001875680_480174080_reward_34.260.pth new file mode 100644 index 0000000000000000000000000000000000000000..5cf8b61dcd92902819ff3eb2367197fccb5708aa --- /dev/null +++ b/checkpoint_p0/best_001875680_480174080_reward_34.260.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e2d362a3a690f7fac67d079a964b931699ecbaa2e7d40d4492a13631db3238a +size 20795763 diff --git a/checkpoint_p0/checkpoint_001953504_500203520.pth b/checkpoint_p0/checkpoint_001953504_500203520.pth new file mode 100644 index 0000000000000000000000000000000000000000..453337bf4c96e93a5236e86ee56d0b4e506168c5 --- /dev/null +++ b/checkpoint_p0/checkpoint_001953504_500203520.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3b0f7a27fced906be2b267a14c2389dc13721b20b97c5821b4f357da9fca67b +size 20796099 diff --git a/checkpoint_p0/checkpoint_001953968_500441088.pth b/checkpoint_p0/checkpoint_001953968_500441088.pth new file mode 100644 index 0000000000000000000000000000000000000000..36bd1d1905a49c362985e54e4bb020ddfc405ad0 --- /dev/null +++ b/checkpoint_p0/checkpoint_001953968_500441088.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d479b0c0ce66205ca397e081e4d03cb26c829d7f040a339805051d05cb1cd9b7 +size 20796099 diff --git a/checkpoint_p0/milestones/checkpoint_000013728_3514368.pth b/checkpoint_p0/milestones/checkpoint_000013728_3514368.pth new file mode 100644 index 0000000000000000000000000000000000000000..3d45716c2be3dcf83399913786a23f2604c81b15 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000013728_3514368.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a43d5c1519beefb839e7e6b993111e38096ed07b7c0707374b036880383fc746 +size 20796955 diff --git a/checkpoint_p0/milestones/checkpoint_000027712_7094272.pth b/checkpoint_p0/milestones/checkpoint_000027712_7094272.pth new file mode 100644 index 0000000000000000000000000000000000000000..beb365c944b1f8df70a9ae421a3e5c27bbdbda73 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000027712_7094272.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77c95cc3e6d92c683ddd3d083b03392fde907a31df1e75a31f13dea1788682f4 +size 20796955 diff --git a/checkpoint_p0/milestones/checkpoint_000041792_10698752.pth b/checkpoint_p0/milestones/checkpoint_000041792_10698752.pth new file mode 100644 index 0000000000000000000000000000000000000000..d7428fd242d3a5d6e025aa57a191c5cd72e0d6ec --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000041792_10698752.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acb126c3b590a1542e468ea08dbfa1d3ee21c4a345c288d3cb74aa9603ae037a +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000055968_14327808.pth b/checkpoint_p0/milestones/checkpoint_000055968_14327808.pth new file mode 100644 index 0000000000000000000000000000000000000000..50b09bf82d830a6bfd2f5b9a6b2d295a52e9ede7 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000055968_14327808.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba903e3e849bc71a4c08f9baa19c95c03f89d1380d8e72acc04dd925f127c9c4 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000070016_17924096.pth b/checkpoint_p0/milestones/checkpoint_000070016_17924096.pth new file mode 100644 index 0000000000000000000000000000000000000000..29633d81e3b4b3e264a20ed26bd78327483da765 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000070016_17924096.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:605af8d06ccd03b9d524aa2de2ed1fd0ee1c57cf66853ccb0ded2792845812a4 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000084128_21536768.pth b/checkpoint_p0/milestones/checkpoint_000084128_21536768.pth new file mode 100644 index 0000000000000000000000000000000000000000..9f58cf3bbf1f004e8f3a63c0db78859f5dc4ed10 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000084128_21536768.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faed992ccc2747b5aeb8f904b38c0174633f75c743246bb501fed14f95ec7829 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000098272_25157632.pth b/checkpoint_p0/milestones/checkpoint_000098272_25157632.pth new file mode 100644 index 0000000000000000000000000000000000000000..7d1e42c216b8bcc8f38dcea65c6117efb090948f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000098272_25157632.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdbe8f4c65533aa1ffa23a851a9a2651d265d750c7a145810e0702c860d945ba +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000112448_28786688.pth b/checkpoint_p0/milestones/checkpoint_000112448_28786688.pth new file mode 100644 index 0000000000000000000000000000000000000000..c18c099fe89fde0604cf3b7262b1c9a26001a599 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000112448_28786688.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc59e190011eb9ab108d92a3ad54b086d8e37aa48a65a86628e43493deeb3231 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000125408_32104448.pth b/checkpoint_p0/milestones/checkpoint_000125408_32104448.pth new file mode 100644 index 0000000000000000000000000000000000000000..1589efef420d9e63e9fb95ce8f36e9d478c14134 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000125408_32104448.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5408063c944bc1ad7e786c41d46366e67946917709beed0871be0f4eab2a5517 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000139584_35733504.pth b/checkpoint_p0/milestones/checkpoint_000139584_35733504.pth new file mode 100644 index 0000000000000000000000000000000000000000..9d8326a2bec3502409aef393dfcc715a3b52841c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000139584_35733504.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a07dbc9dfb6e6d3df4a887316beda46998358c0ad31e8a6ba94b5f11ab91062 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000153728_39354368.pth b/checkpoint_p0/milestones/checkpoint_000153728_39354368.pth new file mode 100644 index 0000000000000000000000000000000000000000..011bd5975490c10099db4793931fccebf0907b3f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000153728_39354368.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8986503fb79039e812f896a7ca5fa79460282e2181da052683d471ecdb9774b4 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000167776_42950656.pth b/checkpoint_p0/milestones/checkpoint_000167776_42950656.pth new file mode 100644 index 0000000000000000000000000000000000000000..75fb6a3edb89e4c8570d601834a77d7833e7fa03 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000167776_42950656.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b8c12169e0dceb950e72ba9b0f6449fb0b8e92be7289b78404e56556fb639a5 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000181888_46563328.pth b/checkpoint_p0/milestones/checkpoint_000181888_46563328.pth new file mode 100644 index 0000000000000000000000000000000000000000..dc8d29c78a50f37f5715ad98fcd21bfe7c0d90d4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000181888_46563328.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4743cc355386e77d96e61930516545fc1fd760e6081e1f8e86b5562dc9156817 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000196032_50184192.pth b/checkpoint_p0/milestones/checkpoint_000196032_50184192.pth new file mode 100644 index 0000000000000000000000000000000000000000..335bef2fc80304f295c8b17a2e0b2aaa03335c60 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000196032_50184192.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d70f547d23e097db69b7cb27843c69cd6f146359dd17598b2c3461452b9d970 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000210176_53805056.pth b/checkpoint_p0/milestones/checkpoint_000210176_53805056.pth new file mode 100644 index 0000000000000000000000000000000000000000..cc047dd33b490e14c20574afd8cc10432348dcdb --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000210176_53805056.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d6104bb2a35dece58c95335e0665d781c7052dd75aac1f4f7fbee00a1a3ed7b +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000224352_57434112.pth b/checkpoint_p0/milestones/checkpoint_000224352_57434112.pth new file mode 100644 index 0000000000000000000000000000000000000000..4fd3a36f4e4e52e93ba35996f47d4a57b91d7203 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000224352_57434112.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32dcb7469f6829de47258a477480471a2373fabb9a3d09fa5fb29846685f8b44 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000238432_61038592.pth b/checkpoint_p0/milestones/checkpoint_000238432_61038592.pth new file mode 100644 index 0000000000000000000000000000000000000000..ffc7d2a310d3942686c0092099c01ebf4506e555 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000238432_61038592.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:114139d9bdc412a7195666c7e6f5f5d4bae103708db4e355376d5664c7639f5c +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000252544_64651264.pth b/checkpoint_p0/milestones/checkpoint_000252544_64651264.pth new file mode 100644 index 0000000000000000000000000000000000000000..59a8011170226195b6d70e9ac104ceb19a9749e2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000252544_64651264.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbe251508c8cff39ec51db58b4287d22386fbce83c8bb6a43f666b45a8f5abbc +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000266624_68255744.pth b/checkpoint_p0/milestones/checkpoint_000266624_68255744.pth new file mode 100644 index 0000000000000000000000000000000000000000..a74fdb2c5d7932f4130d8536c79a56cfbd6ea527 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000266624_68255744.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9ca0ec207c08567d7f9b6900e2ef50bea3dd1c8fefeb866c3987f91df1943a2 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000280736_71868416.pth b/checkpoint_p0/milestones/checkpoint_000280736_71868416.pth new file mode 100644 index 0000000000000000000000000000000000000000..7060774f59909f6bb3d92e69bc4c8145f3fad3a5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000280736_71868416.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2933d09a3f1ea241614d1b2948b194f1447c3ebde3475869d81e3d196afee6da +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000294912_75497472.pth b/checkpoint_p0/milestones/checkpoint_000294912_75497472.pth new file mode 100644 index 0000000000000000000000000000000000000000..7e8c79f9aaf838ae40a55930a0311c0ce6079590 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000294912_75497472.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b268886fc7be824a5c03cdd7f84c57b1f24e9a6535bd392ad9b0700239e39e36 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000309056_79118336.pth b/checkpoint_p0/milestones/checkpoint_000309056_79118336.pth new file mode 100644 index 0000000000000000000000000000000000000000..2dfd6652a3a40caf6f39f707152ef1037de82978 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000309056_79118336.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b41196570ff4dd679b861b7f40a00ba54d5a66dbaccf370098ead6e3f62d8dfc +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000323392_82788352.pth b/checkpoint_p0/milestones/checkpoint_000323392_82788352.pth new file mode 100644 index 0000000000000000000000000000000000000000..90b49a94986adf6505a4a1937f248d9b0f84683e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000323392_82788352.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb6cad209d597d36622f8f580d724b7ace4f3211d63998e201e228dc5ee388b5 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000337504_86401024.pth b/checkpoint_p0/milestones/checkpoint_000337504_86401024.pth new file mode 100644 index 0000000000000000000000000000000000000000..4121ec0d98dfb9c2c8e3cc956411bf88e8e31e18 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000337504_86401024.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51b148a24ead6664246bed9c7c81929a71e63c004b7f33f07db71862a1238728 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000351520_89989120.pth b/checkpoint_p0/milestones/checkpoint_000351520_89989120.pth new file mode 100644 index 0000000000000000000000000000000000000000..5a10ed86ce70bd74db6db66824e44a8e27ecc65a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000351520_89989120.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:402a726b0cd876de0380cf5440e7a40fff190d0e6f11084888635370d69e9c45 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000364096_93208576.pth b/checkpoint_p0/milestones/checkpoint_000364096_93208576.pth new file mode 100644 index 0000000000000000000000000000000000000000..4845d42cf30e3e72b73c0ec23cc354cb6c0e7919 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000364096_93208576.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e60f9c92e82588a132b20afb1744c200d81dc0ed1494fc5232d2b598b3cee64 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000373248_95551488.pth b/checkpoint_p0/milestones/checkpoint_000373248_95551488.pth new file mode 100644 index 0000000000000000000000000000000000000000..13c3984f8e11b9be061cb8a6c7a3f577adfb213e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000373248_95551488.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16519024f963440a02c6381cf791b36c7a600277256af0a30aa64abda7c58fd2 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000382464_97910784.pth b/checkpoint_p0/milestones/checkpoint_000382464_97910784.pth new file mode 100644 index 0000000000000000000000000000000000000000..86f7c045b9ddce29bce68ed29b7da0b89977c561 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000382464_97910784.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40b64510c678906d3182debfef6c18d1942a770efd4ab17c2da667d0e43486bb +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000391680_100270080.pth b/checkpoint_p0/milestones/checkpoint_000391680_100270080.pth new file mode 100644 index 0000000000000000000000000000000000000000..05c44eb3d72342b7e4e48be65b3f3e14cc76c237 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000391680_100270080.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63a79ff047368bb253f544435d54a577a301594310171576fa28588d19d53e9f +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000400928_102637568.pth b/checkpoint_p0/milestones/checkpoint_000400928_102637568.pth new file mode 100644 index 0000000000000000000000000000000000000000..529f15c4a92c42b3bf45563178d233202fcfcc3f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000400928_102637568.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df6f3d6f739826898382c2af48dfebbe8940a1efbfa24e57dca8a05bfcb35f23 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000410176_105005056.pth b/checkpoint_p0/milestones/checkpoint_000410176_105005056.pth new file mode 100644 index 0000000000000000000000000000000000000000..47ad016bcb29180db93d57101406f73d103ec30a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000410176_105005056.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19bf158eaf09ba8c6fd034c5664088c5597e8c2dcee0299a10f4788b4cace497 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000419392_107364352.pth b/checkpoint_p0/milestones/checkpoint_000419392_107364352.pth new file mode 100644 index 0000000000000000000000000000000000000000..62a75a1b022c165e0eb415aee98442c366ee48ec --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000419392_107364352.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27258069769dfd45a34429e15ab561b97af38d8bcced342052822770c169d7bc +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000428608_109723648.pth b/checkpoint_p0/milestones/checkpoint_000428608_109723648.pth new file mode 100644 index 0000000000000000000000000000000000000000..7246760c5536b3c522bbe2478278d03bfd0b7719 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000428608_109723648.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:698e87a95ad13132aa40b9e0625b86c097174a0414aa0068db622d4cc69f3949 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000437824_112082944.pth b/checkpoint_p0/milestones/checkpoint_000437824_112082944.pth new file mode 100644 index 0000000000000000000000000000000000000000..2df9d3aeacd26913737bef881c3162ff4597a969 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000437824_112082944.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76489ebabea0c00919ee888fdd43279d57cfe4354a2ef323fd057bf133727c47 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000447040_114442240.pth b/checkpoint_p0/milestones/checkpoint_000447040_114442240.pth new file mode 100644 index 0000000000000000000000000000000000000000..d4986afa56bed32698a6313bbcb5a6321998b4af --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000447040_114442240.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13df87e8b6107d4bf20c8261fb1d706f06fd2d713246b25a7ed4878c4b5b3cfe +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000457216_117047296.pth b/checkpoint_p0/milestones/checkpoint_000457216_117047296.pth new file mode 100644 index 0000000000000000000000000000000000000000..b4ff87838f832fc97d5b27a180d18f79b0bb73c2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000457216_117047296.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfe6c08dfffdd777c72d3c6b3634dea7937efd264781441a5d9d15f99fda45bf +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000466560_119439360.pth b/checkpoint_p0/milestones/checkpoint_000466560_119439360.pth new file mode 100644 index 0000000000000000000000000000000000000000..8f4108e18324fb50d502c3b2af712f726687eda9 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000466560_119439360.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3db6a853d70ca154051032ac9c0b0542ee012cde6b9d22e8438aa0c12d251f5e +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000475808_121806848.pth b/checkpoint_p0/milestones/checkpoint_000475808_121806848.pth new file mode 100644 index 0000000000000000000000000000000000000000..58a7ef0027de057030c9ac6c9ce583d65be12007 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000475808_121806848.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e53c870fa62aa9ebcdbdb71bf63cacf02d4a842f2d54cdc38e1c249e43678ddc +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000485056_124174336.pth b/checkpoint_p0/milestones/checkpoint_000485056_124174336.pth new file mode 100644 index 0000000000000000000000000000000000000000..cbcaa8c31ad09dd1a710cbb2ac834a147efd0208 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000485056_124174336.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad82067259527cb47c1b6341e93940b1570c36380489d2ad071145dd45958ed5 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000494272_126533632.pth b/checkpoint_p0/milestones/checkpoint_000494272_126533632.pth new file mode 100644 index 0000000000000000000000000000000000000000..cbc5e94c83196e5745ad9f04f97db0117c479073 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000494272_126533632.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e57c7b2db296e2512e52d49c7fbd669ee0356146dfa092614731229a85173dc9 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000503488_128892928.pth b/checkpoint_p0/milestones/checkpoint_000503488_128892928.pth new file mode 100644 index 0000000000000000000000000000000000000000..c49de83cd7f52448f307ecfdaa851a2d3b48475a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000503488_128892928.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:441ac4f2538bd860af372d213132ff30b2755bfadc79350e49148e36136b2a52 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000512704_131252224.pth b/checkpoint_p0/milestones/checkpoint_000512704_131252224.pth new file mode 100644 index 0000000000000000000000000000000000000000..28d8bb185107cf377d051d2eb010ae728ce8f1f5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000512704_131252224.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc120ad04c0b0396d208d32c6d63ec7a16d7bed43cae7d60ba8964c59f4e9b39 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000521920_133611520.pth b/checkpoint_p0/milestones/checkpoint_000521920_133611520.pth new file mode 100644 index 0000000000000000000000000000000000000000..f4f0cd4b396ab582d42a61c659bad9ec15d72c50 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000521920_133611520.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29e0302f1c8864c2e772123fdc410c524987fedce0e4fa5393183c5d44c9ac08 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000531136_135970816.pth b/checkpoint_p0/milestones/checkpoint_000531136_135970816.pth new file mode 100644 index 0000000000000000000000000000000000000000..a901122ac562ff32026163f2fccf9a6a47e31b9a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000531136_135970816.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbf17a87f51e16d5ece660cc44a7e186fee00b4a87f6350319d8337b6ff32e9b +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000540352_138330112.pth b/checkpoint_p0/milestones/checkpoint_000540352_138330112.pth new file mode 100644 index 0000000000000000000000000000000000000000..95e832982a71744664f9bd5ab27b802b3a8fe92d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000540352_138330112.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c05eb65e9b4137791782246b59e429280004dd83bc3ac733ca1fcd131c8eee4 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000550112_140828672.pth b/checkpoint_p0/milestones/checkpoint_000550112_140828672.pth new file mode 100644 index 0000000000000000000000000000000000000000..b9f6eaca4d94ad33d4a63326d0ed72edbe072fbb --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000550112_140828672.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d32661d150af63934549fd6872fc62991aa26a343b753a272dc117e6511e3a4 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000559904_143335424.pth b/checkpoint_p0/milestones/checkpoint_000559904_143335424.pth new file mode 100644 index 0000000000000000000000000000000000000000..565d79c45856e0184fff33e6e99959724fe87a1c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000559904_143335424.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c24d36e9ea027452553d1fd3307bbd57a75023670ba53e3a8078d779c9c7873 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000569184_145711104.pth b/checkpoint_p0/milestones/checkpoint_000569184_145711104.pth new file mode 100644 index 0000000000000000000000000000000000000000..b9ff9bf532a3277a9f671f51e3c9130fae4e6da5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000569184_145711104.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ade73d4769b8ab62ef74ef8284e80e30763951e63db38749b0006d0bbfdf3ffb +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000578400_148070400.pth b/checkpoint_p0/milestones/checkpoint_000578400_148070400.pth new file mode 100644 index 0000000000000000000000000000000000000000..414d4d2fe71bf0c9db52844866937c7c6b497fe6 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000578400_148070400.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a88e497a06862dd635f65d39fe9a88992e593b3f2570247c2efa2e73d8329706 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000587648_150437888.pth b/checkpoint_p0/milestones/checkpoint_000587648_150437888.pth new file mode 100644 index 0000000000000000000000000000000000000000..42d59839ea57da13e9e7bf4d6226272e0e235d1c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000587648_150437888.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c0ec7cad45a4d870121c4549cfb8098f356f07fdd30da6ce9a0e79ac00ded60 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000596800_152780800.pth b/checkpoint_p0/milestones/checkpoint_000596800_152780800.pth new file mode 100644 index 0000000000000000000000000000000000000000..8e92d33c00485f15ee2e2ec081058dc4eaee9ccc --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000596800_152780800.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6a2ef44a3adaef181986b2b19130244c66f1e1b8fd8972b17abf4c91eea8b14 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000606016_155140096.pth b/checkpoint_p0/milestones/checkpoint_000606016_155140096.pth new file mode 100644 index 0000000000000000000000000000000000000000..05aebf88306305e6b1da5e3cb1d9e112a8cadffa --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000606016_155140096.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:458f909f52d6859b6610d555e17f0097ff8f0618c820906d0d74b81b0214f9f2 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000615264_157507584.pth b/checkpoint_p0/milestones/checkpoint_000615264_157507584.pth new file mode 100644 index 0000000000000000000000000000000000000000..706900fe1eb23c0e290294914ad0e4dcd02ab166 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000615264_157507584.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a242adc77f251c0e07e9a4671b58fd4a5e2edeec78d44d7949b38bdd63396e8b +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000624480_159866880.pth b/checkpoint_p0/milestones/checkpoint_000624480_159866880.pth new file mode 100644 index 0000000000000000000000000000000000000000..5cb63212eb014bd73ccc1d0c11258323ff0316aa --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000624480_159866880.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b7ffce17eb89f7b4034acf3c3ce0f3cd0f0339ab8be4384811160fbec6759d0 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000633728_162234368.pth b/checkpoint_p0/milestones/checkpoint_000633728_162234368.pth new file mode 100644 index 0000000000000000000000000000000000000000..4e34f940297773d274511047bf0e4675344554a8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000633728_162234368.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ef36d68b671fe86b2abb29d1fe05acd27578ab776968d3c4e13f534f8e522ba +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000643040_164618240.pth b/checkpoint_p0/milestones/checkpoint_000643040_164618240.pth new file mode 100644 index 0000000000000000000000000000000000000000..8a9b06f25306fe93b8e7f356e2d694a4af99faa2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000643040_164618240.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fef634a810d6768205f8ed2510471ffe2ea9d335eb45e1cb81a6aeb668a76747 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000653632_167329792.pth b/checkpoint_p0/milestones/checkpoint_000653632_167329792.pth new file mode 100644 index 0000000000000000000000000000000000000000..97dd862fe49c47b17c51f5b7c86b153849539dca --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000653632_167329792.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec4ca85f3313ca461d62622c44d5667c2458a9d2590d6dd54eb0684aef489dac +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000665088_170262528.pth b/checkpoint_p0/milestones/checkpoint_000665088_170262528.pth new file mode 100644 index 0000000000000000000000000000000000000000..b87686430321ea5a03e3c0e1ac24fe8e469ea853 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000665088_170262528.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea0c76eae7a179597947a41d4f8d7c73bec5c4d2932a0f97e41613954b9df3d7 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000679296_173899776.pth b/checkpoint_p0/milestones/checkpoint_000679296_173899776.pth new file mode 100644 index 0000000000000000000000000000000000000000..99e767f156e69d15ee5b5d6313b25864921e0a8c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000679296_173899776.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7820e0e22a4aef36cda986d1ef346985ccdb41a82fb3def7077ca2add4ed3c4d +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000693568_177553408.pth b/checkpoint_p0/milestones/checkpoint_000693568_177553408.pth new file mode 100644 index 0000000000000000000000000000000000000000..5dedeeb2cf675267f2f20daa8d95575365aff820 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000693568_177553408.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49ac523ae3a7ea6f199999a18de7abd84517740bb908ce97b81584aef3e780a8 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000707776_181190656.pth b/checkpoint_p0/milestones/checkpoint_000707776_181190656.pth new file mode 100644 index 0000000000000000000000000000000000000000..ef862681ccc204bfbcb3ed7c3fef7de52b6d3d29 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000707776_181190656.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25b4e19c37f344d652890ce642ad37ca5f4fe05b3dddf057a871b9b78349a2e9 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000721984_184827904.pth b/checkpoint_p0/milestones/checkpoint_000721984_184827904.pth new file mode 100644 index 0000000000000000000000000000000000000000..006b0e2b2834f0ef36e1b81bd0a7a665c1492dfc --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000721984_184827904.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f370d756a41667b6dd5575bd1c7358d6b1d9e20598078544c96c2f2159fab968 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000736160_188456960.pth b/checkpoint_p0/milestones/checkpoint_000736160_188456960.pth new file mode 100644 index 0000000000000000000000000000000000000000..b7536883ae24fbe6ef05232c3dcc02f953614ab8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000736160_188456960.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f1c35de317b158865bf1bd0a6950f6417492d25941f7fdebfe0b8f9734f31e4 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000750464_192118784.pth b/checkpoint_p0/milestones/checkpoint_000750464_192118784.pth new file mode 100644 index 0000000000000000000000000000000000000000..b46fbe3d9adad66803ac48f10d35e02fc8d3f8a7 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000750464_192118784.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8df9b4b3c40f583e12537bfc4dbfc23bf8c06829b644f292c41dcb54bf63dd14 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000764672_195756032.pth b/checkpoint_p0/milestones/checkpoint_000764672_195756032.pth new file mode 100644 index 0000000000000000000000000000000000000000..0182899714e9f2cf19e87ae5c7334e7d37bd19ff --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000764672_195756032.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:677bb12a8960f0871d3f906e056c0b49b6e037c2b6ef0654fcfd33eed567b109 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000778816_199376896.pth b/checkpoint_p0/milestones/checkpoint_000778816_199376896.pth new file mode 100644 index 0000000000000000000000000000000000000000..4d3ca48527d35e0a13143c46fb6fdb3afaca743b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000778816_199376896.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ece8a226decb1341d2322c90cf518548fbc842b285bda9a88754a6367a8ce51f +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000793024_203014144.pth b/checkpoint_p0/milestones/checkpoint_000793024_203014144.pth new file mode 100644 index 0000000000000000000000000000000000000000..55c3f6117c2160a8c39faefa35068b6c8fc61a8f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000793024_203014144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ddc34fe4725b8ed83ec23738f8a84c812decd43c5e958bc3c29784d6ac16ea9 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000807200_206643200.pth b/checkpoint_p0/milestones/checkpoint_000807200_206643200.pth new file mode 100644 index 0000000000000000000000000000000000000000..5f4ed0d437c468cd2e721ac563cd02a81afb9835 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000807200_206643200.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4542315250254433887491c2f3d124246e235b25a2ec5ae688a9cdea337563ca +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000821408_210280448.pth b/checkpoint_p0/milestones/checkpoint_000821408_210280448.pth new file mode 100644 index 0000000000000000000000000000000000000000..894a9a661a41dfcda776694f6042a434237d3909 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000821408_210280448.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6ccd1abec49e367133fae39448fc0839edf1d31ede85233d3e99856985db647 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000835584_213909504.pth b/checkpoint_p0/milestones/checkpoint_000835584_213909504.pth new file mode 100644 index 0000000000000000000000000000000000000000..2a9c9de8f7181382ca61bd879e6748da65913ea8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000835584_213909504.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ac3a0be4b19fc11eb58b853b12a1c9de7acf2540a9fdd85b76d1e698910a93b +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000849792_217546752.pth b/checkpoint_p0/milestones/checkpoint_000849792_217546752.pth new file mode 100644 index 0000000000000000000000000000000000000000..5baa05d616322fe9eda67ba250f60f7f1e0fae91 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000849792_217546752.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c006a64776d7f9869fb02c0f130d39d49ee3ee74cf64232d97819ea0eeeb03b +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000863968_221175808.pth b/checkpoint_p0/milestones/checkpoint_000863968_221175808.pth new file mode 100644 index 0000000000000000000000000000000000000000..568749282d367cec3b0fbea98f4d1dd58d4137f1 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000863968_221175808.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee474141e66340b5478f831b1505ab6d27391e7537b05ac3e45ad672ab0a9457 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000878176_224813056.pth b/checkpoint_p0/milestones/checkpoint_000878176_224813056.pth new file mode 100644 index 0000000000000000000000000000000000000000..daf450d691bc30b0cb8842d707711e8b22b0f0ca --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000878176_224813056.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8ac17a600693c27f30f9e45c1a57420ead93c4f40853b71782bdcecd588d415 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000892416_228458496.pth b/checkpoint_p0/milestones/checkpoint_000892416_228458496.pth new file mode 100644 index 0000000000000000000000000000000000000000..b4c53fb1d13dcdbc9696da58d3af306e34718759 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000892416_228458496.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7aeb1df1c69f416a3b17166759e8654507e17c5a70395505b90e00f175c9dff +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000906560_232079360.pth b/checkpoint_p0/milestones/checkpoint_000906560_232079360.pth new file mode 100644 index 0000000000000000000000000000000000000000..9da98ac8e389249a89d4f0f6aaf411c3cfa3f30b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000906560_232079360.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bffd99bb42684e0984c7b06acaac63c48e469eb6cac09162d092bb2e9b9479e +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000920832_235732992.pth b/checkpoint_p0/milestones/checkpoint_000920832_235732992.pth new file mode 100644 index 0000000000000000000000000000000000000000..6fad16b2f95b0b1792f2812b5c349a9cf06ce435 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000920832_235732992.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4858424d3d70eb464ca87968ec016df71f9fea4bfd1cdbf8eb963d67b54d275f +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000935040_239370240.pth b/checkpoint_p0/milestones/checkpoint_000935040_239370240.pth new file mode 100644 index 0000000000000000000000000000000000000000..9ec89819148942a83a1d2986702c86c9807df206 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000935040_239370240.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d20b461b9819db45df919a134b7f8cd28cfa8bb1cf4aaf0e56baee68096be8c +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000949280_243015680.pth b/checkpoint_p0/milestones/checkpoint_000949280_243015680.pth new file mode 100644 index 0000000000000000000000000000000000000000..fbd086ea4222dca826725a33027d6b99bf2bc33f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000949280_243015680.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:431f691cb1e1297ded78f3a149c17e58dbc2018f99d12da7b2a979857d18416f +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000963488_246652928.pth b/checkpoint_p0/milestones/checkpoint_000963488_246652928.pth new file mode 100644 index 0000000000000000000000000000000000000000..f2e3bf4e7f4f469ebf661b9b83fb8d6ea5490686 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000963488_246652928.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0adb51785cdc8130aad58300558a45bc3e366594bcba386ec8e7e935b7b2c49e +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000977664_250281984.pth b/checkpoint_p0/milestones/checkpoint_000977664_250281984.pth new file mode 100644 index 0000000000000000000000000000000000000000..b5ed23685a3400826957e4ca5750b2e7ac8ec959 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000977664_250281984.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3b5ec328fc49e9a2174a257fce95fadf7be01788b0c44e7cc231486c498249b +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000991840_253911040.pth b/checkpoint_p0/milestones/checkpoint_000991840_253911040.pth new file mode 100644 index 0000000000000000000000000000000000000000..0486757a5ca4e33d755b8dcfb1d4bbcdfb226fb2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000991840_253911040.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8552562c4aff44ab2df82c37caf39943b81cb332599aeee725e434977f6d730f +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001006112_257564672.pth b/checkpoint_p0/milestones/checkpoint_001006112_257564672.pth new file mode 100644 index 0000000000000000000000000000000000000000..debe4da7fa2e5c36db91dcf58558d1e23dcaa2c1 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001006112_257564672.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1e89c9481611f5f5b922c95805e7c70c3877214b58f561a00f706cebeee68b7 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001020352_261210112.pth b/checkpoint_p0/milestones/checkpoint_001020352_261210112.pth new file mode 100644 index 0000000000000000000000000000000000000000..da7f4045cdc7c534db395a7adca0cb5b08bba66c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001020352_261210112.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcdd2a38ec0826dfb6de76eedd3e6deb3b0ebe9c1c0d5d41d847ef6135a19515 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001034688_264880128.pth b/checkpoint_p0/milestones/checkpoint_001034688_264880128.pth new file mode 100644 index 0000000000000000000000000000000000000000..1100c94df70cd1e5f8bf4ffc9c9bdee4a6b4c812 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001034688_264880128.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66413caac0a6bb0d2e03e70922702eb066647d1e244b064cc6d33c324dc23472 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001048800_268492800.pth b/checkpoint_p0/milestones/checkpoint_001048800_268492800.pth new file mode 100644 index 0000000000000000000000000000000000000000..8cc9c3216dcbbedac6bd0b06f7c006c36dc95f72 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001048800_268492800.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:349b810fbdc904ac4b0fd7f8f5b177749de813261325cff185af7dafd59e20ec +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001062944_272113664.pth b/checkpoint_p0/milestones/checkpoint_001062944_272113664.pth new file mode 100644 index 0000000000000000000000000000000000000000..504e2dab36478f20914b2a006240893677f184bf --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001062944_272113664.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a9872418555bbfe68f60336ac7d04489bd217d9aabe91aacd66d335ae569798 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001077216_275767296.pth b/checkpoint_p0/milestones/checkpoint_001077216_275767296.pth new file mode 100644 index 0000000000000000000000000000000000000000..272733477c92fc245c3cbea6a272a88095c168fe --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001077216_275767296.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c091b2b1845503d8a946927dbf25c95b30baeb1605b31efd315c84166023814 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001091424_279404544.pth b/checkpoint_p0/milestones/checkpoint_001091424_279404544.pth new file mode 100644 index 0000000000000000000000000000000000000000..0f163d53b41f3d3b9923b4c6e2ec18ff97b02026 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001091424_279404544.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:495135d461d09185fae880faf1a9b8b0b195dd6aa53216787cf54ba8620a6859 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001105632_283041792.pth b/checkpoint_p0/milestones/checkpoint_001105632_283041792.pth new file mode 100644 index 0000000000000000000000000000000000000000..3821019e71edd2aac7f232d2213d3798193b2538 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001105632_283041792.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcda56f34249649cbe387f6ad6e44e5a5c37b315282570af487852d31e65e505 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001119808_286670848.pth b/checkpoint_p0/milestones/checkpoint_001119808_286670848.pth new file mode 100644 index 0000000000000000000000000000000000000000..c0123add675a4924ebaf0ee2d7b986a0125b97be --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001119808_286670848.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddace18b59301a6e70949a0c2585ce9db7de19989b5726ec2a81db0c7a90e6a9 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001133984_290299904.pth b/checkpoint_p0/milestones/checkpoint_001133984_290299904.pth new file mode 100644 index 0000000000000000000000000000000000000000..9466aa34b9431a6fdcf42cc723297290acae27eb --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001133984_290299904.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62bc66169e5107def015cda6176073fd83005dec1bd00a4d65bcdace38c7a4c2 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001148256_293953536.pth b/checkpoint_p0/milestones/checkpoint_001148256_293953536.pth new file mode 100644 index 0000000000000000000000000000000000000000..e786eb9dcd99841e4979cea48a68ed0ef7c1ba2e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001148256_293953536.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ed7e05c2148a6232cca4c26e63eb52c1909b5253c5217195ce201d98bb214d1 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001162496_297598976.pth b/checkpoint_p0/milestones/checkpoint_001162496_297598976.pth new file mode 100644 index 0000000000000000000000000000000000000000..d9e48bb138bc6e06479877573fadacecbe612e2d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001162496_297598976.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1dc1796de32e9f4aef69b1c5c1d0ec08e86ca5b401197fe426d808502d8edaf +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001176704_301236224.pth b/checkpoint_p0/milestones/checkpoint_001176704_301236224.pth new file mode 100644 index 0000000000000000000000000000000000000000..e3d5adb73f7758696414351b287072966af1e62f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001176704_301236224.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9aeff07ee2c1f2d6a1bfe0179d961bd468e9b04958fa2c25e4d6c408ade04b9 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001190944_304881664.pth b/checkpoint_p0/milestones/checkpoint_001190944_304881664.pth new file mode 100644 index 0000000000000000000000000000000000000000..95776bfebc203946bd15ff4c7b36d721942b1043 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001190944_304881664.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae747c7efa7ad1943c5c005fe450b9580c3b5dfd0bbb77c8e071d50db819746d +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001205120_308510720.pth b/checkpoint_p0/milestones/checkpoint_001205120_308510720.pth new file mode 100644 index 0000000000000000000000000000000000000000..3b06fafc28d95ad5e4b8dc1e09838e7b03c1d158 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001205120_308510720.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5de82755a49ed53fe6b639f4dd2e468cd2d4d5fbd31abe17b3ff3a130ca874dd +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001219296_312139776.pth b/checkpoint_p0/milestones/checkpoint_001219296_312139776.pth new file mode 100644 index 0000000000000000000000000000000000000000..a04c23b39efa9d03b512dcb6f959b6fbada14ae1 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001219296_312139776.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7807177a68298ffdb80fa219ba7a7cf626a18abf07997c7600f02e3116efee53 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001233568_315793408.pth b/checkpoint_p0/milestones/checkpoint_001233568_315793408.pth new file mode 100644 index 0000000000000000000000000000000000000000..3b5a16fa484e637abf0514a2d57bc6109ca6ab01 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001233568_315793408.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80c9f4c3261b4d0614b50bb15f49ba7091cd3a7f767e1b643f06b5018fc130ca +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001247744_319422464.pth b/checkpoint_p0/milestones/checkpoint_001247744_319422464.pth new file mode 100644 index 0000000000000000000000000000000000000000..7396619f729e34ffe959872bccb391750ad66cbe --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001247744_319422464.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d78b2afdf4416246b432c67aaddcb8c322399e3c003bb88ea3e8cafdfd4392bf +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001261984_323067904.pth b/checkpoint_p0/milestones/checkpoint_001261984_323067904.pth new file mode 100644 index 0000000000000000000000000000000000000000..24da8e829ee276be989aa0afcd6ad661263d8084 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001261984_323067904.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6ab57a4183d5528b60a3fa29c399c7600837a1469ed0f15637a79845cdfea98 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001276288_326729728.pth b/checkpoint_p0/milestones/checkpoint_001276288_326729728.pth new file mode 100644 index 0000000000000000000000000000000000000000..85b332000f14105f0b8452c45b8866f90fe36577 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001276288_326729728.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10f99c9aeff6e2d67fd57531c0b6c8efe0076630682494e1bf918777b28100ab +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001290560_330383360.pth b/checkpoint_p0/milestones/checkpoint_001290560_330383360.pth new file mode 100644 index 0000000000000000000000000000000000000000..ee9400df8fb814932bc90a9a9ba6a4cd1a7cb681 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001290560_330383360.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eda1fc6f49cb70eae127215e3af3bd00cef13697a70d14e94d159816a0074bef +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001304864_334045184.pth b/checkpoint_p0/milestones/checkpoint_001304864_334045184.pth new file mode 100644 index 0000000000000000000000000000000000000000..f29e700e3c5d169c1e3660effb131524443bb149 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001304864_334045184.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccd584d7fa1c9e33f3e269c76e2b5e8b8adad9e7a52625e3bdcf5d62e8a7fd06 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001319104_337690624.pth b/checkpoint_p0/milestones/checkpoint_001319104_337690624.pth new file mode 100644 index 0000000000000000000000000000000000000000..78b579c8b96abba625c45b8d58894fc6cc65f109 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001319104_337690624.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:632d250b34f7c8c35686c94f1341e489cf8bf63baa14aa99b68437a6ba8c2ae3 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001333376_341344256.pth b/checkpoint_p0/milestones/checkpoint_001333376_341344256.pth new file mode 100644 index 0000000000000000000000000000000000000000..15172fb7055bfc7087b80034bd79f7b9bdb4dd15 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001333376_341344256.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9b387678bfc02601a67d90076300bb5061d15ac3c3af35b5d00892894812a97 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001347616_344989696.pth b/checkpoint_p0/milestones/checkpoint_001347616_344989696.pth new file mode 100644 index 0000000000000000000000000000000000000000..8ee913ff90b3d372d1f609015957680644a7c65c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001347616_344989696.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e94cc320eccefd2c9edbc2e664b98a5247cb3438fa731d14b8771fa5e6fb2206 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001361888_348643328.pth b/checkpoint_p0/milestones/checkpoint_001361888_348643328.pth new file mode 100644 index 0000000000000000000000000000000000000000..e5bf67284e88203f5ce13cad5ec7afe5d71b4018 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001361888_348643328.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6692f500e1597a8f829c700dbb258c4951f4f8ab5c06603fa4e83350c34579a +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001376192_352305152.pth b/checkpoint_p0/milestones/checkpoint_001376192_352305152.pth new file mode 100644 index 0000000000000000000000000000000000000000..ad565cbb1a1a5fce98e74c9f28a10618cf441d43 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001376192_352305152.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eba97a3d2f5ab3f8a4621710af2930991f278655ae2d52961fd223c4087eb9fd +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001390496_355966976.pth b/checkpoint_p0/milestones/checkpoint_001390496_355966976.pth new file mode 100644 index 0000000000000000000000000000000000000000..8347ff047ebbb7733971c9a08f501cd75cd585f4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001390496_355966976.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c89d7ac4d495a20e9928b92821f7ff2e0ac63b33f4963444d5985457994f297 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001404768_359620608.pth b/checkpoint_p0/milestones/checkpoint_001404768_359620608.pth new file mode 100644 index 0000000000000000000000000000000000000000..418adecba7516dc4cae09fb9f846e37559b0fcc8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001404768_359620608.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d790f86f4d1d66e55d56227827b689c0e6d843c2988846d33992a02eb6d983a +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001419008_363266048.pth b/checkpoint_p0/milestones/checkpoint_001419008_363266048.pth new file mode 100644 index 0000000000000000000000000000000000000000..43692f6d6cf28e653dbdecc0a4f526f4f40cc9d5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001419008_363266048.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f454e0b7a44bdc7ffc41447f108bac68fc23c3663955eb6b9747c637120ab8b +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001433216_366903296.pth b/checkpoint_p0/milestones/checkpoint_001433216_366903296.pth new file mode 100644 index 0000000000000000000000000000000000000000..3579a617a94d9aa38ffb4c7aae79ce538c2f1d87 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001433216_366903296.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6900d584237614cb2344224ac0aa029c5f36079a2496b3420f6cd552abe902c9 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001447424_370540544.pth b/checkpoint_p0/milestones/checkpoint_001447424_370540544.pth new file mode 100644 index 0000000000000000000000000000000000000000..908c1d40b55fa247610675b5de8c94e7723d56cd --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001447424_370540544.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f57fb51abac148beb0d86177c6f7d471d974339bf53cb3b7c7cc0a370b7022cf +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001461696_374194176.pth b/checkpoint_p0/milestones/checkpoint_001461696_374194176.pth new file mode 100644 index 0000000000000000000000000000000000000000..90bf8f4ca96bab9f3757ff646308f28627503e1f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001461696_374194176.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:861e23979739281bd9b91d07a7ba7f29d48df09bb4905747f3ec0678feb5dc00 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001475904_377831424.pth b/checkpoint_p0/milestones/checkpoint_001475904_377831424.pth new file mode 100644 index 0000000000000000000000000000000000000000..7903f35dca3872b7bfe28193b235938dd9dc1c99 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001475904_377831424.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b64aa48af3d46588219578f6752518a2ef7c381f0956b0376028f83c89eb66ea +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001490048_381452288.pth b/checkpoint_p0/milestones/checkpoint_001490048_381452288.pth new file mode 100644 index 0000000000000000000000000000000000000000..e1a5e03ad0768a254a9027133e07ce613d599c80 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001490048_381452288.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afc7a75a94ffbc558f7bd4cdc10ffdaeac9e06216fd772eebd29e3d0feffdd61 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001504256_385089536.pth b/checkpoint_p0/milestones/checkpoint_001504256_385089536.pth new file mode 100644 index 0000000000000000000000000000000000000000..3dfbcf68deecb4ad21f4f6ff06a77f4d5b65b2c0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001504256_385089536.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a68da7ac906512a6b9d85a4e55ebbcda17e308d3f5815d3914d1fa88c5f0d2b3 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001518528_388743168.pth b/checkpoint_p0/milestones/checkpoint_001518528_388743168.pth new file mode 100644 index 0000000000000000000000000000000000000000..9f4c805dc6ea01acc8b81441ba0b1582cf964795 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001518528_388743168.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a09dca1d01d6af67e888edaa416455d7d8d5b2cd99cd5d1078b7f15879448c2 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001532800_392396800.pth b/checkpoint_p0/milestones/checkpoint_001532800_392396800.pth new file mode 100644 index 0000000000000000000000000000000000000000..62da657b479640605cd52c7ba6fa82d04037aeff --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001532800_392396800.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6479a9c3f7916d46d5268caf221b257e1d7f2b1f7749b6e2a2c7237e7017f1aa +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001546976_396025856.pth b/checkpoint_p0/milestones/checkpoint_001546976_396025856.pth new file mode 100644 index 0000000000000000000000000000000000000000..869d876a93db73e17c6d1aac94ae53dca85df286 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001546976_396025856.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:feb697993c4c6d75130edce128d92791e9d00d7ea2103a6193b30a29606d45ba +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001561152_399654912.pth b/checkpoint_p0/milestones/checkpoint_001561152_399654912.pth new file mode 100644 index 0000000000000000000000000000000000000000..c3ba30734877c6cf496eaddf9467505efae09f24 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001561152_399654912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:850befbb9b819c3e10863d1e9ab755b3ab571d73ffccec7b4568f5b5f5dcc140 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001575456_403316736.pth b/checkpoint_p0/milestones/checkpoint_001575456_403316736.pth new file mode 100644 index 0000000000000000000000000000000000000000..be7a224ee5cf1cf610c44374c2ad9051ed725ac4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001575456_403316736.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76cec380f0a314458ad9659a48cf2975d48929196bf50e6ff512dd65d0d39ea8 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001589792_406986752.pth b/checkpoint_p0/milestones/checkpoint_001589792_406986752.pth new file mode 100644 index 0000000000000000000000000000000000000000..3a0a3f0b0515832bcdf037a15ccb82063fc1d527 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001589792_406986752.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:346535b122453f5a789f7762a0f36cd76f81a4498c94b5aa7093d1cd4a09c074 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001604096_410648576.pth b/checkpoint_p0/milestones/checkpoint_001604096_410648576.pth new file mode 100644 index 0000000000000000000000000000000000000000..523e8d4308c2d10dc7f458410ebc13fdbf2b23bf --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001604096_410648576.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a833c0f208413c2f8918164616fdbacad419e47c73e4b835a517a9d06ceddf4 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001618336_414294016.pth b/checkpoint_p0/milestones/checkpoint_001618336_414294016.pth new file mode 100644 index 0000000000000000000000000000000000000000..5f522febc97248b9f79a9478b6ead1aaf8f6ba7e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001618336_414294016.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1de402fd8a3ae880b02eed37f1ffdfcee74c25d739954d785226a21a742abb0 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001632576_417939456.pth b/checkpoint_p0/milestones/checkpoint_001632576_417939456.pth new file mode 100644 index 0000000000000000000000000000000000000000..dfb5d98006b169ac20a5611a01fdc92042c7a5b7 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001632576_417939456.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b6c07ef4ca23b72e078f9ba355e2170eab1de0dcfddd3ff7e0e0c31fed9ea3b +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001646848_421593088.pth b/checkpoint_p0/milestones/checkpoint_001646848_421593088.pth new file mode 100644 index 0000000000000000000000000000000000000000..24ae2721fb38c36216faeb6d86af62a2df4617a1 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001646848_421593088.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bba157d32fdd3298fe5799a83552551f0da11a78a99f945821a1e1dc227868e8 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001661120_425246720.pth b/checkpoint_p0/milestones/checkpoint_001661120_425246720.pth new file mode 100644 index 0000000000000000000000000000000000000000..fa8889ffdc9b13c2c390fed70fffa69fa6dee063 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001661120_425246720.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2382484ecd07438fe1674dad2b8deb2268cc7602f92fce8ed1126232027208d3 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001675424_428908544.pth b/checkpoint_p0/milestones/checkpoint_001675424_428908544.pth new file mode 100644 index 0000000000000000000000000000000000000000..aa8197a91301c096022077576f1fa819e88a571b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001675424_428908544.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4201fbf313ef7df2492ea241949c343771b03d76d33bb0333543ba62153498f4 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001689696_432562176.pth b/checkpoint_p0/milestones/checkpoint_001689696_432562176.pth new file mode 100644 index 0000000000000000000000000000000000000000..488ea6c3db44d37aa68b3ae14f1da3930894e5d2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001689696_432562176.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40c58f58d4de1b2f842cbc554b2f43af94dd1f537f4a1e00c2db1510a5ad9c87 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001704000_436224000.pth b/checkpoint_p0/milestones/checkpoint_001704000_436224000.pth new file mode 100644 index 0000000000000000000000000000000000000000..d3af78dc831e0f373cef5d89fc708914ac7c1a63 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001704000_436224000.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b69d637b1dd3f25510bf46f3dd408a4df29f3e53dab7af7ab160780292e3c2bd +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001718336_439894016.pth b/checkpoint_p0/milestones/checkpoint_001718336_439894016.pth new file mode 100644 index 0000000000000000000000000000000000000000..cc9ad06871710a0c404e5c87966e2dff6e2befec --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001718336_439894016.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c103f8531d46f3e0e4c4986a6c0495f0a144ed50b4ca7872818e3e4e1ee00d17 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001732640_443555840.pth b/checkpoint_p0/milestones/checkpoint_001732640_443555840.pth new file mode 100644 index 0000000000000000000000000000000000000000..5a1d3db054832f4d340ccf8a277d962abafe56b0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001732640_443555840.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e230d4b6baeafa4e37dedb99bde4325b9209b910bc2b158dfac6162e45445c17 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001746848_447193088.pth b/checkpoint_p0/milestones/checkpoint_001746848_447193088.pth new file mode 100644 index 0000000000000000000000000000000000000000..deb8b6071fb2bf0b65b2fb5ed055958b71ae2a25 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001746848_447193088.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f6a55439720a92be2ee4457932ee1a8ef4e235c0949fa9973fa015dbf7bc801 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001761088_450838528.pth b/checkpoint_p0/milestones/checkpoint_001761088_450838528.pth new file mode 100644 index 0000000000000000000000000000000000000000..fcff96b3ba8b42f5928a77e41e90f89a58ac06cc --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001761088_450838528.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60997d81bf23b96f031c1a85bbc0b0fcd8a45571c28691bc9cac09c34cf1d248 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001775488_454524928.pth b/checkpoint_p0/milestones/checkpoint_001775488_454524928.pth new file mode 100644 index 0000000000000000000000000000000000000000..198eabeb5922a8c5ae9d7730c352eb904bb04dc5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001775488_454524928.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e86b6a62ea1f18cbd94d5b3fa9770a4b16d5cb3645769b49bc81248860fd900d +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001789792_458186752.pth b/checkpoint_p0/milestones/checkpoint_001789792_458186752.pth new file mode 100644 index 0000000000000000000000000000000000000000..0fc4408203b9e63f330542fc7d8876f8f0ef6fc1 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001789792_458186752.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94cd569ff69b44d58648d66d1d74cbea73d1fe8a0ad341667703532e3b46cf3e +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001804032_461832192.pth b/checkpoint_p0/milestones/checkpoint_001804032_461832192.pth new file mode 100644 index 0000000000000000000000000000000000000000..3a91a03a8396bfa66e1f803249e94ff77fc7e603 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001804032_461832192.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76ce90e80349e54287398aa0e72b4606abb124218096d2bee3ddff120459912f +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001818304_465485824.pth b/checkpoint_p0/milestones/checkpoint_001818304_465485824.pth new file mode 100644 index 0000000000000000000000000000000000000000..7d152309a98089159bdbfd8d7309391d57bc7376 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001818304_465485824.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6a60e48e580ab2421d81c70d3cb4f10e2655cc77bc458eb5a7ee948da25562b +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001832544_469131264.pth b/checkpoint_p0/milestones/checkpoint_001832544_469131264.pth new file mode 100644 index 0000000000000000000000000000000000000000..255df410767e870fa0f31a2bba6fccc30409bd55 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001832544_469131264.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2aea73a3a4db507411119d0fa6d2c5b6e9e32dab7884d7827a8288d355b2499 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001846816_472784896.pth b/checkpoint_p0/milestones/checkpoint_001846816_472784896.pth new file mode 100644 index 0000000000000000000000000000000000000000..d98dcb20a68fb16d434b0f24e36441a2ee2e8992 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001846816_472784896.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdf1d5681b767c4d8e234505cdd6221179687d76b70515d186286ea83c494fac +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001861120_476446720.pth b/checkpoint_p0/milestones/checkpoint_001861120_476446720.pth new file mode 100644 index 0000000000000000000000000000000000000000..51fbca03ba0942e03ca310cc2fa02f7e4f8c51ea --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001861120_476446720.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd6dec5b817387ad84a5b6839b499c2ca9ede0167c235c3e7121a37e5ceb33f9 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001875456_480116736.pth b/checkpoint_p0/milestones/checkpoint_001875456_480116736.pth new file mode 100644 index 0000000000000000000000000000000000000000..9b83e6588c2b8fd3d4f38aff54419d196a25735f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001875456_480116736.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f84694873866c6965303e1a67886b87fb3725f78e2371e5981d5625e1868a811 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001889664_483753984.pth b/checkpoint_p0/milestones/checkpoint_001889664_483753984.pth new file mode 100644 index 0000000000000000000000000000000000000000..f7319f4c03454b98f68b95950863865b16963d38 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001889664_483753984.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fe7f34f98c73699f20fd7eb0606eefe4e196f5bb0137a88cf9b2f227aab38c5 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001903968_487415808.pth b/checkpoint_p0/milestones/checkpoint_001903968_487415808.pth new file mode 100644 index 0000000000000000000000000000000000000000..9fd0302aa361f6326e071a95445d8210fad8a46f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001903968_487415808.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f146c351d8c469ffbbf0f235bd6d70abfad6313485636ea7da70fe907a337c2 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001918208_491061248.pth b/checkpoint_p0/milestones/checkpoint_001918208_491061248.pth new file mode 100644 index 0000000000000000000000000000000000000000..640ed86d8b653542822632a8e370b71d6a62a994 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001918208_491061248.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0693febdffcc803d18ee5e5399ea93b093e4ef05cadef6c5b0f7b55bb78eba80 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001932480_494714880.pth b/checkpoint_p0/milestones/checkpoint_001932480_494714880.pth new file mode 100644 index 0000000000000000000000000000000000000000..557020a67a667b164f5301f769f68ad2fa938a13 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001932480_494714880.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56ebf3de28ef0121573b2874e5c2aaad34c1298ba3ef34ff512face0a6f1cc4c +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001946784_498376704.pth b/checkpoint_p0/milestones/checkpoint_001946784_498376704.pth new file mode 100644 index 0000000000000000000000000000000000000000..f0fe21b324446a9655c710f518984ac7fa43ce58 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001946784_498376704.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0819e75083d2270144f419f577c90018e4fbc57841ced8fcc41344f8d1a6f62 +size 20797067 diff --git a/checkpoint_p1/best_001849888_473571328_reward_47.560.pth b/checkpoint_p1/best_001849888_473571328_reward_47.560.pth new file mode 100644 index 0000000000000000000000000000000000000000..1000048648dfc1ead7bd93c6943e46285760a62a --- /dev/null +++ b/checkpoint_p1/best_001849888_473571328_reward_47.560.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:083e10d09f119b003887e7f84141468ff72d915bfe3446efe1086d52a480e9dd +size 20795763 diff --git a/checkpoint_p1/checkpoint_001952352_499802112.pth b/checkpoint_p1/checkpoint_001952352_499802112.pth new file mode 100644 index 0000000000000000000000000000000000000000..27eee5c9bc5cfdfb7a79c33611bdb754c933ab89 --- /dev/null +++ b/checkpoint_p1/checkpoint_001952352_499802112.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5752d3b89523424b6512ee6169bc56c52115fd8bcd328e272e69bcb1d68c14e +size 20796099 diff --git a/checkpoint_p1/checkpoint_001953136_500015104.pth b/checkpoint_p1/checkpoint_001953136_500015104.pth new file mode 100644 index 0000000000000000000000000000000000000000..2413d4ddd7c29181304e44ea9fcd3cf75a116f68 --- /dev/null +++ b/checkpoint_p1/checkpoint_001953136_500015104.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91f73c5592fe4c558fdb849a286114195d7e9c6954e2e78cf9887035d9485706 +size 20796099 diff --git a/checkpoint_p1/milestones/checkpoint_000013696_3506176.pth b/checkpoint_p1/milestones/checkpoint_000013696_3506176.pth new file mode 100644 index 0000000000000000000000000000000000000000..a95489522d505c62485640e1274d84a1e4496278 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000013696_3506176.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dd78d0c850118488c75d9d3597f34b8d8ef23f3d8dbc5cf56e612d34546c9b0 +size 20796955 diff --git a/checkpoint_p1/milestones/checkpoint_000027584_7061504.pth b/checkpoint_p1/milestones/checkpoint_000027584_7061504.pth new file mode 100644 index 0000000000000000000000000000000000000000..215909ae7f289787ed6459ac5251a276a2fb697c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000027584_7061504.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39ebf7ac10dcdf6768cb701ce17717c114fa42283fa5d8cffa33a44dac2f3899 +size 20796955 diff --git a/checkpoint_p1/milestones/checkpoint_000041568_10641408.pth b/checkpoint_p1/milestones/checkpoint_000041568_10641408.pth new file mode 100644 index 0000000000000000000000000000000000000000..69c0313f4e112eee69de075ea54c794a865f2e62 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000041568_10641408.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79b1a1a8473ae03fade4402a8a26efe0aa12fa490716d00289f2702d30a11bcd +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000055520_14213120.pth b/checkpoint_p1/milestones/checkpoint_000055520_14213120.pth new file mode 100644 index 0000000000000000000000000000000000000000..60aafb63406f556c93e65b0e2681d4cdeaf08153 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000055520_14213120.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ea8093ac7d6e22005bb90dea1fadf8280d71852237a4e26dcb2e98b59e44416 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000069408_17768448.pth b/checkpoint_p1/milestones/checkpoint_000069408_17768448.pth new file mode 100644 index 0000000000000000000000000000000000000000..9a11d3b0332402278408556f1b6240acab3f25dd --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000069408_17768448.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e17b260b0573780f5119f190f1d2e7a006eb770167f4828ba0f8f4ed869cbb04 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000083456_21364736.pth b/checkpoint_p1/milestones/checkpoint_000083456_21364736.pth new file mode 100644 index 0000000000000000000000000000000000000000..92a7c36f1e27c2504a295dab7fce24fe7b87f935 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000083456_21364736.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcc8ee24ed153c0ba8ac36d4dc326f90d004ee854e6d81ef42211dec9eb86943 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000097504_24961024.pth b/checkpoint_p1/milestones/checkpoint_000097504_24961024.pth new file mode 100644 index 0000000000000000000000000000000000000000..2e6e8949014933fe2051007622469089ed1b9b7b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000097504_24961024.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23ccc5b6b499f13f844fe8562e02a69c64e69a0792c913731b33fac8e0d82c8c +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000111648_28581888.pth b/checkpoint_p1/milestones/checkpoint_000111648_28581888.pth new file mode 100644 index 0000000000000000000000000000000000000000..49c0850ceb6911b79b4cf4358500ff7e76f17070 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000111648_28581888.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70cfeb67a041fd0d31a2af18bf02f50f21e3bbca446c02405d446c8250c67ffe +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000124512_31875072.pth b/checkpoint_p1/milestones/checkpoint_000124512_31875072.pth new file mode 100644 index 0000000000000000000000000000000000000000..1c0303a4f588169ac2736e9a4b6a9267f7566cb3 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000124512_31875072.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34c24565688d696d999ce71f98a2b71d77acda7db2a4efc231a349928078f675 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000138624_35487744.pth b/checkpoint_p1/milestones/checkpoint_000138624_35487744.pth new file mode 100644 index 0000000000000000000000000000000000000000..a088e39aa6f1de8eaf7a077fb74e7ccb463355fd --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000138624_35487744.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ae0c23f757c5dad5fa8f9f9dcd0d7b121fe71b18f8e14148d9347b4e0b51b05 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000152704_39092224.pth b/checkpoint_p1/milestones/checkpoint_000152704_39092224.pth new file mode 100644 index 0000000000000000000000000000000000000000..81d459032c2e9a02a4df0e525735d18c4e1d069b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000152704_39092224.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f13fb6fdfbebe1fece87164b7e57988321396a25dd0935e2487e0753c4dbea6f +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000166784_42696704.pth b/checkpoint_p1/milestones/checkpoint_000166784_42696704.pth new file mode 100644 index 0000000000000000000000000000000000000000..e4d6c49648e623dbf2134c1fd4b8fad608b115f5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000166784_42696704.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:681a35534ee298d4d666fd2b44e7c734629131ca72668e93deb644ee2a23ce37 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000180928_46317568.pth b/checkpoint_p1/milestones/checkpoint_000180928_46317568.pth new file mode 100644 index 0000000000000000000000000000000000000000..3d409a49c64bc835e9e0ea5098cc7bb8f2d03de2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000180928_46317568.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b3821692f8d5c3138dc2b03a8bd04dca57c999e6531d4b63c98cfbc2e054ea7 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000195040_49930240.pth b/checkpoint_p1/milestones/checkpoint_000195040_49930240.pth new file mode 100644 index 0000000000000000000000000000000000000000..6f184346dad2a38aeea7a91c57438f4f7afcc567 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000195040_49930240.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fab668f43b7b2b8b40c77d830eaf72d92d39efefaf7134a9fd2b927fe0af1f5 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000208992_53501952.pth b/checkpoint_p1/milestones/checkpoint_000208992_53501952.pth new file mode 100644 index 0000000000000000000000000000000000000000..b0ee0907a82f6cb198d5a85db0c70d9d308128e1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000208992_53501952.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10539a8521c0579c106a7457ea1a6b15da86e58cd2af2cefc39205e3c4622906 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000223136_57122816.pth b/checkpoint_p1/milestones/checkpoint_000223136_57122816.pth new file mode 100644 index 0000000000000000000000000000000000000000..7a9190ce4849125acf7a5116bda75b737819d090 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000223136_57122816.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2122a7582fcc68988a33b49c2d096128bc652d95a17666eafc4738d42c648a9c +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000237216_60727296.pth b/checkpoint_p1/milestones/checkpoint_000237216_60727296.pth new file mode 100644 index 0000000000000000000000000000000000000000..a118d1894e5ebf358e1d61b7be6c85103e420428 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000237216_60727296.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e6bcad42f621e5cd17373e4c4f443c319fd9d7efb4d23cc6dbc587f2ee911c1 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000251232_64315392.pth b/checkpoint_p1/milestones/checkpoint_000251232_64315392.pth new file mode 100644 index 0000000000000000000000000000000000000000..50eae64cb4c74fc6705c91481f14a48b27e1459d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000251232_64315392.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ce05d42ea05a37df1758f94fbbaa9af79dc5da23c2665c6e985b7dc86d2a596 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000265312_67919872.pth b/checkpoint_p1/milestones/checkpoint_000265312_67919872.pth new file mode 100644 index 0000000000000000000000000000000000000000..8b6c818708c3f17a8214a5433622126baeb6c033 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000265312_67919872.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:354bd72043db7b67090ca5123b5a7051b0c38c5fc26204fb8197b4c77f7d7785 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000279392_71524352.pth b/checkpoint_p1/milestones/checkpoint_000279392_71524352.pth new file mode 100644 index 0000000000000000000000000000000000000000..2bfe8192c88349e7fff0974af43b1a2c1f52f088 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000279392_71524352.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b524350065eab241d2e25ca841f984fe0af2c65348f0de58df4507a187f25f07 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000293472_75128832.pth b/checkpoint_p1/milestones/checkpoint_000293472_75128832.pth new file mode 100644 index 0000000000000000000000000000000000000000..b5dc3e912b16a073e28faa97ea1ed230f90e4111 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000293472_75128832.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9950aaeb1170149f025583e16ea13871e28b7a16c61ae393e9b3d3e7ae0f530 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000307680_78766080.pth b/checkpoint_p1/milestones/checkpoint_000307680_78766080.pth new file mode 100644 index 0000000000000000000000000000000000000000..b9b42e5e83466412df36e2c57be7b3d6fdf496c6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000307680_78766080.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca17857317a2b77c46391077976370d2a86327d85ca3ae7ede749e97b22580e7 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000321696_82354176.pth b/checkpoint_p1/milestones/checkpoint_000321696_82354176.pth new file mode 100644 index 0000000000000000000000000000000000000000..3c2bc0d2d8e31026651263a3aa21455f707dc97a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000321696_82354176.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a44b3df46b2710746f22dbea4abd325326fb330841e3e095d86f34d98cda09c +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000335808_85966848.pth b/checkpoint_p1/milestones/checkpoint_000335808_85966848.pth new file mode 100644 index 0000000000000000000000000000000000000000..9e87046ed1f50307e483b8582237cb0c14166af1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000335808_85966848.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b3725b399a038d38332c41ccd43a9d4210cd93084995a5840e906a89b40098d +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000349824_89554944.pth b/checkpoint_p1/milestones/checkpoint_000349824_89554944.pth new file mode 100644 index 0000000000000000000000000000000000000000..eac0a24dd4e21c1b7040475b0145389e7fa3bae1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000349824_89554944.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48e20377a2a818005d041a8112d1eaa39a1befa8df1a2b4e3d6e080fc1a2ea36 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000362400_92774400.pth b/checkpoint_p1/milestones/checkpoint_000362400_92774400.pth new file mode 100644 index 0000000000000000000000000000000000000000..d99bdd1825af87fb9cae58c7f36bcb61a17389ce --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000362400_92774400.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15231f5b29340f56809ea27863e7a7c2b98eaa2b685acfe8f7047531bfa6bb29 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000371520_95109120.pth b/checkpoint_p1/milestones/checkpoint_000371520_95109120.pth new file mode 100644 index 0000000000000000000000000000000000000000..7c0ebac3dd8b6df520180f0938827661839d523e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000371520_95109120.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f71a2cb720982a27f5454872f680ed6d8a8b5e47bf7387da41ff0050d93b8ce +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000380704_97460224.pth b/checkpoint_p1/milestones/checkpoint_000380704_97460224.pth new file mode 100644 index 0000000000000000000000000000000000000000..6759ff0994ddf9d0788301720ac4f35e4860f748 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000380704_97460224.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f1375dbb79d370b2a12b9d44343c9e8dd647bbb6c989d710924822c581cdc2c +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000389920_99819520.pth b/checkpoint_p1/milestones/checkpoint_000389920_99819520.pth new file mode 100644 index 0000000000000000000000000000000000000000..cb4781641a42f398073f79115667d8ce3bedea51 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000389920_99819520.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98ba29e676e778eb2700a817d6872372a1fcaf9c04e67cdea64af1561dd4e610 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000399104_102170624.pth b/checkpoint_p1/milestones/checkpoint_000399104_102170624.pth new file mode 100644 index 0000000000000000000000000000000000000000..4effde3581ea4957814d6acbaad89449786dbf75 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000399104_102170624.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bf18f039b68193bfd41540aa401675530ee546b02a1649e31ea2ff4eb29c91c +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000408320_104529920.pth b/checkpoint_p1/milestones/checkpoint_000408320_104529920.pth new file mode 100644 index 0000000000000000000000000000000000000000..d2aad44c1530fc467e5af45f4d41cbb8df97652a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000408320_104529920.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d7d6419e3902f672c7a3aeb87fc283e6c40912465eb3cadc3edd961e4b2c753 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000417536_106889216.pth b/checkpoint_p1/milestones/checkpoint_000417536_106889216.pth new file mode 100644 index 0000000000000000000000000000000000000000..5bea90a1c071900468960c8b7c5f1e292fc66fb9 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000417536_106889216.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae92390c83b558bf3821f1189f7298f05bf355ff10713196d6b59486b0f1516f +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000426752_109248512.pth b/checkpoint_p1/milestones/checkpoint_000426752_109248512.pth new file mode 100644 index 0000000000000000000000000000000000000000..c52e835131697a9d3d2c4f1d506fbbcae9f70b85 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000426752_109248512.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:061d6b3ce2ff837a502e8978194ff324b07c8158271552b46e3509e5868561f9 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000435936_111599616.pth b/checkpoint_p1/milestones/checkpoint_000435936_111599616.pth new file mode 100644 index 0000000000000000000000000000000000000000..6126f69cab0d38b0fd989b71e63ab0c0fa638d2e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000435936_111599616.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5fa8780a1d6a894296494b958e1a2906270a3d7340aab55f0434ce8e07b1c7c +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000445152_113958912.pth b/checkpoint_p1/milestones/checkpoint_000445152_113958912.pth new file mode 100644 index 0000000000000000000000000000000000000000..1c4902f07cbb18ae20373a0bca5dcf89fd340d3b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000445152_113958912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e19a9eb120d3b05bc0b128fac200492d48a73e0c965b7eb78ac2225053fbd334 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000455296_116555776.pth b/checkpoint_p1/milestones/checkpoint_000455296_116555776.pth new file mode 100644 index 0000000000000000000000000000000000000000..e8dd4d3f687d350ddbfe5ff378d7fca071638bd7 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000455296_116555776.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fee279d095669c9e9311b9fa213bb229c2e923d1ea208abb7182720fd4adf015 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000464640_118947840.pth b/checkpoint_p1/milestones/checkpoint_000464640_118947840.pth new file mode 100644 index 0000000000000000000000000000000000000000..cb0ee2df0b6d149ab9035fb771b0cb4cd6fec3bf --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000464640_118947840.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2cfc314e84dcde10ef32aaa257dc24adbad2ed2e76cbb9b718b7619f9932a48 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000473856_121307136.pth b/checkpoint_p1/milestones/checkpoint_000473856_121307136.pth new file mode 100644 index 0000000000000000000000000000000000000000..32f8da77f926326e8346a3fde9f2231b2292f996 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000473856_121307136.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe27520a1482933f32785bfdc65c05f5184cd5d2f06cdcb77d3cda6e67d65fa7 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000483072_123666432.pth b/checkpoint_p1/milestones/checkpoint_000483072_123666432.pth new file mode 100644 index 0000000000000000000000000000000000000000..b1194cc142588d793f4f806bbf24148ed9a318a6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000483072_123666432.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:381ea1c379b20c2b051df10f0ecc76ddc56d22e3b69b504a9523d10c46376257 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000492288_126025728.pth b/checkpoint_p1/milestones/checkpoint_000492288_126025728.pth new file mode 100644 index 0000000000000000000000000000000000000000..9df4239b696ba3a156c2f6a194a8a417addd6424 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000492288_126025728.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c87d43f683536b5921f6b9f3f7216b52516c2ff53e405277c41248cf6a8862c3 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000501504_128385024.pth b/checkpoint_p1/milestones/checkpoint_000501504_128385024.pth new file mode 100644 index 0000000000000000000000000000000000000000..08bdf7c9165e06cc8c58458fa7d45e91066511f1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000501504_128385024.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ffb984e39e0611d0e5ab0c111d6982e9b97ba69928e0fec14b04a3ecfbc9927 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000510688_130736128.pth b/checkpoint_p1/milestones/checkpoint_000510688_130736128.pth new file mode 100644 index 0000000000000000000000000000000000000000..0108163feb09796ca531ea497b85f2d1a099697f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000510688_130736128.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd04067b518fe625ad6332534042c564d22ed47af6989767c4bcc969cdc6fd8b +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000519904_133095424.pth b/checkpoint_p1/milestones/checkpoint_000519904_133095424.pth new file mode 100644 index 0000000000000000000000000000000000000000..b0c5845d5a6bc042ec3928721862c637ed7d9231 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000519904_133095424.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3626053902423fb1bb677c76f040329146e86dd3407d503033436ff8097bcae9 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000529120_135454720.pth b/checkpoint_p1/milestones/checkpoint_000529120_135454720.pth new file mode 100644 index 0000000000000000000000000000000000000000..88dfa958a2ceaec9a1f618136d30a491baec90d2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000529120_135454720.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:049374cf51f2114e3f37924aa449c179f19c26fd49545edc3d121dabb282e314 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000538336_137814016.pth b/checkpoint_p1/milestones/checkpoint_000538336_137814016.pth new file mode 100644 index 0000000000000000000000000000000000000000..10e9a9be228dc9db81f91a6e3f16d6d1ae81126f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000538336_137814016.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:132634a308f8b46f466ee00d1d800a8d80cec0382cb9db8cb7b495844d65604e +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000548032_140296192.pth b/checkpoint_p1/milestones/checkpoint_000548032_140296192.pth new file mode 100644 index 0000000000000000000000000000000000000000..61ae5a927bc644187bdc8d8f5da12f9a7073d293 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000548032_140296192.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03dc550b50e1c14c2d6547d290996d6434a2dbfb5c5ac84f6e764777e4e8944b +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000557856_142811136.pth b/checkpoint_p1/milestones/checkpoint_000557856_142811136.pth new file mode 100644 index 0000000000000000000000000000000000000000..62daf1a5de9886001e42c67edabcbbefb2e8d594 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000557856_142811136.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d4cc55e9214c18801cc6029776dcbbfc3cbb4da3713fae808165b3687318e57 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000567104_145178624.pth b/checkpoint_p1/milestones/checkpoint_000567104_145178624.pth new file mode 100644 index 0000000000000000000000000000000000000000..8b47d7ceae29f1dc7a9520fa3d172e566aadb5f8 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000567104_145178624.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3deacd60d49a852a7884229c7e373a0883cfd1b27c869c2dda9d59a7013442b7 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000576320_147537920.pth b/checkpoint_p1/milestones/checkpoint_000576320_147537920.pth new file mode 100644 index 0000000000000000000000000000000000000000..ec9da7ffb093defb3d6529e20c2f2320327fc916 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000576320_147537920.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b58c34f4bbccbca27cc48d70cf000e9db5da9f82395c295a2841d8738a2be0f0 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000585536_149897216.pth b/checkpoint_p1/milestones/checkpoint_000585536_149897216.pth new file mode 100644 index 0000000000000000000000000000000000000000..e34347cb4e1a3c813bf37cdfdab46b105b5bda8d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000585536_149897216.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a4c5b96f2d8a0af3c39b4bba90c0048a65113dc4b6df710da6fc25aad1eaa7e +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000594656_152231936.pth b/checkpoint_p1/milestones/checkpoint_000594656_152231936.pth new file mode 100644 index 0000000000000000000000000000000000000000..b277001b8b3ce49f5c1e4076a5893d799fd5a06a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000594656_152231936.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e49dd2b537f1ca108ee7ddedc77ead2c2ae0d835058da63d7ee8613c2301b0a +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000603872_154591232.pth b/checkpoint_p1/milestones/checkpoint_000603872_154591232.pth new file mode 100644 index 0000000000000000000000000000000000000000..1944064e75a24c996bd7455db6079738359c7d6f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000603872_154591232.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71c66971b0de7ffb8e20002e5015f4a4665c3208102c6ba9d3f0acb45359b451 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000613088_156950528.pth b/checkpoint_p1/milestones/checkpoint_000613088_156950528.pth new file mode 100644 index 0000000000000000000000000000000000000000..78cacb0f37731133b3df3574acdf3a5ce75bd6e5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000613088_156950528.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9208fef3b08cc25ee4e0907ad638e4262365a34a64e26f11353d6df684101fa2 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000622304_159309824.pth b/checkpoint_p1/milestones/checkpoint_000622304_159309824.pth new file mode 100644 index 0000000000000000000000000000000000000000..6c78b2cbd88f7337a34c69a9193909cd7f1659ba --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000622304_159309824.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16894b6ca55ac969888a69952d1b5ebda8c471a0a9623b1073fb6a083196f2a6 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000631520_161669120.pth b/checkpoint_p1/milestones/checkpoint_000631520_161669120.pth new file mode 100644 index 0000000000000000000000000000000000000000..2220370d5a1c3d53fbf5a0d090c148f7073d0237 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000631520_161669120.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d004b0ccf8d28edfc02a0b571b2066e380ca8c1b1befd733e47628220a67139 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000640832_164052992.pth b/checkpoint_p1/milestones/checkpoint_000640832_164052992.pth new file mode 100644 index 0000000000000000000000000000000000000000..a06018eacf8a1609657d29a07f9805a3a7f42096 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000640832_164052992.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:345251a025067b1276880c84178fe24ad6f4227a4515a2398f17e0daac31216e +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000651424_166764544.pth b/checkpoint_p1/milestones/checkpoint_000651424_166764544.pth new file mode 100644 index 0000000000000000000000000000000000000000..73ad6b2b9ea808af85940e483b8c5fbf0950050e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000651424_166764544.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cca8971973a748ad87e5d22f0266d8b30b22782eb1c2d5e41b7e5c9f5875a32d +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000662848_169689088.pth b/checkpoint_p1/milestones/checkpoint_000662848_169689088.pth new file mode 100644 index 0000000000000000000000000000000000000000..f4c2db4dd091031840673ac835128656979aa54a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000662848_169689088.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23467cb7e1d3f1431120aa6dcc33681cb0d160cd447f2bd6858d28bd1cf41a84 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000677024_173318144.pth b/checkpoint_p1/milestones/checkpoint_000677024_173318144.pth new file mode 100644 index 0000000000000000000000000000000000000000..db1ae8eb1c3a818832b10bc90fc0667e0f6c7842 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000677024_173318144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1eee0af8aa82bf035e23a99bad94fb270c77d7bfed86354dd3f30d9b598e8829 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000691136_176930816.pth b/checkpoint_p1/milestones/checkpoint_000691136_176930816.pth new file mode 100644 index 0000000000000000000000000000000000000000..4461e60c35d0b5b14a24c924e55039597235738c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000691136_176930816.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9898beb46c3ab861434de453e056a90549ed88a71f8b702fb243d29707fdbf8e +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000705376_180576256.pth b/checkpoint_p1/milestones/checkpoint_000705376_180576256.pth new file mode 100644 index 0000000000000000000000000000000000000000..ae6146a89fc8d63613f24fbb1d26d225fa6a7190 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000705376_180576256.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ded8db7828272e11e66ace385c579418ad88241e6eed9ef929118ac951f726c2 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000719488_184188928.pth b/checkpoint_p1/milestones/checkpoint_000719488_184188928.pth new file mode 100644 index 0000000000000000000000000000000000000000..311120c50dd2d56dc6082fbeffdba40eb9b1749e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000719488_184188928.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7d0c5bd481fb7f6f2e6bc53cacf357a931750dd0e4ae6d9c580fc41a1a4d6f8 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000733728_187834368.pth b/checkpoint_p1/milestones/checkpoint_000733728_187834368.pth new file mode 100644 index 0000000000000000000000000000000000000000..3a54d4030b997c246b815b676b6b95a0e8c195fc --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000733728_187834368.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abb71fb95402835b2895952b5ee5fec1dcdf64702969d384d2fe4e99a93867e8 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000747872_191455232.pth b/checkpoint_p1/milestones/checkpoint_000747872_191455232.pth new file mode 100644 index 0000000000000000000000000000000000000000..4504b6df6837dd5d9f77170afb638d41188d8faf --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000747872_191455232.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7645a818a714aed511cb9fbd9a2691b1ac9dcce6c58b3834cb7d8cf53444875b +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000761984_195067904.pth b/checkpoint_p1/milestones/checkpoint_000761984_195067904.pth new file mode 100644 index 0000000000000000000000000000000000000000..5d297331da9b328940facb43ed76a5a924c416f3 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000761984_195067904.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40c0fd21127616df9cd168a3afcc51f171ec037cd7946c386fad2d08bb1d617e +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000776224_198713344.pth b/checkpoint_p1/milestones/checkpoint_000776224_198713344.pth new file mode 100644 index 0000000000000000000000000000000000000000..329dc233b9e074486e08b5c409303ee56363cdcc --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000776224_198713344.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f1916309103c4a13a6e64ef502faa0b640aa2c8584a8a3bdf4815776d933b6d +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000790368_202334208.pth b/checkpoint_p1/milestones/checkpoint_000790368_202334208.pth new file mode 100644 index 0000000000000000000000000000000000000000..7e32338f4285be29fad4b252c003f90014f1ade9 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000790368_202334208.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cb05b3d379c069fc414d017692693a367e78fd8cab52ba57458a5e71d72716e +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000804608_205979648.pth b/checkpoint_p1/milestones/checkpoint_000804608_205979648.pth new file mode 100644 index 0000000000000000000000000000000000000000..d66d4e817b6b5961290673ad5354ffb3bc4b76d7 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000804608_205979648.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01e045db11170812b7e39d303f67ead9d9615bfcc84e0d6d5209700febfd0efb +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000818816_209616896.pth b/checkpoint_p1/milestones/checkpoint_000818816_209616896.pth new file mode 100644 index 0000000000000000000000000000000000000000..969d58ccf91153900faa54e55429951f5fbc2e3d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000818816_209616896.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3165545a60a2c38752c37b25487c0319b5d9a6ef1691e16f794890cf7c2d4f75 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000832992_213245952.pth b/checkpoint_p1/milestones/checkpoint_000832992_213245952.pth new file mode 100644 index 0000000000000000000000000000000000000000..6d3cfd6ff689d35a15e2843ae06e0342419da644 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000832992_213245952.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adf804b8212526e8fdd819f84167757f13f0b51b74ae92bf200023b29f6b2f3b +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000847264_216899584.pth b/checkpoint_p1/milestones/checkpoint_000847264_216899584.pth new file mode 100644 index 0000000000000000000000000000000000000000..a7a0d875dda037b896e03bc5f86c29588682431e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000847264_216899584.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04ad34e99f1c23b1a105c9f288c7ddd53db73c54a174b93794bbbcea5e9f2a6c +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000861472_220536832.pth b/checkpoint_p1/milestones/checkpoint_000861472_220536832.pth new file mode 100644 index 0000000000000000000000000000000000000000..076c39537d5fdc18d04abcdcbd6aaf767bef64ef --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000861472_220536832.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd1420f60d1c2dd91b1b658882252740062b087ea57dee3c8a9b50bf36a3c5af +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000875648_224165888.pth b/checkpoint_p1/milestones/checkpoint_000875648_224165888.pth new file mode 100644 index 0000000000000000000000000000000000000000..82c8a5ded86188ab1da02b91169a2959b7c9cc77 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000875648_224165888.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90dc9bf9b1376430c8d02082bd4bd089f5927c95fdeae9f2b881c6943671b004 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000889856_227803136.pth b/checkpoint_p1/milestones/checkpoint_000889856_227803136.pth new file mode 100644 index 0000000000000000000000000000000000000000..e3b36febd00fa04942f0a0c37fb6b76187f72c1b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000889856_227803136.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ca4a461b3e3f92d8b4df179a31cd4a84ac472419b4a152f89e3498b43c9a27a +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000904000_231424000.pth b/checkpoint_p1/milestones/checkpoint_000904000_231424000.pth new file mode 100644 index 0000000000000000000000000000000000000000..c5540bc10120446bc86e857069d21756361eec78 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000904000_231424000.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e61bb13553c0758018a40f160408035a18b20aac26f8429f2d9bd5e26c1f0e5d +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000918240_235069440.pth b/checkpoint_p1/milestones/checkpoint_000918240_235069440.pth new file mode 100644 index 0000000000000000000000000000000000000000..b63149439f1ce24f847d967d8c768e7fc98d4502 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000918240_235069440.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d35a7deb04ad45f20f7e6c6169a3213f72d0bdf8320ab5a7e0b43e25e3222ccb +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000932448_238706688.pth b/checkpoint_p1/milestones/checkpoint_000932448_238706688.pth new file mode 100644 index 0000000000000000000000000000000000000000..bac32662896e958cec02f98f4b3b551d798e3f1a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000932448_238706688.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1efa1262b686eb067887a1e989c0982e1fa8165d45a21d25ca02eccfb6218499 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000946720_242360320.pth b/checkpoint_p1/milestones/checkpoint_000946720_242360320.pth new file mode 100644 index 0000000000000000000000000000000000000000..012ecb38bfe080deefe89ba9eca99dc5bbae7725 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000946720_242360320.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:255e22375c89ad9617130efaf13dfd2c569653d82f49047b27bbaee2f7171a68 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000960992_246013952.pth b/checkpoint_p1/milestones/checkpoint_000960992_246013952.pth new file mode 100644 index 0000000000000000000000000000000000000000..5df108c7f1aae93ba02d824d06d0e6079d4611a4 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000960992_246013952.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a24549b206bb8abf3e8fd99dd8770e704db5bf49861f28c29fe22fd287a6a76 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000975232_249659392.pth b/checkpoint_p1/milestones/checkpoint_000975232_249659392.pth new file mode 100644 index 0000000000000000000000000000000000000000..ec448d7b0f4d47a46320f08e67f5d71dfb3275d9 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000975232_249659392.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9532110962207bede1515c1a45cb86b3e48f32770ca6f4e8e9f3b4a8ccd510a0 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000989440_253296640.pth b/checkpoint_p1/milestones/checkpoint_000989440_253296640.pth new file mode 100644 index 0000000000000000000000000000000000000000..0e7962a8c8e054818ed178ac479501124427d816 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000989440_253296640.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:757350b67697f2708b95fba8dd33ac015cbf08b8bb13a6555c96dda1e61910f6 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001003648_256933888.pth b/checkpoint_p1/milestones/checkpoint_001003648_256933888.pth new file mode 100644 index 0000000000000000000000000000000000000000..cb8d917696c23309fb4daddf00601bee7d3cf1bd --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001003648_256933888.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dec3db2497064d89e95bc3ca9ff6a65fd90502d44baafc7d7762f2a08da1b37 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001017856_260571136.pth b/checkpoint_p1/milestones/checkpoint_001017856_260571136.pth new file mode 100644 index 0000000000000000000000000000000000000000..48db886be2ce9160a51ecbea73efb36d6d7ccf58 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001017856_260571136.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e5f9e7cb396b985bf98d91a75aeae3fce4a6cc802ae3da1e01737833094c09a +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001032096_264216576.pth b/checkpoint_p1/milestones/checkpoint_001032096_264216576.pth new file mode 100644 index 0000000000000000000000000000000000000000..28e391ec8deac13edaf09e67ef1edc6b66d6ddcc --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001032096_264216576.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e996b5fbd29172219c5659845f9c5b4f0ccc234326d19eb57b39a69a4ce2daf4 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001046272_267845632.pth b/checkpoint_p1/milestones/checkpoint_001046272_267845632.pth new file mode 100644 index 0000000000000000000000000000000000000000..532a580ad63811b7f4c52e1264743f8eb192f8a2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001046272_267845632.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2eab462ec601f39a194785ae56347a5700c237d1dc1e7df29ac278c3dab2e74e +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001060544_271499264.pth b/checkpoint_p1/milestones/checkpoint_001060544_271499264.pth new file mode 100644 index 0000000000000000000000000000000000000000..7a990e3491121871183bf3d6fff5fe2711035b55 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001060544_271499264.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05ded4291a0e2ec82c4b99d4d8ebafe6cbe170e483ccc8ec775d5a11c0723e4d +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001074784_275144704.pth b/checkpoint_p1/milestones/checkpoint_001074784_275144704.pth new file mode 100644 index 0000000000000000000000000000000000000000..da59150754abadf15ef1c13544ab2681ae39b74f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001074784_275144704.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea986cb7e8b51d701f83bd5164e186827e413adc59f132c5021e748c79c1ef2c +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001089056_278798336.pth b/checkpoint_p1/milestones/checkpoint_001089056_278798336.pth new file mode 100644 index 0000000000000000000000000000000000000000..676d52a2a7e19dac8699b045bcd9ccad2bb12010 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001089056_278798336.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9aff1f4720e953b6887a8a4fe133acf7c522d563419863146a7d531281c1fc1e +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001103232_282427392.pth b/checkpoint_p1/milestones/checkpoint_001103232_282427392.pth new file mode 100644 index 0000000000000000000000000000000000000000..27c11d118a691a8397e21afe879e39199cc7b7b4 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001103232_282427392.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4d3db54b256157741877a4d8fb9c222faeafdc4303bf1a5d110cbea3611581d +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001117568_286097408.pth b/checkpoint_p1/milestones/checkpoint_001117568_286097408.pth new file mode 100644 index 0000000000000000000000000000000000000000..68273b751dca0c2796df2d5857d30c6fd99334a3 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001117568_286097408.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7acc88bdaf5f895867b7601cfd40716e97222179fb8878a6f948e82b51c68c4 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001131808_289742848.pth b/checkpoint_p1/milestones/checkpoint_001131808_289742848.pth new file mode 100644 index 0000000000000000000000000000000000000000..cf6529f1bf5a2225ae59efb28495902e54312edc --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001131808_289742848.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59eca1ff1262b5ed1d4b56a86e9533c59fe56112cb90c24d674858069e1a4a0b +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001145984_293371904.pth b/checkpoint_p1/milestones/checkpoint_001145984_293371904.pth new file mode 100644 index 0000000000000000000000000000000000000000..3e7c814a5c0806bb3d9df61425ec70bae8c0c65a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001145984_293371904.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb091acd42bee68e9986b97b233f1280d0d9ce7768f9986c6584f9dc815880ed +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001160160_297000960.pth b/checkpoint_p1/milestones/checkpoint_001160160_297000960.pth new file mode 100644 index 0000000000000000000000000000000000000000..59d2c18db0ca14b7fdf6eb36364a47f86deb82bc --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001160160_297000960.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:490cbcab96da3b5827320e65f5ba4113b461a3e5f63c235f14aa73911f4dab75 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001174432_300654592.pth b/checkpoint_p1/milestones/checkpoint_001174432_300654592.pth new file mode 100644 index 0000000000000000000000000000000000000000..9cae76154a61386a978934c29c029a086d6a177d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001174432_300654592.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:373f812bc37ae458352c74452a5fb09593062bb031dc896124c56d234213e000 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001188704_304308224.pth b/checkpoint_p1/milestones/checkpoint_001188704_304308224.pth new file mode 100644 index 0000000000000000000000000000000000000000..f2bdf0746292dd6fc3280698046bd445a95617f7 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001188704_304308224.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5f4f1b9e1c23c84082d8200e46b171aa3ae2bc3629aaa1f6a0bbeb5c2a8a2f7 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001202944_307953664.pth b/checkpoint_p1/milestones/checkpoint_001202944_307953664.pth new file mode 100644 index 0000000000000000000000000000000000000000..595bc86142ac7a66c7717f2b4c734bceb1d7cdd2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001202944_307953664.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf98097c5b2376081cda75ad89f87aa24f3a7df21358fc3c4bed1e467e3c06cb +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001217184_311599104.pth b/checkpoint_p1/milestones/checkpoint_001217184_311599104.pth new file mode 100644 index 0000000000000000000000000000000000000000..7a7dad7d089668e21d0f43f72b0031a86887d5df --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001217184_311599104.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:601295555e26a49f64c6dd9ac63e06a3ff76f3a4085b8827940a4d5044539c3e +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001231520_315269120.pth b/checkpoint_p1/milestones/checkpoint_001231520_315269120.pth new file mode 100644 index 0000000000000000000000000000000000000000..637228e3c83f1afdeb1235dcfadf09e3a2e15c5f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001231520_315269120.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac7643e562f1fffa65cf3e81cdaf3204e983e16d6bb679bf4eefea97151dbd14 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001245760_318914560.pth b/checkpoint_p1/milestones/checkpoint_001245760_318914560.pth new file mode 100644 index 0000000000000000000000000000000000000000..631ae7d5a6bcd9a54a718dd4964e0b95f1d476da --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001245760_318914560.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:933a68ef7ee0f357a3618fe8870968ae618e6ccd538c48fa8abdd1f573694459 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001260064_322576384.pth b/checkpoint_p1/milestones/checkpoint_001260064_322576384.pth new file mode 100644 index 0000000000000000000000000000000000000000..88af695c6da62751da57a6843f83bf7fcd2b8fe8 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001260064_322576384.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7667cdc7a58983ec4540fde63f64c59a66bc9ed3f635624dcdaa04aa466edcd9 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001274400_326246400.pth b/checkpoint_p1/milestones/checkpoint_001274400_326246400.pth new file mode 100644 index 0000000000000000000000000000000000000000..099be00222ca24f119d46b40f13580d9decfb065 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001274400_326246400.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c4b0c04ae58232b4661f0c3b88395bc807d952f5c442e6c878110f16be88f91 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001288672_329900032.pth b/checkpoint_p1/milestones/checkpoint_001288672_329900032.pth new file mode 100644 index 0000000000000000000000000000000000000000..6e666bafe8d88b39d1f7a38d96b95ace62065b92 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001288672_329900032.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb07b8dac54eba319f76b09487d3bdb2add15d811f61c2380bbf6251777dd576 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001302912_333545472.pth b/checkpoint_p1/milestones/checkpoint_001302912_333545472.pth new file mode 100644 index 0000000000000000000000000000000000000000..1ccc872d6305ae6a55cc7e14cb1dc6022526cd41 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001302912_333545472.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c95d6bea8c6850b1a49729736f697536e690bf56b3ae4dc9aee3199794369693 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001317184_337199104.pth b/checkpoint_p1/milestones/checkpoint_001317184_337199104.pth new file mode 100644 index 0000000000000000000000000000000000000000..3cf2a27b5c2414507d8160d24a97d717871350d5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001317184_337199104.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfa57b2aae2733f47f4e63f833c957a25be90182c64237d41ab861527204000b +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001331520_340869120.pth b/checkpoint_p1/milestones/checkpoint_001331520_340869120.pth new file mode 100644 index 0000000000000000000000000000000000000000..dbd168f60db410ec2865b64ef80e14f3d7a4d30c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001331520_340869120.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bde72250eb1116d85c3daaa32c84ba6168368f644cc4f35425ce51d71715431 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001345792_344522752.pth b/checkpoint_p1/milestones/checkpoint_001345792_344522752.pth new file mode 100644 index 0000000000000000000000000000000000000000..3136c100b090f576529466e7e245ea1ea9a65398 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001345792_344522752.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:059970aea26848210e46ef6ea11a83e118f437e8a4d38b7cd8660d9ba7717a86 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001359936_348143616.pth b/checkpoint_p1/milestones/checkpoint_001359936_348143616.pth new file mode 100644 index 0000000000000000000000000000000000000000..d6ecb1a93839ecf9f9ad016f748955d90fdecefc --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001359936_348143616.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:133b4ed28b5e6e8c48011f398fda5ad583fe239a6d235ef8a0faf1ec04282032 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001374272_351813632.pth b/checkpoint_p1/milestones/checkpoint_001374272_351813632.pth new file mode 100644 index 0000000000000000000000000000000000000000..69f64c67e926473eb90d3b488165520e604fbed4 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001374272_351813632.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fb31c0f26148cdf1a428839735ef67e79a0caa991e39b24a716865e5292f2dc +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001388544_355467264.pth b/checkpoint_p1/milestones/checkpoint_001388544_355467264.pth new file mode 100644 index 0000000000000000000000000000000000000000..c3defbe4e6371c51e34d6d36549f70e482f09e65 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001388544_355467264.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f39c7d63c66c81d6d096710e3dc76ddf4319f892b691ff99c6e6374e57c61d7f +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001402848_359129088.pth b/checkpoint_p1/milestones/checkpoint_001402848_359129088.pth new file mode 100644 index 0000000000000000000000000000000000000000..56c8514c81857428c657f100d91afced41d93702 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001402848_359129088.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e77204f2631bb5ada0d810e04148b83543309cabfec69d7c1f9159bb3d675d9c +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001417088_362774528.pth b/checkpoint_p1/milestones/checkpoint_001417088_362774528.pth new file mode 100644 index 0000000000000000000000000000000000000000..c7eabae3eb3425b6e9247181917b6a18dbebbcd3 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001417088_362774528.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a30bc5dac0b974052cfa6ab4df99455149638ede5ffb977827e358b30e886a9c +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001431296_366411776.pth b/checkpoint_p1/milestones/checkpoint_001431296_366411776.pth new file mode 100644 index 0000000000000000000000000000000000000000..ef01b23cd4e76eb5982929862705bec509786d33 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001431296_366411776.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:109fec859ba2f06e056f4ed74422c7afe0c1eb95c19ad1f4fc0e6124703b0897 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001445536_370057216.pth b/checkpoint_p1/milestones/checkpoint_001445536_370057216.pth new file mode 100644 index 0000000000000000000000000000000000000000..0584003580bc1b3bd57b19ead14d93614845b67e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001445536_370057216.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2977f3abb90f397adf9929637b94e4878298cdca36a2405c1ce0082e380b02f5 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001459872_373727232.pth b/checkpoint_p1/milestones/checkpoint_001459872_373727232.pth new file mode 100644 index 0000000000000000000000000000000000000000..24c9dfc5ed6769371ca3b2c3707f233554c10882 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001459872_373727232.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:208c96de203422d5ce3d16e0f773bbed5bc8722891adfaedb4e5c76ab11238c4 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001474080_377364480.pth b/checkpoint_p1/milestones/checkpoint_001474080_377364480.pth new file mode 100644 index 0000000000000000000000000000000000000000..7471030625e11c6f4f1d1ce02949573fd3160f28 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001474080_377364480.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34ac2b457103a889209ba2c85a3c09eed02d9466a082ce595f8faf7398b97d12 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001488384_381026304.pth b/checkpoint_p1/milestones/checkpoint_001488384_381026304.pth new file mode 100644 index 0000000000000000000000000000000000000000..432ba058e024e9435da632a46a48f580bacb645d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001488384_381026304.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4f4f15b81881a9bfecc590cd96dd93454f1d3fcff72bb13f5eff388870f776b +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001502688_384688128.pth b/checkpoint_p1/milestones/checkpoint_001502688_384688128.pth new file mode 100644 index 0000000000000000000000000000000000000000..de6e431742eee7ec17532fbfa909f12d32717aac --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001502688_384688128.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1b11bd5cebd0e6af61436e9f9e1cb3f6f1a1bab133d5c8fb6a5ad5f3c46f743 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001516960_388341760.pth b/checkpoint_p1/milestones/checkpoint_001516960_388341760.pth new file mode 100644 index 0000000000000000000000000000000000000000..f0067ccdc1e8df38e64a67c04ef9ca051684a72a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001516960_388341760.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:740acc55e01f428b837a0b80a8038d5ac516b3321d9041d6922542d04ca74512 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001531296_392011776.pth b/checkpoint_p1/milestones/checkpoint_001531296_392011776.pth new file mode 100644 index 0000000000000000000000000000000000000000..4acdb5985e42c97c81b67e75e4d36d105fe02d46 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001531296_392011776.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9feb0168f2d0cbabd96c821b4fae1be8af08e00c21b5344bb4b8acb4c2c27050 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001545504_395649024.pth b/checkpoint_p1/milestones/checkpoint_001545504_395649024.pth new file mode 100644 index 0000000000000000000000000000000000000000..1161903ef11909094822cdec4c3e7745a0e5ccd8 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001545504_395649024.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faaa875ea84331f5008085aad65ff94135df9445f40682326ac318798799ca32 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001559808_399310848.pth b/checkpoint_p1/milestones/checkpoint_001559808_399310848.pth new file mode 100644 index 0000000000000000000000000000000000000000..375b6ea746d20faaedda700f2a39795f697b9cd7 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001559808_399310848.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27b622ee375e865d6cc0e436eaae738027767922b4a4ed05fcdd0f2ce94c8776 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001574016_402948096.pth b/checkpoint_p1/milestones/checkpoint_001574016_402948096.pth new file mode 100644 index 0000000000000000000000000000000000000000..ff1e5c8e5c3786519ab11b1bcbf2ca0544dc8a5b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001574016_402948096.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d553fbc2916792fe0a53ef70bfdd19c9c0e1368cc349711b0bdc45767513841a +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001588288_406601728.pth b/checkpoint_p1/milestones/checkpoint_001588288_406601728.pth new file mode 100644 index 0000000000000000000000000000000000000000..a3e06795b6847ea3e8c25056a80bb60e0d4cd148 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001588288_406601728.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57174cb9ff32425988b3d19adb93e91789518100b603ace79e7969fc29721b48 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001602560_410255360.pth b/checkpoint_p1/milestones/checkpoint_001602560_410255360.pth new file mode 100644 index 0000000000000000000000000000000000000000..649df9bc2e0bc4790bd2dd274193c5939e47013f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001602560_410255360.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f7857efbd6b218e9c40fb2ed1b18a374da9763d0e031815d5afc283c1e22e8b +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001616864_413917184.pth b/checkpoint_p1/milestones/checkpoint_001616864_413917184.pth new file mode 100644 index 0000000000000000000000000000000000000000..c9f993b361f551f3579daf1f07c8716852858e1a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001616864_413917184.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e393a5694b6e3982b57b6406d203b24455f20ae10768128dab9e41160bf41edd +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001631072_417554432.pth b/checkpoint_p1/milestones/checkpoint_001631072_417554432.pth new file mode 100644 index 0000000000000000000000000000000000000000..dd4b1b17d78cf32287682198cf20bb377ab605fb --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001631072_417554432.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c63201adbcd032c992d0507e47f263af7b5d68cfbebebc60ce6efdddb77123a +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001645376_421216256.pth b/checkpoint_p1/milestones/checkpoint_001645376_421216256.pth new file mode 100644 index 0000000000000000000000000000000000000000..f231c7ba40beedd0bafb0e6d8d50c7a09c2b2ad1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001645376_421216256.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daaadc403d0fd0d9577673de3a945b3236d408dc8bb7290b9bb21162285a53c0 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001659712_424886272.pth b/checkpoint_p1/milestones/checkpoint_001659712_424886272.pth new file mode 100644 index 0000000000000000000000000000000000000000..e495991286ea37b17d430f074ef314b8b6510912 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001659712_424886272.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b7f14b02622863f52eed851d6354bb7d438ce7cab5996cdbb545edcec8314fc +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001673952_428531712.pth b/checkpoint_p1/milestones/checkpoint_001673952_428531712.pth new file mode 100644 index 0000000000000000000000000000000000000000..4818618d45032a9452006f1f7d958b12233cf5ad --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001673952_428531712.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a032dbe316c6ed19c6b0ceba66d5b9fe5e37218a8f04b39eb8e97149f8e3e108 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001688160_432168960.pth b/checkpoint_p1/milestones/checkpoint_001688160_432168960.pth new file mode 100644 index 0000000000000000000000000000000000000000..045162d2d60a63933e7f0a47d3e9ab0cedd49f06 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001688160_432168960.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb06ab260423ced51958f767ca8ab9cba8c9ae3f2b5465aadb8a9c9566aa2fc7 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001702400_435814400.pth b/checkpoint_p1/milestones/checkpoint_001702400_435814400.pth new file mode 100644 index 0000000000000000000000000000000000000000..3f3e1ce98e133a9677fd443b59fa9d878174bd84 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001702400_435814400.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a0008280644414853c2500ca3b44f578cc4f6ea94f1206059dd632b780c32bb +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001716672_439468032.pth b/checkpoint_p1/milestones/checkpoint_001716672_439468032.pth new file mode 100644 index 0000000000000000000000000000000000000000..87a5915ab5086b3e48fbbdb50890423d9a571d47 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001716672_439468032.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2004622ab2fc65f3eb01da23878faa8a4ea163d1c4fdc1db451b0e44feb69001 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001731040_443146240.pth b/checkpoint_p1/milestones/checkpoint_001731040_443146240.pth new file mode 100644 index 0000000000000000000000000000000000000000..a7e5e587dbf3c720f6a757828abf211fba7e70c8 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001731040_443146240.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55fea653ded697d7a9f9f384330848b8fa15379372f7511508f1bbed0bf66b42 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001745312_446799872.pth b/checkpoint_p1/milestones/checkpoint_001745312_446799872.pth new file mode 100644 index 0000000000000000000000000000000000000000..f3ed7625a4fe4276cc8fce45d6324db47e9c34b5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001745312_446799872.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55280f8ffe3c8c67153715de35d2dd04f7b4f9545d70d76fc8a9c91e55107d67 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001759648_450469888.pth b/checkpoint_p1/milestones/checkpoint_001759648_450469888.pth new file mode 100644 index 0000000000000000000000000000000000000000..04547e87a2a2527eb86164837537d5061c48a21e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001759648_450469888.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d32054f38f939add7b173699bcbbd36398f185f9cb29df426bad79c81d12c45f +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001773984_454139904.pth b/checkpoint_p1/milestones/checkpoint_001773984_454139904.pth new file mode 100644 index 0000000000000000000000000000000000000000..083275cdb016e2f8fea4e458cbf5d96d7e9c5166 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001773984_454139904.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bc64161095d3f81334a1f20736a8dfb6779b059e0c4f3b8fb6996a53591c868 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001788256_457793536.pth b/checkpoint_p1/milestones/checkpoint_001788256_457793536.pth new file mode 100644 index 0000000000000000000000000000000000000000..59d204462b37ae5627db44b7d63c73717a4863e6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001788256_457793536.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24616fa8ada872105d6bbaef924fd46030074c7c7baff24431a8f924f82754b3 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001802464_461430784.pth b/checkpoint_p1/milestones/checkpoint_001802464_461430784.pth new file mode 100644 index 0000000000000000000000000000000000000000..d7ff50ae0a7a283e48bf18159e6c6520f9e24bca --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001802464_461430784.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92923b101686c32d7ab72793a2ea380cc90f77ee13eae857127b76380b3cbad4 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001816736_465084416.pth b/checkpoint_p1/milestones/checkpoint_001816736_465084416.pth new file mode 100644 index 0000000000000000000000000000000000000000..b877cb6a3494cbda502217f83e3538d24092ef62 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001816736_465084416.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b3dbb91f172c231a69ff6ba135e60e4cc658fe3390be8b8d065313729117691 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001831040_468746240.pth b/checkpoint_p1/milestones/checkpoint_001831040_468746240.pth new file mode 100644 index 0000000000000000000000000000000000000000..d839c759d45909749254651b64f49febafcb3918 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001831040_468746240.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0aa8dc3810e6fbb2a3b302f25e416c9746d038441beac2caa8cabc139a8f997 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001845312_472399872.pth b/checkpoint_p1/milestones/checkpoint_001845312_472399872.pth new file mode 100644 index 0000000000000000000000000000000000000000..62f32463b0a69a9cf4984272c70a74de9cc74f71 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001845312_472399872.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2750806f52da3fb66f455f6d87998b6314a3cc73484a76066a1f12acac9bff0 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001859520_476037120.pth b/checkpoint_p1/milestones/checkpoint_001859520_476037120.pth new file mode 100644 index 0000000000000000000000000000000000000000..d9f8d5de7dc92ef046c3a115c2dac0a5436e1590 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001859520_476037120.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8acdd2a01c114a40dca495b7686eed1c250e9126a0cd935592ace931129a85a7 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001873824_479698944.pth b/checkpoint_p1/milestones/checkpoint_001873824_479698944.pth new file mode 100644 index 0000000000000000000000000000000000000000..1fd6c3286454066306d4bd7b135bdcdf4d8b51f7 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001873824_479698944.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5d52119d7afaf63b67854831b4df43476a2cc10f51d445ac2cbd55af676120d +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001888128_483360768.pth b/checkpoint_p1/milestones/checkpoint_001888128_483360768.pth new file mode 100644 index 0000000000000000000000000000000000000000..a44d8da149c92e61676a284ef98e8b19afe3d139 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001888128_483360768.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:672fbba0416913b201555707383b7b0f530374d5f406ae08360a37202406206b +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001902400_487014400.pth b/checkpoint_p1/milestones/checkpoint_001902400_487014400.pth new file mode 100644 index 0000000000000000000000000000000000000000..89b77883978f66dcea9322fbea0356387f339797 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001902400_487014400.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2c4c0fb7ccda1201953a3eae18c6546d983e36737a04dd3acb85348b4e0130b +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001916672_490668032.pth b/checkpoint_p1/milestones/checkpoint_001916672_490668032.pth new file mode 100644 index 0000000000000000000000000000000000000000..416f9591ff29103b1991ba65cd3f70408930dcf5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001916672_490668032.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abadc199ae61f0bd4efafa40fd70dd3f6483536d8a2363935dcbac7d53af7b45 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001930912_494313472.pth b/checkpoint_p1/milestones/checkpoint_001930912_494313472.pth new file mode 100644 index 0000000000000000000000000000000000000000..cb872a41ca298e19e03af16e5ad73a915e06ccf0 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001930912_494313472.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1648e8ad7d2cf91aab0d40269652871a7e4b176abd069af7731dc689af1f6b0 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001945152_497958912.pth b/checkpoint_p1/milestones/checkpoint_001945152_497958912.pth new file mode 100644 index 0000000000000000000000000000000000000000..2277096fd897a9bf8dcc5574685d68e6f040efbe --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001945152_497958912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e767705f701b9f07124f019b59f1cecfcfa25a688af6679434b7da233a1935c8 +size 20797067 diff --git a/config.json b/config.json index 28eabaf2dab139a22e48348459ebfea494adebf0..bade3624d46be900a4612b3e01d4f313b4b73182 100644 --- a/config.json +++ b/config.json @@ -4,7 +4,7 @@ "env": "atari_berzerk", "experiment": "atari_berzerk_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_berzerk --experiment=atari_berzerk_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_berzerk --wandb_job_type=SF --wandb_tags=atari", + "command_line": "--algo=APPO --env=atari_berzerk --experiment=atari_berzerk_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_berzerk --wandb_job_type=SF --wandb_tags=atari", "cli_args": { "algo": "APPO", "env": "atari_berzerk", "experiment": "atari_berzerk_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_berzerk_APPO_20231009_081613_083909" + "wandb_unique_id": "atari_berzerk_APPO_20231024_073146_056389" } \ 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 eb8736f090be704d6c56661248ff44b368d5ad5b..250d69619d8f5d9ec6f6db5c7f0131a70903272f 100644 --- a/replay.mp4 +++ b/replay.mp4 @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:dba2d55c7016da5a9114ab281d5010b92e3b7d792496f04fee8a4a5a863185e6 -size 2003694 +oid sha256:6bdd58b75f92b92ab3570e2ce877f4c58578d4f4834cd85344d021f5ff4988c3 +size 34117055 diff --git a/sf_log.txt b/sf_log.txt index 28598ec887cf4e4ff3c449d8772d0dcf196a3874..b71b0eb3a355a7a4ec09560bfba1e3b9e837a395 100644 --- a/sf_log.txt +++ b/sf_log.txt @@ -1,26224 +1,3 @@ -[2023-10-09 08:16:20,021][22500] Saving configuration to ./train_atari/atari_berzerk_APPO/config.json... -[2023-10-09 08:16:20,339][22500] Rollout worker 0 uses device cpu -[2023-10-09 08:16:20,340][22500] Rollout worker 1 uses device cpu -[2023-10-09 08:16:20,340][22500] Rollout worker 2 uses device cpu -[2023-10-09 08:16:20,341][22500] Rollout worker 3 uses device cpu -[2023-10-09 08:16:20,342][22500] Rollout worker 4 uses device cpu -[2023-10-09 08:16:20,342][22500] Rollout worker 5 uses device cpu -[2023-10-09 08:16:20,343][22500] Rollout worker 6 uses device cpu -[2023-10-09 08:16:20,343][22500] Rollout worker 7 uses device cpu -[2023-10-09 08:16:20,344][22500] Rollout worker 8 uses device cpu -[2023-10-09 08:16:20,344][22500] Rollout worker 9 uses device cpu -[2023-10-09 08:16:20,345][22500] Rollout worker 10 uses device cpu -[2023-10-09 08:16:20,345][22500] Rollout worker 11 uses device cpu -[2023-10-09 08:16:20,345][22500] Rollout worker 12 uses device cpu -[2023-10-09 08:16:20,346][22500] Rollout worker 13 uses device cpu -[2023-10-09 08:16:20,346][22500] Rollout worker 14 uses device cpu -[2023-10-09 08:16:20,347][22500] Rollout worker 15 uses device cpu -[2023-10-09 08:16:20,639][22500] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-09 08:16:20,639][22500] InferenceWorker_p0-w0: min num requests: 2 -[2023-10-09 08:16:20,643][22500] Using GPUs [1] for process 1 (actually maps to GPUs [1]) -[2023-10-09 08:16:20,643][22500] InferenceWorker_p1-w0: min num requests: 2 -[2023-10-09 08:16:20,691][22500] Starting all processes... -[2023-10-09 08:16:20,691][22500] Starting process learner_proc0 -[2023-10-09 08:16:22,424][22500] Starting process learner_proc1 -[2023-10-09 08:16:22,427][23265] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-09 08:16:22,428][23265] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 -[2023-10-09 08:16:22,446][23265] Num visible devices: 1 -[2023-10-09 08:16:22,464][23265] Setting fixed seed 1234 -[2023-10-09 08:16:22,466][23265] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-09 08:16:22,466][23265] Initializing actor-critic model on device cuda:0 -[2023-10-09 08:16:22,466][23265] RunningMeanStd input shape: (4, 84, 84) -[2023-10-09 08:16:22,467][23265] RunningMeanStd input shape: (1,) -[2023-10-09 08:16:22,478][23265] ConvEncoder: input_channels=4 -[2023-10-09 08:16:22,657][23265] Conv encoder output size: 512 -[2023-10-09 08:16:22,659][23265] Created Actor Critic model with architecture: -[2023-10-09 08:16:22,659][23265] 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) - ) -) -[2023-10-09 08:16:23,222][23265] Using optimizer -[2023-10-09 08:16:23,222][23265] No checkpoints found -[2023-10-09 08:16:23,223][23265] Did not load from checkpoint, starting from scratch! -[2023-10-09 08:16:23,223][23265] Initialized policy 0 weights for model version 0 -[2023-10-09 08:16:23,224][23265] LearnerWorker_p0 finished initialization! -[2023-10-09 08:16:23,225][23265] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-09 08:16:24,138][22500] Starting all processes... -[2023-10-09 08:16:24,144][23343] Using GPUs [1] for process 1 (actually maps to GPUs [1]) -[2023-10-09 08:16:24,144][23343] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [1]) for learning process 1 -[2023-10-09 08:16:24,146][22500] Starting process inference_proc0-0 -[2023-10-09 08:16:24,146][22500] Starting process inference_proc1-0 -[2023-10-09 08:16:24,146][22500] Starting process rollout_proc0 -[2023-10-09 08:16:24,162][23343] Num visible devices: 1 -[2023-10-09 08:16:24,147][22500] Starting process rollout_proc1 -[2023-10-09 08:16:24,147][22500] Starting process rollout_proc2 -[2023-10-09 08:16:24,180][23343] Setting fixed seed 1234 -[2023-10-09 08:16:24,147][22500] Starting process rollout_proc3 -[2023-10-09 08:16:24,181][23343] Using GPUs [0] for process 1 (actually maps to GPUs [1]) -[2023-10-09 08:16:24,181][23343] Initializing actor-critic model on device cuda:0 -[2023-10-09 08:16:24,182][23343] RunningMeanStd input shape: (4, 84, 84) -[2023-10-09 08:16:24,152][22500] Starting process rollout_proc4 -[2023-10-09 08:16:24,182][23343] RunningMeanStd input shape: (1,) -[2023-10-09 08:16:24,152][22500] Starting process rollout_proc5 -[2023-10-09 08:16:24,156][22500] Starting process rollout_proc6 -[2023-10-09 08:16:24,158][22500] Starting process rollout_proc7 -[2023-10-09 08:16:24,159][22500] Starting process rollout_proc8 -[2023-10-09 08:16:24,194][23343] ConvEncoder: input_channels=4 -[2023-10-09 08:16:24,160][22500] Starting process rollout_proc9 -[2023-10-09 08:16:24,160][22500] Starting process rollout_proc10 -[2023-10-09 08:16:24,163][22500] Starting process rollout_proc11 -[2023-10-09 08:16:24,164][22500] Starting process rollout_proc12 -[2023-10-09 08:16:24,165][22500] Starting process rollout_proc13 -[2023-10-09 08:16:24,657][23343] Conv encoder output size: 512 -[2023-10-09 08:16:24,659][23343] Created Actor Critic model with architecture: -[2023-10-09 08:16:24,659][23343] 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) - ) -) -[2023-10-09 08:16:25,256][23343] Using optimizer -[2023-10-09 08:16:25,257][23343] No checkpoints found -[2023-10-09 08:16:25,257][23343] Did not load from checkpoint, starting from scratch! -[2023-10-09 08:16:25,257][23343] Initialized policy 1 weights for model version 0 -[2023-10-09 08:16:25,259][23343] LearnerWorker_p1 finished initialization! -[2023-10-09 08:16:25,259][23343] Using GPUs [0] for process 1 (actually maps to GPUs [1]) -[2023-10-09 08:16:26,332][22500] Starting process rollout_proc14 -[2023-10-09 08:16:26,339][22500] Starting process rollout_proc15 -[2023-10-09 08:16:26,339][23531] Worker 9 uses CPU cores [18, 19] -[2023-10-09 08:16:26,344][23517] Worker 3 uses CPU cores [6, 7] -[2023-10-09 08:16:26,358][23516] Worker 2 uses CPU cores [4, 5] -[2023-10-09 08:16:26,361][23468] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-09 08:16:26,361][23468] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 -[2023-10-09 08:16:26,364][23520] Worker 5 uses CPU cores [10, 11] -[2023-10-09 08:16:26,364][23513] Worker 1 uses CPU cores [2, 3] -[2023-10-09 08:16:26,372][23525] Worker 7 uses CPU cores [14, 15] -[2023-10-09 08:16:26,374][23535] Worker 13 uses CPU cores [26, 27] -[2023-10-09 08:16:26,380][23468] Num visible devices: 1 -[2023-10-09 08:16:26,412][23534] Worker 12 uses CPU cores [24, 25] -[2023-10-09 08:16:26,451][23522] Worker 6 uses CPU cores [12, 13] -[2023-10-09 08:16:26,780][23533] Worker 11 uses CPU cores [22, 23] -[2023-10-09 08:16:26,863][23514] Worker 0 uses CPU cores [0, 1] -[2023-10-09 08:16:26,888][23530] Worker 8 uses CPU cores [16, 17] -[2023-10-09 08:16:26,982][23469] Using GPUs [1] for process 1 (actually maps to GPUs [1]) -[2023-10-09 08:16:26,982][23469] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [1]) for inference process 1 -[2023-10-09 08:16:27,001][23469] Num visible devices: 1 -[2023-10-09 08:16:27,049][23523] Worker 4 uses CPU cores [8, 9] -[2023-10-09 08:16:27,077][23468] RunningMeanStd input shape: (4, 84, 84) -[2023-10-09 08:16:27,078][23468] RunningMeanStd input shape: (1,) -[2023-10-09 08:16:27,090][23468] ConvEncoder: input_channels=4 -[2023-10-09 08:16:27,136][23532] Worker 10 uses CPU cores [20, 21] -[2023-10-09 08:16:27,207][23468] Conv encoder output size: 512 -[2023-10-09 08:16:27,573][23469] RunningMeanStd input shape: (4, 84, 84) -[2023-10-09 08:16:27,574][23469] RunningMeanStd input shape: (1,) -[2023-10-09 08:16:27,585][23469] ConvEncoder: input_channels=4 -[2023-10-09 08:16:27,687][23469] Conv encoder output size: 512 -[2023-10-09 08:16:28,196][24382] Worker 14 uses CPU cores [28, 29] -[2023-10-09 08:16:28,214][22500] Inference worker 0-0 is ready! -[2023-10-09 08:16:28,215][22500] Inference worker 1-0 is ready! -[2023-10-09 08:16:28,216][24383] Worker 15 uses CPU cores [30, 31] -[2023-10-09 08:16:28,216][22500] All inference workers are ready! Signal rollout workers to start! -[2023-10-09 08:16:28,217][23522] EnvRunner 6-0 uses policy 0 -[2023-10-09 08:16:28,218][23513] EnvRunner 1-0 uses policy 1 -[2023-10-09 08:16:28,218][23520] EnvRunner 5-0 uses policy 1 -[2023-10-09 08:16:28,218][23531] EnvRunner 9-0 uses policy 1 -[2023-10-09 08:16:28,218][23523] EnvRunner 4-0 uses policy 0 -[2023-10-09 08:16:28,218][23532] EnvRunner 10-0 uses policy 0 -[2023-10-09 08:16:28,218][23535] EnvRunner 13-0 uses policy 1 -[2023-10-09 08:16:28,218][23516] EnvRunner 2-0 uses policy 0 -[2023-10-09 08:16:28,218][23534] EnvRunner 12-0 uses policy 0 -[2023-10-09 08:16:28,218][23530] EnvRunner 8-0 uses policy 0 -[2023-10-09 08:16:28,218][23525] EnvRunner 7-0 uses policy 1 -[2023-10-09 08:16:28,218][23517] EnvRunner 3-0 uses policy 1 -[2023-10-09 08:16:28,218][23514] EnvRunner 0-0 uses policy 0 -[2023-10-09 08:16:28,218][22500] 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) -[2023-10-09 08:16:28,218][23533] EnvRunner 11-0 uses policy 1 -[2023-10-09 08:16:28,392][24382] EnvRunner 14-0 uses policy 0 -[2023-10-09 08:16:28,440][24383] EnvRunner 15-0 uses policy 1 -[2023-10-09 08:16:30,626][22500] Heartbeat connected on Batcher_0 -[2023-10-09 08:16:30,629][22500] Heartbeat connected on LearnerWorker_p0 -[2023-10-09 08:16:30,632][22500] Heartbeat connected on Batcher_1 -[2023-10-09 08:16:30,635][22500] Heartbeat connected on LearnerWorker_p1 -[2023-10-09 08:16:30,646][22500] Heartbeat connected on InferenceWorker_p0-w0 -[2023-10-09 08:16:30,648][22500] Heartbeat connected on InferenceWorker_p1-w0 -[2023-10-09 08:16:30,650][22500] Heartbeat connected on RolloutWorker_w1 -[2023-10-09 08:16:30,650][22500] Heartbeat connected on RolloutWorker_w0 -[2023-10-09 08:16:30,658][22500] Heartbeat connected on RolloutWorker_w2 -[2023-10-09 08:16:30,658][22500] Heartbeat connected on RolloutWorker_w3 -[2023-10-09 08:16:30,659][22500] Heartbeat connected on RolloutWorker_w4 -[2023-10-09 08:16:30,661][22500] Heartbeat connected on RolloutWorker_w5 -[2023-10-09 08:16:30,664][22500] Heartbeat connected on RolloutWorker_w6 -[2023-10-09 08:16:30,667][22500] Heartbeat connected on RolloutWorker_w7 -[2023-10-09 08:16:30,670][22500] Heartbeat connected on RolloutWorker_w8 -[2023-10-09 08:16:30,678][22500] Heartbeat connected on RolloutWorker_w11 -[2023-10-09 08:16:30,679][22500] Heartbeat connected on RolloutWorker_w9 -[2023-10-09 08:16:30,680][22500] Heartbeat connected on RolloutWorker_w10 -[2023-10-09 08:16:30,686][22500] Heartbeat connected on RolloutWorker_w13 -[2023-10-09 08:16:30,689][22500] Heartbeat connected on RolloutWorker_w12 -[2023-10-09 08:16:30,693][22500] Heartbeat connected on RolloutWorker_w15 -[2023-10-09 08:16:30,698][22500] Heartbeat connected on RolloutWorker_w14 -[2023-10-09 08:16:31,077][22500] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 445.6, 1: 740.0. Samples: 3390. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-10-09 08:16:31,078][22500] Avg episode reward: [(0, '0.674'), (1, '1.080')] -[2023-10-09 08:16:36,077][22500] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 947.4, 1: 1052.3. Samples: 15716. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-10-09 08:16:36,078][22500] Avg episode reward: [(0, '1.040'), (1, '1.040')] -[2023-10-09 08:16:38,230][23468] Updated weights for policy 0, policy_version 10 (0.0010) -[2023-10-09 08:16:38,256][23469] Updated weights for policy 1, policy_version 10 (0.0007) -[2023-10-09 08:16:38,602][23468] Updated weights for policy 0, policy_version 20 (0.0008) -[2023-10-09 08:16:38,626][23469] Updated weights for policy 1, policy_version 20 (0.0007) -[2023-10-09 08:16:38,964][23468] Updated weights for policy 0, policy_version 30 (0.0007) -[2023-10-09 08:16:38,995][23469] Updated weights for policy 1, policy_version 30 (0.0007) -[2023-10-09 08:16:41,075][23469] Updated weights for policy 1, policy_version 40 (0.0008) -[2023-10-09 08:16:41,077][22500] Fps is (10 sec: 6553.7, 60 sec: 5096.4, 300 sec: 5096.4). Total num frames: 65536. Throughput: 0: 1225.7, 1: 1300.4. Samples: 32484. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 08:16:41,078][22500] Avg episode reward: [(0, '1.040'), (1, '0.990')] -[2023-10-09 08:16:41,186][23468] Updated weights for policy 0, policy_version 40 (0.0007) -[2023-10-09 08:16:41,450][23469] Updated weights for policy 1, policy_version 50 (0.0009) -[2023-10-09 08:16:41,556][23468] Updated weights for policy 0, policy_version 50 (0.0008) -[2023-10-09 08:16:41,806][23469] Updated weights for policy 1, policy_version 60 (0.0007) -[2023-10-09 08:16:41,922][23468] Updated weights for policy 0, policy_version 60 (0.0009) -[2023-10-09 08:16:45,038][23468] Updated weights for policy 0, policy_version 70 (0.0009) -[2023-10-09 08:16:45,291][23469] Updated weights for policy 1, policy_version 70 (0.0009) -[2023-10-09 08:16:45,400][23468] Updated weights for policy 0, policy_version 80 (0.0008) -[2023-10-09 08:16:45,645][23469] Updated weights for policy 1, policy_version 80 (0.0009) -[2023-10-09 08:16:45,779][23468] Updated weights for policy 0, policy_version 90 (0.0008) -[2023-10-09 08:16:46,013][23469] Updated weights for policy 1, policy_version 90 (0.0007) -[2023-10-09 08:16:46,077][22500] Fps is (10 sec: 16383.9, 60 sec: 9173.9, 300 sec: 9173.9). Total num frames: 163840. Throughput: 0: 1460.2, 1: 1482.9. Samples: 52562. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 08:16:46,078][22500] Avg episode reward: [(0, '1.030'), (1, '0.960')] -[2023-10-09 08:16:49,426][23468] Updated weights for policy 0, policy_version 100 (0.0008) -[2023-10-09 08:16:49,486][23469] Updated weights for policy 1, policy_version 100 (0.0007) -[2023-10-09 08:16:49,798][23468] Updated weights for policy 0, policy_version 110 (0.0010) -[2023-10-09 08:16:49,852][23469] Updated weights for policy 1, policy_version 110 (0.0008) -[2023-10-09 08:16:50,169][23468] Updated weights for policy 0, policy_version 120 (0.0008) -[2023-10-09 08:16:50,229][23469] Updated weights for policy 1, policy_version 120 (0.0007) -[2023-10-09 08:16:51,077][22500] Fps is (10 sec: 19660.7, 60 sec: 11467.7, 300 sec: 11467.7). Total num frames: 262144. Throughput: 0: 1363.4, 1: 1405.6. Samples: 63296. Policy #0 lag: (min: 22.0, avg: 22.3, max: 33.0) -[2023-10-09 08:16:51,078][22500] Avg episode reward: [(0, '1.240'), (1, '1.090')] -[2023-10-09 08:16:51,079][23265] Saving new best policy, reward=1.240! -[2023-10-09 08:16:51,079][23343] Saving new best policy, reward=1.090! -[2023-10-09 08:16:54,182][23468] Updated weights for policy 0, policy_version 130 (0.0007) -[2023-10-09 08:16:54,246][23469] Updated weights for policy 1, policy_version 130 (0.0007) -[2023-10-09 08:16:54,549][23468] Updated weights for policy 0, policy_version 140 (0.0007) -[2023-10-09 08:16:54,616][23469] Updated weights for policy 1, policy_version 140 (0.0008) -[2023-10-09 08:16:54,918][23468] Updated weights for policy 0, policy_version 150 (0.0007) -[2023-10-09 08:16:54,986][23469] Updated weights for policy 1, policy_version 150 (0.0007) -[2023-10-09 08:16:55,293][23468] Updated weights for policy 0, policy_version 160 (0.0008) -[2023-10-09 08:16:55,358][23469] Updated weights for policy 1, policy_version 160 (0.0008) -[2023-10-09 08:16:56,077][22500] Fps is (10 sec: 16383.8, 60 sec: 11761.9, 300 sec: 11761.9). Total num frames: 327680. Throughput: 0: 1500.0, 1: 1515.3. Samples: 84004. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:16:56,078][22500] Avg episode reward: [(0, '1.620'), (1, '1.230')] -[2023-10-09 08:16:56,079][23265] Saving new best policy, reward=1.620! -[2023-10-09 08:16:56,079][23343] Saving new best policy, reward=1.230! -[2023-10-09 08:16:59,179][23469] Updated weights for policy 1, policy_version 170 (0.0008) -[2023-10-09 08:16:59,330][23468] Updated weights for policy 0, policy_version 170 (0.0009) -[2023-10-09 08:16:59,547][23469] Updated weights for policy 1, policy_version 180 (0.0008) -[2023-10-09 08:16:59,695][23468] Updated weights for policy 0, policy_version 180 (0.0010) -[2023-10-09 08:16:59,912][23469] Updated weights for policy 1, policy_version 190 (0.0007) -[2023-10-09 08:17:00,060][23468] Updated weights for policy 0, policy_version 190 (0.0008) -[2023-10-09 08:17:01,077][22500] Fps is (10 sec: 13107.2, 60 sec: 11966.7, 300 sec: 11966.7). Total num frames: 393216. Throughput: 0: 1563.6, 1: 1598.3. Samples: 103900. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-10-09 08:17:01,078][22500] Avg episode reward: [(0, '1.140'), (1, '1.120')] -[2023-10-09 08:17:03,878][23469] Updated weights for policy 1, policy_version 200 (0.0009) -[2023-10-09 08:17:04,087][23468] Updated weights for policy 0, policy_version 200 (0.0010) -[2023-10-09 08:17:04,253][23469] Updated weights for policy 1, policy_version 210 (0.0008) -[2023-10-09 08:17:04,457][23468] Updated weights for policy 0, policy_version 210 (0.0008) -[2023-10-09 08:17:04,621][23469] Updated weights for policy 1, policy_version 220 (0.0008) -[2023-10-09 08:17:04,832][23468] Updated weights for policy 0, policy_version 220 (0.0008) -[2023-10-09 08:17:06,077][22500] Fps is (10 sec: 13107.4, 60 sec: 12117.3, 300 sec: 12117.3). Total num frames: 458752. Throughput: 0: 1517.6, 1: 1542.0. Samples: 115834. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-09 08:17:06,078][22500] Avg episode reward: [(0, '1.350'), (1, '1.420')] -[2023-10-09 08:17:06,079][23343] Saving new best policy, reward=1.420! -[2023-10-09 08:17:08,609][23469] Updated weights for policy 1, policy_version 230 (0.0008) -[2023-10-09 08:17:08,766][23468] Updated weights for policy 0, policy_version 230 (0.0009) -[2023-10-09 08:17:08,980][23469] Updated weights for policy 1, policy_version 240 (0.0009) -[2023-10-09 08:17:09,126][23468] Updated weights for policy 0, policy_version 240 (0.0007) -[2023-10-09 08:17:09,336][23469] Updated weights for policy 1, policy_version 250 (0.0007) -[2023-10-09 08:17:09,492][23468] Updated weights for policy 0, policy_version 250 (0.0008) -[2023-10-09 08:17:11,078][22500] Fps is (10 sec: 13106.9, 60 sec: 12232.7, 300 sec: 12232.7). Total num frames: 524288. Throughput: 0: 1571.8, 1: 1584.3. Samples: 135268. Policy #0 lag: (min: 4.0, avg: 19.1, max: 36.0) -[2023-10-09 08:17:11,079][22500] Avg episode reward: [(0, '1.170'), (1, '1.390')] -[2023-10-09 08:17:13,229][23469] Updated weights for policy 1, policy_version 260 (0.0008) -[2023-10-09 08:17:13,232][23468] Updated weights for policy 0, policy_version 260 (0.0007) -[2023-10-09 08:17:13,598][23469] Updated weights for policy 1, policy_version 270 (0.0007) -[2023-10-09 08:17:13,609][23468] Updated weights for policy 0, policy_version 270 (0.0007) -[2023-10-09 08:17:13,964][23469] Updated weights for policy 1, policy_version 280 (0.0008) -[2023-10-09 08:17:13,973][23468] Updated weights for policy 0, policy_version 280 (0.0007) -[2023-10-09 08:17:16,077][22500] Fps is (10 sec: 13107.1, 60 sec: 12324.1, 300 sec: 12324.1). Total num frames: 589824. Throughput: 0: 1703.3, 1: 1704.4. Samples: 156738. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 08:17:16,078][22500] Avg episode reward: [(0, '1.410'), (1, '1.110')] -[2023-10-09 08:17:17,775][23468] Updated weights for policy 0, policy_version 290 (0.0007) -[2023-10-09 08:17:17,839][23469] Updated weights for policy 1, policy_version 290 (0.0008) -[2023-10-09 08:17:18,139][23468] Updated weights for policy 0, policy_version 300 (0.0007) -[2023-10-09 08:17:18,206][23469] Updated weights for policy 1, policy_version 300 (0.0008) -[2023-10-09 08:17:18,514][23468] Updated weights for policy 0, policy_version 310 (0.0008) -[2023-10-09 08:17:18,574][23469] Updated weights for policy 1, policy_version 310 (0.0009) -[2023-10-09 08:17:18,875][23468] Updated weights for policy 0, policy_version 320 (0.0008) -[2023-10-09 08:17:18,937][23469] Updated weights for policy 1, policy_version 320 (0.0008) -[2023-10-09 08:17:21,077][22500] Fps is (10 sec: 13107.6, 60 sec: 12398.2, 300 sec: 12398.2). Total num frames: 655360. Throughput: 0: 1690.9, 1: 1679.6. Samples: 167388. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-10-09 08:17:21,078][22500] Avg episode reward: [(0, '1.390'), (1, '1.270')] -[2023-10-09 08:17:22,551][23469] Updated weights for policy 1, policy_version 330 (0.0007) -[2023-10-09 08:17:22,915][23469] Updated weights for policy 1, policy_version 340 (0.0008) -[2023-10-09 08:17:22,921][23468] Updated weights for policy 0, policy_version 330 (0.0009) -[2023-10-09 08:17:23,284][23469] Updated weights for policy 1, policy_version 350 (0.0007) -[2023-10-09 08:17:23,286][23468] Updated weights for policy 0, policy_version 340 (0.0007) -[2023-10-09 08:17:23,656][23468] Updated weights for policy 0, policy_version 350 (0.0008) -[2023-10-09 08:17:26,077][22500] Fps is (10 sec: 13107.4, 60 sec: 12459.5, 300 sec: 12459.5). Total num frames: 720896. Throughput: 0: 1732.3, 1: 1732.6. Samples: 188402. Policy #0 lag: (min: 26.0, avg: 26.3, max: 39.0) -[2023-10-09 08:17:26,078][22500] Avg episode reward: [(0, '1.140'), (1, '1.550')] -[2023-10-09 08:17:26,078][23343] Saving new best policy, reward=1.550! -[2023-10-09 08:17:27,139][23469] Updated weights for policy 1, policy_version 360 (0.0007) -[2023-10-09 08:17:27,476][23468] Updated weights for policy 0, policy_version 360 (0.0009) -[2023-10-09 08:17:27,524][23469] Updated weights for policy 1, policy_version 370 (0.0008) -[2023-10-09 08:17:27,850][23468] Updated weights for policy 0, policy_version 370 (0.0008) -[2023-10-09 08:17:27,894][23469] Updated weights for policy 1, policy_version 380 (0.0009) -[2023-10-09 08:17:28,223][23468] Updated weights for policy 0, policy_version 380 (0.0010) -[2023-10-09 08:17:31,077][22500] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12511.0). Total num frames: 786432. Throughput: 0: 1745.8, 1: 1761.6. Samples: 210394. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-09 08:17:31,078][22500] Avg episode reward: [(0, '1.580'), (1, '1.770')] -[2023-10-09 08:17:31,088][23343] Saving new best policy, reward=1.770! -[2023-10-09 08:17:31,699][23469] Updated weights for policy 1, policy_version 390 (0.0009) -[2023-10-09 08:17:32,025][23468] Updated weights for policy 0, policy_version 390 (0.0009) -[2023-10-09 08:17:32,061][23469] Updated weights for policy 1, policy_version 400 (0.0007) -[2023-10-09 08:17:32,395][23468] Updated weights for policy 0, policy_version 400 (0.0008) -[2023-10-09 08:17:32,436][23469] Updated weights for policy 1, policy_version 410 (0.0009) -[2023-10-09 08:17:32,759][23468] Updated weights for policy 0, policy_version 410 (0.0007) -[2023-10-09 08:17:36,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 12554.9). Total num frames: 851968. Throughput: 0: 1739.4, 1: 1741.1. Samples: 219916. Policy #0 lag: (min: 22.0, avg: 29.8, max: 54.0) -[2023-10-09 08:17:36,078][22500] Avg episode reward: [(0, '1.680'), (1, '1.370')] -[2023-10-09 08:17:36,080][23265] Saving new best policy, reward=1.680! -[2023-10-09 08:17:36,285][23469] Updated weights for policy 1, policy_version 420 (0.0007) -[2023-10-09 08:17:36,522][23468] Updated weights for policy 0, policy_version 420 (0.0007) -[2023-10-09 08:17:36,650][23469] Updated weights for policy 1, policy_version 430 (0.0007) -[2023-10-09 08:17:36,901][23468] Updated weights for policy 0, policy_version 430 (0.0008) -[2023-10-09 08:17:37,014][23469] Updated weights for policy 1, policy_version 440 (0.0008) -[2023-10-09 08:17:37,271][23468] Updated weights for policy 0, policy_version 440 (0.0007) -[2023-10-09 08:17:41,019][23469] Updated weights for policy 1, policy_version 450 (0.0007) -[2023-10-09 08:17:41,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 12592.8). Total num frames: 917504. Throughput: 0: 1748.9, 1: 1762.9. Samples: 242034. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:17:41,078][22500] Avg episode reward: [(0, '1.650'), (1, '1.660')] -[2023-10-09 08:17:41,103][23468] Updated weights for policy 0, policy_version 450 (0.0010) -[2023-10-09 08:17:41,390][23469] Updated weights for policy 1, policy_version 460 (0.0007) -[2023-10-09 08:17:41,474][23468] Updated weights for policy 0, policy_version 460 (0.0008) -[2023-10-09 08:17:41,750][23469] Updated weights for policy 1, policy_version 470 (0.0007) -[2023-10-09 08:17:41,843][23468] Updated weights for policy 0, policy_version 470 (0.0008) -[2023-10-09 08:17:42,114][23469] Updated weights for policy 1, policy_version 480 (0.0008) -[2023-10-09 08:17:42,207][23468] Updated weights for policy 0, policy_version 480 (0.0009) -[2023-10-09 08:17:46,011][23468] Updated weights for policy 0, policy_version 490 (0.0007) -[2023-10-09 08:17:46,025][23469] Updated weights for policy 1, policy_version 490 (0.0008) -[2023-10-09 08:17:46,077][22500] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 12625.8). Total num frames: 983040. Throughput: 0: 1780.6, 1: 1770.6. Samples: 263706. Policy #0 lag: (min: 1.0, avg: 2.9, max: 28.0) -[2023-10-09 08:17:46,078][22500] Avg episode reward: [(0, '1.660'), (1, '1.810')] -[2023-10-09 08:17:46,374][23468] Updated weights for policy 0, policy_version 500 (0.0009) -[2023-10-09 08:17:46,399][23469] Updated weights for policy 1, policy_version 500 (0.0007) -[2023-10-09 08:17:46,746][23468] Updated weights for policy 0, policy_version 510 (0.0008) -[2023-10-09 08:17:46,770][23469] Updated weights for policy 1, policy_version 510 (0.0007) -[2023-10-09 08:17:46,845][23343] Saving new best policy, reward=1.810! -[2023-10-09 08:17:50,608][23469] Updated weights for policy 1, policy_version 520 (0.0008) -[2023-10-09 08:17:50,626][23468] Updated weights for policy 0, policy_version 520 (0.0007) -[2023-10-09 08:17:50,977][23469] Updated weights for policy 1, policy_version 530 (0.0008) -[2023-10-09 08:17:50,991][23468] Updated weights for policy 0, policy_version 530 (0.0009) -[2023-10-09 08:17:51,077][22500] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12654.9). Total num frames: 1048576. Throughput: 0: 1750.7, 1: 1750.4. Samples: 273380. Policy #0 lag: (min: 26.0, avg: 28.8, max: 58.0) -[2023-10-09 08:17:51,078][22500] Avg episode reward: [(0, '1.830'), (1, '1.740')] -[2023-10-09 08:17:51,345][23469] Updated weights for policy 1, policy_version 540 (0.0007) -[2023-10-09 08:17:51,363][23468] Updated weights for policy 0, policy_version 540 (0.0007) -[2023-10-09 08:17:51,510][23265] Saving new best policy, reward=1.830! -[2023-10-09 08:17:55,174][23468] Updated weights for policy 0, policy_version 550 (0.0007) -[2023-10-09 08:17:55,219][23469] Updated weights for policy 1, policy_version 550 (0.0008) -[2023-10-09 08:17:55,542][23468] Updated weights for policy 0, policy_version 560 (0.0008) -[2023-10-09 08:17:55,585][23469] Updated weights for policy 1, policy_version 560 (0.0009) -[2023-10-09 08:17:55,920][23468] Updated weights for policy 0, policy_version 570 (0.0007) -[2023-10-09 08:17:55,944][23469] Updated weights for policy 1, policy_version 570 (0.0007) -[2023-10-09 08:17:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12680.6). Total num frames: 1114112. Throughput: 0: 1772.7, 1: 1779.1. Samples: 295096. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:17:56,078][22500] Avg episode reward: [(0, '1.800'), (1, '1.870')] -[2023-10-09 08:17:56,171][23343] Saving new best policy, reward=1.870! -[2023-10-09 08:17:59,607][23468] Updated weights for policy 0, policy_version 580 (0.0007) -[2023-10-09 08:17:59,775][23469] Updated weights for policy 1, policy_version 580 (0.0007) -[2023-10-09 08:17:59,966][23468] Updated weights for policy 0, policy_version 590 (0.0007) -[2023-10-09 08:18:00,146][23469] Updated weights for policy 1, policy_version 590 (0.0009) -[2023-10-09 08:18:00,335][23468] Updated weights for policy 0, policy_version 600 (0.0008) -[2023-10-09 08:18:00,513][23469] Updated weights for policy 1, policy_version 600 (0.0007) -[2023-10-09 08:18:01,077][22500] Fps is (10 sec: 19660.5, 60 sec: 14199.4, 300 sec: 13409.4). Total num frames: 1245184. Throughput: 0: 1764.4, 1: 1754.4. Samples: 315080. Policy #0 lag: (min: 17.0, avg: 33.0, max: 49.0) -[2023-10-09 08:18:01,078][22500] Avg episode reward: [(0, '2.110'), (1, '2.290')] -[2023-10-09 08:18:01,087][23265] Saving new best policy, reward=2.110! -[2023-10-09 08:18:01,087][23343] Saving new best policy, reward=2.290! -[2023-10-09 08:18:04,112][23468] Updated weights for policy 0, policy_version 610 (0.0008) -[2023-10-09 08:18:04,219][23469] Updated weights for policy 1, policy_version 610 (0.0009) -[2023-10-09 08:18:04,484][23468] Updated weights for policy 0, policy_version 620 (0.0008) -[2023-10-09 08:18:04,589][23469] Updated weights for policy 1, policy_version 620 (0.0007) -[2023-10-09 08:18:04,856][23468] Updated weights for policy 0, policy_version 630 (0.0009) -[2023-10-09 08:18:04,948][23469] Updated weights for policy 1, policy_version 630 (0.0007) -[2023-10-09 08:18:05,228][23468] Updated weights for policy 0, policy_version 640 (0.0007) -[2023-10-09 08:18:05,319][23469] Updated weights for policy 1, policy_version 640 (0.0008) -[2023-10-09 08:18:06,077][22500] Fps is (10 sec: 19660.5, 60 sec: 14199.4, 300 sec: 13393.9). Total num frames: 1310720. Throughput: 0: 1766.3, 1: 1781.5. Samples: 327040. Policy #0 lag: (min: 28.0, avg: 34.1, max: 60.0) -[2023-10-09 08:18:06,079][22500] Avg episode reward: [(0, '2.160'), (1, '2.270')] -[2023-10-09 08:18:06,080][23265] Saving new best policy, reward=2.160! -[2023-10-09 08:18:09,054][23468] Updated weights for policy 0, policy_version 650 (0.0011) -[2023-10-09 08:18:09,154][23469] Updated weights for policy 1, policy_version 650 (0.0008) -[2023-10-09 08:18:09,428][23468] Updated weights for policy 0, policy_version 660 (0.0008) -[2023-10-09 08:18:09,530][23469] Updated weights for policy 1, policy_version 660 (0.0007) -[2023-10-09 08:18:09,793][23468] Updated weights for policy 0, policy_version 670 (0.0010) -[2023-10-09 08:18:09,894][23469] Updated weights for policy 1, policy_version 670 (0.0008) -[2023-10-09 08:18:11,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13380.0). Total num frames: 1376256. Throughput: 0: 1772.3, 1: 1761.6. Samples: 347430. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-10-09 08:18:11,079][22500] Avg episode reward: [(0, '2.110'), (1, '1.900')] -[2023-10-09 08:18:13,689][23469] Updated weights for policy 1, policy_version 680 (0.0009) -[2023-10-09 08:18:13,798][23468] Updated weights for policy 0, policy_version 680 (0.0009) -[2023-10-09 08:18:14,059][23469] Updated weights for policy 1, policy_version 690 (0.0008) -[2023-10-09 08:18:14,184][23468] Updated weights for policy 0, policy_version 690 (0.0009) -[2023-10-09 08:18:14,425][23469] Updated weights for policy 1, policy_version 700 (0.0007) -[2023-10-09 08:18:14,549][23468] Updated weights for policy 0, policy_version 700 (0.0009) -[2023-10-09 08:18:16,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13367.3). Total num frames: 1441792. Throughput: 0: 1753.3, 1: 1754.0. Samples: 368224. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 08:18:16,078][22500] Avg episode reward: [(0, '2.460'), (1, '2.210')] -[2023-10-09 08:18:16,085][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000000704_720896.pth... -[2023-10-09 08:18:16,085][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000000704_720896.pth... -[2023-10-09 08:18:16,116][23265] Saving new best policy, reward=2.460! -[2023-10-09 08:18:18,164][23469] Updated weights for policy 1, policy_version 710 (0.0009) -[2023-10-09 08:18:18,512][23468] Updated weights for policy 0, policy_version 710 (0.0008) -[2023-10-09 08:18:18,521][23469] Updated weights for policy 1, policy_version 720 (0.0008) -[2023-10-09 08:18:18,886][23468] Updated weights for policy 0, policy_version 720 (0.0007) -[2023-10-09 08:18:18,888][23469] Updated weights for policy 1, policy_version 730 (0.0009) -[2023-10-09 08:18:19,247][23468] Updated weights for policy 0, policy_version 730 (0.0008) -[2023-10-09 08:18:21,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13355.8). Total num frames: 1507328. Throughput: 0: 1784.7, 1: 1768.4. Samples: 379806. Policy #0 lag: (min: 4.0, avg: 11.5, max: 36.0) -[2023-10-09 08:18:21,078][22500] Avg episode reward: [(0, '2.950'), (1, '2.440')] -[2023-10-09 08:18:21,079][23265] Saving new best policy, reward=2.950! -[2023-10-09 08:18:21,079][23343] Saving new best policy, reward=2.440! -[2023-10-09 08:18:22,624][23469] Updated weights for policy 1, policy_version 740 (0.0009) -[2023-10-09 08:18:22,984][23469] Updated weights for policy 1, policy_version 750 (0.0007) -[2023-10-09 08:18:23,053][23468] Updated weights for policy 0, policy_version 740 (0.0009) -[2023-10-09 08:18:23,359][23469] Updated weights for policy 1, policy_version 760 (0.0007) -[2023-10-09 08:18:23,415][23468] Updated weights for policy 0, policy_version 750 (0.0009) -[2023-10-09 08:18:23,782][23468] Updated weights for policy 0, policy_version 760 (0.0009) -[2023-10-09 08:18:26,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13345.3). Total num frames: 1572864. Throughput: 0: 1752.8, 1: 1762.4. Samples: 400216. Policy #0 lag: (min: 31.0, avg: 32.6, max: 59.0) -[2023-10-09 08:18:26,078][22500] Avg episode reward: [(0, '2.690'), (1, '2.430')] -[2023-10-09 08:18:27,195][23469] Updated weights for policy 1, policy_version 770 (0.0008) -[2023-10-09 08:18:27,565][23469] Updated weights for policy 1, policy_version 780 (0.0007) -[2023-10-09 08:18:27,581][23468] Updated weights for policy 0, policy_version 770 (0.0008) -[2023-10-09 08:18:27,943][23469] Updated weights for policy 1, policy_version 790 (0.0008) -[2023-10-09 08:18:27,949][23468] Updated weights for policy 0, policy_version 780 (0.0008) -[2023-10-09 08:18:28,306][23469] Updated weights for policy 1, policy_version 800 (0.0008) -[2023-10-09 08:18:28,331][23468] Updated weights for policy 0, policy_version 790 (0.0008) -[2023-10-09 08:18:28,705][23468] Updated weights for policy 0, policy_version 800 (0.0009) -[2023-10-09 08:18:31,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13335.6). Total num frames: 1638400. Throughput: 0: 1749.6, 1: 1771.3. Samples: 422144. Policy #0 lag: (min: 15.0, avg: 24.6, max: 47.0) -[2023-10-09 08:18:31,078][22500] Avg episode reward: [(0, '2.770'), (1, '2.730')] -[2023-10-09 08:18:31,085][23343] Saving new best policy, reward=2.730! -[2023-10-09 08:18:32,119][23469] Updated weights for policy 1, policy_version 810 (0.0007) -[2023-10-09 08:18:32,478][23469] Updated weights for policy 1, policy_version 820 (0.0007) -[2023-10-09 08:18:32,626][23468] Updated weights for policy 0, policy_version 810 (0.0007) -[2023-10-09 08:18:32,849][23469] Updated weights for policy 1, policy_version 830 (0.0008) -[2023-10-09 08:18:32,991][23468] Updated weights for policy 0, policy_version 820 (0.0009) -[2023-10-09 08:18:33,370][23468] Updated weights for policy 0, policy_version 830 (0.0009) -[2023-10-09 08:18:36,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13326.6). Total num frames: 1703936. Throughput: 0: 1757.3, 1: 1769.0. Samples: 432062. Policy #0 lag: (min: 12.0, avg: 21.6, max: 44.0) -[2023-10-09 08:18:36,078][22500] Avg episode reward: [(0, '2.730'), (1, '2.500')] -[2023-10-09 08:18:36,629][23469] Updated weights for policy 1, policy_version 840 (0.0009) -[2023-10-09 08:18:37,000][23469] Updated weights for policy 1, policy_version 850 (0.0008) -[2023-10-09 08:18:37,098][23468] Updated weights for policy 0, policy_version 840 (0.0007) -[2023-10-09 08:18:37,373][23469] Updated weights for policy 1, policy_version 860 (0.0007) -[2023-10-09 08:18:37,476][23468] Updated weights for policy 0, policy_version 850 (0.0007) -[2023-10-09 08:18:37,850][23468] Updated weights for policy 0, policy_version 860 (0.0008) -[2023-10-09 08:18:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13318.4). Total num frames: 1769472. Throughput: 0: 1756.9, 1: 1775.1. Samples: 454036. Policy #0 lag: (min: 8.0, avg: 29.0, max: 40.0) -[2023-10-09 08:18:41,078][22500] Avg episode reward: [(0, '2.910'), (1, '2.430')] -[2023-10-09 08:18:41,229][23469] Updated weights for policy 1, policy_version 870 (0.0007) -[2023-10-09 08:18:41,593][23469] Updated weights for policy 1, policy_version 880 (0.0007) -[2023-10-09 08:18:41,746][23468] Updated weights for policy 0, policy_version 870 (0.0009) -[2023-10-09 08:18:41,967][23469] Updated weights for policy 1, policy_version 890 (0.0007) -[2023-10-09 08:18:42,114][23468] Updated weights for policy 0, policy_version 880 (0.0007) -[2023-10-09 08:18:42,477][23468] Updated weights for policy 0, policy_version 890 (0.0007) -[2023-10-09 08:18:45,718][23469] Updated weights for policy 1, policy_version 900 (0.0007) -[2023-10-09 08:18:46,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13310.7). Total num frames: 1835008. Throughput: 0: 1781.2, 1: 1797.2. Samples: 476108. Policy #0 lag: (min: 16.0, avg: 44.3, max: 48.0) -[2023-10-09 08:18:46,078][22500] Avg episode reward: [(0, '2.800'), (1, '2.850')] -[2023-10-09 08:18:46,092][23469] Updated weights for policy 1, policy_version 910 (0.0007) -[2023-10-09 08:18:46,247][23468] Updated weights for policy 0, policy_version 900 (0.0008) -[2023-10-09 08:18:46,466][23469] Updated weights for policy 1, policy_version 920 (0.0008) -[2023-10-09 08:18:46,628][23468] Updated weights for policy 0, policy_version 910 (0.0008) -[2023-10-09 08:18:46,763][23343] Saving new best policy, reward=2.850! -[2023-10-09 08:18:46,992][23468] Updated weights for policy 0, policy_version 920 (0.0008) -[2023-10-09 08:18:50,288][23469] Updated weights for policy 1, policy_version 930 (0.0007) -[2023-10-09 08:18:50,655][23469] Updated weights for policy 1, policy_version 940 (0.0007) -[2023-10-09 08:18:50,753][23468] Updated weights for policy 0, policy_version 930 (0.0007) -[2023-10-09 08:18:51,025][23469] Updated weights for policy 1, policy_version 950 (0.0008) -[2023-10-09 08:18:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13303.6). Total num frames: 1900544. Throughput: 0: 1759.3, 1: 1769.3. Samples: 485822. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) -[2023-10-09 08:18:51,078][22500] Avg episode reward: [(0, '2.560'), (1, '2.420')] -[2023-10-09 08:18:51,123][23468] Updated weights for policy 0, policy_version 940 (0.0008) -[2023-10-09 08:18:51,391][23469] Updated weights for policy 1, policy_version 960 (0.0009) -[2023-10-09 08:18:51,497][23468] Updated weights for policy 0, policy_version 950 (0.0007) -[2023-10-09 08:18:51,872][23468] Updated weights for policy 0, policy_version 960 (0.0007) -[2023-10-09 08:18:55,187][23469] Updated weights for policy 1, policy_version 970 (0.0008) -[2023-10-09 08:18:55,499][23468] Updated weights for policy 0, policy_version 970 (0.0009) -[2023-10-09 08:18:55,559][23469] Updated weights for policy 1, policy_version 980 (0.0009) -[2023-10-09 08:18:55,873][23468] Updated weights for policy 0, policy_version 980 (0.0009) -[2023-10-09 08:18:55,941][23469] Updated weights for policy 1, policy_version 990 (0.0010) -[2023-10-09 08:18:56,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 13518.6). Total num frames: 1998848. Throughput: 0: 1776.9, 1: 1796.3. Samples: 508224. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 08:18:56,078][22500] Avg episode reward: [(0, '2.690'), (1, '2.550')] -[2023-10-09 08:18:56,248][23468] Updated weights for policy 0, policy_version 990 (0.0011) -[2023-10-09 08:18:59,848][23469] Updated weights for policy 1, policy_version 1000 (0.0008) -[2023-10-09 08:18:59,935][23468] Updated weights for policy 0, policy_version 1000 (0.0007) -[2023-10-09 08:19:00,226][23469] Updated weights for policy 1, policy_version 1010 (0.0008) -[2023-10-09 08:19:00,307][23468] Updated weights for policy 0, policy_version 1010 (0.0008) -[2023-10-09 08:19:00,599][23469] Updated weights for policy 1, policy_version 1020 (0.0008) -[2023-10-09 08:19:00,680][23468] Updated weights for policy 0, policy_version 1020 (0.0009) -[2023-10-09 08:19:01,078][22500] Fps is (10 sec: 19660.3, 60 sec: 14199.4, 300 sec: 13719.5). Total num frames: 2097152. Throughput: 0: 1786.3, 1: 1769.9. Samples: 528254. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 08:19:01,079][22500] Avg episode reward: [(0, '3.120'), (1, '2.960')] -[2023-10-09 08:19:01,087][23265] Saving new best policy, reward=3.120! -[2023-10-09 08:19:01,087][23343] Saving new best policy, reward=2.960! -[2023-10-09 08:19:04,437][23469] Updated weights for policy 1, policy_version 1030 (0.0008) -[2023-10-09 08:19:04,559][23468] Updated weights for policy 0, policy_version 1030 (0.0009) -[2023-10-09 08:19:04,798][23469] Updated weights for policy 1, policy_version 1040 (0.0008) -[2023-10-09 08:19:04,926][23468] Updated weights for policy 0, policy_version 1040 (0.0007) -[2023-10-09 08:19:05,171][23469] Updated weights for policy 1, policy_version 1050 (0.0008) -[2023-10-09 08:19:05,302][23468] Updated weights for policy 0, policy_version 1050 (0.0007) -[2023-10-09 08:19:06,078][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13700.1). Total num frames: 2162688. Throughput: 0: 1770.5, 1: 1788.6. Samples: 539968. Policy #0 lag: (min: 3.0, avg: 6.3, max: 35.0) -[2023-10-09 08:19:06,079][22500] Avg episode reward: [(0, '2.950'), (1, '2.910')] -[2023-10-09 08:19:08,916][23469] Updated weights for policy 1, policy_version 1060 (0.0010) -[2023-10-09 08:19:09,160][23468] Updated weights for policy 0, policy_version 1060 (0.0009) -[2023-10-09 08:19:09,287][23469] Updated weights for policy 1, policy_version 1070 (0.0008) -[2023-10-09 08:19:09,526][23468] Updated weights for policy 0, policy_version 1070 (0.0009) -[2023-10-09 08:19:09,655][23469] Updated weights for policy 1, policy_version 1080 (0.0008) -[2023-10-09 08:19:09,891][23468] Updated weights for policy 0, policy_version 1080 (0.0009) -[2023-10-09 08:19:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13681.9). Total num frames: 2228224. Throughput: 0: 1793.2, 1: 1769.1. Samples: 560520. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:19:11,078][22500] Avg episode reward: [(0, '3.080'), (1, '2.940')] -[2023-10-09 08:19:13,544][23469] Updated weights for policy 1, policy_version 1090 (0.0008) -[2023-10-09 08:19:13,731][23468] Updated weights for policy 0, policy_version 1090 (0.0007) -[2023-10-09 08:19:13,915][23469] Updated weights for policy 1, policy_version 1100 (0.0010) -[2023-10-09 08:19:14,107][23468] Updated weights for policy 0, policy_version 1100 (0.0009) -[2023-10-09 08:19:14,280][23469] Updated weights for policy 1, policy_version 1110 (0.0008) -[2023-10-09 08:19:14,475][23468] Updated weights for policy 0, policy_version 1110 (0.0008) -[2023-10-09 08:19:14,643][23469] Updated weights for policy 1, policy_version 1120 (0.0008) -[2023-10-09 08:19:14,837][23468] Updated weights for policy 0, policy_version 1120 (0.0007) -[2023-10-09 08:19:16,078][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13664.8). Total num frames: 2293760. Throughput: 0: 1772.4, 1: 1761.2. Samples: 581158. Policy #0 lag: (min: 6.0, avg: 8.7, max: 38.0) -[2023-10-09 08:19:16,079][22500] Avg episode reward: [(0, '3.040'), (1, '2.820')] -[2023-10-09 08:19:18,350][23469] Updated weights for policy 1, policy_version 1130 (0.0009) -[2023-10-09 08:19:18,472][23468] Updated weights for policy 0, policy_version 1130 (0.0008) -[2023-10-09 08:19:18,733][23469] Updated weights for policy 1, policy_version 1140 (0.0009) -[2023-10-09 08:19:18,830][23468] Updated weights for policy 0, policy_version 1140 (0.0011) -[2023-10-09 08:19:19,105][23469] Updated weights for policy 1, policy_version 1150 (0.0008) -[2023-10-09 08:19:19,204][23468] Updated weights for policy 0, policy_version 1150 (0.0007) -[2023-10-09 08:19:21,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13648.6). Total num frames: 2359296. Throughput: 0: 1795.2, 1: 1774.9. Samples: 592714. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) -[2023-10-09 08:19:21,078][22500] Avg episode reward: [(0, '2.920'), (1, '3.180')] -[2023-10-09 08:19:21,080][23343] Saving new best policy, reward=3.180! -[2023-10-09 08:19:22,937][23469] Updated weights for policy 1, policy_version 1160 (0.0008) -[2023-10-09 08:19:22,965][23468] Updated weights for policy 0, policy_version 1160 (0.0008) -[2023-10-09 08:19:23,304][23469] Updated weights for policy 1, policy_version 1170 (0.0009) -[2023-10-09 08:19:23,340][23468] Updated weights for policy 0, policy_version 1170 (0.0007) -[2023-10-09 08:19:23,678][23469] Updated weights for policy 1, policy_version 1180 (0.0009) -[2023-10-09 08:19:23,711][23468] Updated weights for policy 0, policy_version 1180 (0.0008) -[2023-10-09 08:19:26,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13633.4). Total num frames: 2424832. Throughput: 0: 1771.0, 1: 1762.7. Samples: 613052. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:19:26,078][22500] Avg episode reward: [(0, '2.840'), (1, '3.290')] -[2023-10-09 08:19:26,079][23343] Saving new best policy, reward=3.290! -[2023-10-09 08:19:27,506][23468] Updated weights for policy 0, policy_version 1190 (0.0008) -[2023-10-09 08:19:27,547][23469] Updated weights for policy 1, policy_version 1190 (0.0008) -[2023-10-09 08:19:27,882][23468] Updated weights for policy 0, policy_version 1200 (0.0009) -[2023-10-09 08:19:27,923][23469] Updated weights for policy 1, policy_version 1200 (0.0008) -[2023-10-09 08:19:28,251][23468] Updated weights for policy 0, policy_version 1210 (0.0009) -[2023-10-09 08:19:28,292][23469] Updated weights for policy 1, policy_version 1210 (0.0008) -[2023-10-09 08:19:31,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13619.0). Total num frames: 2490368. Throughput: 0: 1767.4, 1: 1762.5. Samples: 634952. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:19:31,078][22500] Avg episode reward: [(0, '3.000'), (1, '3.240')] -[2023-10-09 08:19:32,057][23468] Updated weights for policy 0, policy_version 1220 (0.0007) -[2023-10-09 08:19:32,212][23469] Updated weights for policy 1, policy_version 1220 (0.0008) -[2023-10-09 08:19:32,426][23468] Updated weights for policy 0, policy_version 1230 (0.0008) -[2023-10-09 08:19:32,576][23469] Updated weights for policy 1, policy_version 1230 (0.0007) -[2023-10-09 08:19:32,795][23468] Updated weights for policy 0, policy_version 1240 (0.0007) -[2023-10-09 08:19:32,943][23469] Updated weights for policy 1, policy_version 1240 (0.0007) -[2023-10-09 08:19:36,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13605.4). Total num frames: 2555904. Throughput: 0: 1766.4, 1: 1758.5. Samples: 644442. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:19:36,078][22500] Avg episode reward: [(0, '3.300'), (1, '3.320')] -[2023-10-09 08:19:36,079][23265] Saving new best policy, reward=3.300! -[2023-10-09 08:19:36,079][23343] Saving new best policy, reward=3.320! -[2023-10-09 08:19:36,644][23468] Updated weights for policy 0, policy_version 1250 (0.0008) -[2023-10-09 08:19:36,738][23469] Updated weights for policy 1, policy_version 1250 (0.0009) -[2023-10-09 08:19:37,005][23468] Updated weights for policy 0, policy_version 1260 (0.0008) -[2023-10-09 08:19:37,110][23469] Updated weights for policy 1, policy_version 1260 (0.0007) -[2023-10-09 08:19:37,378][23468] Updated weights for policy 0, policy_version 1270 (0.0009) -[2023-10-09 08:19:37,478][23469] Updated weights for policy 1, policy_version 1270 (0.0007) -[2023-10-09 08:19:37,749][23468] Updated weights for policy 0, policy_version 1280 (0.0009) -[2023-10-09 08:19:37,848][23469] Updated weights for policy 1, policy_version 1280 (0.0008) -[2023-10-09 08:19:41,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13592.5). Total num frames: 2621440. Throughput: 0: 1760.9, 1: 1756.4. Samples: 666504. Policy #0 lag: (min: 31.0, avg: 32.9, max: 61.0) -[2023-10-09 08:19:41,079][22500] Avg episode reward: [(0, '3.580'), (1, '3.510')] -[2023-10-09 08:19:41,080][23265] Saving new best policy, reward=3.580! -[2023-10-09 08:19:41,080][23343] Saving new best policy, reward=3.510! -[2023-10-09 08:19:41,602][23468] Updated weights for policy 0, policy_version 1290 (0.0010) -[2023-10-09 08:19:41,817][23469] Updated weights for policy 1, policy_version 1290 (0.0007) -[2023-10-09 08:19:41,967][23468] Updated weights for policy 0, policy_version 1300 (0.0010) -[2023-10-09 08:19:42,182][23469] Updated weights for policy 1, policy_version 1300 (0.0007) -[2023-10-09 08:19:42,336][23468] Updated weights for policy 0, policy_version 1310 (0.0008) -[2023-10-09 08:19:42,550][23469] Updated weights for policy 1, policy_version 1310 (0.0008) -[2023-10-09 08:19:46,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13580.2). Total num frames: 2686976. Throughput: 0: 1774.5, 1: 1786.5. Samples: 688498. Policy #0 lag: (min: 26.0, avg: 26.1, max: 32.0) -[2023-10-09 08:19:46,078][22500] Avg episode reward: [(0, '3.140'), (1, '3.350')] -[2023-10-09 08:19:46,127][23468] Updated weights for policy 0, policy_version 1320 (0.0007) -[2023-10-09 08:19:46,455][23469] Updated weights for policy 1, policy_version 1320 (0.0007) -[2023-10-09 08:19:46,496][23468] Updated weights for policy 0, policy_version 1330 (0.0008) -[2023-10-09 08:19:46,840][23469] Updated weights for policy 1, policy_version 1330 (0.0008) -[2023-10-09 08:19:46,873][23468] Updated weights for policy 0, policy_version 1340 (0.0008) -[2023-10-09 08:19:47,212][23469] Updated weights for policy 1, policy_version 1340 (0.0007) -[2023-10-09 08:19:50,649][23468] Updated weights for policy 0, policy_version 1350 (0.0008) -[2023-10-09 08:19:51,024][23468] Updated weights for policy 0, policy_version 1360 (0.0008) -[2023-10-09 08:19:51,054][23469] Updated weights for policy 1, policy_version 1350 (0.0007) -[2023-10-09 08:19:51,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13568.6). Total num frames: 2752512. Throughput: 0: 1757.4, 1: 1751.7. Samples: 697876. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-09 08:19:51,078][22500] Avg episode reward: [(0, '3.010'), (1, '3.000')] -[2023-10-09 08:19:51,391][23468] Updated weights for policy 0, policy_version 1370 (0.0008) -[2023-10-09 08:19:51,422][23469] Updated weights for policy 1, policy_version 1360 (0.0008) -[2023-10-09 08:19:51,788][23469] Updated weights for policy 1, policy_version 1370 (0.0008) -[2023-10-09 08:19:55,196][23468] Updated weights for policy 0, policy_version 1380 (0.0009) -[2023-10-09 08:19:55,415][23469] Updated weights for policy 1, policy_version 1380 (0.0008) -[2023-10-09 08:19:55,571][23468] Updated weights for policy 0, policy_version 1390 (0.0007) -[2023-10-09 08:19:55,785][23469] Updated weights for policy 1, policy_version 1390 (0.0008) -[2023-10-09 08:19:55,947][23468] Updated weights for policy 0, policy_version 1400 (0.0007) -[2023-10-09 08:19:56,077][22500] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13557.5). Total num frames: 2818048. Throughput: 0: 1771.6, 1: 1778.5. Samples: 720272. Policy #0 lag: (min: 10.0, avg: 13.2, max: 42.0) -[2023-10-09 08:19:56,078][22500] Avg episode reward: [(0, '3.430'), (1, '3.240')] -[2023-10-09 08:19:56,153][23469] Updated weights for policy 1, policy_version 1400 (0.0008) -[2023-10-09 08:19:59,872][23468] Updated weights for policy 0, policy_version 1410 (0.0007) -[2023-10-09 08:20:00,055][23469] Updated weights for policy 1, policy_version 1410 (0.0010) -[2023-10-09 08:20:00,244][23468] Updated weights for policy 0, policy_version 1420 (0.0008) -[2023-10-09 08:20:00,429][23469] Updated weights for policy 1, policy_version 1420 (0.0008) -[2023-10-09 08:20:00,618][23468] Updated weights for policy 0, policy_version 1430 (0.0007) -[2023-10-09 08:20:00,801][23469] Updated weights for policy 1, policy_version 1430 (0.0008) -[2023-10-09 08:20:00,990][23468] Updated weights for policy 0, policy_version 1440 (0.0009) -[2023-10-09 08:20:01,077][22500] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13700.8). Total num frames: 2916352. Throughput: 0: 1783.1, 1: 1762.5. Samples: 740706. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 08:20:01,078][22500] Avg episode reward: [(0, '3.530'), (1, '3.540')] -[2023-10-09 08:20:01,165][23343] Saving new best policy, reward=3.540! -[2023-10-09 08:20:01,167][23469] Updated weights for policy 1, policy_version 1440 (0.0008) -[2023-10-09 08:20:04,875][23468] Updated weights for policy 0, policy_version 1450 (0.0008) -[2023-10-09 08:20:05,019][23469] Updated weights for policy 1, policy_version 1450 (0.0008) -[2023-10-09 08:20:05,239][23468] Updated weights for policy 0, policy_version 1460 (0.0009) -[2023-10-09 08:20:05,384][23469] Updated weights for policy 1, policy_version 1460 (0.0008) -[2023-10-09 08:20:05,615][23468] Updated weights for policy 0, policy_version 1470 (0.0008) -[2023-10-09 08:20:05,759][23469] Updated weights for policy 1, policy_version 1470 (0.0009) -[2023-10-09 08:20:06,077][22500] Fps is (10 sec: 19660.3, 60 sec: 14199.5, 300 sec: 13837.6). Total num frames: 3014656. Throughput: 0: 1768.0, 1: 1768.8. Samples: 751866. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:20:06,079][22500] Avg episode reward: [(0, '3.370'), (1, '3.730')] -[2023-10-09 08:20:06,080][23343] Saving new best policy, reward=3.730! -[2023-10-09 08:20:09,385][23468] Updated weights for policy 0, policy_version 1480 (0.0007) -[2023-10-09 08:20:09,667][23469] Updated weights for policy 1, policy_version 1480 (0.0008) -[2023-10-09 08:20:09,751][23468] Updated weights for policy 0, policy_version 1490 (0.0007) -[2023-10-09 08:20:10,039][23469] Updated weights for policy 1, policy_version 1490 (0.0008) -[2023-10-09 08:20:10,120][23468] Updated weights for policy 0, policy_version 1500 (0.0008) -[2023-10-09 08:20:10,397][23469] Updated weights for policy 1, policy_version 1500 (0.0008) -[2023-10-09 08:20:11,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13821.2). Total num frames: 3080192. Throughput: 0: 1788.4, 1: 1765.4. Samples: 772974. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 08:20:11,078][22500] Avg episode reward: [(0, '3.370'), (1, '3.700')] -[2023-10-09 08:20:13,944][23468] Updated weights for policy 0, policy_version 1510 (0.0011) -[2023-10-09 08:20:14,241][23469] Updated weights for policy 1, policy_version 1510 (0.0008) -[2023-10-09 08:20:14,307][23468] Updated weights for policy 0, policy_version 1520 (0.0009) -[2023-10-09 08:20:14,599][23469] Updated weights for policy 1, policy_version 1520 (0.0007) -[2023-10-09 08:20:14,673][23468] Updated weights for policy 0, policy_version 1530 (0.0011) -[2023-10-09 08:20:14,974][23469] Updated weights for policy 1, policy_version 1530 (0.0007) -[2023-10-09 08:20:16,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13805.6). Total num frames: 3145728. Throughput: 0: 1757.4, 1: 1745.1. Samples: 792566. Policy #0 lag: (min: 5.0, avg: 7.3, max: 37.0) -[2023-10-09 08:20:16,079][22500] Avg episode reward: [(0, '3.310'), (1, '3.650')] -[2023-10-09 08:20:16,091][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000001536_1572864.pth... -[2023-10-09 08:20:16,091][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000001536_1572864.pth... -[2023-10-09 08:20:18,540][23468] Updated weights for policy 0, policy_version 1540 (0.0009) -[2023-10-09 08:20:18,714][23469] Updated weights for policy 1, policy_version 1540 (0.0008) -[2023-10-09 08:20:18,909][23468] Updated weights for policy 0, policy_version 1550 (0.0009) -[2023-10-09 08:20:19,082][23469] Updated weights for policy 1, policy_version 1550 (0.0008) -[2023-10-09 08:20:19,280][23468] Updated weights for policy 0, policy_version 1560 (0.0008) -[2023-10-09 08:20:19,457][23469] Updated weights for policy 1, policy_version 1560 (0.0008) -[2023-10-09 08:20:21,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13790.6). Total num frames: 3211264. Throughput: 0: 1792.0, 1: 1775.6. Samples: 804984. Policy #0 lag: (min: 17.0, avg: 24.8, max: 49.0) -[2023-10-09 08:20:21,079][22500] Avg episode reward: [(0, '3.560'), (1, '3.610')] -[2023-10-09 08:20:22,988][23468] Updated weights for policy 0, policy_version 1570 (0.0007) -[2023-10-09 08:20:23,233][23469] Updated weights for policy 1, policy_version 1570 (0.0009) -[2023-10-09 08:20:23,358][23468] Updated weights for policy 0, policy_version 1580 (0.0007) -[2023-10-09 08:20:23,603][23469] Updated weights for policy 1, policy_version 1580 (0.0008) -[2023-10-09 08:20:23,723][23468] Updated weights for policy 0, policy_version 1590 (0.0008) -[2023-10-09 08:20:23,973][23469] Updated weights for policy 1, policy_version 1590 (0.0008) -[2023-10-09 08:20:24,102][23468] Updated weights for policy 0, policy_version 1600 (0.0007) -[2023-10-09 08:20:24,346][23469] Updated weights for policy 1, policy_version 1600 (0.0007) -[2023-10-09 08:20:26,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13776.2). Total num frames: 3276800. Throughput: 0: 1760.5, 1: 1752.1. Samples: 824574. Policy #0 lag: (min: 30.0, avg: 31.4, max: 56.0) -[2023-10-09 08:20:26,079][22500] Avg episode reward: [(0, '3.460'), (1, '3.680')] -[2023-10-09 08:20:27,876][23468] Updated weights for policy 0, policy_version 1610 (0.0007) -[2023-10-09 08:20:28,122][23469] Updated weights for policy 1, policy_version 1610 (0.0009) -[2023-10-09 08:20:28,249][23468] Updated weights for policy 0, policy_version 1620 (0.0007) -[2023-10-09 08:20:28,492][23469] Updated weights for policy 1, policy_version 1620 (0.0007) -[2023-10-09 08:20:28,618][23468] Updated weights for policy 0, policy_version 1630 (0.0008) -[2023-10-09 08:20:28,859][23469] Updated weights for policy 1, policy_version 1630 (0.0008) -[2023-10-09 08:20:31,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13762.4). Total num frames: 3342336. Throughput: 0: 1762.7, 1: 1756.7. Samples: 846876. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 08:20:31,078][22500] Avg episode reward: [(0, '3.420'), (1, '3.700')] -[2023-10-09 08:20:32,624][23468] Updated weights for policy 0, policy_version 1640 (0.0008) -[2023-10-09 08:20:32,761][23469] Updated weights for policy 1, policy_version 1640 (0.0007) -[2023-10-09 08:20:33,009][23468] Updated weights for policy 0, policy_version 1650 (0.0009) -[2023-10-09 08:20:33,144][23469] Updated weights for policy 1, policy_version 1650 (0.0008) -[2023-10-09 08:20:33,377][23468] Updated weights for policy 0, policy_version 1660 (0.0007) -[2023-10-09 08:20:33,511][23469] Updated weights for policy 1, policy_version 1660 (0.0008) -[2023-10-09 08:20:36,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13749.2). Total num frames: 3407872. Throughput: 0: 1764.3, 1: 1756.0. Samples: 856288. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-09 08:20:36,078][22500] Avg episode reward: [(0, '3.780'), (1, '3.890')] -[2023-10-09 08:20:36,079][23343] Saving new best policy, reward=3.890! -[2023-10-09 08:20:36,079][23265] Saving new best policy, reward=3.780! -[2023-10-09 08:20:37,118][23468] Updated weights for policy 0, policy_version 1670 (0.0007) -[2023-10-09 08:20:37,168][23469] Updated weights for policy 1, policy_version 1670 (0.0007) -[2023-10-09 08:20:37,483][23468] Updated weights for policy 0, policy_version 1680 (0.0007) -[2023-10-09 08:20:37,533][23469] Updated weights for policy 1, policy_version 1680 (0.0008) -[2023-10-09 08:20:37,849][23468] Updated weights for policy 0, policy_version 1690 (0.0008) -[2023-10-09 08:20:37,901][23469] Updated weights for policy 1, policy_version 1690 (0.0007) -[2023-10-09 08:20:41,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13736.5). Total num frames: 3473408. Throughput: 0: 1752.8, 1: 1759.1. Samples: 878308. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:20:41,078][22500] Avg episode reward: [(0, '3.800'), (1, '3.930')] -[2023-10-09 08:20:41,078][23265] Saving new best policy, reward=3.800! -[2023-10-09 08:20:41,079][23343] Saving new best policy, reward=3.930! -[2023-10-09 08:20:41,631][23469] Updated weights for policy 1, policy_version 1700 (0.0008) -[2023-10-09 08:20:41,699][23468] Updated weights for policy 0, policy_version 1700 (0.0009) -[2023-10-09 08:20:41,996][23469] Updated weights for policy 1, policy_version 1710 (0.0008) -[2023-10-09 08:20:42,075][23468] Updated weights for policy 0, policy_version 1710 (0.0008) -[2023-10-09 08:20:42,369][23469] Updated weights for policy 1, policy_version 1720 (0.0008) -[2023-10-09 08:20:42,437][23468] Updated weights for policy 0, policy_version 1720 (0.0009) -[2023-10-09 08:20:46,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13724.3). Total num frames: 3538944. Throughput: 0: 1765.6, 1: 1787.9. Samples: 900610. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-09 08:20:46,078][22500] Avg episode reward: [(0, '3.900'), (1, '4.060')] -[2023-10-09 08:20:46,084][23265] Saving new best policy, reward=3.900! -[2023-10-09 08:20:46,232][23469] Updated weights for policy 1, policy_version 1730 (0.0008) -[2023-10-09 08:20:46,343][23468] Updated weights for policy 0, policy_version 1730 (0.0008) -[2023-10-09 08:20:46,589][23469] Updated weights for policy 1, policy_version 1740 (0.0009) -[2023-10-09 08:20:46,711][23468] Updated weights for policy 0, policy_version 1740 (0.0008) -[2023-10-09 08:20:46,962][23469] Updated weights for policy 1, policy_version 1750 (0.0007) -[2023-10-09 08:20:47,087][23468] Updated weights for policy 0, policy_version 1750 (0.0009) -[2023-10-09 08:20:47,332][23343] Saving new best policy, reward=4.060! -[2023-10-09 08:20:47,333][23469] Updated weights for policy 1, policy_version 1760 (0.0008) -[2023-10-09 08:20:47,454][23468] Updated weights for policy 0, policy_version 1760 (0.0008) -[2023-10-09 08:20:51,047][23469] Updated weights for policy 1, policy_version 1770 (0.0008) -[2023-10-09 08:20:51,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13712.6). Total num frames: 3604480. Throughput: 0: 1749.6, 1: 1768.1. Samples: 910162. Policy #0 lag: (min: 31.0, avg: 31.8, max: 51.0) -[2023-10-09 08:20:51,079][22500] Avg episode reward: [(0, '3.650'), (1, '3.880')] -[2023-10-09 08:20:51,278][23468] Updated weights for policy 0, policy_version 1770 (0.0007) -[2023-10-09 08:20:51,407][23469] Updated weights for policy 1, policy_version 1780 (0.0009) -[2023-10-09 08:20:51,641][23468] Updated weights for policy 0, policy_version 1780 (0.0008) -[2023-10-09 08:20:51,783][23469] Updated weights for policy 1, policy_version 1790 (0.0009) -[2023-10-09 08:20:52,011][23468] Updated weights for policy 0, policy_version 1790 (0.0007) -[2023-10-09 08:20:55,752][23469] Updated weights for policy 1, policy_version 1800 (0.0008) -[2023-10-09 08:20:55,767][23468] Updated weights for policy 0, policy_version 1800 (0.0008) -[2023-10-09 08:20:56,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13701.3). Total num frames: 3670016. Throughput: 0: 1759.1, 1: 1782.4. Samples: 932340. Policy #0 lag: (min: 8.0, avg: 21.9, max: 40.0) -[2023-10-09 08:20:56,079][22500] Avg episode reward: [(0, '3.720'), (1, '3.950')] -[2023-10-09 08:20:56,119][23469] Updated weights for policy 1, policy_version 1810 (0.0007) -[2023-10-09 08:20:56,148][23468] Updated weights for policy 0, policy_version 1810 (0.0009) -[2023-10-09 08:20:56,488][23469] Updated weights for policy 1, policy_version 1820 (0.0008) -[2023-10-09 08:20:56,520][23468] Updated weights for policy 0, policy_version 1820 (0.0009) -[2023-10-09 08:21:00,125][23469] Updated weights for policy 1, policy_version 1830 (0.0008) -[2023-10-09 08:21:00,308][23468] Updated weights for policy 0, policy_version 1830 (0.0009) -[2023-10-09 08:21:00,494][23469] Updated weights for policy 1, policy_version 1840 (0.0007) -[2023-10-09 08:21:00,667][23468] Updated weights for policy 0, policy_version 1840 (0.0007) -[2023-10-09 08:21:00,868][23469] Updated weights for policy 1, policy_version 1850 (0.0008) -[2023-10-09 08:21:01,046][23468] Updated weights for policy 0, policy_version 1850 (0.0008) -[2023-10-09 08:21:01,077][22500] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13690.4). Total num frames: 3735552. Throughput: 0: 1785.8, 1: 1793.8. Samples: 953648. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:21:01,078][22500] Avg episode reward: [(0, '3.930'), (1, '3.910')] -[2023-10-09 08:21:01,271][23265] Saving new best policy, reward=3.930! -[2023-10-09 08:21:04,526][23469] Updated weights for policy 1, policy_version 1860 (0.0008) -[2023-10-09 08:21:04,885][23469] Updated weights for policy 1, policy_version 1870 (0.0008) -[2023-10-09 08:21:04,897][23468] Updated weights for policy 0, policy_version 1860 (0.0009) -[2023-10-09 08:21:05,258][23469] Updated weights for policy 1, policy_version 1880 (0.0009) -[2023-10-09 08:21:05,267][23468] Updated weights for policy 0, policy_version 1870 (0.0009) -[2023-10-09 08:21:05,628][23468] Updated weights for policy 0, policy_version 1880 (0.0011) -[2023-10-09 08:21:06,077][22500] Fps is (10 sec: 19661.0, 60 sec: 14199.5, 300 sec: 13915.8). Total num frames: 3866624. Throughput: 0: 1760.2, 1: 1788.9. Samples: 964696. Policy #0 lag: (min: 26.0, avg: 26.3, max: 35.0) -[2023-10-09 08:21:06,078][22500] Avg episode reward: [(0, '4.130'), (1, '3.820')] -[2023-10-09 08:21:06,079][23265] Saving new best policy, reward=4.130! -[2023-10-09 08:21:09,078][23469] Updated weights for policy 1, policy_version 1890 (0.0011) -[2023-10-09 08:21:09,426][23468] Updated weights for policy 0, policy_version 1890 (0.0007) -[2023-10-09 08:21:09,441][23469] Updated weights for policy 1, policy_version 1900 (0.0009) -[2023-10-09 08:21:09,794][23468] Updated weights for policy 0, policy_version 1900 (0.0008) -[2023-10-09 08:21:09,806][23469] Updated weights for policy 1, policy_version 1910 (0.0008) -[2023-10-09 08:21:10,159][23468] Updated weights for policy 0, policy_version 1910 (0.0007) -[2023-10-09 08:21:10,180][23469] Updated weights for policy 1, policy_version 1920 (0.0009) -[2023-10-09 08:21:10,535][23468] Updated weights for policy 0, policy_version 1920 (0.0009) -[2023-10-09 08:21:11,077][22500] Fps is (10 sec: 19660.9, 60 sec: 14199.5, 300 sec: 13901.5). Total num frames: 3932160. Throughput: 0: 1796.0, 1: 1790.3. Samples: 985956. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:21:11,078][22500] Avg episode reward: [(0, '3.900'), (1, '3.720')] -[2023-10-09 08:21:14,087][23469] Updated weights for policy 1, policy_version 1930 (0.0008) -[2023-10-09 08:21:14,371][23468] Updated weights for policy 0, policy_version 1930 (0.0008) -[2023-10-09 08:21:14,452][23469] Updated weights for policy 1, policy_version 1940 (0.0009) -[2023-10-09 08:21:14,739][23468] Updated weights for policy 0, policy_version 1940 (0.0009) -[2023-10-09 08:21:14,824][23469] Updated weights for policy 1, policy_version 1950 (0.0009) -[2023-10-09 08:21:15,107][23468] Updated weights for policy 0, policy_version 1950 (0.0009) -[2023-10-09 08:21:16,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13887.7). Total num frames: 3997696. Throughput: 0: 1759.0, 1: 1775.0. Samples: 1005904. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:21:16,078][22500] Avg episode reward: [(0, '3.700'), (1, '3.650')] -[2023-10-09 08:21:18,812][23469] Updated weights for policy 1, policy_version 1960 (0.0008) -[2023-10-09 08:21:18,986][23468] Updated weights for policy 0, policy_version 1960 (0.0008) -[2023-10-09 08:21:19,196][23469] Updated weights for policy 1, policy_version 1970 (0.0008) -[2023-10-09 08:21:19,375][23468] Updated weights for policy 0, policy_version 1970 (0.0009) -[2023-10-09 08:21:19,569][23469] Updated weights for policy 1, policy_version 1980 (0.0008) -[2023-10-09 08:21:19,730][23468] Updated weights for policy 0, policy_version 1980 (0.0008) -[2023-10-09 08:21:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13874.4). Total num frames: 4063232. Throughput: 0: 1793.9, 1: 1799.0. Samples: 1017968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:21:21,078][22500] Avg episode reward: [(0, '3.810'), (1, '3.610')] -[2023-10-09 08:21:23,419][23469] Updated weights for policy 1, policy_version 1990 (0.0008) -[2023-10-09 08:21:23,549][23468] Updated weights for policy 0, policy_version 1990 (0.0009) -[2023-10-09 08:21:23,785][23469] Updated weights for policy 1, policy_version 2000 (0.0007) -[2023-10-09 08:21:23,917][23468] Updated weights for policy 0, policy_version 2000 (0.0009) -[2023-10-09 08:21:24,149][23469] Updated weights for policy 1, policy_version 2010 (0.0007) -[2023-10-09 08:21:24,288][23468] Updated weights for policy 0, policy_version 2010 (0.0009) -[2023-10-09 08:21:26,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 4128768. Throughput: 0: 1771.0, 1: 1764.1. Samples: 1037388. Policy #0 lag: (min: 1.0, avg: 9.1, max: 33.0) -[2023-10-09 08:21:26,078][22500] Avg episode reward: [(0, '3.920'), (1, '3.850')] -[2023-10-09 08:21:27,795][23469] Updated weights for policy 1, policy_version 2020 (0.0007) -[2023-10-09 08:21:28,025][23468] Updated weights for policy 0, policy_version 2020 (0.0008) -[2023-10-09 08:21:28,164][23469] Updated weights for policy 1, policy_version 2030 (0.0007) -[2023-10-09 08:21:28,401][23468] Updated weights for policy 0, policy_version 2030 (0.0008) -[2023-10-09 08:21:28,535][23469] Updated weights for policy 1, policy_version 2040 (0.0007) -[2023-10-09 08:21:28,775][23468] Updated weights for policy 0, policy_version 2040 (0.0007) -[2023-10-09 08:21:31,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 4194304. Throughput: 0: 1762.2, 1: 1761.9. Samples: 1059196. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 08:21:31,078][22500] Avg episode reward: [(0, '4.060'), (1, '3.900')] -[2023-10-09 08:21:32,231][23469] Updated weights for policy 1, policy_version 2050 (0.0008) -[2023-10-09 08:21:32,509][23468] Updated weights for policy 0, policy_version 2050 (0.0008) -[2023-10-09 08:21:32,596][23469] Updated weights for policy 1, policy_version 2060 (0.0007) -[2023-10-09 08:21:32,878][23468] Updated weights for policy 0, policy_version 2060 (0.0007) -[2023-10-09 08:21:32,969][23469] Updated weights for policy 1, policy_version 2070 (0.0007) -[2023-10-09 08:21:33,255][23468] Updated weights for policy 0, policy_version 2070 (0.0009) -[2023-10-09 08:21:33,330][23469] Updated weights for policy 1, policy_version 2080 (0.0007) -[2023-10-09 08:21:33,625][23468] Updated weights for policy 0, policy_version 2080 (0.0008) -[2023-10-09 08:21:36,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 4259840. Throughput: 0: 1778.0, 1: 1760.6. Samples: 1069402. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-09 08:21:36,078][22500] Avg episode reward: [(0, '4.090'), (1, '4.020')] -[2023-10-09 08:21:37,215][23469] Updated weights for policy 1, policy_version 2090 (0.0007) -[2023-10-09 08:21:37,333][23468] Updated weights for policy 0, policy_version 2090 (0.0011) -[2023-10-09 08:21:37,575][23469] Updated weights for policy 1, policy_version 2100 (0.0007) -[2023-10-09 08:21:37,696][23468] Updated weights for policy 0, policy_version 2100 (0.0009) -[2023-10-09 08:21:37,953][23469] Updated weights for policy 1, policy_version 2110 (0.0008) -[2023-10-09 08:21:38,072][23468] Updated weights for policy 0, policy_version 2110 (0.0008) -[2023-10-09 08:21:41,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 4325376. Throughput: 0: 1766.8, 1: 1762.3. Samples: 1091146. Policy #0 lag: (min: 26.0, avg: 26.1, max: 33.0) -[2023-10-09 08:21:41,079][22500] Avg episode reward: [(0, '3.920'), (1, '3.860')] -[2023-10-09 08:21:41,624][23469] Updated weights for policy 1, policy_version 2120 (0.0008) -[2023-10-09 08:21:41,986][23469] Updated weights for policy 1, policy_version 2130 (0.0007) -[2023-10-09 08:21:41,989][23468] Updated weights for policy 0, policy_version 2120 (0.0007) -[2023-10-09 08:21:42,345][23469] Updated weights for policy 1, policy_version 2140 (0.0007) -[2023-10-09 08:21:42,367][23468] Updated weights for policy 0, policy_version 2130 (0.0007) -[2023-10-09 08:21:42,736][23468] Updated weights for policy 0, policy_version 2140 (0.0007) -[2023-10-09 08:21:46,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 4390912. Throughput: 0: 1771.3, 1: 1780.7. Samples: 1113486. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 08:21:46,079][22500] Avg episode reward: [(0, '4.100'), (1, '3.680')] -[2023-10-09 08:21:46,203][23469] Updated weights for policy 1, policy_version 2150 (0.0009) -[2023-10-09 08:21:46,462][23468] Updated weights for policy 0, policy_version 2150 (0.0007) -[2023-10-09 08:21:46,576][23469] Updated weights for policy 1, policy_version 2160 (0.0007) -[2023-10-09 08:21:46,833][23468] Updated weights for policy 0, policy_version 2160 (0.0008) -[2023-10-09 08:21:46,947][23469] Updated weights for policy 1, policy_version 2170 (0.0009) -[2023-10-09 08:21:47,209][23468] Updated weights for policy 0, policy_version 2170 (0.0007) -[2023-10-09 08:21:50,855][23469] Updated weights for policy 1, policy_version 2180 (0.0008) -[2023-10-09 08:21:51,047][23468] Updated weights for policy 0, policy_version 2180 (0.0008) -[2023-10-09 08:21:51,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 4456448. Throughput: 0: 1766.2, 1: 1753.4. Samples: 1123078. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:21:51,078][22500] Avg episode reward: [(0, '4.020'), (1, '4.010')] -[2023-10-09 08:21:51,226][23469] Updated weights for policy 1, policy_version 2190 (0.0008) -[2023-10-09 08:21:51,417][23468] Updated weights for policy 0, policy_version 2190 (0.0008) -[2023-10-09 08:21:51,600][23469] Updated weights for policy 1, policy_version 2200 (0.0008) -[2023-10-09 08:21:51,790][23468] Updated weights for policy 0, policy_version 2200 (0.0008) -[2023-10-09 08:21:55,483][23469] Updated weights for policy 1, policy_version 2210 (0.0009) -[2023-10-09 08:21:55,548][23468] Updated weights for policy 0, policy_version 2210 (0.0008) -[2023-10-09 08:21:55,858][23469] Updated weights for policy 1, policy_version 2220 (0.0008) -[2023-10-09 08:21:55,917][23468] Updated weights for policy 0, policy_version 2220 (0.0007) -[2023-10-09 08:21:56,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 4521984. Throughput: 0: 1764.3, 1: 1770.8. Samples: 1145038. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 08:21:56,078][22500] Avg episode reward: [(0, '4.010'), (1, '4.040')] -[2023-10-09 08:21:56,230][23469] Updated weights for policy 1, policy_version 2230 (0.0007) -[2023-10-09 08:21:56,293][23468] Updated weights for policy 0, policy_version 2230 (0.0008) -[2023-10-09 08:21:56,595][23469] Updated weights for policy 1, policy_version 2240 (0.0007) -[2023-10-09 08:21:56,665][23468] Updated weights for policy 0, policy_version 2240 (0.0008) -[2023-10-09 08:22:00,352][23469] Updated weights for policy 1, policy_version 2250 (0.0008) -[2023-10-09 08:22:00,459][23468] Updated weights for policy 0, policy_version 2250 (0.0008) -[2023-10-09 08:22:00,729][23469] Updated weights for policy 1, policy_version 2260 (0.0008) -[2023-10-09 08:22:00,830][23468] Updated weights for policy 0, policy_version 2260 (0.0008) -[2023-10-09 08:22:01,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 4587520. Throughput: 0: 1793.7, 1: 1768.8. Samples: 1166216. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-09 08:22:01,078][22500] Avg episode reward: [(0, '4.060'), (1, '4.020')] -[2023-10-09 08:22:01,095][23469] Updated weights for policy 1, policy_version 2270 (0.0007) -[2023-10-09 08:22:01,206][23468] Updated weights for policy 0, policy_version 2270 (0.0008) -[2023-10-09 08:22:05,090][23469] Updated weights for policy 1, policy_version 2280 (0.0007) -[2023-10-09 08:22:05,099][23468] Updated weights for policy 0, policy_version 2280 (0.0010) -[2023-10-09 08:22:05,472][23469] Updated weights for policy 1, policy_version 2290 (0.0007) -[2023-10-09 08:22:05,482][23468] Updated weights for policy 0, policy_version 2290 (0.0008) -[2023-10-09 08:22:05,832][23469] Updated weights for policy 1, policy_version 2300 (0.0008) -[2023-10-09 08:22:05,846][23468] Updated weights for policy 0, policy_version 2300 (0.0009) -[2023-10-09 08:22:06,077][22500] Fps is (10 sec: 19660.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 4718592. Throughput: 0: 1765.0, 1: 1767.2. Samples: 1176920. Policy #0 lag: (min: 9.0, avg: 21.6, max: 41.0) -[2023-10-09 08:22:06,079][22500] Avg episode reward: [(0, '3.790'), (1, '3.810')] -[2023-10-09 08:22:09,590][23468] Updated weights for policy 0, policy_version 2310 (0.0007) -[2023-10-09 08:22:09,713][23469] Updated weights for policy 1, policy_version 2310 (0.0008) -[2023-10-09 08:22:09,954][23468] Updated weights for policy 0, policy_version 2320 (0.0008) -[2023-10-09 08:22:10,072][23469] Updated weights for policy 1, policy_version 2320 (0.0008) -[2023-10-09 08:22:10,327][23468] Updated weights for policy 0, policy_version 2330 (0.0009) -[2023-10-09 08:22:10,441][23469] Updated weights for policy 1, policy_version 2330 (0.0007) -[2023-10-09 08:22:11,077][22500] Fps is (10 sec: 19660.6, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 4784128. Throughput: 0: 1791.7, 1: 1784.2. Samples: 1198302. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:22:11,079][22500] Avg episode reward: [(0, '3.910'), (1, '3.950')] -[2023-10-09 08:22:14,145][23468] Updated weights for policy 0, policy_version 2340 (0.0009) -[2023-10-09 08:22:14,332][23469] Updated weights for policy 1, policy_version 2340 (0.0007) -[2023-10-09 08:22:14,520][23468] Updated weights for policy 0, policy_version 2350 (0.0007) -[2023-10-09 08:22:14,697][23469] Updated weights for policy 1, policy_version 2350 (0.0008) -[2023-10-09 08:22:14,886][23468] Updated weights for policy 0, policy_version 2360 (0.0008) -[2023-10-09 08:22:15,073][23469] Updated weights for policy 1, policy_version 2360 (0.0010) -[2023-10-09 08:22:16,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 4849664. Throughput: 0: 1769.1, 1: 1753.9. Samples: 1217730. Policy #0 lag: (min: 14.0, avg: 16.9, max: 46.0) -[2023-10-09 08:22:16,078][22500] Avg episode reward: [(0, '3.910'), (1, '4.030')] -[2023-10-09 08:22:16,088][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000002368_2424832.pth... -[2023-10-09 08:22:16,088][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000002368_2424832.pth... -[2023-10-09 08:22:16,123][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000000704_720896.pth -[2023-10-09 08:22:16,132][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000000704_720896.pth -[2023-10-09 08:22:18,755][23468] Updated weights for policy 0, policy_version 2370 (0.0008) -[2023-10-09 08:22:18,794][23469] Updated weights for policy 1, policy_version 2370 (0.0009) -[2023-10-09 08:22:19,119][23468] Updated weights for policy 0, policy_version 2380 (0.0008) -[2023-10-09 08:22:19,161][23469] Updated weights for policy 1, policy_version 2380 (0.0008) -[2023-10-09 08:22:19,495][23468] Updated weights for policy 0, policy_version 2390 (0.0007) -[2023-10-09 08:22:19,544][23469] Updated weights for policy 1, policy_version 2390 (0.0008) -[2023-10-09 08:22:19,864][23468] Updated weights for policy 0, policy_version 2400 (0.0008) -[2023-10-09 08:22:19,913][23469] Updated weights for policy 1, policy_version 2400 (0.0009) -[2023-10-09 08:22:21,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 4915200. Throughput: 0: 1785.1, 1: 1789.3. Samples: 1230248. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:22:21,078][22500] Avg episode reward: [(0, '4.130'), (1, '4.480')] -[2023-10-09 08:22:21,078][23343] Saving new best policy, reward=4.480! -[2023-10-09 08:22:23,546][23469] Updated weights for policy 1, policy_version 2410 (0.0010) -[2023-10-09 08:22:23,598][23468] Updated weights for policy 0, policy_version 2410 (0.0007) -[2023-10-09 08:22:23,916][23469] Updated weights for policy 1, policy_version 2420 (0.0008) -[2023-10-09 08:22:23,963][23468] Updated weights for policy 0, policy_version 2420 (0.0009) -[2023-10-09 08:22:24,293][23469] Updated weights for policy 1, policy_version 2430 (0.0007) -[2023-10-09 08:22:24,337][23468] Updated weights for policy 0, policy_version 2430 (0.0008) -[2023-10-09 08:22:26,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 4980736. Throughput: 0: 1763.3, 1: 1760.8. Samples: 1249730. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:22:26,078][22500] Avg episode reward: [(0, '4.080'), (1, '4.280')] -[2023-10-09 08:22:27,898][23469] Updated weights for policy 1, policy_version 2440 (0.0008) -[2023-10-09 08:22:28,182][23468] Updated weights for policy 0, policy_version 2440 (0.0011) -[2023-10-09 08:22:28,259][23469] Updated weights for policy 1, policy_version 2450 (0.0007) -[2023-10-09 08:22:28,561][23468] Updated weights for policy 0, policy_version 2450 (0.0007) -[2023-10-09 08:22:28,630][23469] Updated weights for policy 1, policy_version 2460 (0.0009) -[2023-10-09 08:22:28,922][23468] Updated weights for policy 0, policy_version 2460 (0.0008) -[2023-10-09 08:22:31,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 5046272. Throughput: 0: 1752.4, 1: 1763.9. Samples: 1271718. Policy #0 lag: (min: 31.0, avg: 41.7, max: 63.0) -[2023-10-09 08:22:31,078][22500] Avg episode reward: [(0, '4.190'), (1, '3.990')] -[2023-10-09 08:22:31,089][23265] Saving new best policy, reward=4.190! -[2023-10-09 08:22:32,416][23469] Updated weights for policy 1, policy_version 2470 (0.0010) -[2023-10-09 08:22:32,785][23469] Updated weights for policy 1, policy_version 2480 (0.0009) -[2023-10-09 08:22:32,865][23468] Updated weights for policy 0, policy_version 2470 (0.0008) -[2023-10-09 08:22:33,147][23469] Updated weights for policy 1, policy_version 2490 (0.0008) -[2023-10-09 08:22:33,234][23468] Updated weights for policy 0, policy_version 2480 (0.0008) -[2023-10-09 08:22:33,611][23468] Updated weights for policy 0, policy_version 2490 (0.0009) -[2023-10-09 08:22:36,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 5111808. Throughput: 0: 1764.9, 1: 1766.8. Samples: 1282006. Policy #0 lag: (min: 21.0, avg: 27.0, max: 53.0) -[2023-10-09 08:22:36,078][22500] Avg episode reward: [(0, '4.080'), (1, '4.090')] -[2023-10-09 08:22:36,938][23469] Updated weights for policy 1, policy_version 2500 (0.0007) -[2023-10-09 08:22:37,304][23469] Updated weights for policy 1, policy_version 2510 (0.0008) -[2023-10-09 08:22:37,380][23468] Updated weights for policy 0, policy_version 2500 (0.0009) -[2023-10-09 08:22:37,676][23469] Updated weights for policy 1, policy_version 2520 (0.0007) -[2023-10-09 08:22:37,749][23468] Updated weights for policy 0, policy_version 2510 (0.0008) -[2023-10-09 08:22:38,126][23468] Updated weights for policy 0, policy_version 2520 (0.0007) -[2023-10-09 08:22:41,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 5177344. Throughput: 0: 1751.6, 1: 1776.8. Samples: 1303818. Policy #0 lag: (min: 18.0, avg: 18.6, max: 35.0) -[2023-10-09 08:22:41,078][22500] Avg episode reward: [(0, '4.040'), (1, '4.110')] -[2023-10-09 08:22:41,406][23469] Updated weights for policy 1, policy_version 2530 (0.0007) -[2023-10-09 08:22:41,739][23468] Updated weights for policy 0, policy_version 2530 (0.0009) -[2023-10-09 08:22:41,779][23469] Updated weights for policy 1, policy_version 2540 (0.0008) -[2023-10-09 08:22:42,108][23468] Updated weights for policy 0, policy_version 2540 (0.0009) -[2023-10-09 08:22:42,148][23469] Updated weights for policy 1, policy_version 2550 (0.0007) -[2023-10-09 08:22:42,475][23468] Updated weights for policy 0, policy_version 2550 (0.0008) -[2023-10-09 08:22:42,520][23469] Updated weights for policy 1, policy_version 2560 (0.0007) -[2023-10-09 08:22:42,851][23468] Updated weights for policy 0, policy_version 2560 (0.0009) -[2023-10-09 08:22:46,078][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 5242880. Throughput: 0: 1760.5, 1: 1798.3. Samples: 1326360. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:22:46,079][22500] Avg episode reward: [(0, '4.070'), (1, '4.040')] -[2023-10-09 08:22:46,257][23469] Updated weights for policy 1, policy_version 2570 (0.0010) -[2023-10-09 08:22:46,622][23469] Updated weights for policy 1, policy_version 2580 (0.0008) -[2023-10-09 08:22:46,745][23468] Updated weights for policy 0, policy_version 2570 (0.0009) -[2023-10-09 08:22:46,998][23469] Updated weights for policy 1, policy_version 2590 (0.0009) -[2023-10-09 08:22:47,126][23468] Updated weights for policy 0, policy_version 2580 (0.0009) -[2023-10-09 08:22:47,492][23468] Updated weights for policy 0, policy_version 2590 (0.0008) -[2023-10-09 08:22:50,879][23469] Updated weights for policy 1, policy_version 2600 (0.0008) -[2023-10-09 08:22:51,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 5308416. Throughput: 0: 1751.6, 1: 1780.6. Samples: 1335870. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-09 08:22:51,078][22500] Avg episode reward: [(0, '4.030'), (1, '4.010')] -[2023-10-09 08:22:51,257][23469] Updated weights for policy 1, policy_version 2610 (0.0009) -[2023-10-09 08:22:51,444][23468] Updated weights for policy 0, policy_version 2600 (0.0007) -[2023-10-09 08:22:51,614][23469] Updated weights for policy 1, policy_version 2620 (0.0007) -[2023-10-09 08:22:51,812][23468] Updated weights for policy 0, policy_version 2610 (0.0008) -[2023-10-09 08:22:52,185][23468] Updated weights for policy 0, policy_version 2620 (0.0008) -[2023-10-09 08:22:55,278][23469] Updated weights for policy 1, policy_version 2630 (0.0008) -[2023-10-09 08:22:55,656][23469] Updated weights for policy 1, policy_version 2640 (0.0007) -[2023-10-09 08:22:55,921][23468] Updated weights for policy 0, policy_version 2630 (0.0008) -[2023-10-09 08:22:56,024][23469] Updated weights for policy 1, policy_version 2650 (0.0007) -[2023-10-09 08:22:56,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 5373952. Throughput: 0: 1752.9, 1: 1794.3. Samples: 1357924. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-09 08:22:56,078][22500] Avg episode reward: [(0, '4.110'), (1, '3.740')] -[2023-10-09 08:22:56,297][23468] Updated weights for policy 0, policy_version 2640 (0.0008) -[2023-10-09 08:22:56,659][23468] Updated weights for policy 0, policy_version 2650 (0.0009) -[2023-10-09 08:22:59,796][23469] Updated weights for policy 1, policy_version 2660 (0.0008) -[2023-10-09 08:23:00,164][23469] Updated weights for policy 1, policy_version 2670 (0.0010) -[2023-10-09 08:23:00,365][23468] Updated weights for policy 0, policy_version 2660 (0.0008) -[2023-10-09 08:23:00,538][23469] Updated weights for policy 1, policy_version 2680 (0.0008) -[2023-10-09 08:23:00,743][23468] Updated weights for policy 0, policy_version 2670 (0.0009) -[2023-10-09 08:23:01,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14106.9). Total num frames: 5472256. Throughput: 0: 1783.7, 1: 1798.7. Samples: 1378938. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-09 08:23:01,078][22500] Avg episode reward: [(0, '4.200'), (1, '3.830')] -[2023-10-09 08:23:01,110][23468] Updated weights for policy 0, policy_version 2680 (0.0009) -[2023-10-09 08:23:01,413][23265] Saving new best policy, reward=4.200! -[2023-10-09 08:23:04,249][23469] Updated weights for policy 1, policy_version 2690 (0.0007) -[2023-10-09 08:23:04,623][23469] Updated weights for policy 1, policy_version 2700 (0.0007) -[2023-10-09 08:23:04,850][23468] Updated weights for policy 0, policy_version 2690 (0.0007) -[2023-10-09 08:23:04,989][23469] Updated weights for policy 1, policy_version 2710 (0.0007) -[2023-10-09 08:23:05,210][23468] Updated weights for policy 0, policy_version 2700 (0.0008) -[2023-10-09 08:23:05,358][23469] Updated weights for policy 1, policy_version 2720 (0.0008) -[2023-10-09 08:23:05,580][23468] Updated weights for policy 0, policy_version 2710 (0.0011) -[2023-10-09 08:23:05,947][23468] Updated weights for policy 0, policy_version 2720 (0.0007) -[2023-10-09 08:23:06,077][22500] Fps is (10 sec: 19660.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 5570560. Throughput: 0: 1753.6, 1: 1795.3. Samples: 1389950. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:23:06,078][22500] Avg episode reward: [(0, '4.280'), (1, '3.980')] -[2023-10-09 08:23:06,079][23265] Saving new best policy, reward=4.280! -[2023-10-09 08:23:09,181][23469] Updated weights for policy 1, policy_version 2730 (0.0008) -[2023-10-09 08:23:09,551][23469] Updated weights for policy 1, policy_version 2740 (0.0009) -[2023-10-09 08:23:09,806][23468] Updated weights for policy 0, policy_version 2730 (0.0009) -[2023-10-09 08:23:09,923][23469] Updated weights for policy 1, policy_version 2750 (0.0007) -[2023-10-09 08:23:10,186][23468] Updated weights for policy 0, policy_version 2740 (0.0009) -[2023-10-09 08:23:10,559][23468] Updated weights for policy 0, policy_version 2750 (0.0009) -[2023-10-09 08:23:11,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 5636096. Throughput: 0: 1791.1, 1: 1798.8. Samples: 1411274. Policy #0 lag: (min: 15.0, avg: 18.8, max: 47.0) -[2023-10-09 08:23:11,078][22500] Avg episode reward: [(0, '4.180'), (1, '4.010')] -[2023-10-09 08:23:13,724][23469] Updated weights for policy 1, policy_version 2760 (0.0010) -[2023-10-09 08:23:14,096][23469] Updated weights for policy 1, policy_version 2770 (0.0010) -[2023-10-09 08:23:14,335][23468] Updated weights for policy 0, policy_version 2760 (0.0008) -[2023-10-09 08:23:14,473][23469] Updated weights for policy 1, policy_version 2780 (0.0008) -[2023-10-09 08:23:14,712][23468] Updated weights for policy 0, policy_version 2770 (0.0008) -[2023-10-09 08:23:15,092][23468] Updated weights for policy 0, policy_version 2780 (0.0011) -[2023-10-09 08:23:16,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 5701632. Throughput: 0: 1767.5, 1: 1789.1. Samples: 1431764. Policy #0 lag: (min: 25.0, avg: 31.0, max: 57.0) -[2023-10-09 08:23:16,079][22500] Avg episode reward: [(0, '4.270'), (1, '4.120')] -[2023-10-09 08:23:18,180][23469] Updated weights for policy 1, policy_version 2790 (0.0008) -[2023-10-09 08:23:18,546][23469] Updated weights for policy 1, policy_version 2800 (0.0008) -[2023-10-09 08:23:18,854][23468] Updated weights for policy 0, policy_version 2790 (0.0012) -[2023-10-09 08:23:18,924][23469] Updated weights for policy 1, policy_version 2810 (0.0008) -[2023-10-09 08:23:19,228][23468] Updated weights for policy 0, policy_version 2800 (0.0008) -[2023-10-09 08:23:19,599][23468] Updated weights for policy 0, policy_version 2810 (0.0009) -[2023-10-09 08:23:21,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 5767168. Throughput: 0: 1788.9, 1: 1798.6. Samples: 1443442. Policy #0 lag: (min: 19.0, avg: 24.2, max: 51.0) -[2023-10-09 08:23:21,078][22500] Avg episode reward: [(0, '4.210'), (1, '4.200')] -[2023-10-09 08:23:22,682][23469] Updated weights for policy 1, policy_version 2820 (0.0009) -[2023-10-09 08:23:23,056][23469] Updated weights for policy 1, policy_version 2830 (0.0008) -[2023-10-09 08:23:23,415][23469] Updated weights for policy 1, policy_version 2840 (0.0007) -[2023-10-09 08:23:23,455][23468] Updated weights for policy 0, policy_version 2820 (0.0008) -[2023-10-09 08:23:23,822][23468] Updated weights for policy 0, policy_version 2830 (0.0008) -[2023-10-09 08:23:24,195][23468] Updated weights for policy 0, policy_version 2840 (0.0011) -[2023-10-09 08:23:26,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 5832704. Throughput: 0: 1777.7, 1: 1784.2. Samples: 1464104. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-09 08:23:26,078][22500] Avg episode reward: [(0, '4.370'), (1, '4.260')] -[2023-10-09 08:23:26,078][23265] Saving new best policy, reward=4.370! -[2023-10-09 08:23:27,279][23469] Updated weights for policy 1, policy_version 2850 (0.0008) -[2023-10-09 08:23:27,653][23469] Updated weights for policy 1, policy_version 2860 (0.0010) -[2023-10-09 08:23:27,988][23468] Updated weights for policy 0, policy_version 2850 (0.0010) -[2023-10-09 08:23:28,030][23469] Updated weights for policy 1, policy_version 2870 (0.0009) -[2023-10-09 08:23:28,347][23468] Updated weights for policy 0, policy_version 2860 (0.0008) -[2023-10-09 08:23:28,400][23469] Updated weights for policy 1, policy_version 2880 (0.0008) -[2023-10-09 08:23:28,718][23468] Updated weights for policy 0, policy_version 2870 (0.0007) -[2023-10-09 08:23:29,087][23468] Updated weights for policy 0, policy_version 2880 (0.0007) -[2023-10-09 08:23:31,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 5898240. Throughput: 0: 1770.4, 1: 1776.6. Samples: 1485976. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-09 08:23:31,079][22500] Avg episode reward: [(0, '4.180'), (1, '4.110')] -[2023-10-09 08:23:32,275][23469] Updated weights for policy 1, policy_version 2890 (0.0009) -[2023-10-09 08:23:32,645][23469] Updated weights for policy 1, policy_version 2900 (0.0007) -[2023-10-09 08:23:32,764][23468] Updated weights for policy 0, policy_version 2890 (0.0009) -[2023-10-09 08:23:33,010][23469] Updated weights for policy 1, policy_version 2910 (0.0008) -[2023-10-09 08:23:33,145][23468] Updated weights for policy 0, policy_version 2900 (0.0008) -[2023-10-09 08:23:33,510][23468] Updated weights for policy 0, policy_version 2910 (0.0008) -[2023-10-09 08:23:36,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 5963776. Throughput: 0: 1783.2, 1: 1777.7. Samples: 1496108. Policy #0 lag: (min: 15.0, avg: 22.1, max: 47.0) -[2023-10-09 08:23:36,078][22500] Avg episode reward: [(0, '4.040'), (1, '3.920')] -[2023-10-09 08:23:36,942][23469] Updated weights for policy 1, policy_version 2920 (0.0010) -[2023-10-09 08:23:37,318][23469] Updated weights for policy 1, policy_version 2930 (0.0008) -[2023-10-09 08:23:37,493][23468] Updated weights for policy 0, policy_version 2920 (0.0008) -[2023-10-09 08:23:37,688][23469] Updated weights for policy 1, policy_version 2940 (0.0007) -[2023-10-09 08:23:37,870][23468] Updated weights for policy 0, policy_version 2930 (0.0008) -[2023-10-09 08:23:38,233][23468] Updated weights for policy 0, policy_version 2940 (0.0008) -[2023-10-09 08:23:41,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 6029312. Throughput: 0: 1771.7, 1: 1777.5. Samples: 1517636. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 08:23:41,078][22500] Avg episode reward: [(0, '3.990'), (1, '3.930')] -[2023-10-09 08:23:41,442][23469] Updated weights for policy 1, policy_version 2950 (0.0007) -[2023-10-09 08:23:41,806][23469] Updated weights for policy 1, policy_version 2960 (0.0007) -[2023-10-09 08:23:42,006][23468] Updated weights for policy 0, policy_version 2950 (0.0008) -[2023-10-09 08:23:42,183][23469] Updated weights for policy 1, policy_version 2970 (0.0007) -[2023-10-09 08:23:42,379][23468] Updated weights for policy 0, policy_version 2960 (0.0007) -[2023-10-09 08:23:42,743][23468] Updated weights for policy 0, policy_version 2970 (0.0007) -[2023-10-09 08:23:45,916][23469] Updated weights for policy 1, policy_version 2980 (0.0007) -[2023-10-09 08:23:46,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 6094848. Throughput: 0: 1775.7, 1: 1803.0. Samples: 1539982. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:23:46,078][22500] Avg episode reward: [(0, '4.050'), (1, '4.180')] -[2023-10-09 08:23:46,279][23469] Updated weights for policy 1, policy_version 2990 (0.0007) -[2023-10-09 08:23:46,502][23468] Updated weights for policy 0, policy_version 2980 (0.0009) -[2023-10-09 08:23:46,650][23469] Updated weights for policy 1, policy_version 3000 (0.0009) -[2023-10-09 08:23:46,873][23468] Updated weights for policy 0, policy_version 2990 (0.0007) -[2023-10-09 08:23:47,242][23468] Updated weights for policy 0, policy_version 3000 (0.0009) -[2023-10-09 08:23:50,441][23469] Updated weights for policy 1, policy_version 3010 (0.0009) -[2023-10-09 08:23:50,807][23469] Updated weights for policy 1, policy_version 3020 (0.0010) -[2023-10-09 08:23:51,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 6160384. Throughput: 0: 1773.9, 1: 1771.1. Samples: 1549474. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:23:51,078][22500] Avg episode reward: [(0, '3.950'), (1, '4.170')] -[2023-10-09 08:23:51,179][23469] Updated weights for policy 1, policy_version 3030 (0.0010) -[2023-10-09 08:23:51,202][23468] Updated weights for policy 0, policy_version 3010 (0.0010) -[2023-10-09 08:23:51,542][23469] Updated weights for policy 1, policy_version 3040 (0.0008) -[2023-10-09 08:23:51,570][23468] Updated weights for policy 0, policy_version 3020 (0.0008) -[2023-10-09 08:23:51,942][23468] Updated weights for policy 0, policy_version 3030 (0.0007) -[2023-10-09 08:23:52,309][23468] Updated weights for policy 0, policy_version 3040 (0.0008) -[2023-10-09 08:23:55,223][23469] Updated weights for policy 1, policy_version 3050 (0.0007) -[2023-10-09 08:23:55,592][23469] Updated weights for policy 1, policy_version 3060 (0.0009) -[2023-10-09 08:23:55,962][23469] Updated weights for policy 1, policy_version 3070 (0.0008) -[2023-10-09 08:23:56,042][23468] Updated weights for policy 0, policy_version 3050 (0.0007) -[2023-10-09 08:23:56,078][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.5, 300 sec: 14106.9). Total num frames: 6258688. Throughput: 0: 1767.1, 1: 1799.8. Samples: 1571782. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:23:56,079][22500] Avg episode reward: [(0, '4.030'), (1, '3.970')] -[2023-10-09 08:23:56,409][23468] Updated weights for policy 0, policy_version 3060 (0.0007) -[2023-10-09 08:23:56,777][23468] Updated weights for policy 0, policy_version 3070 (0.0009) -[2023-10-09 08:23:59,621][23469] Updated weights for policy 1, policy_version 3080 (0.0008) -[2023-10-09 08:23:59,998][23469] Updated weights for policy 1, policy_version 3090 (0.0007) -[2023-10-09 08:24:00,368][23469] Updated weights for policy 1, policy_version 3100 (0.0007) -[2023-10-09 08:24:00,497][23468] Updated weights for policy 0, policy_version 3080 (0.0008) -[2023-10-09 08:24:00,873][23468] Updated weights for policy 0, policy_version 3090 (0.0009) -[2023-10-09 08:24:01,078][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 6324224. Throughput: 0: 1800.2, 1: 1775.0. Samples: 1592648. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:24:01,079][22500] Avg episode reward: [(0, '4.130'), (1, '4.270')] -[2023-10-09 08:24:01,248][23468] Updated weights for policy 0, policy_version 3100 (0.0008) -[2023-10-09 08:24:04,190][23469] Updated weights for policy 1, policy_version 3110 (0.0008) -[2023-10-09 08:24:04,557][23469] Updated weights for policy 1, policy_version 3120 (0.0007) -[2023-10-09 08:24:04,874][23468] Updated weights for policy 0, policy_version 3110 (0.0009) -[2023-10-09 08:24:04,930][23469] Updated weights for policy 1, policy_version 3130 (0.0008) -[2023-10-09 08:24:05,247][23468] Updated weights for policy 0, policy_version 3120 (0.0007) -[2023-10-09 08:24:05,607][23468] Updated weights for policy 0, policy_version 3130 (0.0008) -[2023-10-09 08:24:06,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 6422528. Throughput: 0: 1767.7, 1: 1800.3. Samples: 1604002. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-09 08:24:06,079][22500] Avg episode reward: [(0, '4.250'), (1, '4.420')] -[2023-10-09 08:24:08,582][23469] Updated weights for policy 1, policy_version 3140 (0.0008) -[2023-10-09 08:24:08,954][23469] Updated weights for policy 1, policy_version 3150 (0.0007) -[2023-10-09 08:24:09,329][23469] Updated weights for policy 1, policy_version 3160 (0.0008) -[2023-10-09 08:24:09,382][23468] Updated weights for policy 0, policy_version 3140 (0.0009) -[2023-10-09 08:24:09,748][23468] Updated weights for policy 0, policy_version 3150 (0.0010) -[2023-10-09 08:24:10,124][23468] Updated weights for policy 0, policy_version 3160 (0.0011) -[2023-10-09 08:24:11,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 6488064. Throughput: 0: 1796.9, 1: 1777.6. Samples: 1624958. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-09 08:24:11,079][22500] Avg episode reward: [(0, '4.090'), (1, '4.660')] -[2023-10-09 08:24:11,080][23343] Saving new best policy, reward=4.660! -[2023-10-09 08:24:13,161][23469] Updated weights for policy 1, policy_version 3170 (0.0008) -[2023-10-09 08:24:13,528][23469] Updated weights for policy 1, policy_version 3180 (0.0010) -[2023-10-09 08:24:13,892][23469] Updated weights for policy 1, policy_version 3190 (0.0009) -[2023-10-09 08:24:14,045][23468] Updated weights for policy 0, policy_version 3170 (0.0007) -[2023-10-09 08:24:14,266][23469] Updated weights for policy 1, policy_version 3200 (0.0008) -[2023-10-09 08:24:14,428][23468] Updated weights for policy 0, policy_version 3180 (0.0008) -[2023-10-09 08:24:14,788][23468] Updated weights for policy 0, policy_version 3190 (0.0007) -[2023-10-09 08:24:15,158][23468] Updated weights for policy 0, policy_version 3200 (0.0009) -[2023-10-09 08:24:16,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 6553600. Throughput: 0: 1764.2, 1: 1782.3. Samples: 1645568. Policy #0 lag: (min: 29.0, avg: 34.3, max: 61.0) -[2023-10-09 08:24:16,078][22500] Avg episode reward: [(0, '4.320'), (1, '4.350')] -[2023-10-09 08:24:16,089][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000003200_3276800.pth... -[2023-10-09 08:24:16,089][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000003200_3276800.pth... -[2023-10-09 08:24:16,119][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000001536_1572864.pth -[2023-10-09 08:24:16,131][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000001536_1572864.pth -[2023-10-09 08:24:17,991][23469] Updated weights for policy 1, policy_version 3210 (0.0009) -[2023-10-09 08:24:18,361][23469] Updated weights for policy 1, policy_version 3220 (0.0008) -[2023-10-09 08:24:18,737][23469] Updated weights for policy 1, policy_version 3230 (0.0009) -[2023-10-09 08:24:19,111][23468] Updated weights for policy 0, policy_version 3210 (0.0007) -[2023-10-09 08:24:19,488][23468] Updated weights for policy 0, policy_version 3220 (0.0009) -[2023-10-09 08:24:19,853][23468] Updated weights for policy 0, policy_version 3230 (0.0008) -[2023-10-09 08:24:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 6619136. Throughput: 0: 1784.7, 1: 1782.1. Samples: 1656618. Policy #0 lag: (min: 29.0, avg: 34.3, max: 61.0) -[2023-10-09 08:24:21,078][22500] Avg episode reward: [(0, '4.270'), (1, '4.030')] -[2023-10-09 08:24:22,563][23469] Updated weights for policy 1, policy_version 3240 (0.0007) -[2023-10-09 08:24:22,934][23469] Updated weights for policy 1, policy_version 3250 (0.0009) -[2023-10-09 08:24:23,300][23469] Updated weights for policy 1, policy_version 3260 (0.0010) -[2023-10-09 08:24:23,685][23468] Updated weights for policy 0, policy_version 3240 (0.0008) -[2023-10-09 08:24:24,050][23468] Updated weights for policy 0, policy_version 3250 (0.0008) -[2023-10-09 08:24:24,424][23468] Updated weights for policy 0, policy_version 3260 (0.0007) -[2023-10-09 08:24:26,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 6684672. Throughput: 0: 1776.3, 1: 1784.3. Samples: 1677860. Policy #0 lag: (min: 19.0, avg: 25.0, max: 51.0) -[2023-10-09 08:24:26,078][22500] Avg episode reward: [(0, '4.300'), (1, '3.970')] -[2023-10-09 08:24:27,118][23469] Updated weights for policy 1, policy_version 3270 (0.0010) -[2023-10-09 08:24:27,506][23469] Updated weights for policy 1, policy_version 3280 (0.0007) -[2023-10-09 08:24:27,877][23469] Updated weights for policy 1, policy_version 3290 (0.0007) -[2023-10-09 08:24:28,244][23468] Updated weights for policy 0, policy_version 3270 (0.0009) -[2023-10-09 08:24:28,613][23468] Updated weights for policy 0, policy_version 3280 (0.0007) -[2023-10-09 08:24:28,982][23468] Updated weights for policy 0, policy_version 3290 (0.0007) -[2023-10-09 08:24:31,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 6750208. Throughput: 0: 1765.0, 1: 1784.8. Samples: 1699724. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:24:31,078][22500] Avg episode reward: [(0, '4.470'), (1, '4.150')] -[2023-10-09 08:24:31,086][23265] Saving new best policy, reward=4.470! -[2023-10-09 08:24:31,541][23469] Updated weights for policy 1, policy_version 3300 (0.0007) -[2023-10-09 08:24:31,904][23469] Updated weights for policy 1, policy_version 3310 (0.0008) -[2023-10-09 08:24:32,266][23469] Updated weights for policy 1, policy_version 3320 (0.0008) -[2023-10-09 08:24:32,692][23468] Updated weights for policy 0, policy_version 3300 (0.0008) -[2023-10-09 08:24:33,074][23468] Updated weights for policy 0, policy_version 3310 (0.0008) -[2023-10-09 08:24:33,443][23468] Updated weights for policy 0, policy_version 3320 (0.0009) -[2023-10-09 08:24:36,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 6815744. Throughput: 0: 1785.4, 1: 1786.0. Samples: 1710188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:24:36,078][22500] Avg episode reward: [(0, '4.560'), (1, '4.080')] -[2023-10-09 08:24:36,078][23265] Saving new best policy, reward=4.560! -[2023-10-09 08:24:36,211][23469] Updated weights for policy 1, policy_version 3330 (0.0008) -[2023-10-09 08:24:36,595][23469] Updated weights for policy 1, policy_version 3340 (0.0011) -[2023-10-09 08:24:36,964][23469] Updated weights for policy 1, policy_version 3350 (0.0010) -[2023-10-09 08:24:37,223][23468] Updated weights for policy 0, policy_version 3330 (0.0007) -[2023-10-09 08:24:37,327][23469] Updated weights for policy 1, policy_version 3360 (0.0008) -[2023-10-09 08:24:37,606][23468] Updated weights for policy 0, policy_version 3340 (0.0010) -[2023-10-09 08:24:37,984][23468] Updated weights for policy 0, policy_version 3350 (0.0010) -[2023-10-09 08:24:38,356][23468] Updated weights for policy 0, policy_version 3360 (0.0010) -[2023-10-09 08:24:41,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 6881280. Throughput: 0: 1772.5, 1: 1780.5. Samples: 1731666. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:24:41,079][22500] Avg episode reward: [(0, '4.430'), (1, '4.070')] -[2023-10-09 08:24:41,133][23469] Updated weights for policy 1, policy_version 3370 (0.0007) -[2023-10-09 08:24:41,511][23469] Updated weights for policy 1, policy_version 3380 (0.0009) -[2023-10-09 08:24:41,869][23469] Updated weights for policy 1, policy_version 3390 (0.0009) -[2023-10-09 08:24:42,125][23468] Updated weights for policy 0, policy_version 3370 (0.0009) -[2023-10-09 08:24:42,500][23468] Updated weights for policy 0, policy_version 3380 (0.0007) -[2023-10-09 08:24:42,866][23468] Updated weights for policy 0, policy_version 3390 (0.0008) -[2023-10-09 08:24:45,608][23469] Updated weights for policy 1, policy_version 3400 (0.0009) -[2023-10-09 08:24:45,973][23469] Updated weights for policy 1, policy_version 3410 (0.0009) -[2023-10-09 08:24:46,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 6946816. Throughput: 0: 1773.2, 1: 1799.7. Samples: 1753426. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:24:46,078][22500] Avg episode reward: [(0, '4.420'), (1, '4.080')] -[2023-10-09 08:24:46,347][23469] Updated weights for policy 1, policy_version 3420 (0.0008) -[2023-10-09 08:24:46,727][23468] Updated weights for policy 0, policy_version 3400 (0.0008) -[2023-10-09 08:24:47,099][23468] Updated weights for policy 0, policy_version 3410 (0.0008) -[2023-10-09 08:24:47,476][23468] Updated weights for policy 0, policy_version 3420 (0.0007) -[2023-10-09 08:24:50,111][23469] Updated weights for policy 1, policy_version 3430 (0.0009) -[2023-10-09 08:24:50,482][23469] Updated weights for policy 1, policy_version 3440 (0.0008) -[2023-10-09 08:24:50,848][23469] Updated weights for policy 1, policy_version 3450 (0.0008) -[2023-10-09 08:24:51,077][22500] Fps is (10 sec: 16384.5, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 7045120. Throughput: 0: 1769.5, 1: 1775.0. Samples: 1763502. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:24:51,078][22500] Avg episode reward: [(0, '4.340'), (1, '4.210')] -[2023-10-09 08:24:51,335][23468] Updated weights for policy 0, policy_version 3430 (0.0008) -[2023-10-09 08:24:51,711][23468] Updated weights for policy 0, policy_version 3440 (0.0010) -[2023-10-09 08:24:52,089][23468] Updated weights for policy 0, policy_version 3450 (0.0008) -[2023-10-09 08:24:54,457][23469] Updated weights for policy 1, policy_version 3460 (0.0008) -[2023-10-09 08:24:54,827][23469] Updated weights for policy 1, policy_version 3470 (0.0007) -[2023-10-09 08:24:55,195][23469] Updated weights for policy 1, policy_version 3480 (0.0007) -[2023-10-09 08:24:55,843][23468] Updated weights for policy 0, policy_version 3460 (0.0010) -[2023-10-09 08:24:56,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 7110656. Throughput: 0: 1761.2, 1: 1801.1. Samples: 1785264. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:24:56,078][22500] Avg episode reward: [(0, '4.260'), (1, '4.270')] -[2023-10-09 08:24:56,222][23468] Updated weights for policy 0, policy_version 3470 (0.0009) -[2023-10-09 08:24:56,593][23468] Updated weights for policy 0, policy_version 3480 (0.0009) -[2023-10-09 08:24:59,005][23469] Updated weights for policy 1, policy_version 3490 (0.0009) -[2023-10-09 08:24:59,382][23469] Updated weights for policy 1, policy_version 3500 (0.0009) -[2023-10-09 08:24:59,745][23469] Updated weights for policy 1, policy_version 3510 (0.0010) -[2023-10-09 08:25:00,117][23469] Updated weights for policy 1, policy_version 3520 (0.0010) -[2023-10-09 08:25:00,309][23468] Updated weights for policy 0, policy_version 3490 (0.0010) -[2023-10-09 08:25:00,680][23468] Updated weights for policy 0, policy_version 3500 (0.0008) -[2023-10-09 08:25:01,043][23468] Updated weights for policy 0, policy_version 3510 (0.0008) -[2023-10-09 08:25:01,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 7176192. Throughput: 0: 1797.0, 1: 1782.2. Samples: 1806634. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 08:25:01,078][22500] Avg episode reward: [(0, '4.340'), (1, '4.100')] -[2023-10-09 08:25:01,419][23468] Updated weights for policy 0, policy_version 3520 (0.0008) -[2023-10-09 08:25:03,817][23469] Updated weights for policy 1, policy_version 3530 (0.0008) -[2023-10-09 08:25:04,179][23469] Updated weights for policy 1, policy_version 3540 (0.0007) -[2023-10-09 08:25:04,543][23469] Updated weights for policy 1, policy_version 3550 (0.0007) -[2023-10-09 08:25:05,129][23468] Updated weights for policy 0, policy_version 3530 (0.0007) -[2023-10-09 08:25:05,507][23468] Updated weights for policy 0, policy_version 3540 (0.0008) -[2023-10-09 08:25:05,878][23468] Updated weights for policy 0, policy_version 3550 (0.0007) -[2023-10-09 08:25:06,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 7274496. Throughput: 0: 1768.9, 1: 1809.2. Samples: 1817630. Policy #0 lag: (min: 31.0, avg: 36.2, max: 63.0) -[2023-10-09 08:25:06,078][22500] Avg episode reward: [(0, '4.120'), (1, '3.980')] -[2023-10-09 08:25:08,259][23469] Updated weights for policy 1, policy_version 3560 (0.0007) -[2023-10-09 08:25:08,630][23469] Updated weights for policy 1, policy_version 3570 (0.0009) -[2023-10-09 08:25:09,001][23469] Updated weights for policy 1, policy_version 3580 (0.0008) -[2023-10-09 08:25:09,794][23468] Updated weights for policy 0, policy_version 3560 (0.0009) -[2023-10-09 08:25:10,167][23468] Updated weights for policy 0, policy_version 3570 (0.0007) -[2023-10-09 08:25:10,546][23468] Updated weights for policy 0, policy_version 3580 (0.0008) -[2023-10-09 08:25:11,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 7340032. Throughput: 0: 1795.5, 1: 1788.5. Samples: 1839138. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 08:25:11,078][22500] Avg episode reward: [(0, '4.120'), (1, '4.440')] -[2023-10-09 08:25:12,794][23469] Updated weights for policy 1, policy_version 3590 (0.0008) -[2023-10-09 08:25:13,191][23469] Updated weights for policy 1, policy_version 3600 (0.0010) -[2023-10-09 08:25:13,564][23469] Updated weights for policy 1, policy_version 3610 (0.0011) -[2023-10-09 08:25:14,252][23468] Updated weights for policy 0, policy_version 3590 (0.0009) -[2023-10-09 08:25:14,625][23468] Updated weights for policy 0, policy_version 3600 (0.0011) -[2023-10-09 08:25:14,991][23468] Updated weights for policy 0, policy_version 3610 (0.0008) -[2023-10-09 08:25:16,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 7405568. Throughput: 0: 1771.1, 1: 1787.7. Samples: 1859868. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 08:25:16,078][22500] Avg episode reward: [(0, '4.150'), (1, '4.410')] -[2023-10-09 08:25:17,299][23469] Updated weights for policy 1, policy_version 3620 (0.0009) -[2023-10-09 08:25:17,673][23469] Updated weights for policy 1, policy_version 3630 (0.0007) -[2023-10-09 08:25:18,041][23469] Updated weights for policy 1, policy_version 3640 (0.0009) -[2023-10-09 08:25:18,661][23468] Updated weights for policy 0, policy_version 3620 (0.0010) -[2023-10-09 08:25:19,027][23468] Updated weights for policy 0, policy_version 3630 (0.0011) -[2023-10-09 08:25:19,397][23468] Updated weights for policy 0, policy_version 3640 (0.0009) -[2023-10-09 08:25:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 7471104. Throughput: 0: 1788.7, 1: 1787.5. Samples: 1871118. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-10-09 08:25:21,079][22500] Avg episode reward: [(0, '4.390'), (1, '4.040')] -[2023-10-09 08:25:21,891][23469] Updated weights for policy 1, policy_version 3650 (0.0009) -[2023-10-09 08:25:22,276][23469] Updated weights for policy 1, policy_version 3660 (0.0011) -[2023-10-09 08:25:22,644][23469] Updated weights for policy 1, policy_version 3670 (0.0011) -[2023-10-09 08:25:23,013][23469] Updated weights for policy 1, policy_version 3680 (0.0007) -[2023-10-09 08:25:23,519][23468] Updated weights for policy 0, policy_version 3650 (0.0010) -[2023-10-09 08:25:23,885][23468] Updated weights for policy 0, policy_version 3660 (0.0008) -[2023-10-09 08:25:24,259][23468] Updated weights for policy 0, policy_version 3670 (0.0007) -[2023-10-09 08:25:24,634][23468] Updated weights for policy 0, policy_version 3680 (0.0008) -[2023-10-09 08:25:26,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 7536640. Throughput: 0: 1776.1, 1: 1786.0. Samples: 1891962. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-10-09 08:25:26,079][22500] Avg episode reward: [(0, '4.840'), (1, '4.100')] -[2023-10-09 08:25:26,080][23265] Saving new best policy, reward=4.840! -[2023-10-09 08:25:26,911][23469] Updated weights for policy 1, policy_version 3690 (0.0007) -[2023-10-09 08:25:27,285][23469] Updated weights for policy 1, policy_version 3700 (0.0007) -[2023-10-09 08:25:27,655][23469] Updated weights for policy 1, policy_version 3710 (0.0007) -[2023-10-09 08:25:28,450][23468] Updated weights for policy 0, policy_version 3690 (0.0007) -[2023-10-09 08:25:28,812][23468] Updated weights for policy 0, policy_version 3700 (0.0009) -[2023-10-09 08:25:29,186][23468] Updated weights for policy 0, policy_version 3710 (0.0007) -[2023-10-09 08:25:31,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 7602176. Throughput: 0: 1765.1, 1: 1794.3. Samples: 1913598. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 08:25:31,078][22500] Avg episode reward: [(0, '4.440'), (1, '4.020')] -[2023-10-09 08:25:31,410][23469] Updated weights for policy 1, policy_version 3720 (0.0008) -[2023-10-09 08:25:31,778][23469] Updated weights for policy 1, policy_version 3730 (0.0009) -[2023-10-09 08:25:32,146][23469] Updated weights for policy 1, policy_version 3740 (0.0007) -[2023-10-09 08:25:32,988][23468] Updated weights for policy 0, policy_version 3720 (0.0009) -[2023-10-09 08:25:33,369][23468] Updated weights for policy 0, policy_version 3730 (0.0012) -[2023-10-09 08:25:33,738][23468] Updated weights for policy 0, policy_version 3740 (0.0011) -[2023-10-09 08:25:35,896][23469] Updated weights for policy 1, policy_version 3750 (0.0008) -[2023-10-09 08:25:36,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 7667712. Throughput: 0: 1784.1, 1: 1785.7. Samples: 1924144. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 08:25:36,078][22500] Avg episode reward: [(0, '4.100'), (1, '4.040')] -[2023-10-09 08:25:36,267][23469] Updated weights for policy 1, policy_version 3760 (0.0007) -[2023-10-09 08:25:36,642][23469] Updated weights for policy 1, policy_version 3770 (0.0009) -[2023-10-09 08:25:37,501][23468] Updated weights for policy 0, policy_version 3750 (0.0009) -[2023-10-09 08:25:37,881][23468] Updated weights for policy 0, policy_version 3760 (0.0010) -[2023-10-09 08:25:38,258][23468] Updated weights for policy 0, policy_version 3770 (0.0011) -[2023-10-09 08:25:40,237][23469] Updated weights for policy 1, policy_version 3780 (0.0008) -[2023-10-09 08:25:40,609][23469] Updated weights for policy 1, policy_version 3790 (0.0007) -[2023-10-09 08:25:40,976][23469] Updated weights for policy 1, policy_version 3800 (0.0008) -[2023-10-09 08:25:41,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 7733248. Throughput: 0: 1776.8, 1: 1799.7. Samples: 1946206. Policy #0 lag: (min: 35.0, avg: 47.5, max: 48.0) -[2023-10-09 08:25:41,078][22500] Avg episode reward: [(0, '4.130'), (1, '4.130')] -[2023-10-09 08:25:41,918][23468] Updated weights for policy 0, policy_version 3780 (0.0011) -[2023-10-09 08:25:42,289][23468] Updated weights for policy 0, policy_version 3790 (0.0008) -[2023-10-09 08:25:42,655][23468] Updated weights for policy 0, policy_version 3800 (0.0008) -[2023-10-09 08:25:44,709][23469] Updated weights for policy 1, policy_version 3810 (0.0008) -[2023-10-09 08:25:45,074][23469] Updated weights for policy 1, policy_version 3820 (0.0009) -[2023-10-09 08:25:45,439][23469] Updated weights for policy 1, policy_version 3830 (0.0008) -[2023-10-09 08:25:45,812][23469] Updated weights for policy 1, policy_version 3840 (0.0008) -[2023-10-09 08:25:46,078][22500] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 7831552. Throughput: 0: 1776.1, 1: 1792.2. Samples: 1967210. Policy #0 lag: (min: 35.0, avg: 47.5, max: 48.0) -[2023-10-09 08:25:46,079][22500] Avg episode reward: [(0, '4.260'), (1, '4.120')] -[2023-10-09 08:25:46,254][23468] Updated weights for policy 0, policy_version 3810 (0.0009) -[2023-10-09 08:25:46,630][23468] Updated weights for policy 0, policy_version 3820 (0.0010) -[2023-10-09 08:25:47,002][23468] Updated weights for policy 0, policy_version 3830 (0.0010) -[2023-10-09 08:25:47,376][23468] Updated weights for policy 0, policy_version 3840 (0.0010) -[2023-10-09 08:25:49,436][23469] Updated weights for policy 1, policy_version 3850 (0.0007) -[2023-10-09 08:25:49,810][23469] Updated weights for policy 1, policy_version 3860 (0.0008) -[2023-10-09 08:25:50,187][23469] Updated weights for policy 1, policy_version 3870 (0.0009) -[2023-10-09 08:25:51,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 7897088. Throughput: 0: 1772.1, 1: 1796.6. Samples: 1978220. Policy #0 lag: (min: 29.0, avg: 30.2, max: 53.0) -[2023-10-09 08:25:51,079][22500] Avg episode reward: [(0, '4.420'), (1, '4.330')] -[2023-10-09 08:25:51,184][23468] Updated weights for policy 0, policy_version 3850 (0.0010) -[2023-10-09 08:25:51,558][23468] Updated weights for policy 0, policy_version 3860 (0.0009) -[2023-10-09 08:25:51,925][23468] Updated weights for policy 0, policy_version 3870 (0.0009) -[2023-10-09 08:25:54,060][23469] Updated weights for policy 1, policy_version 3880 (0.0009) -[2023-10-09 08:25:54,436][23469] Updated weights for policy 1, policy_version 3890 (0.0007) -[2023-10-09 08:25:54,800][23469] Updated weights for policy 1, policy_version 3900 (0.0007) -[2023-10-09 08:25:55,797][23468] Updated weights for policy 0, policy_version 3880 (0.0008) -[2023-10-09 08:25:56,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 7962624. Throughput: 0: 1769.1, 1: 1787.8. Samples: 1999200. Policy #0 lag: (min: 29.0, avg: 30.2, max: 53.0) -[2023-10-09 08:25:56,078][22500] Avg episode reward: [(0, '4.710'), (1, '4.290')] -[2023-10-09 08:25:56,170][23468] Updated weights for policy 0, policy_version 3890 (0.0007) -[2023-10-09 08:25:56,552][23468] Updated weights for policy 0, policy_version 3900 (0.0008) -[2023-10-09 08:25:58,855][23469] Updated weights for policy 1, policy_version 3910 (0.0007) -[2023-10-09 08:25:59,240][23469] Updated weights for policy 1, policy_version 3920 (0.0008) -[2023-10-09 08:25:59,605][23469] Updated weights for policy 1, policy_version 3930 (0.0007) -[2023-10-09 08:26:00,260][23468] Updated weights for policy 0, policy_version 3910 (0.0009) -[2023-10-09 08:26:00,627][23468] Updated weights for policy 0, policy_version 3920 (0.0009) -[2023-10-09 08:26:00,998][23468] Updated weights for policy 0, policy_version 3930 (0.0008) -[2023-10-09 08:26:01,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 8028160. Throughput: 0: 1800.9, 1: 1776.4. Samples: 2020848. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:26:01,078][22500] Avg episode reward: [(0, '4.730'), (1, '4.130')] -[2023-10-09 08:26:03,312][23469] Updated weights for policy 1, policy_version 3940 (0.0008) -[2023-10-09 08:26:03,677][23469] Updated weights for policy 1, policy_version 3950 (0.0010) -[2023-10-09 08:26:04,041][23469] Updated weights for policy 1, policy_version 3960 (0.0011) -[2023-10-09 08:26:04,779][23468] Updated weights for policy 0, policy_version 3940 (0.0008) -[2023-10-09 08:26:05,160][23468] Updated weights for policy 0, policy_version 3950 (0.0009) -[2023-10-09 08:26:05,522][23468] Updated weights for policy 0, policy_version 3960 (0.0008) -[2023-10-09 08:26:06,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 8126464. Throughput: 0: 1773.9, 1: 1793.0. Samples: 2031630. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) -[2023-10-09 08:26:06,078][22500] Avg episode reward: [(0, '4.810'), (1, '4.080')] -[2023-10-09 08:26:07,834][23469] Updated weights for policy 1, policy_version 3970 (0.0009) -[2023-10-09 08:26:08,201][23469] Updated weights for policy 1, policy_version 3980 (0.0008) -[2023-10-09 08:26:08,569][23469] Updated weights for policy 1, policy_version 3990 (0.0008) -[2023-10-09 08:26:08,941][23469] Updated weights for policy 1, policy_version 4000 (0.0009) -[2023-10-09 08:26:09,205][23468] Updated weights for policy 0, policy_version 3970 (0.0007) -[2023-10-09 08:26:09,584][23468] Updated weights for policy 0, policy_version 3980 (0.0008) -[2023-10-09 08:26:09,959][23468] Updated weights for policy 0, policy_version 3990 (0.0008) -[2023-10-09 08:26:10,324][23468] Updated weights for policy 0, policy_version 4000 (0.0009) -[2023-10-09 08:26:11,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 8192000. Throughput: 0: 1801.7, 1: 1784.6. Samples: 2053346. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) -[2023-10-09 08:26:11,078][22500] Avg episode reward: [(0, '4.720'), (1, '4.190')] -[2023-10-09 08:26:12,522][23469] Updated weights for policy 1, policy_version 4010 (0.0008) -[2023-10-09 08:26:12,887][23469] Updated weights for policy 1, policy_version 4020 (0.0008) -[2023-10-09 08:26:13,261][23469] Updated weights for policy 1, policy_version 4030 (0.0008) -[2023-10-09 08:26:14,021][23468] Updated weights for policy 0, policy_version 4010 (0.0009) -[2023-10-09 08:26:14,387][23468] Updated weights for policy 0, policy_version 4020 (0.0007) -[2023-10-09 08:26:14,764][23468] Updated weights for policy 0, policy_version 4030 (0.0008) -[2023-10-09 08:26:16,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 8257536. Throughput: 0: 1788.1, 1: 1787.1. Samples: 2074482. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 08:26:16,078][22500] Avg episode reward: [(0, '4.890'), (1, '4.260')] -[2023-10-09 08:26:16,087][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000004032_4128768.pth... -[2023-10-09 08:26:16,087][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000004032_4128768.pth... -[2023-10-09 08:26:16,117][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000002368_2424832.pth -[2023-10-09 08:26:16,124][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000002368_2424832.pth -[2023-10-09 08:26:16,130][23265] Saving new best policy, reward=4.890! -[2023-10-09 08:26:17,113][23469] Updated weights for policy 1, policy_version 4040 (0.0008) -[2023-10-09 08:26:17,475][23469] Updated weights for policy 1, policy_version 4050 (0.0007) -[2023-10-09 08:26:17,844][23469] Updated weights for policy 1, policy_version 4060 (0.0007) -[2023-10-09 08:26:18,387][23468] Updated weights for policy 0, policy_version 4040 (0.0008) -[2023-10-09 08:26:18,764][23468] Updated weights for policy 0, policy_version 4050 (0.0008) -[2023-10-09 08:26:19,126][23468] Updated weights for policy 0, policy_version 4060 (0.0009) -[2023-10-09 08:26:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 8323072. Throughput: 0: 1801.4, 1: 1786.3. Samples: 2085588. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 08:26:21,078][22500] Avg episode reward: [(0, '5.050'), (1, '4.280')] -[2023-10-09 08:26:21,078][23265] Saving new best policy, reward=5.050! -[2023-10-09 08:26:21,511][23469] Updated weights for policy 1, policy_version 4070 (0.0009) -[2023-10-09 08:26:21,879][23469] Updated weights for policy 1, policy_version 4080 (0.0007) -[2023-10-09 08:26:22,252][23469] Updated weights for policy 1, policy_version 4090 (0.0009) -[2023-10-09 08:26:22,911][23468] Updated weights for policy 0, policy_version 4070 (0.0010) -[2023-10-09 08:26:23,280][23468] Updated weights for policy 0, policy_version 4080 (0.0007) -[2023-10-09 08:26:23,645][23468] Updated weights for policy 0, policy_version 4090 (0.0008) -[2023-10-09 08:26:26,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 8388608. Throughput: 0: 1782.0, 1: 1779.0. Samples: 2106450. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-09 08:26:26,078][22500] Avg episode reward: [(0, '4.770'), (1, '4.200')] -[2023-10-09 08:26:26,176][23469] Updated weights for policy 1, policy_version 4100 (0.0009) -[2023-10-09 08:26:26,552][23469] Updated weights for policy 1, policy_version 4110 (0.0009) -[2023-10-09 08:26:26,920][23469] Updated weights for policy 1, policy_version 4120 (0.0011) -[2023-10-09 08:26:27,586][23468] Updated weights for policy 0, policy_version 4100 (0.0009) -[2023-10-09 08:26:27,951][23468] Updated weights for policy 0, policy_version 4110 (0.0008) -[2023-10-09 08:26:28,333][23468] Updated weights for policy 0, policy_version 4120 (0.0008) -[2023-10-09 08:26:30,792][23469] Updated weights for policy 1, policy_version 4130 (0.0009) -[2023-10-09 08:26:31,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 8454144. Throughput: 0: 1783.9, 1: 1801.3. Samples: 2128542. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 08:26:31,078][22500] Avg episode reward: [(0, '4.350'), (1, '4.000')] -[2023-10-09 08:26:31,152][23469] Updated weights for policy 1, policy_version 4140 (0.0009) -[2023-10-09 08:26:31,519][23469] Updated weights for policy 1, policy_version 4150 (0.0008) -[2023-10-09 08:26:31,889][23469] Updated weights for policy 1, policy_version 4160 (0.0007) -[2023-10-09 08:26:32,178][23468] Updated weights for policy 0, policy_version 4130 (0.0010) -[2023-10-09 08:26:32,547][23468] Updated weights for policy 0, policy_version 4140 (0.0007) -[2023-10-09 08:26:32,921][23468] Updated weights for policy 0, policy_version 4150 (0.0008) -[2023-10-09 08:26:33,300][23468] Updated weights for policy 0, policy_version 4160 (0.0008) -[2023-10-09 08:26:35,663][23469] Updated weights for policy 1, policy_version 4170 (0.0009) -[2023-10-09 08:26:36,040][23469] Updated weights for policy 1, policy_version 4180 (0.0009) -[2023-10-09 08:26:36,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 8519680. Throughput: 0: 1787.7, 1: 1771.3. Samples: 2138370. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 08:26:36,078][22500] Avg episode reward: [(0, '4.390'), (1, '4.170')] -[2023-10-09 08:26:36,413][23469] Updated weights for policy 1, policy_version 4190 (0.0009) -[2023-10-09 08:26:37,084][23468] Updated weights for policy 0, policy_version 4170 (0.0007) -[2023-10-09 08:26:37,461][23468] Updated weights for policy 0, policy_version 4180 (0.0007) -[2023-10-09 08:26:37,827][23468] Updated weights for policy 0, policy_version 4190 (0.0008) -[2023-10-09 08:26:40,070][23469] Updated weights for policy 1, policy_version 4200 (0.0008) -[2023-10-09 08:26:40,443][23469] Updated weights for policy 1, policy_version 4210 (0.0009) -[2023-10-09 08:26:40,808][23469] Updated weights for policy 1, policy_version 4220 (0.0009) -[2023-10-09 08:26:41,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 8617984. Throughput: 0: 1785.3, 1: 1801.2. Samples: 2160594. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 08:26:41,078][22500] Avg episode reward: [(0, '4.620'), (1, '4.140')] -[2023-10-09 08:26:41,630][23468] Updated weights for policy 0, policy_version 4200 (0.0010) -[2023-10-09 08:26:42,008][23468] Updated weights for policy 0, policy_version 4210 (0.0010) -[2023-10-09 08:26:42,382][23468] Updated weights for policy 0, policy_version 4220 (0.0009) -[2023-10-09 08:26:44,711][23469] Updated weights for policy 1, policy_version 4230 (0.0009) -[2023-10-09 08:26:45,093][23469] Updated weights for policy 1, policy_version 4240 (0.0009) -[2023-10-09 08:26:45,459][23469] Updated weights for policy 1, policy_version 4250 (0.0008) -[2023-10-09 08:26:45,897][23468] Updated weights for policy 0, policy_version 4230 (0.0011) -[2023-10-09 08:26:46,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 8683520. Throughput: 0: 1792.7, 1: 1779.6. Samples: 2181602. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 08:26:46,078][22500] Avg episode reward: [(0, '4.690'), (1, '4.320')] -[2023-10-09 08:26:46,283][23468] Updated weights for policy 0, policy_version 4240 (0.0008) -[2023-10-09 08:26:46,652][23468] Updated weights for policy 0, policy_version 4250 (0.0007) -[2023-10-09 08:26:49,119][23469] Updated weights for policy 1, policy_version 4260 (0.0008) -[2023-10-09 08:26:49,489][23469] Updated weights for policy 1, policy_version 4270 (0.0007) -[2023-10-09 08:26:49,867][23469] Updated weights for policy 1, policy_version 4280 (0.0008) -[2023-10-09 08:26:50,445][23468] Updated weights for policy 0, policy_version 4260 (0.0008) -[2023-10-09 08:26:50,812][23468] Updated weights for policy 0, policy_version 4270 (0.0008) -[2023-10-09 08:26:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 8749056. Throughput: 0: 1783.6, 1: 1796.7. Samples: 2192742. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 08:26:51,078][22500] Avg episode reward: [(0, '4.640'), (1, '4.410')] -[2023-10-09 08:26:51,185][23468] Updated weights for policy 0, policy_version 4280 (0.0009) -[2023-10-09 08:26:53,660][23469] Updated weights for policy 1, policy_version 4290 (0.0008) -[2023-10-09 08:26:54,033][23469] Updated weights for policy 1, policy_version 4300 (0.0010) -[2023-10-09 08:26:54,402][23469] Updated weights for policy 1, policy_version 4310 (0.0007) -[2023-10-09 08:26:54,768][23469] Updated weights for policy 1, policy_version 4320 (0.0007) -[2023-10-09 08:26:54,904][23468] Updated weights for policy 0, policy_version 4290 (0.0008) -[2023-10-09 08:26:55,269][23468] Updated weights for policy 0, policy_version 4300 (0.0008) -[2023-10-09 08:26:55,646][23468] Updated weights for policy 0, policy_version 4310 (0.0009) -[2023-10-09 08:26:56,010][23468] Updated weights for policy 0, policy_version 4320 (0.0008) -[2023-10-09 08:26:56,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 8847360. Throughput: 0: 1784.8, 1: 1779.6. Samples: 2213748. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:26:56,078][22500] Avg episode reward: [(0, '4.670'), (1, '4.630')] -[2023-10-09 08:26:58,583][23469] Updated weights for policy 1, policy_version 4330 (0.0009) -[2023-10-09 08:26:58,965][23469] Updated weights for policy 1, policy_version 4340 (0.0009) -[2023-10-09 08:26:59,331][23469] Updated weights for policy 1, policy_version 4350 (0.0008) -[2023-10-09 08:26:59,832][23468] Updated weights for policy 0, policy_version 4330 (0.0009) -[2023-10-09 08:27:00,196][23468] Updated weights for policy 0, policy_version 4340 (0.0009) -[2023-10-09 08:27:00,572][23468] Updated weights for policy 0, policy_version 4350 (0.0011) -[2023-10-09 08:27:01,078][22500] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14218.0). Total num frames: 8912896. Throughput: 0: 1791.9, 1: 1778.3. Samples: 2235144. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-09 08:27:01,079][22500] Avg episode reward: [(0, '5.040'), (1, '4.500')] -[2023-10-09 08:27:03,078][23469] Updated weights for policy 1, policy_version 4360 (0.0007) -[2023-10-09 08:27:03,454][23469] Updated weights for policy 1, policy_version 4370 (0.0008) -[2023-10-09 08:27:03,829][23469] Updated weights for policy 1, policy_version 4380 (0.0009) -[2023-10-09 08:27:04,359][23468] Updated weights for policy 0, policy_version 4360 (0.0008) -[2023-10-09 08:27:04,729][23468] Updated weights for policy 0, policy_version 4370 (0.0010) -[2023-10-09 08:27:05,100][23468] Updated weights for policy 0, policy_version 4380 (0.0010) -[2023-10-09 08:27:06,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 8978432. Throughput: 0: 1783.2, 1: 1782.8. Samples: 2246062. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-09 08:27:06,078][22500] Avg episode reward: [(0, '4.760'), (1, '4.480')] -[2023-10-09 08:27:07,645][23469] Updated weights for policy 1, policy_version 4390 (0.0007) -[2023-10-09 08:27:08,019][23469] Updated weights for policy 1, policy_version 4400 (0.0008) -[2023-10-09 08:27:08,398][23469] Updated weights for policy 1, policy_version 4410 (0.0008) -[2023-10-09 08:27:09,045][23468] Updated weights for policy 0, policy_version 4390 (0.0007) -[2023-10-09 08:27:09,410][23468] Updated weights for policy 0, policy_version 4400 (0.0008) -[2023-10-09 08:27:09,787][23468] Updated weights for policy 0, policy_version 4410 (0.0007) -[2023-10-09 08:27:11,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 9043968. Throughput: 0: 1801.9, 1: 1777.3. Samples: 2267514. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-09 08:27:11,079][22500] Avg episode reward: [(0, '4.920'), (1, '4.390')] -[2023-10-09 08:27:12,086][23469] Updated weights for policy 1, policy_version 4420 (0.0008) -[2023-10-09 08:27:12,459][23469] Updated weights for policy 1, policy_version 4430 (0.0007) -[2023-10-09 08:27:12,829][23469] Updated weights for policy 1, policy_version 4440 (0.0008) -[2023-10-09 08:27:13,338][23468] Updated weights for policy 0, policy_version 4420 (0.0008) -[2023-10-09 08:27:13,716][23468] Updated weights for policy 0, policy_version 4430 (0.0007) -[2023-10-09 08:27:14,082][23468] Updated weights for policy 0, policy_version 4440 (0.0010) -[2023-10-09 08:27:16,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 9109504. Throughput: 0: 1787.4, 1: 1780.5. Samples: 2289098. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-09 08:27:16,078][22500] Avg episode reward: [(0, '4.850'), (1, '4.350')] -[2023-10-09 08:27:16,581][23469] Updated weights for policy 1, policy_version 4450 (0.0007) -[2023-10-09 08:27:16,961][23469] Updated weights for policy 1, policy_version 4460 (0.0007) -[2023-10-09 08:27:17,322][23469] Updated weights for policy 1, policy_version 4470 (0.0009) -[2023-10-09 08:27:17,691][23469] Updated weights for policy 1, policy_version 4480 (0.0007) -[2023-10-09 08:27:17,722][23468] Updated weights for policy 0, policy_version 4450 (0.0009) -[2023-10-09 08:27:18,093][23468] Updated weights for policy 0, policy_version 4460 (0.0007) -[2023-10-09 08:27:18,473][23468] Updated weights for policy 0, policy_version 4470 (0.0009) -[2023-10-09 08:27:18,843][23468] Updated weights for policy 0, policy_version 4480 (0.0009) -[2023-10-09 08:27:21,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 9175040. Throughput: 0: 1799.9, 1: 1779.7. Samples: 2299452. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:27:21,078][22500] Avg episode reward: [(0, '4.900'), (1, '4.330')] -[2023-10-09 08:27:21,543][23469] Updated weights for policy 1, policy_version 4490 (0.0008) -[2023-10-09 08:27:21,913][23469] Updated weights for policy 1, policy_version 4500 (0.0009) -[2023-10-09 08:27:22,280][23469] Updated weights for policy 1, policy_version 4510 (0.0008) -[2023-10-09 08:27:22,707][23468] Updated weights for policy 0, policy_version 4490 (0.0008) -[2023-10-09 08:27:23,084][23468] Updated weights for policy 0, policy_version 4500 (0.0009) -[2023-10-09 08:27:23,457][23468] Updated weights for policy 0, policy_version 4510 (0.0008) -[2023-10-09 08:27:25,909][23469] Updated weights for policy 1, policy_version 4520 (0.0009) -[2023-10-09 08:27:26,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 9240576. Throughput: 0: 1783.1, 1: 1781.6. Samples: 2321006. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:27:26,078][22500] Avg episode reward: [(0, '4.910'), (1, '4.450')] -[2023-10-09 08:27:26,276][23469] Updated weights for policy 1, policy_version 4530 (0.0009) -[2023-10-09 08:27:26,647][23469] Updated weights for policy 1, policy_version 4540 (0.0008) -[2023-10-09 08:27:27,407][23468] Updated weights for policy 0, policy_version 4520 (0.0007) -[2023-10-09 08:27:27,788][23468] Updated weights for policy 0, policy_version 4530 (0.0007) -[2023-10-09 08:27:28,162][23468] Updated weights for policy 0, policy_version 4540 (0.0008) -[2023-10-09 08:27:30,517][23469] Updated weights for policy 1, policy_version 4550 (0.0010) -[2023-10-09 08:27:30,901][23469] Updated weights for policy 1, policy_version 4560 (0.0009) -[2023-10-09 08:27:31,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 9306112. Throughput: 0: 1778.2, 1: 1801.2. Samples: 2342676. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-09 08:27:31,078][22500] Avg episode reward: [(0, '4.450'), (1, '4.490')] -[2023-10-09 08:27:31,278][23469] Updated weights for policy 1, policy_version 4570 (0.0008) -[2023-10-09 08:27:31,949][23468] Updated weights for policy 0, policy_version 4550 (0.0008) -[2023-10-09 08:27:32,330][23468] Updated weights for policy 0, policy_version 4560 (0.0009) -[2023-10-09 08:27:32,700][23468] Updated weights for policy 0, policy_version 4570 (0.0007) -[2023-10-09 08:27:34,947][23469] Updated weights for policy 1, policy_version 4580 (0.0008) -[2023-10-09 08:27:35,321][23469] Updated weights for policy 1, policy_version 4590 (0.0008) -[2023-10-09 08:27:35,687][23469] Updated weights for policy 1, policy_version 4600 (0.0009) -[2023-10-09 08:27:36,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 9404416. Throughput: 0: 1780.8, 1: 1780.1. Samples: 2352984. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-09 08:27:36,078][22500] Avg episode reward: [(0, '4.260'), (1, '4.510')] -[2023-10-09 08:27:36,447][23468] Updated weights for policy 0, policy_version 4580 (0.0007) -[2023-10-09 08:27:36,826][23468] Updated weights for policy 0, policy_version 4590 (0.0007) -[2023-10-09 08:27:37,186][23468] Updated weights for policy 0, policy_version 4600 (0.0007) -[2023-10-09 08:27:39,601][23469] Updated weights for policy 1, policy_version 4610 (0.0007) -[2023-10-09 08:27:39,974][23469] Updated weights for policy 1, policy_version 4620 (0.0008) -[2023-10-09 08:27:40,343][23469] Updated weights for policy 1, policy_version 4630 (0.0009) -[2023-10-09 08:27:40,706][23469] Updated weights for policy 1, policy_version 4640 (0.0010) -[2023-10-09 08:27:41,070][23468] Updated weights for policy 0, policy_version 4610 (0.0008) -[2023-10-09 08:27:41,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 9469952. Throughput: 0: 1780.2, 1: 1800.4. Samples: 2374874. Policy #0 lag: (min: 10.0, avg: 18.0, max: 42.0) -[2023-10-09 08:27:41,078][22500] Avg episode reward: [(0, '4.450'), (1, '4.550')] -[2023-10-09 08:27:41,442][23468] Updated weights for policy 0, policy_version 4620 (0.0008) -[2023-10-09 08:27:41,817][23468] Updated weights for policy 0, policy_version 4630 (0.0008) -[2023-10-09 08:27:42,185][23468] Updated weights for policy 0, policy_version 4640 (0.0009) -[2023-10-09 08:27:44,470][23469] Updated weights for policy 1, policy_version 4650 (0.0008) -[2023-10-09 08:27:44,834][23469] Updated weights for policy 1, policy_version 4660 (0.0007) -[2023-10-09 08:27:45,198][23469] Updated weights for policy 1, policy_version 4670 (0.0010) -[2023-10-09 08:27:45,894][23468] Updated weights for policy 0, policy_version 4650 (0.0008) -[2023-10-09 08:27:46,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 9535488. Throughput: 0: 1797.2, 1: 1779.8. Samples: 2396106. Policy #0 lag: (min: 10.0, avg: 18.0, max: 42.0) -[2023-10-09 08:27:46,079][22500] Avg episode reward: [(0, '4.770'), (1, '4.270')] -[2023-10-09 08:27:46,266][23468] Updated weights for policy 0, policy_version 4660 (0.0009) -[2023-10-09 08:27:46,644][23468] Updated weights for policy 0, policy_version 4670 (0.0008) -[2023-10-09 08:27:48,910][23469] Updated weights for policy 1, policy_version 4680 (0.0009) -[2023-10-09 08:27:49,275][23469] Updated weights for policy 1, policy_version 4690 (0.0007) -[2023-10-09 08:27:49,645][23469] Updated weights for policy 1, policy_version 4700 (0.0007) -[2023-10-09 08:27:50,412][23468] Updated weights for policy 0, policy_version 4680 (0.0007) -[2023-10-09 08:27:50,783][23468] Updated weights for policy 0, policy_version 4690 (0.0008) -[2023-10-09 08:27:51,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 9601024. Throughput: 0: 1772.1, 1: 1807.7. Samples: 2407154. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:27:51,078][22500] Avg episode reward: [(0, '4.870'), (1, '4.430')] -[2023-10-09 08:27:51,151][23468] Updated weights for policy 0, policy_version 4700 (0.0010) -[2023-10-09 08:27:53,236][23469] Updated weights for policy 1, policy_version 4710 (0.0009) -[2023-10-09 08:27:53,613][23469] Updated weights for policy 1, policy_version 4720 (0.0007) -[2023-10-09 08:27:53,976][23469] Updated weights for policy 1, policy_version 4730 (0.0007) -[2023-10-09 08:27:55,021][23468] Updated weights for policy 0, policy_version 4710 (0.0008) -[2023-10-09 08:27:55,392][23468] Updated weights for policy 0, policy_version 4720 (0.0008) -[2023-10-09 08:27:55,766][23468] Updated weights for policy 0, policy_version 4730 (0.0009) -[2023-10-09 08:27:56,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 9699328. Throughput: 0: 1782.4, 1: 1793.7. Samples: 2428438. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:27:56,078][22500] Avg episode reward: [(0, '5.000'), (1, '4.510')] -[2023-10-09 08:27:57,607][23469] Updated weights for policy 1, policy_version 4740 (0.0008) -[2023-10-09 08:27:57,980][23469] Updated weights for policy 1, policy_version 4750 (0.0007) -[2023-10-09 08:27:58,352][23469] Updated weights for policy 1, policy_version 4760 (0.0008) -[2023-10-09 08:27:59,464][23468] Updated weights for policy 0, policy_version 4740 (0.0010) -[2023-10-09 08:27:59,830][23468] Updated weights for policy 0, policy_version 4750 (0.0008) -[2023-10-09 08:28:00,200][23468] Updated weights for policy 0, policy_version 4760 (0.0008) -[2023-10-09 08:28:01,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 9764864. Throughput: 0: 1771.9, 1: 1796.4. Samples: 2449672. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:28:01,078][22500] Avg episode reward: [(0, '4.870'), (1, '4.330')] -[2023-10-09 08:28:02,217][23469] Updated weights for policy 1, policy_version 4770 (0.0007) -[2023-10-09 08:28:02,590][23469] Updated weights for policy 1, policy_version 4780 (0.0007) -[2023-10-09 08:28:02,954][23469] Updated weights for policy 1, policy_version 4790 (0.0007) -[2023-10-09 08:28:03,329][23469] Updated weights for policy 1, policy_version 4800 (0.0009) -[2023-10-09 08:28:03,999][23468] Updated weights for policy 0, policy_version 4770 (0.0010) -[2023-10-09 08:28:04,374][23468] Updated weights for policy 0, policy_version 4780 (0.0010) -[2023-10-09 08:28:04,753][23468] Updated weights for policy 0, policy_version 4790 (0.0008) -[2023-10-09 08:28:05,116][23468] Updated weights for policy 0, policy_version 4800 (0.0009) -[2023-10-09 08:28:06,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 9830400. Throughput: 0: 1785.6, 1: 1792.6. Samples: 2460474. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 08:28:06,078][22500] Avg episode reward: [(0, '4.970'), (1, '4.330')] -[2023-10-09 08:28:07,049][23469] Updated weights for policy 1, policy_version 4810 (0.0008) -[2023-10-09 08:28:07,415][23469] Updated weights for policy 1, policy_version 4820 (0.0011) -[2023-10-09 08:28:07,781][23469] Updated weights for policy 1, policy_version 4830 (0.0010) -[2023-10-09 08:28:08,888][23468] Updated weights for policy 0, policy_version 4810 (0.0008) -[2023-10-09 08:28:09,258][23468] Updated weights for policy 0, policy_version 4820 (0.0008) -[2023-10-09 08:28:09,633][23468] Updated weights for policy 0, policy_version 4830 (0.0008) -[2023-10-09 08:28:11,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 9895936. Throughput: 0: 1785.4, 1: 1795.2. Samples: 2482134. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 08:28:11,078][22500] Avg episode reward: [(0, '5.300'), (1, '4.340')] -[2023-10-09 08:28:11,079][23265] Saving new best policy, reward=5.300! -[2023-10-09 08:28:11,565][23469] Updated weights for policy 1, policy_version 4840 (0.0008) -[2023-10-09 08:28:11,934][23469] Updated weights for policy 1, policy_version 4850 (0.0007) -[2023-10-09 08:28:12,313][23469] Updated weights for policy 1, policy_version 4860 (0.0009) -[2023-10-09 08:28:13,436][23468] Updated weights for policy 0, policy_version 4840 (0.0008) -[2023-10-09 08:28:13,808][23468] Updated weights for policy 0, policy_version 4850 (0.0009) -[2023-10-09 08:28:14,183][23468] Updated weights for policy 0, policy_version 4860 (0.0008) -[2023-10-09 08:28:16,008][23469] Updated weights for policy 1, policy_version 4870 (0.0008) -[2023-10-09 08:28:16,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 9961472. Throughput: 0: 1770.8, 1: 1809.5. Samples: 2503790. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 08:28:16,078][22500] Avg episode reward: [(0, '5.030'), (1, '4.600')] -[2023-10-09 08:28:16,086][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000004864_4980736.pth... -[2023-10-09 08:28:16,120][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000003200_3276800.pth -[2023-10-09 08:28:16,393][23469] Updated weights for policy 1, policy_version 4880 (0.0010) -[2023-10-09 08:28:16,759][23469] Updated weights for policy 1, policy_version 4890 (0.0007) -[2023-10-09 08:28:16,979][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000004896_5013504.pth... -[2023-10-09 08:28:17,007][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000003200_3276800.pth -[2023-10-09 08:28:18,015][23468] Updated weights for policy 0, policy_version 4870 (0.0010) -[2023-10-09 08:28:18,383][23468] Updated weights for policy 0, policy_version 4880 (0.0009) -[2023-10-09 08:28:18,756][23468] Updated weights for policy 0, policy_version 4890 (0.0011) -[2023-10-09 08:28:20,481][23469] Updated weights for policy 1, policy_version 4900 (0.0007) -[2023-10-09 08:28:20,842][23469] Updated weights for policy 1, policy_version 4910 (0.0010) -[2023-10-09 08:28:21,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 10027008. Throughput: 0: 1785.3, 1: 1795.9. Samples: 2514142. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 08:28:21,078][22500] Avg episode reward: [(0, '5.030'), (1, '4.840')] -[2023-10-09 08:28:21,222][23469] Updated weights for policy 1, policy_version 4920 (0.0010) -[2023-10-09 08:28:21,521][23343] Saving new best policy, reward=4.840! -[2023-10-09 08:28:22,511][23468] Updated weights for policy 0, policy_version 4900 (0.0009) -[2023-10-09 08:28:22,884][23468] Updated weights for policy 0, policy_version 4910 (0.0007) -[2023-10-09 08:28:23,261][23468] Updated weights for policy 0, policy_version 4920 (0.0007) -[2023-10-09 08:28:24,862][23469] Updated weights for policy 1, policy_version 4930 (0.0008) -[2023-10-09 08:28:25,229][23469] Updated weights for policy 1, policy_version 4940 (0.0009) -[2023-10-09 08:28:25,601][23469] Updated weights for policy 1, policy_version 4950 (0.0007) -[2023-10-09 08:28:25,973][23469] Updated weights for policy 1, policy_version 4960 (0.0007) -[2023-10-09 08:28:26,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 10125312. Throughput: 0: 1767.9, 1: 1809.5. Samples: 2535858. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:28:26,079][22500] Avg episode reward: [(0, '4.830'), (1, '5.400')] -[2023-10-09 08:28:26,080][23343] Saving new best policy, reward=5.400! -[2023-10-09 08:28:27,039][23468] Updated weights for policy 0, policy_version 4930 (0.0008) -[2023-10-09 08:28:27,401][23468] Updated weights for policy 0, policy_version 4940 (0.0008) -[2023-10-09 08:28:27,773][23468] Updated weights for policy 0, policy_version 4950 (0.0009) -[2023-10-09 08:28:28,145][23468] Updated weights for policy 0, policy_version 4960 (0.0009) -[2023-10-09 08:28:29,647][23469] Updated weights for policy 1, policy_version 4970 (0.0007) -[2023-10-09 08:28:30,016][23469] Updated weights for policy 1, policy_version 4980 (0.0008) -[2023-10-09 08:28:30,389][23469] Updated weights for policy 1, policy_version 4990 (0.0007) -[2023-10-09 08:28:31,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 10190848. Throughput: 0: 1772.0, 1: 1800.0. Samples: 2556846. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:28:31,078][22500] Avg episode reward: [(0, '4.880'), (1, '5.110')] -[2023-10-09 08:28:31,836][23468] Updated weights for policy 0, policy_version 4970 (0.0008) -[2023-10-09 08:28:32,213][23468] Updated weights for policy 0, policy_version 4980 (0.0008) -[2023-10-09 08:28:32,589][23468] Updated weights for policy 0, policy_version 4990 (0.0008) -[2023-10-09 08:28:34,271][23469] Updated weights for policy 1, policy_version 5000 (0.0011) -[2023-10-09 08:28:34,644][23469] Updated weights for policy 1, policy_version 5010 (0.0009) -[2023-10-09 08:28:35,019][23469] Updated weights for policy 1, policy_version 5020 (0.0007) -[2023-10-09 08:28:36,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 10256384. Throughput: 0: 1773.3, 1: 1799.0. Samples: 2567908. Policy #0 lag: (min: 15.0, avg: 38.3, max: 40.0) -[2023-10-09 08:28:36,079][22500] Avg episode reward: [(0, '5.000'), (1, '4.930')] -[2023-10-09 08:28:36,482][23468] Updated weights for policy 0, policy_version 5000 (0.0008) -[2023-10-09 08:28:36,859][23468] Updated weights for policy 0, policy_version 5010 (0.0008) -[2023-10-09 08:28:37,228][23468] Updated weights for policy 0, policy_version 5020 (0.0008) -[2023-10-09 08:28:38,692][23469] Updated weights for policy 1, policy_version 5030 (0.0010) -[2023-10-09 08:28:39,056][23469] Updated weights for policy 1, policy_version 5040 (0.0009) -[2023-10-09 08:28:39,425][23469] Updated weights for policy 1, policy_version 5050 (0.0010) -[2023-10-09 08:28:40,950][23468] Updated weights for policy 0, policy_version 5030 (0.0007) -[2023-10-09 08:28:41,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 10321920. Throughput: 0: 1765.4, 1: 1786.5. Samples: 2588272. Policy #0 lag: (min: 15.0, avg: 38.3, max: 40.0) -[2023-10-09 08:28:41,078][22500] Avg episode reward: [(0, '5.200'), (1, '4.670')] -[2023-10-09 08:28:41,314][23468] Updated weights for policy 0, policy_version 5040 (0.0008) -[2023-10-09 08:28:41,698][23468] Updated weights for policy 0, policy_version 5050 (0.0010) -[2023-10-09 08:28:43,366][23469] Updated weights for policy 1, policy_version 5060 (0.0008) -[2023-10-09 08:28:43,736][23469] Updated weights for policy 1, policy_version 5070 (0.0009) -[2023-10-09 08:28:44,115][23469] Updated weights for policy 1, policy_version 5080 (0.0010) -[2023-10-09 08:28:45,309][23468] Updated weights for policy 0, policy_version 5060 (0.0008) -[2023-10-09 08:28:45,676][23468] Updated weights for policy 0, policy_version 5070 (0.0009) -[2023-10-09 08:28:46,045][23468] Updated weights for policy 0, policy_version 5080 (0.0008) -[2023-10-09 08:28:46,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 10387456. Throughput: 0: 1796.9, 1: 1781.0. Samples: 2610678. Policy #0 lag: (min: 27.0, avg: 35.1, max: 59.0) -[2023-10-09 08:28:46,078][22500] Avg episode reward: [(0, '5.300'), (1, '4.970')] -[2023-10-09 08:28:47,787][23469] Updated weights for policy 1, policy_version 5090 (0.0009) -[2023-10-09 08:28:48,164][23469] Updated weights for policy 1, policy_version 5100 (0.0009) -[2023-10-09 08:28:48,530][23469] Updated weights for policy 1, policy_version 5110 (0.0009) -[2023-10-09 08:28:48,897][23469] Updated weights for policy 1, policy_version 5120 (0.0009) -[2023-10-09 08:28:49,762][23468] Updated weights for policy 0, policy_version 5090 (0.0009) -[2023-10-09 08:28:50,135][23468] Updated weights for policy 0, policy_version 5100 (0.0008) -[2023-10-09 08:28:50,506][23468] Updated weights for policy 0, policy_version 5110 (0.0008) -[2023-10-09 08:28:50,884][23468] Updated weights for policy 0, policy_version 5120 (0.0008) -[2023-10-09 08:28:51,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 10485760. Throughput: 0: 1772.3, 1: 1791.1. Samples: 2620830. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:28:51,078][22500] Avg episode reward: [(0, '5.190'), (1, '4.860')] -[2023-10-09 08:28:52,701][23469] Updated weights for policy 1, policy_version 5130 (0.0009) -[2023-10-09 08:28:53,061][23469] Updated weights for policy 1, policy_version 5140 (0.0008) -[2023-10-09 08:28:53,435][23469] Updated weights for policy 1, policy_version 5150 (0.0007) -[2023-10-09 08:28:54,498][23468] Updated weights for policy 0, policy_version 5130 (0.0010) -[2023-10-09 08:28:54,876][23468] Updated weights for policy 0, policy_version 5140 (0.0010) -[2023-10-09 08:28:55,241][23468] Updated weights for policy 0, policy_version 5150 (0.0007) -[2023-10-09 08:28:56,077][22500] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 10551296. Throughput: 0: 1794.8, 1: 1780.4. Samples: 2643014. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:28:56,079][22500] Avg episode reward: [(0, '5.190'), (1, '4.850')] -[2023-10-09 08:28:57,299][23469] Updated weights for policy 1, policy_version 5160 (0.0007) -[2023-10-09 08:28:57,669][23469] Updated weights for policy 1, policy_version 5170 (0.0007) -[2023-10-09 08:28:58,038][23469] Updated weights for policy 1, policy_version 5180 (0.0007) -[2023-10-09 08:28:59,143][23468] Updated weights for policy 0, policy_version 5160 (0.0010) -[2023-10-09 08:28:59,516][23468] Updated weights for policy 0, policy_version 5170 (0.0008) -[2023-10-09 08:28:59,889][23468] Updated weights for policy 0, policy_version 5180 (0.0008) -[2023-10-09 08:29:01,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 10616832. Throughput: 0: 1779.7, 1: 1776.6. Samples: 2663826. Policy #0 lag: (min: 26.0, avg: 30.5, max: 58.0) -[2023-10-09 08:29:01,079][22500] Avg episode reward: [(0, '4.980'), (1, '4.880')] -[2023-10-09 08:29:01,996][23469] Updated weights for policy 1, policy_version 5190 (0.0007) -[2023-10-09 08:29:02,387][23469] Updated weights for policy 1, policy_version 5200 (0.0008) -[2023-10-09 08:29:02,757][23469] Updated weights for policy 1, policy_version 5210 (0.0009) -[2023-10-09 08:29:03,545][23468] Updated weights for policy 0, policy_version 5190 (0.0007) -[2023-10-09 08:29:03,916][23468] Updated weights for policy 0, policy_version 5200 (0.0009) -[2023-10-09 08:29:04,292][23468] Updated weights for policy 0, policy_version 5210 (0.0008) -[2023-10-09 08:29:06,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 10682368. Throughput: 0: 1799.5, 1: 1774.4. Samples: 2674966. Policy #0 lag: (min: 26.0, avg: 30.5, max: 58.0) -[2023-10-09 08:29:06,078][22500] Avg episode reward: [(0, '4.900'), (1, '4.950')] -[2023-10-09 08:29:06,448][23469] Updated weights for policy 1, policy_version 5220 (0.0008) -[2023-10-09 08:29:06,825][23469] Updated weights for policy 1, policy_version 5230 (0.0009) -[2023-10-09 08:29:07,185][23469] Updated weights for policy 1, policy_version 5240 (0.0008) -[2023-10-09 08:29:08,002][23468] Updated weights for policy 0, policy_version 5220 (0.0008) -[2023-10-09 08:29:08,382][23468] Updated weights for policy 0, policy_version 5230 (0.0010) -[2023-10-09 08:29:08,752][23468] Updated weights for policy 0, policy_version 5240 (0.0010) -[2023-10-09 08:29:11,075][23469] Updated weights for policy 1, policy_version 5250 (0.0009) -[2023-10-09 08:29:11,078][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 10747904. Throughput: 0: 1786.8, 1: 1772.9. Samples: 2696044. Policy #0 lag: (min: 1.0, avg: 9.9, max: 33.0) -[2023-10-09 08:29:11,079][22500] Avg episode reward: [(0, '4.960'), (1, '4.850')] -[2023-10-09 08:29:11,451][23469] Updated weights for policy 1, policy_version 5260 (0.0008) -[2023-10-09 08:29:11,826][23469] Updated weights for policy 1, policy_version 5270 (0.0008) -[2023-10-09 08:29:12,187][23469] Updated weights for policy 1, policy_version 5280 (0.0007) -[2023-10-09 08:29:12,680][23468] Updated weights for policy 0, policy_version 5250 (0.0011) -[2023-10-09 08:29:13,057][23468] Updated weights for policy 0, policy_version 5260 (0.0009) -[2023-10-09 08:29:13,430][23468] Updated weights for policy 0, policy_version 5270 (0.0009) -[2023-10-09 08:29:13,797][23468] Updated weights for policy 0, policy_version 5280 (0.0009) -[2023-10-09 08:29:15,914][23469] Updated weights for policy 1, policy_version 5290 (0.0007) -[2023-10-09 08:29:16,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 10813440. Throughput: 0: 1784.3, 1: 1796.0. Samples: 2717962. Policy #0 lag: (min: 1.0, avg: 9.9, max: 33.0) -[2023-10-09 08:29:16,079][22500] Avg episode reward: [(0, '5.100'), (1, '4.570')] -[2023-10-09 08:29:16,288][23469] Updated weights for policy 1, policy_version 5300 (0.0007) -[2023-10-09 08:29:16,658][23469] Updated weights for policy 1, policy_version 5310 (0.0009) -[2023-10-09 08:29:17,473][23468] Updated weights for policy 0, policy_version 5290 (0.0008) -[2023-10-09 08:29:17,849][23468] Updated weights for policy 0, policy_version 5300 (0.0008) -[2023-10-09 08:29:18,213][23468] Updated weights for policy 0, policy_version 5310 (0.0007) -[2023-10-09 08:29:20,306][23469] Updated weights for policy 1, policy_version 5320 (0.0008) -[2023-10-09 08:29:20,681][23469] Updated weights for policy 1, policy_version 5330 (0.0010) -[2023-10-09 08:29:21,053][23469] Updated weights for policy 1, policy_version 5340 (0.0008) -[2023-10-09 08:29:21,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 10878976. Throughput: 0: 1789.5, 1: 1772.6. Samples: 2728200. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:29:21,078][22500] Avg episode reward: [(0, '5.060'), (1, '4.870')] -[2023-10-09 08:29:22,110][23468] Updated weights for policy 0, policy_version 5320 (0.0009) -[2023-10-09 08:29:22,489][23468] Updated weights for policy 0, policy_version 5330 (0.0009) -[2023-10-09 08:29:22,864][23468] Updated weights for policy 0, policy_version 5340 (0.0011) -[2023-10-09 08:29:24,775][23469] Updated weights for policy 1, policy_version 5350 (0.0009) -[2023-10-09 08:29:25,132][23469] Updated weights for policy 1, policy_version 5360 (0.0008) -[2023-10-09 08:29:25,497][23469] Updated weights for policy 1, policy_version 5370 (0.0008) -[2023-10-09 08:29:26,077][22500] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 10977280. Throughput: 0: 1794.3, 1: 1798.8. Samples: 2749960. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:29:26,078][22500] Avg episode reward: [(0, '4.800'), (1, '4.720')] -[2023-10-09 08:29:26,667][23468] Updated weights for policy 0, policy_version 5350 (0.0008) -[2023-10-09 08:29:27,035][23468] Updated weights for policy 0, policy_version 5360 (0.0007) -[2023-10-09 08:29:27,403][23468] Updated weights for policy 0, policy_version 5370 (0.0007) -[2023-10-09 08:29:29,188][23469] Updated weights for policy 1, policy_version 5380 (0.0007) -[2023-10-09 08:29:29,566][23469] Updated weights for policy 1, policy_version 5390 (0.0009) -[2023-10-09 08:29:29,933][23469] Updated weights for policy 1, policy_version 5400 (0.0008) -[2023-10-09 08:29:31,078][22500] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 11042816. Throughput: 0: 1787.8, 1: 1781.5. Samples: 2771298. Policy #0 lag: (min: 4.0, avg: 4.3, max: 16.0) -[2023-10-09 08:29:31,079][22500] Avg episode reward: [(0, '4.730'), (1, '4.580')] -[2023-10-09 08:29:31,259][23468] Updated weights for policy 0, policy_version 5380 (0.0009) -[2023-10-09 08:29:31,630][23468] Updated weights for policy 0, policy_version 5390 (0.0011) -[2023-10-09 08:29:32,002][23468] Updated weights for policy 0, policy_version 5400 (0.0011) -[2023-10-09 08:29:33,636][23469] Updated weights for policy 1, policy_version 5410 (0.0008) -[2023-10-09 08:29:34,017][23469] Updated weights for policy 1, policy_version 5420 (0.0009) -[2023-10-09 08:29:34,390][23469] Updated weights for policy 1, policy_version 5430 (0.0007) -[2023-10-09 08:29:34,769][23469] Updated weights for policy 1, policy_version 5440 (0.0008) -[2023-10-09 08:29:35,813][23468] Updated weights for policy 0, policy_version 5410 (0.0009) -[2023-10-09 08:29:36,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 11108352. Throughput: 0: 1782.5, 1: 1804.9. Samples: 2782260. Policy #0 lag: (min: 4.0, avg: 4.3, max: 16.0) -[2023-10-09 08:29:36,078][22500] Avg episode reward: [(0, '4.720'), (1, '4.570')] -[2023-10-09 08:29:36,190][23468] Updated weights for policy 0, policy_version 5420 (0.0009) -[2023-10-09 08:29:36,553][23468] Updated weights for policy 0, policy_version 5430 (0.0010) -[2023-10-09 08:29:36,919][23468] Updated weights for policy 0, policy_version 5440 (0.0009) -[2023-10-09 08:29:38,737][23469] Updated weights for policy 1, policy_version 5450 (0.0009) -[2023-10-09 08:29:39,109][23469] Updated weights for policy 1, policy_version 5460 (0.0009) -[2023-10-09 08:29:39,481][23469] Updated weights for policy 1, policy_version 5470 (0.0007) -[2023-10-09 08:29:40,556][23468] Updated weights for policy 0, policy_version 5450 (0.0007) -[2023-10-09 08:29:40,920][23468] Updated weights for policy 0, policy_version 5460 (0.0011) -[2023-10-09 08:29:41,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 11173888. Throughput: 0: 1782.3, 1: 1779.8. Samples: 2803308. Policy #0 lag: (min: 2.0, avg: 8.6, max: 34.0) -[2023-10-09 08:29:41,078][22500] Avg episode reward: [(0, '4.750'), (1, '4.240')] -[2023-10-09 08:29:41,297][23468] Updated weights for policy 0, policy_version 5470 (0.0008) -[2023-10-09 08:29:43,177][23469] Updated weights for policy 1, policy_version 5480 (0.0008) -[2023-10-09 08:29:43,540][23469] Updated weights for policy 1, policy_version 5490 (0.0008) -[2023-10-09 08:29:43,910][23469] Updated weights for policy 1, policy_version 5500 (0.0008) -[2023-10-09 08:29:45,114][23468] Updated weights for policy 0, policy_version 5480 (0.0008) -[2023-10-09 08:29:45,508][23468] Updated weights for policy 0, policy_version 5490 (0.0010) -[2023-10-09 08:29:45,885][23468] Updated weights for policy 0, policy_version 5500 (0.0009) -[2023-10-09 08:29:46,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 11272192. Throughput: 0: 1799.7, 1: 1782.5. Samples: 2825028. Policy #0 lag: (min: 17.0, avg: 25.6, max: 49.0) -[2023-10-09 08:29:46,078][22500] Avg episode reward: [(0, '4.700'), (1, '4.650')] -[2023-10-09 08:29:47,720][23469] Updated weights for policy 1, policy_version 5510 (0.0007) -[2023-10-09 08:29:48,111][23469] Updated weights for policy 1, policy_version 5520 (0.0008) -[2023-10-09 08:29:48,481][23469] Updated weights for policy 1, policy_version 5530 (0.0008) -[2023-10-09 08:29:49,631][23468] Updated weights for policy 0, policy_version 5510 (0.0008) -[2023-10-09 08:29:50,003][23468] Updated weights for policy 0, policy_version 5520 (0.0007) -[2023-10-09 08:29:50,381][23468] Updated weights for policy 0, policy_version 5530 (0.0008) -[2023-10-09 08:29:51,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 11337728. Throughput: 0: 1774.9, 1: 1785.5. Samples: 2835182. Policy #0 lag: (min: 17.0, avg: 25.6, max: 49.0) -[2023-10-09 08:29:51,078][22500] Avg episode reward: [(0, '4.890'), (1, '4.520')] -[2023-10-09 08:29:52,274][23469] Updated weights for policy 1, policy_version 5540 (0.0009) -[2023-10-09 08:29:52,640][23469] Updated weights for policy 1, policy_version 5550 (0.0009) -[2023-10-09 08:29:53,017][23469] Updated weights for policy 1, policy_version 5560 (0.0007) -[2023-10-09 08:29:54,200][23468] Updated weights for policy 0, policy_version 5540 (0.0008) -[2023-10-09 08:29:54,571][23468] Updated weights for policy 0, policy_version 5550 (0.0007) -[2023-10-09 08:29:54,943][23468] Updated weights for policy 0, policy_version 5560 (0.0008) -[2023-10-09 08:29:56,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 11403264. Throughput: 0: 1798.0, 1: 1785.8. Samples: 2857314. Policy #0 lag: (min: 17.0, avg: 35.1, max: 49.0) -[2023-10-09 08:29:56,078][22500] Avg episode reward: [(0, '4.940'), (1, '4.910')] -[2023-10-09 08:29:56,792][23469] Updated weights for policy 1, policy_version 5570 (0.0007) -[2023-10-09 08:29:57,164][23469] Updated weights for policy 1, policy_version 5580 (0.0007) -[2023-10-09 08:29:57,537][23469] Updated weights for policy 1, policy_version 5590 (0.0008) -[2023-10-09 08:29:57,906][23469] Updated weights for policy 1, policy_version 5600 (0.0007) -[2023-10-09 08:29:58,709][23468] Updated weights for policy 0, policy_version 5570 (0.0008) -[2023-10-09 08:29:59,082][23468] Updated weights for policy 0, policy_version 5580 (0.0009) -[2023-10-09 08:29:59,455][23468] Updated weights for policy 0, policy_version 5590 (0.0009) -[2023-10-09 08:29:59,830][23468] Updated weights for policy 0, policy_version 5600 (0.0007) -[2023-10-09 08:30:01,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 11468800. Throughput: 0: 1773.4, 1: 1795.3. Samples: 2878554. Policy #0 lag: (min: 17.0, avg: 35.1, max: 49.0) -[2023-10-09 08:30:01,079][22500] Avg episode reward: [(0, '5.060'), (1, '4.920')] -[2023-10-09 08:30:01,727][23469] Updated weights for policy 1, policy_version 5610 (0.0009) -[2023-10-09 08:30:02,093][23469] Updated weights for policy 1, policy_version 5620 (0.0007) -[2023-10-09 08:30:02,464][23469] Updated weights for policy 1, policy_version 5630 (0.0007) -[2023-10-09 08:30:03,707][23468] Updated weights for policy 0, policy_version 5610 (0.0008) -[2023-10-09 08:30:04,088][23468] Updated weights for policy 0, policy_version 5620 (0.0007) -[2023-10-09 08:30:04,464][23468] Updated weights for policy 0, policy_version 5630 (0.0011) -[2023-10-09 08:30:06,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 11534336. Throughput: 0: 1803.4, 1: 1788.1. Samples: 2889816. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 08:30:06,078][22500] Avg episode reward: [(0, '5.270'), (1, '5.210')] -[2023-10-09 08:30:06,105][23469] Updated weights for policy 1, policy_version 5640 (0.0009) -[2023-10-09 08:30:06,476][23469] Updated weights for policy 1, policy_version 5650 (0.0009) -[2023-10-09 08:30:06,854][23469] Updated weights for policy 1, policy_version 5660 (0.0011) -[2023-10-09 08:30:08,172][23468] Updated weights for policy 0, policy_version 5640 (0.0008) -[2023-10-09 08:30:08,534][23468] Updated weights for policy 0, policy_version 5650 (0.0007) -[2023-10-09 08:30:08,908][23468] Updated weights for policy 0, policy_version 5660 (0.0008) -[2023-10-09 08:30:10,509][23469] Updated weights for policy 1, policy_version 5670 (0.0009) -[2023-10-09 08:30:10,878][23469] Updated weights for policy 1, policy_version 5680 (0.0010) -[2023-10-09 08:30:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 11599872. Throughput: 0: 1775.8, 1: 1796.7. Samples: 2910720. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 08:30:11,078][22500] Avg episode reward: [(0, '5.030'), (1, '5.200')] -[2023-10-09 08:30:11,260][23469] Updated weights for policy 1, policy_version 5690 (0.0010) -[2023-10-09 08:30:12,675][23468] Updated weights for policy 0, policy_version 5670 (0.0007) -[2023-10-09 08:30:13,054][23468] Updated weights for policy 0, policy_version 5680 (0.0008) -[2023-10-09 08:30:13,420][23468] Updated weights for policy 0, policy_version 5690 (0.0010) -[2023-10-09 08:30:15,146][23469] Updated weights for policy 1, policy_version 5700 (0.0009) -[2023-10-09 08:30:15,513][23469] Updated weights for policy 1, policy_version 5710 (0.0007) -[2023-10-09 08:30:15,884][23469] Updated weights for policy 1, policy_version 5720 (0.0009) -[2023-10-09 08:30:16,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 11665408. Throughput: 0: 1773.3, 1: 1797.0. Samples: 2931960. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:30:16,078][22500] Avg episode reward: [(0, '5.010'), (1, '5.160')] -[2023-10-09 08:30:16,088][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000005696_5832704.pth... -[2023-10-09 08:30:16,122][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000004032_4128768.pth -[2023-10-09 08:30:16,179][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000005728_5865472.pth... -[2023-10-09 08:30:16,208][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000004032_4128768.pth -[2023-10-09 08:30:17,258][23468] Updated weights for policy 0, policy_version 5700 (0.0011) -[2023-10-09 08:30:17,627][23468] Updated weights for policy 0, policy_version 5710 (0.0009) -[2023-10-09 08:30:18,001][23468] Updated weights for policy 0, policy_version 5720 (0.0009) -[2023-10-09 08:30:19,561][23469] Updated weights for policy 1, policy_version 5730 (0.0008) -[2023-10-09 08:30:19,934][23469] Updated weights for policy 1, policy_version 5740 (0.0009) -[2023-10-09 08:30:20,295][23469] Updated weights for policy 1, policy_version 5750 (0.0008) -[2023-10-09 08:30:20,670][23469] Updated weights for policy 1, policy_version 5760 (0.0008) -[2023-10-09 08:30:21,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 11763712. Throughput: 0: 1778.3, 1: 1787.6. Samples: 2942724. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:30:21,078][22500] Avg episode reward: [(0, '4.950'), (1, '5.200')] -[2023-10-09 08:30:21,782][23468] Updated weights for policy 0, policy_version 5730 (0.0007) -[2023-10-09 08:30:22,149][23468] Updated weights for policy 0, policy_version 5740 (0.0008) -[2023-10-09 08:30:22,531][23468] Updated weights for policy 0, policy_version 5750 (0.0007) -[2023-10-09 08:30:22,893][23468] Updated weights for policy 0, policy_version 5760 (0.0007) -[2023-10-09 08:30:24,451][23469] Updated weights for policy 1, policy_version 5770 (0.0008) -[2023-10-09 08:30:24,828][23469] Updated weights for policy 1, policy_version 5780 (0.0007) -[2023-10-09 08:30:25,196][23469] Updated weights for policy 1, policy_version 5790 (0.0008) -[2023-10-09 08:30:26,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 11829248. Throughput: 0: 1775.0, 1: 1804.0. Samples: 2964362. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:30:26,079][22500] Avg episode reward: [(0, '4.880'), (1, '5.160')] -[2023-10-09 08:30:26,689][23468] Updated weights for policy 0, policy_version 5770 (0.0009) -[2023-10-09 08:30:27,054][23468] Updated weights for policy 0, policy_version 5780 (0.0008) -[2023-10-09 08:30:27,423][23468] Updated weights for policy 0, policy_version 5790 (0.0011) -[2023-10-09 08:30:28,862][23469] Updated weights for policy 1, policy_version 5800 (0.0010) -[2023-10-09 08:30:29,232][23469] Updated weights for policy 1, policy_version 5810 (0.0008) -[2023-10-09 08:30:29,607][23469] Updated weights for policy 1, policy_version 5820 (0.0007) -[2023-10-09 08:30:31,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 11894784. Throughput: 0: 1786.8, 1: 1793.4. Samples: 2986140. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:30:31,078][22500] Avg episode reward: [(0, '5.170'), (1, '5.570')] -[2023-10-09 08:30:31,085][23343] Saving new best policy, reward=5.570! -[2023-10-09 08:30:31,337][23468] Updated weights for policy 0, policy_version 5800 (0.0009) -[2023-10-09 08:30:31,722][23468] Updated weights for policy 0, policy_version 5810 (0.0007) -[2023-10-09 08:30:32,093][23468] Updated weights for policy 0, policy_version 5820 (0.0008) -[2023-10-09 08:30:33,468][23469] Updated weights for policy 1, policy_version 5830 (0.0007) -[2023-10-09 08:30:33,851][23469] Updated weights for policy 1, policy_version 5840 (0.0009) -[2023-10-09 08:30:34,221][23469] Updated weights for policy 1, policy_version 5850 (0.0011) -[2023-10-09 08:30:35,786][23468] Updated weights for policy 0, policy_version 5830 (0.0010) -[2023-10-09 08:30:36,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 11960320. Throughput: 0: 1770.8, 1: 1812.9. Samples: 2996448. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:30:36,078][22500] Avg episode reward: [(0, '4.910'), (1, '5.340')] -[2023-10-09 08:30:36,151][23468] Updated weights for policy 0, policy_version 5840 (0.0011) -[2023-10-09 08:30:36,528][23468] Updated weights for policy 0, policy_version 5850 (0.0009) -[2023-10-09 08:30:37,818][23469] Updated weights for policy 1, policy_version 5860 (0.0008) -[2023-10-09 08:30:38,188][23469] Updated weights for policy 1, policy_version 5870 (0.0010) -[2023-10-09 08:30:38,549][23469] Updated weights for policy 1, policy_version 5880 (0.0010) -[2023-10-09 08:30:40,293][23468] Updated weights for policy 0, policy_version 5860 (0.0009) -[2023-10-09 08:30:40,660][23468] Updated weights for policy 0, policy_version 5870 (0.0010) -[2023-10-09 08:30:41,043][23468] Updated weights for policy 0, policy_version 5880 (0.0009) -[2023-10-09 08:30:41,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 12025856. Throughput: 0: 1779.1, 1: 1792.0. Samples: 3018016. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:30:41,078][22500] Avg episode reward: [(0, '4.860'), (1, '5.140')] -[2023-10-09 08:30:42,231][23469] Updated weights for policy 1, policy_version 5890 (0.0008) -[2023-10-09 08:30:42,607][23469] Updated weights for policy 1, policy_version 5900 (0.0007) -[2023-10-09 08:30:42,973][23469] Updated weights for policy 1, policy_version 5910 (0.0011) -[2023-10-09 08:30:43,338][23469] Updated weights for policy 1, policy_version 5920 (0.0008) -[2023-10-09 08:30:44,731][23468] Updated weights for policy 0, policy_version 5890 (0.0010) -[2023-10-09 08:30:45,102][23468] Updated weights for policy 0, policy_version 5900 (0.0008) -[2023-10-09 08:30:45,471][23468] Updated weights for policy 0, policy_version 5910 (0.0007) -[2023-10-09 08:30:45,840][23468] Updated weights for policy 0, policy_version 5920 (0.0008) -[2023-10-09 08:30:46,078][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 12124160. Throughput: 0: 1787.9, 1: 1794.7. Samples: 3039768. Policy #0 lag: (min: 31.0, avg: 41.9, max: 63.0) -[2023-10-09 08:30:46,079][22500] Avg episode reward: [(0, '4.960'), (1, '4.760')] -[2023-10-09 08:30:47,067][23469] Updated weights for policy 1, policy_version 5930 (0.0007) -[2023-10-09 08:30:47,430][23469] Updated weights for policy 1, policy_version 5940 (0.0007) -[2023-10-09 08:30:47,793][23469] Updated weights for policy 1, policy_version 5950 (0.0008) -[2023-10-09 08:30:49,593][23468] Updated weights for policy 0, policy_version 5930 (0.0008) -[2023-10-09 08:30:49,970][23468] Updated weights for policy 0, policy_version 5940 (0.0009) -[2023-10-09 08:30:50,340][23468] Updated weights for policy 0, policy_version 5950 (0.0008) -[2023-10-09 08:30:51,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 12189696. Throughput: 0: 1774.1, 1: 1793.0. Samples: 3050334. Policy #0 lag: (min: 17.0, avg: 32.0, max: 49.0) -[2023-10-09 08:30:51,078][22500] Avg episode reward: [(0, '5.010'), (1, '4.650')] -[2023-10-09 08:30:51,650][23469] Updated weights for policy 1, policy_version 5960 (0.0009) -[2023-10-09 08:30:52,012][23469] Updated weights for policy 1, policy_version 5970 (0.0008) -[2023-10-09 08:30:52,379][23469] Updated weights for policy 1, policy_version 5980 (0.0007) -[2023-10-09 08:30:54,181][23468] Updated weights for policy 0, policy_version 5960 (0.0008) -[2023-10-09 08:30:54,554][23468] Updated weights for policy 0, policy_version 5970 (0.0007) -[2023-10-09 08:30:54,933][23468] Updated weights for policy 0, policy_version 5980 (0.0008) -[2023-10-09 08:30:56,064][23469] Updated weights for policy 1, policy_version 5990 (0.0007) -[2023-10-09 08:30:56,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 12255232. Throughput: 0: 1789.3, 1: 1793.0. Samples: 3071924. Policy #0 lag: (min: 17.0, avg: 32.0, max: 49.0) -[2023-10-09 08:30:56,079][22500] Avg episode reward: [(0, '5.300'), (1, '4.860')] -[2023-10-09 08:30:56,441][23469] Updated weights for policy 1, policy_version 6000 (0.0008) -[2023-10-09 08:30:56,819][23469] Updated weights for policy 1, policy_version 6010 (0.0009) -[2023-10-09 08:30:58,720][23468] Updated weights for policy 0, policy_version 5990 (0.0007) -[2023-10-09 08:30:59,089][23468] Updated weights for policy 0, policy_version 6000 (0.0009) -[2023-10-09 08:30:59,459][23468] Updated weights for policy 0, policy_version 6010 (0.0007) -[2023-10-09 08:31:00,608][23469] Updated weights for policy 1, policy_version 6020 (0.0009) -[2023-10-09 08:31:00,984][23469] Updated weights for policy 1, policy_version 6030 (0.0011) -[2023-10-09 08:31:01,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 12320768. Throughput: 0: 1769.3, 1: 1802.0. Samples: 3092670. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:31:01,078][22500] Avg episode reward: [(0, '5.230'), (1, '4.600')] -[2023-10-09 08:31:01,348][23469] Updated weights for policy 1, policy_version 6040 (0.0009) -[2023-10-09 08:31:03,391][23468] Updated weights for policy 0, policy_version 6020 (0.0008) -[2023-10-09 08:31:03,761][23468] Updated weights for policy 0, policy_version 6030 (0.0008) -[2023-10-09 08:31:04,130][23468] Updated weights for policy 0, policy_version 6040 (0.0007) -[2023-10-09 08:31:05,058][23469] Updated weights for policy 1, policy_version 6050 (0.0009) -[2023-10-09 08:31:05,425][23469] Updated weights for policy 1, policy_version 6060 (0.0008) -[2023-10-09 08:31:05,803][23469] Updated weights for policy 1, policy_version 6070 (0.0008) -[2023-10-09 08:31:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 12386304. Throughput: 0: 1795.1, 1: 1793.1. Samples: 3104196. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:31:06,079][22500] Avg episode reward: [(0, '5.460'), (1, '4.370')] -[2023-10-09 08:31:06,080][23265] Saving new best policy, reward=5.460! -[2023-10-09 08:31:06,176][23469] Updated weights for policy 1, policy_version 6080 (0.0009) -[2023-10-09 08:31:07,805][23468] Updated weights for policy 0, policy_version 6050 (0.0009) -[2023-10-09 08:31:08,176][23468] Updated weights for policy 0, policy_version 6060 (0.0011) -[2023-10-09 08:31:08,544][23468] Updated weights for policy 0, policy_version 6070 (0.0010) -[2023-10-09 08:31:08,917][23468] Updated weights for policy 0, policy_version 6080 (0.0010) -[2023-10-09 08:31:09,846][23469] Updated weights for policy 1, policy_version 6090 (0.0008) -[2023-10-09 08:31:10,216][23469] Updated weights for policy 1, policy_version 6100 (0.0009) -[2023-10-09 08:31:10,594][23469] Updated weights for policy 1, policy_version 6110 (0.0009) -[2023-10-09 08:31:11,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 12484608. Throughput: 0: 1762.0, 1: 1803.3. Samples: 3124800. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:31:11,078][22500] Avg episode reward: [(0, '5.070'), (1, '4.820')] -[2023-10-09 08:31:12,706][23468] Updated weights for policy 0, policy_version 6090 (0.0008) -[2023-10-09 08:31:13,084][23468] Updated weights for policy 0, policy_version 6100 (0.0009) -[2023-10-09 08:31:13,456][23468] Updated weights for policy 0, policy_version 6110 (0.0011) -[2023-10-09 08:31:14,275][23469] Updated weights for policy 1, policy_version 6120 (0.0008) -[2023-10-09 08:31:14,652][23469] Updated weights for policy 1, policy_version 6130 (0.0009) -[2023-10-09 08:31:15,011][23469] Updated weights for policy 1, policy_version 6140 (0.0009) -[2023-10-09 08:31:16,078][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 12550144. Throughput: 0: 1764.0, 1: 1790.3. Samples: 3146084. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:31:16,079][22500] Avg episode reward: [(0, '5.110'), (1, '5.100')] -[2023-10-09 08:31:17,392][23468] Updated weights for policy 0, policy_version 6120 (0.0010) -[2023-10-09 08:31:17,772][23468] Updated weights for policy 0, policy_version 6130 (0.0009) -[2023-10-09 08:31:18,146][23468] Updated weights for policy 0, policy_version 6140 (0.0009) -[2023-10-09 08:31:18,939][23469] Updated weights for policy 1, policy_version 6150 (0.0007) -[2023-10-09 08:31:19,341][23469] Updated weights for policy 1, policy_version 6160 (0.0007) -[2023-10-09 08:31:19,702][23469] Updated weights for policy 1, policy_version 6170 (0.0008) -[2023-10-09 08:31:21,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 12615680. Throughput: 0: 1768.2, 1: 1799.9. Samples: 3157012. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-09 08:31:21,078][22500] Avg episode reward: [(0, '5.150'), (1, '5.120')] -[2023-10-09 08:31:21,980][23468] Updated weights for policy 0, policy_version 6150 (0.0009) -[2023-10-09 08:31:22,361][23468] Updated weights for policy 0, policy_version 6160 (0.0007) -[2023-10-09 08:31:22,741][23468] Updated weights for policy 0, policy_version 6170 (0.0008) -[2023-10-09 08:31:23,607][23469] Updated weights for policy 1, policy_version 6180 (0.0009) -[2023-10-09 08:31:23,981][23469] Updated weights for policy 1, policy_version 6190 (0.0010) -[2023-10-09 08:31:24,351][23469] Updated weights for policy 1, policy_version 6200 (0.0007) -[2023-10-09 08:31:26,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 12681216. Throughput: 0: 1761.0, 1: 1780.2. Samples: 3177368. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-09 08:31:26,079][22500] Avg episode reward: [(0, '5.160'), (1, '5.020')] -[2023-10-09 08:31:26,495][23468] Updated weights for policy 0, policy_version 6180 (0.0008) -[2023-10-09 08:31:26,864][23468] Updated weights for policy 0, policy_version 6190 (0.0007) -[2023-10-09 08:31:27,235][23468] Updated weights for policy 0, policy_version 6200 (0.0007) -[2023-10-09 08:31:28,084][23469] Updated weights for policy 1, policy_version 6210 (0.0007) -[2023-10-09 08:31:28,454][23469] Updated weights for policy 1, policy_version 6220 (0.0008) -[2023-10-09 08:31:28,822][23469] Updated weights for policy 1, policy_version 6230 (0.0008) -[2023-10-09 08:31:29,191][23469] Updated weights for policy 1, policy_version 6240 (0.0008) -[2023-10-09 08:31:30,925][23468] Updated weights for policy 0, policy_version 6210 (0.0007) -[2023-10-09 08:31:31,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 12746752. Throughput: 0: 1779.3, 1: 1775.9. Samples: 3199748. Policy #0 lag: (min: 30.0, avg: 35.8, max: 62.0) -[2023-10-09 08:31:31,078][22500] Avg episode reward: [(0, '5.220'), (1, '5.330')] -[2023-10-09 08:31:31,295][23468] Updated weights for policy 0, policy_version 6220 (0.0008) -[2023-10-09 08:31:31,663][23468] Updated weights for policy 0, policy_version 6230 (0.0007) -[2023-10-09 08:31:32,030][23468] Updated weights for policy 0, policy_version 6240 (0.0008) -[2023-10-09 08:31:32,951][23469] Updated weights for policy 1, policy_version 6250 (0.0008) -[2023-10-09 08:31:33,317][23469] Updated weights for policy 1, policy_version 6260 (0.0007) -[2023-10-09 08:31:33,693][23469] Updated weights for policy 1, policy_version 6270 (0.0007) -[2023-10-09 08:31:35,797][23468] Updated weights for policy 0, policy_version 6250 (0.0008) -[2023-10-09 08:31:36,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 12812288. Throughput: 0: 1760.1, 1: 1777.7. Samples: 3209534. Policy #0 lag: (min: 30.0, avg: 35.8, max: 62.0) -[2023-10-09 08:31:36,078][22500] Avg episode reward: [(0, '5.040'), (1, '4.800')] -[2023-10-09 08:31:36,166][23468] Updated weights for policy 0, policy_version 6260 (0.0008) -[2023-10-09 08:31:36,546][23468] Updated weights for policy 0, policy_version 6270 (0.0008) -[2023-10-09 08:31:37,426][23469] Updated weights for policy 1, policy_version 6280 (0.0011) -[2023-10-09 08:31:37,794][23469] Updated weights for policy 1, policy_version 6290 (0.0010) -[2023-10-09 08:31:38,161][23469] Updated weights for policy 1, policy_version 6300 (0.0008) -[2023-10-09 08:31:40,191][23468] Updated weights for policy 0, policy_version 6280 (0.0009) -[2023-10-09 08:31:40,563][23468] Updated weights for policy 0, policy_version 6290 (0.0007) -[2023-10-09 08:31:40,943][23468] Updated weights for policy 0, policy_version 6300 (0.0007) -[2023-10-09 08:31:41,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 12877824. Throughput: 0: 1782.7, 1: 1773.6. Samples: 3231960. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:31:41,079][22500] Avg episode reward: [(0, '4.940'), (1, '4.730')] -[2023-10-09 08:31:41,948][23469] Updated weights for policy 1, policy_version 6310 (0.0008) -[2023-10-09 08:31:42,314][23469] Updated weights for policy 1, policy_version 6320 (0.0010) -[2023-10-09 08:31:42,689][23469] Updated weights for policy 1, policy_version 6330 (0.0007) -[2023-10-09 08:31:44,827][23468] Updated weights for policy 0, policy_version 6310 (0.0008) -[2023-10-09 08:31:45,192][23468] Updated weights for policy 0, policy_version 6320 (0.0007) -[2023-10-09 08:31:45,570][23468] Updated weights for policy 0, policy_version 6330 (0.0009) -[2023-10-09 08:31:46,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 12976128. Throughput: 0: 1784.3, 1: 1789.7. Samples: 3253498. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-09 08:31:46,078][22500] Avg episode reward: [(0, '4.680'), (1, '4.850')] -[2023-10-09 08:31:46,453][23469] Updated weights for policy 1, policy_version 6340 (0.0009) -[2023-10-09 08:31:46,828][23469] Updated weights for policy 1, policy_version 6350 (0.0007) -[2023-10-09 08:31:47,197][23469] Updated weights for policy 1, policy_version 6360 (0.0008) -[2023-10-09 08:31:49,409][23468] Updated weights for policy 0, policy_version 6340 (0.0007) -[2023-10-09 08:31:49,793][23468] Updated weights for policy 0, policy_version 6350 (0.0008) -[2023-10-09 08:31:50,158][23468] Updated weights for policy 0, policy_version 6360 (0.0009) -[2023-10-09 08:31:51,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 13041664. Throughput: 0: 1773.7, 1: 1777.5. Samples: 3264000. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-09 08:31:51,078][22500] Avg episode reward: [(0, '5.060'), (1, '5.200')] -[2023-10-09 08:31:51,082][23469] Updated weights for policy 1, policy_version 6370 (0.0010) -[2023-10-09 08:31:51,457][23469] Updated weights for policy 1, policy_version 6380 (0.0007) -[2023-10-09 08:31:51,824][23469] Updated weights for policy 1, policy_version 6390 (0.0008) -[2023-10-09 08:31:52,195][23469] Updated weights for policy 1, policy_version 6400 (0.0011) -[2023-10-09 08:31:53,865][23468] Updated weights for policy 0, policy_version 6370 (0.0008) -[2023-10-09 08:31:54,239][23468] Updated weights for policy 0, policy_version 6380 (0.0007) -[2023-10-09 08:31:54,618][23468] Updated weights for policy 0, policy_version 6390 (0.0007) -[2023-10-09 08:31:54,992][23468] Updated weights for policy 0, policy_version 6400 (0.0009) -[2023-10-09 08:31:55,920][23469] Updated weights for policy 1, policy_version 6410 (0.0010) -[2023-10-09 08:31:56,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 13107200. Throughput: 0: 1793.7, 1: 1778.2. Samples: 3285536. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-09 08:31:56,078][22500] Avg episode reward: [(0, '5.020'), (1, '5.210')] -[2023-10-09 08:31:56,286][23469] Updated weights for policy 1, policy_version 6420 (0.0007) -[2023-10-09 08:31:56,662][23469] Updated weights for policy 1, policy_version 6430 (0.0009) -[2023-10-09 08:31:58,778][23468] Updated weights for policy 0, policy_version 6410 (0.0007) -[2023-10-09 08:31:59,147][23468] Updated weights for policy 0, policy_version 6420 (0.0008) -[2023-10-09 08:31:59,523][23468] Updated weights for policy 0, policy_version 6430 (0.0009) -[2023-10-09 08:32:00,453][23469] Updated weights for policy 1, policy_version 6440 (0.0008) -[2023-10-09 08:32:00,821][23469] Updated weights for policy 1, policy_version 6450 (0.0008) -[2023-10-09 08:32:01,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 13172736. Throughput: 0: 1779.1, 1: 1786.9. Samples: 3306552. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-09 08:32:01,078][22500] Avg episode reward: [(0, '5.390'), (1, '5.130')] -[2023-10-09 08:32:01,196][23469] Updated weights for policy 1, policy_version 6460 (0.0010) -[2023-10-09 08:32:03,227][23468] Updated weights for policy 0, policy_version 6440 (0.0010) -[2023-10-09 08:32:03,603][23468] Updated weights for policy 0, policy_version 6450 (0.0010) -[2023-10-09 08:32:03,973][23468] Updated weights for policy 0, policy_version 6460 (0.0008) -[2023-10-09 08:32:04,899][23469] Updated weights for policy 1, policy_version 6470 (0.0010) -[2023-10-09 08:32:05,271][23469] Updated weights for policy 1, policy_version 6480 (0.0009) -[2023-10-09 08:32:05,643][23469] Updated weights for policy 1, policy_version 6490 (0.0010) -[2023-10-09 08:32:06,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 13271040. Throughput: 0: 1801.5, 1: 1777.5. Samples: 3318066. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:32:06,078][22500] Avg episode reward: [(0, '5.210'), (1, '5.360')] -[2023-10-09 08:32:07,792][23468] Updated weights for policy 0, policy_version 6470 (0.0009) -[2023-10-09 08:32:08,156][23468] Updated weights for policy 0, policy_version 6480 (0.0010) -[2023-10-09 08:32:08,535][23468] Updated weights for policy 0, policy_version 6490 (0.0010) -[2023-10-09 08:32:09,268][23469] Updated weights for policy 1, policy_version 6500 (0.0008) -[2023-10-09 08:32:09,650][23469] Updated weights for policy 1, policy_version 6510 (0.0007) -[2023-10-09 08:32:10,015][23469] Updated weights for policy 1, policy_version 6520 (0.0009) -[2023-10-09 08:32:11,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 13336576. Throughput: 0: 1783.7, 1: 1800.8. Samples: 3338670. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:32:11,078][22500] Avg episode reward: [(0, '5.270'), (1, '5.520')] -[2023-10-09 08:32:12,026][23468] Updated weights for policy 0, policy_version 6500 (0.0009) -[2023-10-09 08:32:12,393][23468] Updated weights for policy 0, policy_version 6510 (0.0007) -[2023-10-09 08:32:12,765][23468] Updated weights for policy 0, policy_version 6520 (0.0007) -[2023-10-09 08:32:13,793][23469] Updated weights for policy 1, policy_version 6530 (0.0009) -[2023-10-09 08:32:14,155][23469] Updated weights for policy 1, policy_version 6540 (0.0009) -[2023-10-09 08:32:14,527][23469] Updated weights for policy 1, policy_version 6550 (0.0007) -[2023-10-09 08:32:14,903][23469] Updated weights for policy 1, policy_version 6560 (0.0008) -[2023-10-09 08:32:16,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 13402112. Throughput: 0: 1788.1, 1: 1784.6. Samples: 3360520. Policy #0 lag: (min: 6.0, avg: 28.5, max: 32.0) -[2023-10-09 08:32:16,078][22500] Avg episode reward: [(0, '5.040'), (1, '5.390')] -[2023-10-09 08:32:16,088][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000006560_6717440.pth... -[2023-10-09 08:32:16,088][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000006528_6684672.pth... -[2023-10-09 08:32:16,126][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000004896_5013504.pth -[2023-10-09 08:32:16,130][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000004864_4980736.pth -[2023-10-09 08:32:16,493][23468] Updated weights for policy 0, policy_version 6530 (0.0010) -[2023-10-09 08:32:16,878][23468] Updated weights for policy 0, policy_version 6540 (0.0009) -[2023-10-09 08:32:17,252][23468] Updated weights for policy 0, policy_version 6550 (0.0009) -[2023-10-09 08:32:17,630][23468] Updated weights for policy 0, policy_version 6560 (0.0009) -[2023-10-09 08:32:18,641][23469] Updated weights for policy 1, policy_version 6570 (0.0011) -[2023-10-09 08:32:19,008][23469] Updated weights for policy 1, policy_version 6580 (0.0010) -[2023-10-09 08:32:19,374][23469] Updated weights for policy 1, policy_version 6590 (0.0011) -[2023-10-09 08:32:21,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 13467648. Throughput: 0: 1784.8, 1: 1805.8. Samples: 3371112. Policy #0 lag: (min: 6.0, avg: 28.5, max: 32.0) -[2023-10-09 08:32:21,079][22500] Avg episode reward: [(0, '5.060'), (1, '5.270')] -[2023-10-09 08:32:21,546][23468] Updated weights for policy 0, policy_version 6570 (0.0007) -[2023-10-09 08:32:21,919][23468] Updated weights for policy 0, policy_version 6580 (0.0010) -[2023-10-09 08:32:22,308][23468] Updated weights for policy 0, policy_version 6590 (0.0009) -[2023-10-09 08:32:23,207][23469] Updated weights for policy 1, policy_version 6600 (0.0009) -[2023-10-09 08:32:23,579][23469] Updated weights for policy 1, policy_version 6610 (0.0008) -[2023-10-09 08:32:23,950][23469] Updated weights for policy 1, policy_version 6620 (0.0009) -[2023-10-09 08:32:26,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 13533184. Throughput: 0: 1781.2, 1: 1790.1. Samples: 3392670. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:32:26,079][22500] Avg episode reward: [(0, '4.790'), (1, '5.060')] -[2023-10-09 08:32:26,125][23468] Updated weights for policy 0, policy_version 6600 (0.0008) -[2023-10-09 08:32:26,500][23468] Updated weights for policy 0, policy_version 6610 (0.0007) -[2023-10-09 08:32:26,867][23468] Updated weights for policy 0, policy_version 6620 (0.0007) -[2023-10-09 08:32:27,669][23469] Updated weights for policy 1, policy_version 6630 (0.0007) -[2023-10-09 08:32:28,028][23469] Updated weights for policy 1, policy_version 6640 (0.0009) -[2023-10-09 08:32:28,396][23469] Updated weights for policy 1, policy_version 6650 (0.0010) -[2023-10-09 08:32:30,673][23468] Updated weights for policy 0, policy_version 6630 (0.0009) -[2023-10-09 08:32:31,049][23468] Updated weights for policy 0, policy_version 6640 (0.0009) -[2023-10-09 08:32:31,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 13598720. Throughput: 0: 1804.3, 1: 1778.9. Samples: 3414742. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:32:31,078][22500] Avg episode reward: [(0, '5.060'), (1, '5.050')] -[2023-10-09 08:32:31,411][23468] Updated weights for policy 0, policy_version 6650 (0.0007) -[2023-10-09 08:32:32,289][23469] Updated weights for policy 1, policy_version 6660 (0.0008) -[2023-10-09 08:32:32,665][23469] Updated weights for policy 1, policy_version 6670 (0.0007) -[2023-10-09 08:32:33,041][23469] Updated weights for policy 1, policy_version 6680 (0.0007) -[2023-10-09 08:32:35,203][23468] Updated weights for policy 0, policy_version 6660 (0.0008) -[2023-10-09 08:32:35,572][23468] Updated weights for policy 0, policy_version 6670 (0.0010) -[2023-10-09 08:32:35,952][23468] Updated weights for policy 0, policy_version 6680 (0.0008) -[2023-10-09 08:32:36,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 13664256. Throughput: 0: 1787.2, 1: 1778.6. Samples: 3424460. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-10-09 08:32:36,079][22500] Avg episode reward: [(0, '5.090'), (1, '4.960')] -[2023-10-09 08:32:36,907][23469] Updated weights for policy 1, policy_version 6690 (0.0007) -[2023-10-09 08:32:37,276][23469] Updated weights for policy 1, policy_version 6700 (0.0008) -[2023-10-09 08:32:37,654][23469] Updated weights for policy 1, policy_version 6710 (0.0010) -[2023-10-09 08:32:38,025][23469] Updated weights for policy 1, policy_version 6720 (0.0007) -[2023-10-09 08:32:39,848][23468] Updated weights for policy 0, policy_version 6690 (0.0008) -[2023-10-09 08:32:40,211][23468] Updated weights for policy 0, policy_version 6700 (0.0009) -[2023-10-09 08:32:40,586][23468] Updated weights for policy 0, policy_version 6710 (0.0008) -[2023-10-09 08:32:40,959][23468] Updated weights for policy 0, policy_version 6720 (0.0009) -[2023-10-09 08:32:41,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 13762560. Throughput: 0: 1799.8, 1: 1779.9. Samples: 3446622. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:32:41,078][22500] Avg episode reward: [(0, '5.140'), (1, '5.150')] -[2023-10-09 08:32:41,765][23469] Updated weights for policy 1, policy_version 6730 (0.0011) -[2023-10-09 08:32:42,140][23469] Updated weights for policy 1, policy_version 6740 (0.0011) -[2023-10-09 08:32:42,509][23469] Updated weights for policy 1, policy_version 6750 (0.0009) -[2023-10-09 08:32:44,644][23468] Updated weights for policy 0, policy_version 6730 (0.0009) -[2023-10-09 08:32:45,016][23468] Updated weights for policy 0, policy_version 6740 (0.0008) -[2023-10-09 08:32:45,394][23468] Updated weights for policy 0, policy_version 6750 (0.0008) -[2023-10-09 08:32:46,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 13828096. Throughput: 0: 1786.6, 1: 1799.9. Samples: 3467948. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:32:46,078][22500] Avg episode reward: [(0, '5.030'), (1, '5.080')] -[2023-10-09 08:32:46,214][23469] Updated weights for policy 1, policy_version 6760 (0.0007) -[2023-10-09 08:32:46,575][23469] Updated weights for policy 1, policy_version 6770 (0.0009) -[2023-10-09 08:32:46,949][23469] Updated weights for policy 1, policy_version 6780 (0.0008) -[2023-10-09 08:32:49,136][23468] Updated weights for policy 0, policy_version 6760 (0.0010) -[2023-10-09 08:32:49,509][23468] Updated weights for policy 0, policy_version 6770 (0.0008) -[2023-10-09 08:32:49,881][23468] Updated weights for policy 0, policy_version 6780 (0.0007) -[2023-10-09 08:32:50,873][23469] Updated weights for policy 1, policy_version 6790 (0.0009) -[2023-10-09 08:32:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 13893632. Throughput: 0: 1796.3, 1: 1778.0. Samples: 3478912. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:32:51,078][22500] Avg episode reward: [(0, '5.220'), (1, '5.060')] -[2023-10-09 08:32:51,265][23469] Updated weights for policy 1, policy_version 6800 (0.0010) -[2023-10-09 08:32:51,628][23469] Updated weights for policy 1, policy_version 6810 (0.0008) -[2023-10-09 08:32:53,638][23468] Updated weights for policy 0, policy_version 6790 (0.0007) -[2023-10-09 08:32:54,013][23468] Updated weights for policy 0, policy_version 6800 (0.0011) -[2023-10-09 08:32:54,390][23468] Updated weights for policy 0, policy_version 6810 (0.0010) -[2023-10-09 08:32:55,490][23469] Updated weights for policy 1, policy_version 6820 (0.0008) -[2023-10-09 08:32:55,850][23469] Updated weights for policy 1, policy_version 6830 (0.0009) -[2023-10-09 08:32:56,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 13959168. Throughput: 0: 1792.5, 1: 1787.9. Samples: 3499788. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:32:56,078][22500] Avg episode reward: [(0, '5.160'), (1, '5.270')] -[2023-10-09 08:32:56,225][23469] Updated weights for policy 1, policy_version 6840 (0.0009) -[2023-10-09 08:32:58,187][23468] Updated weights for policy 0, policy_version 6820 (0.0009) -[2023-10-09 08:32:58,558][23468] Updated weights for policy 0, policy_version 6830 (0.0008) -[2023-10-09 08:32:58,929][23468] Updated weights for policy 0, policy_version 6840 (0.0008) -[2023-10-09 08:33:00,046][23469] Updated weights for policy 1, policy_version 6850 (0.0008) -[2023-10-09 08:33:00,421][23469] Updated weights for policy 1, policy_version 6860 (0.0008) -[2023-10-09 08:33:00,786][23469] Updated weights for policy 1, policy_version 6870 (0.0009) -[2023-10-09 08:33:01,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 14024704. Throughput: 0: 1778.3, 1: 1781.1. Samples: 3520694. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 08:33:01,078][22500] Avg episode reward: [(0, '5.380'), (1, '5.300')] -[2023-10-09 08:33:01,150][23469] Updated weights for policy 1, policy_version 6880 (0.0008) -[2023-10-09 08:33:02,719][23468] Updated weights for policy 0, policy_version 6850 (0.0008) -[2023-10-09 08:33:03,095][23468] Updated weights for policy 0, policy_version 6860 (0.0010) -[2023-10-09 08:33:03,467][23468] Updated weights for policy 0, policy_version 6870 (0.0011) -[2023-10-09 08:33:03,846][23468] Updated weights for policy 0, policy_version 6880 (0.0011) -[2023-10-09 08:33:04,795][23469] Updated weights for policy 1, policy_version 6890 (0.0008) -[2023-10-09 08:33:05,162][23469] Updated weights for policy 1, policy_version 6900 (0.0009) -[2023-10-09 08:33:05,542][23469] Updated weights for policy 1, policy_version 6910 (0.0009) -[2023-10-09 08:33:06,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 14123008. Throughput: 0: 1795.6, 1: 1785.3. Samples: 3532252. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 08:33:06,078][22500] Avg episode reward: [(0, '5.230'), (1, '5.470')] -[2023-10-09 08:33:07,513][23468] Updated weights for policy 0, policy_version 6890 (0.0010) -[2023-10-09 08:33:07,887][23468] Updated weights for policy 0, policy_version 6900 (0.0009) -[2023-10-09 08:33:08,260][23468] Updated weights for policy 0, policy_version 6910 (0.0008) -[2023-10-09 08:33:09,378][23469] Updated weights for policy 1, policy_version 6920 (0.0009) -[2023-10-09 08:33:09,750][23469] Updated weights for policy 1, policy_version 6930 (0.0007) -[2023-10-09 08:33:10,124][23469] Updated weights for policy 1, policy_version 6940 (0.0009) -[2023-10-09 08:33:11,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 14188544. Throughput: 0: 1774.3, 1: 1784.0. Samples: 3552790. Policy #0 lag: (min: 30.0, avg: 52.7, max: 56.0) -[2023-10-09 08:33:11,078][22500] Avg episode reward: [(0, '5.380'), (1, '4.940')] -[2023-10-09 08:33:12,109][23468] Updated weights for policy 0, policy_version 6920 (0.0009) -[2023-10-09 08:33:12,485][23468] Updated weights for policy 0, policy_version 6930 (0.0008) -[2023-10-09 08:33:12,867][23468] Updated weights for policy 0, policy_version 6940 (0.0010) -[2023-10-09 08:33:13,728][23469] Updated weights for policy 1, policy_version 6950 (0.0008) -[2023-10-09 08:33:14,090][23469] Updated weights for policy 1, policy_version 6960 (0.0009) -[2023-10-09 08:33:14,460][23469] Updated weights for policy 1, policy_version 6970 (0.0007) -[2023-10-09 08:33:16,078][22500] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 14254080. Throughput: 0: 1772.4, 1: 1778.4. Samples: 3574532. Policy #0 lag: (min: 30.0, avg: 52.7, max: 56.0) -[2023-10-09 08:33:16,079][22500] Avg episode reward: [(0, '5.190'), (1, '5.090')] -[2023-10-09 08:33:16,611][23468] Updated weights for policy 0, policy_version 6950 (0.0008) -[2023-10-09 08:33:16,995][23468] Updated weights for policy 0, policy_version 6960 (0.0008) -[2023-10-09 08:33:17,358][23468] Updated weights for policy 0, policy_version 6970 (0.0011) -[2023-10-09 08:33:18,323][23469] Updated weights for policy 1, policy_version 6980 (0.0007) -[2023-10-09 08:33:18,697][23469] Updated weights for policy 1, policy_version 6990 (0.0009) -[2023-10-09 08:33:19,068][23469] Updated weights for policy 1, policy_version 7000 (0.0011) -[2023-10-09 08:33:21,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 14319616. Throughput: 0: 1769.9, 1: 1794.5. Samples: 3584856. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:33:21,078][22500] Avg episode reward: [(0, '5.230'), (1, '4.720')] -[2023-10-09 08:33:21,195][23468] Updated weights for policy 0, policy_version 6980 (0.0010) -[2023-10-09 08:33:21,569][23468] Updated weights for policy 0, policy_version 6990 (0.0008) -[2023-10-09 08:33:21,947][23468] Updated weights for policy 0, policy_version 7000 (0.0009) -[2023-10-09 08:33:22,700][23469] Updated weights for policy 1, policy_version 7010 (0.0009) -[2023-10-09 08:33:23,075][23469] Updated weights for policy 1, policy_version 7020 (0.0009) -[2023-10-09 08:33:23,451][23469] Updated weights for policy 1, policy_version 7030 (0.0008) -[2023-10-09 08:33:23,820][23469] Updated weights for policy 1, policy_version 7040 (0.0009) -[2023-10-09 08:33:25,727][23468] Updated weights for policy 0, policy_version 7010 (0.0010) -[2023-10-09 08:33:26,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 14385152. Throughput: 0: 1772.3, 1: 1785.3. Samples: 3606712. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:33:26,078][22500] Avg episode reward: [(0, '5.000'), (1, '5.240')] -[2023-10-09 08:33:26,095][23468] Updated weights for policy 0, policy_version 7020 (0.0007) -[2023-10-09 08:33:26,469][23468] Updated weights for policy 0, policy_version 7030 (0.0010) -[2023-10-09 08:33:26,834][23468] Updated weights for policy 0, policy_version 7040 (0.0010) -[2023-10-09 08:33:27,491][23469] Updated weights for policy 1, policy_version 7050 (0.0010) -[2023-10-09 08:33:27,865][23469] Updated weights for policy 1, policy_version 7060 (0.0009) -[2023-10-09 08:33:28,227][23469] Updated weights for policy 1, policy_version 7070 (0.0007) -[2023-10-09 08:33:30,593][23468] Updated weights for policy 0, policy_version 7050 (0.0008) -[2023-10-09 08:33:30,974][23468] Updated weights for policy 0, policy_version 7060 (0.0009) -[2023-10-09 08:33:31,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 14450688. Throughput: 0: 1795.8, 1: 1784.6. Samples: 3629066. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 08:33:31,078][22500] Avg episode reward: [(0, '5.190'), (1, '5.250')] -[2023-10-09 08:33:31,347][23468] Updated weights for policy 0, policy_version 7070 (0.0007) -[2023-10-09 08:33:32,084][23469] Updated weights for policy 1, policy_version 7080 (0.0009) -[2023-10-09 08:33:32,464][23469] Updated weights for policy 1, policy_version 7090 (0.0009) -[2023-10-09 08:33:32,828][23469] Updated weights for policy 1, policy_version 7100 (0.0007) -[2023-10-09 08:33:35,370][23468] Updated weights for policy 0, policy_version 7080 (0.0009) -[2023-10-09 08:33:35,740][23468] Updated weights for policy 0, policy_version 7090 (0.0010) -[2023-10-09 08:33:36,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 14516224. Throughput: 0: 1766.2, 1: 1785.1. Samples: 3638720. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 08:33:36,078][22500] Avg episode reward: [(0, '5.310'), (1, '5.600')] -[2023-10-09 08:33:36,080][23343] Saving new best policy, reward=5.600! -[2023-10-09 08:33:36,110][23468] Updated weights for policy 0, policy_version 7100 (0.0009) -[2023-10-09 08:33:36,514][23469] Updated weights for policy 1, policy_version 7110 (0.0008) -[2023-10-09 08:33:36,895][23469] Updated weights for policy 1, policy_version 7120 (0.0007) -[2023-10-09 08:33:37,266][23469] Updated weights for policy 1, policy_version 7130 (0.0007) -[2023-10-09 08:33:39,896][23468] Updated weights for policy 0, policy_version 7110 (0.0010) -[2023-10-09 08:33:40,270][23468] Updated weights for policy 0, policy_version 7120 (0.0010) -[2023-10-09 08:33:40,639][23468] Updated weights for policy 0, policy_version 7130 (0.0009) -[2023-10-09 08:33:41,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 14614528. Throughput: 0: 1789.0, 1: 1792.6. Samples: 3660960. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:33:41,079][22500] Avg episode reward: [(0, '5.510'), (1, '5.180')] -[2023-10-09 08:33:41,080][23265] Saving new best policy, reward=5.510! -[2023-10-09 08:33:41,085][23469] Updated weights for policy 1, policy_version 7140 (0.0009) -[2023-10-09 08:33:41,462][23469] Updated weights for policy 1, policy_version 7150 (0.0009) -[2023-10-09 08:33:41,822][23469] Updated weights for policy 1, policy_version 7160 (0.0007) -[2023-10-09 08:33:44,475][23468] Updated weights for policy 0, policy_version 7140 (0.0008) -[2023-10-09 08:33:44,856][23468] Updated weights for policy 0, policy_version 7150 (0.0007) -[2023-10-09 08:33:45,220][23468] Updated weights for policy 0, policy_version 7160 (0.0007) -[2023-10-09 08:33:45,564][23469] Updated weights for policy 1, policy_version 7170 (0.0008) -[2023-10-09 08:33:45,930][23469] Updated weights for policy 1, policy_version 7180 (0.0009) -[2023-10-09 08:33:46,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 14680064. Throughput: 0: 1766.3, 1: 1813.0. Samples: 3681762. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:33:46,078][22500] Avg episode reward: [(0, '5.610'), (1, '5.160')] -[2023-10-09 08:33:46,087][23265] Saving new best policy, reward=5.610! -[2023-10-09 08:33:46,297][23469] Updated weights for policy 1, policy_version 7190 (0.0008) -[2023-10-09 08:33:46,663][23469] Updated weights for policy 1, policy_version 7200 (0.0007) -[2023-10-09 08:33:48,916][23468] Updated weights for policy 0, policy_version 7170 (0.0007) -[2023-10-09 08:33:49,284][23468] Updated weights for policy 0, policy_version 7180 (0.0008) -[2023-10-09 08:33:49,658][23468] Updated weights for policy 0, policy_version 7190 (0.0008) -[2023-10-09 08:33:50,029][23468] Updated weights for policy 0, policy_version 7200 (0.0008) -[2023-10-09 08:33:50,284][23469] Updated weights for policy 1, policy_version 7210 (0.0009) -[2023-10-09 08:33:50,652][23469] Updated weights for policy 1, policy_version 7220 (0.0008) -[2023-10-09 08:33:51,021][23469] Updated weights for policy 1, policy_version 7230 (0.0007) -[2023-10-09 08:33:51,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 14745600. Throughput: 0: 1779.8, 1: 1792.4. Samples: 3693000. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:33:51,078][22500] Avg episode reward: [(0, '5.490'), (1, '5.580')] -[2023-10-09 08:33:53,759][23468] Updated weights for policy 0, policy_version 7210 (0.0007) -[2023-10-09 08:33:54,127][23468] Updated weights for policy 0, policy_version 7220 (0.0009) -[2023-10-09 08:33:54,502][23468] Updated weights for policy 0, policy_version 7230 (0.0007) -[2023-10-09 08:33:54,883][23469] Updated weights for policy 1, policy_version 7240 (0.0008) -[2023-10-09 08:33:55,261][23469] Updated weights for policy 1, policy_version 7250 (0.0008) -[2023-10-09 08:33:55,624][23469] Updated weights for policy 1, policy_version 7260 (0.0009) -[2023-10-09 08:33:56,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 14843904. Throughput: 0: 1775.7, 1: 1808.4. Samples: 3714078. Policy #0 lag: (min: 29.0, avg: 31.5, max: 61.0) -[2023-10-09 08:33:56,078][22500] Avg episode reward: [(0, '5.490'), (1, '5.710')] -[2023-10-09 08:33:56,079][23343] Saving new best policy, reward=5.710! -[2023-10-09 08:33:58,265][23468] Updated weights for policy 0, policy_version 7240 (0.0007) -[2023-10-09 08:33:58,643][23468] Updated weights for policy 0, policy_version 7250 (0.0008) -[2023-10-09 08:33:59,029][23468] Updated weights for policy 0, policy_version 7260 (0.0007) -[2023-10-09 08:33:59,233][23469] Updated weights for policy 1, policy_version 7270 (0.0010) -[2023-10-09 08:33:59,604][23469] Updated weights for policy 1, policy_version 7280 (0.0007) -[2023-10-09 08:33:59,977][23469] Updated weights for policy 1, policy_version 7290 (0.0007) -[2023-10-09 08:34:01,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 14909440. Throughput: 0: 1766.5, 1: 1793.1. Samples: 3734714. Policy #0 lag: (min: 29.0, avg: 31.5, max: 61.0) -[2023-10-09 08:34:01,078][22500] Avg episode reward: [(0, '5.470'), (1, '5.640')] -[2023-10-09 08:34:02,900][23468] Updated weights for policy 0, policy_version 7270 (0.0008) -[2023-10-09 08:34:03,273][23468] Updated weights for policy 0, policy_version 7280 (0.0009) -[2023-10-09 08:34:03,659][23468] Updated weights for policy 0, policy_version 7290 (0.0009) -[2023-10-09 08:34:03,945][23469] Updated weights for policy 1, policy_version 7300 (0.0008) -[2023-10-09 08:34:04,314][23469] Updated weights for policy 1, policy_version 7310 (0.0007) -[2023-10-09 08:34:04,683][23469] Updated weights for policy 1, policy_version 7320 (0.0007) -[2023-10-09 08:34:06,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 14974976. Throughput: 0: 1786.3, 1: 1809.0. Samples: 3746646. Policy #0 lag: (min: 1.0, avg: 15.2, max: 33.0) -[2023-10-09 08:34:06,079][22500] Avg episode reward: [(0, '5.470'), (1, '5.600')] -[2023-10-09 08:34:07,413][23468] Updated weights for policy 0, policy_version 7300 (0.0008) -[2023-10-09 08:34:07,792][23468] Updated weights for policy 0, policy_version 7310 (0.0008) -[2023-10-09 08:34:08,163][23468] Updated weights for policy 0, policy_version 7320 (0.0011) -[2023-10-09 08:34:08,368][23469] Updated weights for policy 1, policy_version 7330 (0.0009) -[2023-10-09 08:34:08,744][23469] Updated weights for policy 1, policy_version 7340 (0.0009) -[2023-10-09 08:34:09,118][23469] Updated weights for policy 1, policy_version 7350 (0.0009) -[2023-10-09 08:34:09,480][23469] Updated weights for policy 1, policy_version 7360 (0.0009) -[2023-10-09 08:34:11,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 15040512. Throughput: 0: 1764.0, 1: 1790.1. Samples: 3766646. Policy #0 lag: (min: 1.0, avg: 15.2, max: 33.0) -[2023-10-09 08:34:11,078][22500] Avg episode reward: [(0, '5.560'), (1, '5.740')] -[2023-10-09 08:34:11,080][23343] Saving new best policy, reward=5.740! -[2023-10-09 08:34:11,951][23468] Updated weights for policy 0, policy_version 7330 (0.0009) -[2023-10-09 08:34:12,330][23468] Updated weights for policy 0, policy_version 7340 (0.0010) -[2023-10-09 08:34:12,713][23468] Updated weights for policy 0, policy_version 7350 (0.0010) -[2023-10-09 08:34:13,054][23469] Updated weights for policy 1, policy_version 7370 (0.0008) -[2023-10-09 08:34:13,090][23468] Updated weights for policy 0, policy_version 7360 (0.0008) -[2023-10-09 08:34:13,424][23469] Updated weights for policy 1, policy_version 7380 (0.0009) -[2023-10-09 08:34:13,786][23469] Updated weights for policy 1, policy_version 7390 (0.0009) -[2023-10-09 08:34:16,078][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 15106048. Throughput: 0: 1762.7, 1: 1794.0. Samples: 3789116. Policy #0 lag: (min: 13.0, avg: 15.2, max: 45.0) -[2023-10-09 08:34:16,079][22500] Avg episode reward: [(0, '5.420'), (1, '5.920')] -[2023-10-09 08:34:16,090][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000007360_7536640.pth... -[2023-10-09 08:34:16,090][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000007392_7569408.pth... -[2023-10-09 08:34:16,119][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000005696_5832704.pth -[2023-10-09 08:34:16,129][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000005728_5865472.pth -[2023-10-09 08:34:16,134][23343] Saving new best policy, reward=5.920! -[2023-10-09 08:34:17,000][23468] Updated weights for policy 0, policy_version 7370 (0.0007) -[2023-10-09 08:34:17,363][23468] Updated weights for policy 0, policy_version 7380 (0.0007) -[2023-10-09 08:34:17,559][23469] Updated weights for policy 1, policy_version 7400 (0.0008) -[2023-10-09 08:34:17,733][23468] Updated weights for policy 0, policy_version 7390 (0.0007) -[2023-10-09 08:34:17,926][23469] Updated weights for policy 1, policy_version 7410 (0.0007) -[2023-10-09 08:34:18,289][23469] Updated weights for policy 1, policy_version 7420 (0.0009) -[2023-10-09 08:34:21,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 15171584. Throughput: 0: 1761.7, 1: 1799.0. Samples: 3798954. Policy #0 lag: (min: 13.0, avg: 15.2, max: 45.0) -[2023-10-09 08:34:21,078][22500] Avg episode reward: [(0, '5.100'), (1, '5.750')] -[2023-10-09 08:34:21,506][23468] Updated weights for policy 0, policy_version 7400 (0.0010) -[2023-10-09 08:34:21,877][23468] Updated weights for policy 0, policy_version 7410 (0.0009) -[2023-10-09 08:34:22,124][23469] Updated weights for policy 1, policy_version 7430 (0.0009) -[2023-10-09 08:34:22,250][23468] Updated weights for policy 0, policy_version 7420 (0.0007) -[2023-10-09 08:34:22,486][23469] Updated weights for policy 1, policy_version 7440 (0.0007) -[2023-10-09 08:34:22,858][23469] Updated weights for policy 1, policy_version 7450 (0.0008) -[2023-10-09 08:34:26,039][23468] Updated weights for policy 0, policy_version 7430 (0.0009) -[2023-10-09 08:34:26,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 15237120. Throughput: 0: 1765.6, 1: 1792.3. Samples: 3821066. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 08:34:26,078][22500] Avg episode reward: [(0, '4.890'), (1, '5.550')] -[2023-10-09 08:34:26,414][23468] Updated weights for policy 0, policy_version 7440 (0.0008) -[2023-10-09 08:34:26,638][23469] Updated weights for policy 1, policy_version 7460 (0.0008) -[2023-10-09 08:34:26,786][23468] Updated weights for policy 0, policy_version 7450 (0.0008) -[2023-10-09 08:34:27,005][23469] Updated weights for policy 1, policy_version 7470 (0.0010) -[2023-10-09 08:34:27,381][23469] Updated weights for policy 1, policy_version 7480 (0.0008) -[2023-10-09 08:34:30,578][23468] Updated weights for policy 0, policy_version 7460 (0.0008) -[2023-10-09 08:34:30,904][23469] Updated weights for policy 1, policy_version 7490 (0.0008) -[2023-10-09 08:34:30,955][23468] Updated weights for policy 0, policy_version 7470 (0.0009) -[2023-10-09 08:34:31,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 15302656. Throughput: 0: 1795.6, 1: 1801.7. Samples: 3843640. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 08:34:31,078][22500] Avg episode reward: [(0, '5.230'), (1, '5.780')] -[2023-10-09 08:34:31,281][23469] Updated weights for policy 1, policy_version 7500 (0.0009) -[2023-10-09 08:34:31,327][23468] Updated weights for policy 0, policy_version 7480 (0.0008) -[2023-10-09 08:34:31,648][23469] Updated weights for policy 1, policy_version 7510 (0.0008) -[2023-10-09 08:34:32,014][23469] Updated weights for policy 1, policy_version 7520 (0.0009) -[2023-10-09 08:34:35,139][23468] Updated weights for policy 0, policy_version 7490 (0.0007) -[2023-10-09 08:34:35,508][23468] Updated weights for policy 0, policy_version 7500 (0.0008) -[2023-10-09 08:34:35,822][23469] Updated weights for policy 1, policy_version 7530 (0.0007) -[2023-10-09 08:34:35,890][23468] Updated weights for policy 0, policy_version 7510 (0.0010) -[2023-10-09 08:34:36,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 15368192. Throughput: 0: 1765.4, 1: 1793.1. Samples: 3853134. Policy #0 lag: (min: 31.0, avg: 32.4, max: 57.0) -[2023-10-09 08:34:36,078][22500] Avg episode reward: [(0, '5.380'), (1, '5.760')] -[2023-10-09 08:34:36,197][23469] Updated weights for policy 1, policy_version 7540 (0.0007) -[2023-10-09 08:34:36,259][23468] Updated weights for policy 0, policy_version 7520 (0.0008) -[2023-10-09 08:34:36,565][23469] Updated weights for policy 1, policy_version 7550 (0.0007) -[2023-10-09 08:34:40,008][23468] Updated weights for policy 0, policy_version 7530 (0.0010) -[2023-10-09 08:34:40,334][23469] Updated weights for policy 1, policy_version 7560 (0.0008) -[2023-10-09 08:34:40,376][23468] Updated weights for policy 0, policy_version 7540 (0.0008) -[2023-10-09 08:34:40,696][23469] Updated weights for policy 1, policy_version 7570 (0.0010) -[2023-10-09 08:34:40,745][23468] Updated weights for policy 0, policy_version 7550 (0.0008) -[2023-10-09 08:34:41,073][23469] Updated weights for policy 1, policy_version 7580 (0.0007) -[2023-10-09 08:34:41,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 15466496. Throughput: 0: 1785.3, 1: 1794.7. Samples: 3875180. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-09 08:34:41,079][22500] Avg episode reward: [(0, '5.420'), (1, '6.090')] -[2023-10-09 08:34:41,213][23343] Saving new best policy, reward=6.090! -[2023-10-09 08:34:44,549][23468] Updated weights for policy 0, policy_version 7560 (0.0009) -[2023-10-09 08:34:44,738][23469] Updated weights for policy 1, policy_version 7590 (0.0007) -[2023-10-09 08:34:44,930][23468] Updated weights for policy 0, policy_version 7570 (0.0007) -[2023-10-09 08:34:45,108][23469] Updated weights for policy 1, policy_version 7600 (0.0007) -[2023-10-09 08:34:45,302][23468] Updated weights for policy 0, policy_version 7580 (0.0007) -[2023-10-09 08:34:45,479][23469] Updated weights for policy 1, policy_version 7610 (0.0009) -[2023-10-09 08:34:46,077][22500] Fps is (10 sec: 19660.5, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 15564800. Throughput: 0: 1760.7, 1: 1793.4. Samples: 3894646. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-09 08:34:46,078][22500] Avg episode reward: [(0, '5.100'), (1, '6.030')] -[2023-10-09 08:34:49,164][23468] Updated weights for policy 0, policy_version 7590 (0.0009) -[2023-10-09 08:34:49,379][23469] Updated weights for policy 1, policy_version 7620 (0.0009) -[2023-10-09 08:34:49,538][23468] Updated weights for policy 0, policy_version 7600 (0.0008) -[2023-10-09 08:34:49,748][23469] Updated weights for policy 1, policy_version 7630 (0.0009) -[2023-10-09 08:34:49,903][23468] Updated weights for policy 0, policy_version 7610 (0.0007) -[2023-10-09 08:34:50,126][23469] Updated weights for policy 1, policy_version 7640 (0.0009) -[2023-10-09 08:34:51,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 15630336. Throughput: 0: 1766.2, 1: 1793.5. Samples: 3906830. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-09 08:34:51,079][22500] Avg episode reward: [(0, '4.980'), (1, '5.790')] -[2023-10-09 08:34:53,862][23468] Updated weights for policy 0, policy_version 7620 (0.0010) -[2023-10-09 08:34:53,890][23469] Updated weights for policy 1, policy_version 7650 (0.0008) -[2023-10-09 08:34:54,234][23468] Updated weights for policy 0, policy_version 7630 (0.0009) -[2023-10-09 08:34:54,254][23469] Updated weights for policy 1, policy_version 7660 (0.0008) -[2023-10-09 08:34:54,605][23468] Updated weights for policy 0, policy_version 7640 (0.0007) -[2023-10-09 08:34:54,618][23469] Updated weights for policy 1, policy_version 7670 (0.0008) -[2023-10-09 08:34:54,989][23469] Updated weights for policy 1, policy_version 7680 (0.0009) -[2023-10-09 08:34:56,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 15695872. Throughput: 0: 1769.1, 1: 1797.8. Samples: 3927156. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-09 08:34:56,078][22500] Avg episode reward: [(0, '5.170'), (1, '5.510')] -[2023-10-09 08:34:58,359][23468] Updated weights for policy 0, policy_version 7650 (0.0009) -[2023-10-09 08:34:58,727][23468] Updated weights for policy 0, policy_version 7660 (0.0007) -[2023-10-09 08:34:58,813][23469] Updated weights for policy 1, policy_version 7690 (0.0007) -[2023-10-09 08:34:59,101][23468] Updated weights for policy 0, policy_version 7670 (0.0007) -[2023-10-09 08:34:59,179][23469] Updated weights for policy 1, policy_version 7700 (0.0008) -[2023-10-09 08:34:59,472][23468] Updated weights for policy 0, policy_version 7680 (0.0007) -[2023-10-09 08:34:59,546][23469] Updated weights for policy 1, policy_version 7710 (0.0007) -[2023-10-09 08:35:01,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 15761408. Throughput: 0: 1757.1, 1: 1783.6. Samples: 3948448. Policy #0 lag: (min: 25.0, avg: 29.8, max: 57.0) -[2023-10-09 08:35:01,079][22500] Avg episode reward: [(0, '5.110'), (1, '5.000')] -[2023-10-09 08:35:03,293][23469] Updated weights for policy 1, policy_version 7720 (0.0008) -[2023-10-09 08:35:03,323][23468] Updated weights for policy 0, policy_version 7690 (0.0008) -[2023-10-09 08:35:03,657][23469] Updated weights for policy 1, policy_version 7730 (0.0008) -[2023-10-09 08:35:03,692][23468] Updated weights for policy 0, policy_version 7700 (0.0008) -[2023-10-09 08:35:04,023][23469] Updated weights for policy 1, policy_version 7740 (0.0007) -[2023-10-09 08:35:04,063][23468] Updated weights for policy 0, policy_version 7710 (0.0007) -[2023-10-09 08:35:06,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 15826944. Throughput: 0: 1775.3, 1: 1790.9. Samples: 3959434. Policy #0 lag: (min: 25.0, avg: 29.8, max: 57.0) -[2023-10-09 08:35:06,079][22500] Avg episode reward: [(0, '5.080'), (1, '4.960')] -[2023-10-09 08:35:07,868][23469] Updated weights for policy 1, policy_version 7750 (0.0008) -[2023-10-09 08:35:07,908][23468] Updated weights for policy 0, policy_version 7720 (0.0008) -[2023-10-09 08:35:08,241][23469] Updated weights for policy 1, policy_version 7760 (0.0009) -[2023-10-09 08:35:08,295][23468] Updated weights for policy 0, policy_version 7730 (0.0008) -[2023-10-09 08:35:08,620][23469] Updated weights for policy 1, policy_version 7770 (0.0008) -[2023-10-09 08:35:08,667][23468] Updated weights for policy 0, policy_version 7740 (0.0010) -[2023-10-09 08:35:11,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 15892480. Throughput: 0: 1747.1, 1: 1781.9. Samples: 3979874. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:35:11,079][22500] Avg episode reward: [(0, '5.410'), (1, '4.910')] -[2023-10-09 08:35:12,362][23469] Updated weights for policy 1, policy_version 7780 (0.0008) -[2023-10-09 08:35:12,511][23468] Updated weights for policy 0, policy_version 7750 (0.0008) -[2023-10-09 08:35:12,731][23469] Updated weights for policy 1, policy_version 7790 (0.0008) -[2023-10-09 08:35:12,881][23468] Updated weights for policy 0, policy_version 7760 (0.0008) -[2023-10-09 08:35:13,097][23469] Updated weights for policy 1, policy_version 7800 (0.0007) -[2023-10-09 08:35:13,246][23468] Updated weights for policy 0, policy_version 7770 (0.0008) -[2023-10-09 08:35:16,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 15958016. Throughput: 0: 1747.5, 1: 1777.5. Samples: 4002262. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:35:16,078][22500] Avg episode reward: [(0, '5.660'), (1, '5.170')] -[2023-10-09 08:35:16,088][23265] Saving new best policy, reward=5.660! -[2023-10-09 08:35:16,808][23469] Updated weights for policy 1, policy_version 7810 (0.0009) -[2023-10-09 08:35:17,041][23468] Updated weights for policy 0, policy_version 7780 (0.0010) -[2023-10-09 08:35:17,170][23469] Updated weights for policy 1, policy_version 7820 (0.0007) -[2023-10-09 08:35:17,414][23468] Updated weights for policy 0, policy_version 7790 (0.0009) -[2023-10-09 08:35:17,546][23469] Updated weights for policy 1, policy_version 7830 (0.0008) -[2023-10-09 08:35:17,786][23468] Updated weights for policy 0, policy_version 7800 (0.0007) -[2023-10-09 08:35:17,916][23469] Updated weights for policy 1, policy_version 7840 (0.0010) -[2023-10-09 08:35:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 16023552. Throughput: 0: 1747.0, 1: 1779.0. Samples: 4011802. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:35:21,078][22500] Avg episode reward: [(0, '6.050'), (1, '5.450')] -[2023-10-09 08:35:21,080][23265] Saving new best policy, reward=6.050! -[2023-10-09 08:35:21,669][23469] Updated weights for policy 1, policy_version 7850 (0.0008) -[2023-10-09 08:35:21,751][23468] Updated weights for policy 0, policy_version 7810 (0.0008) -[2023-10-09 08:35:22,036][23469] Updated weights for policy 1, policy_version 7860 (0.0008) -[2023-10-09 08:35:22,117][23468] Updated weights for policy 0, policy_version 7820 (0.0007) -[2023-10-09 08:35:22,404][23469] Updated weights for policy 1, policy_version 7870 (0.0007) -[2023-10-09 08:35:22,492][23468] Updated weights for policy 0, policy_version 7830 (0.0007) -[2023-10-09 08:35:22,868][23468] Updated weights for policy 0, policy_version 7840 (0.0008) -[2023-10-09 08:35:26,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 16089088. Throughput: 0: 1753.6, 1: 1783.4. Samples: 4034348. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:35:26,078][22500] Avg episode reward: [(0, '5.630'), (1, '5.500')] -[2023-10-09 08:35:26,149][23469] Updated weights for policy 1, policy_version 7880 (0.0009) -[2023-10-09 08:35:26,513][23469] Updated weights for policy 1, policy_version 7890 (0.0007) -[2023-10-09 08:35:26,634][23468] Updated weights for policy 0, policy_version 7850 (0.0009) -[2023-10-09 08:35:26,885][23469] Updated weights for policy 1, policy_version 7900 (0.0008) -[2023-10-09 08:35:27,012][23468] Updated weights for policy 0, policy_version 7860 (0.0010) -[2023-10-09 08:35:27,401][23468] Updated weights for policy 0, policy_version 7870 (0.0010) -[2023-10-09 08:35:30,640][23469] Updated weights for policy 1, policy_version 7910 (0.0009) -[2023-10-09 08:35:30,997][23469] Updated weights for policy 1, policy_version 7920 (0.0007) -[2023-10-09 08:35:31,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 16154624. Throughput: 0: 1788.8, 1: 1803.8. Samples: 4056312. Policy #0 lag: (min: 31.0, avg: 33.1, max: 61.0) -[2023-10-09 08:35:31,078][22500] Avg episode reward: [(0, '5.470'), (1, '5.720')] -[2023-10-09 08:35:31,136][23468] Updated weights for policy 0, policy_version 7880 (0.0008) -[2023-10-09 08:35:31,371][23469] Updated weights for policy 1, policy_version 7930 (0.0008) -[2023-10-09 08:35:31,513][23468] Updated weights for policy 0, policy_version 7890 (0.0008) -[2023-10-09 08:35:31,887][23468] Updated weights for policy 0, policy_version 7900 (0.0007) -[2023-10-09 08:35:35,324][23469] Updated weights for policy 1, policy_version 7940 (0.0009) -[2023-10-09 08:35:35,611][23468] Updated weights for policy 0, policy_version 7910 (0.0008) -[2023-10-09 08:35:35,689][23469] Updated weights for policy 1, policy_version 7950 (0.0009) -[2023-10-09 08:35:35,988][23468] Updated weights for policy 0, policy_version 7920 (0.0009) -[2023-10-09 08:35:36,063][23469] Updated weights for policy 1, policy_version 7960 (0.0007) -[2023-10-09 08:35:36,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 16220160. Throughput: 0: 1765.1, 1: 1781.2. Samples: 4066412. Policy #0 lag: (min: 31.0, avg: 33.1, max: 61.0) -[2023-10-09 08:35:36,079][22500] Avg episode reward: [(0, '5.130'), (1, '5.600')] -[2023-10-09 08:35:36,362][23468] Updated weights for policy 0, policy_version 7930 (0.0007) -[2023-10-09 08:35:39,746][23469] Updated weights for policy 1, policy_version 7970 (0.0007) -[2023-10-09 08:35:40,117][23469] Updated weights for policy 1, policy_version 7980 (0.0009) -[2023-10-09 08:35:40,274][23468] Updated weights for policy 0, policy_version 7940 (0.0007) -[2023-10-09 08:35:40,487][23469] Updated weights for policy 1, policy_version 7990 (0.0009) -[2023-10-09 08:35:40,643][23468] Updated weights for policy 0, policy_version 7950 (0.0008) -[2023-10-09 08:35:40,855][23469] Updated weights for policy 1, policy_version 8000 (0.0007) -[2023-10-09 08:35:41,018][23468] Updated weights for policy 0, policy_version 7960 (0.0007) -[2023-10-09 08:35:41,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 16318464. Throughput: 0: 1777.5, 1: 1803.9. Samples: 4088318. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:35:41,078][22500] Avg episode reward: [(0, '5.410'), (1, '5.760')] -[2023-10-09 08:35:44,605][23469] Updated weights for policy 1, policy_version 8010 (0.0008) -[2023-10-09 08:35:44,715][23468] Updated weights for policy 0, policy_version 7970 (0.0008) -[2023-10-09 08:35:44,963][23469] Updated weights for policy 1, policy_version 8020 (0.0007) -[2023-10-09 08:35:45,080][23468] Updated weights for policy 0, policy_version 7980 (0.0008) -[2023-10-09 08:35:45,336][23469] Updated weights for policy 1, policy_version 8030 (0.0008) -[2023-10-09 08:35:45,461][23468] Updated weights for policy 0, policy_version 7990 (0.0008) -[2023-10-09 08:35:45,826][23468] Updated weights for policy 0, policy_version 8000 (0.0007) -[2023-10-09 08:35:46,077][22500] Fps is (10 sec: 19661.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 16416768. Throughput: 0: 1778.1, 1: 1780.1. Samples: 4108568. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) -[2023-10-09 08:35:46,078][22500] Avg episode reward: [(0, '5.280'), (1, '5.300')] -[2023-10-09 08:35:49,318][23469] Updated weights for policy 1, policy_version 8040 (0.0008) -[2023-10-09 08:35:49,621][23468] Updated weights for policy 0, policy_version 8010 (0.0007) -[2023-10-09 08:35:49,697][23469] Updated weights for policy 1, policy_version 8050 (0.0008) -[2023-10-09 08:35:49,988][23468] Updated weights for policy 0, policy_version 8020 (0.0007) -[2023-10-09 08:35:50,070][23469] Updated weights for policy 1, policy_version 8060 (0.0009) -[2023-10-09 08:35:50,365][23468] Updated weights for policy 0, policy_version 8030 (0.0008) -[2023-10-09 08:35:51,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 16482304. Throughput: 0: 1778.0, 1: 1799.8. Samples: 4120436. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) -[2023-10-09 08:35:51,078][22500] Avg episode reward: [(0, '5.310'), (1, '5.410')] -[2023-10-09 08:35:54,037][23469] Updated weights for policy 1, policy_version 8070 (0.0008) -[2023-10-09 08:35:54,323][23468] Updated weights for policy 0, policy_version 8040 (0.0010) -[2023-10-09 08:35:54,420][23469] Updated weights for policy 1, policy_version 8080 (0.0008) -[2023-10-09 08:35:54,703][23468] Updated weights for policy 0, policy_version 8050 (0.0009) -[2023-10-09 08:35:54,798][23469] Updated weights for policy 1, policy_version 8090 (0.0007) -[2023-10-09 08:35:55,085][23468] Updated weights for policy 0, policy_version 8060 (0.0007) -[2023-10-09 08:35:56,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 16547840. Throughput: 0: 1794.9, 1: 1779.1. Samples: 4140702. Policy #0 lag: (min: 21.0, avg: 22.4, max: 46.0) -[2023-10-09 08:35:56,078][22500] Avg episode reward: [(0, '5.170'), (1, '4.980')] -[2023-10-09 08:35:58,641][23469] Updated weights for policy 1, policy_version 8100 (0.0008) -[2023-10-09 08:35:58,805][23468] Updated weights for policy 0, policy_version 8070 (0.0007) -[2023-10-09 08:35:59,003][23469] Updated weights for policy 1, policy_version 8110 (0.0008) -[2023-10-09 08:35:59,171][23468] Updated weights for policy 0, policy_version 8080 (0.0007) -[2023-10-09 08:35:59,369][23469] Updated weights for policy 1, policy_version 8120 (0.0009) -[2023-10-09 08:35:59,543][23468] Updated weights for policy 0, policy_version 8090 (0.0008) -[2023-10-09 08:36:01,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 16613376. Throughput: 0: 1766.2, 1: 1764.4. Samples: 4161136. Policy #0 lag: (min: 21.0, avg: 22.4, max: 46.0) -[2023-10-09 08:36:01,078][22500] Avg episode reward: [(0, '5.170'), (1, '4.950')] -[2023-10-09 08:36:03,180][23469] Updated weights for policy 1, policy_version 8130 (0.0009) -[2023-10-09 08:36:03,190][23468] Updated weights for policy 0, policy_version 8100 (0.0008) -[2023-10-09 08:36:03,552][23469] Updated weights for policy 1, policy_version 8140 (0.0007) -[2023-10-09 08:36:03,560][23468] Updated weights for policy 0, policy_version 8110 (0.0007) -[2023-10-09 08:36:03,912][23469] Updated weights for policy 1, policy_version 8150 (0.0009) -[2023-10-09 08:36:03,939][23468] Updated weights for policy 0, policy_version 8120 (0.0007) -[2023-10-09 08:36:04,287][23469] Updated weights for policy 1, policy_version 8160 (0.0009) -[2023-10-09 08:36:06,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 16678912. Throughput: 0: 1795.5, 1: 1777.8. Samples: 4172602. Policy #0 lag: (min: 2.0, avg: 3.6, max: 22.0) -[2023-10-09 08:36:06,078][22500] Avg episode reward: [(0, '5.490'), (1, '4.940')] -[2023-10-09 08:36:07,810][23468] Updated weights for policy 0, policy_version 8130 (0.0007) -[2023-10-09 08:36:08,186][23468] Updated weights for policy 0, policy_version 8140 (0.0008) -[2023-10-09 08:36:08,277][23469] Updated weights for policy 1, policy_version 8170 (0.0008) -[2023-10-09 08:36:08,559][23468] Updated weights for policy 0, policy_version 8150 (0.0007) -[2023-10-09 08:36:08,644][23469] Updated weights for policy 1, policy_version 8180 (0.0008) -[2023-10-09 08:36:08,936][23468] Updated weights for policy 0, policy_version 8160 (0.0007) -[2023-10-09 08:36:09,026][23469] Updated weights for policy 1, policy_version 8190 (0.0009) -[2023-10-09 08:36:11,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 16744448. Throughput: 0: 1767.0, 1: 1752.0. Samples: 4192704. Policy #0 lag: (min: 2.0, avg: 3.6, max: 22.0) -[2023-10-09 08:36:11,078][22500] Avg episode reward: [(0, '5.320'), (1, '5.440')] -[2023-10-09 08:36:12,660][23468] Updated weights for policy 0, policy_version 8170 (0.0008) -[2023-10-09 08:36:12,695][23469] Updated weights for policy 1, policy_version 8200 (0.0008) -[2023-10-09 08:36:13,034][23468] Updated weights for policy 0, policy_version 8180 (0.0007) -[2023-10-09 08:36:13,070][23469] Updated weights for policy 1, policy_version 8210 (0.0007) -[2023-10-09 08:36:13,398][23468] Updated weights for policy 0, policy_version 8190 (0.0008) -[2023-10-09 08:36:13,451][23469] Updated weights for policy 1, policy_version 8220 (0.0008) -[2023-10-09 08:36:16,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 16809984. Throughput: 0: 1762.2, 1: 1761.5. Samples: 4214876. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 08:36:16,078][22500] Avg episode reward: [(0, '5.280'), (1, '5.640')] -[2023-10-09 08:36:16,086][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000008224_8421376.pth... -[2023-10-09 08:36:16,086][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000008192_8388608.pth... -[2023-10-09 08:36:16,125][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000006528_6684672.pth -[2023-10-09 08:36:16,125][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000006560_6717440.pth -[2023-10-09 08:36:16,131][23343] Saving a milestone ./train_atari/atari_berzerk_APPO/checkpoint_p1/milestones/checkpoint_000008224_8421376.pth -[2023-10-09 08:36:16,131][23265] Saving a milestone ./train_atari/atari_berzerk_APPO/checkpoint_p0/milestones/checkpoint_000008192_8388608.pth -[2023-10-09 08:36:17,142][23469] Updated weights for policy 1, policy_version 8230 (0.0008) -[2023-10-09 08:36:17,266][23468] Updated weights for policy 0, policy_version 8200 (0.0008) -[2023-10-09 08:36:17,513][23469] Updated weights for policy 1, policy_version 8240 (0.0008) -[2023-10-09 08:36:17,636][23468] Updated weights for policy 0, policy_version 8210 (0.0008) -[2023-10-09 08:36:17,890][23469] Updated weights for policy 1, policy_version 8250 (0.0008) -[2023-10-09 08:36:18,002][23468] Updated weights for policy 0, policy_version 8220 (0.0009) -[2023-10-09 08:36:21,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 16875520. Throughput: 0: 1763.6, 1: 1753.4. Samples: 4224678. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 08:36:21,079][22500] Avg episode reward: [(0, '5.010'), (1, '5.540')] -[2023-10-09 08:36:21,588][23469] Updated weights for policy 1, policy_version 8260 (0.0008) -[2023-10-09 08:36:21,693][23468] Updated weights for policy 0, policy_version 8230 (0.0008) -[2023-10-09 08:36:21,963][23469] Updated weights for policy 1, policy_version 8270 (0.0008) -[2023-10-09 08:36:22,068][23468] Updated weights for policy 0, policy_version 8240 (0.0009) -[2023-10-09 08:36:22,328][23469] Updated weights for policy 1, policy_version 8280 (0.0008) -[2023-10-09 08:36:22,435][23468] Updated weights for policy 0, policy_version 8250 (0.0007) -[2023-10-09 08:36:26,067][23469] Updated weights for policy 1, policy_version 8290 (0.0008) -[2023-10-09 08:36:26,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 16941056. Throughput: 0: 1765.9, 1: 1761.5. Samples: 4247052. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-09 08:36:26,078][22500] Avg episode reward: [(0, '5.540'), (1, '5.460')] -[2023-10-09 08:36:26,300][23468] Updated weights for policy 0, policy_version 8260 (0.0008) -[2023-10-09 08:36:26,434][23469] Updated weights for policy 1, policy_version 8300 (0.0008) -[2023-10-09 08:36:26,673][23468] Updated weights for policy 0, policy_version 8270 (0.0007) -[2023-10-09 08:36:26,800][23469] Updated weights for policy 1, policy_version 8310 (0.0007) -[2023-10-09 08:36:27,041][23468] Updated weights for policy 0, policy_version 8280 (0.0007) -[2023-10-09 08:36:27,172][23469] Updated weights for policy 1, policy_version 8320 (0.0007) -[2023-10-09 08:36:30,671][23468] Updated weights for policy 0, policy_version 8290 (0.0008) -[2023-10-09 08:36:30,874][23469] Updated weights for policy 1, policy_version 8330 (0.0010) -[2023-10-09 08:36:31,041][23468] Updated weights for policy 0, policy_version 8300 (0.0010) -[2023-10-09 08:36:31,078][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 17006592. Throughput: 0: 1783.0, 1: 1788.8. Samples: 4269300. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-09 08:36:31,078][22500] Avg episode reward: [(0, '5.480'), (1, '5.270')] -[2023-10-09 08:36:31,255][23469] Updated weights for policy 1, policy_version 8340 (0.0009) -[2023-10-09 08:36:31,405][23468] Updated weights for policy 0, policy_version 8310 (0.0007) -[2023-10-09 08:36:31,624][23469] Updated weights for policy 1, policy_version 8350 (0.0008) -[2023-10-09 08:36:31,786][23468] Updated weights for policy 0, policy_version 8320 (0.0009) -[2023-10-09 08:36:35,460][23469] Updated weights for policy 1, policy_version 8360 (0.0007) -[2023-10-09 08:36:35,646][23468] Updated weights for policy 0, policy_version 8330 (0.0008) -[2023-10-09 08:36:35,828][23469] Updated weights for policy 1, policy_version 8370 (0.0007) -[2023-10-09 08:36:36,014][23468] Updated weights for policy 0, policy_version 8340 (0.0008) -[2023-10-09 08:36:36,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 17072128. Throughput: 0: 1761.5, 1: 1764.2. Samples: 4279092. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:36:36,078][22500] Avg episode reward: [(0, '5.900'), (1, '5.250')] -[2023-10-09 08:36:36,190][23469] Updated weights for policy 1, policy_version 8380 (0.0008) -[2023-10-09 08:36:36,384][23468] Updated weights for policy 0, policy_version 8350 (0.0008) -[2023-10-09 08:36:40,121][23469] Updated weights for policy 1, policy_version 8390 (0.0008) -[2023-10-09 08:36:40,391][23468] Updated weights for policy 0, policy_version 8360 (0.0009) -[2023-10-09 08:36:40,496][23469] Updated weights for policy 1, policy_version 8400 (0.0007) -[2023-10-09 08:36:40,768][23468] Updated weights for policy 0, policy_version 8370 (0.0009) -[2023-10-09 08:36:40,868][23469] Updated weights for policy 1, policy_version 8410 (0.0008) -[2023-10-09 08:36:41,078][22500] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 17137664. Throughput: 0: 1763.5, 1: 1795.7. Samples: 4300866. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:36:41,079][22500] Avg episode reward: [(0, '5.770'), (1, '4.950')] -[2023-10-09 08:36:41,131][23468] Updated weights for policy 0, policy_version 8380 (0.0008) -[2023-10-09 08:36:44,704][23469] Updated weights for policy 1, policy_version 8420 (0.0008) -[2023-10-09 08:36:44,961][23468] Updated weights for policy 0, policy_version 8390 (0.0009) -[2023-10-09 08:36:45,066][23469] Updated weights for policy 1, policy_version 8430 (0.0008) -[2023-10-09 08:36:45,345][23468] Updated weights for policy 0, policy_version 8400 (0.0007) -[2023-10-09 08:36:45,434][23469] Updated weights for policy 1, policy_version 8440 (0.0008) -[2023-10-09 08:36:45,711][23468] Updated weights for policy 0, policy_version 8410 (0.0007) -[2023-10-09 08:36:46,077][22500] Fps is (10 sec: 19661.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 17268736. Throughput: 0: 1777.2, 1: 1767.7. Samples: 4320654. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-09 08:36:46,078][22500] Avg episode reward: [(0, '5.830'), (1, '5.290')] -[2023-10-09 08:36:49,290][23469] Updated weights for policy 1, policy_version 8450 (0.0008) -[2023-10-09 08:36:49,654][23469] Updated weights for policy 1, policy_version 8460 (0.0010) -[2023-10-09 08:36:49,741][23468] Updated weights for policy 0, policy_version 8420 (0.0009) -[2023-10-09 08:36:50,023][23469] Updated weights for policy 1, policy_version 8470 (0.0008) -[2023-10-09 08:36:50,109][23468] Updated weights for policy 0, policy_version 8430 (0.0007) -[2023-10-09 08:36:50,384][23469] Updated weights for policy 1, policy_version 8480 (0.0008) -[2023-10-09 08:36:50,482][23468] Updated weights for policy 0, policy_version 8440 (0.0008) -[2023-10-09 08:36:51,077][22500] Fps is (10 sec: 19661.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 17334272. Throughput: 0: 1758.2, 1: 1786.6. Samples: 4332118. Policy #0 lag: (min: 21.0, avg: 27.7, max: 53.0) -[2023-10-09 08:36:51,078][22500] Avg episode reward: [(0, '5.430'), (1, '5.310')] -[2023-10-09 08:36:54,246][23469] Updated weights for policy 1, policy_version 8490 (0.0007) -[2023-10-09 08:36:54,246][23468] Updated weights for policy 0, policy_version 8450 (0.0011) -[2023-10-09 08:36:54,610][23469] Updated weights for policy 1, policy_version 8500 (0.0008) -[2023-10-09 08:36:54,620][23468] Updated weights for policy 0, policy_version 8460 (0.0010) -[2023-10-09 08:36:54,986][23469] Updated weights for policy 1, policy_version 8510 (0.0010) -[2023-10-09 08:36:54,993][23468] Updated weights for policy 0, policy_version 8470 (0.0007) -[2023-10-09 08:36:55,361][23468] Updated weights for policy 0, policy_version 8480 (0.0007) -[2023-10-09 08:36:56,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 17399808. Throughput: 0: 1779.9, 1: 1784.3. Samples: 4353092. Policy #0 lag: (min: 21.0, avg: 27.7, max: 53.0) -[2023-10-09 08:36:56,079][22500] Avg episode reward: [(0, '5.330'), (1, '5.260')] -[2023-10-09 08:36:58,681][23469] Updated weights for policy 1, policy_version 8520 (0.0008) -[2023-10-09 08:36:59,041][23469] Updated weights for policy 1, policy_version 8530 (0.0008) -[2023-10-09 08:36:59,181][23468] Updated weights for policy 0, policy_version 8490 (0.0008) -[2023-10-09 08:36:59,410][23469] Updated weights for policy 1, policy_version 8540 (0.0008) -[2023-10-09 08:36:59,546][23468] Updated weights for policy 0, policy_version 8500 (0.0010) -[2023-10-09 08:36:59,926][23468] Updated weights for policy 0, policy_version 8510 (0.0008) -[2023-10-09 08:37:01,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 17465344. Throughput: 0: 1747.3, 1: 1777.0. Samples: 4373470. Policy #0 lag: (min: 26.0, avg: 29.0, max: 58.0) -[2023-10-09 08:37:01,079][22500] Avg episode reward: [(0, '5.400'), (1, '5.310')] -[2023-10-09 08:37:03,085][23469] Updated weights for policy 1, policy_version 8550 (0.0007) -[2023-10-09 08:37:03,459][23469] Updated weights for policy 1, policy_version 8560 (0.0007) -[2023-10-09 08:37:03,727][23468] Updated weights for policy 0, policy_version 8520 (0.0008) -[2023-10-09 08:37:03,820][23469] Updated weights for policy 1, policy_version 8570 (0.0007) -[2023-10-09 08:37:04,092][23468] Updated weights for policy 0, policy_version 8530 (0.0008) -[2023-10-09 08:37:04,461][23468] Updated weights for policy 0, policy_version 8540 (0.0010) -[2023-10-09 08:37:06,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 17530880. Throughput: 0: 1781.2, 1: 1785.8. Samples: 4385192. Policy #0 lag: (min: 26.0, avg: 29.0, max: 58.0) -[2023-10-09 08:37:06,078][22500] Avg episode reward: [(0, '5.570'), (1, '5.280')] -[2023-10-09 08:37:07,551][23469] Updated weights for policy 1, policy_version 8580 (0.0011) -[2023-10-09 08:37:07,916][23469] Updated weights for policy 1, policy_version 8590 (0.0009) -[2023-10-09 08:37:08,286][23469] Updated weights for policy 1, policy_version 8600 (0.0008) -[2023-10-09 08:37:08,345][23468] Updated weights for policy 0, policy_version 8550 (0.0009) -[2023-10-09 08:37:08,722][23468] Updated weights for policy 0, policy_version 8560 (0.0008) -[2023-10-09 08:37:09,100][23468] Updated weights for policy 0, policy_version 8570 (0.0009) -[2023-10-09 08:37:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 17596416. Throughput: 0: 1750.8, 1: 1770.7. Samples: 4405518. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:37:11,078][22500] Avg episode reward: [(0, '5.380'), (1, '5.410')] -[2023-10-09 08:37:12,156][23469] Updated weights for policy 1, policy_version 8610 (0.0008) -[2023-10-09 08:37:12,522][23469] Updated weights for policy 1, policy_version 8620 (0.0010) -[2023-10-09 08:37:12,890][23469] Updated weights for policy 1, policy_version 8630 (0.0009) -[2023-10-09 08:37:12,931][23468] Updated weights for policy 0, policy_version 8580 (0.0007) -[2023-10-09 08:37:13,260][23469] Updated weights for policy 1, policy_version 8640 (0.0008) -[2023-10-09 08:37:13,302][23468] Updated weights for policy 0, policy_version 8590 (0.0007) -[2023-10-09 08:37:13,684][23468] Updated weights for policy 0, policy_version 8600 (0.0008) -[2023-10-09 08:37:16,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 17661952. Throughput: 0: 1748.6, 1: 1770.6. Samples: 4427666. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:37:16,078][22500] Avg episode reward: [(0, '5.100'), (1, '5.300')] -[2023-10-09 08:37:17,130][23469] Updated weights for policy 1, policy_version 8650 (0.0008) -[2023-10-09 08:37:17,347][23468] Updated weights for policy 0, policy_version 8610 (0.0007) -[2023-10-09 08:37:17,495][23469] Updated weights for policy 1, policy_version 8660 (0.0007) -[2023-10-09 08:37:17,723][23468] Updated weights for policy 0, policy_version 8620 (0.0007) -[2023-10-09 08:37:17,860][23469] Updated weights for policy 1, policy_version 8670 (0.0008) -[2023-10-09 08:37:18,098][23468] Updated weights for policy 0, policy_version 8630 (0.0009) -[2023-10-09 08:37:18,470][23468] Updated weights for policy 0, policy_version 8640 (0.0007) -[2023-10-09 08:37:21,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 17727488. Throughput: 0: 1757.2, 1: 1762.1. Samples: 4437458. Policy #0 lag: (min: 31.0, avg: 46.9, max: 63.0) -[2023-10-09 08:37:21,078][22500] Avg episode reward: [(0, '5.260'), (1, '5.380')] -[2023-10-09 08:37:21,647][23469] Updated weights for policy 1, policy_version 8680 (0.0008) -[2023-10-09 08:37:22,013][23469] Updated weights for policy 1, policy_version 8690 (0.0008) -[2023-10-09 08:37:22,242][23468] Updated weights for policy 0, policy_version 8650 (0.0008) -[2023-10-09 08:37:22,385][23469] Updated weights for policy 1, policy_version 8700 (0.0008) -[2023-10-09 08:37:22,621][23468] Updated weights for policy 0, policy_version 8660 (0.0008) -[2023-10-09 08:37:23,001][23468] Updated weights for policy 0, policy_version 8670 (0.0008) -[2023-10-09 08:37:26,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 17793024. Throughput: 0: 1762.7, 1: 1765.1. Samples: 4459616. Policy #0 lag: (min: 31.0, avg: 46.9, max: 63.0) -[2023-10-09 08:37:26,078][22500] Avg episode reward: [(0, '5.300'), (1, '5.160')] -[2023-10-09 08:37:26,253][23469] Updated weights for policy 1, policy_version 8710 (0.0009) -[2023-10-09 08:37:26,632][23469] Updated weights for policy 1, policy_version 8720 (0.0009) -[2023-10-09 08:37:26,712][23468] Updated weights for policy 0, policy_version 8680 (0.0009) -[2023-10-09 08:37:27,004][23469] Updated weights for policy 1, policy_version 8730 (0.0007) -[2023-10-09 08:37:27,093][23468] Updated weights for policy 0, policy_version 8690 (0.0007) -[2023-10-09 08:37:27,467][23468] Updated weights for policy 0, policy_version 8700 (0.0010) -[2023-10-09 08:37:30,613][23469] Updated weights for policy 1, policy_version 8740 (0.0007) -[2023-10-09 08:37:30,984][23469] Updated weights for policy 1, policy_version 8750 (0.0007) -[2023-10-09 08:37:31,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 17858560. Throughput: 0: 1769.4, 1: 1801.0. Samples: 4481322. Policy #0 lag: (min: 15.0, avg: 15.8, max: 34.0) -[2023-10-09 08:37:31,078][22500] Avg episode reward: [(0, '5.440'), (1, '5.270')] -[2023-10-09 08:37:31,362][23469] Updated weights for policy 1, policy_version 8760 (0.0007) -[2023-10-09 08:37:31,426][23468] Updated weights for policy 0, policy_version 8710 (0.0008) -[2023-10-09 08:37:31,797][23468] Updated weights for policy 0, policy_version 8720 (0.0008) -[2023-10-09 08:37:32,166][23468] Updated weights for policy 0, policy_version 8730 (0.0008) -[2023-10-09 08:37:35,024][23469] Updated weights for policy 1, policy_version 8770 (0.0009) -[2023-10-09 08:37:35,396][23469] Updated weights for policy 1, policy_version 8780 (0.0008) -[2023-10-09 08:37:35,764][23469] Updated weights for policy 1, policy_version 8790 (0.0009) -[2023-10-09 08:37:36,022][23468] Updated weights for policy 0, policy_version 8740 (0.0009) -[2023-10-09 08:37:36,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 17924096. Throughput: 0: 1760.1, 1: 1778.5. Samples: 4491356. Policy #0 lag: (min: 15.0, avg: 15.8, max: 34.0) -[2023-10-09 08:37:36,078][22500] Avg episode reward: [(0, '5.230'), (1, '5.480')] -[2023-10-09 08:37:36,130][23469] Updated weights for policy 1, policy_version 8800 (0.0008) -[2023-10-09 08:37:36,393][23468] Updated weights for policy 0, policy_version 8750 (0.0009) -[2023-10-09 08:37:36,768][23468] Updated weights for policy 0, policy_version 8760 (0.0008) -[2023-10-09 08:37:39,994][23469] Updated weights for policy 1, policy_version 8810 (0.0008) -[2023-10-09 08:37:40,365][23469] Updated weights for policy 1, policy_version 8820 (0.0008) -[2023-10-09 08:37:40,687][23468] Updated weights for policy 0, policy_version 8770 (0.0009) -[2023-10-09 08:37:40,740][23469] Updated weights for policy 1, policy_version 8830 (0.0007) -[2023-10-09 08:37:41,058][23468] Updated weights for policy 0, policy_version 8780 (0.0007) -[2023-10-09 08:37:41,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 18022400. Throughput: 0: 1759.7, 1: 1797.7. Samples: 4513172. Policy #0 lag: (min: 9.0, avg: 18.2, max: 41.0) -[2023-10-09 08:37:41,078][22500] Avg episode reward: [(0, '5.700'), (1, '5.540')] -[2023-10-09 08:37:41,430][23468] Updated weights for policy 0, policy_version 8790 (0.0007) -[2023-10-09 08:37:41,799][23468] Updated weights for policy 0, policy_version 8800 (0.0008) -[2023-10-09 08:37:44,516][23469] Updated weights for policy 1, policy_version 8840 (0.0009) -[2023-10-09 08:37:44,889][23469] Updated weights for policy 1, policy_version 8850 (0.0008) -[2023-10-09 08:37:45,265][23469] Updated weights for policy 1, policy_version 8860 (0.0008) -[2023-10-09 08:37:45,635][23468] Updated weights for policy 0, policy_version 8810 (0.0008) -[2023-10-09 08:37:45,999][23468] Updated weights for policy 0, policy_version 8820 (0.0008) -[2023-10-09 08:37:46,077][22500] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 14218.0). Total num frames: 18087936. Throughput: 0: 1794.0, 1: 1776.3. Samples: 4534132. Policy #0 lag: (min: 9.0, avg: 18.2, max: 41.0) -[2023-10-09 08:37:46,078][22500] Avg episode reward: [(0, '5.280'), (1, '5.590')] -[2023-10-09 08:37:46,383][23468] Updated weights for policy 0, policy_version 8830 (0.0008) -[2023-10-09 08:37:48,964][23469] Updated weights for policy 1, policy_version 8870 (0.0008) -[2023-10-09 08:37:49,331][23469] Updated weights for policy 1, policy_version 8880 (0.0008) -[2023-10-09 08:37:49,706][23469] Updated weights for policy 1, policy_version 8890 (0.0007) -[2023-10-09 08:37:50,084][23468] Updated weights for policy 0, policy_version 8840 (0.0008) -[2023-10-09 08:37:50,457][23468] Updated weights for policy 0, policy_version 8850 (0.0009) -[2023-10-09 08:37:50,830][23468] Updated weights for policy 0, policy_version 8860 (0.0008) -[2023-10-09 08:37:51,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 18186240. Throughput: 0: 1758.0, 1: 1803.5. Samples: 4545460. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 08:37:51,079][22500] Avg episode reward: [(0, '5.400'), (1, '5.450')] -[2023-10-09 08:37:53,343][23469] Updated weights for policy 1, policy_version 8900 (0.0009) -[2023-10-09 08:37:53,718][23469] Updated weights for policy 1, policy_version 8910 (0.0010) -[2023-10-09 08:37:54,085][23469] Updated weights for policy 1, policy_version 8920 (0.0009) -[2023-10-09 08:37:54,594][23468] Updated weights for policy 0, policy_version 8870 (0.0008) -[2023-10-09 08:37:54,974][23468] Updated weights for policy 0, policy_version 8880 (0.0008) -[2023-10-09 08:37:55,341][23468] Updated weights for policy 0, policy_version 8890 (0.0008) -[2023-10-09 08:37:56,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 18251776. Throughput: 0: 1795.8, 1: 1786.3. Samples: 4566710. Policy #0 lag: (min: 17.0, avg: 27.2, max: 49.0) -[2023-10-09 08:37:56,078][22500] Avg episode reward: [(0, '5.370'), (1, '5.580')] -[2023-10-09 08:37:57,931][23469] Updated weights for policy 1, policy_version 8930 (0.0009) -[2023-10-09 08:37:58,294][23469] Updated weights for policy 1, policy_version 8940 (0.0008) -[2023-10-09 08:37:58,659][23469] Updated weights for policy 1, policy_version 8950 (0.0007) -[2023-10-09 08:37:58,958][23468] Updated weights for policy 0, policy_version 8900 (0.0008) -[2023-10-09 08:37:59,029][23469] Updated weights for policy 1, policy_version 8960 (0.0009) -[2023-10-09 08:37:59,334][23468] Updated weights for policy 0, policy_version 8910 (0.0007) -[2023-10-09 08:37:59,716][23468] Updated weights for policy 0, policy_version 8920 (0.0009) -[2023-10-09 08:38:01,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 18317312. Throughput: 0: 1762.4, 1: 1790.2. Samples: 4587532. Policy #0 lag: (min: 17.0, avg: 27.2, max: 49.0) -[2023-10-09 08:38:01,078][22500] Avg episode reward: [(0, '5.600'), (1, '5.600')] -[2023-10-09 08:38:02,725][23469] Updated weights for policy 1, policy_version 8970 (0.0008) -[2023-10-09 08:38:03,096][23469] Updated weights for policy 1, policy_version 8980 (0.0008) -[2023-10-09 08:38:03,323][23468] Updated weights for policy 0, policy_version 8930 (0.0008) -[2023-10-09 08:38:03,474][23469] Updated weights for policy 1, policy_version 8990 (0.0009) -[2023-10-09 08:38:03,694][23468] Updated weights for policy 0, policy_version 8940 (0.0007) -[2023-10-09 08:38:04,063][23468] Updated weights for policy 0, policy_version 8950 (0.0007) -[2023-10-09 08:38:04,429][23468] Updated weights for policy 0, policy_version 8960 (0.0007) -[2023-10-09 08:38:06,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 18382848. Throughput: 0: 1788.3, 1: 1794.6. Samples: 4598690. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-09 08:38:06,079][22500] Avg episode reward: [(0, '5.500'), (1, '5.290')] -[2023-10-09 08:38:07,166][23469] Updated weights for policy 1, policy_version 9000 (0.0008) -[2023-10-09 08:38:07,533][23469] Updated weights for policy 1, policy_version 9010 (0.0010) -[2023-10-09 08:38:07,910][23469] Updated weights for policy 1, policy_version 9020 (0.0010) -[2023-10-09 08:38:08,275][23468] Updated weights for policy 0, policy_version 8970 (0.0009) -[2023-10-09 08:38:08,647][23468] Updated weights for policy 0, policy_version 8980 (0.0009) -[2023-10-09 08:38:09,023][23468] Updated weights for policy 0, policy_version 8990 (0.0008) -[2023-10-09 08:38:11,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 18448384. Throughput: 0: 1757.8, 1: 1794.2. Samples: 4619456. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-09 08:38:11,078][22500] Avg episode reward: [(0, '5.840'), (1, '5.530')] -[2023-10-09 08:38:11,877][23469] Updated weights for policy 1, policy_version 9030 (0.0007) -[2023-10-09 08:38:12,237][23469] Updated weights for policy 1, policy_version 9040 (0.0010) -[2023-10-09 08:38:12,617][23469] Updated weights for policy 1, policy_version 9050 (0.0008) -[2023-10-09 08:38:12,921][23468] Updated weights for policy 0, policy_version 9000 (0.0008) -[2023-10-09 08:38:13,294][23468] Updated weights for policy 0, policy_version 9010 (0.0007) -[2023-10-09 08:38:13,666][23468] Updated weights for policy 0, policy_version 9020 (0.0007) -[2023-10-09 08:38:16,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 18513920. Throughput: 0: 1761.8, 1: 1794.3. Samples: 4641346. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-09 08:38:16,078][22500] Avg episode reward: [(0, '5.970'), (1, '5.310')] -[2023-10-09 08:38:16,088][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000009024_9240576.pth... -[2023-10-09 08:38:16,088][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000009056_9273344.pth... -[2023-10-09 08:38:16,123][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000007392_7569408.pth -[2023-10-09 08:38:16,128][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000007360_7536640.pth -[2023-10-09 08:38:16,371][23469] Updated weights for policy 1, policy_version 9060 (0.0009) -[2023-10-09 08:38:16,732][23469] Updated weights for policy 1, policy_version 9070 (0.0008) -[2023-10-09 08:38:17,103][23469] Updated weights for policy 1, policy_version 9080 (0.0008) -[2023-10-09 08:38:17,420][23468] Updated weights for policy 0, policy_version 9030 (0.0008) -[2023-10-09 08:38:17,796][23468] Updated weights for policy 0, policy_version 9040 (0.0008) -[2023-10-09 08:38:18,165][23468] Updated weights for policy 0, policy_version 9050 (0.0007) -[2023-10-09 08:38:20,907][23469] Updated weights for policy 1, policy_version 9090 (0.0008) -[2023-10-09 08:38:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 18579456. Throughput: 0: 1770.3, 1: 1786.1. Samples: 4651394. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-09 08:38:21,078][22500] Avg episode reward: [(0, '6.060'), (1, '5.610')] -[2023-10-09 08:38:21,079][23265] Saving new best policy, reward=6.060! -[2023-10-09 08:38:21,281][23469] Updated weights for policy 1, policy_version 9100 (0.0008) -[2023-10-09 08:38:21,663][23469] Updated weights for policy 1, policy_version 9110 (0.0009) -[2023-10-09 08:38:21,989][23468] Updated weights for policy 0, policy_version 9060 (0.0009) -[2023-10-09 08:38:22,027][23469] Updated weights for policy 1, policy_version 9120 (0.0009) -[2023-10-09 08:38:22,373][23468] Updated weights for policy 0, policy_version 9070 (0.0009) -[2023-10-09 08:38:22,742][23468] Updated weights for policy 0, policy_version 9080 (0.0009) -[2023-10-09 08:38:25,598][23469] Updated weights for policy 1, policy_version 9130 (0.0010) -[2023-10-09 08:38:25,963][23469] Updated weights for policy 1, policy_version 9140 (0.0010) -[2023-10-09 08:38:26,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 18644992. Throughput: 0: 1771.5, 1: 1797.2. Samples: 4673764. Policy #0 lag: (min: 26.0, avg: 29.7, max: 58.0) -[2023-10-09 08:38:26,079][22500] Avg episode reward: [(0, '5.500'), (1, '5.460')] -[2023-10-09 08:38:26,342][23469] Updated weights for policy 1, policy_version 9150 (0.0007) -[2023-10-09 08:38:26,642][23468] Updated weights for policy 0, policy_version 9090 (0.0009) -[2023-10-09 08:38:27,021][23468] Updated weights for policy 0, policy_version 9100 (0.0007) -[2023-10-09 08:38:27,383][23468] Updated weights for policy 0, policy_version 9110 (0.0007) -[2023-10-09 08:38:27,758][23468] Updated weights for policy 0, policy_version 9120 (0.0009) -[2023-10-09 08:38:29,990][23469] Updated weights for policy 1, policy_version 9160 (0.0009) -[2023-10-09 08:38:30,357][23469] Updated weights for policy 1, policy_version 9170 (0.0011) -[2023-10-09 08:38:30,731][23469] Updated weights for policy 1, policy_version 9180 (0.0008) -[2023-10-09 08:38:31,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 18743296. Throughput: 0: 1771.4, 1: 1800.2. Samples: 4694856. Policy #0 lag: (min: 26.0, avg: 29.7, max: 58.0) -[2023-10-09 08:38:31,078][22500] Avg episode reward: [(0, '5.330'), (1, '5.780')] -[2023-10-09 08:38:31,514][23468] Updated weights for policy 0, policy_version 9130 (0.0008) -[2023-10-09 08:38:31,888][23468] Updated weights for policy 0, policy_version 9140 (0.0009) -[2023-10-09 08:38:32,265][23468] Updated weights for policy 0, policy_version 9150 (0.0008) -[2023-10-09 08:38:34,588][23469] Updated weights for policy 1, policy_version 9190 (0.0009) -[2023-10-09 08:38:34,956][23469] Updated weights for policy 1, policy_version 9200 (0.0008) -[2023-10-09 08:38:35,325][23469] Updated weights for policy 1, policy_version 9210 (0.0007) -[2023-10-09 08:38:36,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 18808832. Throughput: 0: 1769.3, 1: 1793.7. Samples: 4705794. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-09 08:38:36,078][22500] Avg episode reward: [(0, '5.430'), (1, '5.760')] -[2023-10-09 08:38:36,114][23468] Updated weights for policy 0, policy_version 9160 (0.0008) -[2023-10-09 08:38:36,480][23468] Updated weights for policy 0, policy_version 9170 (0.0007) -[2023-10-09 08:38:36,862][23468] Updated weights for policy 0, policy_version 9180 (0.0007) -[2023-10-09 08:38:39,059][23469] Updated weights for policy 1, policy_version 9220 (0.0008) -[2023-10-09 08:38:39,435][23469] Updated weights for policy 1, policy_version 9230 (0.0008) -[2023-10-09 08:38:39,799][23469] Updated weights for policy 1, policy_version 9240 (0.0009) -[2023-10-09 08:38:40,773][23468] Updated weights for policy 0, policy_version 9190 (0.0009) -[2023-10-09 08:38:41,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 18874368. Throughput: 0: 1763.4, 1: 1799.4. Samples: 4727036. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-09 08:38:41,079][22500] Avg episode reward: [(0, '5.490'), (1, '6.090')] -[2023-10-09 08:38:41,145][23468] Updated weights for policy 0, policy_version 9200 (0.0011) -[2023-10-09 08:38:41,515][23468] Updated weights for policy 0, policy_version 9210 (0.0009) -[2023-10-09 08:38:43,563][23469] Updated weights for policy 1, policy_version 9250 (0.0009) -[2023-10-09 08:38:43,927][23469] Updated weights for policy 1, policy_version 9260 (0.0009) -[2023-10-09 08:38:44,309][23469] Updated weights for policy 1, policy_version 9270 (0.0008) -[2023-10-09 08:38:44,688][23469] Updated weights for policy 1, policy_version 9280 (0.0009) -[2023-10-09 08:38:45,261][23468] Updated weights for policy 0, policy_version 9220 (0.0008) -[2023-10-09 08:38:45,641][23468] Updated weights for policy 0, policy_version 9230 (0.0009) -[2023-10-09 08:38:46,012][23468] Updated weights for policy 0, policy_version 9240 (0.0009) -[2023-10-09 08:38:46,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 18939904. Throughput: 0: 1795.6, 1: 1785.2. Samples: 4748670. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:38:46,078][22500] Avg episode reward: [(0, '5.230'), (1, '5.820')] -[2023-10-09 08:38:48,536][23469] Updated weights for policy 1, policy_version 9290 (0.0008) -[2023-10-09 08:38:48,904][23469] Updated weights for policy 1, policy_version 9300 (0.0009) -[2023-10-09 08:38:49,272][23469] Updated weights for policy 1, policy_version 9310 (0.0008) -[2023-10-09 08:38:49,818][23468] Updated weights for policy 0, policy_version 9250 (0.0007) -[2023-10-09 08:38:50,189][23468] Updated weights for policy 0, policy_version 9260 (0.0007) -[2023-10-09 08:38:50,565][23468] Updated weights for policy 0, policy_version 9270 (0.0009) -[2023-10-09 08:38:50,943][23468] Updated weights for policy 0, policy_version 9280 (0.0008) -[2023-10-09 08:38:51,077][22500] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 19038208. Throughput: 0: 1767.3, 1: 1799.8. Samples: 4759210. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-09 08:38:51,078][22500] Avg episode reward: [(0, '5.670'), (1, '5.420')] -[2023-10-09 08:38:52,962][23469] Updated weights for policy 1, policy_version 9320 (0.0007) -[2023-10-09 08:38:53,339][23469] Updated weights for policy 1, policy_version 9330 (0.0007) -[2023-10-09 08:38:53,711][23469] Updated weights for policy 1, policy_version 9340 (0.0009) -[2023-10-09 08:38:54,723][23468] Updated weights for policy 0, policy_version 9290 (0.0008) -[2023-10-09 08:38:55,104][23468] Updated weights for policy 0, policy_version 9300 (0.0010) -[2023-10-09 08:38:55,478][23468] Updated weights for policy 0, policy_version 9310 (0.0008) -[2023-10-09 08:38:56,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 19103744. Throughput: 0: 1800.4, 1: 1785.6. Samples: 4780828. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-09 08:38:56,078][22500] Avg episode reward: [(0, '5.810'), (1, '5.360')] -[2023-10-09 08:38:57,752][23469] Updated weights for policy 1, policy_version 9350 (0.0009) -[2023-10-09 08:38:58,134][23469] Updated weights for policy 1, policy_version 9360 (0.0010) -[2023-10-09 08:38:58,503][23469] Updated weights for policy 1, policy_version 9370 (0.0008) -[2023-10-09 08:38:59,157][23468] Updated weights for policy 0, policy_version 9320 (0.0008) -[2023-10-09 08:38:59,537][23468] Updated weights for policy 0, policy_version 9330 (0.0009) -[2023-10-09 08:38:59,908][23468] Updated weights for policy 0, policy_version 9340 (0.0009) -[2023-10-09 08:39:01,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 19169280. Throughput: 0: 1770.3, 1: 1788.4. Samples: 4801488. Policy #0 lag: (min: 31.0, avg: 42.1, max: 63.0) -[2023-10-09 08:39:01,078][22500] Avg episode reward: [(0, '5.840'), (1, '5.440')] -[2023-10-09 08:39:02,204][23469] Updated weights for policy 1, policy_version 9380 (0.0008) -[2023-10-09 08:39:02,571][23469] Updated weights for policy 1, policy_version 9390 (0.0008) -[2023-10-09 08:39:02,938][23469] Updated weights for policy 1, policy_version 9400 (0.0009) -[2023-10-09 08:39:03,618][23468] Updated weights for policy 0, policy_version 9350 (0.0008) -[2023-10-09 08:39:03,987][23468] Updated weights for policy 0, policy_version 9360 (0.0007) -[2023-10-09 08:39:04,365][23468] Updated weights for policy 0, policy_version 9370 (0.0007) -[2023-10-09 08:39:06,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 19234816. Throughput: 0: 1802.6, 1: 1786.8. Samples: 4812918. Policy #0 lag: (min: 31.0, avg: 42.1, max: 63.0) -[2023-10-09 08:39:06,079][22500] Avg episode reward: [(0, '5.740'), (1, '5.480')] -[2023-10-09 08:39:06,690][23469] Updated weights for policy 1, policy_version 9410 (0.0007) -[2023-10-09 08:39:07,053][23469] Updated weights for policy 1, policy_version 9420 (0.0007) -[2023-10-09 08:39:07,428][23469] Updated weights for policy 1, policy_version 9430 (0.0007) -[2023-10-09 08:39:07,802][23469] Updated weights for policy 1, policy_version 9440 (0.0008) -[2023-10-09 08:39:08,024][23468] Updated weights for policy 0, policy_version 9380 (0.0008) -[2023-10-09 08:39:08,389][23468] Updated weights for policy 0, policy_version 9390 (0.0011) -[2023-10-09 08:39:08,757][23468] Updated weights for policy 0, policy_version 9400 (0.0010) -[2023-10-09 08:39:11,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 19300352. Throughput: 0: 1773.0, 1: 1785.3. Samples: 4833890. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-09 08:39:11,078][22500] Avg episode reward: [(0, '5.630'), (1, '5.410')] -[2023-10-09 08:39:11,609][23469] Updated weights for policy 1, policy_version 9450 (0.0008) -[2023-10-09 08:39:11,978][23469] Updated weights for policy 1, policy_version 9460 (0.0010) -[2023-10-09 08:39:12,351][23469] Updated weights for policy 1, policy_version 9470 (0.0010) -[2023-10-09 08:39:12,619][23468] Updated weights for policy 0, policy_version 9410 (0.0008) -[2023-10-09 08:39:12,988][23468] Updated weights for policy 0, policy_version 9420 (0.0007) -[2023-10-09 08:39:13,351][23468] Updated weights for policy 0, policy_version 9430 (0.0008) -[2023-10-09 08:39:13,722][23468] Updated weights for policy 0, policy_version 9440 (0.0008) -[2023-10-09 08:39:15,952][23469] Updated weights for policy 1, policy_version 9480 (0.0008) -[2023-10-09 08:39:16,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 19365888. Throughput: 0: 1775.5, 1: 1807.8. Samples: 4856104. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-09 08:39:16,078][22500] Avg episode reward: [(0, '6.290'), (1, '5.470')] -[2023-10-09 08:39:16,089][23265] Saving new best policy, reward=6.290! -[2023-10-09 08:39:16,319][23469] Updated weights for policy 1, policy_version 9490 (0.0008) -[2023-10-09 08:39:16,696][23469] Updated weights for policy 1, policy_version 9500 (0.0007) -[2023-10-09 08:39:17,514][23468] Updated weights for policy 0, policy_version 9450 (0.0010) -[2023-10-09 08:39:17,885][23468] Updated weights for policy 0, policy_version 9460 (0.0010) -[2023-10-09 08:39:18,258][23468] Updated weights for policy 0, policy_version 9470 (0.0011) -[2023-10-09 08:39:20,582][23469] Updated weights for policy 1, policy_version 9510 (0.0009) -[2023-10-09 08:39:20,951][23469] Updated weights for policy 1, policy_version 9520 (0.0011) -[2023-10-09 08:39:21,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 19431424. Throughput: 0: 1783.2, 1: 1783.4. Samples: 4866290. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-09 08:39:21,078][22500] Avg episode reward: [(0, '5.810'), (1, '5.430')] -[2023-10-09 08:39:21,328][23469] Updated weights for policy 1, policy_version 9530 (0.0009) -[2023-10-09 08:39:21,937][23468] Updated weights for policy 0, policy_version 9480 (0.0008) -[2023-10-09 08:39:22,304][23468] Updated weights for policy 0, policy_version 9490 (0.0008) -[2023-10-09 08:39:22,674][23468] Updated weights for policy 0, policy_version 9500 (0.0008) -[2023-10-09 08:39:25,150][23469] Updated weights for policy 1, policy_version 9540 (0.0009) -[2023-10-09 08:39:25,512][23469] Updated weights for policy 1, policy_version 9550 (0.0011) -[2023-10-09 08:39:25,880][23469] Updated weights for policy 1, policy_version 9560 (0.0009) -[2023-10-09 08:39:26,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 19496960. Throughput: 0: 1781.0, 1: 1799.3. Samples: 4888146. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-09 08:39:26,078][22500] Avg episode reward: [(0, '5.400'), (1, '5.230')] -[2023-10-09 08:39:26,529][23468] Updated weights for policy 0, policy_version 9510 (0.0007) -[2023-10-09 08:39:26,903][23468] Updated weights for policy 0, policy_version 9520 (0.0008) -[2023-10-09 08:39:27,276][23468] Updated weights for policy 0, policy_version 9530 (0.0008) -[2023-10-09 08:39:29,580][23469] Updated weights for policy 1, policy_version 9570 (0.0007) -[2023-10-09 08:39:29,951][23469] Updated weights for policy 1, policy_version 9580 (0.0007) -[2023-10-09 08:39:30,325][23469] Updated weights for policy 1, policy_version 9590 (0.0007) -[2023-10-09 08:39:30,700][23469] Updated weights for policy 1, policy_version 9600 (0.0009) -[2023-10-09 08:39:31,053][23468] Updated weights for policy 0, policy_version 9540 (0.0007) -[2023-10-09 08:39:31,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 19595264. Throughput: 0: 1784.1, 1: 1778.9. Samples: 4909006. Policy #0 lag: (min: 9.0, avg: 24.0, max: 41.0) -[2023-10-09 08:39:31,078][22500] Avg episode reward: [(0, '5.170'), (1, '5.210')] -[2023-10-09 08:39:31,427][23468] Updated weights for policy 0, policy_version 9550 (0.0009) -[2023-10-09 08:39:31,801][23468] Updated weights for policy 0, policy_version 9560 (0.0008) -[2023-10-09 08:39:34,304][23469] Updated weights for policy 1, policy_version 9610 (0.0007) -[2023-10-09 08:39:34,670][23469] Updated weights for policy 1, policy_version 9620 (0.0007) -[2023-10-09 08:39:35,043][23469] Updated weights for policy 1, policy_version 9630 (0.0009) -[2023-10-09 08:39:35,616][23468] Updated weights for policy 0, policy_version 9570 (0.0008) -[2023-10-09 08:39:35,986][23468] Updated weights for policy 0, policy_version 9580 (0.0010) -[2023-10-09 08:39:36,078][22500] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 19660800. Throughput: 0: 1782.4, 1: 1800.2. Samples: 4920428. Policy #0 lag: (min: 9.0, avg: 24.0, max: 41.0) -[2023-10-09 08:39:36,079][22500] Avg episode reward: [(0, '5.220'), (1, '5.520')] -[2023-10-09 08:39:36,365][23468] Updated weights for policy 0, policy_version 9590 (0.0007) -[2023-10-09 08:39:36,741][23468] Updated weights for policy 0, policy_version 9600 (0.0007) -[2023-10-09 08:39:38,796][23469] Updated weights for policy 1, policy_version 9640 (0.0007) -[2023-10-09 08:39:39,166][23469] Updated weights for policy 1, policy_version 9650 (0.0008) -[2023-10-09 08:39:39,540][23469] Updated weights for policy 1, policy_version 9660 (0.0007) -[2023-10-09 08:39:40,540][23468] Updated weights for policy 0, policy_version 9610 (0.0011) -[2023-10-09 08:39:40,907][23468] Updated weights for policy 0, policy_version 9620 (0.0010) -[2023-10-09 08:39:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.6, 300 sec: 14106.9). Total num frames: 19726336. Throughput: 0: 1782.9, 1: 1784.5. Samples: 4941364. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:39:41,078][22500] Avg episode reward: [(0, '5.320'), (1, '6.050')] -[2023-10-09 08:39:41,283][23468] Updated weights for policy 0, policy_version 9630 (0.0008) -[2023-10-09 08:39:43,374][23469] Updated weights for policy 1, policy_version 9670 (0.0009) -[2023-10-09 08:39:43,775][23469] Updated weights for policy 1, policy_version 9680 (0.0008) -[2023-10-09 08:39:44,142][23469] Updated weights for policy 1, policy_version 9690 (0.0008) -[2023-10-09 08:39:45,040][23468] Updated weights for policy 0, policy_version 9640 (0.0008) -[2023-10-09 08:39:45,418][23468] Updated weights for policy 0, policy_version 9650 (0.0007) -[2023-10-09 08:39:45,783][23468] Updated weights for policy 0, policy_version 9660 (0.0008) -[2023-10-09 08:39:46,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 19824640. Throughput: 0: 1802.2, 1: 1787.5. Samples: 4963024. Policy #0 lag: (min: 25.0, avg: 36.0, max: 57.0) -[2023-10-09 08:39:46,078][22500] Avg episode reward: [(0, '5.900'), (1, '6.150')] -[2023-10-09 08:39:46,087][23343] Saving new best policy, reward=6.150! -[2023-10-09 08:39:47,778][23469] Updated weights for policy 1, policy_version 9700 (0.0008) -[2023-10-09 08:39:48,149][23469] Updated weights for policy 1, policy_version 9710 (0.0010) -[2023-10-09 08:39:48,525][23469] Updated weights for policy 1, policy_version 9720 (0.0009) -[2023-10-09 08:39:49,551][23468] Updated weights for policy 0, policy_version 9670 (0.0008) -[2023-10-09 08:39:49,922][23468] Updated weights for policy 0, policy_version 9680 (0.0008) -[2023-10-09 08:39:50,286][23468] Updated weights for policy 0, policy_version 9690 (0.0008) -[2023-10-09 08:39:51,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 19890176. Throughput: 0: 1778.0, 1: 1789.2. Samples: 4973444. Policy #0 lag: (min: 25.0, avg: 36.0, max: 57.0) -[2023-10-09 08:39:51,079][22500] Avg episode reward: [(0, '5.940'), (1, '5.640')] -[2023-10-09 08:39:52,112][23469] Updated weights for policy 1, policy_version 9730 (0.0009) -[2023-10-09 08:39:52,473][23469] Updated weights for policy 1, policy_version 9740 (0.0010) -[2023-10-09 08:39:52,841][23469] Updated weights for policy 1, policy_version 9750 (0.0007) -[2023-10-09 08:39:53,209][23469] Updated weights for policy 1, policy_version 9760 (0.0007) -[2023-10-09 08:39:54,024][23468] Updated weights for policy 0, policy_version 9700 (0.0009) -[2023-10-09 08:39:54,397][23468] Updated weights for policy 0, policy_version 9710 (0.0007) -[2023-10-09 08:39:54,762][23468] Updated weights for policy 0, policy_version 9720 (0.0007) -[2023-10-09 08:39:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 19955712. Throughput: 0: 1801.9, 1: 1790.6. Samples: 4995550. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 08:39:56,078][22500] Avg episode reward: [(0, '6.380'), (1, '5.530')] -[2023-10-09 08:39:56,079][23265] Saving new best policy, reward=6.380! -[2023-10-09 08:39:56,914][23469] Updated weights for policy 1, policy_version 9770 (0.0010) -[2023-10-09 08:39:57,282][23469] Updated weights for policy 1, policy_version 9780 (0.0008) -[2023-10-09 08:39:57,650][23469] Updated weights for policy 1, policy_version 9790 (0.0007) -[2023-10-09 08:39:58,554][23468] Updated weights for policy 0, policy_version 9730 (0.0010) -[2023-10-09 08:39:58,933][23468] Updated weights for policy 0, policy_version 9740 (0.0007) -[2023-10-09 08:39:59,304][23468] Updated weights for policy 0, policy_version 9750 (0.0010) -[2023-10-09 08:39:59,671][23468] Updated weights for policy 0, policy_version 9760 (0.0007) -[2023-10-09 08:40:01,078][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 20021248. Throughput: 0: 1781.3, 1: 1794.7. Samples: 5017024. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 08:40:01,079][22500] Avg episode reward: [(0, '5.680'), (1, '5.220')] -[2023-10-09 08:40:01,494][23469] Updated weights for policy 1, policy_version 9800 (0.0009) -[2023-10-09 08:40:01,866][23469] Updated weights for policy 1, policy_version 9810 (0.0008) -[2023-10-09 08:40:02,234][23469] Updated weights for policy 1, policy_version 9820 (0.0010) -[2023-10-09 08:40:03,481][23468] Updated weights for policy 0, policy_version 9770 (0.0008) -[2023-10-09 08:40:03,857][23468] Updated weights for policy 0, policy_version 9780 (0.0008) -[2023-10-09 08:40:04,230][23468] Updated weights for policy 0, policy_version 9790 (0.0007) -[2023-10-09 08:40:06,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 20086784. Throughput: 0: 1803.2, 1: 1790.6. Samples: 5028012. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:40:06,079][22500] Avg episode reward: [(0, '5.690'), (1, '5.290')] -[2023-10-09 08:40:06,155][23469] Updated weights for policy 1, policy_version 9830 (0.0008) -[2023-10-09 08:40:06,524][23469] Updated weights for policy 1, policy_version 9840 (0.0007) -[2023-10-09 08:40:06,892][23469] Updated weights for policy 1, policy_version 9850 (0.0008) -[2023-10-09 08:40:08,025][23468] Updated weights for policy 0, policy_version 9800 (0.0009) -[2023-10-09 08:40:08,406][23468] Updated weights for policy 0, policy_version 9810 (0.0008) -[2023-10-09 08:40:08,785][23468] Updated weights for policy 0, policy_version 9820 (0.0007) -[2023-10-09 08:40:10,600][23469] Updated weights for policy 1, policy_version 9860 (0.0008) -[2023-10-09 08:40:10,974][23469] Updated weights for policy 1, policy_version 9870 (0.0011) -[2023-10-09 08:40:11,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 20152320. Throughput: 0: 1776.0, 1: 1796.8. Samples: 5048920. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:40:11,078][22500] Avg episode reward: [(0, '5.480'), (1, '5.040')] -[2023-10-09 08:40:11,339][23469] Updated weights for policy 1, policy_version 9880 (0.0007) -[2023-10-09 08:40:12,479][23468] Updated weights for policy 0, policy_version 9830 (0.0008) -[2023-10-09 08:40:12,851][23468] Updated weights for policy 0, policy_version 9840 (0.0008) -[2023-10-09 08:40:13,232][23468] Updated weights for policy 0, policy_version 9850 (0.0009) -[2023-10-09 08:40:15,090][23469] Updated weights for policy 1, policy_version 9890 (0.0009) -[2023-10-09 08:40:15,460][23469] Updated weights for policy 1, policy_version 9900 (0.0009) -[2023-10-09 08:40:15,831][23469] Updated weights for policy 1, policy_version 9910 (0.0007) -[2023-10-09 08:40:16,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 20217856. Throughput: 0: 1776.4, 1: 1808.7. Samples: 5070338. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 08:40:16,079][22500] Avg episode reward: [(0, '5.660'), (1, '5.110')] -[2023-10-09 08:40:16,089][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000009856_10092544.pth... -[2023-10-09 08:40:16,120][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000008192_8388608.pth -[2023-10-09 08:40:16,204][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000009920_10158080.pth... -[2023-10-09 08:40:16,208][23469] Updated weights for policy 1, policy_version 9920 (0.0007) -[2023-10-09 08:40:16,242][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000008224_8421376.pth -[2023-10-09 08:40:16,993][23468] Updated weights for policy 0, policy_version 9860 (0.0009) -[2023-10-09 08:40:17,360][23468] Updated weights for policy 0, policy_version 9870 (0.0010) -[2023-10-09 08:40:17,739][23468] Updated weights for policy 0, policy_version 9880 (0.0007) -[2023-10-09 08:40:19,907][23469] Updated weights for policy 1, policy_version 9930 (0.0009) -[2023-10-09 08:40:20,282][23469] Updated weights for policy 1, policy_version 9940 (0.0008) -[2023-10-09 08:40:20,642][23469] Updated weights for policy 1, policy_version 9950 (0.0009) -[2023-10-09 08:40:21,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 20316160. Throughput: 0: 1776.0, 1: 1796.9. Samples: 5081210. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 08:40:21,078][22500] Avg episode reward: [(0, '6.290'), (1, '5.240')] -[2023-10-09 08:40:21,635][23468] Updated weights for policy 0, policy_version 9890 (0.0008) -[2023-10-09 08:40:22,016][23468] Updated weights for policy 0, policy_version 9900 (0.0009) -[2023-10-09 08:40:22,394][23468] Updated weights for policy 0, policy_version 9910 (0.0010) -[2023-10-09 08:40:22,767][23468] Updated weights for policy 0, policy_version 9920 (0.0011) -[2023-10-09 08:40:24,508][23469] Updated weights for policy 1, policy_version 9960 (0.0008) -[2023-10-09 08:40:24,885][23469] Updated weights for policy 1, policy_version 9970 (0.0008) -[2023-10-09 08:40:25,261][23469] Updated weights for policy 1, policy_version 9980 (0.0009) -[2023-10-09 08:40:26,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 20381696. Throughput: 0: 1777.9, 1: 1811.1. Samples: 5102870. Policy #0 lag: (min: 30.0, avg: 53.3, max: 56.0) -[2023-10-09 08:40:26,079][22500] Avg episode reward: [(0, '5.810'), (1, '5.420')] -[2023-10-09 08:40:26,530][23468] Updated weights for policy 0, policy_version 9930 (0.0010) -[2023-10-09 08:40:26,905][23468] Updated weights for policy 0, policy_version 9940 (0.0011) -[2023-10-09 08:40:27,276][23468] Updated weights for policy 0, policy_version 9950 (0.0007) -[2023-10-09 08:40:29,100][23469] Updated weights for policy 1, policy_version 9990 (0.0007) -[2023-10-09 08:40:29,493][23469] Updated weights for policy 1, policy_version 10000 (0.0008) -[2023-10-09 08:40:29,866][23469] Updated weights for policy 1, policy_version 10010 (0.0007) -[2023-10-09 08:40:31,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 20447232. Throughput: 0: 1791.8, 1: 1790.9. Samples: 5124246. Policy #0 lag: (min: 30.0, avg: 53.3, max: 56.0) -[2023-10-09 08:40:31,078][22500] Avg episode reward: [(0, '5.690'), (1, '5.390')] -[2023-10-09 08:40:31,195][23468] Updated weights for policy 0, policy_version 9960 (0.0007) -[2023-10-09 08:40:31,571][23468] Updated weights for policy 0, policy_version 9970 (0.0007) -[2023-10-09 08:40:31,942][23468] Updated weights for policy 0, policy_version 9980 (0.0007) -[2023-10-09 08:40:33,422][23469] Updated weights for policy 1, policy_version 10020 (0.0009) -[2023-10-09 08:40:33,784][23469] Updated weights for policy 1, policy_version 10030 (0.0009) -[2023-10-09 08:40:34,148][23469] Updated weights for policy 1, policy_version 10040 (0.0009) -[2023-10-09 08:40:35,473][23468] Updated weights for policy 0, policy_version 9990 (0.0008) -[2023-10-09 08:40:35,839][23468] Updated weights for policy 0, policy_version 10000 (0.0010) -[2023-10-09 08:40:36,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 20512768. Throughput: 0: 1773.4, 1: 1814.5. Samples: 5134898. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-09 08:40:36,079][22500] Avg episode reward: [(0, '5.350'), (1, '5.370')] -[2023-10-09 08:40:36,212][23468] Updated weights for policy 0, policy_version 10010 (0.0010) -[2023-10-09 08:40:37,946][23469] Updated weights for policy 1, policy_version 10050 (0.0009) -[2023-10-09 08:40:38,316][23469] Updated weights for policy 1, policy_version 10060 (0.0007) -[2023-10-09 08:40:38,690][23469] Updated weights for policy 1, policy_version 10070 (0.0009) -[2023-10-09 08:40:39,063][23469] Updated weights for policy 1, policy_version 10080 (0.0009) -[2023-10-09 08:40:39,994][23468] Updated weights for policy 0, policy_version 10020 (0.0010) -[2023-10-09 08:40:40,365][23468] Updated weights for policy 0, policy_version 10030 (0.0009) -[2023-10-09 08:40:40,745][23468] Updated weights for policy 0, policy_version 10040 (0.0008) -[2023-10-09 08:40:41,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 20611072. Throughput: 0: 1782.0, 1: 1792.2. Samples: 5156388. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-09 08:40:41,078][22500] Avg episode reward: [(0, '5.680'), (1, '5.300')] -[2023-10-09 08:40:42,787][23469] Updated weights for policy 1, policy_version 10090 (0.0009) -[2023-10-09 08:40:43,159][23469] Updated weights for policy 1, policy_version 10100 (0.0009) -[2023-10-09 08:40:43,523][23469] Updated weights for policy 1, policy_version 10110 (0.0011) -[2023-10-09 08:40:44,661][23468] Updated weights for policy 0, policy_version 10050 (0.0007) -[2023-10-09 08:40:45,034][23468] Updated weights for policy 0, policy_version 10060 (0.0008) -[2023-10-09 08:40:45,394][23468] Updated weights for policy 0, policy_version 10070 (0.0009) -[2023-10-09 08:40:45,770][23468] Updated weights for policy 0, policy_version 10080 (0.0010) -[2023-10-09 08:40:46,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 20676608. Throughput: 0: 1780.4, 1: 1792.1. Samples: 5177786. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-09 08:40:46,078][22500] Avg episode reward: [(0, '5.510'), (1, '5.540')] -[2023-10-09 08:40:47,361][23469] Updated weights for policy 1, policy_version 10120 (0.0009) -[2023-10-09 08:40:47,725][23469] Updated weights for policy 1, policy_version 10130 (0.0008) -[2023-10-09 08:40:48,105][23469] Updated weights for policy 1, policy_version 10140 (0.0008) -[2023-10-09 08:40:49,627][23468] Updated weights for policy 0, policy_version 10090 (0.0007) -[2023-10-09 08:40:49,996][23468] Updated weights for policy 0, policy_version 10100 (0.0008) -[2023-10-09 08:40:50,373][23468] Updated weights for policy 0, policy_version 10110 (0.0009) -[2023-10-09 08:40:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 20742144. Throughput: 0: 1772.0, 1: 1788.9. Samples: 5188250. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-09 08:40:51,078][22500] Avg episode reward: [(0, '5.630'), (1, '5.580')] -[2023-10-09 08:40:51,811][23469] Updated weights for policy 1, policy_version 10150 (0.0008) -[2023-10-09 08:40:52,175][23469] Updated weights for policy 1, policy_version 10160 (0.0008) -[2023-10-09 08:40:52,552][23469] Updated weights for policy 1, policy_version 10170 (0.0007) -[2023-10-09 08:40:54,214][23468] Updated weights for policy 0, policy_version 10120 (0.0009) -[2023-10-09 08:40:54,581][23468] Updated weights for policy 0, policy_version 10130 (0.0007) -[2023-10-09 08:40:54,954][23468] Updated weights for policy 0, policy_version 10140 (0.0008) -[2023-10-09 08:40:56,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 20807680. Throughput: 0: 1790.0, 1: 1789.5. Samples: 5210000. Policy #0 lag: (min: 9.0, avg: 17.5, max: 41.0) -[2023-10-09 08:40:56,078][22500] Avg episode reward: [(0, '5.820'), (1, '6.000')] -[2023-10-09 08:40:56,353][23469] Updated weights for policy 1, policy_version 10180 (0.0009) -[2023-10-09 08:40:56,721][23469] Updated weights for policy 1, policy_version 10190 (0.0011) -[2023-10-09 08:40:57,092][23469] Updated weights for policy 1, policy_version 10200 (0.0011) -[2023-10-09 08:40:58,572][23468] Updated weights for policy 0, policy_version 10150 (0.0009) -[2023-10-09 08:40:58,939][23468] Updated weights for policy 0, policy_version 10160 (0.0007) -[2023-10-09 08:40:59,315][23468] Updated weights for policy 0, policy_version 10170 (0.0007) -[2023-10-09 08:41:00,801][23469] Updated weights for policy 1, policy_version 10210 (0.0009) -[2023-10-09 08:41:01,078][22500] Fps is (10 sec: 13106.6, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 20873216. Throughput: 0: 1770.4, 1: 1809.7. Samples: 5231444. Policy #0 lag: (min: 9.0, avg: 17.5, max: 41.0) -[2023-10-09 08:41:01,079][22500] Avg episode reward: [(0, '6.090'), (1, '5.880')] -[2023-10-09 08:41:01,176][23469] Updated weights for policy 1, policy_version 10220 (0.0009) -[2023-10-09 08:41:01,549][23469] Updated weights for policy 1, policy_version 10230 (0.0010) -[2023-10-09 08:41:01,918][23469] Updated weights for policy 1, policy_version 10240 (0.0008) -[2023-10-09 08:41:03,065][23468] Updated weights for policy 0, policy_version 10180 (0.0007) -[2023-10-09 08:41:03,442][23468] Updated weights for policy 0, policy_version 10190 (0.0008) -[2023-10-09 08:41:03,818][23468] Updated weights for policy 0, policy_version 10200 (0.0009) -[2023-10-09 08:41:05,617][23469] Updated weights for policy 1, policy_version 10250 (0.0009) -[2023-10-09 08:41:05,991][23469] Updated weights for policy 1, policy_version 10260 (0.0008) -[2023-10-09 08:41:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 20938752. Throughput: 0: 1790.5, 1: 1787.8. Samples: 5242232. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-09 08:41:06,078][22500] Avg episode reward: [(0, '5.920'), (1, '5.680')] -[2023-10-09 08:41:06,351][23469] Updated weights for policy 1, policy_version 10270 (0.0007) -[2023-10-09 08:41:07,552][23468] Updated weights for policy 0, policy_version 10210 (0.0011) -[2023-10-09 08:41:07,925][23468] Updated weights for policy 0, policy_version 10220 (0.0011) -[2023-10-09 08:41:08,296][23468] Updated weights for policy 0, policy_version 10230 (0.0010) -[2023-10-09 08:41:08,669][23468] Updated weights for policy 0, policy_version 10240 (0.0007) -[2023-10-09 08:41:10,076][23469] Updated weights for policy 1, policy_version 10280 (0.0010) -[2023-10-09 08:41:10,448][23469] Updated weights for policy 1, policy_version 10290 (0.0010) -[2023-10-09 08:41:10,830][23469] Updated weights for policy 1, policy_version 10300 (0.0010) -[2023-10-09 08:41:11,077][22500] Fps is (10 sec: 16384.6, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 21037056. Throughput: 0: 1768.8, 1: 1809.0. Samples: 5263872. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-09 08:41:11,078][22500] Avg episode reward: [(0, '5.770'), (1, '5.440')] -[2023-10-09 08:41:12,552][23468] Updated weights for policy 0, policy_version 10250 (0.0008) -[2023-10-09 08:41:12,924][23468] Updated weights for policy 0, policy_version 10260 (0.0008) -[2023-10-09 08:41:13,302][23468] Updated weights for policy 0, policy_version 10270 (0.0007) -[2023-10-09 08:41:14,560][23469] Updated weights for policy 1, policy_version 10310 (0.0010) -[2023-10-09 08:41:14,943][23469] Updated weights for policy 1, policy_version 10320 (0.0007) -[2023-10-09 08:41:15,317][23469] Updated weights for policy 1, policy_version 10330 (0.0007) -[2023-10-09 08:41:16,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 21102592. Throughput: 0: 1771.6, 1: 1795.6. Samples: 5284770. Policy #0 lag: (min: 10.0, avg: 13.0, max: 42.0) -[2023-10-09 08:41:16,078][22500] Avg episode reward: [(0, '5.650'), (1, '5.450')] -[2023-10-09 08:41:17,053][23468] Updated weights for policy 0, policy_version 10280 (0.0010) -[2023-10-09 08:41:17,428][23468] Updated weights for policy 0, policy_version 10290 (0.0007) -[2023-10-09 08:41:17,798][23468] Updated weights for policy 0, policy_version 10300 (0.0008) -[2023-10-09 08:41:19,152][23469] Updated weights for policy 1, policy_version 10340 (0.0008) -[2023-10-09 08:41:19,538][23469] Updated weights for policy 1, policy_version 10350 (0.0009) -[2023-10-09 08:41:19,911][23469] Updated weights for policy 1, policy_version 10360 (0.0009) -[2023-10-09 08:41:21,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 21168128. Throughput: 0: 1772.0, 1: 1805.6. Samples: 5295890. Policy #0 lag: (min: 10.0, avg: 13.0, max: 42.0) -[2023-10-09 08:41:21,079][22500] Avg episode reward: [(0, '5.610'), (1, '5.330')] -[2023-10-09 08:41:21,463][23468] Updated weights for policy 0, policy_version 10310 (0.0007) -[2023-10-09 08:41:21,838][23468] Updated weights for policy 0, policy_version 10320 (0.0007) -[2023-10-09 08:41:22,215][23468] Updated weights for policy 0, policy_version 10330 (0.0008) -[2023-10-09 08:41:23,506][23469] Updated weights for policy 1, policy_version 10370 (0.0008) -[2023-10-09 08:41:23,879][23469] Updated weights for policy 1, policy_version 10380 (0.0007) -[2023-10-09 08:41:24,244][23469] Updated weights for policy 1, policy_version 10390 (0.0007) -[2023-10-09 08:41:24,616][23469] Updated weights for policy 1, policy_version 10400 (0.0007) -[2023-10-09 08:41:26,070][23468] Updated weights for policy 0, policy_version 10340 (0.0008) -[2023-10-09 08:41:26,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 21233664. Throughput: 0: 1774.1, 1: 1792.8. Samples: 5316900. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:41:26,078][22500] Avg episode reward: [(0, '5.700'), (1, '5.660')] -[2023-10-09 08:41:26,448][23468] Updated weights for policy 0, policy_version 10350 (0.0009) -[2023-10-09 08:41:26,805][23468] Updated weights for policy 0, policy_version 10360 (0.0008) -[2023-10-09 08:41:28,273][23469] Updated weights for policy 1, policy_version 10410 (0.0010) -[2023-10-09 08:41:28,637][23469] Updated weights for policy 1, policy_version 10420 (0.0010) -[2023-10-09 08:41:29,013][23469] Updated weights for policy 1, policy_version 10430 (0.0007) -[2023-10-09 08:41:30,655][23468] Updated weights for policy 0, policy_version 10370 (0.0010) -[2023-10-09 08:41:31,019][23468] Updated weights for policy 0, policy_version 10380 (0.0009) -[2023-10-09 08:41:31,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 21299200. Throughput: 0: 1792.9, 1: 1797.3. Samples: 5339346. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:41:31,078][22500] Avg episode reward: [(0, '5.960'), (1, '5.880')] -[2023-10-09 08:41:31,395][23468] Updated weights for policy 0, policy_version 10390 (0.0010) -[2023-10-09 08:41:31,773][23468] Updated weights for policy 0, policy_version 10400 (0.0009) -[2023-10-09 08:41:32,689][23469] Updated weights for policy 1, policy_version 10440 (0.0008) -[2023-10-09 08:41:33,057][23469] Updated weights for policy 1, policy_version 10450 (0.0009) -[2023-10-09 08:41:33,423][23469] Updated weights for policy 1, policy_version 10460 (0.0008) -[2023-10-09 08:41:35,579][23468] Updated weights for policy 0, policy_version 10410 (0.0010) -[2023-10-09 08:41:35,956][23468] Updated weights for policy 0, policy_version 10420 (0.0010) -[2023-10-09 08:41:36,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 21364736. Throughput: 0: 1771.8, 1: 1799.2. Samples: 5348946. Policy #0 lag: (min: 26.0, avg: 28.0, max: 58.0) -[2023-10-09 08:41:36,079][22500] Avg episode reward: [(0, '5.820'), (1, '5.720')] -[2023-10-09 08:41:36,343][23468] Updated weights for policy 0, policy_version 10430 (0.0007) -[2023-10-09 08:41:37,034][23469] Updated weights for policy 1, policy_version 10470 (0.0007) -[2023-10-09 08:41:37,406][23469] Updated weights for policy 1, policy_version 10480 (0.0007) -[2023-10-09 08:41:37,769][23469] Updated weights for policy 1, policy_version 10490 (0.0007) -[2023-10-09 08:41:40,249][23468] Updated weights for policy 0, policy_version 10440 (0.0009) -[2023-10-09 08:41:40,623][23468] Updated weights for policy 0, policy_version 10450 (0.0007) -[2023-10-09 08:41:40,995][23468] Updated weights for policy 0, policy_version 10460 (0.0009) -[2023-10-09 08:41:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 21430272. Throughput: 0: 1784.8, 1: 1805.7. Samples: 5371576. Policy #0 lag: (min: 26.0, avg: 28.0, max: 58.0) -[2023-10-09 08:41:41,078][22500] Avg episode reward: [(0, '5.440'), (1, '5.880')] -[2023-10-09 08:41:41,575][23469] Updated weights for policy 1, policy_version 10500 (0.0008) -[2023-10-09 08:41:41,954][23469] Updated weights for policy 1, policy_version 10510 (0.0009) -[2023-10-09 08:41:42,322][23469] Updated weights for policy 1, policy_version 10520 (0.0008) -[2023-10-09 08:41:44,537][23468] Updated weights for policy 0, policy_version 10470 (0.0010) -[2023-10-09 08:41:44,907][23468] Updated weights for policy 0, policy_version 10480 (0.0007) -[2023-10-09 08:41:45,280][23468] Updated weights for policy 0, policy_version 10490 (0.0010) -[2023-10-09 08:41:45,970][23469] Updated weights for policy 1, policy_version 10530 (0.0009) -[2023-10-09 08:41:46,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 21528576. Throughput: 0: 1781.2, 1: 1809.3. Samples: 5393012. Policy #0 lag: (min: 20.0, avg: 22.0, max: 51.0) -[2023-10-09 08:41:46,078][22500] Avg episode reward: [(0, '5.100'), (1, '5.640')] -[2023-10-09 08:41:46,341][23469] Updated weights for policy 1, policy_version 10540 (0.0008) -[2023-10-09 08:41:46,711][23469] Updated weights for policy 1, policy_version 10550 (0.0010) -[2023-10-09 08:41:47,083][23469] Updated weights for policy 1, policy_version 10560 (0.0010) -[2023-10-09 08:41:49,052][23468] Updated weights for policy 0, policy_version 10500 (0.0008) -[2023-10-09 08:41:49,425][23468] Updated weights for policy 0, policy_version 10510 (0.0008) -[2023-10-09 08:41:49,800][23468] Updated weights for policy 0, policy_version 10520 (0.0007) -[2023-10-09 08:41:50,896][23469] Updated weights for policy 1, policy_version 10570 (0.0010) -[2023-10-09 08:41:51,078][22500] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 21594112. Throughput: 0: 1786.0, 1: 1804.6. Samples: 5403812. Policy #0 lag: (min: 11.0, avg: 14.1, max: 43.0) -[2023-10-09 08:41:51,079][22500] Avg episode reward: [(0, '5.440'), (1, '5.600')] -[2023-10-09 08:41:51,271][23469] Updated weights for policy 1, policy_version 10580 (0.0007) -[2023-10-09 08:41:51,639][23469] Updated weights for policy 1, policy_version 10590 (0.0007) -[2023-10-09 08:41:53,608][23468] Updated weights for policy 0, policy_version 10530 (0.0009) -[2023-10-09 08:41:53,995][23468] Updated weights for policy 0, policy_version 10540 (0.0011) -[2023-10-09 08:41:54,380][23468] Updated weights for policy 0, policy_version 10550 (0.0010) -[2023-10-09 08:41:54,745][23468] Updated weights for policy 0, policy_version 10560 (0.0008) -[2023-10-09 08:41:55,387][23469] Updated weights for policy 1, policy_version 10600 (0.0008) -[2023-10-09 08:41:55,752][23469] Updated weights for policy 1, policy_version 10610 (0.0009) -[2023-10-09 08:41:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 21659648. Throughput: 0: 1784.6, 1: 1802.7. Samples: 5425300. Policy #0 lag: (min: 11.0, avg: 14.1, max: 43.0) -[2023-10-09 08:41:56,078][22500] Avg episode reward: [(0, '5.980'), (1, '5.620')] -[2023-10-09 08:41:56,123][23469] Updated weights for policy 1, policy_version 10620 (0.0007) -[2023-10-09 08:41:58,525][23468] Updated weights for policy 0, policy_version 10570 (0.0008) -[2023-10-09 08:41:58,900][23468] Updated weights for policy 0, policy_version 10580 (0.0008) -[2023-10-09 08:41:59,274][23468] Updated weights for policy 0, policy_version 10590 (0.0009) -[2023-10-09 08:41:59,854][23469] Updated weights for policy 1, policy_version 10630 (0.0007) -[2023-10-09 08:42:00,224][23469] Updated weights for policy 1, policy_version 10640 (0.0010) -[2023-10-09 08:42:00,596][23469] Updated weights for policy 1, policy_version 10650 (0.0009) -[2023-10-09 08:42:01,078][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 21757952. Throughput: 0: 1772.3, 1: 1803.7. Samples: 5445694. Policy #0 lag: (min: 25.0, avg: 40.0, max: 57.0) -[2023-10-09 08:42:01,079][22500] Avg episode reward: [(0, '6.270'), (1, '5.720')] -[2023-10-09 08:42:03,008][23468] Updated weights for policy 0, policy_version 10600 (0.0008) -[2023-10-09 08:42:03,382][23468] Updated weights for policy 0, policy_version 10610 (0.0010) -[2023-10-09 08:42:03,763][23468] Updated weights for policy 0, policy_version 10620 (0.0009) -[2023-10-09 08:42:04,409][23469] Updated weights for policy 1, policy_version 10660 (0.0008) -[2023-10-09 08:42:04,777][23469] Updated weights for policy 1, policy_version 10670 (0.0007) -[2023-10-09 08:42:05,139][23469] Updated weights for policy 1, policy_version 10680 (0.0007) -[2023-10-09 08:42:06,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 21823488. Throughput: 0: 1788.8, 1: 1797.7. Samples: 5457282. Policy #0 lag: (min: 25.0, avg: 40.0, max: 57.0) -[2023-10-09 08:42:06,078][22500] Avg episode reward: [(0, '6.040'), (1, '5.800')] -[2023-10-09 08:42:07,534][23468] Updated weights for policy 0, policy_version 10630 (0.0011) -[2023-10-09 08:42:07,909][23468] Updated weights for policy 0, policy_version 10640 (0.0011) -[2023-10-09 08:42:08,288][23468] Updated weights for policy 0, policy_version 10650 (0.0011) -[2023-10-09 08:42:08,890][23469] Updated weights for policy 1, policy_version 10690 (0.0008) -[2023-10-09 08:42:09,257][23469] Updated weights for policy 1, policy_version 10700 (0.0010) -[2023-10-09 08:42:09,629][23469] Updated weights for policy 1, policy_version 10710 (0.0010) -[2023-10-09 08:42:09,995][23469] Updated weights for policy 1, policy_version 10720 (0.0011) -[2023-10-09 08:42:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 21889024. Throughput: 0: 1771.8, 1: 1801.2. Samples: 5477684. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 08:42:11,078][22500] Avg episode reward: [(0, '5.450'), (1, '5.790')] -[2023-10-09 08:42:11,999][23468] Updated weights for policy 0, policy_version 10660 (0.0010) -[2023-10-09 08:42:12,376][23468] Updated weights for policy 0, policy_version 10670 (0.0009) -[2023-10-09 08:42:12,752][23468] Updated weights for policy 0, policy_version 10680 (0.0009) -[2023-10-09 08:42:13,741][23469] Updated weights for policy 1, policy_version 10730 (0.0007) -[2023-10-09 08:42:14,109][23469] Updated weights for policy 1, policy_version 10740 (0.0007) -[2023-10-09 08:42:14,478][23469] Updated weights for policy 1, policy_version 10750 (0.0008) -[2023-10-09 08:42:16,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 21954560. Throughput: 0: 1777.4, 1: 1788.6. Samples: 5499816. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 08:42:16,078][22500] Avg episode reward: [(0, '5.870'), (1, '5.780')] -[2023-10-09 08:42:16,088][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000010752_11010048.pth... -[2023-10-09 08:42:16,088][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000010688_10944512.pth... -[2023-10-09 08:42:16,123][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000009024_9240576.pth -[2023-10-09 08:42:16,127][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000009056_9273344.pth -[2023-10-09 08:42:16,543][23468] Updated weights for policy 0, policy_version 10690 (0.0008) -[2023-10-09 08:42:16,913][23468] Updated weights for policy 0, policy_version 10700 (0.0009) -[2023-10-09 08:42:17,293][23468] Updated weights for policy 0, policy_version 10710 (0.0008) -[2023-10-09 08:42:17,655][23468] Updated weights for policy 0, policy_version 10720 (0.0007) -[2023-10-09 08:42:18,272][23469] Updated weights for policy 1, policy_version 10760 (0.0007) -[2023-10-09 08:42:18,632][23469] Updated weights for policy 1, policy_version 10770 (0.0010) -[2023-10-09 08:42:18,999][23469] Updated weights for policy 1, policy_version 10780 (0.0008) -[2023-10-09 08:42:21,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 22020096. Throughput: 0: 1779.5, 1: 1807.8. Samples: 5510374. Policy #0 lag: (min: 33.0, avg: 46.6, max: 48.0) -[2023-10-09 08:42:21,078][22500] Avg episode reward: [(0, '6.430'), (1, '5.560')] -[2023-10-09 08:42:21,503][23468] Updated weights for policy 0, policy_version 10730 (0.0008) -[2023-10-09 08:42:21,869][23468] Updated weights for policy 0, policy_version 10740 (0.0008) -[2023-10-09 08:42:22,248][23468] Updated weights for policy 0, policy_version 10750 (0.0009) -[2023-10-09 08:42:22,311][23265] Saving new best policy, reward=6.430! -[2023-10-09 08:42:22,660][23469] Updated weights for policy 1, policy_version 10790 (0.0007) -[2023-10-09 08:42:23,032][23469] Updated weights for policy 1, policy_version 10800 (0.0008) -[2023-10-09 08:42:23,404][23469] Updated weights for policy 1, policy_version 10810 (0.0009) -[2023-10-09 08:42:25,795][23468] Updated weights for policy 0, policy_version 10760 (0.0010) -[2023-10-09 08:42:26,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 22085632. Throughput: 0: 1784.8, 1: 1789.0. Samples: 5532400. Policy #0 lag: (min: 33.0, avg: 46.6, max: 48.0) -[2023-10-09 08:42:26,078][22500] Avg episode reward: [(0, '6.230'), (1, '5.470')] -[2023-10-09 08:42:26,171][23468] Updated weights for policy 0, policy_version 10770 (0.0009) -[2023-10-09 08:42:26,543][23468] Updated weights for policy 0, policy_version 10780 (0.0007) -[2023-10-09 08:42:27,241][23469] Updated weights for policy 1, policy_version 10820 (0.0007) -[2023-10-09 08:42:27,611][23469] Updated weights for policy 1, policy_version 10830 (0.0007) -[2023-10-09 08:42:27,975][23469] Updated weights for policy 1, policy_version 10840 (0.0008) -[2023-10-09 08:42:30,349][23468] Updated weights for policy 0, policy_version 10790 (0.0009) -[2023-10-09 08:42:30,717][23468] Updated weights for policy 0, policy_version 10800 (0.0010) -[2023-10-09 08:42:31,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 22151168. Throughput: 0: 1801.6, 1: 1788.3. Samples: 5554558. Policy #0 lag: (min: 5.0, avg: 5.3, max: 16.0) -[2023-10-09 08:42:31,078][22500] Avg episode reward: [(0, '5.870'), (1, '5.410')] -[2023-10-09 08:42:31,096][23468] Updated weights for policy 0, policy_version 10810 (0.0010) -[2023-10-09 08:42:31,719][23469] Updated weights for policy 1, policy_version 10850 (0.0009) -[2023-10-09 08:42:32,084][23469] Updated weights for policy 1, policy_version 10860 (0.0008) -[2023-10-09 08:42:32,450][23469] Updated weights for policy 1, policy_version 10870 (0.0010) -[2023-10-09 08:42:32,824][23469] Updated weights for policy 1, policy_version 10880 (0.0008) -[2023-10-09 08:42:34,938][23468] Updated weights for policy 0, policy_version 10820 (0.0010) -[2023-10-09 08:42:35,308][23468] Updated weights for policy 0, policy_version 10830 (0.0010) -[2023-10-09 08:42:35,689][23468] Updated weights for policy 0, policy_version 10840 (0.0010) -[2023-10-09 08:42:36,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 22249472. Throughput: 0: 1781.5, 1: 1790.1. Samples: 5564530. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 08:42:36,078][22500] Avg episode reward: [(0, '5.670'), (1, '5.290')] -[2023-10-09 08:42:36,565][23469] Updated weights for policy 1, policy_version 10890 (0.0007) -[2023-10-09 08:42:36,925][23469] Updated weights for policy 1, policy_version 10900 (0.0009) -[2023-10-09 08:42:37,293][23469] Updated weights for policy 1, policy_version 10910 (0.0010) -[2023-10-09 08:42:39,457][23468] Updated weights for policy 0, policy_version 10850 (0.0008) -[2023-10-09 08:42:39,831][23468] Updated weights for policy 0, policy_version 10860 (0.0008) -[2023-10-09 08:42:40,200][23468] Updated weights for policy 0, policy_version 10870 (0.0008) -[2023-10-09 08:42:40,574][23468] Updated weights for policy 0, policy_version 10880 (0.0009) -[2023-10-09 08:42:41,038][23469] Updated weights for policy 1, policy_version 10920 (0.0008) -[2023-10-09 08:42:41,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 22315008. Throughput: 0: 1802.2, 1: 1787.2. Samples: 5586820. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 08:42:41,078][22500] Avg episode reward: [(0, '5.730'), (1, '5.180')] -[2023-10-09 08:42:41,402][23469] Updated weights for policy 1, policy_version 10930 (0.0007) -[2023-10-09 08:42:41,780][23469] Updated weights for policy 1, policy_version 10940 (0.0007) -[2023-10-09 08:42:44,556][23468] Updated weights for policy 0, policy_version 10890 (0.0007) -[2023-10-09 08:42:44,929][23468] Updated weights for policy 0, policy_version 10900 (0.0009) -[2023-10-09 08:42:45,301][23468] Updated weights for policy 0, policy_version 10910 (0.0009) -[2023-10-09 08:42:45,740][23469] Updated weights for policy 1, policy_version 10950 (0.0008) -[2023-10-09 08:42:46,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 22380544. Throughput: 0: 1779.5, 1: 1811.6. Samples: 5607294. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 08:42:46,078][22500] Avg episode reward: [(0, '6.220'), (1, '5.310')] -[2023-10-09 08:42:46,134][23469] Updated weights for policy 1, policy_version 10960 (0.0010) -[2023-10-09 08:42:46,492][23469] Updated weights for policy 1, policy_version 10970 (0.0011) -[2023-10-09 08:42:49,008][23468] Updated weights for policy 0, policy_version 10920 (0.0008) -[2023-10-09 08:42:49,389][23468] Updated weights for policy 0, policy_version 10930 (0.0009) -[2023-10-09 08:42:49,771][23468] Updated weights for policy 0, policy_version 10940 (0.0008) -[2023-10-09 08:42:50,268][23469] Updated weights for policy 1, policy_version 10980 (0.0011) -[2023-10-09 08:42:50,636][23469] Updated weights for policy 1, policy_version 10990 (0.0011) -[2023-10-09 08:42:51,009][23469] Updated weights for policy 1, policy_version 11000 (0.0008) -[2023-10-09 08:42:51,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 22446080. Throughput: 0: 1795.5, 1: 1783.7. Samples: 5618346. Policy #0 lag: (min: 31.0, avg: 31.9, max: 52.0) -[2023-10-09 08:42:51,078][22500] Avg episode reward: [(0, '6.210'), (1, '5.610')] -[2023-10-09 08:42:53,643][23468] Updated weights for policy 0, policy_version 10950 (0.0008) -[2023-10-09 08:42:54,023][23468] Updated weights for policy 0, policy_version 10960 (0.0010) -[2023-10-09 08:42:54,399][23468] Updated weights for policy 0, policy_version 10970 (0.0010) -[2023-10-09 08:42:54,648][23469] Updated weights for policy 1, policy_version 11010 (0.0009) -[2023-10-09 08:42:55,024][23469] Updated weights for policy 1, policy_version 11020 (0.0009) -[2023-10-09 08:42:55,396][23469] Updated weights for policy 1, policy_version 11030 (0.0009) -[2023-10-09 08:42:55,765][23469] Updated weights for policy 1, policy_version 11040 (0.0010) -[2023-10-09 08:42:56,077][22500] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 22544384. Throughput: 0: 1782.8, 1: 1808.8. Samples: 5639306. Policy #0 lag: (min: 31.0, avg: 31.9, max: 52.0) -[2023-10-09 08:42:56,079][22500] Avg episode reward: [(0, '6.260'), (1, '5.560')] -[2023-10-09 08:42:58,148][23468] Updated weights for policy 0, policy_version 10980 (0.0007) -[2023-10-09 08:42:58,519][23468] Updated weights for policy 0, policy_version 10990 (0.0009) -[2023-10-09 08:42:58,893][23468] Updated weights for policy 0, policy_version 11000 (0.0008) -[2023-10-09 08:42:59,680][23469] Updated weights for policy 1, policy_version 11050 (0.0009) -[2023-10-09 08:43:00,051][23469] Updated weights for policy 1, policy_version 11060 (0.0010) -[2023-10-09 08:43:00,417][23469] Updated weights for policy 1, policy_version 11070 (0.0009) -[2023-10-09 08:43:01,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 22609920. Throughput: 0: 1773.5, 1: 1783.5. Samples: 5659884. Policy #0 lag: (min: 31.0, avg: 31.9, max: 52.0) -[2023-10-09 08:43:01,078][22500] Avg episode reward: [(0, '5.790'), (1, '5.340')] -[2023-10-09 08:43:02,609][23468] Updated weights for policy 0, policy_version 11010 (0.0007) -[2023-10-09 08:43:02,985][23468] Updated weights for policy 0, policy_version 11020 (0.0009) -[2023-10-09 08:43:03,363][23468] Updated weights for policy 0, policy_version 11030 (0.0007) -[2023-10-09 08:43:03,733][23468] Updated weights for policy 0, policy_version 11040 (0.0007) -[2023-10-09 08:43:04,187][23469] Updated weights for policy 1, policy_version 11080 (0.0008) -[2023-10-09 08:43:04,558][23469] Updated weights for policy 1, policy_version 11090 (0.0009) -[2023-10-09 08:43:04,929][23469] Updated weights for policy 1, policy_version 11100 (0.0009) -[2023-10-09 08:43:06,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 22675456. Throughput: 0: 1784.0, 1: 1800.0. Samples: 5671656. Policy #0 lag: (min: 26.0, avg: 26.2, max: 36.0) -[2023-10-09 08:43:06,078][22500] Avg episode reward: [(0, '5.760'), (1, '5.110')] -[2023-10-09 08:43:07,382][23468] Updated weights for policy 0, policy_version 11050 (0.0008) -[2023-10-09 08:43:07,755][23468] Updated weights for policy 0, policy_version 11060 (0.0007) -[2023-10-09 08:43:08,129][23468] Updated weights for policy 0, policy_version 11070 (0.0008) -[2023-10-09 08:43:08,594][23469] Updated weights for policy 1, policy_version 11110 (0.0009) -[2023-10-09 08:43:08,966][23469] Updated weights for policy 1, policy_version 11120 (0.0009) -[2023-10-09 08:43:09,335][23469] Updated weights for policy 1, policy_version 11130 (0.0008) -[2023-10-09 08:43:11,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 22740992. Throughput: 0: 1766.5, 1: 1781.3. Samples: 5692052. Policy #0 lag: (min: 26.0, avg: 26.2, max: 36.0) -[2023-10-09 08:43:11,079][22500] Avg episode reward: [(0, '5.570'), (1, '5.380')] -[2023-10-09 08:43:12,082][23468] Updated weights for policy 0, policy_version 11080 (0.0010) -[2023-10-09 08:43:12,456][23468] Updated weights for policy 0, policy_version 11090 (0.0008) -[2023-10-09 08:43:12,828][23468] Updated weights for policy 0, policy_version 11100 (0.0008) -[2023-10-09 08:43:12,985][23469] Updated weights for policy 1, policy_version 11140 (0.0008) -[2023-10-09 08:43:13,366][23469] Updated weights for policy 1, policy_version 11150 (0.0007) -[2023-10-09 08:43:13,736][23469] Updated weights for policy 1, policy_version 11160 (0.0008) -[2023-10-09 08:43:16,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 22806528. Throughput: 0: 1772.3, 1: 1783.9. Samples: 5714586. Policy #0 lag: (min: 26.0, avg: 26.2, max: 36.0) -[2023-10-09 08:43:16,079][22500] Avg episode reward: [(0, '5.730'), (1, '5.050')] -[2023-10-09 08:43:16,473][23468] Updated weights for policy 0, policy_version 11110 (0.0008) -[2023-10-09 08:43:16,856][23468] Updated weights for policy 0, policy_version 11120 (0.0009) -[2023-10-09 08:43:17,229][23468] Updated weights for policy 0, policy_version 11130 (0.0011) -[2023-10-09 08:43:17,553][23469] Updated weights for policy 1, policy_version 11170 (0.0008) -[2023-10-09 08:43:17,921][23469] Updated weights for policy 1, policy_version 11180 (0.0008) -[2023-10-09 08:43:18,288][23469] Updated weights for policy 1, policy_version 11190 (0.0010) -[2023-10-09 08:43:18,656][23469] Updated weights for policy 1, policy_version 11200 (0.0011) -[2023-10-09 08:43:21,078][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 22872064. Throughput: 0: 1766.1, 1: 1781.2. Samples: 5724158. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 08:43:21,079][22500] Avg episode reward: [(0, '5.820'), (1, '5.000')] -[2023-10-09 08:43:21,219][23468] Updated weights for policy 0, policy_version 11140 (0.0008) -[2023-10-09 08:43:21,592][23468] Updated weights for policy 0, policy_version 11150 (0.0008) -[2023-10-09 08:43:21,962][23468] Updated weights for policy 0, policy_version 11160 (0.0009) -[2023-10-09 08:43:22,493][23469] Updated weights for policy 1, policy_version 11210 (0.0009) -[2023-10-09 08:43:22,865][23469] Updated weights for policy 1, policy_version 11220 (0.0009) -[2023-10-09 08:43:23,237][23469] Updated weights for policy 1, policy_version 11230 (0.0008) -[2023-10-09 08:43:25,688][23468] Updated weights for policy 0, policy_version 11170 (0.0009) -[2023-10-09 08:43:26,052][23468] Updated weights for policy 0, policy_version 11180 (0.0009) -[2023-10-09 08:43:26,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 22937600. Throughput: 0: 1767.4, 1: 1776.6. Samples: 5746298. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 08:43:26,078][22500] Avg episode reward: [(0, '5.770'), (1, '5.150')] -[2023-10-09 08:43:26,425][23468] Updated weights for policy 0, policy_version 11190 (0.0007) -[2023-10-09 08:43:26,794][23468] Updated weights for policy 0, policy_version 11200 (0.0008) -[2023-10-09 08:43:27,006][23469] Updated weights for policy 1, policy_version 11240 (0.0007) -[2023-10-09 08:43:27,376][23469] Updated weights for policy 1, policy_version 11250 (0.0008) -[2023-10-09 08:43:27,740][23469] Updated weights for policy 1, policy_version 11260 (0.0010) -[2023-10-09 08:43:30,523][23468] Updated weights for policy 0, policy_version 11210 (0.0008) -[2023-10-09 08:43:30,894][23468] Updated weights for policy 0, policy_version 11220 (0.0009) -[2023-10-09 08:43:31,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 23003136. Throughput: 0: 1797.6, 1: 1786.9. Samples: 5768596. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 08:43:31,078][22500] Avg episode reward: [(0, '6.060'), (1, '5.450')] -[2023-10-09 08:43:31,269][23468] Updated weights for policy 0, policy_version 11230 (0.0010) -[2023-10-09 08:43:31,614][23469] Updated weights for policy 1, policy_version 11270 (0.0009) -[2023-10-09 08:43:31,997][23469] Updated weights for policy 1, policy_version 11280 (0.0010) -[2023-10-09 08:43:32,375][23469] Updated weights for policy 1, policy_version 11290 (0.0011) -[2023-10-09 08:43:35,028][23468] Updated weights for policy 0, policy_version 11240 (0.0008) -[2023-10-09 08:43:35,399][23468] Updated weights for policy 0, policy_version 11250 (0.0008) -[2023-10-09 08:43:35,775][23468] Updated weights for policy 0, policy_version 11260 (0.0010) -[2023-10-09 08:43:36,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 23101440. Throughput: 0: 1770.0, 1: 1780.0. Samples: 5778098. Policy #0 lag: (min: 17.0, avg: 33.9, max: 49.0) -[2023-10-09 08:43:36,078][22500] Avg episode reward: [(0, '5.930'), (1, '5.460')] -[2023-10-09 08:43:36,191][23469] Updated weights for policy 1, policy_version 11300 (0.0008) -[2023-10-09 08:43:36,568][23469] Updated weights for policy 1, policy_version 11310 (0.0008) -[2023-10-09 08:43:36,940][23469] Updated weights for policy 1, policy_version 11320 (0.0007) -[2023-10-09 08:43:39,386][23468] Updated weights for policy 0, policy_version 11270 (0.0009) -[2023-10-09 08:43:39,764][23468] Updated weights for policy 0, policy_version 11280 (0.0008) -[2023-10-09 08:43:40,140][23468] Updated weights for policy 0, policy_version 11290 (0.0007) -[2023-10-09 08:43:40,819][23469] Updated weights for policy 1, policy_version 11330 (0.0007) -[2023-10-09 08:43:41,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 23166976. Throughput: 0: 1796.1, 1: 1778.9. Samples: 5800182. Policy #0 lag: (min: 17.0, avg: 33.9, max: 49.0) -[2023-10-09 08:43:41,078][22500] Avg episode reward: [(0, '5.950'), (1, '5.570')] -[2023-10-09 08:43:41,195][23469] Updated weights for policy 1, policy_version 11340 (0.0007) -[2023-10-09 08:43:41,565][23469] Updated weights for policy 1, policy_version 11350 (0.0007) -[2023-10-09 08:43:41,924][23469] Updated weights for policy 1, policy_version 11360 (0.0007) -[2023-10-09 08:43:44,000][23468] Updated weights for policy 0, policy_version 11300 (0.0009) -[2023-10-09 08:43:44,369][23468] Updated weights for policy 0, policy_version 11310 (0.0007) -[2023-10-09 08:43:44,742][23468] Updated weights for policy 0, policy_version 11320 (0.0009) -[2023-10-09 08:43:45,648][23469] Updated weights for policy 1, policy_version 11370 (0.0008) -[2023-10-09 08:43:46,020][23469] Updated weights for policy 1, policy_version 11380 (0.0010) -[2023-10-09 08:43:46,078][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 23232512. Throughput: 0: 1772.9, 1: 1798.8. Samples: 5820610. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:43:46,079][22500] Avg episode reward: [(0, '5.510'), (1, '5.060')] -[2023-10-09 08:43:46,410][23469] Updated weights for policy 1, policy_version 11390 (0.0010) -[2023-10-09 08:43:48,547][23468] Updated weights for policy 0, policy_version 11330 (0.0010) -[2023-10-09 08:43:48,920][23468] Updated weights for policy 0, policy_version 11340 (0.0008) -[2023-10-09 08:43:49,299][23468] Updated weights for policy 0, policy_version 11350 (0.0008) -[2023-10-09 08:43:49,672][23468] Updated weights for policy 0, policy_version 11360 (0.0010) -[2023-10-09 08:43:50,089][23469] Updated weights for policy 1, policy_version 11400 (0.0009) -[2023-10-09 08:43:50,466][23469] Updated weights for policy 1, policy_version 11410 (0.0009) -[2023-10-09 08:43:50,835][23469] Updated weights for policy 1, policy_version 11420 (0.0008) -[2023-10-09 08:43:51,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 23330816. Throughput: 0: 1795.9, 1: 1775.2. Samples: 5832356. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:43:51,078][22500] Avg episode reward: [(0, '5.380'), (1, '5.380')] -[2023-10-09 08:43:53,448][23468] Updated weights for policy 0, policy_version 11370 (0.0009) -[2023-10-09 08:43:53,822][23468] Updated weights for policy 0, policy_version 11380 (0.0008) -[2023-10-09 08:43:54,184][23468] Updated weights for policy 0, policy_version 11390 (0.0009) -[2023-10-09 08:43:54,610][23469] Updated weights for policy 1, policy_version 11430 (0.0009) -[2023-10-09 08:43:54,985][23469] Updated weights for policy 1, policy_version 11440 (0.0010) -[2023-10-09 08:43:55,347][23469] Updated weights for policy 1, policy_version 11450 (0.0009) -[2023-10-09 08:43:56,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 23396352. Throughput: 0: 1774.0, 1: 1792.4. Samples: 5852540. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:43:56,078][22500] Avg episode reward: [(0, '5.850'), (1, '5.250')] -[2023-10-09 08:43:57,947][23468] Updated weights for policy 0, policy_version 11400 (0.0010) -[2023-10-09 08:43:58,324][23468] Updated weights for policy 0, policy_version 11410 (0.0009) -[2023-10-09 08:43:58,706][23468] Updated weights for policy 0, policy_version 11420 (0.0009) -[2023-10-09 08:43:59,199][23469] Updated weights for policy 1, policy_version 11460 (0.0010) -[2023-10-09 08:43:59,571][23469] Updated weights for policy 1, policy_version 11470 (0.0010) -[2023-10-09 08:43:59,940][23469] Updated weights for policy 1, policy_version 11480 (0.0009) -[2023-10-09 08:44:01,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 23461888. Throughput: 0: 1775.6, 1: 1762.5. Samples: 5873802. Policy #0 lag: (min: 24.0, avg: 46.6, max: 56.0) -[2023-10-09 08:44:01,079][22500] Avg episode reward: [(0, '5.630'), (1, '5.600')] -[2023-10-09 08:44:02,473][23468] Updated weights for policy 0, policy_version 11430 (0.0008) -[2023-10-09 08:44:02,848][23468] Updated weights for policy 0, policy_version 11440 (0.0007) -[2023-10-09 08:44:03,217][23468] Updated weights for policy 0, policy_version 11450 (0.0009) -[2023-10-09 08:44:03,687][23469] Updated weights for policy 1, policy_version 11490 (0.0009) -[2023-10-09 08:44:04,050][23469] Updated weights for policy 1, policy_version 11500 (0.0011) -[2023-10-09 08:44:04,425][23469] Updated weights for policy 1, policy_version 11510 (0.0011) -[2023-10-09 08:44:04,796][23469] Updated weights for policy 1, policy_version 11520 (0.0010) -[2023-10-09 08:44:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 23527424. Throughput: 0: 1781.1, 1: 1794.5. Samples: 5885058. Policy #0 lag: (min: 24.0, avg: 46.6, max: 56.0) -[2023-10-09 08:44:06,078][22500] Avg episode reward: [(0, '5.470'), (1, '5.250')] -[2023-10-09 08:44:07,093][23468] Updated weights for policy 0, policy_version 11460 (0.0009) -[2023-10-09 08:44:07,468][23468] Updated weights for policy 0, policy_version 11470 (0.0010) -[2023-10-09 08:44:07,850][23468] Updated weights for policy 0, policy_version 11480 (0.0007) -[2023-10-09 08:44:08,622][23469] Updated weights for policy 1, policy_version 11530 (0.0011) -[2023-10-09 08:44:08,993][23469] Updated weights for policy 1, policy_version 11540 (0.0007) -[2023-10-09 08:44:09,363][23469] Updated weights for policy 1, policy_version 11550 (0.0007) -[2023-10-09 08:44:11,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 23592960. Throughput: 0: 1774.6, 1: 1767.6. Samples: 5905696. Policy #0 lag: (min: 24.0, avg: 46.6, max: 56.0) -[2023-10-09 08:44:11,079][22500] Avg episode reward: [(0, '5.300'), (1, '5.730')] -[2023-10-09 08:44:11,612][23468] Updated weights for policy 0, policy_version 11490 (0.0009) -[2023-10-09 08:44:11,978][23468] Updated weights for policy 0, policy_version 11500 (0.0008) -[2023-10-09 08:44:12,354][23468] Updated weights for policy 0, policy_version 11510 (0.0008) -[2023-10-09 08:44:12,727][23468] Updated weights for policy 0, policy_version 11520 (0.0009) -[2023-10-09 08:44:13,211][23469] Updated weights for policy 1, policy_version 11560 (0.0011) -[2023-10-09 08:44:13,589][23469] Updated weights for policy 1, policy_version 11570 (0.0010) -[2023-10-09 08:44:13,960][23469] Updated weights for policy 1, policy_version 11580 (0.0010) -[2023-10-09 08:44:16,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 23658496. Throughput: 0: 1781.0, 1: 1764.4. Samples: 5928140. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-09 08:44:16,078][22500] Avg episode reward: [(0, '4.970'), (1, '5.570')] -[2023-10-09 08:44:16,088][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000011584_11862016.pth... -[2023-10-09 08:44:16,121][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000009920_10158080.pth -[2023-10-09 08:44:16,532][23468] Updated weights for policy 0, policy_version 11530 (0.0008) -[2023-10-09 08:44:16,902][23468] Updated weights for policy 0, policy_version 11540 (0.0008) -[2023-10-09 08:44:17,286][23468] Updated weights for policy 0, policy_version 11550 (0.0010) -[2023-10-09 08:44:17,358][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000011552_11829248.pth... -[2023-10-09 08:44:17,391][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000009856_10092544.pth -[2023-10-09 08:44:17,842][23469] Updated weights for policy 1, policy_version 11590 (0.0007) -[2023-10-09 08:44:18,225][23469] Updated weights for policy 1, policy_version 11600 (0.0009) -[2023-10-09 08:44:18,603][23469] Updated weights for policy 1, policy_version 11610 (0.0009) -[2023-10-09 08:44:21,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 23724032. Throughput: 0: 1779.2, 1: 1770.4. Samples: 5937830. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-09 08:44:21,078][22500] Avg episode reward: [(0, '5.740'), (1, '5.440')] -[2023-10-09 08:44:21,168][23468] Updated weights for policy 0, policy_version 11560 (0.0007) -[2023-10-09 08:44:21,532][23468] Updated weights for policy 0, policy_version 11570 (0.0010) -[2023-10-09 08:44:21,913][23468] Updated weights for policy 0, policy_version 11580 (0.0007) -[2023-10-09 08:44:22,238][23469] Updated weights for policy 1, policy_version 11620 (0.0008) -[2023-10-09 08:44:22,605][23469] Updated weights for policy 1, policy_version 11630 (0.0008) -[2023-10-09 08:44:22,966][23469] Updated weights for policy 1, policy_version 11640 (0.0008) -[2023-10-09 08:44:25,469][23468] Updated weights for policy 0, policy_version 11590 (0.0007) -[2023-10-09 08:44:25,849][23468] Updated weights for policy 0, policy_version 11600 (0.0008) -[2023-10-09 08:44:26,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 23789568. Throughput: 0: 1786.0, 1: 1768.0. Samples: 5960110. Policy #0 lag: (min: 31.0, avg: 41.7, max: 63.0) -[2023-10-09 08:44:26,078][22500] Avg episode reward: [(0, '6.060'), (1, '5.240')] -[2023-10-09 08:44:26,210][23468] Updated weights for policy 0, policy_version 11610 (0.0009) -[2023-10-09 08:44:26,842][23469] Updated weights for policy 1, policy_version 11650 (0.0009) -[2023-10-09 08:44:27,204][23469] Updated weights for policy 1, policy_version 11660 (0.0008) -[2023-10-09 08:44:27,582][23469] Updated weights for policy 1, policy_version 11670 (0.0009) -[2023-10-09 08:44:27,949][23469] Updated weights for policy 1, policy_version 11680 (0.0008) -[2023-10-09 08:44:30,049][23468] Updated weights for policy 0, policy_version 11620 (0.0008) -[2023-10-09 08:44:30,416][23468] Updated weights for policy 0, policy_version 11630 (0.0009) -[2023-10-09 08:44:30,788][23468] Updated weights for policy 0, policy_version 11640 (0.0010) -[2023-10-09 08:44:31,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 23855104. Throughput: 0: 1801.3, 1: 1776.8. Samples: 5981626. Policy #0 lag: (min: 31.0, avg: 41.7, max: 63.0) -[2023-10-09 08:44:31,078][22500] Avg episode reward: [(0, '5.870'), (1, '5.320')] -[2023-10-09 08:44:31,750][23469] Updated weights for policy 1, policy_version 11690 (0.0007) -[2023-10-09 08:44:32,119][23469] Updated weights for policy 1, policy_version 11700 (0.0008) -[2023-10-09 08:44:32,489][23469] Updated weights for policy 1, policy_version 11710 (0.0007) -[2023-10-09 08:44:34,481][23468] Updated weights for policy 0, policy_version 11650 (0.0010) -[2023-10-09 08:44:34,845][23468] Updated weights for policy 0, policy_version 11660 (0.0009) -[2023-10-09 08:44:35,223][23468] Updated weights for policy 0, policy_version 11670 (0.0011) -[2023-10-09 08:44:35,598][23468] Updated weights for policy 0, policy_version 11680 (0.0007) -[2023-10-09 08:44:36,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 23953408. Throughput: 0: 1779.8, 1: 1764.1. Samples: 5991830. Policy #0 lag: (min: 31.0, avg: 39.9, max: 63.0) -[2023-10-09 08:44:36,078][22500] Avg episode reward: [(0, '5.510'), (1, '5.440')] -[2023-10-09 08:44:36,197][23469] Updated weights for policy 1, policy_version 11720 (0.0007) -[2023-10-09 08:44:36,572][23469] Updated weights for policy 1, policy_version 11730 (0.0007) -[2023-10-09 08:44:36,934][23469] Updated weights for policy 1, policy_version 11740 (0.0007) -[2023-10-09 08:44:39,279][23468] Updated weights for policy 0, policy_version 11690 (0.0009) -[2023-10-09 08:44:39,658][23468] Updated weights for policy 0, policy_version 11700 (0.0008) -[2023-10-09 08:44:40,035][23468] Updated weights for policy 0, policy_version 11710 (0.0008) -[2023-10-09 08:44:40,790][23469] Updated weights for policy 1, policy_version 11750 (0.0008) -[2023-10-09 08:44:41,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 24018944. Throughput: 0: 1805.6, 1: 1781.7. Samples: 6013966. Policy #0 lag: (min: 31.0, avg: 39.9, max: 63.0) -[2023-10-09 08:44:41,078][22500] Avg episode reward: [(0, '5.480'), (1, '5.650')] -[2023-10-09 08:44:41,154][23469] Updated weights for policy 1, policy_version 11760 (0.0009) -[2023-10-09 08:44:41,530][23469] Updated weights for policy 1, policy_version 11770 (0.0008) -[2023-10-09 08:44:43,755][23468] Updated weights for policy 0, policy_version 11720 (0.0009) -[2023-10-09 08:44:44,126][23468] Updated weights for policy 0, policy_version 11730 (0.0011) -[2023-10-09 08:44:44,513][23468] Updated weights for policy 0, policy_version 11740 (0.0011) -[2023-10-09 08:44:45,232][23469] Updated weights for policy 1, policy_version 11780 (0.0009) -[2023-10-09 08:44:45,604][23469] Updated weights for policy 1, policy_version 11790 (0.0010) -[2023-10-09 08:44:45,979][23469] Updated weights for policy 1, policy_version 11800 (0.0008) -[2023-10-09 08:44:46,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 24084480. Throughput: 0: 1780.7, 1: 1792.7. Samples: 6034602. Policy #0 lag: (min: 31.0, avg: 39.9, max: 63.0) -[2023-10-09 08:44:46,078][22500] Avg episode reward: [(0, '5.620'), (1, '5.840')] -[2023-10-09 08:44:48,243][23468] Updated weights for policy 0, policy_version 11750 (0.0010) -[2023-10-09 08:44:48,614][23468] Updated weights for policy 0, policy_version 11760 (0.0007) -[2023-10-09 08:44:48,992][23468] Updated weights for policy 0, policy_version 11770 (0.0009) -[2023-10-09 08:44:49,618][23469] Updated weights for policy 1, policy_version 11810 (0.0007) -[2023-10-09 08:44:49,984][23469] Updated weights for policy 1, policy_version 11820 (0.0009) -[2023-10-09 08:44:50,361][23469] Updated weights for policy 1, policy_version 11830 (0.0007) -[2023-10-09 08:44:50,725][23469] Updated weights for policy 1, policy_version 11840 (0.0008) -[2023-10-09 08:44:51,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 24182784. Throughput: 0: 1800.3, 1: 1781.5. Samples: 6046240. Policy #0 lag: (min: 9.0, avg: 20.4, max: 41.0) -[2023-10-09 08:44:51,078][22500] Avg episode reward: [(0, '5.970'), (1, '5.460')] -[2023-10-09 08:44:52,789][23468] Updated weights for policy 0, policy_version 11780 (0.0009) -[2023-10-09 08:44:53,171][23468] Updated weights for policy 0, policy_version 11790 (0.0008) -[2023-10-09 08:44:53,542][23468] Updated weights for policy 0, policy_version 11800 (0.0008) -[2023-10-09 08:44:54,436][23469] Updated weights for policy 1, policy_version 11850 (0.0009) -[2023-10-09 08:44:54,802][23469] Updated weights for policy 1, policy_version 11860 (0.0010) -[2023-10-09 08:44:55,176][23469] Updated weights for policy 1, policy_version 11870 (0.0009) -[2023-10-09 08:44:56,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 24248320. Throughput: 0: 1782.3, 1: 1797.6. Samples: 6066790. Policy #0 lag: (min: 9.0, avg: 20.4, max: 41.0) -[2023-10-09 08:44:56,079][22500] Avg episode reward: [(0, '5.650'), (1, '5.180')] -[2023-10-09 08:44:57,268][23468] Updated weights for policy 0, policy_version 11810 (0.0007) -[2023-10-09 08:44:57,644][23468] Updated weights for policy 0, policy_version 11820 (0.0008) -[2023-10-09 08:44:58,012][23468] Updated weights for policy 0, policy_version 11830 (0.0007) -[2023-10-09 08:44:58,393][23468] Updated weights for policy 0, policy_version 11840 (0.0008) -[2023-10-09 08:44:58,984][23469] Updated weights for policy 1, policy_version 11880 (0.0010) -[2023-10-09 08:44:59,352][23469] Updated weights for policy 1, policy_version 11890 (0.0008) -[2023-10-09 08:44:59,718][23469] Updated weights for policy 1, policy_version 11900 (0.0009) -[2023-10-09 08:45:01,078][22500] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 24313856. Throughput: 0: 1783.8, 1: 1780.5. Samples: 6088536. Policy #0 lag: (min: 9.0, avg: 20.4, max: 41.0) -[2023-10-09 08:45:01,079][22500] Avg episode reward: [(0, '6.140'), (1, '5.260')] -[2023-10-09 08:45:02,250][23468] Updated weights for policy 0, policy_version 11850 (0.0007) -[2023-10-09 08:45:02,631][23468] Updated weights for policy 0, policy_version 11860 (0.0008) -[2023-10-09 08:45:03,009][23468] Updated weights for policy 0, policy_version 11870 (0.0008) -[2023-10-09 08:45:03,673][23469] Updated weights for policy 1, policy_version 11910 (0.0008) -[2023-10-09 08:45:04,062][23469] Updated weights for policy 1, policy_version 11920 (0.0007) -[2023-10-09 08:45:04,437][23469] Updated weights for policy 1, policy_version 11930 (0.0007) -[2023-10-09 08:45:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 24379392. Throughput: 0: 1784.5, 1: 1802.4. Samples: 6099240. Policy #0 lag: (min: 26.0, avg: 29.2, max: 58.0) -[2023-10-09 08:45:06,078][22500] Avg episode reward: [(0, '6.360'), (1, '5.610')] -[2023-10-09 08:45:06,954][23468] Updated weights for policy 0, policy_version 11880 (0.0007) -[2023-10-09 08:45:07,340][23468] Updated weights for policy 0, policy_version 11890 (0.0009) -[2023-10-09 08:45:07,724][23468] Updated weights for policy 0, policy_version 11900 (0.0009) -[2023-10-09 08:45:07,976][23469] Updated weights for policy 1, policy_version 11940 (0.0008) -[2023-10-09 08:45:08,351][23469] Updated weights for policy 1, policy_version 11950 (0.0007) -[2023-10-09 08:45:08,712][23469] Updated weights for policy 1, policy_version 11960 (0.0007) -[2023-10-09 08:45:11,077][22500] Fps is (10 sec: 13107.8, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 24444928. Throughput: 0: 1775.7, 1: 1787.1. Samples: 6120436. Policy #0 lag: (min: 26.0, avg: 29.2, max: 58.0) -[2023-10-09 08:45:11,078][22500] Avg episode reward: [(0, '6.800'), (1, '5.840')] -[2023-10-09 08:45:11,078][23265] Saving new best policy, reward=6.800! -[2023-10-09 08:45:11,496][23468] Updated weights for policy 0, policy_version 11910 (0.0009) -[2023-10-09 08:45:11,865][23468] Updated weights for policy 0, policy_version 11920 (0.0009) -[2023-10-09 08:45:12,245][23468] Updated weights for policy 0, policy_version 11930 (0.0008) -[2023-10-09 08:45:12,479][23469] Updated weights for policy 1, policy_version 11970 (0.0008) -[2023-10-09 08:45:12,857][23469] Updated weights for policy 1, policy_version 11980 (0.0011) -[2023-10-09 08:45:13,220][23469] Updated weights for policy 1, policy_version 11990 (0.0011) -[2023-10-09 08:45:13,592][23469] Updated weights for policy 1, policy_version 12000 (0.0010) -[2023-10-09 08:45:16,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 24510464. Throughput: 0: 1788.2, 1: 1786.2. Samples: 6142472. Policy #0 lag: (min: 26.0, avg: 29.2, max: 58.0) -[2023-10-09 08:45:16,079][22500] Avg episode reward: [(0, '6.940'), (1, '5.810')] -[2023-10-09 08:45:16,124][23468] Updated weights for policy 0, policy_version 11940 (0.0008) -[2023-10-09 08:45:16,498][23468] Updated weights for policy 0, policy_version 11950 (0.0008) -[2023-10-09 08:45:16,875][23468] Updated weights for policy 0, policy_version 11960 (0.0011) -[2023-10-09 08:45:17,172][23265] Saving new best policy, reward=6.940! -[2023-10-09 08:45:17,311][23469] Updated weights for policy 1, policy_version 12010 (0.0010) -[2023-10-09 08:45:17,682][23469] Updated weights for policy 1, policy_version 12020 (0.0010) -[2023-10-09 08:45:18,046][23469] Updated weights for policy 1, policy_version 12030 (0.0010) -[2023-10-09 08:45:20,322][23468] Updated weights for policy 0, policy_version 11970 (0.0007) -[2023-10-09 08:45:20,703][23468] Updated weights for policy 0, policy_version 11980 (0.0008) -[2023-10-09 08:45:21,066][23468] Updated weights for policy 0, policy_version 11990 (0.0008) -[2023-10-09 08:45:21,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 24576000. Throughput: 0: 1776.3, 1: 1786.7. Samples: 6152164. Policy #0 lag: (min: 27.0, avg: 35.5, max: 59.0) -[2023-10-09 08:45:21,078][22500] Avg episode reward: [(0, '6.440'), (1, '5.560')] -[2023-10-09 08:45:21,443][23468] Updated weights for policy 0, policy_version 12000 (0.0008) -[2023-10-09 08:45:21,940][23469] Updated weights for policy 1, policy_version 12040 (0.0008) -[2023-10-09 08:45:22,310][23469] Updated weights for policy 1, policy_version 12050 (0.0007) -[2023-10-09 08:45:22,676][23469] Updated weights for policy 1, policy_version 12060 (0.0007) -[2023-10-09 08:45:25,342][23468] Updated weights for policy 0, policy_version 12010 (0.0007) -[2023-10-09 08:45:25,721][23468] Updated weights for policy 0, policy_version 12020 (0.0009) -[2023-10-09 08:45:26,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 24641536. Throughput: 0: 1787.6, 1: 1779.2. Samples: 6174472. Policy #0 lag: (min: 27.0, avg: 35.5, max: 59.0) -[2023-10-09 08:45:26,078][22500] Avg episode reward: [(0, '5.990'), (1, '5.380')] -[2023-10-09 08:45:26,088][23468] Updated weights for policy 0, policy_version 12030 (0.0007) -[2023-10-09 08:45:26,346][23469] Updated weights for policy 1, policy_version 12070 (0.0008) -[2023-10-09 08:45:26,716][23469] Updated weights for policy 1, policy_version 12080 (0.0009) -[2023-10-09 08:45:27,089][23469] Updated weights for policy 1, policy_version 12090 (0.0009) -[2023-10-09 08:45:29,888][23468] Updated weights for policy 0, policy_version 12040 (0.0010) -[2023-10-09 08:45:30,269][23468] Updated weights for policy 0, policy_version 12050 (0.0008) -[2023-10-09 08:45:30,643][23468] Updated weights for policy 0, policy_version 12060 (0.0010) -[2023-10-09 08:45:30,787][23469] Updated weights for policy 1, policy_version 12100 (0.0008) -[2023-10-09 08:45:31,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 24739840. Throughput: 0: 1791.2, 1: 1794.5. Samples: 6195956. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 08:45:31,078][22500] Avg episode reward: [(0, '5.190'), (1, '5.560')] -[2023-10-09 08:45:31,152][23469] Updated weights for policy 1, policy_version 12110 (0.0010) -[2023-10-09 08:45:31,532][23469] Updated weights for policy 1, policy_version 12120 (0.0008) -[2023-10-09 08:45:34,232][23468] Updated weights for policy 0, policy_version 12070 (0.0009) -[2023-10-09 08:45:34,607][23468] Updated weights for policy 0, policy_version 12080 (0.0009) -[2023-10-09 08:45:34,978][23468] Updated weights for policy 0, policy_version 12090 (0.0008) -[2023-10-09 08:45:35,297][23469] Updated weights for policy 1, policy_version 12130 (0.0007) -[2023-10-09 08:45:35,678][23469] Updated weights for policy 1, policy_version 12140 (0.0010) -[2023-10-09 08:45:36,052][23469] Updated weights for policy 1, policy_version 12150 (0.0009) -[2023-10-09 08:45:36,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 24805376. Throughput: 0: 1792.4, 1: 1778.7. Samples: 6206936. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 08:45:36,078][22500] Avg episode reward: [(0, '5.540'), (1, '5.580')] -[2023-10-09 08:45:36,427][23469] Updated weights for policy 1, policy_version 12160 (0.0008) -[2023-10-09 08:45:38,688][23468] Updated weights for policy 0, policy_version 12100 (0.0007) -[2023-10-09 08:45:39,061][23468] Updated weights for policy 0, policy_version 12110 (0.0007) -[2023-10-09 08:45:39,430][23468] Updated weights for policy 0, policy_version 12120 (0.0009) -[2023-10-09 08:45:40,118][23469] Updated weights for policy 1, policy_version 12170 (0.0010) -[2023-10-09 08:45:40,480][23469] Updated weights for policy 1, policy_version 12180 (0.0011) -[2023-10-09 08:45:40,848][23469] Updated weights for policy 1, policy_version 12190 (0.0009) -[2023-10-09 08:45:41,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 24903680. Throughput: 0: 1800.1, 1: 1798.9. Samples: 6228746. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 08:45:41,078][22500] Avg episode reward: [(0, '5.580'), (1, '5.760')] -[2023-10-09 08:45:43,332][23468] Updated weights for policy 0, policy_version 12130 (0.0010) -[2023-10-09 08:45:43,704][23468] Updated weights for policy 0, policy_version 12140 (0.0007) -[2023-10-09 08:45:44,082][23468] Updated weights for policy 0, policy_version 12150 (0.0009) -[2023-10-09 08:45:44,447][23468] Updated weights for policy 0, policy_version 12160 (0.0009) -[2023-10-09 08:45:44,544][23469] Updated weights for policy 1, policy_version 12200 (0.0008) -[2023-10-09 08:45:44,923][23469] Updated weights for policy 1, policy_version 12210 (0.0010) -[2023-10-09 08:45:45,286][23469] Updated weights for policy 1, policy_version 12220 (0.0011) -[2023-10-09 08:45:46,078][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 24969216. Throughput: 0: 1777.4, 1: 1784.8. Samples: 6248832. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 08:45:46,079][22500] Avg episode reward: [(0, '6.390'), (1, '5.460')] -[2023-10-09 08:45:47,956][23468] Updated weights for policy 0, policy_version 12170 (0.0008) -[2023-10-09 08:45:48,338][23468] Updated weights for policy 0, policy_version 12180 (0.0009) -[2023-10-09 08:45:48,709][23468] Updated weights for policy 0, policy_version 12190 (0.0007) -[2023-10-09 08:45:49,228][23469] Updated weights for policy 1, policy_version 12230 (0.0010) -[2023-10-09 08:45:49,611][23469] Updated weights for policy 1, policy_version 12240 (0.0008) -[2023-10-09 08:45:49,986][23469] Updated weights for policy 1, policy_version 12250 (0.0007) -[2023-10-09 08:45:51,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 25034752. Throughput: 0: 1795.8, 1: 1800.3. Samples: 6261064. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 08:45:51,079][22500] Avg episode reward: [(0, '6.110'), (1, '5.610')] -[2023-10-09 08:45:52,509][23468] Updated weights for policy 0, policy_version 12200 (0.0008) -[2023-10-09 08:45:52,879][23468] Updated weights for policy 0, policy_version 12210 (0.0008) -[2023-10-09 08:45:53,259][23468] Updated weights for policy 0, policy_version 12220 (0.0008) -[2023-10-09 08:45:53,573][23469] Updated weights for policy 1, policy_version 12260 (0.0008) -[2023-10-09 08:45:53,943][23469] Updated weights for policy 1, policy_version 12270 (0.0011) -[2023-10-09 08:45:54,312][23469] Updated weights for policy 1, policy_version 12280 (0.0009) -[2023-10-09 08:45:56,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 25100288. Throughput: 0: 1785.9, 1: 1786.8. Samples: 6281206. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 08:45:56,078][22500] Avg episode reward: [(0, '6.110'), (1, '5.180')] -[2023-10-09 08:45:57,062][23468] Updated weights for policy 0, policy_version 12230 (0.0007) -[2023-10-09 08:45:57,439][23468] Updated weights for policy 0, policy_version 12240 (0.0007) -[2023-10-09 08:45:57,821][23468] Updated weights for policy 0, policy_version 12250 (0.0011) -[2023-10-09 08:45:58,108][23469] Updated weights for policy 1, policy_version 12290 (0.0009) -[2023-10-09 08:45:58,482][23469] Updated weights for policy 1, policy_version 12300 (0.0009) -[2023-10-09 08:45:58,858][23469] Updated weights for policy 1, policy_version 12310 (0.0011) -[2023-10-09 08:45:59,230][23469] Updated weights for policy 1, policy_version 12320 (0.0009) -[2023-10-09 08:46:01,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.6, 300 sec: 14329.1). Total num frames: 25165824. Throughput: 0: 1788.6, 1: 1793.9. Samples: 6303686. Policy #0 lag: (min: 8.0, avg: 33.9, max: 40.0) -[2023-10-09 08:46:01,078][22500] Avg episode reward: [(0, '5.750'), (1, '5.440')] -[2023-10-09 08:46:01,505][23468] Updated weights for policy 0, policy_version 12260 (0.0009) -[2023-10-09 08:46:01,886][23468] Updated weights for policy 0, policy_version 12270 (0.0008) -[2023-10-09 08:46:02,261][23468] Updated weights for policy 0, policy_version 12280 (0.0009) -[2023-10-09 08:46:02,899][23469] Updated weights for policy 1, policy_version 12330 (0.0007) -[2023-10-09 08:46:03,271][23469] Updated weights for policy 1, policy_version 12340 (0.0007) -[2023-10-09 08:46:03,645][23469] Updated weights for policy 1, policy_version 12350 (0.0007) -[2023-10-09 08:46:06,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 25231360. Throughput: 0: 1785.6, 1: 1794.2. Samples: 6313254. Policy #0 lag: (min: 8.0, avg: 33.9, max: 40.0) -[2023-10-09 08:46:06,078][22500] Avg episode reward: [(0, '5.760'), (1, '5.410')] -[2023-10-09 08:46:06,102][23468] Updated weights for policy 0, policy_version 12290 (0.0009) -[2023-10-09 08:46:06,472][23468] Updated weights for policy 0, policy_version 12300 (0.0007) -[2023-10-09 08:46:06,846][23468] Updated weights for policy 0, policy_version 12310 (0.0010) -[2023-10-09 08:46:07,216][23468] Updated weights for policy 0, policy_version 12320 (0.0010) -[2023-10-09 08:46:07,408][23469] Updated weights for policy 1, policy_version 12360 (0.0008) -[2023-10-09 08:46:07,768][23469] Updated weights for policy 1, policy_version 12370 (0.0010) -[2023-10-09 08:46:08,138][23469] Updated weights for policy 1, policy_version 12380 (0.0011) -[2023-10-09 08:46:11,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 25296896. Throughput: 0: 1766.1, 1: 1776.0. Samples: 6333870. Policy #0 lag: (min: 8.0, avg: 33.9, max: 40.0) -[2023-10-09 08:46:11,078][22500] Avg episode reward: [(0, '5.900'), (1, '5.660')] -[2023-10-09 08:46:11,723][23468] Updated weights for policy 0, policy_version 12330 (0.0010) -[2023-10-09 08:46:12,162][23468] Updated weights for policy 0, policy_version 12342 (0.0010) -[2023-10-09 08:46:12,534][23468] Updated weights for policy 0, policy_version 12352 (0.0011) -[2023-10-09 08:46:12,815][23469] Updated weights for policy 1, policy_version 12391 (0.0010) -[2023-10-09 08:46:13,191][23469] Updated weights for policy 1, policy_version 12401 (0.0010) -[2023-10-09 08:46:13,554][23469] Updated weights for policy 1, policy_version 12411 (0.0011) -[2023-10-09 08:46:16,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 25362432. Throughput: 0: 1743.0, 1: 1731.3. Samples: 6352302. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:46:16,078][22500] Avg episode reward: [(0, '5.700'), (1, '5.680')] -[2023-10-09 08:46:16,087][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000012416_12713984.pth... -[2023-10-09 08:46:16,088][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000012352_12648448.pth... -[2023-10-09 08:46:16,128][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000010752_11010048.pth -[2023-10-09 08:46:16,131][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000010688_10944512.pth -[2023-10-09 08:46:17,304][23468] Updated weights for policy 0, policy_version 12362 (0.0011) -[2023-10-09 08:46:17,710][23468] Updated weights for policy 0, policy_version 12373 (0.0010) -[2023-10-09 08:46:18,068][23468] Updated weights for policy 0, policy_version 12383 (0.0010) -[2023-10-09 08:46:18,377][23469] Updated weights for policy 1, policy_version 12421 (0.0010) -[2023-10-09 08:46:18,743][23469] Updated weights for policy 1, policy_version 12431 (0.0010) -[2023-10-09 08:46:19,112][23469] Updated weights for policy 1, policy_version 12441 (0.0009) -[2023-10-09 08:46:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 25427968. Throughput: 0: 1689.1, 1: 1719.7. Samples: 6360330. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:46:21,078][22500] Avg episode reward: [(0, '5.680'), (1, '5.500')] -[2023-10-09 08:46:22,938][23468] Updated weights for policy 0, policy_version 12393 (0.0010) -[2023-10-09 08:46:23,315][23468] Updated weights for policy 0, policy_version 12403 (0.0010) -[2023-10-09 08:46:23,687][23468] Updated weights for policy 0, policy_version 12413 (0.0011) -[2023-10-09 08:46:23,755][23469] Updated weights for policy 1, policy_version 12451 (0.0014) -[2023-10-09 08:46:24,123][23469] Updated weights for policy 1, policy_version 12461 (0.0011) -[2023-10-09 08:46:24,496][23469] Updated weights for policy 1, policy_version 12471 (0.0011) -[2023-10-09 08:46:26,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 25493504. Throughput: 0: 1658.7, 1: 1658.6. Samples: 6378024. Policy #0 lag: (min: 25.0, avg: 36.5, max: 57.0) -[2023-10-09 08:46:26,078][22500] Avg episode reward: [(0, '5.570'), (1, '5.650')] -[2023-10-09 08:46:28,275][23468] Updated weights for policy 0, policy_version 12423 (0.0011) -[2023-10-09 08:46:28,646][23468] Updated weights for policy 0, policy_version 12433 (0.0011) -[2023-10-09 08:46:29,013][23468] Updated weights for policy 0, policy_version 12443 (0.0011) -[2023-10-09 08:46:29,146][23469] Updated weights for policy 1, policy_version 12481 (0.0010) -[2023-10-09 08:46:29,518][23469] Updated weights for policy 1, policy_version 12491 (0.0011) -[2023-10-09 08:46:29,892][23469] Updated weights for policy 1, policy_version 12501 (0.0011) -[2023-10-09 08:46:30,260][23469] Updated weights for policy 1, policy_version 12511 (0.0011) -[2023-10-09 08:46:31,077][22500] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 14218.0). Total num frames: 25559040. Throughput: 0: 1632.0, 1: 1641.3. Samples: 6396130. Policy #0 lag: (min: 25.0, avg: 36.5, max: 57.0) -[2023-10-09 08:46:31,078][22500] Avg episode reward: [(0, '5.790'), (1, '5.140')] -[2023-10-09 08:46:33,506][23468] Updated weights for policy 0, policy_version 12453 (0.0009) -[2023-10-09 08:46:33,885][23468] Updated weights for policy 0, policy_version 12463 (0.0008) -[2023-10-09 08:46:34,247][23468] Updated weights for policy 0, policy_version 12473 (0.0009) -[2023-10-09 08:46:34,598][23469] Updated weights for policy 1, policy_version 12521 (0.0008) -[2023-10-09 08:46:34,977][23469] Updated weights for policy 1, policy_version 12531 (0.0007) -[2023-10-09 08:46:35,342][23469] Updated weights for policy 1, policy_version 12541 (0.0008) -[2023-10-09 08:46:36,077][22500] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 14218.0). Total num frames: 25624576. Throughput: 0: 1622.3, 1: 1616.2. Samples: 6406798. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:46:36,078][22500] Avg episode reward: [(0, '5.900'), (1, '5.350')] -[2023-10-09 08:46:37,894][23468] Updated weights for policy 0, policy_version 12483 (0.0008) -[2023-10-09 08:46:38,256][23468] Updated weights for policy 0, policy_version 12493 (0.0009) -[2023-10-09 08:46:38,631][23468] Updated weights for policy 0, policy_version 12503 (0.0011) -[2023-10-09 08:46:39,345][23469] Updated weights for policy 1, policy_version 12551 (0.0009) -[2023-10-09 08:46:39,708][23469] Updated weights for policy 1, policy_version 12561 (0.0010) -[2023-10-09 08:46:40,085][23469] Updated weights for policy 1, policy_version 12571 (0.0010) -[2023-10-09 08:46:41,077][22500] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 14106.9). Total num frames: 25690112. Throughput: 0: 1604.4, 1: 1619.6. Samples: 6426284. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:46:41,078][22500] Avg episode reward: [(0, '5.790'), (1, '5.300')] -[2023-10-09 08:46:43,403][23468] Updated weights for policy 0, policy_version 12513 (0.0010) -[2023-10-09 08:46:43,813][23468] Updated weights for policy 0, policy_version 12523 (0.0010) -[2023-10-09 08:46:44,191][23468] Updated weights for policy 0, policy_version 12533 (0.0010) -[2023-10-09 08:46:44,567][23468] Updated weights for policy 0, policy_version 12543 (0.0010) -[2023-10-09 08:46:44,665][23469] Updated weights for policy 1, policy_version 12581 (0.0010) -[2023-10-09 08:46:45,037][23469] Updated weights for policy 1, policy_version 12591 (0.0010) -[2023-10-09 08:46:45,401][23469] Updated weights for policy 1, policy_version 12601 (0.0010) -[2023-10-09 08:46:46,077][22500] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 14106.9). Total num frames: 25755648. Throughput: 0: 1558.0, 1: 1563.5. Samples: 6444154. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:46:46,078][22500] Avg episode reward: [(0, '5.870'), (1, '5.600')] -[2023-10-09 08:46:49,222][23468] Updated weights for policy 0, policy_version 12553 (0.0011) -[2023-10-09 08:46:49,591][23468] Updated weights for policy 0, policy_version 12563 (0.0011) -[2023-10-09 08:46:49,962][23468] Updated weights for policy 0, policy_version 12573 (0.0011) -[2023-10-09 08:46:50,058][23469] Updated weights for policy 1, policy_version 12611 (0.0010) -[2023-10-09 08:46:50,430][23469] Updated weights for policy 1, policy_version 12621 (0.0010) -[2023-10-09 08:46:50,802][23469] Updated weights for policy 1, policy_version 12631 (0.0011) -[2023-10-09 08:46:51,077][22500] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 13995.8). Total num frames: 25788416. Throughput: 0: 1563.2, 1: 1565.9. Samples: 6454062. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 08:46:51,078][22500] Avg episode reward: [(0, '6.090'), (1, '5.810')] -[2023-10-09 08:46:54,560][23468] Updated weights for policy 0, policy_version 12583 (0.0009) -[2023-10-09 08:46:54,927][23468] Updated weights for policy 0, policy_version 12593 (0.0007) -[2023-10-09 08:46:55,215][23469] Updated weights for policy 1, policy_version 12641 (0.0011) -[2023-10-09 08:46:55,310][23468] Updated weights for policy 0, policy_version 12603 (0.0008) -[2023-10-09 08:46:55,586][23469] Updated weights for policy 1, policy_version 12651 (0.0010) -[2023-10-09 08:46:55,946][23469] Updated weights for policy 1, policy_version 12661 (0.0007) -[2023-10-09 08:46:56,077][22500] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 13884.8). Total num frames: 25853952. Throughput: 0: 1537.3, 1: 1550.9. Samples: 6472842. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 08:46:56,078][22500] Avg episode reward: [(0, '6.120'), (1, '5.830')] -[2023-10-09 08:46:56,327][23469] Updated weights for policy 1, policy_version 12671 (0.0008) -[2023-10-09 08:46:59,088][23468] Updated weights for policy 0, policy_version 12613 (0.0008) -[2023-10-09 08:46:59,462][23468] Updated weights for policy 0, policy_version 12623 (0.0007) -[2023-10-09 08:46:59,847][23468] Updated weights for policy 0, policy_version 12633 (0.0010) -[2023-10-09 08:47:00,109][23469] Updated weights for policy 1, policy_version 12681 (0.0008) -[2023-10-09 08:47:00,476][23469] Updated weights for policy 1, policy_version 12691 (0.0008) -[2023-10-09 08:47:00,846][23469] Updated weights for policy 1, policy_version 12701 (0.0008) -[2023-10-09 08:47:01,077][22500] Fps is (10 sec: 16383.8, 60 sec: 13107.2, 300 sec: 13995.8). Total num frames: 25952256. Throughput: 0: 1542.5, 1: 1566.4. Samples: 6492204. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 08:47:01,078][22500] Avg episode reward: [(0, '6.030'), (1, '5.890')] -[2023-10-09 08:47:03,644][23468] Updated weights for policy 0, policy_version 12643 (0.0009) -[2023-10-09 08:47:04,014][23468] Updated weights for policy 0, policy_version 12653 (0.0011) -[2023-10-09 08:47:04,393][23468] Updated weights for policy 0, policy_version 12663 (0.0010) -[2023-10-09 08:47:04,638][23469] Updated weights for policy 1, policy_version 12711 (0.0008) -[2023-10-09 08:47:05,020][23469] Updated weights for policy 1, policy_version 12721 (0.0008) -[2023-10-09 08:47:05,386][23469] Updated weights for policy 1, policy_version 12731 (0.0007) -[2023-10-09 08:47:06,077][22500] Fps is (10 sec: 16383.7, 60 sec: 13107.2, 300 sec: 13995.8). Total num frames: 26017792. Throughput: 0: 1605.1, 1: 1605.5. Samples: 6504806. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 08:47:06,079][22500] Avg episode reward: [(0, '5.940'), (1, '5.680')] -[2023-10-09 08:47:08,195][23468] Updated weights for policy 0, policy_version 12673 (0.0009) -[2023-10-09 08:47:08,571][23468] Updated weights for policy 0, policy_version 12683 (0.0007) -[2023-10-09 08:47:08,942][23468] Updated weights for policy 0, policy_version 12693 (0.0007) -[2023-10-09 08:47:09,051][23469] Updated weights for policy 1, policy_version 12741 (0.0010) -[2023-10-09 08:47:09,321][23468] Updated weights for policy 0, policy_version 12703 (0.0007) -[2023-10-09 08:47:09,420][23469] Updated weights for policy 1, policy_version 12751 (0.0009) -[2023-10-09 08:47:09,792][23469] Updated weights for policy 1, policy_version 12761 (0.0009) -[2023-10-09 08:47:11,077][22500] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13995.8). Total num frames: 26083328. Throughput: 0: 1620.6, 1: 1637.2. Samples: 6524622. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 08:47:11,078][22500] Avg episode reward: [(0, '6.460'), (1, '5.300')] -[2023-10-09 08:47:13,104][23468] Updated weights for policy 0, policy_version 12713 (0.0007) -[2023-10-09 08:47:13,483][23468] Updated weights for policy 0, policy_version 12723 (0.0008) -[2023-10-09 08:47:13,505][23469] Updated weights for policy 1, policy_version 12771 (0.0007) -[2023-10-09 08:47:13,851][23468] Updated weights for policy 0, policy_version 12733 (0.0009) -[2023-10-09 08:47:13,875][23469] Updated weights for policy 1, policy_version 12781 (0.0008) -[2023-10-09 08:47:14,247][23469] Updated weights for policy 1, policy_version 12791 (0.0007) -[2023-10-09 08:47:16,077][22500] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13995.8). Total num frames: 26148864. Throughput: 0: 1663.1, 1: 1680.5. Samples: 6546590. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:47:16,078][22500] Avg episode reward: [(0, '5.980'), (1, '5.080')] -[2023-10-09 08:47:17,622][23468] Updated weights for policy 0, policy_version 12743 (0.0008) -[2023-10-09 08:47:17,993][23468] Updated weights for policy 0, policy_version 12753 (0.0009) -[2023-10-09 08:47:18,226][23469] Updated weights for policy 1, policy_version 12801 (0.0008) -[2023-10-09 08:47:18,364][23468] Updated weights for policy 0, policy_version 12763 (0.0009) -[2023-10-09 08:47:18,594][23469] Updated weights for policy 1, policy_version 12811 (0.0007) -[2023-10-09 08:47:18,960][23469] Updated weights for policy 1, policy_version 12821 (0.0009) -[2023-10-09 08:47:19,336][23469] Updated weights for policy 1, policy_version 12831 (0.0010) -[2023-10-09 08:47:21,077][22500] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13995.8). Total num frames: 26214400. Throughput: 0: 1660.5, 1: 1680.6. Samples: 6557148. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:47:21,078][22500] Avg episode reward: [(0, '6.020'), (1, '5.370')] -[2023-10-09 08:47:22,105][23468] Updated weights for policy 0, policy_version 12773 (0.0008) -[2023-10-09 08:47:22,475][23468] Updated weights for policy 0, policy_version 12783 (0.0009) -[2023-10-09 08:47:22,849][23468] Updated weights for policy 0, policy_version 12793 (0.0009) -[2023-10-09 08:47:23,061][23469] Updated weights for policy 1, policy_version 12841 (0.0007) -[2023-10-09 08:47:23,437][23469] Updated weights for policy 1, policy_version 12851 (0.0008) -[2023-10-09 08:47:23,806][23469] Updated weights for policy 1, policy_version 12861 (0.0009) -[2023-10-09 08:47:26,077][22500] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13995.8). Total num frames: 26279936. Throughput: 0: 1682.6, 1: 1696.0. Samples: 6578322. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:47:26,079][22500] Avg episode reward: [(0, '5.900'), (1, '5.330')] -[2023-10-09 08:47:26,622][23468] Updated weights for policy 0, policy_version 12803 (0.0009) -[2023-10-09 08:47:26,995][23468] Updated weights for policy 0, policy_version 12813 (0.0011) -[2023-10-09 08:47:27,367][23468] Updated weights for policy 0, policy_version 12823 (0.0009) -[2023-10-09 08:47:27,512][23469] Updated weights for policy 1, policy_version 12871 (0.0007) -[2023-10-09 08:47:27,897][23469] Updated weights for policy 1, policy_version 12881 (0.0008) -[2023-10-09 08:47:28,257][23469] Updated weights for policy 1, policy_version 12891 (0.0009) -[2023-10-09 08:47:31,077][22500] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13884.7). Total num frames: 26345472. Throughput: 0: 1730.3, 1: 1745.6. Samples: 6600568. Policy #0 lag: (min: 31.0, avg: 32.8, max: 60.0) -[2023-10-09 08:47:31,078][22500] Avg episode reward: [(0, '6.280'), (1, '5.260')] -[2023-10-09 08:47:31,205][23468] Updated weights for policy 0, policy_version 12833 (0.0007) -[2023-10-09 08:47:31,615][23468] Updated weights for policy 0, policy_version 12843 (0.0007) -[2023-10-09 08:47:31,987][23468] Updated weights for policy 0, policy_version 12853 (0.0009) -[2023-10-09 08:47:32,030][23469] Updated weights for policy 1, policy_version 12901 (0.0008) -[2023-10-09 08:47:32,361][23468] Updated weights for policy 0, policy_version 12863 (0.0009) -[2023-10-09 08:47:32,403][23469] Updated weights for policy 1, policy_version 12911 (0.0007) -[2023-10-09 08:47:32,773][23469] Updated weights for policy 1, policy_version 12921 (0.0008) -[2023-10-09 08:47:36,077][22500] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13884.7). Total num frames: 26411008. Throughput: 0: 1723.1, 1: 1744.6. Samples: 6610108. Policy #0 lag: (min: 31.0, avg: 32.8, max: 60.0) -[2023-10-09 08:47:36,078][22500] Avg episode reward: [(0, '6.330'), (1, '4.950')] -[2023-10-09 08:47:36,179][23468] Updated weights for policy 0, policy_version 12873 (0.0007) -[2023-10-09 08:47:36,529][23469] Updated weights for policy 1, policy_version 12931 (0.0008) -[2023-10-09 08:47:36,557][23468] Updated weights for policy 0, policy_version 12883 (0.0009) -[2023-10-09 08:47:36,894][23469] Updated weights for policy 1, policy_version 12941 (0.0008) -[2023-10-09 08:47:36,932][23468] Updated weights for policy 0, policy_version 12893 (0.0009) -[2023-10-09 08:47:37,266][23469] Updated weights for policy 1, policy_version 12951 (0.0007) -[2023-10-09 08:47:40,703][23468] Updated weights for policy 0, policy_version 12903 (0.0010) -[2023-10-09 08:47:41,071][23468] Updated weights for policy 0, policy_version 12913 (0.0009) -[2023-10-09 08:47:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13884.7). Total num frames: 26476544. Throughput: 0: 1766.8, 1: 1779.0. Samples: 6632402. Policy #0 lag: (min: 31.0, avg: 32.8, max: 60.0) -[2023-10-09 08:47:41,078][22500] Avg episode reward: [(0, '6.280'), (1, '5.590')] -[2023-10-09 08:47:41,291][23469] Updated weights for policy 1, policy_version 12961 (0.0007) -[2023-10-09 08:47:41,437][23468] Updated weights for policy 0, policy_version 12923 (0.0007) -[2023-10-09 08:47:41,653][23469] Updated weights for policy 1, policy_version 12971 (0.0008) -[2023-10-09 08:47:42,029][23469] Updated weights for policy 1, policy_version 12981 (0.0009) -[2023-10-09 08:47:42,399][23469] Updated weights for policy 1, policy_version 12991 (0.0007) -[2023-10-09 08:47:45,299][23468] Updated weights for policy 0, policy_version 12933 (0.0008) -[2023-10-09 08:47:45,671][23468] Updated weights for policy 0, policy_version 12943 (0.0009) -[2023-10-09 08:47:46,038][23468] Updated weights for policy 0, policy_version 12953 (0.0009) -[2023-10-09 08:47:46,047][23469] Updated weights for policy 1, policy_version 13001 (0.0008) -[2023-10-09 08:47:46,078][22500] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13884.7). Total num frames: 26542080. Throughput: 0: 1794.1, 1: 1807.6. Samples: 6654282. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:47:46,078][22500] Avg episode reward: [(0, '6.090'), (1, '5.440')] -[2023-10-09 08:47:46,414][23469] Updated weights for policy 1, policy_version 13011 (0.0007) -[2023-10-09 08:47:46,785][23469] Updated weights for policy 1, policy_version 13021 (0.0008) -[2023-10-09 08:47:49,746][23468] Updated weights for policy 0, policy_version 12963 (0.0008) -[2023-10-09 08:47:50,113][23468] Updated weights for policy 0, policy_version 12973 (0.0010) -[2023-10-09 08:47:50,451][23469] Updated weights for policy 1, policy_version 13031 (0.0007) -[2023-10-09 08:47:50,493][23468] Updated weights for policy 0, policy_version 12983 (0.0009) -[2023-10-09 08:47:50,814][23469] Updated weights for policy 1, policy_version 13041 (0.0009) -[2023-10-09 08:47:51,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 26640384. Throughput: 0: 1763.7, 1: 1778.6. Samples: 6664212. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:47:51,078][22500] Avg episode reward: [(0, '5.950'), (1, '5.690')] -[2023-10-09 08:47:51,189][23469] Updated weights for policy 1, policy_version 13051 (0.0009) -[2023-10-09 08:47:54,324][23468] Updated weights for policy 0, policy_version 12993 (0.0010) -[2023-10-09 08:47:54,698][23468] Updated weights for policy 0, policy_version 13003 (0.0009) -[2023-10-09 08:47:54,871][23469] Updated weights for policy 1, policy_version 13061 (0.0009) -[2023-10-09 08:47:55,068][23468] Updated weights for policy 0, policy_version 13013 (0.0007) -[2023-10-09 08:47:55,245][23469] Updated weights for policy 1, policy_version 13071 (0.0007) -[2023-10-09 08:47:55,432][23468] Updated weights for policy 0, policy_version 13023 (0.0009) -[2023-10-09 08:47:55,620][23469] Updated weights for policy 1, policy_version 13081 (0.0009) -[2023-10-09 08:47:56,077][22500] Fps is (10 sec: 19661.2, 60 sec: 14745.6, 300 sec: 13995.8). Total num frames: 26738688. Throughput: 0: 1795.2, 1: 1802.2. Samples: 6686502. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-09 08:47:56,078][22500] Avg episode reward: [(0, '6.100'), (1, '5.510')] -[2023-10-09 08:47:59,334][23468] Updated weights for policy 0, policy_version 13033 (0.0007) -[2023-10-09 08:47:59,349][23469] Updated weights for policy 1, policy_version 13091 (0.0008) -[2023-10-09 08:47:59,697][23468] Updated weights for policy 0, policy_version 13043 (0.0007) -[2023-10-09 08:47:59,709][23469] Updated weights for policy 1, policy_version 13101 (0.0010) -[2023-10-09 08:48:00,079][23469] Updated weights for policy 1, policy_version 13111 (0.0010) -[2023-10-09 08:48:00,085][23468] Updated weights for policy 0, policy_version 13053 (0.0008) -[2023-10-09 08:48:01,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 26804224. Throughput: 0: 1762.8, 1: 1780.5. Samples: 6706040. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-09 08:48:01,078][22500] Avg episode reward: [(0, '6.080'), (1, '5.830')] -[2023-10-09 08:48:03,834][23469] Updated weights for policy 1, policy_version 13121 (0.0007) -[2023-10-09 08:48:03,861][23468] Updated weights for policy 0, policy_version 13063 (0.0008) -[2023-10-09 08:48:04,197][23469] Updated weights for policy 1, policy_version 13131 (0.0008) -[2023-10-09 08:48:04,238][23468] Updated weights for policy 0, policy_version 13073 (0.0009) -[2023-10-09 08:48:04,565][23469] Updated weights for policy 1, policy_version 13141 (0.0007) -[2023-10-09 08:48:04,606][23468] Updated weights for policy 0, policy_version 13083 (0.0007) -[2023-10-09 08:48:04,937][23469] Updated weights for policy 1, policy_version 13151 (0.0009) -[2023-10-09 08:48:06,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 26869760. Throughput: 0: 1789.9, 1: 1800.0. Samples: 6718694. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-09 08:48:06,079][22500] Avg episode reward: [(0, '6.110'), (1, '6.070')] -[2023-10-09 08:48:08,415][23468] Updated weights for policy 0, policy_version 13093 (0.0008) -[2023-10-09 08:48:08,607][23469] Updated weights for policy 1, policy_version 13161 (0.0007) -[2023-10-09 08:48:08,783][23468] Updated weights for policy 0, policy_version 13103 (0.0008) -[2023-10-09 08:48:08,979][23469] Updated weights for policy 1, policy_version 13171 (0.0008) -[2023-10-09 08:48:09,153][23468] Updated weights for policy 0, policy_version 13113 (0.0007) -[2023-10-09 08:48:09,351][23469] Updated weights for policy 1, policy_version 13181 (0.0007) -[2023-10-09 08:48:11,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 26935296. Throughput: 0: 1770.5, 1: 1786.4. Samples: 6738380. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:48:11,078][22500] Avg episode reward: [(0, '5.920'), (1, '5.760')] -[2023-10-09 08:48:12,741][23468] Updated weights for policy 0, policy_version 13123 (0.0008) -[2023-10-09 08:48:13,112][23468] Updated weights for policy 0, policy_version 13133 (0.0008) -[2023-10-09 08:48:13,259][23469] Updated weights for policy 1, policy_version 13191 (0.0009) -[2023-10-09 08:48:13,495][23468] Updated weights for policy 0, policy_version 13143 (0.0007) -[2023-10-09 08:48:13,635][23469] Updated weights for policy 1, policy_version 13201 (0.0009) -[2023-10-09 08:48:14,006][23469] Updated weights for policy 1, policy_version 13211 (0.0009) -[2023-10-09 08:48:16,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 27000832. Throughput: 0: 1764.8, 1: 1789.7. Samples: 6760522. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:48:16,079][22500] Avg episode reward: [(0, '6.090'), (1, '5.850')] -[2023-10-09 08:48:16,091][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000013216_13533184.pth... -[2023-10-09 08:48:16,091][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000013152_13467648.pth... -[2023-10-09 08:48:16,127][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000011552_11829248.pth -[2023-10-09 08:48:16,128][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000011584_11862016.pth -[2023-10-09 08:48:17,381][23468] Updated weights for policy 0, policy_version 13153 (0.0008) -[2023-10-09 08:48:17,743][23469] Updated weights for policy 1, policy_version 13221 (0.0007) -[2023-10-09 08:48:17,795][23468] Updated weights for policy 0, policy_version 13163 (0.0007) -[2023-10-09 08:48:18,116][23469] Updated weights for policy 1, policy_version 13231 (0.0008) -[2023-10-09 08:48:18,175][23468] Updated weights for policy 0, policy_version 13173 (0.0007) -[2023-10-09 08:48:18,490][23469] Updated weights for policy 1, policy_version 13241 (0.0007) -[2023-10-09 08:48:18,538][23468] Updated weights for policy 0, policy_version 13183 (0.0007) -[2023-10-09 08:48:21,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 27066368. Throughput: 0: 1776.0, 1: 1790.5. Samples: 6770602. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:48:21,079][22500] Avg episode reward: [(0, '5.940'), (1, '5.680')] -[2023-10-09 08:48:22,357][23469] Updated weights for policy 1, policy_version 13251 (0.0008) -[2023-10-09 08:48:22,369][23468] Updated weights for policy 0, policy_version 13193 (0.0007) -[2023-10-09 08:48:22,725][23469] Updated weights for policy 1, policy_version 13261 (0.0007) -[2023-10-09 08:48:22,736][23468] Updated weights for policy 0, policy_version 13203 (0.0007) -[2023-10-09 08:48:23,103][23469] Updated weights for policy 1, policy_version 13271 (0.0009) -[2023-10-09 08:48:23,104][23468] Updated weights for policy 0, policy_version 13213 (0.0008) -[2023-10-09 08:48:26,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 27131904. Throughput: 0: 1764.3, 1: 1789.3. Samples: 6792312. Policy #0 lag: (min: 11.0, avg: 14.9, max: 43.0) -[2023-10-09 08:48:26,078][22500] Avg episode reward: [(0, '5.600'), (1, '5.720')] -[2023-10-09 08:48:26,819][23468] Updated weights for policy 0, policy_version 13223 (0.0009) -[2023-10-09 08:48:26,821][23469] Updated weights for policy 1, policy_version 13281 (0.0008) -[2023-10-09 08:48:27,181][23468] Updated weights for policy 0, policy_version 13233 (0.0008) -[2023-10-09 08:48:27,191][23469] Updated weights for policy 1, policy_version 13291 (0.0007) -[2023-10-09 08:48:27,548][23469] Updated weights for policy 1, policy_version 13301 (0.0008) -[2023-10-09 08:48:27,555][23468] Updated weights for policy 0, policy_version 13243 (0.0008) -[2023-10-09 08:48:27,922][23469] Updated weights for policy 1, policy_version 13311 (0.0009) -[2023-10-09 08:48:31,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 27197440. Throughput: 0: 1774.8, 1: 1787.6. Samples: 6814590. Policy #0 lag: (min: 11.0, avg: 14.9, max: 43.0) -[2023-10-09 08:48:31,078][22500] Avg episode reward: [(0, '6.150'), (1, '5.370')] -[2023-10-09 08:48:31,283][23468] Updated weights for policy 0, policy_version 13253 (0.0008) -[2023-10-09 08:48:31,653][23468] Updated weights for policy 0, policy_version 13263 (0.0008) -[2023-10-09 08:48:31,731][23469] Updated weights for policy 1, policy_version 13321 (0.0008) -[2023-10-09 08:48:32,021][23468] Updated weights for policy 0, policy_version 13273 (0.0009) -[2023-10-09 08:48:32,099][23469] Updated weights for policy 1, policy_version 13331 (0.0009) -[2023-10-09 08:48:32,464][23469] Updated weights for policy 1, policy_version 13341 (0.0009) -[2023-10-09 08:48:35,903][23468] Updated weights for policy 0, policy_version 13283 (0.0009) -[2023-10-09 08:48:36,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 27262976. Throughput: 0: 1769.2, 1: 1789.4. Samples: 6824350. Policy #0 lag: (min: 11.0, avg: 14.9, max: 43.0) -[2023-10-09 08:48:36,078][22500] Avg episode reward: [(0, '6.450'), (1, '5.250')] -[2023-10-09 08:48:36,281][23468] Updated weights for policy 0, policy_version 13293 (0.0009) -[2023-10-09 08:48:36,321][23469] Updated weights for policy 1, policy_version 13351 (0.0008) -[2023-10-09 08:48:36,645][23468] Updated weights for policy 0, policy_version 13303 (0.0008) -[2023-10-09 08:48:36,691][23469] Updated weights for policy 1, policy_version 13361 (0.0007) -[2023-10-09 08:48:37,063][23469] Updated weights for policy 1, policy_version 13371 (0.0008) -[2023-10-09 08:48:40,334][23468] Updated weights for policy 0, policy_version 13313 (0.0008) -[2023-10-09 08:48:40,710][23468] Updated weights for policy 0, policy_version 13323 (0.0008) -[2023-10-09 08:48:40,778][23469] Updated weights for policy 1, policy_version 13381 (0.0009) -[2023-10-09 08:48:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 27328512. Throughput: 0: 1770.7, 1: 1783.9. Samples: 6846464. Policy #0 lag: (min: 31.0, avg: 32.7, max: 58.0) -[2023-10-09 08:48:41,078][22500] Avg episode reward: [(0, '7.010'), (1, '5.030')] -[2023-10-09 08:48:41,080][23468] Updated weights for policy 0, policy_version 13333 (0.0009) -[2023-10-09 08:48:41,141][23469] Updated weights for policy 1, policy_version 13391 (0.0008) -[2023-10-09 08:48:41,444][23468] Updated weights for policy 0, policy_version 13343 (0.0007) -[2023-10-09 08:48:41,479][23265] Saving new best policy, reward=7.010! -[2023-10-09 08:48:41,509][23469] Updated weights for policy 1, policy_version 13401 (0.0007) -[2023-10-09 08:48:45,236][23469] Updated weights for policy 1, policy_version 13411 (0.0008) -[2023-10-09 08:48:45,305][23468] Updated weights for policy 0, policy_version 13353 (0.0008) -[2023-10-09 08:48:45,595][23469] Updated weights for policy 1, policy_version 13421 (0.0007) -[2023-10-09 08:48:45,666][23468] Updated weights for policy 0, policy_version 13363 (0.0007) -[2023-10-09 08:48:45,971][23469] Updated weights for policy 1, policy_version 13431 (0.0008) -[2023-10-09 08:48:46,038][23468] Updated weights for policy 0, policy_version 13373 (0.0008) -[2023-10-09 08:48:46,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 27394048. Throughput: 0: 1796.8, 1: 1798.5. Samples: 6867828. Policy #0 lag: (min: 31.0, avg: 32.7, max: 58.0) -[2023-10-09 08:48:46,079][22500] Avg episode reward: [(0, '6.850'), (1, '5.110')] -[2023-10-09 08:48:49,738][23469] Updated weights for policy 1, policy_version 13441 (0.0010) -[2023-10-09 08:48:50,046][23468] Updated weights for policy 0, policy_version 13383 (0.0008) -[2023-10-09 08:48:50,110][23469] Updated weights for policy 1, policy_version 13451 (0.0008) -[2023-10-09 08:48:50,418][23468] Updated weights for policy 0, policy_version 13393 (0.0008) -[2023-10-09 08:48:50,471][23469] Updated weights for policy 1, policy_version 13461 (0.0008) -[2023-10-09 08:48:50,789][23468] Updated weights for policy 0, policy_version 13403 (0.0008) -[2023-10-09 08:48:50,839][23469] Updated weights for policy 1, policy_version 13471 (0.0009) -[2023-10-09 08:48:51,077][22500] Fps is (10 sec: 19660.8, 60 sec: 14745.6, 300 sec: 13995.8). Total num frames: 27525120. Throughput: 0: 1767.3, 1: 1783.1. Samples: 6878460. Policy #0 lag: (min: 20.0, avg: 27.5, max: 52.0) -[2023-10-09 08:48:51,079][22500] Avg episode reward: [(0, '6.640'), (1, '5.110')] -[2023-10-09 08:48:54,647][23468] Updated weights for policy 0, policy_version 13413 (0.0007) -[2023-10-09 08:48:54,842][23469] Updated weights for policy 1, policy_version 13481 (0.0009) -[2023-10-09 08:48:55,013][23468] Updated weights for policy 0, policy_version 13423 (0.0007) -[2023-10-09 08:48:55,216][23469] Updated weights for policy 1, policy_version 13491 (0.0009) -[2023-10-09 08:48:55,387][23468] Updated weights for policy 0, policy_version 13433 (0.0007) -[2023-10-09 08:48:55,574][23469] Updated weights for policy 1, policy_version 13501 (0.0008) -[2023-10-09 08:48:56,077][22500] Fps is (10 sec: 19660.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 27590656. Throughput: 0: 1791.5, 1: 1803.0. Samples: 6900132. Policy #0 lag: (min: 20.0, avg: 27.5, max: 52.0) -[2023-10-09 08:48:56,078][22500] Avg episode reward: [(0, '6.000'), (1, '5.170')] -[2023-10-09 08:48:59,280][23468] Updated weights for policy 0, policy_version 13443 (0.0008) -[2023-10-09 08:48:59,378][23469] Updated weights for policy 1, policy_version 13511 (0.0007) -[2023-10-09 08:48:59,646][23468] Updated weights for policy 0, policy_version 13453 (0.0008) -[2023-10-09 08:48:59,768][23469] Updated weights for policy 1, policy_version 13521 (0.0008) -[2023-10-09 08:49:00,024][23468] Updated weights for policy 0, policy_version 13463 (0.0008) -[2023-10-09 08:49:00,137][23469] Updated weights for policy 1, policy_version 13531 (0.0007) -[2023-10-09 08:49:01,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 27656192. Throughput: 0: 1762.9, 1: 1774.3. Samples: 6919696. Policy #0 lag: (min: 20.0, avg: 27.5, max: 52.0) -[2023-10-09 08:49:01,078][22500] Avg episode reward: [(0, '6.090'), (1, '5.380')] -[2023-10-09 08:49:03,637][23469] Updated weights for policy 1, policy_version 13541 (0.0007) -[2023-10-09 08:49:03,906][23468] Updated weights for policy 0, policy_version 13473 (0.0009) -[2023-10-09 08:49:03,998][23469] Updated weights for policy 1, policy_version 13551 (0.0008) -[2023-10-09 08:49:04,323][23468] Updated weights for policy 0, policy_version 13483 (0.0007) -[2023-10-09 08:49:04,377][23469] Updated weights for policy 1, policy_version 13561 (0.0009) -[2023-10-09 08:49:04,684][23468] Updated weights for policy 0, policy_version 13493 (0.0007) -[2023-10-09 08:49:05,067][23468] Updated weights for policy 0, policy_version 13503 (0.0008) -[2023-10-09 08:49:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 27721728. Throughput: 0: 1783.0, 1: 1801.0. Samples: 6931882. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-09 08:49:06,078][22500] Avg episode reward: [(0, '5.930'), (1, '5.570')] -[2023-10-09 08:49:08,005][23469] Updated weights for policy 1, policy_version 13571 (0.0009) -[2023-10-09 08:49:08,376][23469] Updated weights for policy 1, policy_version 13581 (0.0011) -[2023-10-09 08:49:08,745][23469] Updated weights for policy 1, policy_version 13591 (0.0007) -[2023-10-09 08:49:08,799][23468] Updated weights for policy 0, policy_version 13513 (0.0008) -[2023-10-09 08:49:09,176][23468] Updated weights for policy 0, policy_version 13523 (0.0008) -[2023-10-09 08:49:09,552][23468] Updated weights for policy 0, policy_version 13533 (0.0008) -[2023-10-09 08:49:11,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 27787264. Throughput: 0: 1768.6, 1: 1784.1. Samples: 6952186. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-09 08:49:11,078][22500] Avg episode reward: [(0, '6.250'), (1, '5.450')] -[2023-10-09 08:49:12,486][23469] Updated weights for policy 1, policy_version 13601 (0.0008) -[2023-10-09 08:49:12,852][23469] Updated weights for policy 1, policy_version 13611 (0.0009) -[2023-10-09 08:49:13,232][23469] Updated weights for policy 1, policy_version 13621 (0.0008) -[2023-10-09 08:49:13,384][23468] Updated weights for policy 0, policy_version 13543 (0.0007) -[2023-10-09 08:49:13,598][23469] Updated weights for policy 1, policy_version 13631 (0.0008) -[2023-10-09 08:49:13,750][23468] Updated weights for policy 0, policy_version 13553 (0.0009) -[2023-10-09 08:49:14,126][23468] Updated weights for policy 0, policy_version 13563 (0.0010) -[2023-10-09 08:49:16,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 27852800. Throughput: 0: 1754.3, 1: 1782.8. Samples: 6973764. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-09 08:49:16,079][22500] Avg episode reward: [(0, '6.150'), (1, '5.330')] -[2023-10-09 08:49:17,333][23469] Updated weights for policy 1, policy_version 13641 (0.0009) -[2023-10-09 08:49:17,701][23469] Updated weights for policy 1, policy_version 13651 (0.0009) -[2023-10-09 08:49:17,809][23468] Updated weights for policy 0, policy_version 13573 (0.0008) -[2023-10-09 08:49:18,058][23469] Updated weights for policy 1, policy_version 13661 (0.0008) -[2023-10-09 08:49:18,179][23468] Updated weights for policy 0, policy_version 13583 (0.0007) -[2023-10-09 08:49:18,554][23468] Updated weights for policy 0, policy_version 13593 (0.0007) -[2023-10-09 08:49:21,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 27918336. Throughput: 0: 1770.1, 1: 1780.3. Samples: 6984118. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:49:21,078][22500] Avg episode reward: [(0, '5.870'), (1, '5.510')] -[2023-10-09 08:49:21,905][23469] Updated weights for policy 1, policy_version 13671 (0.0010) -[2023-10-09 08:49:22,174][23468] Updated weights for policy 0, policy_version 13603 (0.0007) -[2023-10-09 08:49:22,276][23469] Updated weights for policy 1, policy_version 13681 (0.0008) -[2023-10-09 08:49:22,544][23468] Updated weights for policy 0, policy_version 13613 (0.0008) -[2023-10-09 08:49:22,638][23469] Updated weights for policy 1, policy_version 13691 (0.0007) -[2023-10-09 08:49:22,915][23468] Updated weights for policy 0, policy_version 13623 (0.0008) -[2023-10-09 08:49:26,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 27983872. Throughput: 0: 1755.9, 1: 1787.9. Samples: 7005932. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:49:26,078][22500] Avg episode reward: [(0, '5.460'), (1, '5.580')] -[2023-10-09 08:49:26,459][23469] Updated weights for policy 1, policy_version 13701 (0.0009) -[2023-10-09 08:49:26,803][23468] Updated weights for policy 0, policy_version 13633 (0.0010) -[2023-10-09 08:49:26,822][23469] Updated weights for policy 1, policy_version 13711 (0.0008) -[2023-10-09 08:49:27,167][23468] Updated weights for policy 0, policy_version 13643 (0.0008) -[2023-10-09 08:49:27,185][23469] Updated weights for policy 1, policy_version 13721 (0.0008) -[2023-10-09 08:49:27,536][23468] Updated weights for policy 0, policy_version 13653 (0.0008) -[2023-10-09 08:49:27,921][23468] Updated weights for policy 0, policy_version 13663 (0.0008) -[2023-10-09 08:49:30,900][23469] Updated weights for policy 1, policy_version 13731 (0.0008) -[2023-10-09 08:49:31,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 28049408. Throughput: 0: 1766.3, 1: 1802.8. Samples: 7028438. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:49:31,078][22500] Avg episode reward: [(0, '5.630'), (1, '5.690')] -[2023-10-09 08:49:31,260][23469] Updated weights for policy 1, policy_version 13741 (0.0009) -[2023-10-09 08:49:31,630][23469] Updated weights for policy 1, policy_version 13751 (0.0008) -[2023-10-09 08:49:31,689][23468] Updated weights for policy 0, policy_version 13673 (0.0009) -[2023-10-09 08:49:32,065][23468] Updated weights for policy 0, policy_version 13683 (0.0009) -[2023-10-09 08:49:32,435][23468] Updated weights for policy 0, policy_version 13693 (0.0010) -[2023-10-09 08:49:35,438][23469] Updated weights for policy 1, policy_version 13761 (0.0007) -[2023-10-09 08:49:35,807][23469] Updated weights for policy 1, policy_version 13771 (0.0009) -[2023-10-09 08:49:36,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 28114944. Throughput: 0: 1762.5, 1: 1788.1. Samples: 7038238. Policy #0 lag: (min: 21.0, avg: 29.0, max: 53.0) -[2023-10-09 08:49:36,078][22500] Avg episode reward: [(0, '5.610'), (1, '5.480')] -[2023-10-09 08:49:36,180][23469] Updated weights for policy 1, policy_version 13781 (0.0008) -[2023-10-09 08:49:36,263][23468] Updated weights for policy 0, policy_version 13703 (0.0008) -[2023-10-09 08:49:36,539][23469] Updated weights for policy 1, policy_version 13791 (0.0008) -[2023-10-09 08:49:36,636][23468] Updated weights for policy 0, policy_version 13713 (0.0008) -[2023-10-09 08:49:37,007][23468] Updated weights for policy 0, policy_version 13723 (0.0010) -[2023-10-09 08:49:40,309][23469] Updated weights for policy 1, policy_version 13801 (0.0010) -[2023-10-09 08:49:40,677][23469] Updated weights for policy 1, policy_version 13811 (0.0010) -[2023-10-09 08:49:40,747][23468] Updated weights for policy 0, policy_version 13733 (0.0008) -[2023-10-09 08:49:41,062][23469] Updated weights for policy 1, policy_version 13821 (0.0010) -[2023-10-09 08:49:41,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 28180480. Throughput: 0: 1767.3, 1: 1798.1. Samples: 7060574. Policy #0 lag: (min: 21.0, avg: 29.0, max: 53.0) -[2023-10-09 08:49:41,078][22500] Avg episode reward: [(0, '5.570'), (1, '5.720')] -[2023-10-09 08:49:41,123][23468] Updated weights for policy 0, policy_version 13743 (0.0011) -[2023-10-09 08:49:41,520][23468] Updated weights for policy 0, policy_version 13753 (0.0011) -[2023-10-09 08:49:44,805][23469] Updated weights for policy 1, policy_version 13831 (0.0008) -[2023-10-09 08:49:45,154][23468] Updated weights for policy 0, policy_version 13763 (0.0010) -[2023-10-09 08:49:45,180][23469] Updated weights for policy 1, policy_version 13841 (0.0008) -[2023-10-09 08:49:45,530][23468] Updated weights for policy 0, policy_version 13773 (0.0008) -[2023-10-09 08:49:45,546][23469] Updated weights for policy 1, policy_version 13851 (0.0007) -[2023-10-09 08:49:45,899][23468] Updated weights for policy 0, policy_version 13783 (0.0007) -[2023-10-09 08:49:46,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 13884.7). Total num frames: 28278784. Throughput: 0: 1793.2, 1: 1794.0. Samples: 7081120. Policy #0 lag: (min: 21.0, avg: 29.0, max: 53.0) -[2023-10-09 08:49:46,078][22500] Avg episode reward: [(0, '5.500'), (1, '5.790')] -[2023-10-09 08:49:49,384][23469] Updated weights for policy 1, policy_version 13861 (0.0007) -[2023-10-09 08:49:49,665][23468] Updated weights for policy 0, policy_version 13793 (0.0009) -[2023-10-09 08:49:49,757][23469] Updated weights for policy 1, policy_version 13871 (0.0007) -[2023-10-09 08:49:50,062][23468] Updated weights for policy 0, policy_version 13803 (0.0007) -[2023-10-09 08:49:50,118][23469] Updated weights for policy 1, policy_version 13881 (0.0007) -[2023-10-09 08:49:50,443][23468] Updated weights for policy 0, policy_version 13813 (0.0008) -[2023-10-09 08:49:50,803][23468] Updated weights for policy 0, policy_version 13823 (0.0010) -[2023-10-09 08:49:51,077][22500] Fps is (10 sec: 19660.8, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 28377088. Throughput: 0: 1772.3, 1: 1795.9. Samples: 7092448. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:49:51,078][22500] Avg episode reward: [(0, '5.590'), (1, '5.790')] -[2023-10-09 08:49:53,905][23469] Updated weights for policy 1, policy_version 13891 (0.0008) -[2023-10-09 08:49:54,279][23469] Updated weights for policy 1, policy_version 13901 (0.0007) -[2023-10-09 08:49:54,562][23468] Updated weights for policy 0, policy_version 13833 (0.0007) -[2023-10-09 08:49:54,655][23469] Updated weights for policy 1, policy_version 13911 (0.0007) -[2023-10-09 08:49:54,930][23468] Updated weights for policy 0, policy_version 13843 (0.0009) -[2023-10-09 08:49:55,310][23468] Updated weights for policy 0, policy_version 13853 (0.0008) -[2023-10-09 08:49:56,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 28442624. Throughput: 0: 1797.8, 1: 1792.5. Samples: 7113748. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:49:56,078][22500] Avg episode reward: [(0, '6.000'), (1, '5.590')] -[2023-10-09 08:49:58,381][23469] Updated weights for policy 1, policy_version 13921 (0.0008) -[2023-10-09 08:49:58,744][23469] Updated weights for policy 1, policy_version 13931 (0.0008) -[2023-10-09 08:49:59,034][23468] Updated weights for policy 0, policy_version 13863 (0.0008) -[2023-10-09 08:49:59,124][23469] Updated weights for policy 1, policy_version 13941 (0.0008) -[2023-10-09 08:49:59,411][23468] Updated weights for policy 0, policy_version 13873 (0.0007) -[2023-10-09 08:49:59,483][23469] Updated weights for policy 1, policy_version 13951 (0.0008) -[2023-10-09 08:49:59,785][23468] Updated weights for policy 0, policy_version 13883 (0.0007) -[2023-10-09 08:50:01,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 28508160. Throughput: 0: 1777.7, 1: 1788.8. Samples: 7134254. Policy #0 lag: (min: 18.0, avg: 25.5, max: 50.0) -[2023-10-09 08:50:01,078][22500] Avg episode reward: [(0, '5.540'), (1, '5.190')] -[2023-10-09 08:50:03,275][23469] Updated weights for policy 1, policy_version 13961 (0.0007) -[2023-10-09 08:50:03,579][23468] Updated weights for policy 0, policy_version 13893 (0.0008) -[2023-10-09 08:50:03,640][23469] Updated weights for policy 1, policy_version 13971 (0.0007) -[2023-10-09 08:50:03,959][23468] Updated weights for policy 0, policy_version 13903 (0.0007) -[2023-10-09 08:50:04,009][23469] Updated weights for policy 1, policy_version 13981 (0.0008) -[2023-10-09 08:50:04,340][23468] Updated weights for policy 0, policy_version 13913 (0.0008) -[2023-10-09 08:50:06,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 28573696. Throughput: 0: 1796.0, 1: 1796.3. Samples: 7145770. Policy #0 lag: (min: 18.0, avg: 25.5, max: 50.0) -[2023-10-09 08:50:06,078][22500] Avg episode reward: [(0, '5.610'), (1, '5.540')] -[2023-10-09 08:50:07,753][23469] Updated weights for policy 1, policy_version 13991 (0.0009) -[2023-10-09 08:50:08,129][23469] Updated weights for policy 1, policy_version 14001 (0.0010) -[2023-10-09 08:50:08,233][23468] Updated weights for policy 0, policy_version 13923 (0.0010) -[2023-10-09 08:50:08,500][23469] Updated weights for policy 1, policy_version 14011 (0.0008) -[2023-10-09 08:50:08,609][23468] Updated weights for policy 0, policy_version 13933 (0.0009) -[2023-10-09 08:50:08,987][23468] Updated weights for policy 0, policy_version 13943 (0.0009) -[2023-10-09 08:50:11,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 28639232. Throughput: 0: 1776.9, 1: 1781.5. Samples: 7166058. Policy #0 lag: (min: 18.0, avg: 25.5, max: 50.0) -[2023-10-09 08:50:11,078][22500] Avg episode reward: [(0, '5.910'), (1, '5.850')] -[2023-10-09 08:50:12,368][23469] Updated weights for policy 1, policy_version 14021 (0.0007) -[2023-10-09 08:50:12,732][23469] Updated weights for policy 1, policy_version 14031 (0.0007) -[2023-10-09 08:50:12,781][23468] Updated weights for policy 0, policy_version 13953 (0.0008) -[2023-10-09 08:50:13,096][23469] Updated weights for policy 1, policy_version 14041 (0.0007) -[2023-10-09 08:50:13,159][23468] Updated weights for policy 0, policy_version 13963 (0.0007) -[2023-10-09 08:50:13,532][23468] Updated weights for policy 0, policy_version 13973 (0.0008) -[2023-10-09 08:50:13,903][23468] Updated weights for policy 0, policy_version 13983 (0.0009) -[2023-10-09 08:50:16,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 28704768. Throughput: 0: 1777.8, 1: 1784.0. Samples: 7188718. Policy #0 lag: (min: 24.0, avg: 46.2, max: 56.0) -[2023-10-09 08:50:16,078][22500] Avg episode reward: [(0, '5.910'), (1, '5.890')] -[2023-10-09 08:50:16,089][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000014048_14385152.pth... -[2023-10-09 08:50:16,089][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000013984_14319616.pth... -[2023-10-09 08:50:16,122][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000012352_12648448.pth -[2023-10-09 08:50:16,128][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000012416_12713984.pth -[2023-10-09 08:50:16,754][23469] Updated weights for policy 1, policy_version 14051 (0.0008) -[2023-10-09 08:50:17,118][23469] Updated weights for policy 1, policy_version 14061 (0.0010) -[2023-10-09 08:50:17,494][23469] Updated weights for policy 1, policy_version 14071 (0.0008) -[2023-10-09 08:50:17,651][23468] Updated weights for policy 0, policy_version 13993 (0.0009) -[2023-10-09 08:50:18,021][23468] Updated weights for policy 0, policy_version 14003 (0.0010) -[2023-10-09 08:50:18,400][23468] Updated weights for policy 0, policy_version 14013 (0.0007) -[2023-10-09 08:50:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 28770304. Throughput: 0: 1787.2, 1: 1780.7. Samples: 7198790. Policy #0 lag: (min: 24.0, avg: 46.2, max: 56.0) -[2023-10-09 08:50:21,078][22500] Avg episode reward: [(0, '5.970'), (1, '5.920')] -[2023-10-09 08:50:21,352][23469] Updated weights for policy 1, policy_version 14081 (0.0008) -[2023-10-09 08:50:21,727][23469] Updated weights for policy 1, policy_version 14091 (0.0009) -[2023-10-09 08:50:22,088][23469] Updated weights for policy 1, policy_version 14101 (0.0009) -[2023-10-09 08:50:22,314][23468] Updated weights for policy 0, policy_version 14023 (0.0009) -[2023-10-09 08:50:22,452][23469] Updated weights for policy 1, policy_version 14111 (0.0009) -[2023-10-09 08:50:22,689][23468] Updated weights for policy 0, policy_version 14033 (0.0009) -[2023-10-09 08:50:23,069][23468] Updated weights for policy 0, policy_version 14043 (0.0008) -[2023-10-09 08:50:26,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 28835840. Throughput: 0: 1773.7, 1: 1778.6. Samples: 7220428. Policy #0 lag: (min: 24.0, avg: 46.2, max: 56.0) -[2023-10-09 08:50:26,078][22500] Avg episode reward: [(0, '5.980'), (1, '5.350')] -[2023-10-09 08:50:26,223][23469] Updated weights for policy 1, policy_version 14121 (0.0010) -[2023-10-09 08:50:26,600][23469] Updated weights for policy 1, policy_version 14131 (0.0010) -[2023-10-09 08:50:26,814][23468] Updated weights for policy 0, policy_version 14053 (0.0008) -[2023-10-09 08:50:26,963][23469] Updated weights for policy 1, policy_version 14141 (0.0008) -[2023-10-09 08:50:27,184][23468] Updated weights for policy 0, policy_version 14063 (0.0009) -[2023-10-09 08:50:27,569][23468] Updated weights for policy 0, policy_version 14073 (0.0011) -[2023-10-09 08:50:30,856][23469] Updated weights for policy 1, policy_version 14151 (0.0008) -[2023-10-09 08:50:31,036][23468] Updated weights for policy 0, policy_version 14083 (0.0010) -[2023-10-09 08:50:31,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 28901376. Throughput: 0: 1788.9, 1: 1802.7. Samples: 7242742. Policy #0 lag: (min: 3.0, avg: 12.7, max: 35.0) -[2023-10-09 08:50:31,078][22500] Avg episode reward: [(0, '6.390'), (1, '5.310')] -[2023-10-09 08:50:31,248][23469] Updated weights for policy 1, policy_version 14161 (0.0008) -[2023-10-09 08:50:31,403][23468] Updated weights for policy 0, policy_version 14093 (0.0007) -[2023-10-09 08:50:31,624][23469] Updated weights for policy 1, policy_version 14171 (0.0008) -[2023-10-09 08:50:31,777][23468] Updated weights for policy 0, policy_version 14103 (0.0009) -[2023-10-09 08:50:35,281][23469] Updated weights for policy 1, policy_version 14181 (0.0009) -[2023-10-09 08:50:35,487][23468] Updated weights for policy 0, policy_version 14113 (0.0007) -[2023-10-09 08:50:35,656][23469] Updated weights for policy 1, policy_version 14191 (0.0008) -[2023-10-09 08:50:35,894][23468] Updated weights for policy 0, policy_version 14123 (0.0009) -[2023-10-09 08:50:36,017][23469] Updated weights for policy 1, policy_version 14201 (0.0008) -[2023-10-09 08:50:36,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 28966912. Throughput: 0: 1788.0, 1: 1773.2. Samples: 7252700. Policy #0 lag: (min: 3.0, avg: 12.7, max: 35.0) -[2023-10-09 08:50:36,078][22500] Avg episode reward: [(0, '6.430'), (1, '5.260')] -[2023-10-09 08:50:36,262][23468] Updated weights for policy 0, policy_version 14133 (0.0008) -[2023-10-09 08:50:36,637][23468] Updated weights for policy 0, policy_version 14143 (0.0007) -[2023-10-09 08:50:39,794][23469] Updated weights for policy 1, policy_version 14211 (0.0008) -[2023-10-09 08:50:40,157][23469] Updated weights for policy 1, policy_version 14221 (0.0007) -[2023-10-09 08:50:40,535][23469] Updated weights for policy 1, policy_version 14231 (0.0008) -[2023-10-09 08:50:40,580][23468] Updated weights for policy 0, policy_version 14153 (0.0009) -[2023-10-09 08:50:40,944][23468] Updated weights for policy 0, policy_version 14163 (0.0009) -[2023-10-09 08:50:41,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 13884.8). Total num frames: 29065216. Throughput: 0: 1783.7, 1: 1794.9. Samples: 7274784. Policy #0 lag: (min: 3.0, avg: 12.7, max: 35.0) -[2023-10-09 08:50:41,078][22500] Avg episode reward: [(0, '6.520'), (1, '5.480')] -[2023-10-09 08:50:41,322][23468] Updated weights for policy 0, policy_version 14173 (0.0010) -[2023-10-09 08:50:44,359][23469] Updated weights for policy 1, policy_version 14241 (0.0010) -[2023-10-09 08:50:44,735][23469] Updated weights for policy 1, policy_version 14251 (0.0007) -[2023-10-09 08:50:45,095][23469] Updated weights for policy 1, policy_version 14261 (0.0007) -[2023-10-09 08:50:45,149][23468] Updated weights for policy 0, policy_version 14183 (0.0007) -[2023-10-09 08:50:45,467][23469] Updated weights for policy 1, policy_version 14271 (0.0008) -[2023-10-09 08:50:45,530][23468] Updated weights for policy 0, policy_version 14193 (0.0008) -[2023-10-09 08:50:45,902][23468] Updated weights for policy 0, policy_version 14203 (0.0010) -[2023-10-09 08:50:46,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13884.8). Total num frames: 29130752. Throughput: 0: 1801.3, 1: 1770.3. Samples: 7294974. Policy #0 lag: (min: 30.0, avg: 31.4, max: 54.0) -[2023-10-09 08:50:46,078][22500] Avg episode reward: [(0, '5.920'), (1, '5.380')] -[2023-10-09 08:50:49,052][23469] Updated weights for policy 1, policy_version 14281 (0.0008) -[2023-10-09 08:50:49,418][23469] Updated weights for policy 1, policy_version 14291 (0.0008) -[2023-10-09 08:50:49,792][23468] Updated weights for policy 0, policy_version 14213 (0.0008) -[2023-10-09 08:50:49,795][23469] Updated weights for policy 1, policy_version 14301 (0.0009) -[2023-10-09 08:50:50,162][23468] Updated weights for policy 0, policy_version 14223 (0.0007) -[2023-10-09 08:50:50,536][23468] Updated weights for policy 0, policy_version 14233 (0.0009) -[2023-10-09 08:50:51,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 29229056. Throughput: 0: 1779.3, 1: 1799.1. Samples: 7306796. Policy #0 lag: (min: 30.0, avg: 31.4, max: 54.0) -[2023-10-09 08:50:51,078][22500] Avg episode reward: [(0, '5.850'), (1, '5.560')] -[2023-10-09 08:50:53,638][23469] Updated weights for policy 1, policy_version 14311 (0.0009) -[2023-10-09 08:50:54,013][23469] Updated weights for policy 1, policy_version 14321 (0.0009) -[2023-10-09 08:50:54,233][23468] Updated weights for policy 0, policy_version 14243 (0.0007) -[2023-10-09 08:50:54,381][23469] Updated weights for policy 1, policy_version 14331 (0.0007) -[2023-10-09 08:50:54,604][23468] Updated weights for policy 0, policy_version 14253 (0.0007) -[2023-10-09 08:50:54,976][23468] Updated weights for policy 0, policy_version 14263 (0.0007) -[2023-10-09 08:50:56,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 29294592. Throughput: 0: 1805.0, 1: 1778.9. Samples: 7327334. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:50:56,078][22500] Avg episode reward: [(0, '5.690'), (1, '5.540')] -[2023-10-09 08:50:58,004][23469] Updated weights for policy 1, policy_version 14341 (0.0007) -[2023-10-09 08:50:58,374][23469] Updated weights for policy 1, policy_version 14351 (0.0007) -[2023-10-09 08:50:58,584][23468] Updated weights for policy 0, policy_version 14273 (0.0008) -[2023-10-09 08:50:58,745][23469] Updated weights for policy 1, policy_version 14361 (0.0009) -[2023-10-09 08:50:58,951][23468] Updated weights for policy 0, policy_version 14283 (0.0008) -[2023-10-09 08:50:59,328][23468] Updated weights for policy 0, policy_version 14293 (0.0007) -[2023-10-09 08:50:59,706][23468] Updated weights for policy 0, policy_version 14303 (0.0008) -[2023-10-09 08:51:01,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 29360128. Throughput: 0: 1778.5, 1: 1783.7. Samples: 7349012. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:51:01,078][22500] Avg episode reward: [(0, '5.760'), (1, '5.450')] -[2023-10-09 08:51:02,309][23469] Updated weights for policy 1, policy_version 14371 (0.0007) -[2023-10-09 08:51:02,693][23469] Updated weights for policy 1, policy_version 14381 (0.0007) -[2023-10-09 08:51:03,060][23469] Updated weights for policy 1, policy_version 14391 (0.0008) -[2023-10-09 08:51:03,509][23468] Updated weights for policy 0, policy_version 14313 (0.0010) -[2023-10-09 08:51:03,887][23468] Updated weights for policy 0, policy_version 14323 (0.0009) -[2023-10-09 08:51:04,265][23468] Updated weights for policy 0, policy_version 14333 (0.0010) -[2023-10-09 08:51:06,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 29425664. Throughput: 0: 1797.3, 1: 1787.4. Samples: 7360100. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:51:06,079][22500] Avg episode reward: [(0, '6.060'), (1, '5.320')] -[2023-10-09 08:51:06,855][23469] Updated weights for policy 1, policy_version 14401 (0.0008) -[2023-10-09 08:51:07,211][23469] Updated weights for policy 1, policy_version 14411 (0.0009) -[2023-10-09 08:51:07,579][23469] Updated weights for policy 1, policy_version 14421 (0.0009) -[2023-10-09 08:51:07,950][23469] Updated weights for policy 1, policy_version 14431 (0.0007) -[2023-10-09 08:51:08,106][23468] Updated weights for policy 0, policy_version 14343 (0.0010) -[2023-10-09 08:51:08,490][23468] Updated weights for policy 0, policy_version 14353 (0.0008) -[2023-10-09 08:51:08,860][23468] Updated weights for policy 0, policy_version 14363 (0.0008) -[2023-10-09 08:51:11,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 29491200. Throughput: 0: 1779.1, 1: 1799.0. Samples: 7381444. Policy #0 lag: (min: 27.0, avg: 30.9, max: 59.0) -[2023-10-09 08:51:11,079][22500] Avg episode reward: [(0, '5.960'), (1, '5.770')] -[2023-10-09 08:51:11,755][23469] Updated weights for policy 1, policy_version 14441 (0.0008) -[2023-10-09 08:51:12,124][23469] Updated weights for policy 1, policy_version 14451 (0.0011) -[2023-10-09 08:51:12,495][23469] Updated weights for policy 1, policy_version 14461 (0.0009) -[2023-10-09 08:51:12,527][23468] Updated weights for policy 0, policy_version 14373 (0.0007) -[2023-10-09 08:51:12,898][23468] Updated weights for policy 0, policy_version 14383 (0.0007) -[2023-10-09 08:51:13,269][23468] Updated weights for policy 0, policy_version 14393 (0.0009) -[2023-10-09 08:51:16,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 29556736. Throughput: 0: 1770.5, 1: 1803.3. Samples: 7403564. Policy #0 lag: (min: 27.0, avg: 30.9, max: 59.0) -[2023-10-09 08:51:16,079][22500] Avg episode reward: [(0, '6.300'), (1, '5.400')] -[2023-10-09 08:51:16,382][23469] Updated weights for policy 1, policy_version 14471 (0.0009) -[2023-10-09 08:51:16,770][23469] Updated weights for policy 1, policy_version 14481 (0.0010) -[2023-10-09 08:51:17,018][23468] Updated weights for policy 0, policy_version 14403 (0.0008) -[2023-10-09 08:51:17,137][23469] Updated weights for policy 1, policy_version 14491 (0.0008) -[2023-10-09 08:51:17,383][23468] Updated weights for policy 0, policy_version 14413 (0.0008) -[2023-10-09 08:51:17,760][23468] Updated weights for policy 0, policy_version 14423 (0.0007) -[2023-10-09 08:51:20,776][23469] Updated weights for policy 1, policy_version 14501 (0.0008) -[2023-10-09 08:51:21,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 29622272. Throughput: 0: 1768.5, 1: 1798.1. Samples: 7413198. Policy #0 lag: (min: 27.0, avg: 30.9, max: 59.0) -[2023-10-09 08:51:21,078][22500] Avg episode reward: [(0, '6.140'), (1, '5.420')] -[2023-10-09 08:51:21,143][23469] Updated weights for policy 1, policy_version 14511 (0.0008) -[2023-10-09 08:51:21,520][23469] Updated weights for policy 1, policy_version 14521 (0.0009) -[2023-10-09 08:51:21,731][23468] Updated weights for policy 0, policy_version 14433 (0.0009) -[2023-10-09 08:51:22,105][23468] Updated weights for policy 0, policy_version 14443 (0.0009) -[2023-10-09 08:51:22,479][23468] Updated weights for policy 0, policy_version 14453 (0.0008) -[2023-10-09 08:51:22,850][23468] Updated weights for policy 0, policy_version 14463 (0.0007) -[2023-10-09 08:51:25,384][23469] Updated weights for policy 1, policy_version 14531 (0.0009) -[2023-10-09 08:51:25,753][23469] Updated weights for policy 1, policy_version 14541 (0.0009) -[2023-10-09 08:51:26,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 29687808. Throughput: 0: 1766.9, 1: 1798.3. Samples: 7435220. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:51:26,078][22500] Avg episode reward: [(0, '6.250'), (1, '5.360')] -[2023-10-09 08:51:26,131][23469] Updated weights for policy 1, policy_version 14551 (0.0008) -[2023-10-09 08:51:26,675][23468] Updated weights for policy 0, policy_version 14473 (0.0009) -[2023-10-09 08:51:27,046][23468] Updated weights for policy 0, policy_version 14483 (0.0008) -[2023-10-09 08:51:27,421][23468] Updated weights for policy 0, policy_version 14493 (0.0009) -[2023-10-09 08:51:29,974][23469] Updated weights for policy 1, policy_version 14561 (0.0008) -[2023-10-09 08:51:30,345][23469] Updated weights for policy 1, policy_version 14571 (0.0008) -[2023-10-09 08:51:30,716][23469] Updated weights for policy 1, policy_version 14581 (0.0007) -[2023-10-09 08:51:31,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 29753344. Throughput: 0: 1781.2, 1: 1811.3. Samples: 7456638. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:51:31,078][22500] Avg episode reward: [(0, '6.240'), (1, '5.270')] -[2023-10-09 08:51:31,083][23469] Updated weights for policy 1, policy_version 14591 (0.0007) -[2023-10-09 08:51:31,204][23468] Updated weights for policy 0, policy_version 14503 (0.0007) -[2023-10-09 08:51:31,577][23468] Updated weights for policy 0, policy_version 14513 (0.0009) -[2023-10-09 08:51:31,955][23468] Updated weights for policy 0, policy_version 14523 (0.0009) -[2023-10-09 08:51:34,636][23469] Updated weights for policy 1, policy_version 14601 (0.0007) -[2023-10-09 08:51:35,004][23469] Updated weights for policy 1, policy_version 14611 (0.0007) -[2023-10-09 08:51:35,370][23469] Updated weights for policy 1, policy_version 14621 (0.0007) -[2023-10-09 08:51:35,635][23468] Updated weights for policy 0, policy_version 14533 (0.0010) -[2023-10-09 08:51:36,006][23468] Updated weights for policy 0, policy_version 14543 (0.0011) -[2023-10-09 08:51:36,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14106.9). Total num frames: 29851648. Throughput: 0: 1767.0, 1: 1795.7. Samples: 7467116. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:51:36,078][22500] Avg episode reward: [(0, '6.470'), (1, '5.440')] -[2023-10-09 08:51:36,385][23468] Updated weights for policy 0, policy_version 14553 (0.0009) -[2023-10-09 08:51:39,011][23469] Updated weights for policy 1, policy_version 14631 (0.0010) -[2023-10-09 08:51:39,377][23469] Updated weights for policy 1, policy_version 14641 (0.0008) -[2023-10-09 08:51:39,741][23469] Updated weights for policy 1, policy_version 14651 (0.0008) -[2023-10-09 08:51:40,146][23468] Updated weights for policy 0, policy_version 14563 (0.0010) -[2023-10-09 08:51:40,518][23468] Updated weights for policy 0, policy_version 14573 (0.0007) -[2023-10-09 08:51:40,892][23468] Updated weights for policy 0, policy_version 14583 (0.0011) -[2023-10-09 08:51:41,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 29917184. Throughput: 0: 1778.7, 1: 1804.4. Samples: 7488572. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:51:41,078][22500] Avg episode reward: [(0, '6.310'), (1, '5.470')] -[2023-10-09 08:51:43,675][23469] Updated weights for policy 1, policy_version 14661 (0.0009) -[2023-10-09 08:51:44,041][23469] Updated weights for policy 1, policy_version 14671 (0.0012) -[2023-10-09 08:51:44,419][23469] Updated weights for policy 1, policy_version 14681 (0.0008) -[2023-10-09 08:51:44,708][23468] Updated weights for policy 0, policy_version 14593 (0.0007) -[2023-10-09 08:51:45,092][23468] Updated weights for policy 0, policy_version 14603 (0.0009) -[2023-10-09 08:51:45,457][23468] Updated weights for policy 0, policy_version 14613 (0.0011) -[2023-10-09 08:51:45,835][23468] Updated weights for policy 0, policy_version 14623 (0.0009) -[2023-10-09 08:51:46,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 30015488. Throughput: 0: 1786.9, 1: 1791.3. Samples: 7510034. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:51:46,078][22500] Avg episode reward: [(0, '6.480'), (1, '5.460')] -[2023-10-09 08:51:48,247][23469] Updated weights for policy 1, policy_version 14691 (0.0009) -[2023-10-09 08:51:48,616][23469] Updated weights for policy 1, policy_version 14701 (0.0007) -[2023-10-09 08:51:48,982][23469] Updated weights for policy 1, policy_version 14711 (0.0008) -[2023-10-09 08:51:49,524][23468] Updated weights for policy 0, policy_version 14633 (0.0009) -[2023-10-09 08:51:49,896][23468] Updated weights for policy 0, policy_version 14643 (0.0009) -[2023-10-09 08:51:50,264][23468] Updated weights for policy 0, policy_version 14653 (0.0009) -[2023-10-09 08:51:51,077][22500] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 30081024. Throughput: 0: 1776.3, 1: 1802.7. Samples: 7521154. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 08:51:51,078][22500] Avg episode reward: [(0, '6.130'), (1, '5.420')] -[2023-10-09 08:51:52,825][23469] Updated weights for policy 1, policy_version 14721 (0.0008) -[2023-10-09 08:51:53,192][23469] Updated weights for policy 1, policy_version 14731 (0.0007) -[2023-10-09 08:51:53,559][23469] Updated weights for policy 1, policy_version 14741 (0.0007) -[2023-10-09 08:51:53,936][23469] Updated weights for policy 1, policy_version 14751 (0.0007) -[2023-10-09 08:51:53,961][23468] Updated weights for policy 0, policy_version 14663 (0.0007) -[2023-10-09 08:51:54,327][23468] Updated weights for policy 0, policy_version 14673 (0.0007) -[2023-10-09 08:51:54,714][23468] Updated weights for policy 0, policy_version 14683 (0.0008) -[2023-10-09 08:51:56,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 30146560. Throughput: 0: 1795.7, 1: 1776.5. Samples: 7542194. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 08:51:56,078][22500] Avg episode reward: [(0, '6.180'), (1, '5.690')] -[2023-10-09 08:51:57,694][23469] Updated weights for policy 1, policy_version 14761 (0.0011) -[2023-10-09 08:51:58,066][23469] Updated weights for policy 1, policy_version 14771 (0.0007) -[2023-10-09 08:51:58,432][23469] Updated weights for policy 1, policy_version 14781 (0.0010) -[2023-10-09 08:51:58,515][23468] Updated weights for policy 0, policy_version 14693 (0.0008) -[2023-10-09 08:51:58,879][23468] Updated weights for policy 0, policy_version 14703 (0.0007) -[2023-10-09 08:51:59,261][23468] Updated weights for policy 0, policy_version 14713 (0.0007) -[2023-10-09 08:52:01,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 30212096. Throughput: 0: 1776.8, 1: 1779.6. Samples: 7563598. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 08:52:01,078][22500] Avg episode reward: [(0, '5.880'), (1, '5.700')] -[2023-10-09 08:52:02,248][23469] Updated weights for policy 1, policy_version 14791 (0.0009) -[2023-10-09 08:52:02,629][23469] Updated weights for policy 1, policy_version 14801 (0.0007) -[2023-10-09 08:52:02,995][23469] Updated weights for policy 1, policy_version 14811 (0.0009) -[2023-10-09 08:52:03,094][23468] Updated weights for policy 0, policy_version 14723 (0.0007) -[2023-10-09 08:52:03,459][23468] Updated weights for policy 0, policy_version 14733 (0.0007) -[2023-10-09 08:52:03,840][23468] Updated weights for policy 0, policy_version 14743 (0.0009) -[2023-10-09 08:52:06,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 30277632. Throughput: 0: 1800.4, 1: 1779.9. Samples: 7574308. Policy #0 lag: (min: 5.0, avg: 7.5, max: 37.0) -[2023-10-09 08:52:06,078][22500] Avg episode reward: [(0, '5.820'), (1, '5.690')] -[2023-10-09 08:52:06,788][23469] Updated weights for policy 1, policy_version 14821 (0.0007) -[2023-10-09 08:52:07,159][23469] Updated weights for policy 1, policy_version 14831 (0.0007) -[2023-10-09 08:52:07,508][23468] Updated weights for policy 0, policy_version 14753 (0.0008) -[2023-10-09 08:52:07,521][23469] Updated weights for policy 1, policy_version 14841 (0.0007) -[2023-10-09 08:52:07,920][23468] Updated weights for policy 0, policy_version 14763 (0.0010) -[2023-10-09 08:52:08,299][23468] Updated weights for policy 0, policy_version 14773 (0.0011) -[2023-10-09 08:52:08,669][23468] Updated weights for policy 0, policy_version 14783 (0.0009) -[2023-10-09 08:52:11,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 30343168. Throughput: 0: 1782.8, 1: 1780.2. Samples: 7595556. Policy #0 lag: (min: 5.0, avg: 7.5, max: 37.0) -[2023-10-09 08:52:11,079][22500] Avg episode reward: [(0, '5.830'), (1, '5.710')] -[2023-10-09 08:52:11,291][23469] Updated weights for policy 1, policy_version 14851 (0.0009) -[2023-10-09 08:52:11,660][23469] Updated weights for policy 1, policy_version 14861 (0.0008) -[2023-10-09 08:52:12,040][23469] Updated weights for policy 1, policy_version 14871 (0.0010) -[2023-10-09 08:52:12,449][23468] Updated weights for policy 0, policy_version 14793 (0.0007) -[2023-10-09 08:52:12,815][23468] Updated weights for policy 0, policy_version 14803 (0.0008) -[2023-10-09 08:52:13,189][23468] Updated weights for policy 0, policy_version 14813 (0.0007) -[2023-10-09 08:52:15,800][23469] Updated weights for policy 1, policy_version 14881 (0.0007) -[2023-10-09 08:52:16,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 30408704. Throughput: 0: 1781.3, 1: 1801.3. Samples: 7617854. Policy #0 lag: (min: 5.0, avg: 7.5, max: 37.0) -[2023-10-09 08:52:16,078][22500] Avg episode reward: [(0, '5.880'), (1, '6.020')] -[2023-10-09 08:52:16,086][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000014816_15171584.pth... -[2023-10-09 08:52:16,122][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000013152_13467648.pth -[2023-10-09 08:52:16,167][23469] Updated weights for policy 1, policy_version 14891 (0.0008) -[2023-10-09 08:52:16,539][23469] Updated weights for policy 1, policy_version 14901 (0.0008) -[2023-10-09 08:52:16,908][23469] Updated weights for policy 1, policy_version 14911 (0.0007) -[2023-10-09 08:52:16,937][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000014912_15269888.pth... -[2023-10-09 08:52:16,969][23468] Updated weights for policy 0, policy_version 14823 (0.0010) -[2023-10-09 08:52:16,970][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000013216_13533184.pth -[2023-10-09 08:52:17,340][23468] Updated weights for policy 0, policy_version 14833 (0.0009) -[2023-10-09 08:52:17,703][23468] Updated weights for policy 0, policy_version 14843 (0.0008) -[2023-10-09 08:52:20,614][23469] Updated weights for policy 1, policy_version 14921 (0.0008) -[2023-10-09 08:52:20,978][23469] Updated weights for policy 1, policy_version 14931 (0.0008) -[2023-10-09 08:52:21,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 30474240. Throughput: 0: 1784.5, 1: 1780.9. Samples: 7627560. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 08:52:21,078][22500] Avg episode reward: [(0, '6.150'), (1, '5.700')] -[2023-10-09 08:52:21,360][23469] Updated weights for policy 1, policy_version 14941 (0.0009) -[2023-10-09 08:52:21,554][23468] Updated weights for policy 0, policy_version 14853 (0.0008) -[2023-10-09 08:52:21,928][23468] Updated weights for policy 0, policy_version 14863 (0.0008) -[2023-10-09 08:52:22,297][23468] Updated weights for policy 0, policy_version 14873 (0.0008) -[2023-10-09 08:52:25,024][23469] Updated weights for policy 1, policy_version 14951 (0.0007) -[2023-10-09 08:52:25,392][23469] Updated weights for policy 1, policy_version 14961 (0.0009) -[2023-10-09 08:52:25,769][23469] Updated weights for policy 1, policy_version 14971 (0.0011) -[2023-10-09 08:52:25,980][23468] Updated weights for policy 0, policy_version 14883 (0.0008) -[2023-10-09 08:52:26,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 30572544. Throughput: 0: 1776.7, 1: 1810.1. Samples: 7649980. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 08:52:26,078][22500] Avg episode reward: [(0, '5.740'), (1, '5.670')] -[2023-10-09 08:52:26,345][23468] Updated weights for policy 0, policy_version 14893 (0.0009) -[2023-10-09 08:52:26,723][23468] Updated weights for policy 0, policy_version 14903 (0.0007) -[2023-10-09 08:52:29,493][23469] Updated weights for policy 1, policy_version 14981 (0.0008) -[2023-10-09 08:52:29,867][23469] Updated weights for policy 1, policy_version 14991 (0.0007) -[2023-10-09 08:52:30,233][23469] Updated weights for policy 1, policy_version 15001 (0.0009) -[2023-10-09 08:52:30,276][23468] Updated weights for policy 0, policy_version 14913 (0.0007) -[2023-10-09 08:52:30,657][23468] Updated weights for policy 0, policy_version 14923 (0.0010) -[2023-10-09 08:52:31,028][23468] Updated weights for policy 0, policy_version 14933 (0.0009) -[2023-10-09 08:52:31,078][22500] Fps is (10 sec: 16383.3, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 30638080. Throughput: 0: 1795.5, 1: 1785.7. Samples: 7671188. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 08:52:31,079][22500] Avg episode reward: [(0, '5.540'), (1, '5.160')] -[2023-10-09 08:52:31,411][23468] Updated weights for policy 0, policy_version 14943 (0.0010) -[2023-10-09 08:52:33,938][23469] Updated weights for policy 1, policy_version 15011 (0.0008) -[2023-10-09 08:52:34,318][23469] Updated weights for policy 1, policy_version 15021 (0.0010) -[2023-10-09 08:52:34,681][23469] Updated weights for policy 1, policy_version 15031 (0.0010) -[2023-10-09 08:52:35,351][23468] Updated weights for policy 0, policy_version 14953 (0.0009) -[2023-10-09 08:52:35,724][23468] Updated weights for policy 0, policy_version 14963 (0.0011) -[2023-10-09 08:52:36,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 30703616. Throughput: 0: 1780.0, 1: 1801.4. Samples: 7682318. Policy #0 lag: (min: 5.0, avg: 11.5, max: 37.0) -[2023-10-09 08:52:36,079][22500] Avg episode reward: [(0, '5.480'), (1, '5.190')] -[2023-10-09 08:52:36,100][23468] Updated weights for policy 0, policy_version 14973 (0.0008) -[2023-10-09 08:52:38,471][23469] Updated weights for policy 1, policy_version 15041 (0.0010) -[2023-10-09 08:52:38,837][23469] Updated weights for policy 1, policy_version 15051 (0.0009) -[2023-10-09 08:52:39,207][23469] Updated weights for policy 1, policy_version 15061 (0.0008) -[2023-10-09 08:52:39,582][23469] Updated weights for policy 1, policy_version 15071 (0.0007) -[2023-10-09 08:52:39,835][23468] Updated weights for policy 0, policy_version 14983 (0.0007) -[2023-10-09 08:52:40,208][23468] Updated weights for policy 0, policy_version 14993 (0.0007) -[2023-10-09 08:52:40,570][23468] Updated weights for policy 0, policy_version 15003 (0.0007) -[2023-10-09 08:52:41,077][22500] Fps is (10 sec: 16384.5, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 30801920. Throughput: 0: 1792.9, 1: 1787.5. Samples: 7703316. Policy #0 lag: (min: 5.0, avg: 11.5, max: 37.0) -[2023-10-09 08:52:41,079][22500] Avg episode reward: [(0, '6.170'), (1, '5.170')] -[2023-10-09 08:52:43,383][23469] Updated weights for policy 1, policy_version 15081 (0.0007) -[2023-10-09 08:52:43,750][23469] Updated weights for policy 1, policy_version 15091 (0.0008) -[2023-10-09 08:52:44,131][23469] Updated weights for policy 1, policy_version 15101 (0.0009) -[2023-10-09 08:52:44,378][23468] Updated weights for policy 0, policy_version 15013 (0.0009) -[2023-10-09 08:52:44,757][23468] Updated weights for policy 0, policy_version 15023 (0.0010) -[2023-10-09 08:52:45,121][23468] Updated weights for policy 0, policy_version 15033 (0.0007) -[2023-10-09 08:52:46,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 30867456. Throughput: 0: 1780.8, 1: 1788.3. Samples: 7724210. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:52:46,078][22500] Avg episode reward: [(0, '6.080'), (1, '5.250')] -[2023-10-09 08:52:47,874][23469] Updated weights for policy 1, policy_version 15111 (0.0009) -[2023-10-09 08:52:48,253][23469] Updated weights for policy 1, policy_version 15121 (0.0009) -[2023-10-09 08:52:48,627][23469] Updated weights for policy 1, policy_version 15131 (0.0011) -[2023-10-09 08:52:48,861][23468] Updated weights for policy 0, policy_version 15043 (0.0009) -[2023-10-09 08:52:49,236][23468] Updated weights for policy 0, policy_version 15053 (0.0008) -[2023-10-09 08:52:49,611][23468] Updated weights for policy 0, policy_version 15063 (0.0007) -[2023-10-09 08:52:51,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 30932992. Throughput: 0: 1785.2, 1: 1788.8. Samples: 7735140. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:52:51,078][22500] Avg episode reward: [(0, '6.470'), (1, '5.240')] -[2023-10-09 08:52:52,594][23469] Updated weights for policy 1, policy_version 15141 (0.0008) -[2023-10-09 08:52:52,955][23469] Updated weights for policy 1, policy_version 15151 (0.0008) -[2023-10-09 08:52:53,327][23469] Updated weights for policy 1, policy_version 15161 (0.0008) -[2023-10-09 08:52:53,466][23468] Updated weights for policy 0, policy_version 15073 (0.0007) -[2023-10-09 08:52:53,832][23468] Updated weights for policy 0, policy_version 15083 (0.0008) -[2023-10-09 08:52:54,206][23468] Updated weights for policy 0, policy_version 15093 (0.0007) -[2023-10-09 08:52:54,581][23468] Updated weights for policy 0, policy_version 15103 (0.0008) -[2023-10-09 08:52:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 30998528. Throughput: 0: 1783.7, 1: 1782.5. Samples: 7756034. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:52:56,078][22500] Avg episode reward: [(0, '5.740'), (1, '5.450')] -[2023-10-09 08:52:57,194][23469] Updated weights for policy 1, policy_version 15171 (0.0009) -[2023-10-09 08:52:57,569][23469] Updated weights for policy 1, policy_version 15181 (0.0010) -[2023-10-09 08:52:57,939][23469] Updated weights for policy 1, policy_version 15191 (0.0010) -[2023-10-09 08:52:58,490][23468] Updated weights for policy 0, policy_version 15113 (0.0009) -[2023-10-09 08:52:58,871][23468] Updated weights for policy 0, policy_version 15123 (0.0008) -[2023-10-09 08:52:59,244][23468] Updated weights for policy 0, policy_version 15133 (0.0008) -[2023-10-09 08:53:01,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 31064064. Throughput: 0: 1774.8, 1: 1776.4. Samples: 7777654. Policy #0 lag: (min: 24.0, avg: 50.2, max: 56.0) -[2023-10-09 08:53:01,078][22500] Avg episode reward: [(0, '5.810'), (1, '5.680')] -[2023-10-09 08:53:01,732][23469] Updated weights for policy 1, policy_version 15201 (0.0009) -[2023-10-09 08:53:02,110][23469] Updated weights for policy 1, policy_version 15211 (0.0009) -[2023-10-09 08:53:02,468][23469] Updated weights for policy 1, policy_version 15221 (0.0007) -[2023-10-09 08:53:02,845][23469] Updated weights for policy 1, policy_version 15231 (0.0008) -[2023-10-09 08:53:02,939][23468] Updated weights for policy 0, policy_version 15143 (0.0007) -[2023-10-09 08:53:03,319][23468] Updated weights for policy 0, policy_version 15153 (0.0008) -[2023-10-09 08:53:03,688][23468] Updated weights for policy 0, policy_version 15163 (0.0007) -[2023-10-09 08:53:06,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 31129600. Throughput: 0: 1791.1, 1: 1775.0. Samples: 7788036. Policy #0 lag: (min: 24.0, avg: 50.2, max: 56.0) -[2023-10-09 08:53:06,078][22500] Avg episode reward: [(0, '5.910'), (1, '5.980')] -[2023-10-09 08:53:06,612][23469] Updated weights for policy 1, policy_version 15241 (0.0008) -[2023-10-09 08:53:06,986][23469] Updated weights for policy 1, policy_version 15251 (0.0007) -[2023-10-09 08:53:07,356][23469] Updated weights for policy 1, policy_version 15261 (0.0008) -[2023-10-09 08:53:07,503][23468] Updated weights for policy 0, policy_version 15173 (0.0007) -[2023-10-09 08:53:07,872][23468] Updated weights for policy 0, policy_version 15183 (0.0007) -[2023-10-09 08:53:08,253][23468] Updated weights for policy 0, policy_version 15193 (0.0007) -[2023-10-09 08:53:11,050][23469] Updated weights for policy 1, policy_version 15271 (0.0007) -[2023-10-09 08:53:11,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 31195136. Throughput: 0: 1774.7, 1: 1767.6. Samples: 7809382. Policy #0 lag: (min: 24.0, avg: 50.2, max: 56.0) -[2023-10-09 08:53:11,078][22500] Avg episode reward: [(0, '6.070'), (1, '6.040')] -[2023-10-09 08:53:11,427][23469] Updated weights for policy 1, policy_version 15281 (0.0007) -[2023-10-09 08:53:11,798][23469] Updated weights for policy 1, policy_version 15291 (0.0010) -[2023-10-09 08:53:12,163][23468] Updated weights for policy 0, policy_version 15203 (0.0007) -[2023-10-09 08:53:12,547][23468] Updated weights for policy 0, policy_version 15213 (0.0007) -[2023-10-09 08:53:12,914][23468] Updated weights for policy 0, policy_version 15223 (0.0007) -[2023-10-09 08:53:15,568][23469] Updated weights for policy 1, policy_version 15301 (0.0008) -[2023-10-09 08:53:15,942][23469] Updated weights for policy 1, policy_version 15311 (0.0007) -[2023-10-09 08:53:16,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 31260672. Throughput: 0: 1770.6, 1: 1786.4. Samples: 7831254. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) -[2023-10-09 08:53:16,078][22500] Avg episode reward: [(0, '6.140'), (1, '5.990')] -[2023-10-09 08:53:16,310][23469] Updated weights for policy 1, policy_version 15321 (0.0008) -[2023-10-09 08:53:16,477][23468] Updated weights for policy 0, policy_version 15233 (0.0007) -[2023-10-09 08:53:16,845][23468] Updated weights for policy 0, policy_version 15243 (0.0007) -[2023-10-09 08:53:17,214][23468] Updated weights for policy 0, policy_version 15253 (0.0008) -[2023-10-09 08:53:17,585][23468] Updated weights for policy 0, policy_version 15263 (0.0009) -[2023-10-09 08:53:20,122][23469] Updated weights for policy 1, policy_version 15331 (0.0007) -[2023-10-09 08:53:20,494][23469] Updated weights for policy 1, policy_version 15341 (0.0009) -[2023-10-09 08:53:20,859][23469] Updated weights for policy 1, policy_version 15351 (0.0008) -[2023-10-09 08:53:21,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 31326208. Throughput: 0: 1768.4, 1: 1765.6. Samples: 7841348. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) -[2023-10-09 08:53:21,078][22500] Avg episode reward: [(0, '5.620'), (1, '5.730')] -[2023-10-09 08:53:21,422][23468] Updated weights for policy 0, policy_version 15273 (0.0011) -[2023-10-09 08:53:21,791][23468] Updated weights for policy 0, policy_version 15283 (0.0009) -[2023-10-09 08:53:22,168][23468] Updated weights for policy 0, policy_version 15293 (0.0008) -[2023-10-09 08:53:24,740][23469] Updated weights for policy 1, policy_version 15361 (0.0007) -[2023-10-09 08:53:25,101][23469] Updated weights for policy 1, policy_version 15371 (0.0007) -[2023-10-09 08:53:25,470][23469] Updated weights for policy 1, policy_version 15381 (0.0010) -[2023-10-09 08:53:25,846][23469] Updated weights for policy 1, policy_version 15391 (0.0010) -[2023-10-09 08:53:26,076][23468] Updated weights for policy 0, policy_version 15303 (0.0008) -[2023-10-09 08:53:26,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 31424512. Throughput: 0: 1763.5, 1: 1786.1. Samples: 7863050. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) -[2023-10-09 08:53:26,078][22500] Avg episode reward: [(0, '5.740'), (1, '5.480')] -[2023-10-09 08:53:26,450][23468] Updated weights for policy 0, policy_version 15313 (0.0008) -[2023-10-09 08:53:26,828][23468] Updated weights for policy 0, policy_version 15323 (0.0011) -[2023-10-09 08:53:29,656][23469] Updated weights for policy 1, policy_version 15401 (0.0007) -[2023-10-09 08:53:30,025][23469] Updated weights for policy 1, policy_version 15411 (0.0008) -[2023-10-09 08:53:30,391][23469] Updated weights for policy 1, policy_version 15421 (0.0009) -[2023-10-09 08:53:30,570][23468] Updated weights for policy 0, policy_version 15333 (0.0010) -[2023-10-09 08:53:30,947][23468] Updated weights for policy 0, policy_version 15343 (0.0010) -[2023-10-09 08:53:31,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 31490048. Throughput: 0: 1797.3, 1: 1755.2. Samples: 7884072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:53:31,078][22500] Avg episode reward: [(0, '5.780'), (1, '5.920')] -[2023-10-09 08:53:31,312][23468] Updated weights for policy 0, policy_version 15353 (0.0010) -[2023-10-09 08:53:34,240][23469] Updated weights for policy 1, policy_version 15431 (0.0009) -[2023-10-09 08:53:34,619][23469] Updated weights for policy 1, policy_version 15441 (0.0007) -[2023-10-09 08:53:34,991][23469] Updated weights for policy 1, policy_version 15451 (0.0010) -[2023-10-09 08:53:35,062][23468] Updated weights for policy 0, policy_version 15363 (0.0009) -[2023-10-09 08:53:35,429][23468] Updated weights for policy 0, policy_version 15373 (0.0009) -[2023-10-09 08:53:35,805][23468] Updated weights for policy 0, policy_version 15383 (0.0008) -[2023-10-09 08:53:36,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 31555584. Throughput: 0: 1767.5, 1: 1791.5. Samples: 7895292. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:53:36,079][22500] Avg episode reward: [(0, '6.190'), (1, '5.730')] -[2023-10-09 08:53:38,819][23469] Updated weights for policy 1, policy_version 15461 (0.0009) -[2023-10-09 08:53:39,186][23469] Updated weights for policy 1, policy_version 15471 (0.0007) -[2023-10-09 08:53:39,553][23469] Updated weights for policy 1, policy_version 15481 (0.0007) -[2023-10-09 08:53:39,640][23468] Updated weights for policy 0, policy_version 15393 (0.0009) -[2023-10-09 08:53:40,013][23468] Updated weights for policy 0, policy_version 15403 (0.0009) -[2023-10-09 08:53:40,396][23468] Updated weights for policy 0, policy_version 15413 (0.0009) -[2023-10-09 08:53:40,760][23468] Updated weights for policy 0, policy_version 15423 (0.0010) -[2023-10-09 08:53:41,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 31653888. Throughput: 0: 1792.7, 1: 1763.5. Samples: 7916060. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-09 08:53:41,078][22500] Avg episode reward: [(0, '6.200'), (1, '5.850')] -[2023-10-09 08:53:43,244][23469] Updated weights for policy 1, policy_version 15491 (0.0008) -[2023-10-09 08:53:43,619][23469] Updated weights for policy 1, policy_version 15501 (0.0007) -[2023-10-09 08:53:43,986][23469] Updated weights for policy 1, policy_version 15511 (0.0009) -[2023-10-09 08:53:44,737][23468] Updated weights for policy 0, policy_version 15433 (0.0010) -[2023-10-09 08:53:45,115][23468] Updated weights for policy 0, policy_version 15443 (0.0008) -[2023-10-09 08:53:45,497][23468] Updated weights for policy 0, policy_version 15453 (0.0009) -[2023-10-09 08:53:46,078][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 31719424. Throughput: 0: 1775.8, 1: 1765.6. Samples: 7937018. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-09 08:53:46,079][22500] Avg episode reward: [(0, '6.560'), (1, '5.660')] -[2023-10-09 08:53:47,725][23469] Updated weights for policy 1, policy_version 15521 (0.0010) -[2023-10-09 08:53:48,090][23469] Updated weights for policy 1, policy_version 15531 (0.0009) -[2023-10-09 08:53:48,457][23469] Updated weights for policy 1, policy_version 15541 (0.0007) -[2023-10-09 08:53:48,834][23469] Updated weights for policy 1, policy_version 15551 (0.0008) -[2023-10-09 08:53:49,247][23468] Updated weights for policy 0, policy_version 15463 (0.0009) -[2023-10-09 08:53:49,620][23468] Updated weights for policy 0, policy_version 15473 (0.0009) -[2023-10-09 08:53:49,989][23468] Updated weights for policy 0, policy_version 15483 (0.0009) -[2023-10-09 08:53:51,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 31784960. Throughput: 0: 1782.7, 1: 1773.7. Samples: 7948078. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-09 08:53:51,079][22500] Avg episode reward: [(0, '6.450'), (1, '5.830')] -[2023-10-09 08:53:52,558][23469] Updated weights for policy 1, policy_version 15561 (0.0008) -[2023-10-09 08:53:52,943][23469] Updated weights for policy 1, policy_version 15571 (0.0009) -[2023-10-09 08:53:53,313][23469] Updated weights for policy 1, policy_version 15581 (0.0008) -[2023-10-09 08:53:53,667][23468] Updated weights for policy 0, policy_version 15493 (0.0010) -[2023-10-09 08:53:54,041][23468] Updated weights for policy 0, policy_version 15503 (0.0008) -[2023-10-09 08:53:54,425][23468] Updated weights for policy 0, policy_version 15513 (0.0008) -[2023-10-09 08:53:56,077][22500] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 31850496. Throughput: 0: 1778.7, 1: 1776.0. Samples: 7969344. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-09 08:53:56,078][22500] Avg episode reward: [(0, '6.240'), (1, '5.600')] -[2023-10-09 08:53:56,963][23469] Updated weights for policy 1, policy_version 15591 (0.0007) -[2023-10-09 08:53:57,335][23469] Updated weights for policy 1, policy_version 15601 (0.0007) -[2023-10-09 08:53:57,706][23469] Updated weights for policy 1, policy_version 15611 (0.0007) -[2023-10-09 08:53:58,142][23468] Updated weights for policy 0, policy_version 15523 (0.0010) -[2023-10-09 08:53:58,509][23468] Updated weights for policy 0, policy_version 15533 (0.0009) -[2023-10-09 08:53:58,891][23468] Updated weights for policy 0, policy_version 15543 (0.0010) -[2023-10-09 08:54:01,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 31916032. Throughput: 0: 1764.4, 1: 1786.8. Samples: 7991062. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-09 08:54:01,079][22500] Avg episode reward: [(0, '6.320'), (1, '5.620')] -[2023-10-09 08:54:01,495][23469] Updated weights for policy 1, policy_version 15621 (0.0008) -[2023-10-09 08:54:01,869][23469] Updated weights for policy 1, policy_version 15631 (0.0008) -[2023-10-09 08:54:02,245][23469] Updated weights for policy 1, policy_version 15641 (0.0008) -[2023-10-09 08:54:02,789][23468] Updated weights for policy 0, policy_version 15553 (0.0010) -[2023-10-09 08:54:03,165][23468] Updated weights for policy 0, policy_version 15563 (0.0007) -[2023-10-09 08:54:03,539][23468] Updated weights for policy 0, policy_version 15573 (0.0007) -[2023-10-09 08:54:03,908][23468] Updated weights for policy 0, policy_version 15583 (0.0007) -[2023-10-09 08:54:06,013][23469] Updated weights for policy 1, policy_version 15651 (0.0007) -[2023-10-09 08:54:06,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 31981568. Throughput: 0: 1781.3, 1: 1779.9. Samples: 8001600. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-09 08:54:06,079][22500] Avg episode reward: [(0, '6.020'), (1, '5.780')] -[2023-10-09 08:54:06,377][23469] Updated weights for policy 1, policy_version 15661 (0.0007) -[2023-10-09 08:54:06,748][23469] Updated weights for policy 1, policy_version 15671 (0.0008) -[2023-10-09 08:54:07,671][23468] Updated weights for policy 0, policy_version 15593 (0.0009) -[2023-10-09 08:54:08,048][23468] Updated weights for policy 0, policy_version 15603 (0.0010) -[2023-10-09 08:54:08,431][23468] Updated weights for policy 0, policy_version 15613 (0.0011) -[2023-10-09 08:54:10,541][23469] Updated weights for policy 1, policy_version 15681 (0.0007) -[2023-10-09 08:54:10,911][23469] Updated weights for policy 1, policy_version 15691 (0.0008) -[2023-10-09 08:54:11,077][22500] Fps is (10 sec: 13107.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 32047104. Throughput: 0: 1763.3, 1: 1791.1. Samples: 8023000. Policy #0 lag: (min: 21.0, avg: 26.1, max: 53.0) -[2023-10-09 08:54:11,078][22500] Avg episode reward: [(0, '6.350'), (1, '5.970')] -[2023-10-09 08:54:11,281][23469] Updated weights for policy 1, policy_version 15701 (0.0007) -[2023-10-09 08:54:11,657][23469] Updated weights for policy 1, policy_version 15711 (0.0008) -[2023-10-09 08:54:12,336][23468] Updated weights for policy 0, policy_version 15623 (0.0010) -[2023-10-09 08:54:12,712][23468] Updated weights for policy 0, policy_version 15633 (0.0008) -[2023-10-09 08:54:13,092][23468] Updated weights for policy 0, policy_version 15643 (0.0009) -[2023-10-09 08:54:15,254][23469] Updated weights for policy 1, policy_version 15721 (0.0009) -[2023-10-09 08:54:15,614][23469] Updated weights for policy 1, policy_version 15731 (0.0010) -[2023-10-09 08:54:15,984][23469] Updated weights for policy 1, policy_version 15741 (0.0010) -[2023-10-09 08:54:16,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 32112640. Throughput: 0: 1759.2, 1: 1800.4. Samples: 8044256. Policy #0 lag: (min: 21.0, avg: 26.1, max: 53.0) -[2023-10-09 08:54:16,078][22500] Avg episode reward: [(0, '6.220'), (1, '5.780')] -[2023-10-09 08:54:16,088][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000015648_16023552.pth... -[2023-10-09 08:54:16,095][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000015744_16121856.pth... -[2023-10-09 08:54:16,125][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000013984_14319616.pth -[2023-10-09 08:54:16,135][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000014048_14385152.pth -[2023-10-09 08:54:16,835][23468] Updated weights for policy 0, policy_version 15653 (0.0008) -[2023-10-09 08:54:17,206][23468] Updated weights for policy 0, policy_version 15663 (0.0008) -[2023-10-09 08:54:17,581][23468] Updated weights for policy 0, policy_version 15673 (0.0009) -[2023-10-09 08:54:19,682][23469] Updated weights for policy 1, policy_version 15751 (0.0008) -[2023-10-09 08:54:20,050][23469] Updated weights for policy 1, policy_version 15761 (0.0008) -[2023-10-09 08:54:20,419][23469] Updated weights for policy 1, policy_version 15771 (0.0009) -[2023-10-09 08:54:21,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 32210944. Throughput: 0: 1758.5, 1: 1793.9. Samples: 8055148. Policy #0 lag: (min: 21.0, avg: 26.1, max: 53.0) -[2023-10-09 08:54:21,078][22500] Avg episode reward: [(0, '6.480'), (1, '5.590')] -[2023-10-09 08:54:21,441][23468] Updated weights for policy 0, policy_version 15683 (0.0009) -[2023-10-09 08:54:21,823][23468] Updated weights for policy 0, policy_version 15693 (0.0009) -[2023-10-09 08:54:22,195][23468] Updated weights for policy 0, policy_version 15703 (0.0009) -[2023-10-09 08:54:24,078][23469] Updated weights for policy 1, policy_version 15781 (0.0010) -[2023-10-09 08:54:24,447][23469] Updated weights for policy 1, policy_version 15791 (0.0009) -[2023-10-09 08:54:24,809][23469] Updated weights for policy 1, policy_version 15801 (0.0008) -[2023-10-09 08:54:26,077][22500] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 32276480. Throughput: 0: 1756.1, 1: 1813.6. Samples: 8076698. Policy #0 lag: (min: 1.0, avg: 2.7, max: 29.0) -[2023-10-09 08:54:26,078][22500] Avg episode reward: [(0, '5.980'), (1, '5.440')] -[2023-10-09 08:54:26,079][23468] Updated weights for policy 0, policy_version 15713 (0.0008) -[2023-10-09 08:54:26,451][23468] Updated weights for policy 0, policy_version 15723 (0.0009) -[2023-10-09 08:54:26,827][23468] Updated weights for policy 0, policy_version 15733 (0.0007) -[2023-10-09 08:54:27,198][23468] Updated weights for policy 0, policy_version 15743 (0.0007) -[2023-10-09 08:54:28,605][23469] Updated weights for policy 1, policy_version 15811 (0.0008) -[2023-10-09 08:54:28,971][23469] Updated weights for policy 1, policy_version 15821 (0.0010) -[2023-10-09 08:54:29,344][23469] Updated weights for policy 1, policy_version 15831 (0.0010) -[2023-10-09 08:54:31,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 32342016. Throughput: 0: 1786.1, 1: 1806.8. Samples: 8098694. Policy #0 lag: (min: 1.0, avg: 2.7, max: 29.0) -[2023-10-09 08:54:31,078][22500] Avg episode reward: [(0, '5.810'), (1, '5.470')] -[2023-10-09 08:54:31,089][23468] Updated weights for policy 0, policy_version 15753 (0.0008) -[2023-10-09 08:54:31,458][23468] Updated weights for policy 0, policy_version 15763 (0.0007) -[2023-10-09 08:54:31,826][23468] Updated weights for policy 0, policy_version 15773 (0.0009) -[2023-10-09 08:54:33,009][23469] Updated weights for policy 1, policy_version 15841 (0.0011) -[2023-10-09 08:54:33,374][23469] Updated weights for policy 1, policy_version 15851 (0.0010) -[2023-10-09 08:54:33,741][23469] Updated weights for policy 1, policy_version 15861 (0.0011) -[2023-10-09 08:54:34,112][23469] Updated weights for policy 1, policy_version 15871 (0.0011) -[2023-10-09 08:54:35,593][23468] Updated weights for policy 0, policy_version 15783 (0.0009) -[2023-10-09 08:54:35,958][23468] Updated weights for policy 0, policy_version 15793 (0.0010) -[2023-10-09 08:54:36,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 32407552. Throughput: 0: 1759.5, 1: 1816.4. Samples: 8108992. Policy #0 lag: (min: 1.0, avg: 2.7, max: 29.0) -[2023-10-09 08:54:36,078][22500] Avg episode reward: [(0, '5.590'), (1, '5.720')] -[2023-10-09 08:54:36,328][23468] Updated weights for policy 0, policy_version 15803 (0.0010) -[2023-10-09 08:54:37,979][23469] Updated weights for policy 1, policy_version 15881 (0.0008) -[2023-10-09 08:54:38,347][23469] Updated weights for policy 1, policy_version 15891 (0.0008) -[2023-10-09 08:54:38,712][23469] Updated weights for policy 1, policy_version 15901 (0.0007) -[2023-10-09 08:54:40,139][23468] Updated weights for policy 0, policy_version 15813 (0.0010) -[2023-10-09 08:54:40,511][23468] Updated weights for policy 0, policy_version 15823 (0.0010) -[2023-10-09 08:54:40,874][23468] Updated weights for policy 0, policy_version 15833 (0.0010) -[2023-10-09 08:54:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 14218.0). Total num frames: 32473088. Throughput: 0: 1783.2, 1: 1801.8. Samples: 8130670. Policy #0 lag: (min: 2.0, avg: 13.8, max: 34.0) -[2023-10-09 08:54:41,078][22500] Avg episode reward: [(0, '6.170'), (1, '5.650')] -[2023-10-09 08:54:42,525][23469] Updated weights for policy 1, policy_version 15911 (0.0009) -[2023-10-09 08:54:42,900][23469] Updated weights for policy 1, policy_version 15921 (0.0008) -[2023-10-09 08:54:43,264][23469] Updated weights for policy 1, policy_version 15931 (0.0008) -[2023-10-09 08:54:44,574][23468] Updated weights for policy 0, policy_version 15843 (0.0009) -[2023-10-09 08:54:44,943][23468] Updated weights for policy 0, policy_version 15853 (0.0007) -[2023-10-09 08:54:45,313][23468] Updated weights for policy 0, policy_version 15863 (0.0010) -[2023-10-09 08:54:46,078][22500] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 32571392. Throughput: 0: 1778.5, 1: 1805.3. Samples: 8152330. Policy #0 lag: (min: 2.0, avg: 13.8, max: 34.0) -[2023-10-09 08:54:46,079][22500] Avg episode reward: [(0, '6.060'), (1, '5.060')] -[2023-10-09 08:54:46,998][23469] Updated weights for policy 1, policy_version 15941 (0.0008) -[2023-10-09 08:54:47,367][23469] Updated weights for policy 1, policy_version 15951 (0.0008) -[2023-10-09 08:54:47,737][23469] Updated weights for policy 1, policy_version 15961 (0.0009) -[2023-10-09 08:54:49,105][23468] Updated weights for policy 0, policy_version 15873 (0.0011) -[2023-10-09 08:54:49,484][23468] Updated weights for policy 0, policy_version 15883 (0.0011) -[2023-10-09 08:54:49,854][23468] Updated weights for policy 0, policy_version 15893 (0.0011) -[2023-10-09 08:54:50,231][23468] Updated weights for policy 0, policy_version 15903 (0.0011) -[2023-10-09 08:54:51,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 32636928. Throughput: 0: 1782.8, 1: 1804.4. Samples: 8163022. Policy #0 lag: (min: 7.0, avg: 30.1, max: 32.0) -[2023-10-09 08:54:51,078][22500] Avg episode reward: [(0, '6.050'), (1, '5.510')] -[2023-10-09 08:54:51,620][23469] Updated weights for policy 1, policy_version 15971 (0.0007) -[2023-10-09 08:54:51,990][23469] Updated weights for policy 1, policy_version 15981 (0.0007) -[2023-10-09 08:54:52,363][23469] Updated weights for policy 1, policy_version 15991 (0.0007) -[2023-10-09 08:54:53,903][23468] Updated weights for policy 0, policy_version 15913 (0.0010) -[2023-10-09 08:54:54,283][23468] Updated weights for policy 0, policy_version 15923 (0.0009) -[2023-10-09 08:54:54,652][23468] Updated weights for policy 0, policy_version 15933 (0.0008) -[2023-10-09 08:54:55,994][23469] Updated weights for policy 1, policy_version 16001 (0.0009) -[2023-10-09 08:54:56,078][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 32702464. Throughput: 0: 1785.4, 1: 1803.6. Samples: 8184508. Policy #0 lag: (min: 7.0, avg: 30.1, max: 32.0) -[2023-10-09 08:54:56,079][22500] Avg episode reward: [(0, '6.190'), (1, '5.660')] -[2023-10-09 08:54:56,360][23469] Updated weights for policy 1, policy_version 16011 (0.0008) -[2023-10-09 08:54:56,733][23469] Updated weights for policy 1, policy_version 16021 (0.0010) -[2023-10-09 08:54:57,112][23469] Updated weights for policy 1, policy_version 16031 (0.0010) -[2023-10-09 08:54:58,344][23468] Updated weights for policy 0, policy_version 15943 (0.0009) -[2023-10-09 08:54:58,708][23468] Updated weights for policy 0, policy_version 15953 (0.0007) -[2023-10-09 08:54:59,087][23468] Updated weights for policy 0, policy_version 15963 (0.0009) -[2023-10-09 08:55:00,833][23469] Updated weights for policy 1, policy_version 16041 (0.0009) -[2023-10-09 08:55:01,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.6, 300 sec: 14218.0). Total num frames: 32768000. Throughput: 0: 1773.7, 1: 1821.6. Samples: 8206042. Policy #0 lag: (min: 7.0, avg: 30.1, max: 32.0) -[2023-10-09 08:55:01,078][22500] Avg episode reward: [(0, '6.810'), (1, '6.060')] -[2023-10-09 08:55:01,212][23469] Updated weights for policy 1, policy_version 16051 (0.0008) -[2023-10-09 08:55:01,584][23469] Updated weights for policy 1, policy_version 16061 (0.0008) -[2023-10-09 08:55:02,847][23468] Updated weights for policy 0, policy_version 15973 (0.0011) -[2023-10-09 08:55:03,218][23468] Updated weights for policy 0, policy_version 15983 (0.0008) -[2023-10-09 08:55:03,591][23468] Updated weights for policy 0, policy_version 15993 (0.0009) -[2023-10-09 08:55:05,349][23469] Updated weights for policy 1, policy_version 16071 (0.0008) -[2023-10-09 08:55:05,714][23469] Updated weights for policy 1, policy_version 16081 (0.0011) -[2023-10-09 08:55:06,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 32833536. Throughput: 0: 1792.1, 1: 1802.5. Samples: 8216906. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-09 08:55:06,078][22500] Avg episode reward: [(0, '6.790'), (1, '5.830')] -[2023-10-09 08:55:06,085][23469] Updated weights for policy 1, policy_version 16091 (0.0008) -[2023-10-09 08:55:07,164][23468] Updated weights for policy 0, policy_version 16003 (0.0009) -[2023-10-09 08:55:07,538][23468] Updated weights for policy 0, policy_version 16013 (0.0008) -[2023-10-09 08:55:07,913][23468] Updated weights for policy 0, policy_version 16023 (0.0008) -[2023-10-09 08:55:09,740][23469] Updated weights for policy 1, policy_version 16101 (0.0007) -[2023-10-09 08:55:10,106][23469] Updated weights for policy 1, policy_version 16111 (0.0007) -[2023-10-09 08:55:10,483][23469] Updated weights for policy 1, policy_version 16121 (0.0010) -[2023-10-09 08:55:11,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 32931840. Throughput: 0: 1781.9, 1: 1814.8. Samples: 8238548. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-09 08:55:11,078][22500] Avg episode reward: [(0, '6.610'), (1, '5.840')] -[2023-10-09 08:55:11,675][23468] Updated weights for policy 0, policy_version 16033 (0.0007) -[2023-10-09 08:55:12,050][23468] Updated weights for policy 0, policy_version 16043 (0.0009) -[2023-10-09 08:55:12,423][23468] Updated weights for policy 0, policy_version 16053 (0.0008) -[2023-10-09 08:55:12,796][23468] Updated weights for policy 0, policy_version 16063 (0.0009) -[2023-10-09 08:55:14,215][23469] Updated weights for policy 1, policy_version 16131 (0.0009) -[2023-10-09 08:55:14,583][23469] Updated weights for policy 1, policy_version 16141 (0.0007) -[2023-10-09 08:55:14,953][23469] Updated weights for policy 1, policy_version 16151 (0.0010) -[2023-10-09 08:55:16,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 32997376. Throughput: 0: 1787.3, 1: 1797.1. Samples: 8259990. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-09 08:55:16,078][22500] Avg episode reward: [(0, '6.080'), (1, '5.550')] -[2023-10-09 08:55:16,607][23468] Updated weights for policy 0, policy_version 16073 (0.0008) -[2023-10-09 08:55:16,979][23468] Updated weights for policy 0, policy_version 16083 (0.0009) -[2023-10-09 08:55:17,354][23468] Updated weights for policy 0, policy_version 16093 (0.0008) -[2023-10-09 08:55:18,777][23469] Updated weights for policy 1, policy_version 16161 (0.0010) -[2023-10-09 08:55:19,144][23469] Updated weights for policy 1, policy_version 16171 (0.0008) -[2023-10-09 08:55:19,524][23469] Updated weights for policy 1, policy_version 16181 (0.0007) -[2023-10-09 08:55:19,888][23469] Updated weights for policy 1, policy_version 16191 (0.0008) -[2023-10-09 08:55:21,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 33062912. Throughput: 0: 1784.5, 1: 1813.2. Samples: 8270888. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-09 08:55:21,078][22500] Avg episode reward: [(0, '5.930'), (1, '5.690')] -[2023-10-09 08:55:21,175][23468] Updated weights for policy 0, policy_version 16103 (0.0008) -[2023-10-09 08:55:21,556][23468] Updated weights for policy 0, policy_version 16113 (0.0007) -[2023-10-09 08:55:21,930][23468] Updated weights for policy 0, policy_version 16123 (0.0008) -[2023-10-09 08:55:23,687][23469] Updated weights for policy 1, policy_version 16201 (0.0007) -[2023-10-09 08:55:24,063][23469] Updated weights for policy 1, policy_version 16211 (0.0007) -[2023-10-09 08:55:24,423][23469] Updated weights for policy 1, policy_version 16221 (0.0007) -[2023-10-09 08:55:25,582][23468] Updated weights for policy 0, policy_version 16133 (0.0010) -[2023-10-09 08:55:25,959][23468] Updated weights for policy 0, policy_version 16143 (0.0009) -[2023-10-09 08:55:26,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 33128448. Throughput: 0: 1785.4, 1: 1793.1. Samples: 8291700. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-09 08:55:26,079][22500] Avg episode reward: [(0, '5.790'), (1, '5.610')] -[2023-10-09 08:55:26,335][23468] Updated weights for policy 0, policy_version 16153 (0.0009) -[2023-10-09 08:55:28,161][23469] Updated weights for policy 1, policy_version 16231 (0.0010) -[2023-10-09 08:55:28,529][23469] Updated weights for policy 1, policy_version 16241 (0.0010) -[2023-10-09 08:55:28,905][23469] Updated weights for policy 1, policy_version 16251 (0.0009) -[2023-10-09 08:55:30,041][23468] Updated weights for policy 0, policy_version 16163 (0.0008) -[2023-10-09 08:55:30,407][23468] Updated weights for policy 0, policy_version 16173 (0.0009) -[2023-10-09 08:55:30,784][23468] Updated weights for policy 0, policy_version 16183 (0.0008) -[2023-10-09 08:55:31,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 33193984. Throughput: 0: 1797.5, 1: 1786.6. Samples: 8313612. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-09 08:55:31,079][22500] Avg episode reward: [(0, '5.820'), (1, '5.360')] -[2023-10-09 08:55:32,735][23469] Updated weights for policy 1, policy_version 16261 (0.0009) -[2023-10-09 08:55:33,093][23469] Updated weights for policy 1, policy_version 16271 (0.0011) -[2023-10-09 08:55:33,468][23469] Updated weights for policy 1, policy_version 16281 (0.0010) -[2023-10-09 08:55:34,477][23468] Updated weights for policy 0, policy_version 16193 (0.0009) -[2023-10-09 08:55:34,851][23468] Updated weights for policy 0, policy_version 16203 (0.0007) -[2023-10-09 08:55:35,225][23468] Updated weights for policy 0, policy_version 16213 (0.0009) -[2023-10-09 08:55:35,606][23468] Updated weights for policy 0, policy_version 16223 (0.0008) -[2023-10-09 08:55:36,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 33292288. Throughput: 0: 1786.4, 1: 1788.5. Samples: 8323894. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:55:36,078][22500] Avg episode reward: [(0, '5.880'), (1, '5.450')] -[2023-10-09 08:55:37,140][23469] Updated weights for policy 1, policy_version 16291 (0.0009) -[2023-10-09 08:55:37,511][23469] Updated weights for policy 1, policy_version 16301 (0.0008) -[2023-10-09 08:55:37,893][23469] Updated weights for policy 1, policy_version 16311 (0.0009) -[2023-10-09 08:55:39,573][23468] Updated weights for policy 0, policy_version 16233 (0.0008) -[2023-10-09 08:55:39,945][23468] Updated weights for policy 0, policy_version 16243 (0.0011) -[2023-10-09 08:55:40,317][23468] Updated weights for policy 0, policy_version 16253 (0.0011) -[2023-10-09 08:55:41,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 33357824. Throughput: 0: 1803.2, 1: 1789.7. Samples: 8346186. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:55:41,078][22500] Avg episode reward: [(0, '6.160'), (1, '5.630')] -[2023-10-09 08:55:41,675][23469] Updated weights for policy 1, policy_version 16321 (0.0009) -[2023-10-09 08:55:42,044][23469] Updated weights for policy 1, policy_version 16331 (0.0008) -[2023-10-09 08:55:42,409][23469] Updated weights for policy 1, policy_version 16341 (0.0007) -[2023-10-09 08:55:42,774][23469] Updated weights for policy 1, policy_version 16351 (0.0008) -[2023-10-09 08:55:43,939][23468] Updated weights for policy 0, policy_version 16263 (0.0011) -[2023-10-09 08:55:44,312][23468] Updated weights for policy 0, policy_version 16273 (0.0008) -[2023-10-09 08:55:44,681][23468] Updated weights for policy 0, policy_version 16283 (0.0010) -[2023-10-09 08:55:46,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 33423360. Throughput: 0: 1784.2, 1: 1794.1. Samples: 8367064. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 08:55:46,078][22500] Avg episode reward: [(0, '6.270'), (1, '5.670')] -[2023-10-09 08:55:46,474][23469] Updated weights for policy 1, policy_version 16361 (0.0008) -[2023-10-09 08:55:46,839][23469] Updated weights for policy 1, policy_version 16371 (0.0008) -[2023-10-09 08:55:47,209][23469] Updated weights for policy 1, policy_version 16381 (0.0008) -[2023-10-09 08:55:48,657][23468] Updated weights for policy 0, policy_version 16293 (0.0008) -[2023-10-09 08:55:49,032][23468] Updated weights for policy 0, policy_version 16303 (0.0010) -[2023-10-09 08:55:49,398][23468] Updated weights for policy 0, policy_version 16313 (0.0010) -[2023-10-09 08:55:51,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 33488896. Throughput: 0: 1799.3, 1: 1783.3. Samples: 8378122. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 08:55:51,078][22500] Avg episode reward: [(0, '6.110'), (1, '5.690')] -[2023-10-09 08:55:51,192][23469] Updated weights for policy 1, policy_version 16391 (0.0008) -[2023-10-09 08:55:51,579][23469] Updated weights for policy 1, policy_version 16401 (0.0010) -[2023-10-09 08:55:51,935][23469] Updated weights for policy 1, policy_version 16411 (0.0008) -[2023-10-09 08:55:53,185][23468] Updated weights for policy 0, policy_version 16323 (0.0010) -[2023-10-09 08:55:53,556][23468] Updated weights for policy 0, policy_version 16333 (0.0009) -[2023-10-09 08:55:53,941][23468] Updated weights for policy 0, policy_version 16343 (0.0008) -[2023-10-09 08:55:55,547][23469] Updated weights for policy 1, policy_version 16421 (0.0009) -[2023-10-09 08:55:55,909][23469] Updated weights for policy 1, policy_version 16431 (0.0008) -[2023-10-09 08:55:56,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 33554432. Throughput: 0: 1777.8, 1: 1783.2. Samples: 8398796. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 08:55:56,078][22500] Avg episode reward: [(0, '6.510'), (1, '5.340')] -[2023-10-09 08:55:56,273][23469] Updated weights for policy 1, policy_version 16441 (0.0009) -[2023-10-09 08:55:57,796][23468] Updated weights for policy 0, policy_version 16353 (0.0009) -[2023-10-09 08:55:58,180][23468] Updated weights for policy 0, policy_version 16363 (0.0010) -[2023-10-09 08:55:58,544][23468] Updated weights for policy 0, policy_version 16373 (0.0010) -[2023-10-09 08:55:58,916][23468] Updated weights for policy 0, policy_version 16383 (0.0007) -[2023-10-09 08:55:59,956][23469] Updated weights for policy 1, policy_version 16451 (0.0008) -[2023-10-09 08:56:00,333][23469] Updated weights for policy 1, policy_version 16461 (0.0008) -[2023-10-09 08:56:00,702][23469] Updated weights for policy 1, policy_version 16471 (0.0009) -[2023-10-09 08:56:01,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 33652736. Throughput: 0: 1772.5, 1: 1789.9. Samples: 8420298. Policy #0 lag: (min: 8.0, avg: 34.2, max: 40.0) -[2023-10-09 08:56:01,078][22500] Avg episode reward: [(0, '6.210'), (1, '5.600')] -[2023-10-09 08:56:02,782][23468] Updated weights for policy 0, policy_version 16393 (0.0009) -[2023-10-09 08:56:03,167][23468] Updated weights for policy 0, policy_version 16403 (0.0009) -[2023-10-09 08:56:03,543][23468] Updated weights for policy 0, policy_version 16413 (0.0008) -[2023-10-09 08:56:04,510][23469] Updated weights for policy 1, policy_version 16481 (0.0008) -[2023-10-09 08:56:04,884][23469] Updated weights for policy 1, policy_version 16491 (0.0007) -[2023-10-09 08:56:05,254][23469] Updated weights for policy 1, policy_version 16501 (0.0008) -[2023-10-09 08:56:05,615][23469] Updated weights for policy 1, policy_version 16511 (0.0009) -[2023-10-09 08:56:06,078][22500] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 33718272. Throughput: 0: 1783.3, 1: 1785.1. Samples: 8431466. Policy #0 lag: (min: 8.0, avg: 34.2, max: 40.0) -[2023-10-09 08:56:06,079][22500] Avg episode reward: [(0, '6.390'), (1, '6.080')] -[2023-10-09 08:56:07,313][23468] Updated weights for policy 0, policy_version 16423 (0.0009) -[2023-10-09 08:56:07,682][23468] Updated weights for policy 0, policy_version 16433 (0.0009) -[2023-10-09 08:56:08,053][23468] Updated weights for policy 0, policy_version 16443 (0.0008) -[2023-10-09 08:56:09,514][23469] Updated weights for policy 1, policy_version 16521 (0.0009) -[2023-10-09 08:56:09,884][23469] Updated weights for policy 1, policy_version 16531 (0.0008) -[2023-10-09 08:56:10,253][23469] Updated weights for policy 1, policy_version 16541 (0.0009) -[2023-10-09 08:56:11,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 33783808. Throughput: 0: 1767.9, 1: 1798.2. Samples: 8452172. Policy #0 lag: (min: 8.0, avg: 34.2, max: 40.0) -[2023-10-09 08:56:11,078][22500] Avg episode reward: [(0, '6.250'), (1, '5.970')] -[2023-10-09 08:56:11,731][23468] Updated weights for policy 0, policy_version 16453 (0.0009) -[2023-10-09 08:56:12,117][23468] Updated weights for policy 0, policy_version 16463 (0.0010) -[2023-10-09 08:56:12,489][23468] Updated weights for policy 0, policy_version 16473 (0.0009) -[2023-10-09 08:56:14,003][23469] Updated weights for policy 1, policy_version 16551 (0.0008) -[2023-10-09 08:56:14,374][23469] Updated weights for policy 1, policy_version 16561 (0.0007) -[2023-10-09 08:56:14,749][23469] Updated weights for policy 1, policy_version 16571 (0.0010) -[2023-10-09 08:56:16,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 33849344. Throughput: 0: 1781.9, 1: 1782.0. Samples: 8473988. Policy #0 lag: (min: 6.0, avg: 14.2, max: 38.0) -[2023-10-09 08:56:16,078][22500] Avg episode reward: [(0, '6.470'), (1, '5.690')] -[2023-10-09 08:56:16,086][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000016576_16973824.pth... -[2023-10-09 08:56:16,127][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000014912_15269888.pth -[2023-10-09 08:56:16,133][23343] Saving a milestone ./train_atari/atari_berzerk_APPO/checkpoint_p1/milestones/checkpoint_000016576_16973824.pth -[2023-10-09 08:56:16,267][23468] Updated weights for policy 0, policy_version 16483 (0.0007) -[2023-10-09 08:56:16,645][23468] Updated weights for policy 0, policy_version 16493 (0.0008) -[2023-10-09 08:56:17,020][23468] Updated weights for policy 0, policy_version 16503 (0.0008) -[2023-10-09 08:56:17,348][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000016512_16908288.pth... -[2023-10-09 08:56:17,377][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000014816_15171584.pth -[2023-10-09 08:56:17,381][23265] Saving a milestone ./train_atari/atari_berzerk_APPO/checkpoint_p0/milestones/checkpoint_000016512_16908288.pth -[2023-10-09 08:56:18,462][23469] Updated weights for policy 1, policy_version 16581 (0.0008) -[2023-10-09 08:56:18,827][23469] Updated weights for policy 1, policy_version 16591 (0.0008) -[2023-10-09 08:56:19,203][23469] Updated weights for policy 1, policy_version 16601 (0.0008) -[2023-10-09 08:56:20,642][23468] Updated weights for policy 0, policy_version 16513 (0.0009) -[2023-10-09 08:56:21,011][23468] Updated weights for policy 0, policy_version 16523 (0.0009) -[2023-10-09 08:56:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 33914880. Throughput: 0: 1769.9, 1: 1802.2. Samples: 8484640. Policy #0 lag: (min: 6.0, avg: 14.2, max: 38.0) -[2023-10-09 08:56:21,078][22500] Avg episode reward: [(0, '6.390'), (1, '5.210')] -[2023-10-09 08:56:21,383][23468] Updated weights for policy 0, policy_version 16533 (0.0007) -[2023-10-09 08:56:21,756][23468] Updated weights for policy 0, policy_version 16543 (0.0009) -[2023-10-09 08:56:22,864][23469] Updated weights for policy 1, policy_version 16611 (0.0009) -[2023-10-09 08:56:23,244][23469] Updated weights for policy 1, policy_version 16621 (0.0008) -[2023-10-09 08:56:23,607][23469] Updated weights for policy 1, policy_version 16631 (0.0009) -[2023-10-09 08:56:25,639][23468] Updated weights for policy 0, policy_version 16553 (0.0009) -[2023-10-09 08:56:26,009][23468] Updated weights for policy 0, policy_version 16563 (0.0008) -[2023-10-09 08:56:26,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 33980416. Throughput: 0: 1777.6, 1: 1781.9. Samples: 8506364. Policy #0 lag: (min: 6.0, avg: 14.2, max: 38.0) -[2023-10-09 08:56:26,078][22500] Avg episode reward: [(0, '6.390'), (1, '5.170')] -[2023-10-09 08:56:26,386][23468] Updated weights for policy 0, policy_version 16573 (0.0008) -[2023-10-09 08:56:27,265][23469] Updated weights for policy 1, policy_version 16641 (0.0010) -[2023-10-09 08:56:27,641][23469] Updated weights for policy 1, policy_version 16651 (0.0009) -[2023-10-09 08:56:28,018][23469] Updated weights for policy 1, policy_version 16661 (0.0008) -[2023-10-09 08:56:28,387][23469] Updated weights for policy 1, policy_version 16671 (0.0008) -[2023-10-09 08:56:30,181][23468] Updated weights for policy 0, policy_version 16583 (0.0009) -[2023-10-09 08:56:30,548][23468] Updated weights for policy 0, policy_version 16593 (0.0008) -[2023-10-09 08:56:30,931][23468] Updated weights for policy 0, policy_version 16603 (0.0010) -[2023-10-09 08:56:31,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 34045952. Throughput: 0: 1799.6, 1: 1785.6. Samples: 8528396. Policy #0 lag: (min: 9.0, avg: 17.9, max: 41.0) -[2023-10-09 08:56:31,078][22500] Avg episode reward: [(0, '6.300'), (1, '5.350')] -[2023-10-09 08:56:32,110][23469] Updated weights for policy 1, policy_version 16681 (0.0009) -[2023-10-09 08:56:32,483][23469] Updated weights for policy 1, policy_version 16691 (0.0007) -[2023-10-09 08:56:32,855][23469] Updated weights for policy 1, policy_version 16701 (0.0010) -[2023-10-09 08:56:34,589][23468] Updated weights for policy 0, policy_version 16613 (0.0009) -[2023-10-09 08:56:34,963][23468] Updated weights for policy 0, policy_version 16623 (0.0010) -[2023-10-09 08:56:35,343][23468] Updated weights for policy 0, policy_version 16633 (0.0010) -[2023-10-09 08:56:36,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 34144256. Throughput: 0: 1778.4, 1: 1789.6. Samples: 8538680. Policy #0 lag: (min: 9.0, avg: 17.9, max: 41.0) -[2023-10-09 08:56:36,078][22500] Avg episode reward: [(0, '6.080'), (1, '5.400')] -[2023-10-09 08:56:36,668][23469] Updated weights for policy 1, policy_version 16711 (0.0008) -[2023-10-09 08:56:37,054][23469] Updated weights for policy 1, policy_version 16721 (0.0007) -[2023-10-09 08:56:37,426][23469] Updated weights for policy 1, policy_version 16731 (0.0009) -[2023-10-09 08:56:39,112][23468] Updated weights for policy 0, policy_version 16643 (0.0007) -[2023-10-09 08:56:39,485][23468] Updated weights for policy 0, policy_version 16653 (0.0008) -[2023-10-09 08:56:39,861][23468] Updated weights for policy 0, policy_version 16663 (0.0007) -[2023-10-09 08:56:40,997][23469] Updated weights for policy 1, policy_version 16741 (0.0009) -[2023-10-09 08:56:41,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 34209792. Throughput: 0: 1805.1, 1: 1790.6. Samples: 8560604. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 08:56:41,078][22500] Avg episode reward: [(0, '6.280'), (1, '5.720')] -[2023-10-09 08:56:41,366][23469] Updated weights for policy 1, policy_version 16751 (0.0008) -[2023-10-09 08:56:41,746][23469] Updated weights for policy 1, policy_version 16761 (0.0009) -[2023-10-09 08:56:43,610][23468] Updated weights for policy 0, policy_version 16673 (0.0008) -[2023-10-09 08:56:43,981][23468] Updated weights for policy 0, policy_version 16683 (0.0010) -[2023-10-09 08:56:44,360][23468] Updated weights for policy 0, policy_version 16693 (0.0009) -[2023-10-09 08:56:44,738][23468] Updated weights for policy 0, policy_version 16703 (0.0007) -[2023-10-09 08:56:45,557][23469] Updated weights for policy 1, policy_version 16771 (0.0010) -[2023-10-09 08:56:45,920][23469] Updated weights for policy 1, policy_version 16781 (0.0007) -[2023-10-09 08:56:46,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 34275328. Throughput: 0: 1778.8, 1: 1802.4. Samples: 8581454. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 08:56:46,078][22500] Avg episode reward: [(0, '6.550'), (1, '5.670')] -[2023-10-09 08:56:46,287][23469] Updated weights for policy 1, policy_version 16791 (0.0007) -[2023-10-09 08:56:48,545][23468] Updated weights for policy 0, policy_version 16713 (0.0009) -[2023-10-09 08:56:48,925][23468] Updated weights for policy 0, policy_version 16723 (0.0009) -[2023-10-09 08:56:49,318][23468] Updated weights for policy 0, policy_version 16733 (0.0009) -[2023-10-09 08:56:49,986][23469] Updated weights for policy 1, policy_version 16801 (0.0009) -[2023-10-09 08:56:50,351][23469] Updated weights for policy 1, policy_version 16811 (0.0008) -[2023-10-09 08:56:50,729][23469] Updated weights for policy 1, policy_version 16821 (0.0009) -[2023-10-09 08:56:51,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 34340864. Throughput: 0: 1808.8, 1: 1785.4. Samples: 8593204. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 08:56:51,078][22500] Avg episode reward: [(0, '6.370'), (1, '5.720')] -[2023-10-09 08:56:51,108][23469] Updated weights for policy 1, policy_version 16831 (0.0007) -[2023-10-09 08:56:53,080][23468] Updated weights for policy 0, policy_version 16743 (0.0008) -[2023-10-09 08:56:53,453][23468] Updated weights for policy 0, policy_version 16753 (0.0011) -[2023-10-09 08:56:53,822][23468] Updated weights for policy 0, policy_version 16763 (0.0008) -[2023-10-09 08:56:54,901][23469] Updated weights for policy 1, policy_version 16841 (0.0007) -[2023-10-09 08:56:55,270][23469] Updated weights for policy 1, policy_version 16851 (0.0008) -[2023-10-09 08:56:55,635][23469] Updated weights for policy 1, policy_version 16861 (0.0010) -[2023-10-09 08:56:56,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 34439168. Throughput: 0: 1792.2, 1: 1801.3. Samples: 8613880. Policy #0 lag: (min: 31.0, avg: 32.0, max: 52.0) -[2023-10-09 08:56:56,078][22500] Avg episode reward: [(0, '6.400'), (1, '5.860')] -[2023-10-09 08:56:57,356][23468] Updated weights for policy 0, policy_version 16773 (0.0009) -[2023-10-09 08:56:57,729][23468] Updated weights for policy 0, policy_version 16783 (0.0008) -[2023-10-09 08:56:58,092][23468] Updated weights for policy 0, policy_version 16793 (0.0008) -[2023-10-09 08:56:59,272][23469] Updated weights for policy 1, policy_version 16871 (0.0008) -[2023-10-09 08:56:59,643][23469] Updated weights for policy 1, policy_version 16881 (0.0009) -[2023-10-09 08:57:00,015][23469] Updated weights for policy 1, policy_version 16891 (0.0010) -[2023-10-09 08:57:01,078][22500] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 34504704. Throughput: 0: 1791.3, 1: 1797.8. Samples: 8635500. Policy #0 lag: (min: 31.0, avg: 32.0, max: 52.0) -[2023-10-09 08:57:01,079][22500] Avg episode reward: [(0, '6.200'), (1, '5.630')] -[2023-10-09 08:57:01,896][23468] Updated weights for policy 0, policy_version 16803 (0.0008) -[2023-10-09 08:57:02,269][23468] Updated weights for policy 0, policy_version 16813 (0.0008) -[2023-10-09 08:57:02,638][23468] Updated weights for policy 0, policy_version 16823 (0.0009) -[2023-10-09 08:57:03,691][23469] Updated weights for policy 1, policy_version 16901 (0.0009) -[2023-10-09 08:57:04,055][23469] Updated weights for policy 1, policy_version 16911 (0.0007) -[2023-10-09 08:57:04,427][23469] Updated weights for policy 1, policy_version 16921 (0.0007) -[2023-10-09 08:57:06,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 34570240. Throughput: 0: 1790.4, 1: 1803.3. Samples: 8646356. Policy #0 lag: (min: 31.0, avg: 32.0, max: 52.0) -[2023-10-09 08:57:06,078][22500] Avg episode reward: [(0, '6.450'), (1, '5.420')] -[2023-10-09 08:57:06,349][23468] Updated weights for policy 0, policy_version 16833 (0.0009) -[2023-10-09 08:57:06,717][23468] Updated weights for policy 0, policy_version 16843 (0.0008) -[2023-10-09 08:57:07,085][23468] Updated weights for policy 0, policy_version 16853 (0.0008) -[2023-10-09 08:57:07,458][23468] Updated weights for policy 0, policy_version 16863 (0.0011) -[2023-10-09 08:57:08,373][23469] Updated weights for policy 1, policy_version 16931 (0.0007) -[2023-10-09 08:57:08,742][23469] Updated weights for policy 1, policy_version 16941 (0.0009) -[2023-10-09 08:57:09,116][23469] Updated weights for policy 1, policy_version 16951 (0.0008) -[2023-10-09 08:57:11,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 34635776. Throughput: 0: 1786.3, 1: 1794.9. Samples: 8667518. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-09 08:57:11,078][22500] Avg episode reward: [(0, '6.280'), (1, '5.440')] -[2023-10-09 08:57:11,236][23468] Updated weights for policy 0, policy_version 16873 (0.0011) -[2023-10-09 08:57:11,609][23468] Updated weights for policy 0, policy_version 16883 (0.0008) -[2023-10-09 08:57:11,988][23468] Updated weights for policy 0, policy_version 16893 (0.0008) -[2023-10-09 08:57:12,857][23469] Updated weights for policy 1, policy_version 16961 (0.0008) -[2023-10-09 08:57:13,218][23469] Updated weights for policy 1, policy_version 16971 (0.0008) -[2023-10-09 08:57:13,594][23469] Updated weights for policy 1, policy_version 16981 (0.0007) -[2023-10-09 08:57:13,955][23469] Updated weights for policy 1, policy_version 16991 (0.0008) -[2023-10-09 08:57:15,788][23468] Updated weights for policy 0, policy_version 16903 (0.0007) -[2023-10-09 08:57:16,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 34701312. Throughput: 0: 1798.5, 1: 1789.8. Samples: 8689868. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-09 08:57:16,079][22500] Avg episode reward: [(0, '6.150'), (1, '5.930')] -[2023-10-09 08:57:16,151][23468] Updated weights for policy 0, policy_version 16913 (0.0007) -[2023-10-09 08:57:16,529][23468] Updated weights for policy 0, policy_version 16923 (0.0008) -[2023-10-09 08:57:17,733][23469] Updated weights for policy 1, policy_version 17001 (0.0009) -[2023-10-09 08:57:18,102][23469] Updated weights for policy 1, policy_version 17011 (0.0008) -[2023-10-09 08:57:18,473][23469] Updated weights for policy 1, policy_version 17021 (0.0009) -[2023-10-09 08:57:20,164][23468] Updated weights for policy 0, policy_version 16933 (0.0009) -[2023-10-09 08:57:20,534][23468] Updated weights for policy 0, policy_version 16943 (0.0008) -[2023-10-09 08:57:20,911][23468] Updated weights for policy 0, policy_version 16953 (0.0007) -[2023-10-09 08:57:21,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 34766848. Throughput: 0: 1790.4, 1: 1789.8. Samples: 8699790. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-09 08:57:21,078][22500] Avg episode reward: [(0, '6.200'), (1, '5.890')] -[2023-10-09 08:57:22,409][23469] Updated weights for policy 1, policy_version 17031 (0.0010) -[2023-10-09 08:57:22,774][23469] Updated weights for policy 1, policy_version 17041 (0.0009) -[2023-10-09 08:57:23,145][23469] Updated weights for policy 1, policy_version 17051 (0.0007) -[2023-10-09 08:57:24,697][23468] Updated weights for policy 0, policy_version 16963 (0.0009) -[2023-10-09 08:57:25,074][23468] Updated weights for policy 0, policy_version 16973 (0.0008) -[2023-10-09 08:57:25,452][23468] Updated weights for policy 0, policy_version 16983 (0.0010) -[2023-10-09 08:57:26,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 34865152. Throughput: 0: 1801.4, 1: 1789.5. Samples: 8722194. Policy #0 lag: (min: 12.0, avg: 13.6, max: 38.0) -[2023-10-09 08:57:26,078][22500] Avg episode reward: [(0, '6.590'), (1, '5.780')] -[2023-10-09 08:57:27,135][23469] Updated weights for policy 1, policy_version 17061 (0.0008) -[2023-10-09 08:57:27,549][23469] Updated weights for policy 1, policy_version 17071 (0.0009) -[2023-10-09 08:57:27,912][23469] Updated weights for policy 1, policy_version 17081 (0.0010) -[2023-10-09 08:57:29,015][23468] Updated weights for policy 0, policy_version 16993 (0.0007) -[2023-10-09 08:57:29,395][23468] Updated weights for policy 0, policy_version 17003 (0.0010) -[2023-10-09 08:57:29,778][23468] Updated weights for policy 0, policy_version 17013 (0.0010) -[2023-10-09 08:57:30,151][23468] Updated weights for policy 0, policy_version 17023 (0.0010) -[2023-10-09 08:57:31,078][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 34930688. Throughput: 0: 1789.8, 1: 1789.7. Samples: 8742532. Policy #0 lag: (min: 12.0, avg: 13.6, max: 38.0) -[2023-10-09 08:57:31,079][22500] Avg episode reward: [(0, '6.210'), (1, '5.920')] -[2023-10-09 08:57:31,528][23469] Updated weights for policy 1, policy_version 17091 (0.0008) -[2023-10-09 08:57:31,899][23469] Updated weights for policy 1, policy_version 17101 (0.0007) -[2023-10-09 08:57:32,273][23469] Updated weights for policy 1, policy_version 17111 (0.0007) -[2023-10-09 08:57:34,040][23468] Updated weights for policy 0, policy_version 17033 (0.0009) -[2023-10-09 08:57:34,405][23468] Updated weights for policy 0, policy_version 17043 (0.0010) -[2023-10-09 08:57:34,788][23468] Updated weights for policy 0, policy_version 17053 (0.0011) -[2023-10-09 08:57:35,970][23469] Updated weights for policy 1, policy_version 17121 (0.0008) -[2023-10-09 08:57:36,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 34996224. Throughput: 0: 1793.7, 1: 1775.2. Samples: 8753808. Policy #0 lag: (min: 23.0, avg: 30.2, max: 55.0) -[2023-10-09 08:57:36,078][22500] Avg episode reward: [(0, '5.880'), (1, '6.120')] -[2023-10-09 08:57:36,338][23469] Updated weights for policy 1, policy_version 17131 (0.0010) -[2023-10-09 08:57:36,706][23469] Updated weights for policy 1, policy_version 17141 (0.0008) -[2023-10-09 08:57:37,079][23469] Updated weights for policy 1, policy_version 17151 (0.0009) -[2023-10-09 08:57:38,595][23468] Updated weights for policy 0, policy_version 17063 (0.0010) -[2023-10-09 08:57:38,970][23468] Updated weights for policy 0, policy_version 17073 (0.0009) -[2023-10-09 08:57:39,347][23468] Updated weights for policy 0, policy_version 17083 (0.0009) -[2023-10-09 08:57:40,942][23469] Updated weights for policy 1, policy_version 17161 (0.0008) -[2023-10-09 08:57:41,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 35061760. Throughput: 0: 1790.7, 1: 1787.3. Samples: 8774888. Policy #0 lag: (min: 23.0, avg: 30.2, max: 55.0) -[2023-10-09 08:57:41,078][22500] Avg episode reward: [(0, '6.290'), (1, '6.030')] -[2023-10-09 08:57:41,311][23469] Updated weights for policy 1, policy_version 17171 (0.0007) -[2023-10-09 08:57:41,679][23469] Updated weights for policy 1, policy_version 17181 (0.0008) -[2023-10-09 08:57:43,259][23468] Updated weights for policy 0, policy_version 17093 (0.0008) -[2023-10-09 08:57:43,631][23468] Updated weights for policy 0, policy_version 17103 (0.0007) -[2023-10-09 08:57:44,009][23468] Updated weights for policy 0, policy_version 17113 (0.0008) -[2023-10-09 08:57:45,353][23469] Updated weights for policy 1, policy_version 17191 (0.0008) -[2023-10-09 08:57:45,715][23469] Updated weights for policy 1, policy_version 17201 (0.0008) -[2023-10-09 08:57:46,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 35127296. Throughput: 0: 1775.7, 1: 1793.6. Samples: 8796118. Policy #0 lag: (min: 23.0, avg: 30.2, max: 55.0) -[2023-10-09 08:57:46,078][22500] Avg episode reward: [(0, '6.370'), (1, '6.300')] -[2023-10-09 08:57:46,082][23469] Updated weights for policy 1, policy_version 17211 (0.0009) -[2023-10-09 08:57:46,269][23343] Saving new best policy, reward=6.300! -[2023-10-09 08:57:47,718][23468] Updated weights for policy 0, policy_version 17123 (0.0009) -[2023-10-09 08:57:48,083][23468] Updated weights for policy 0, policy_version 17133 (0.0008) -[2023-10-09 08:57:48,460][23468] Updated weights for policy 0, policy_version 17143 (0.0010) -[2023-10-09 08:57:49,887][23469] Updated weights for policy 1, policy_version 17221 (0.0008) -[2023-10-09 08:57:50,253][23469] Updated weights for policy 1, policy_version 17231 (0.0009) -[2023-10-09 08:57:50,629][23469] Updated weights for policy 1, policy_version 17241 (0.0010) -[2023-10-09 08:57:51,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 35225600. Throughput: 0: 1798.0, 1: 1781.6. Samples: 8807438. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-09 08:57:51,078][22500] Avg episode reward: [(0, '6.740'), (1, '6.180')] -[2023-10-09 08:57:52,272][23468] Updated weights for policy 0, policy_version 17153 (0.0008) -[2023-10-09 08:57:52,643][23468] Updated weights for policy 0, policy_version 17163 (0.0007) -[2023-10-09 08:57:53,013][23468] Updated weights for policy 0, policy_version 17173 (0.0007) -[2023-10-09 08:57:53,390][23468] Updated weights for policy 0, policy_version 17183 (0.0009) -[2023-10-09 08:57:54,495][23469] Updated weights for policy 1, policy_version 17251 (0.0009) -[2023-10-09 08:57:54,864][23469] Updated weights for policy 1, policy_version 17261 (0.0008) -[2023-10-09 08:57:55,239][23469] Updated weights for policy 1, policy_version 17271 (0.0008) -[2023-10-09 08:57:56,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 35291136. Throughput: 0: 1780.1, 1: 1791.8. Samples: 8828256. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-09 08:57:56,079][22500] Avg episode reward: [(0, '6.620'), (1, '6.250')] -[2023-10-09 08:57:57,123][23468] Updated weights for policy 0, policy_version 17193 (0.0007) -[2023-10-09 08:57:57,507][23468] Updated weights for policy 0, policy_version 17203 (0.0007) -[2023-10-09 08:57:57,885][23468] Updated weights for policy 0, policy_version 17213 (0.0008) -[2023-10-09 08:57:58,916][23469] Updated weights for policy 1, policy_version 17281 (0.0009) -[2023-10-09 08:57:59,296][23469] Updated weights for policy 1, policy_version 17291 (0.0010) -[2023-10-09 08:57:59,664][23469] Updated weights for policy 1, policy_version 17301 (0.0011) -[2023-10-09 08:58:00,038][23469] Updated weights for policy 1, policy_version 17311 (0.0007) -[2023-10-09 08:58:01,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 35356672. Throughput: 0: 1780.1, 1: 1768.9. Samples: 8849576. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-09 08:58:01,079][22500] Avg episode reward: [(0, '6.540'), (1, '6.210')] -[2023-10-09 08:58:01,584][23468] Updated weights for policy 0, policy_version 17223 (0.0008) -[2023-10-09 08:58:01,951][23468] Updated weights for policy 0, policy_version 17233 (0.0008) -[2023-10-09 08:58:02,335][23468] Updated weights for policy 0, policy_version 17243 (0.0007) -[2023-10-09 08:58:03,913][23469] Updated weights for policy 1, policy_version 17321 (0.0011) -[2023-10-09 08:58:04,284][23469] Updated weights for policy 1, policy_version 17331 (0.0009) -[2023-10-09 08:58:04,650][23469] Updated weights for policy 1, policy_version 17341 (0.0007) -[2023-10-09 08:58:06,074][23468] Updated weights for policy 0, policy_version 17253 (0.0008) -[2023-10-09 08:58:06,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 35422208. Throughput: 0: 1775.5, 1: 1793.6. Samples: 8860398. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-09 08:58:06,078][22500] Avg episode reward: [(0, '6.090'), (1, '5.710')] -[2023-10-09 08:58:06,452][23468] Updated weights for policy 0, policy_version 17263 (0.0008) -[2023-10-09 08:58:06,824][23468] Updated weights for policy 0, policy_version 17273 (0.0007) -[2023-10-09 08:58:08,337][23469] Updated weights for policy 1, policy_version 17351 (0.0007) -[2023-10-09 08:58:08,706][23469] Updated weights for policy 1, policy_version 17361 (0.0007) -[2023-10-09 08:58:09,071][23469] Updated weights for policy 1, policy_version 17371 (0.0009) -[2023-10-09 08:58:10,511][23468] Updated weights for policy 0, policy_version 17283 (0.0009) -[2023-10-09 08:58:10,878][23468] Updated weights for policy 0, policy_version 17293 (0.0008) -[2023-10-09 08:58:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 35487744. Throughput: 0: 1773.2, 1: 1770.9. Samples: 8881682. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-09 08:58:11,078][22500] Avg episode reward: [(0, '5.890'), (1, '5.450')] -[2023-10-09 08:58:11,261][23468] Updated weights for policy 0, policy_version 17303 (0.0009) -[2023-10-09 08:58:12,854][23469] Updated weights for policy 1, policy_version 17381 (0.0009) -[2023-10-09 08:58:13,255][23469] Updated weights for policy 1, policy_version 17391 (0.0007) -[2023-10-09 08:58:13,630][23469] Updated weights for policy 1, policy_version 17401 (0.0008) -[2023-10-09 08:58:15,159][23468] Updated weights for policy 0, policy_version 17313 (0.0009) -[2023-10-09 08:58:15,527][23468] Updated weights for policy 0, policy_version 17323 (0.0009) -[2023-10-09 08:58:15,908][23468] Updated weights for policy 0, policy_version 17333 (0.0007) -[2023-10-09 08:58:16,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 35553280. Throughput: 0: 1799.7, 1: 1772.3. Samples: 8903272. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-09 08:58:16,079][22500] Avg episode reward: [(0, '5.910'), (1, '5.430')] -[2023-10-09 08:58:16,090][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000017408_17825792.pth... -[2023-10-09 08:58:16,120][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000015744_16121856.pth -[2023-10-09 08:58:16,288][23468] Updated weights for policy 0, policy_version 17343 (0.0009) -[2023-10-09 08:58:16,324][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000017344_17760256.pth... -[2023-10-09 08:58:16,353][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000015648_16023552.pth -[2023-10-09 08:58:17,587][23469] Updated weights for policy 1, policy_version 17411 (0.0009) -[2023-10-09 08:58:17,963][23469] Updated weights for policy 1, policy_version 17421 (0.0011) -[2023-10-09 08:58:18,328][23469] Updated weights for policy 1, policy_version 17431 (0.0010) -[2023-10-09 08:58:20,003][23468] Updated weights for policy 0, policy_version 17353 (0.0009) -[2023-10-09 08:58:20,373][23468] Updated weights for policy 0, policy_version 17363 (0.0008) -[2023-10-09 08:58:20,742][23468] Updated weights for policy 0, policy_version 17373 (0.0007) -[2023-10-09 08:58:21,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 35651584. Throughput: 0: 1766.3, 1: 1774.6. Samples: 8913148. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 08:58:21,078][22500] Avg episode reward: [(0, '5.870'), (1, '5.750')] -[2023-10-09 08:58:22,268][23469] Updated weights for policy 1, policy_version 17441 (0.0007) -[2023-10-09 08:58:22,649][23469] Updated weights for policy 1, policy_version 17451 (0.0007) -[2023-10-09 08:58:23,014][23469] Updated weights for policy 1, policy_version 17461 (0.0007) -[2023-10-09 08:58:23,393][23469] Updated weights for policy 1, policy_version 17471 (0.0008) -[2023-10-09 08:58:24,578][23468] Updated weights for policy 0, policy_version 17383 (0.0008) -[2023-10-09 08:58:24,946][23468] Updated weights for policy 0, policy_version 17393 (0.0007) -[2023-10-09 08:58:25,316][23468] Updated weights for policy 0, policy_version 17403 (0.0009) -[2023-10-09 08:58:26,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 35717120. Throughput: 0: 1800.9, 1: 1767.2. Samples: 8935454. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 08:58:26,078][22500] Avg episode reward: [(0, '6.220'), (1, '5.430')] -[2023-10-09 08:58:27,062][23469] Updated weights for policy 1, policy_version 17481 (0.0009) -[2023-10-09 08:58:27,441][23469] Updated weights for policy 1, policy_version 17491 (0.0011) -[2023-10-09 08:58:27,811][23469] Updated weights for policy 1, policy_version 17501 (0.0010) -[2023-10-09 08:58:29,026][23468] Updated weights for policy 0, policy_version 17413 (0.0010) -[2023-10-09 08:58:29,399][23468] Updated weights for policy 0, policy_version 17423 (0.0009) -[2023-10-09 08:58:29,778][23468] Updated weights for policy 0, policy_version 17433 (0.0007) -[2023-10-09 08:58:31,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 35782656. Throughput: 0: 1778.8, 1: 1789.7. Samples: 8956696. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:58:31,078][22500] Avg episode reward: [(0, '6.450'), (1, '5.790')] -[2023-10-09 08:58:31,426][23469] Updated weights for policy 1, policy_version 17511 (0.0007) -[2023-10-09 08:58:31,799][23469] Updated weights for policy 1, policy_version 17521 (0.0009) -[2023-10-09 08:58:32,171][23469] Updated weights for policy 1, policy_version 17531 (0.0007) -[2023-10-09 08:58:33,547][23468] Updated weights for policy 0, policy_version 17443 (0.0009) -[2023-10-09 08:58:33,914][23468] Updated weights for policy 0, policy_version 17453 (0.0009) -[2023-10-09 08:58:34,296][23468] Updated weights for policy 0, policy_version 17463 (0.0009) -[2023-10-09 08:58:35,810][23469] Updated weights for policy 1, policy_version 17541 (0.0007) -[2023-10-09 08:58:36,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 35848192. Throughput: 0: 1793.5, 1: 1773.3. Samples: 8967944. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:58:36,078][22500] Avg episode reward: [(0, '6.460'), (1, '6.170')] -[2023-10-09 08:58:36,186][23469] Updated weights for policy 1, policy_version 17551 (0.0008) -[2023-10-09 08:58:36,545][23469] Updated weights for policy 1, policy_version 17561 (0.0009) -[2023-10-09 08:58:37,896][23468] Updated weights for policy 0, policy_version 17473 (0.0007) -[2023-10-09 08:58:38,257][23468] Updated weights for policy 0, policy_version 17483 (0.0008) -[2023-10-09 08:58:38,639][23468] Updated weights for policy 0, policy_version 17493 (0.0008) -[2023-10-09 08:58:39,018][23468] Updated weights for policy 0, policy_version 17503 (0.0008) -[2023-10-09 08:58:40,268][23469] Updated weights for policy 1, policy_version 17571 (0.0008) -[2023-10-09 08:58:40,633][23469] Updated weights for policy 1, policy_version 17581 (0.0007) -[2023-10-09 08:58:40,996][23469] Updated weights for policy 1, policy_version 17591 (0.0008) -[2023-10-09 08:58:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 35913728. Throughput: 0: 1781.5, 1: 1790.8. Samples: 8989006. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:58:41,078][22500] Avg episode reward: [(0, '6.370'), (1, '5.760')] -[2023-10-09 08:58:42,973][23468] Updated weights for policy 0, policy_version 17513 (0.0010) -[2023-10-09 08:58:43,343][23468] Updated weights for policy 0, policy_version 17523 (0.0009) -[2023-10-09 08:58:43,715][23468] Updated weights for policy 0, policy_version 17533 (0.0008) -[2023-10-09 08:58:44,553][23469] Updated weights for policy 1, policy_version 17601 (0.0010) -[2023-10-09 08:58:44,933][23469] Updated weights for policy 1, policy_version 17611 (0.0007) -[2023-10-09 08:58:45,298][23469] Updated weights for policy 1, policy_version 17621 (0.0007) -[2023-10-09 08:58:45,675][23469] Updated weights for policy 1, policy_version 17631 (0.0007) -[2023-10-09 08:58:46,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 36012032. Throughput: 0: 1774.8, 1: 1788.8. Samples: 9009938. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-09 08:58:46,078][22500] Avg episode reward: [(0, '6.690'), (1, '5.810')] -[2023-10-09 08:58:47,489][23468] Updated weights for policy 0, policy_version 17543 (0.0008) -[2023-10-09 08:58:47,871][23468] Updated weights for policy 0, policy_version 17553 (0.0011) -[2023-10-09 08:58:48,249][23468] Updated weights for policy 0, policy_version 17563 (0.0009) -[2023-10-09 08:58:49,420][23469] Updated weights for policy 1, policy_version 17641 (0.0007) -[2023-10-09 08:58:49,787][23469] Updated weights for policy 1, policy_version 17651 (0.0007) -[2023-10-09 08:58:50,164][23469] Updated weights for policy 1, policy_version 17661 (0.0009) -[2023-10-09 08:58:51,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 36077568. Throughput: 0: 1780.1, 1: 1798.3. Samples: 9021428. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-09 08:58:51,078][22500] Avg episode reward: [(0, '6.560'), (1, '5.960')] -[2023-10-09 08:58:52,039][23468] Updated weights for policy 0, policy_version 17573 (0.0008) -[2023-10-09 08:58:52,413][23468] Updated weights for policy 0, policy_version 17583 (0.0009) -[2023-10-09 08:58:52,777][23468] Updated weights for policy 0, policy_version 17593 (0.0009) -[2023-10-09 08:58:53,999][23469] Updated weights for policy 1, policy_version 17671 (0.0008) -[2023-10-09 08:58:54,372][23469] Updated weights for policy 1, policy_version 17681 (0.0010) -[2023-10-09 08:58:54,735][23469] Updated weights for policy 1, policy_version 17691 (0.0007) -[2023-10-09 08:58:56,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 36143104. Throughput: 0: 1773.6, 1: 1793.9. Samples: 9042222. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-09 08:58:56,079][22500] Avg episode reward: [(0, '6.390'), (1, '5.960')] -[2023-10-09 08:58:56,627][23468] Updated weights for policy 0, policy_version 17603 (0.0008) -[2023-10-09 08:58:57,000][23468] Updated weights for policy 0, policy_version 17613 (0.0009) -[2023-10-09 08:58:57,378][23468] Updated weights for policy 0, policy_version 17623 (0.0007) -[2023-10-09 08:58:58,620][23469] Updated weights for policy 1, policy_version 17701 (0.0008) -[2023-10-09 08:58:59,010][23469] Updated weights for policy 1, policy_version 17711 (0.0007) -[2023-10-09 08:58:59,384][23469] Updated weights for policy 1, policy_version 17721 (0.0008) -[2023-10-09 08:59:01,011][23468] Updated weights for policy 0, policy_version 17633 (0.0008) -[2023-10-09 08:59:01,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 36208640. Throughput: 0: 1788.2, 1: 1786.6. Samples: 9064138. Policy #0 lag: (min: 24.0, avg: 37.1, max: 56.0) -[2023-10-09 08:59:01,078][22500] Avg episode reward: [(0, '6.000'), (1, '5.330')] -[2023-10-09 08:59:01,380][23468] Updated weights for policy 0, policy_version 17643 (0.0007) -[2023-10-09 08:59:01,768][23468] Updated weights for policy 0, policy_version 17653 (0.0010) -[2023-10-09 08:59:02,140][23468] Updated weights for policy 0, policy_version 17663 (0.0010) -[2023-10-09 08:59:03,115][23469] Updated weights for policy 1, policy_version 17731 (0.0007) -[2023-10-09 08:59:03,490][23469] Updated weights for policy 1, policy_version 17741 (0.0009) -[2023-10-09 08:59:03,857][23469] Updated weights for policy 1, policy_version 17751 (0.0007) -[2023-10-09 08:59:06,042][23468] Updated weights for policy 0, policy_version 17673 (0.0009) -[2023-10-09 08:59:06,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 36274176. Throughput: 0: 1783.2, 1: 1801.5. Samples: 9074456. Policy #0 lag: (min: 24.0, avg: 37.1, max: 56.0) -[2023-10-09 08:59:06,078][22500] Avg episode reward: [(0, '6.100'), (1, '5.670')] -[2023-10-09 08:59:06,417][23468] Updated weights for policy 0, policy_version 17683 (0.0009) -[2023-10-09 08:59:06,795][23468] Updated weights for policy 0, policy_version 17693 (0.0007) -[2023-10-09 08:59:07,746][23469] Updated weights for policy 1, policy_version 17761 (0.0007) -[2023-10-09 08:59:08,119][23469] Updated weights for policy 1, policy_version 17771 (0.0007) -[2023-10-09 08:59:08,494][23469] Updated weights for policy 1, policy_version 17781 (0.0007) -[2023-10-09 08:59:08,861][23469] Updated weights for policy 1, policy_version 17791 (0.0008) -[2023-10-09 08:59:10,575][23468] Updated weights for policy 0, policy_version 17703 (0.0008) -[2023-10-09 08:59:10,949][23468] Updated weights for policy 0, policy_version 17713 (0.0009) -[2023-10-09 08:59:11,079][22500] Fps is (10 sec: 13105.6, 60 sec: 14199.2, 300 sec: 14329.0). Total num frames: 36339712. Throughput: 0: 1777.5, 1: 1790.9. Samples: 9096036. Policy #0 lag: (min: 24.0, avg: 37.1, max: 56.0) -[2023-10-09 08:59:11,079][22500] Avg episode reward: [(0, '6.340'), (1, '5.790')] -[2023-10-09 08:59:11,312][23468] Updated weights for policy 0, policy_version 17723 (0.0009) -[2023-10-09 08:59:12,578][23469] Updated weights for policy 1, policy_version 17801 (0.0008) -[2023-10-09 08:59:12,951][23469] Updated weights for policy 1, policy_version 17811 (0.0007) -[2023-10-09 08:59:13,316][23469] Updated weights for policy 1, policy_version 17821 (0.0008) -[2023-10-09 08:59:15,117][23468] Updated weights for policy 0, policy_version 17733 (0.0009) -[2023-10-09 08:59:15,493][23468] Updated weights for policy 0, policy_version 17743 (0.0009) -[2023-10-09 08:59:15,860][23468] Updated weights for policy 0, policy_version 17753 (0.0008) -[2023-10-09 08:59:16,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.6, 300 sec: 14218.0). Total num frames: 36405248. Throughput: 0: 1794.8, 1: 1780.6. Samples: 9117590. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:59:16,078][22500] Avg episode reward: [(0, '6.420'), (1, '5.890')] -[2023-10-09 08:59:17,013][23469] Updated weights for policy 1, policy_version 17831 (0.0009) -[2023-10-09 08:59:17,387][23469] Updated weights for policy 1, policy_version 17841 (0.0010) -[2023-10-09 08:59:17,766][23469] Updated weights for policy 1, policy_version 17851 (0.0008) -[2023-10-09 08:59:19,705][23468] Updated weights for policy 0, policy_version 17763 (0.0009) -[2023-10-09 08:59:20,076][23468] Updated weights for policy 0, policy_version 17773 (0.0008) -[2023-10-09 08:59:20,453][23468] Updated weights for policy 0, policy_version 17783 (0.0010) -[2023-10-09 08:59:21,077][22500] Fps is (10 sec: 16386.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 36503552. Throughput: 0: 1771.6, 1: 1781.3. Samples: 9127824. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 08:59:21,078][22500] Avg episode reward: [(0, '5.990'), (1, '5.660')] -[2023-10-09 08:59:21,649][23469] Updated weights for policy 1, policy_version 17861 (0.0007) -[2023-10-09 08:59:22,022][23469] Updated weights for policy 1, policy_version 17871 (0.0007) -[2023-10-09 08:59:22,391][23469] Updated weights for policy 1, policy_version 17881 (0.0009) -[2023-10-09 08:59:24,201][23468] Updated weights for policy 0, policy_version 17793 (0.0009) -[2023-10-09 08:59:24,567][23468] Updated weights for policy 0, policy_version 17803 (0.0010) -[2023-10-09 08:59:24,937][23468] Updated weights for policy 0, policy_version 17813 (0.0010) -[2023-10-09 08:59:25,308][23468] Updated weights for policy 0, policy_version 17823 (0.0010) -[2023-10-09 08:59:26,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 36569088. Throughput: 0: 1801.0, 1: 1777.2. Samples: 9150026. Policy #0 lag: (min: 18.0, avg: 19.1, max: 41.0) -[2023-10-09 08:59:26,079][22500] Avg episode reward: [(0, '6.570'), (1, '5.870')] -[2023-10-09 08:59:26,154][23469] Updated weights for policy 1, policy_version 17891 (0.0009) -[2023-10-09 08:59:26,525][23469] Updated weights for policy 1, policy_version 17901 (0.0009) -[2023-10-09 08:59:26,897][23469] Updated weights for policy 1, policy_version 17911 (0.0008) -[2023-10-09 08:59:28,906][23468] Updated weights for policy 0, policy_version 17833 (0.0008) -[2023-10-09 08:59:29,275][23468] Updated weights for policy 0, policy_version 17843 (0.0007) -[2023-10-09 08:59:29,647][23468] Updated weights for policy 0, policy_version 17853 (0.0007) -[2023-10-09 08:59:30,719][23469] Updated weights for policy 1, policy_version 17921 (0.0007) -[2023-10-09 08:59:31,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 36634624. Throughput: 0: 1779.2, 1: 1801.5. Samples: 9171072. Policy #0 lag: (min: 18.0, avg: 19.1, max: 41.0) -[2023-10-09 08:59:31,078][22500] Avg episode reward: [(0, '6.550'), (1, '5.850')] -[2023-10-09 08:59:31,090][23469] Updated weights for policy 1, policy_version 17931 (0.0010) -[2023-10-09 08:59:31,461][23469] Updated weights for policy 1, policy_version 17941 (0.0008) -[2023-10-09 08:59:31,834][23469] Updated weights for policy 1, policy_version 17951 (0.0008) -[2023-10-09 08:59:33,434][23468] Updated weights for policy 0, policy_version 17863 (0.0010) -[2023-10-09 08:59:33,809][23468] Updated weights for policy 0, policy_version 17873 (0.0007) -[2023-10-09 08:59:34,169][23468] Updated weights for policy 0, policy_version 17883 (0.0007) -[2023-10-09 08:59:35,554][23469] Updated weights for policy 1, policy_version 17961 (0.0010) -[2023-10-09 08:59:35,916][23469] Updated weights for policy 1, policy_version 17971 (0.0010) -[2023-10-09 08:59:36,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 36700160. Throughput: 0: 1804.4, 1: 1768.3. Samples: 9182196. Policy #0 lag: (min: 18.0, avg: 19.1, max: 41.0) -[2023-10-09 08:59:36,078][22500] Avg episode reward: [(0, '5.810'), (1, '5.740')] -[2023-10-09 08:59:36,278][23469] Updated weights for policy 1, policy_version 17981 (0.0007) -[2023-10-09 08:59:38,122][23468] Updated weights for policy 0, policy_version 17893 (0.0009) -[2023-10-09 08:59:38,498][23468] Updated weights for policy 0, policy_version 17903 (0.0009) -[2023-10-09 08:59:38,876][23468] Updated weights for policy 0, policy_version 17913 (0.0009) -[2023-10-09 08:59:39,852][23469] Updated weights for policy 1, policy_version 17991 (0.0009) -[2023-10-09 08:59:40,223][23469] Updated weights for policy 1, policy_version 18001 (0.0010) -[2023-10-09 08:59:40,594][23469] Updated weights for policy 1, policy_version 18011 (0.0010) -[2023-10-09 08:59:41,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 36798464. Throughput: 0: 1775.6, 1: 1796.9. Samples: 9202984. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 08:59:41,078][22500] Avg episode reward: [(0, '6.330'), (1, '5.690')] -[2023-10-09 08:59:42,635][23468] Updated weights for policy 0, policy_version 17923 (0.0008) -[2023-10-09 08:59:43,008][23468] Updated weights for policy 0, policy_version 17933 (0.0008) -[2023-10-09 08:59:43,388][23468] Updated weights for policy 0, policy_version 17943 (0.0009) -[2023-10-09 08:59:44,572][23469] Updated weights for policy 1, policy_version 18021 (0.0009) -[2023-10-09 08:59:44,973][23469] Updated weights for policy 1, policy_version 18031 (0.0008) -[2023-10-09 08:59:45,346][23469] Updated weights for policy 1, policy_version 18041 (0.0009) -[2023-10-09 08:59:46,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 36864000. Throughput: 0: 1766.7, 1: 1773.6. Samples: 9223448. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 08:59:46,078][22500] Avg episode reward: [(0, '5.960'), (1, '5.700')] -[2023-10-09 08:59:47,128][23468] Updated weights for policy 0, policy_version 17953 (0.0008) -[2023-10-09 08:59:47,503][23468] Updated weights for policy 0, policy_version 17963 (0.0007) -[2023-10-09 08:59:47,877][23468] Updated weights for policy 0, policy_version 17973 (0.0011) -[2023-10-09 08:59:48,257][23468] Updated weights for policy 0, policy_version 17983 (0.0010) -[2023-10-09 08:59:48,988][23469] Updated weights for policy 1, policy_version 18051 (0.0009) -[2023-10-09 08:59:49,363][23469] Updated weights for policy 1, policy_version 18061 (0.0011) -[2023-10-09 08:59:49,745][23469] Updated weights for policy 1, policy_version 18071 (0.0008) -[2023-10-09 08:59:51,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 36929536. Throughput: 0: 1768.2, 1: 1794.1. Samples: 9234762. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 08:59:51,079][22500] Avg episode reward: [(0, '6.420'), (1, '5.460')] -[2023-10-09 08:59:52,087][23468] Updated weights for policy 0, policy_version 17993 (0.0008) -[2023-10-09 08:59:52,474][23468] Updated weights for policy 0, policy_version 18003 (0.0008) -[2023-10-09 08:59:52,852][23468] Updated weights for policy 0, policy_version 18013 (0.0008) -[2023-10-09 08:59:53,681][23469] Updated weights for policy 1, policy_version 18081 (0.0008) -[2023-10-09 08:59:54,050][23469] Updated weights for policy 1, policy_version 18091 (0.0009) -[2023-10-09 08:59:54,424][23469] Updated weights for policy 1, policy_version 18101 (0.0008) -[2023-10-09 08:59:54,792][23469] Updated weights for policy 1, policy_version 18111 (0.0008) -[2023-10-09 08:59:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 36995072. Throughput: 0: 1767.9, 1: 1772.1. Samples: 9255330. Policy #0 lag: (min: 24.0, avg: 46.3, max: 56.0) -[2023-10-09 08:59:56,078][22500] Avg episode reward: [(0, '6.200'), (1, '5.730')] -[2023-10-09 08:59:56,798][23468] Updated weights for policy 0, policy_version 18023 (0.0007) -[2023-10-09 08:59:57,180][23468] Updated weights for policy 0, policy_version 18033 (0.0007) -[2023-10-09 08:59:57,560][23468] Updated weights for policy 0, policy_version 18043 (0.0009) -[2023-10-09 08:59:58,484][23469] Updated weights for policy 1, policy_version 18121 (0.0007) -[2023-10-09 08:59:58,850][23469] Updated weights for policy 1, policy_version 18131 (0.0007) -[2023-10-09 08:59:59,222][23469] Updated weights for policy 1, policy_version 18141 (0.0007) -[2023-10-09 09:00:01,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 37060608. Throughput: 0: 1781.6, 1: 1772.2. Samples: 9277512. Policy #0 lag: (min: 24.0, avg: 46.3, max: 56.0) -[2023-10-09 09:00:01,078][22500] Avg episode reward: [(0, '6.030'), (1, '5.680')] -[2023-10-09 09:00:01,256][23468] Updated weights for policy 0, policy_version 18053 (0.0009) -[2023-10-09 09:00:01,621][23468] Updated weights for policy 0, policy_version 18063 (0.0009) -[2023-10-09 09:00:02,000][23468] Updated weights for policy 0, policy_version 18073 (0.0008) -[2023-10-09 09:00:03,153][23469] Updated weights for policy 1, policy_version 18151 (0.0007) -[2023-10-09 09:00:03,520][23469] Updated weights for policy 1, policy_version 18161 (0.0007) -[2023-10-09 09:00:03,882][23469] Updated weights for policy 1, policy_version 18171 (0.0007) -[2023-10-09 09:00:05,864][23468] Updated weights for policy 0, policy_version 18083 (0.0010) -[2023-10-09 09:00:06,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 37126144. Throughput: 0: 1768.8, 1: 1780.3. Samples: 9287534. Policy #0 lag: (min: 24.0, avg: 46.3, max: 56.0) -[2023-10-09 09:00:06,079][22500] Avg episode reward: [(0, '6.280'), (1, '5.580')] -[2023-10-09 09:00:06,245][23468] Updated weights for policy 0, policy_version 18093 (0.0010) -[2023-10-09 09:00:06,626][23468] Updated weights for policy 0, policy_version 18103 (0.0010) -[2023-10-09 09:00:07,614][23469] Updated weights for policy 1, policy_version 18181 (0.0008) -[2023-10-09 09:00:07,978][23469] Updated weights for policy 1, policy_version 18191 (0.0009) -[2023-10-09 09:00:08,349][23469] Updated weights for policy 1, policy_version 18201 (0.0007) -[2023-10-09 09:00:10,435][23468] Updated weights for policy 0, policy_version 18113 (0.0008) -[2023-10-09 09:00:10,814][23468] Updated weights for policy 0, policy_version 18123 (0.0009) -[2023-10-09 09:00:11,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.8, 300 sec: 14218.0). Total num frames: 37191680. Throughput: 0: 1765.8, 1: 1778.4. Samples: 9309514. Policy #0 lag: (min: 31.0, avg: 32.0, max: 53.0) -[2023-10-09 09:00:11,078][22500] Avg episode reward: [(0, '6.230'), (1, '5.770')] -[2023-10-09 09:00:11,183][23468] Updated weights for policy 0, policy_version 18133 (0.0008) -[2023-10-09 09:00:11,560][23468] Updated weights for policy 0, policy_version 18143 (0.0009) -[2023-10-09 09:00:12,100][23469] Updated weights for policy 1, policy_version 18211 (0.0008) -[2023-10-09 09:00:12,477][23469] Updated weights for policy 1, policy_version 18221 (0.0010) -[2023-10-09 09:00:12,843][23469] Updated weights for policy 1, policy_version 18231 (0.0010) -[2023-10-09 09:00:15,304][23468] Updated weights for policy 0, policy_version 18153 (0.0009) -[2023-10-09 09:00:15,680][23468] Updated weights for policy 0, policy_version 18163 (0.0009) -[2023-10-09 09:00:16,053][23468] Updated weights for policy 0, policy_version 18173 (0.0007) -[2023-10-09 09:00:16,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 37257216. Throughput: 0: 1784.1, 1: 1779.1. Samples: 9331414. Policy #0 lag: (min: 31.0, avg: 32.0, max: 53.0) -[2023-10-09 09:00:16,078][22500] Avg episode reward: [(0, '6.310'), (1, '5.850')] -[2023-10-09 09:00:16,085][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000018240_18677760.pth... -[2023-10-09 09:00:16,122][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000016576_16973824.pth -[2023-10-09 09:00:16,161][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000018176_18612224.pth... -[2023-10-09 09:00:16,190][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000016512_16908288.pth -[2023-10-09 09:00:16,762][23469] Updated weights for policy 1, policy_version 18241 (0.0008) -[2023-10-09 09:00:17,145][23469] Updated weights for policy 1, policy_version 18251 (0.0011) -[2023-10-09 09:00:17,514][23469] Updated weights for policy 1, policy_version 18261 (0.0010) -[2023-10-09 09:00:17,886][23469] Updated weights for policy 1, policy_version 18271 (0.0010) -[2023-10-09 09:00:19,985][23468] Updated weights for policy 0, policy_version 18183 (0.0007) -[2023-10-09 09:00:20,354][23468] Updated weights for policy 0, policy_version 18193 (0.0008) -[2023-10-09 09:00:20,729][23468] Updated weights for policy 0, policy_version 18203 (0.0007) -[2023-10-09 09:00:21,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 37355520. Throughput: 0: 1762.3, 1: 1775.2. Samples: 9341382. Policy #0 lag: (min: 16.0, avg: 43.7, max: 48.0) -[2023-10-09 09:00:21,078][22500] Avg episode reward: [(0, '6.390'), (1, '5.620')] -[2023-10-09 09:00:21,804][23469] Updated weights for policy 1, policy_version 18281 (0.0008) -[2023-10-09 09:00:22,182][23469] Updated weights for policy 1, policy_version 18291 (0.0009) -[2023-10-09 09:00:22,548][23469] Updated weights for policy 1, policy_version 18301 (0.0009) -[2023-10-09 09:00:24,358][23468] Updated weights for policy 0, policy_version 18213 (0.0009) -[2023-10-09 09:00:24,727][23468] Updated weights for policy 0, policy_version 18223 (0.0008) -[2023-10-09 09:00:25,098][23468] Updated weights for policy 0, policy_version 18233 (0.0008) -[2023-10-09 09:00:26,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 37421056. Throughput: 0: 1791.3, 1: 1773.1. Samples: 9363384. Policy #0 lag: (min: 16.0, avg: 43.7, max: 48.0) -[2023-10-09 09:00:26,078][22500] Avg episode reward: [(0, '6.580'), (1, '5.700')] -[2023-10-09 09:00:26,323][23469] Updated weights for policy 1, policy_version 18311 (0.0007) -[2023-10-09 09:00:26,696][23469] Updated weights for policy 1, policy_version 18321 (0.0007) -[2023-10-09 09:00:27,058][23469] Updated weights for policy 1, policy_version 18331 (0.0007) -[2023-10-09 09:00:28,777][23468] Updated weights for policy 0, policy_version 18243 (0.0007) -[2023-10-09 09:00:29,149][23468] Updated weights for policy 0, policy_version 18253 (0.0008) -[2023-10-09 09:00:29,517][23468] Updated weights for policy 0, policy_version 18263 (0.0007) -[2023-10-09 09:00:30,651][23469] Updated weights for policy 1, policy_version 18341 (0.0008) -[2023-10-09 09:00:31,042][23469] Updated weights for policy 1, policy_version 18351 (0.0007) -[2023-10-09 09:00:31,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 37486592. Throughput: 0: 1768.9, 1: 1804.5. Samples: 9384250. Policy #0 lag: (min: 16.0, avg: 43.7, max: 48.0) -[2023-10-09 09:00:31,078][22500] Avg episode reward: [(0, '6.380'), (1, '5.700')] -[2023-10-09 09:00:31,410][23469] Updated weights for policy 1, policy_version 18361 (0.0008) -[2023-10-09 09:00:33,456][23468] Updated weights for policy 0, policy_version 18273 (0.0007) -[2023-10-09 09:00:33,828][23468] Updated weights for policy 0, policy_version 18283 (0.0008) -[2023-10-09 09:00:34,203][23468] Updated weights for policy 0, policy_version 18293 (0.0008) -[2023-10-09 09:00:34,579][23468] Updated weights for policy 0, policy_version 18303 (0.0008) -[2023-10-09 09:00:34,979][23469] Updated weights for policy 1, policy_version 18371 (0.0008) -[2023-10-09 09:00:35,356][23469] Updated weights for policy 1, policy_version 18381 (0.0007) -[2023-10-09 09:00:35,724][23469] Updated weights for policy 1, policy_version 18391 (0.0008) -[2023-10-09 09:00:36,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 37584896. Throughput: 0: 1797.0, 1: 1781.3. Samples: 9395788. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:00:36,079][22500] Avg episode reward: [(0, '6.750'), (1, '6.030')] -[2023-10-09 09:00:38,289][23468] Updated weights for policy 0, policy_version 18313 (0.0009) -[2023-10-09 09:00:38,662][23468] Updated weights for policy 0, policy_version 18323 (0.0009) -[2023-10-09 09:00:39,022][23468] Updated weights for policy 0, policy_version 18333 (0.0007) -[2023-10-09 09:00:39,633][23469] Updated weights for policy 1, policy_version 18401 (0.0009) -[2023-10-09 09:00:40,000][23469] Updated weights for policy 1, policy_version 18411 (0.0008) -[2023-10-09 09:00:40,376][23469] Updated weights for policy 1, policy_version 18421 (0.0008) -[2023-10-09 09:00:40,738][23469] Updated weights for policy 1, policy_version 18431 (0.0009) -[2023-10-09 09:00:41,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 37650432. Throughput: 0: 1769.2, 1: 1807.8. Samples: 9416294. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:00:41,078][22500] Avg episode reward: [(0, '6.380'), (1, '5.970')] -[2023-10-09 09:00:42,975][23468] Updated weights for policy 0, policy_version 18343 (0.0009) -[2023-10-09 09:00:43,364][23468] Updated weights for policy 0, policy_version 18353 (0.0009) -[2023-10-09 09:00:43,742][23468] Updated weights for policy 0, policy_version 18363 (0.0009) -[2023-10-09 09:00:44,486][23469] Updated weights for policy 1, policy_version 18441 (0.0008) -[2023-10-09 09:00:44,854][23469] Updated weights for policy 1, policy_version 18451 (0.0008) -[2023-10-09 09:00:45,222][23469] Updated weights for policy 1, policy_version 18461 (0.0008) -[2023-10-09 09:00:46,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 37715968. Throughput: 0: 1766.3, 1: 1782.0. Samples: 9437188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:00:46,079][22500] Avg episode reward: [(0, '6.440'), (1, '5.900')] -[2023-10-09 09:00:47,471][23468] Updated weights for policy 0, policy_version 18373 (0.0007) -[2023-10-09 09:00:47,844][23468] Updated weights for policy 0, policy_version 18383 (0.0010) -[2023-10-09 09:00:48,231][23468] Updated weights for policy 0, policy_version 18393 (0.0008) -[2023-10-09 09:00:48,901][23469] Updated weights for policy 1, policy_version 18471 (0.0008) -[2023-10-09 09:00:49,264][23469] Updated weights for policy 1, policy_version 18481 (0.0007) -[2023-10-09 09:00:49,640][23469] Updated weights for policy 1, policy_version 18491 (0.0008) -[2023-10-09 09:00:51,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 37781504. Throughput: 0: 1776.2, 1: 1803.9. Samples: 9448638. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-09 09:00:51,079][22500] Avg episode reward: [(0, '6.730'), (1, '5.770')] -[2023-10-09 09:00:52,154][23468] Updated weights for policy 0, policy_version 18403 (0.0008) -[2023-10-09 09:00:52,524][23468] Updated weights for policy 0, policy_version 18413 (0.0008) -[2023-10-09 09:00:52,895][23468] Updated weights for policy 0, policy_version 18423 (0.0007) -[2023-10-09 09:00:53,494][23469] Updated weights for policy 1, policy_version 18501 (0.0008) -[2023-10-09 09:00:53,860][23469] Updated weights for policy 1, policy_version 18511 (0.0010) -[2023-10-09 09:00:54,225][23469] Updated weights for policy 1, policy_version 18521 (0.0008) -[2023-10-09 09:00:56,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 37847040. Throughput: 0: 1771.0, 1: 1779.3. Samples: 9469278. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-09 09:00:56,078][22500] Avg episode reward: [(0, '6.390'), (1, '5.990')] -[2023-10-09 09:00:56,594][23468] Updated weights for policy 0, policy_version 18433 (0.0008) -[2023-10-09 09:00:56,967][23468] Updated weights for policy 0, policy_version 18443 (0.0007) -[2023-10-09 09:00:57,338][23468] Updated weights for policy 0, policy_version 18453 (0.0007) -[2023-10-09 09:00:57,708][23468] Updated weights for policy 0, policy_version 18463 (0.0007) -[2023-10-09 09:00:57,964][23469] Updated weights for policy 1, policy_version 18531 (0.0009) -[2023-10-09 09:00:58,336][23469] Updated weights for policy 1, policy_version 18541 (0.0007) -[2023-10-09 09:00:58,713][23469] Updated weights for policy 1, policy_version 18551 (0.0008) -[2023-10-09 09:01:01,078][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 37912576. Throughput: 0: 1781.6, 1: 1781.6. Samples: 9491762. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-09 09:01:01,079][22500] Avg episode reward: [(0, '6.470'), (1, '5.610')] -[2023-10-09 09:01:01,418][23468] Updated weights for policy 0, policy_version 18473 (0.0009) -[2023-10-09 09:01:01,786][23468] Updated weights for policy 0, policy_version 18483 (0.0007) -[2023-10-09 09:01:02,165][23468] Updated weights for policy 0, policy_version 18493 (0.0007) -[2023-10-09 09:01:02,423][23469] Updated weights for policy 1, policy_version 18561 (0.0008) -[2023-10-09 09:01:02,794][23469] Updated weights for policy 1, policy_version 18571 (0.0007) -[2023-10-09 09:01:03,167][23469] Updated weights for policy 1, policy_version 18581 (0.0007) -[2023-10-09 09:01:03,537][23469] Updated weights for policy 1, policy_version 18591 (0.0010) -[2023-10-09 09:01:05,815][23468] Updated weights for policy 0, policy_version 18503 (0.0008) -[2023-10-09 09:01:06,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 37978112. Throughput: 0: 1773.1, 1: 1784.4. Samples: 9501470. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-09 09:01:06,079][22500] Avg episode reward: [(0, '6.480'), (1, '5.800')] -[2023-10-09 09:01:06,178][23468] Updated weights for policy 0, policy_version 18513 (0.0009) -[2023-10-09 09:01:06,550][23468] Updated weights for policy 0, policy_version 18523 (0.0009) -[2023-10-09 09:01:07,134][23469] Updated weights for policy 1, policy_version 18601 (0.0010) -[2023-10-09 09:01:07,509][23469] Updated weights for policy 1, policy_version 18611 (0.0011) -[2023-10-09 09:01:07,872][23469] Updated weights for policy 1, policy_version 18621 (0.0012) -[2023-10-09 09:01:10,253][23468] Updated weights for policy 0, policy_version 18533 (0.0007) -[2023-10-09 09:01:10,615][23468] Updated weights for policy 0, policy_version 18543 (0.0007) -[2023-10-09 09:01:11,001][23468] Updated weights for policy 0, policy_version 18553 (0.0008) -[2023-10-09 09:01:11,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 38043648. Throughput: 0: 1780.0, 1: 1792.6. Samples: 9524152. Policy #0 lag: (min: 24.0, avg: 53.2, max: 56.0) -[2023-10-09 09:01:11,078][22500] Avg episode reward: [(0, '6.630'), (1, '5.780')] -[2023-10-09 09:01:11,735][23469] Updated weights for policy 1, policy_version 18631 (0.0009) -[2023-10-09 09:01:12,101][23469] Updated weights for policy 1, policy_version 18641 (0.0007) -[2023-10-09 09:01:12,467][23469] Updated weights for policy 1, policy_version 18651 (0.0007) -[2023-10-09 09:01:14,665][23468] Updated weights for policy 0, policy_version 18563 (0.0008) -[2023-10-09 09:01:15,035][23468] Updated weights for policy 0, policy_version 18573 (0.0009) -[2023-10-09 09:01:15,415][23468] Updated weights for policy 0, policy_version 18583 (0.0010) -[2023-10-09 09:01:16,078][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 38141952. Throughput: 0: 1790.9, 1: 1798.5. Samples: 9545774. Policy #0 lag: (min: 24.0, avg: 53.2, max: 56.0) -[2023-10-09 09:01:16,079][22500] Avg episode reward: [(0, '6.500'), (1, '5.860')] -[2023-10-09 09:01:16,347][23469] Updated weights for policy 1, policy_version 18661 (0.0008) -[2023-10-09 09:01:16,742][23469] Updated weights for policy 1, policy_version 18671 (0.0007) -[2023-10-09 09:01:17,110][23469] Updated weights for policy 1, policy_version 18681 (0.0007) -[2023-10-09 09:01:19,122][23468] Updated weights for policy 0, policy_version 18593 (0.0008) -[2023-10-09 09:01:19,497][23468] Updated weights for policy 0, policy_version 18603 (0.0008) -[2023-10-09 09:01:19,862][23468] Updated weights for policy 0, policy_version 18613 (0.0007) -[2023-10-09 09:01:20,242][23468] Updated weights for policy 0, policy_version 18623 (0.0007) -[2023-10-09 09:01:20,981][23469] Updated weights for policy 1, policy_version 18691 (0.0009) -[2023-10-09 09:01:21,078][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 38207488. Throughput: 0: 1787.1, 1: 1780.9. Samples: 9556346. Policy #0 lag: (min: 24.0, avg: 53.2, max: 56.0) -[2023-10-09 09:01:21,079][22500] Avg episode reward: [(0, '6.290'), (1, '5.790')] -[2023-10-09 09:01:21,351][23469] Updated weights for policy 1, policy_version 18701 (0.0010) -[2023-10-09 09:01:21,713][23469] Updated weights for policy 1, policy_version 18711 (0.0009) -[2023-10-09 09:01:23,981][23468] Updated weights for policy 0, policy_version 18633 (0.0010) -[2023-10-09 09:01:24,357][23468] Updated weights for policy 0, policy_version 18643 (0.0009) -[2023-10-09 09:01:24,737][23468] Updated weights for policy 0, policy_version 18653 (0.0007) -[2023-10-09 09:01:25,382][23469] Updated weights for policy 1, policy_version 18721 (0.0009) -[2023-10-09 09:01:25,741][23469] Updated weights for policy 1, policy_version 18731 (0.0010) -[2023-10-09 09:01:26,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 38273024. Throughput: 0: 1804.6, 1: 1792.2. Samples: 9578152. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-09 09:01:26,078][22500] Avg episode reward: [(0, '6.400'), (1, '5.820')] -[2023-10-09 09:01:26,121][23469] Updated weights for policy 1, policy_version 18741 (0.0008) -[2023-10-09 09:01:26,500][23469] Updated weights for policy 1, policy_version 18751 (0.0011) -[2023-10-09 09:01:28,607][23468] Updated weights for policy 0, policy_version 18663 (0.0008) -[2023-10-09 09:01:28,977][23468] Updated weights for policy 0, policy_version 18673 (0.0007) -[2023-10-09 09:01:29,355][23468] Updated weights for policy 0, policy_version 18683 (0.0009) -[2023-10-09 09:01:30,412][23469] Updated weights for policy 1, policy_version 18761 (0.0008) -[2023-10-09 09:01:30,782][23469] Updated weights for policy 1, policy_version 18771 (0.0010) -[2023-10-09 09:01:31,078][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 38338560. Throughput: 0: 1788.8, 1: 1800.0. Samples: 9598686. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-09 09:01:31,079][22500] Avg episode reward: [(0, '6.450'), (1, '5.650')] -[2023-10-09 09:01:31,155][23469] Updated weights for policy 1, policy_version 18781 (0.0010) -[2023-10-09 09:01:33,152][23468] Updated weights for policy 0, policy_version 18693 (0.0007) -[2023-10-09 09:01:33,527][23468] Updated weights for policy 0, policy_version 18703 (0.0011) -[2023-10-09 09:01:33,899][23468] Updated weights for policy 0, policy_version 18713 (0.0009) -[2023-10-09 09:01:34,865][23469] Updated weights for policy 1, policy_version 18791 (0.0008) -[2023-10-09 09:01:35,234][23469] Updated weights for policy 1, policy_version 18801 (0.0008) -[2023-10-09 09:01:35,611][23469] Updated weights for policy 1, policy_version 18811 (0.0008) -[2023-10-09 09:01:36,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 38436864. Throughput: 0: 1807.3, 1: 1787.6. Samples: 9610404. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-09 09:01:36,078][22500] Avg episode reward: [(0, '6.090'), (1, '5.670')] -[2023-10-09 09:01:37,574][23468] Updated weights for policy 0, policy_version 18723 (0.0009) -[2023-10-09 09:01:37,957][23468] Updated weights for policy 0, policy_version 18733 (0.0007) -[2023-10-09 09:01:38,329][23468] Updated weights for policy 0, policy_version 18743 (0.0008) -[2023-10-09 09:01:39,428][23469] Updated weights for policy 1, policy_version 18821 (0.0007) -[2023-10-09 09:01:39,801][23469] Updated weights for policy 1, policy_version 18831 (0.0007) -[2023-10-09 09:01:40,168][23469] Updated weights for policy 1, policy_version 18841 (0.0007) -[2023-10-09 09:01:41,078][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 38502400. Throughput: 0: 1792.2, 1: 1800.3. Samples: 9630938. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-09 09:01:41,079][22500] Avg episode reward: [(0, '6.440'), (1, '5.570')] -[2023-10-09 09:01:42,194][23468] Updated weights for policy 0, policy_version 18753 (0.0007) -[2023-10-09 09:01:42,564][23468] Updated weights for policy 0, policy_version 18763 (0.0007) -[2023-10-09 09:01:42,937][23468] Updated weights for policy 0, policy_version 18773 (0.0007) -[2023-10-09 09:01:43,317][23468] Updated weights for policy 0, policy_version 18783 (0.0007) -[2023-10-09 09:01:43,874][23469] Updated weights for policy 1, policy_version 18851 (0.0008) -[2023-10-09 09:01:44,254][23469] Updated weights for policy 1, policy_version 18861 (0.0009) -[2023-10-09 09:01:44,612][23469] Updated weights for policy 1, policy_version 18871 (0.0009) -[2023-10-09 09:01:46,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 38567936. Throughput: 0: 1790.7, 1: 1779.5. Samples: 9652420. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-10-09 09:01:46,078][22500] Avg episode reward: [(0, '6.120'), (1, '5.950')] -[2023-10-09 09:01:46,976][23468] Updated weights for policy 0, policy_version 18793 (0.0009) -[2023-10-09 09:01:47,346][23468] Updated weights for policy 0, policy_version 18803 (0.0009) -[2023-10-09 09:01:47,723][23468] Updated weights for policy 0, policy_version 18813 (0.0009) -[2023-10-09 09:01:48,384][23469] Updated weights for policy 1, policy_version 18881 (0.0007) -[2023-10-09 09:01:48,766][23469] Updated weights for policy 1, policy_version 18891 (0.0010) -[2023-10-09 09:01:49,131][23469] Updated weights for policy 1, policy_version 18901 (0.0009) -[2023-10-09 09:01:49,496][23469] Updated weights for policy 1, policy_version 18911 (0.0007) -[2023-10-09 09:01:51,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 38633472. Throughput: 0: 1790.4, 1: 1802.4. Samples: 9663142. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-10-09 09:01:51,078][22500] Avg episode reward: [(0, '6.510'), (1, '6.240')] -[2023-10-09 09:01:51,467][23468] Updated weights for policy 0, policy_version 18823 (0.0009) -[2023-10-09 09:01:51,837][23468] Updated weights for policy 0, policy_version 18833 (0.0009) -[2023-10-09 09:01:52,203][23468] Updated weights for policy 0, policy_version 18843 (0.0008) -[2023-10-09 09:01:53,201][23469] Updated weights for policy 1, policy_version 18921 (0.0007) -[2023-10-09 09:01:53,562][23469] Updated weights for policy 1, policy_version 18931 (0.0007) -[2023-10-09 09:01:53,931][23469] Updated weights for policy 1, policy_version 18941 (0.0007) -[2023-10-09 09:01:56,030][23468] Updated weights for policy 0, policy_version 18853 (0.0008) -[2023-10-09 09:01:56,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 38699008. Throughput: 0: 1790.7, 1: 1778.1. Samples: 9684748. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-10-09 09:01:56,079][22500] Avg episode reward: [(0, '6.520'), (1, '6.030')] -[2023-10-09 09:01:56,401][23468] Updated weights for policy 0, policy_version 18863 (0.0010) -[2023-10-09 09:01:56,782][23468] Updated weights for policy 0, policy_version 18873 (0.0009) -[2023-10-09 09:01:57,751][23469] Updated weights for policy 1, policy_version 18951 (0.0007) -[2023-10-09 09:01:58,130][23469] Updated weights for policy 1, policy_version 18961 (0.0008) -[2023-10-09 09:01:58,492][23469] Updated weights for policy 1, policy_version 18971 (0.0009) -[2023-10-09 09:02:00,571][23468] Updated weights for policy 0, policy_version 18883 (0.0010) -[2023-10-09 09:02:00,945][23468] Updated weights for policy 0, policy_version 18893 (0.0011) -[2023-10-09 09:02:01,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 38764544. Throughput: 0: 1806.7, 1: 1775.3. Samples: 9706962. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-10-09 09:02:01,078][22500] Avg episode reward: [(0, '6.300'), (1, '5.480')] -[2023-10-09 09:02:01,317][23468] Updated weights for policy 0, policy_version 18903 (0.0011) -[2023-10-09 09:02:02,394][23469] Updated weights for policy 1, policy_version 18981 (0.0009) -[2023-10-09 09:02:02,787][23469] Updated weights for policy 1, policy_version 18991 (0.0007) -[2023-10-09 09:02:03,158][23469] Updated weights for policy 1, policy_version 19001 (0.0007) -[2023-10-09 09:02:04,932][23468] Updated weights for policy 0, policy_version 18913 (0.0007) -[2023-10-09 09:02:05,305][23468] Updated weights for policy 0, policy_version 18923 (0.0007) -[2023-10-09 09:02:05,689][23468] Updated weights for policy 0, policy_version 18933 (0.0009) -[2023-10-09 09:02:06,063][23468] Updated weights for policy 0, policy_version 18943 (0.0010) -[2023-10-09 09:02:06,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 38830080. Throughput: 0: 1784.2, 1: 1779.8. Samples: 9716726. Policy #0 lag: (min: 31.0, avg: 33.1, max: 62.0) -[2023-10-09 09:02:06,079][22500] Avg episode reward: [(0, '6.180'), (1, '5.770')] -[2023-10-09 09:02:06,818][23469] Updated weights for policy 1, policy_version 19011 (0.0007) -[2023-10-09 09:02:07,180][23469] Updated weights for policy 1, policy_version 19021 (0.0007) -[2023-10-09 09:02:07,536][23469] Updated weights for policy 1, policy_version 19031 (0.0008) -[2023-10-09 09:02:09,613][23468] Updated weights for policy 0, policy_version 18953 (0.0009) -[2023-10-09 09:02:09,990][23468] Updated weights for policy 0, policy_version 18963 (0.0009) -[2023-10-09 09:02:10,363][23468] Updated weights for policy 0, policy_version 18973 (0.0008) -[2023-10-09 09:02:11,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 38928384. Throughput: 0: 1805.1, 1: 1777.0. Samples: 9739346. Policy #0 lag: (min: 31.0, avg: 33.1, max: 62.0) -[2023-10-09 09:02:11,079][22500] Avg episode reward: [(0, '6.380'), (1, '5.830')] -[2023-10-09 09:02:11,445][23469] Updated weights for policy 1, policy_version 19041 (0.0009) -[2023-10-09 09:02:11,821][23469] Updated weights for policy 1, policy_version 19051 (0.0007) -[2023-10-09 09:02:12,180][23469] Updated weights for policy 1, policy_version 19061 (0.0008) -[2023-10-09 09:02:12,552][23469] Updated weights for policy 1, policy_version 19071 (0.0009) -[2023-10-09 09:02:14,073][23468] Updated weights for policy 0, policy_version 18983 (0.0009) -[2023-10-09 09:02:14,460][23468] Updated weights for policy 0, policy_version 18993 (0.0007) -[2023-10-09 09:02:14,832][23468] Updated weights for policy 0, policy_version 19003 (0.0009) -[2023-10-09 09:02:16,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 38993920. Throughput: 0: 1792.9, 1: 1802.1. Samples: 9760462. Policy #0 lag: (min: 31.0, avg: 33.1, max: 62.0) -[2023-10-09 09:02:16,078][22500] Avg episode reward: [(0, '6.600'), (1, '5.680')] -[2023-10-09 09:02:16,086][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000019008_19464192.pth... -[2023-10-09 09:02:16,122][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000017344_17760256.pth -[2023-10-09 09:02:16,132][23469] Updated weights for policy 1, policy_version 19081 (0.0009) -[2023-10-09 09:02:16,503][23469] Updated weights for policy 1, policy_version 19091 (0.0007) -[2023-10-09 09:02:16,878][23469] Updated weights for policy 1, policy_version 19101 (0.0008) -[2023-10-09 09:02:16,989][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000019104_19562496.pth... -[2023-10-09 09:02:17,023][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000017408_17825792.pth -[2023-10-09 09:02:18,650][23468] Updated weights for policy 0, policy_version 19013 (0.0009) -[2023-10-09 09:02:19,029][23468] Updated weights for policy 0, policy_version 19023 (0.0010) -[2023-10-09 09:02:19,396][23468] Updated weights for policy 0, policy_version 19033 (0.0008) -[2023-10-09 09:02:20,583][23469] Updated weights for policy 1, policy_version 19111 (0.0010) -[2023-10-09 09:02:20,948][23469] Updated weights for policy 1, policy_version 19121 (0.0008) -[2023-10-09 09:02:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 39059456. Throughput: 0: 1799.6, 1: 1784.0. Samples: 9771664. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-09 09:02:21,079][22500] Avg episode reward: [(0, '6.440'), (1, '5.830')] -[2023-10-09 09:02:21,324][23469] Updated weights for policy 1, policy_version 19131 (0.0007) -[2023-10-09 09:02:23,211][23468] Updated weights for policy 0, policy_version 19043 (0.0008) -[2023-10-09 09:02:23,587][23468] Updated weights for policy 0, policy_version 19053 (0.0009) -[2023-10-09 09:02:23,951][23468] Updated weights for policy 0, policy_version 19063 (0.0009) -[2023-10-09 09:02:24,975][23469] Updated weights for policy 1, policy_version 19141 (0.0008) -[2023-10-09 09:02:25,338][23469] Updated weights for policy 1, policy_version 19151 (0.0007) -[2023-10-09 09:02:25,706][23469] Updated weights for policy 1, policy_version 19161 (0.0007) -[2023-10-09 09:02:26,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 39157760. Throughput: 0: 1789.1, 1: 1807.9. Samples: 9792802. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-09 09:02:26,078][22500] Avg episode reward: [(0, '6.920'), (1, '6.050')] -[2023-10-09 09:02:27,770][23468] Updated weights for policy 0, policy_version 19073 (0.0009) -[2023-10-09 09:02:28,142][23468] Updated weights for policy 0, policy_version 19083 (0.0008) -[2023-10-09 09:02:28,511][23468] Updated weights for policy 0, policy_version 19093 (0.0007) -[2023-10-09 09:02:28,883][23468] Updated weights for policy 0, policy_version 19103 (0.0009) -[2023-10-09 09:02:29,437][23469] Updated weights for policy 1, policy_version 19171 (0.0008) -[2023-10-09 09:02:29,800][23469] Updated weights for policy 1, policy_version 19181 (0.0007) -[2023-10-09 09:02:30,172][23469] Updated weights for policy 1, policy_version 19191 (0.0008) -[2023-10-09 09:02:31,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 39223296. Throughput: 0: 1794.4, 1: 1795.3. Samples: 9813958. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-09 09:02:31,078][22500] Avg episode reward: [(0, '6.930'), (1, '5.860')] -[2023-10-09 09:02:32,663][23468] Updated weights for policy 0, policy_version 19113 (0.0008) -[2023-10-09 09:02:33,028][23468] Updated weights for policy 0, policy_version 19123 (0.0008) -[2023-10-09 09:02:33,403][23468] Updated weights for policy 0, policy_version 19133 (0.0008) -[2023-10-09 09:02:33,841][23469] Updated weights for policy 1, policy_version 19201 (0.0008) -[2023-10-09 09:02:34,212][23469] Updated weights for policy 1, policy_version 19211 (0.0007) -[2023-10-09 09:02:34,581][23469] Updated weights for policy 1, policy_version 19221 (0.0007) -[2023-10-09 09:02:34,948][23469] Updated weights for policy 1, policy_version 19231 (0.0007) -[2023-10-09 09:02:36,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 39288832. Throughput: 0: 1802.0, 1: 1808.6. Samples: 9825620. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-09 09:02:36,078][22500] Avg episode reward: [(0, '6.430'), (1, '5.780')] -[2023-10-09 09:02:37,234][23468] Updated weights for policy 0, policy_version 19143 (0.0008) -[2023-10-09 09:02:37,605][23468] Updated weights for policy 0, policy_version 19153 (0.0009) -[2023-10-09 09:02:37,988][23468] Updated weights for policy 0, policy_version 19163 (0.0007) -[2023-10-09 09:02:38,550][23469] Updated weights for policy 1, policy_version 19241 (0.0010) -[2023-10-09 09:02:38,923][23469] Updated weights for policy 1, policy_version 19251 (0.0010) -[2023-10-09 09:02:39,290][23469] Updated weights for policy 1, policy_version 19261 (0.0008) -[2023-10-09 09:02:41,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 39354368. Throughput: 0: 1789.1, 1: 1796.9. Samples: 9846116. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:02:41,078][22500] Avg episode reward: [(0, '6.190'), (1, '5.330')] -[2023-10-09 09:02:41,575][23468] Updated weights for policy 0, policy_version 19173 (0.0008) -[2023-10-09 09:02:41,948][23468] Updated weights for policy 0, policy_version 19183 (0.0009) -[2023-10-09 09:02:42,324][23468] Updated weights for policy 0, policy_version 19193 (0.0008) -[2023-10-09 09:02:43,051][23469] Updated weights for policy 1, policy_version 19271 (0.0007) -[2023-10-09 09:02:43,423][23469] Updated weights for policy 1, policy_version 19281 (0.0008) -[2023-10-09 09:02:43,800][23469] Updated weights for policy 1, policy_version 19291 (0.0007) -[2023-10-09 09:02:46,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 39419904. Throughput: 0: 1790.7, 1: 1800.0. Samples: 9868540. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:02:46,078][22500] Avg episode reward: [(0, '6.070'), (1, '5.590')] -[2023-10-09 09:02:46,223][23468] Updated weights for policy 0, policy_version 19203 (0.0010) -[2023-10-09 09:02:46,593][23468] Updated weights for policy 0, policy_version 19213 (0.0008) -[2023-10-09 09:02:46,967][23468] Updated weights for policy 0, policy_version 19223 (0.0008) -[2023-10-09 09:02:47,709][23469] Updated weights for policy 1, policy_version 19301 (0.0009) -[2023-10-09 09:02:48,110][23469] Updated weights for policy 1, policy_version 19311 (0.0008) -[2023-10-09 09:02:48,485][23469] Updated weights for policy 1, policy_version 19321 (0.0010) -[2023-10-09 09:02:50,861][23468] Updated weights for policy 0, policy_version 19233 (0.0008) -[2023-10-09 09:02:51,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 39485440. Throughput: 0: 1784.6, 1: 1798.3. Samples: 9877954. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:02:51,078][22500] Avg episode reward: [(0, '6.280'), (1, '5.470')] -[2023-10-09 09:02:51,244][23468] Updated weights for policy 0, policy_version 19243 (0.0009) -[2023-10-09 09:02:51,611][23468] Updated weights for policy 0, policy_version 19253 (0.0008) -[2023-10-09 09:02:51,993][23468] Updated weights for policy 0, policy_version 19263 (0.0008) -[2023-10-09 09:02:52,181][23469] Updated weights for policy 1, policy_version 19331 (0.0007) -[2023-10-09 09:02:52,551][23469] Updated weights for policy 1, policy_version 19341 (0.0007) -[2023-10-09 09:02:52,916][23469] Updated weights for policy 1, policy_version 19351 (0.0010) -[2023-10-09 09:02:55,673][23468] Updated weights for policy 0, policy_version 19273 (0.0011) -[2023-10-09 09:02:56,043][23468] Updated weights for policy 0, policy_version 19283 (0.0008) -[2023-10-09 09:02:56,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 39550976. Throughput: 0: 1777.8, 1: 1802.2. Samples: 9900446. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:02:56,079][22500] Avg episode reward: [(0, '6.270'), (1, '5.820')] -[2023-10-09 09:02:56,426][23468] Updated weights for policy 0, policy_version 19293 (0.0008) -[2023-10-09 09:02:56,626][23469] Updated weights for policy 1, policy_version 19361 (0.0007) -[2023-10-09 09:02:57,001][23469] Updated weights for policy 1, policy_version 19371 (0.0008) -[2023-10-09 09:02:57,374][23469] Updated weights for policy 1, policy_version 19381 (0.0007) -[2023-10-09 09:02:57,743][23469] Updated weights for policy 1, policy_version 19391 (0.0010) -[2023-10-09 09:03:00,147][23468] Updated weights for policy 0, policy_version 19303 (0.0008) -[2023-10-09 09:03:00,530][23468] Updated weights for policy 0, policy_version 19313 (0.0007) -[2023-10-09 09:03:00,904][23468] Updated weights for policy 0, policy_version 19323 (0.0008) -[2023-10-09 09:03:01,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 39616512. Throughput: 0: 1798.1, 1: 1803.8. Samples: 9922546. Policy #0 lag: (min: 31.0, avg: 32.6, max: 58.0) -[2023-10-09 09:03:01,078][22500] Avg episode reward: [(0, '6.470'), (1, '5.680')] -[2023-10-09 09:03:01,501][23469] Updated weights for policy 1, policy_version 19401 (0.0009) -[2023-10-09 09:03:01,861][23469] Updated weights for policy 1, policy_version 19411 (0.0011) -[2023-10-09 09:03:02,243][23469] Updated weights for policy 1, policy_version 19421 (0.0009) -[2023-10-09 09:03:04,417][23468] Updated weights for policy 0, policy_version 19333 (0.0008) -[2023-10-09 09:03:04,785][23468] Updated weights for policy 0, policy_version 19343 (0.0008) -[2023-10-09 09:03:05,165][23468] Updated weights for policy 0, policy_version 19353 (0.0008) -[2023-10-09 09:03:05,977][23469] Updated weights for policy 1, policy_version 19431 (0.0009) -[2023-10-09 09:03:06,077][22500] Fps is (10 sec: 16384.5, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 39714816. Throughput: 0: 1780.8, 1: 1800.9. Samples: 9932838. Policy #0 lag: (min: 31.0, avg: 32.6, max: 58.0) -[2023-10-09 09:03:06,078][22500] Avg episode reward: [(0, '6.430'), (1, '5.710')] -[2023-10-09 09:03:06,354][23469] Updated weights for policy 1, policy_version 19441 (0.0007) -[2023-10-09 09:03:06,718][23469] Updated weights for policy 1, policy_version 19451 (0.0007) -[2023-10-09 09:03:09,033][23468] Updated weights for policy 0, policy_version 19363 (0.0009) -[2023-10-09 09:03:09,400][23468] Updated weights for policy 0, policy_version 19373 (0.0011) -[2023-10-09 09:03:09,776][23468] Updated weights for policy 0, policy_version 19383 (0.0011) -[2023-10-09 09:03:10,418][23469] Updated weights for policy 1, policy_version 19461 (0.0009) -[2023-10-09 09:03:10,783][23469] Updated weights for policy 1, policy_version 19471 (0.0010) -[2023-10-09 09:03:11,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 39780352. Throughput: 0: 1805.7, 1: 1796.8. Samples: 9954916. Policy #0 lag: (min: 31.0, avg: 32.6, max: 58.0) -[2023-10-09 09:03:11,078][22500] Avg episode reward: [(0, '6.230'), (1, '5.720')] -[2023-10-09 09:03:11,148][23469] Updated weights for policy 1, policy_version 19481 (0.0009) -[2023-10-09 09:03:13,676][23468] Updated weights for policy 0, policy_version 19393 (0.0010) -[2023-10-09 09:03:14,047][23468] Updated weights for policy 0, policy_version 19403 (0.0007) -[2023-10-09 09:03:14,423][23468] Updated weights for policy 0, policy_version 19413 (0.0008) -[2023-10-09 09:03:14,798][23468] Updated weights for policy 0, policy_version 19423 (0.0007) -[2023-10-09 09:03:14,867][23469] Updated weights for policy 1, policy_version 19491 (0.0009) -[2023-10-09 09:03:15,238][23469] Updated weights for policy 1, policy_version 19501 (0.0007) -[2023-10-09 09:03:15,607][23469] Updated weights for policy 1, policy_version 19511 (0.0007) -[2023-10-09 09:03:16,078][22500] Fps is (10 sec: 16383.3, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 39878656. Throughput: 0: 1777.3, 1: 1805.1. Samples: 9975166. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-09 09:03:16,079][22500] Avg episode reward: [(0, '6.310'), (1, '5.720')] -[2023-10-09 09:03:18,536][23468] Updated weights for policy 0, policy_version 19433 (0.0009) -[2023-10-09 09:03:18,910][23468] Updated weights for policy 0, policy_version 19443 (0.0008) -[2023-10-09 09:03:19,273][23468] Updated weights for policy 0, policy_version 19453 (0.0007) -[2023-10-09 09:03:19,290][23469] Updated weights for policy 1, policy_version 19521 (0.0008) -[2023-10-09 09:03:19,664][23469] Updated weights for policy 1, policy_version 19531 (0.0009) -[2023-10-09 09:03:20,030][23469] Updated weights for policy 1, policy_version 19541 (0.0011) -[2023-10-09 09:03:20,400][23469] Updated weights for policy 1, policy_version 19551 (0.0009) -[2023-10-09 09:03:21,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 39944192. Throughput: 0: 1801.2, 1: 1795.2. Samples: 9987458. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-09 09:03:21,078][22500] Avg episode reward: [(0, '6.690'), (1, '5.600')] -[2023-10-09 09:03:23,041][23468] Updated weights for policy 0, policy_version 19463 (0.0008) -[2023-10-09 09:03:23,408][23468] Updated weights for policy 0, policy_version 19473 (0.0007) -[2023-10-09 09:03:23,779][23468] Updated weights for policy 0, policy_version 19483 (0.0007) -[2023-10-09 09:03:24,193][23469] Updated weights for policy 1, policy_version 19561 (0.0007) -[2023-10-09 09:03:24,565][23469] Updated weights for policy 1, policy_version 19571 (0.0007) -[2023-10-09 09:03:24,941][23469] Updated weights for policy 1, policy_version 19581 (0.0008) -[2023-10-09 09:03:26,078][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 40009728. Throughput: 0: 1782.8, 1: 1805.4. Samples: 10007586. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-09 09:03:26,079][22500] Avg episode reward: [(0, '7.210'), (1, '5.290')] -[2023-10-09 09:03:26,080][23265] Saving new best policy, reward=7.210! -[2023-10-09 09:03:27,592][23468] Updated weights for policy 0, policy_version 19493 (0.0008) -[2023-10-09 09:03:27,958][23468] Updated weights for policy 0, policy_version 19503 (0.0008) -[2023-10-09 09:03:28,335][23468] Updated weights for policy 0, policy_version 19513 (0.0010) -[2023-10-09 09:03:28,633][23469] Updated weights for policy 1, policy_version 19591 (0.0008) -[2023-10-09 09:03:29,011][23469] Updated weights for policy 1, policy_version 19601 (0.0009) -[2023-10-09 09:03:29,385][23469] Updated weights for policy 1, policy_version 19611 (0.0008) -[2023-10-09 09:03:31,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 40075264. Throughput: 0: 1775.8, 1: 1795.6. Samples: 10029250. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-09 09:03:31,078][22500] Avg episode reward: [(0, '6.740'), (1, '5.750')] -[2023-10-09 09:03:32,088][23468] Updated weights for policy 0, policy_version 19523 (0.0008) -[2023-10-09 09:03:32,476][23468] Updated weights for policy 0, policy_version 19533 (0.0007) -[2023-10-09 09:03:32,839][23468] Updated weights for policy 0, policy_version 19543 (0.0010) -[2023-10-09 09:03:33,122][23469] Updated weights for policy 1, policy_version 19621 (0.0007) -[2023-10-09 09:03:33,512][23469] Updated weights for policy 1, policy_version 19631 (0.0009) -[2023-10-09 09:03:33,885][23469] Updated weights for policy 1, policy_version 19641 (0.0009) -[2023-10-09 09:03:36,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 40140800. Throughput: 0: 1774.4, 1: 1809.4. Samples: 10039228. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:03:36,078][22500] Avg episode reward: [(0, '6.750'), (1, '6.060')] -[2023-10-09 09:03:36,503][23468] Updated weights for policy 0, policy_version 19553 (0.0009) -[2023-10-09 09:03:36,879][23468] Updated weights for policy 0, policy_version 19563 (0.0008) -[2023-10-09 09:03:37,245][23468] Updated weights for policy 0, policy_version 19573 (0.0008) -[2023-10-09 09:03:37,632][23468] Updated weights for policy 0, policy_version 19583 (0.0008) -[2023-10-09 09:03:37,677][23469] Updated weights for policy 1, policy_version 19651 (0.0009) -[2023-10-09 09:03:38,052][23469] Updated weights for policy 1, policy_version 19661 (0.0009) -[2023-10-09 09:03:38,422][23469] Updated weights for policy 1, policy_version 19671 (0.0011) -[2023-10-09 09:03:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 40206336. Throughput: 0: 1776.8, 1: 1791.6. Samples: 10061024. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:03:41,078][22500] Avg episode reward: [(0, '6.280'), (1, '6.300')] -[2023-10-09 09:03:41,341][23468] Updated weights for policy 0, policy_version 19593 (0.0009) -[2023-10-09 09:03:41,717][23468] Updated weights for policy 0, policy_version 19603 (0.0008) -[2023-10-09 09:03:42,087][23468] Updated weights for policy 0, policy_version 19613 (0.0009) -[2023-10-09 09:03:42,289][23469] Updated weights for policy 1, policy_version 19681 (0.0010) -[2023-10-09 09:03:42,649][23469] Updated weights for policy 1, policy_version 19691 (0.0010) -[2023-10-09 09:03:43,018][23469] Updated weights for policy 1, policy_version 19701 (0.0011) -[2023-10-09 09:03:43,385][23469] Updated weights for policy 1, policy_version 19711 (0.0011) -[2023-10-09 09:03:46,019][23468] Updated weights for policy 0, policy_version 19623 (0.0008) -[2023-10-09 09:03:46,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 40271872. Throughput: 0: 1793.1, 1: 1780.4. Samples: 10083354. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:03:46,078][22500] Avg episode reward: [(0, '6.830'), (1, '6.080')] -[2023-10-09 09:03:46,403][23468] Updated weights for policy 0, policy_version 19633 (0.0007) -[2023-10-09 09:03:46,782][23468] Updated weights for policy 0, policy_version 19643 (0.0010) -[2023-10-09 09:03:47,218][23469] Updated weights for policy 1, policy_version 19721 (0.0008) -[2023-10-09 09:03:47,584][23469] Updated weights for policy 1, policy_version 19731 (0.0007) -[2023-10-09 09:03:47,961][23469] Updated weights for policy 1, policy_version 19741 (0.0009) -[2023-10-09 09:03:50,583][23468] Updated weights for policy 0, policy_version 19653 (0.0009) -[2023-10-09 09:03:50,964][23468] Updated weights for policy 0, policy_version 19663 (0.0008) -[2023-10-09 09:03:51,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 40337408. Throughput: 0: 1776.6, 1: 1781.9. Samples: 10092970. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:03:51,078][22500] Avg episode reward: [(0, '6.570'), (1, '6.040')] -[2023-10-09 09:03:51,344][23468] Updated weights for policy 0, policy_version 19673 (0.0009) -[2023-10-09 09:03:51,669][23469] Updated weights for policy 1, policy_version 19751 (0.0008) -[2023-10-09 09:03:52,029][23469] Updated weights for policy 1, policy_version 19761 (0.0007) -[2023-10-09 09:03:52,402][23469] Updated weights for policy 1, policy_version 19771 (0.0007) -[2023-10-09 09:03:54,970][23468] Updated weights for policy 0, policy_version 19683 (0.0010) -[2023-10-09 09:03:55,342][23468] Updated weights for policy 0, policy_version 19693 (0.0008) -[2023-10-09 09:03:55,717][23468] Updated weights for policy 0, policy_version 19703 (0.0008) -[2023-10-09 09:03:56,044][23469] Updated weights for policy 1, policy_version 19781 (0.0008) -[2023-10-09 09:03:56,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 40435712. Throughput: 0: 1780.0, 1: 1785.8. Samples: 10115376. Policy #0 lag: (min: 31.0, avg: 31.3, max: 42.0) -[2023-10-09 09:03:56,079][22500] Avg episode reward: [(0, '5.930'), (1, '5.820')] -[2023-10-09 09:03:56,406][23469] Updated weights for policy 1, policy_version 19791 (0.0008) -[2023-10-09 09:03:56,779][23469] Updated weights for policy 1, policy_version 19801 (0.0007) -[2023-10-09 09:03:59,551][23468] Updated weights for policy 0, policy_version 19713 (0.0008) -[2023-10-09 09:03:59,923][23468] Updated weights for policy 0, policy_version 19723 (0.0010) -[2023-10-09 09:04:00,307][23468] Updated weights for policy 0, policy_version 19733 (0.0007) -[2023-10-09 09:04:00,498][23469] Updated weights for policy 1, policy_version 19811 (0.0008) -[2023-10-09 09:04:00,679][23468] Updated weights for policy 0, policy_version 19743 (0.0007) -[2023-10-09 09:04:00,868][23469] Updated weights for policy 1, policy_version 19821 (0.0010) -[2023-10-09 09:04:01,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 40501248. Throughput: 0: 1782.4, 1: 1804.8. Samples: 10136588. Policy #0 lag: (min: 31.0, avg: 31.3, max: 42.0) -[2023-10-09 09:04:01,078][22500] Avg episode reward: [(0, '6.040'), (1, '5.950')] -[2023-10-09 09:04:01,243][23469] Updated weights for policy 1, policy_version 19831 (0.0011) -[2023-10-09 09:04:04,247][23468] Updated weights for policy 0, policy_version 19753 (0.0010) -[2023-10-09 09:04:04,619][23468] Updated weights for policy 0, policy_version 19763 (0.0009) -[2023-10-09 09:04:04,993][23468] Updated weights for policy 0, policy_version 19773 (0.0008) -[2023-10-09 09:04:05,146][23469] Updated weights for policy 1, policy_version 19841 (0.0010) -[2023-10-09 09:04:05,522][23469] Updated weights for policy 1, policy_version 19851 (0.0011) -[2023-10-09 09:04:05,891][23469] Updated weights for policy 1, policy_version 19861 (0.0010) -[2023-10-09 09:04:06,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 40566784. Throughput: 0: 1778.0, 1: 1783.3. Samples: 10147720. Policy #0 lag: (min: 31.0, avg: 31.3, max: 42.0) -[2023-10-09 09:04:06,078][22500] Avg episode reward: [(0, '6.380'), (1, '5.810')] -[2023-10-09 09:04:06,263][23469] Updated weights for policy 1, policy_version 19871 (0.0008) -[2023-10-09 09:04:08,674][23468] Updated weights for policy 0, policy_version 19783 (0.0009) -[2023-10-09 09:04:09,046][23468] Updated weights for policy 0, policy_version 19793 (0.0009) -[2023-10-09 09:04:09,412][23468] Updated weights for policy 0, policy_version 19803 (0.0008) -[2023-10-09 09:04:09,984][23469] Updated weights for policy 1, policy_version 19881 (0.0007) -[2023-10-09 09:04:10,355][23469] Updated weights for policy 1, policy_version 19891 (0.0010) -[2023-10-09 09:04:10,728][23469] Updated weights for policy 1, policy_version 19901 (0.0010) -[2023-10-09 09:04:11,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 40665088. Throughput: 0: 1783.9, 1: 1804.0. Samples: 10169040. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 09:04:11,078][22500] Avg episode reward: [(0, '6.510'), (1, '6.150')] -[2023-10-09 09:04:13,203][23468] Updated weights for policy 0, policy_version 19813 (0.0008) -[2023-10-09 09:04:13,575][23468] Updated weights for policy 0, policy_version 19823 (0.0007) -[2023-10-09 09:04:13,956][23468] Updated weights for policy 0, policy_version 19833 (0.0009) -[2023-10-09 09:04:14,402][23469] Updated weights for policy 1, policy_version 19911 (0.0008) -[2023-10-09 09:04:14,777][23469] Updated weights for policy 1, policy_version 19921 (0.0007) -[2023-10-09 09:04:15,143][23469] Updated weights for policy 1, policy_version 19931 (0.0007) -[2023-10-09 09:04:16,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 40730624. Throughput: 0: 1779.0, 1: 1788.6. Samples: 10189794. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 09:04:16,078][22500] Avg episode reward: [(0, '6.940'), (1, '5.850')] -[2023-10-09 09:04:16,088][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000019936_20414464.pth... -[2023-10-09 09:04:16,089][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000019840_20316160.pth... -[2023-10-09 09:04:16,122][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000018176_18612224.pth -[2023-10-09 09:04:16,128][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000018240_18677760.pth -[2023-10-09 09:04:17,642][23468] Updated weights for policy 0, policy_version 19843 (0.0007) -[2023-10-09 09:04:18,013][23468] Updated weights for policy 0, policy_version 19853 (0.0007) -[2023-10-09 09:04:18,386][23468] Updated weights for policy 0, policy_version 19863 (0.0009) -[2023-10-09 09:04:19,013][23469] Updated weights for policy 1, policy_version 19941 (0.0009) -[2023-10-09 09:04:19,409][23469] Updated weights for policy 1, policy_version 19951 (0.0009) -[2023-10-09 09:04:19,773][23469] Updated weights for policy 1, policy_version 19961 (0.0008) -[2023-10-09 09:04:21,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 40796160. Throughput: 0: 1797.9, 1: 1810.0. Samples: 10201584. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 09:04:21,078][22500] Avg episode reward: [(0, '6.400'), (1, '5.920')] -[2023-10-09 09:04:22,206][23468] Updated weights for policy 0, policy_version 19873 (0.0009) -[2023-10-09 09:04:22,581][23468] Updated weights for policy 0, policy_version 19883 (0.0008) -[2023-10-09 09:04:22,960][23468] Updated weights for policy 0, policy_version 19893 (0.0007) -[2023-10-09 09:04:23,333][23468] Updated weights for policy 0, policy_version 19903 (0.0008) -[2023-10-09 09:04:23,556][23469] Updated weights for policy 1, policy_version 19971 (0.0007) -[2023-10-09 09:04:23,931][23469] Updated weights for policy 1, policy_version 19981 (0.0009) -[2023-10-09 09:04:24,294][23469] Updated weights for policy 1, policy_version 19991 (0.0009) -[2023-10-09 09:04:26,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 40861696. Throughput: 0: 1784.8, 1: 1785.4. Samples: 10221680. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 09:04:26,078][22500] Avg episode reward: [(0, '6.020'), (1, '5.720')] -[2023-10-09 09:04:26,999][23468] Updated weights for policy 0, policy_version 19913 (0.0009) -[2023-10-09 09:04:27,386][23468] Updated weights for policy 0, policy_version 19923 (0.0010) -[2023-10-09 09:04:27,759][23468] Updated weights for policy 0, policy_version 19933 (0.0009) -[2023-10-09 09:04:27,808][23469] Updated weights for policy 1, policy_version 20001 (0.0008) -[2023-10-09 09:04:28,167][23469] Updated weights for policy 1, policy_version 20011 (0.0007) -[2023-10-09 09:04:28,540][23469] Updated weights for policy 1, policy_version 20021 (0.0007) -[2023-10-09 09:04:28,904][23469] Updated weights for policy 1, policy_version 20031 (0.0007) -[2023-10-09 09:04:31,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 40927232. Throughput: 0: 1783.6, 1: 1793.8. Samples: 10244336. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:04:31,078][22500] Avg episode reward: [(0, '5.940'), (1, '5.640')] -[2023-10-09 09:04:31,762][23468] Updated weights for policy 0, policy_version 19943 (0.0010) -[2023-10-09 09:04:32,133][23468] Updated weights for policy 0, policy_version 19953 (0.0011) -[2023-10-09 09:04:32,512][23468] Updated weights for policy 0, policy_version 19963 (0.0007) -[2023-10-09 09:04:32,714][23469] Updated weights for policy 1, policy_version 20041 (0.0009) -[2023-10-09 09:04:33,085][23469] Updated weights for policy 1, policy_version 20051 (0.0011) -[2023-10-09 09:04:33,456][23469] Updated weights for policy 1, policy_version 20061 (0.0011) -[2023-10-09 09:04:36,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 40992768. Throughput: 0: 1780.0, 1: 1792.6. Samples: 10253736. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:04:36,079][22500] Avg episode reward: [(0, '6.390'), (1, '5.450')] -[2023-10-09 09:04:36,297][23468] Updated weights for policy 0, policy_version 19973 (0.0008) -[2023-10-09 09:04:36,665][23468] Updated weights for policy 0, policy_version 19983 (0.0009) -[2023-10-09 09:04:37,032][23468] Updated weights for policy 0, policy_version 19993 (0.0007) -[2023-10-09 09:04:37,285][23469] Updated weights for policy 1, policy_version 20071 (0.0008) -[2023-10-09 09:04:37,659][23469] Updated weights for policy 1, policy_version 20081 (0.0007) -[2023-10-09 09:04:38,017][23469] Updated weights for policy 1, policy_version 20091 (0.0008) -[2023-10-09 09:04:40,741][23468] Updated weights for policy 0, policy_version 20003 (0.0009) -[2023-10-09 09:04:41,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 41058304. Throughput: 0: 1788.3, 1: 1791.6. Samples: 10276468. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:04:41,078][22500] Avg episode reward: [(0, '6.530'), (1, '5.650')] -[2023-10-09 09:04:41,120][23468] Updated weights for policy 0, policy_version 20013 (0.0008) -[2023-10-09 09:04:41,500][23468] Updated weights for policy 0, policy_version 20023 (0.0008) -[2023-10-09 09:04:41,852][23469] Updated weights for policy 1, policy_version 20101 (0.0010) -[2023-10-09 09:04:42,232][23469] Updated weights for policy 1, policy_version 20111 (0.0009) -[2023-10-09 09:04:42,600][23469] Updated weights for policy 1, policy_version 20121 (0.0007) -[2023-10-09 09:04:45,318][23468] Updated weights for policy 0, policy_version 20033 (0.0009) -[2023-10-09 09:04:45,696][23468] Updated weights for policy 0, policy_version 20043 (0.0009) -[2023-10-09 09:04:46,072][23468] Updated weights for policy 0, policy_version 20053 (0.0007) -[2023-10-09 09:04:46,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 41123840. Throughput: 0: 1803.5, 1: 1792.8. Samples: 10298420. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:04:46,078][22500] Avg episode reward: [(0, '6.860'), (1, '6.030')] -[2023-10-09 09:04:46,343][23469] Updated weights for policy 1, policy_version 20131 (0.0010) -[2023-10-09 09:04:46,439][23468] Updated weights for policy 0, policy_version 20063 (0.0008) -[2023-10-09 09:04:46,718][23469] Updated weights for policy 1, policy_version 20141 (0.0009) -[2023-10-09 09:04:47,096][23469] Updated weights for policy 1, policy_version 20151 (0.0010) -[2023-10-09 09:04:50,141][23468] Updated weights for policy 0, policy_version 20073 (0.0010) -[2023-10-09 09:04:50,503][23468] Updated weights for policy 0, policy_version 20083 (0.0010) -[2023-10-09 09:04:50,879][23468] Updated weights for policy 0, policy_version 20093 (0.0008) -[2023-10-09 09:04:50,978][23469] Updated weights for policy 1, policy_version 20161 (0.0008) -[2023-10-09 09:04:51,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 41222144. Throughput: 0: 1778.4, 1: 1786.8. Samples: 10308158. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:04:51,078][22500] Avg episode reward: [(0, '6.030'), (1, '5.730')] -[2023-10-09 09:04:51,347][23469] Updated weights for policy 1, policy_version 20171 (0.0008) -[2023-10-09 09:04:51,710][23469] Updated weights for policy 1, policy_version 20181 (0.0010) -[2023-10-09 09:04:52,084][23469] Updated weights for policy 1, policy_version 20191 (0.0009) -[2023-10-09 09:04:54,710][23468] Updated weights for policy 0, policy_version 20103 (0.0010) -[2023-10-09 09:04:55,076][23468] Updated weights for policy 0, policy_version 20113 (0.0010) -[2023-10-09 09:04:55,448][23468] Updated weights for policy 0, policy_version 20123 (0.0010) -[2023-10-09 09:04:55,791][23469] Updated weights for policy 1, policy_version 20201 (0.0008) -[2023-10-09 09:04:56,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 41287680. Throughput: 0: 1800.0, 1: 1784.8. Samples: 10330358. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:04:56,078][22500] Avg episode reward: [(0, '6.230'), (1, '5.760')] -[2023-10-09 09:04:56,165][23469] Updated weights for policy 1, policy_version 20211 (0.0008) -[2023-10-09 09:04:56,533][23469] Updated weights for policy 1, policy_version 20221 (0.0007) -[2023-10-09 09:04:59,232][23468] Updated weights for policy 0, policy_version 20133 (0.0009) -[2023-10-09 09:04:59,611][23468] Updated weights for policy 0, policy_version 20143 (0.0007) -[2023-10-09 09:04:59,988][23468] Updated weights for policy 0, policy_version 20153 (0.0007) -[2023-10-09 09:05:00,284][23469] Updated weights for policy 1, policy_version 20231 (0.0009) -[2023-10-09 09:05:00,662][23469] Updated weights for policy 1, policy_version 20241 (0.0010) -[2023-10-09 09:05:01,031][23469] Updated weights for policy 1, policy_version 20251 (0.0009) -[2023-10-09 09:05:01,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 41353216. Throughput: 0: 1782.4, 1: 1796.7. Samples: 10350852. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:05:01,078][22500] Avg episode reward: [(0, '6.020'), (1, '5.910')] -[2023-10-09 09:05:03,725][23468] Updated weights for policy 0, policy_version 20163 (0.0008) -[2023-10-09 09:05:04,108][23468] Updated weights for policy 0, policy_version 20173 (0.0009) -[2023-10-09 09:05:04,480][23468] Updated weights for policy 0, policy_version 20183 (0.0008) -[2023-10-09 09:05:04,791][23469] Updated weights for policy 1, policy_version 20261 (0.0008) -[2023-10-09 09:05:05,183][23469] Updated weights for policy 1, policy_version 20271 (0.0009) -[2023-10-09 09:05:05,553][23469] Updated weights for policy 1, policy_version 20281 (0.0008) -[2023-10-09 09:05:06,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 41451520. Throughput: 0: 1801.3, 1: 1780.9. Samples: 10362784. Policy #0 lag: (min: 10.0, avg: 10.6, max: 25.0) -[2023-10-09 09:05:06,078][22500] Avg episode reward: [(0, '6.660'), (1, '6.200')] -[2023-10-09 09:05:08,329][23468] Updated weights for policy 0, policy_version 20193 (0.0007) -[2023-10-09 09:05:08,692][23468] Updated weights for policy 0, policy_version 20203 (0.0007) -[2023-10-09 09:05:09,061][23468] Updated weights for policy 0, policy_version 20213 (0.0007) -[2023-10-09 09:05:09,102][23469] Updated weights for policy 1, policy_version 20291 (0.0008) -[2023-10-09 09:05:09,438][23468] Updated weights for policy 0, policy_version 20223 (0.0007) -[2023-10-09 09:05:09,474][23469] Updated weights for policy 1, policy_version 20301 (0.0008) -[2023-10-09 09:05:09,846][23469] Updated weights for policy 1, policy_version 20311 (0.0007) -[2023-10-09 09:05:11,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 41517056. Throughput: 0: 1792.2, 1: 1801.9. Samples: 10383414. Policy #0 lag: (min: 10.0, avg: 10.6, max: 25.0) -[2023-10-09 09:05:11,078][22500] Avg episode reward: [(0, '6.580'), (1, '6.060')] -[2023-10-09 09:05:13,113][23468] Updated weights for policy 0, policy_version 20233 (0.0007) -[2023-10-09 09:05:13,419][23469] Updated weights for policy 1, policy_version 20321 (0.0007) -[2023-10-09 09:05:13,486][23468] Updated weights for policy 0, policy_version 20243 (0.0008) -[2023-10-09 09:05:13,782][23469] Updated weights for policy 1, policy_version 20331 (0.0008) -[2023-10-09 09:05:13,854][23468] Updated weights for policy 0, policy_version 20253 (0.0008) -[2023-10-09 09:05:14,154][23469] Updated weights for policy 1, policy_version 20341 (0.0010) -[2023-10-09 09:05:14,534][23469] Updated weights for policy 1, policy_version 20351 (0.0009) -[2023-10-09 09:05:16,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 41582592. Throughput: 0: 1789.5, 1: 1787.5. Samples: 10405302. Policy #0 lag: (min: 10.0, avg: 10.6, max: 25.0) -[2023-10-09 09:05:16,079][22500] Avg episode reward: [(0, '6.710'), (1, '5.950')] -[2023-10-09 09:05:17,560][23468] Updated weights for policy 0, policy_version 20263 (0.0009) -[2023-10-09 09:05:17,954][23468] Updated weights for policy 0, policy_version 20273 (0.0010) -[2023-10-09 09:05:18,322][23468] Updated weights for policy 0, policy_version 20283 (0.0008) -[2023-10-09 09:05:18,366][23469] Updated weights for policy 1, policy_version 20361 (0.0008) -[2023-10-09 09:05:18,734][23469] Updated weights for policy 1, policy_version 20371 (0.0009) -[2023-10-09 09:05:19,105][23469] Updated weights for policy 1, policy_version 20381 (0.0008) -[2023-10-09 09:05:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 41648128. Throughput: 0: 1795.1, 1: 1799.9. Samples: 10415508. Policy #0 lag: (min: 10.0, avg: 10.6, max: 25.0) -[2023-10-09 09:05:21,078][22500] Avg episode reward: [(0, '6.700'), (1, '6.150')] -[2023-10-09 09:05:22,142][23468] Updated weights for policy 0, policy_version 20293 (0.0009) -[2023-10-09 09:05:22,516][23468] Updated weights for policy 0, policy_version 20303 (0.0008) -[2023-10-09 09:05:22,864][23469] Updated weights for policy 1, policy_version 20391 (0.0008) -[2023-10-09 09:05:22,894][23468] Updated weights for policy 0, policy_version 20313 (0.0008) -[2023-10-09 09:05:23,240][23469] Updated weights for policy 1, policy_version 20401 (0.0009) -[2023-10-09 09:05:23,605][23469] Updated weights for policy 1, policy_version 20411 (0.0008) -[2023-10-09 09:05:26,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 41713664. Throughput: 0: 1787.2, 1: 1778.4. Samples: 10436916. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:05:26,078][22500] Avg episode reward: [(0, '6.780'), (1, '6.290')] -[2023-10-09 09:05:26,608][23468] Updated weights for policy 0, policy_version 20323 (0.0007) -[2023-10-09 09:05:26,986][23468] Updated weights for policy 0, policy_version 20333 (0.0008) -[2023-10-09 09:05:27,363][23468] Updated weights for policy 0, policy_version 20343 (0.0008) -[2023-10-09 09:05:27,408][23469] Updated weights for policy 1, policy_version 20421 (0.0009) -[2023-10-09 09:05:27,783][23469] Updated weights for policy 1, policy_version 20431 (0.0007) -[2023-10-09 09:05:28,149][23469] Updated weights for policy 1, policy_version 20441 (0.0009) -[2023-10-09 09:05:31,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 41779200. Throughput: 0: 1790.6, 1: 1784.9. Samples: 10459318. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:05:31,079][22500] Avg episode reward: [(0, '7.130'), (1, '5.650')] -[2023-10-09 09:05:31,110][23468] Updated weights for policy 0, policy_version 20353 (0.0008) -[2023-10-09 09:05:31,491][23468] Updated weights for policy 0, policy_version 20363 (0.0007) -[2023-10-09 09:05:31,853][23468] Updated weights for policy 0, policy_version 20373 (0.0008) -[2023-10-09 09:05:31,918][23469] Updated weights for policy 1, policy_version 20451 (0.0008) -[2023-10-09 09:05:32,229][23468] Updated weights for policy 0, policy_version 20383 (0.0007) -[2023-10-09 09:05:32,297][23469] Updated weights for policy 1, policy_version 20461 (0.0007) -[2023-10-09 09:05:32,668][23469] Updated weights for policy 1, policy_version 20471 (0.0008) -[2023-10-09 09:05:35,918][23468] Updated weights for policy 0, policy_version 20393 (0.0007) -[2023-10-09 09:05:36,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 41844736. Throughput: 0: 1790.8, 1: 1786.8. Samples: 10469152. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:05:36,078][22500] Avg episode reward: [(0, '6.920'), (1, '5.700')] -[2023-10-09 09:05:36,304][23468] Updated weights for policy 0, policy_version 20403 (0.0009) -[2023-10-09 09:05:36,468][23469] Updated weights for policy 1, policy_version 20481 (0.0009) -[2023-10-09 09:05:36,669][23468] Updated weights for policy 0, policy_version 20413 (0.0007) -[2023-10-09 09:05:36,837][23469] Updated weights for policy 1, policy_version 20491 (0.0007) -[2023-10-09 09:05:37,204][23469] Updated weights for policy 1, policy_version 20501 (0.0007) -[2023-10-09 09:05:37,577][23469] Updated weights for policy 1, policy_version 20511 (0.0010) -[2023-10-09 09:05:40,406][23468] Updated weights for policy 0, policy_version 20423 (0.0008) -[2023-10-09 09:05:40,791][23468] Updated weights for policy 0, policy_version 20433 (0.0008) -[2023-10-09 09:05:41,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 41910272. Throughput: 0: 1792.7, 1: 1790.0. Samples: 10491578. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:05:41,078][22500] Avg episode reward: [(0, '7.430'), (1, '5.880')] -[2023-10-09 09:05:41,152][23468] Updated weights for policy 0, policy_version 20443 (0.0009) -[2023-10-09 09:05:41,292][23469] Updated weights for policy 1, policy_version 20521 (0.0008) -[2023-10-09 09:05:41,337][23265] Saving new best policy, reward=7.430! -[2023-10-09 09:05:41,661][23469] Updated weights for policy 1, policy_version 20531 (0.0010) -[2023-10-09 09:05:42,037][23469] Updated weights for policy 1, policy_version 20541 (0.0008) -[2023-10-09 09:05:44,974][23468] Updated weights for policy 0, policy_version 20453 (0.0008) -[2023-10-09 09:05:45,359][23468] Updated weights for policy 0, policy_version 20463 (0.0008) -[2023-10-09 09:05:45,737][23468] Updated weights for policy 0, policy_version 20473 (0.0010) -[2023-10-09 09:05:45,751][23469] Updated weights for policy 1, policy_version 20551 (0.0008) -[2023-10-09 09:05:46,078][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 42008576. Throughput: 0: 1806.3, 1: 1795.3. Samples: 10512922. Policy #0 lag: (min: 1.0, avg: 26.3, max: 32.0) -[2023-10-09 09:05:46,079][22500] Avg episode reward: [(0, '7.020'), (1, '5.670')] -[2023-10-09 09:05:46,121][23469] Updated weights for policy 1, policy_version 20561 (0.0007) -[2023-10-09 09:05:46,499][23469] Updated weights for policy 1, policy_version 20571 (0.0009) -[2023-10-09 09:05:49,385][23468] Updated weights for policy 0, policy_version 20483 (0.0008) -[2023-10-09 09:05:49,766][23468] Updated weights for policy 0, policy_version 20493 (0.0007) -[2023-10-09 09:05:50,141][23468] Updated weights for policy 0, policy_version 20503 (0.0008) -[2023-10-09 09:05:50,312][23469] Updated weights for policy 1, policy_version 20581 (0.0011) -[2023-10-09 09:05:50,709][23469] Updated weights for policy 1, policy_version 20591 (0.0008) -[2023-10-09 09:05:51,077][22500] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 42074112. Throughput: 0: 1789.6, 1: 1784.0. Samples: 10523598. Policy #0 lag: (min: 1.0, avg: 26.3, max: 32.0) -[2023-10-09 09:05:51,079][22500] Avg episode reward: [(0, '6.830'), (1, '6.110')] -[2023-10-09 09:05:51,080][23469] Updated weights for policy 1, policy_version 20601 (0.0008) -[2023-10-09 09:05:53,899][23468] Updated weights for policy 0, policy_version 20513 (0.0008) -[2023-10-09 09:05:54,276][23468] Updated weights for policy 0, policy_version 20523 (0.0007) -[2023-10-09 09:05:54,647][23468] Updated weights for policy 0, policy_version 20533 (0.0007) -[2023-10-09 09:05:54,839][23469] Updated weights for policy 1, policy_version 20611 (0.0009) -[2023-10-09 09:05:55,017][23468] Updated weights for policy 0, policy_version 20543 (0.0007) -[2023-10-09 09:05:55,217][23469] Updated weights for policy 1, policy_version 20621 (0.0010) -[2023-10-09 09:05:55,578][23469] Updated weights for policy 1, policy_version 20631 (0.0008) -[2023-10-09 09:05:56,078][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 42172416. Throughput: 0: 1794.6, 1: 1801.8. Samples: 10545252. Policy #0 lag: (min: 1.0, avg: 26.3, max: 32.0) -[2023-10-09 09:05:56,079][22500] Avg episode reward: [(0, '6.640'), (1, '6.250')] -[2023-10-09 09:05:58,964][23468] Updated weights for policy 0, policy_version 20553 (0.0008) -[2023-10-09 09:05:59,180][23469] Updated weights for policy 1, policy_version 20641 (0.0008) -[2023-10-09 09:05:59,342][23468] Updated weights for policy 0, policy_version 20563 (0.0009) -[2023-10-09 09:05:59,547][23469] Updated weights for policy 1, policy_version 20651 (0.0008) -[2023-10-09 09:05:59,710][23468] Updated weights for policy 0, policy_version 20573 (0.0008) -[2023-10-09 09:05:59,923][23469] Updated weights for policy 1, policy_version 20661 (0.0009) -[2023-10-09 09:06:00,299][23469] Updated weights for policy 1, policy_version 20671 (0.0009) -[2023-10-09 09:06:01,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 42237952. Throughput: 0: 1771.0, 1: 1781.6. Samples: 10565170. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:06:01,078][22500] Avg episode reward: [(0, '6.980'), (1, '6.220')] -[2023-10-09 09:06:03,460][23468] Updated weights for policy 0, policy_version 20583 (0.0009) -[2023-10-09 09:06:03,840][23468] Updated weights for policy 0, policy_version 20593 (0.0011) -[2023-10-09 09:06:04,126][23469] Updated weights for policy 1, policy_version 20681 (0.0007) -[2023-10-09 09:06:04,218][23468] Updated weights for policy 0, policy_version 20603 (0.0008) -[2023-10-09 09:06:04,487][23469] Updated weights for policy 1, policy_version 20691 (0.0007) -[2023-10-09 09:06:04,854][23469] Updated weights for policy 1, policy_version 20701 (0.0007) -[2023-10-09 09:06:06,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 42303488. Throughput: 0: 1798.4, 1: 1809.5. Samples: 10577860. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:06:06,078][22500] Avg episode reward: [(0, '7.010'), (1, '5.860')] -[2023-10-09 09:06:08,071][23468] Updated weights for policy 0, policy_version 20613 (0.0008) -[2023-10-09 09:06:08,446][23468] Updated weights for policy 0, policy_version 20623 (0.0009) -[2023-10-09 09:06:08,460][23469] Updated weights for policy 1, policy_version 20711 (0.0009) -[2023-10-09 09:06:08,823][23469] Updated weights for policy 1, policy_version 20721 (0.0007) -[2023-10-09 09:06:08,826][23468] Updated weights for policy 0, policy_version 20633 (0.0009) -[2023-10-09 09:06:09,193][23469] Updated weights for policy 1, policy_version 20731 (0.0009) -[2023-10-09 09:06:11,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 42369024. Throughput: 0: 1768.1, 1: 1798.5. Samples: 10597414. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:06:11,078][22500] Avg episode reward: [(0, '6.620'), (1, '5.710')] -[2023-10-09 09:06:12,532][23468] Updated weights for policy 0, policy_version 20643 (0.0008) -[2023-10-09 09:06:12,903][23468] Updated weights for policy 0, policy_version 20653 (0.0008) -[2023-10-09 09:06:13,014][23469] Updated weights for policy 1, policy_version 20741 (0.0008) -[2023-10-09 09:06:13,280][23468] Updated weights for policy 0, policy_version 20663 (0.0008) -[2023-10-09 09:06:13,379][23469] Updated weights for policy 1, policy_version 20751 (0.0007) -[2023-10-09 09:06:13,742][23469] Updated weights for policy 1, policy_version 20761 (0.0007) -[2023-10-09 09:06:16,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 42434560. Throughput: 0: 1772.6, 1: 1790.2. Samples: 10619642. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:06:16,079][22500] Avg episode reward: [(0, '6.520'), (1, '6.090')] -[2023-10-09 09:06:16,090][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000020768_21266432.pth... -[2023-10-09 09:06:16,090][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000020672_21168128.pth... -[2023-10-09 09:06:16,119][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000019104_19562496.pth -[2023-10-09 09:06:16,127][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000019008_19464192.pth -[2023-10-09 09:06:17,049][23468] Updated weights for policy 0, policy_version 20673 (0.0007) -[2023-10-09 09:06:17,422][23468] Updated weights for policy 0, policy_version 20683 (0.0007) -[2023-10-09 09:06:17,599][23469] Updated weights for policy 1, policy_version 20771 (0.0008) -[2023-10-09 09:06:17,791][23468] Updated weights for policy 0, policy_version 20693 (0.0007) -[2023-10-09 09:06:17,974][23469] Updated weights for policy 1, policy_version 20781 (0.0007) -[2023-10-09 09:06:18,165][23468] Updated weights for policy 0, policy_version 20703 (0.0007) -[2023-10-09 09:06:18,340][23469] Updated weights for policy 1, policy_version 20791 (0.0009) -[2023-10-09 09:06:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 42500096. Throughput: 0: 1770.8, 1: 1790.4. Samples: 10629404. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 09:06:21,078][22500] Avg episode reward: [(0, '6.370'), (1, '6.360')] -[2023-10-09 09:06:21,079][23343] Saving new best policy, reward=6.360! -[2023-10-09 09:06:21,921][23469] Updated weights for policy 1, policy_version 20801 (0.0008) -[2023-10-09 09:06:22,016][23468] Updated weights for policy 0, policy_version 20713 (0.0008) -[2023-10-09 09:06:22,294][23469] Updated weights for policy 1, policy_version 20811 (0.0008) -[2023-10-09 09:06:22,391][23468] Updated weights for policy 0, policy_version 20723 (0.0007) -[2023-10-09 09:06:22,667][23469] Updated weights for policy 1, policy_version 20821 (0.0009) -[2023-10-09 09:06:22,762][23468] Updated weights for policy 0, policy_version 20733 (0.0009) -[2023-10-09 09:06:23,031][23469] Updated weights for policy 1, policy_version 20831 (0.0008) -[2023-10-09 09:06:26,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 42565632. Throughput: 0: 1766.5, 1: 1798.4. Samples: 10652002. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 09:06:26,079][22500] Avg episode reward: [(0, '6.940'), (1, '6.180')] -[2023-10-09 09:06:26,398][23468] Updated weights for policy 0, policy_version 20743 (0.0009) -[2023-10-09 09:06:26,700][23469] Updated weights for policy 1, policy_version 20841 (0.0008) -[2023-10-09 09:06:26,770][23468] Updated weights for policy 0, policy_version 20753 (0.0009) -[2023-10-09 09:06:27,064][23469] Updated weights for policy 1, policy_version 20851 (0.0008) -[2023-10-09 09:06:27,147][23468] Updated weights for policy 0, policy_version 20763 (0.0008) -[2023-10-09 09:06:27,432][23469] Updated weights for policy 1, policy_version 20861 (0.0010) -[2023-10-09 09:06:31,014][23468] Updated weights for policy 0, policy_version 20773 (0.0008) -[2023-10-09 09:06:31,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 42631168. Throughput: 0: 1779.5, 1: 1806.9. Samples: 10674312. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 09:06:31,078][22500] Avg episode reward: [(0, '6.460'), (1, '6.120')] -[2023-10-09 09:06:31,247][23469] Updated weights for policy 1, policy_version 20871 (0.0009) -[2023-10-09 09:06:31,380][23468] Updated weights for policy 0, policy_version 20783 (0.0008) -[2023-10-09 09:06:31,616][23469] Updated weights for policy 1, policy_version 20881 (0.0010) -[2023-10-09 09:06:31,753][23468] Updated weights for policy 0, policy_version 20793 (0.0007) -[2023-10-09 09:06:31,982][23469] Updated weights for policy 1, policy_version 20891 (0.0008) -[2023-10-09 09:06:35,608][23468] Updated weights for policy 0, policy_version 20803 (0.0007) -[2023-10-09 09:06:35,774][23469] Updated weights for policy 1, policy_version 20901 (0.0008) -[2023-10-09 09:06:35,979][23468] Updated weights for policy 0, policy_version 20813 (0.0009) -[2023-10-09 09:06:36,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 42696704. Throughput: 0: 1763.5, 1: 1805.5. Samples: 10684200. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 09:06:36,079][22500] Avg episode reward: [(0, '6.570'), (1, '6.190')] -[2023-10-09 09:06:36,162][23469] Updated weights for policy 1, policy_version 20911 (0.0008) -[2023-10-09 09:06:36,345][23468] Updated weights for policy 0, policy_version 20823 (0.0009) -[2023-10-09 09:06:36,537][23469] Updated weights for policy 1, policy_version 20921 (0.0007) -[2023-10-09 09:06:40,082][23468] Updated weights for policy 0, policy_version 20833 (0.0009) -[2023-10-09 09:06:40,274][23469] Updated weights for policy 1, policy_version 20931 (0.0008) -[2023-10-09 09:06:40,460][23468] Updated weights for policy 0, policy_version 20843 (0.0008) -[2023-10-09 09:06:40,645][23469] Updated weights for policy 1, policy_version 20941 (0.0007) -[2023-10-09 09:06:40,821][23468] Updated weights for policy 0, policy_version 20853 (0.0010) -[2023-10-09 09:06:41,008][23469] Updated weights for policy 1, policy_version 20951 (0.0008) -[2023-10-09 09:06:41,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 42762240. Throughput: 0: 1779.4, 1: 1800.7. Samples: 10706354. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-09 09:06:41,079][22500] Avg episode reward: [(0, '5.890'), (1, '6.100')] -[2023-10-09 09:06:41,197][23468] Updated weights for policy 0, policy_version 20863 (0.0009) -[2023-10-09 09:06:44,680][23469] Updated weights for policy 1, policy_version 20961 (0.0010) -[2023-10-09 09:06:44,995][23468] Updated weights for policy 0, policy_version 20873 (0.0009) -[2023-10-09 09:06:45,037][23469] Updated weights for policy 1, policy_version 20971 (0.0009) -[2023-10-09 09:06:45,373][23468] Updated weights for policy 0, policy_version 20883 (0.0009) -[2023-10-09 09:06:45,400][23469] Updated weights for policy 1, policy_version 20981 (0.0008) -[2023-10-09 09:06:45,745][23468] Updated weights for policy 0, policy_version 20893 (0.0008) -[2023-10-09 09:06:45,768][23469] Updated weights for policy 1, policy_version 20991 (0.0007) -[2023-10-09 09:06:46,077][22500] Fps is (10 sec: 19661.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 42893312. Throughput: 0: 1785.5, 1: 1805.9. Samples: 10726784. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-09 09:06:46,078][22500] Avg episode reward: [(0, '6.280'), (1, '6.000')] -[2023-10-09 09:06:49,571][23468] Updated weights for policy 0, policy_version 20903 (0.0007) -[2023-10-09 09:06:49,588][23469] Updated weights for policy 1, policy_version 21001 (0.0008) -[2023-10-09 09:06:49,937][23468] Updated weights for policy 0, policy_version 20913 (0.0008) -[2023-10-09 09:06:49,943][23469] Updated weights for policy 1, policy_version 21011 (0.0007) -[2023-10-09 09:06:50,315][23469] Updated weights for policy 1, policy_version 21021 (0.0008) -[2023-10-09 09:06:50,317][23468] Updated weights for policy 0, policy_version 20923 (0.0007) -[2023-10-09 09:06:51,077][22500] Fps is (10 sec: 19661.4, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 42958848. Throughput: 0: 1773.2, 1: 1798.5. Samples: 10738588. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-09 09:06:51,078][22500] Avg episode reward: [(0, '6.570'), (1, '6.050')] -[2023-10-09 09:06:54,039][23468] Updated weights for policy 0, policy_version 20933 (0.0007) -[2023-10-09 09:06:54,087][23469] Updated weights for policy 1, policy_version 21031 (0.0009) -[2023-10-09 09:06:54,409][23468] Updated weights for policy 0, policy_version 20943 (0.0008) -[2023-10-09 09:06:54,447][23469] Updated weights for policy 1, policy_version 21041 (0.0008) -[2023-10-09 09:06:54,784][23468] Updated weights for policy 0, policy_version 20953 (0.0008) -[2023-10-09 09:06:54,820][23469] Updated weights for policy 1, policy_version 21051 (0.0008) -[2023-10-09 09:06:56,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 43024384. Throughput: 0: 1796.9, 1: 1799.2. Samples: 10759242. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:06:56,079][22500] Avg episode reward: [(0, '6.670'), (1, '6.100')] -[2023-10-09 09:06:58,512][23469] Updated weights for policy 1, policy_version 21061 (0.0007) -[2023-10-09 09:06:58,754][23468] Updated weights for policy 0, policy_version 20963 (0.0009) -[2023-10-09 09:06:58,884][23469] Updated weights for policy 1, policy_version 21071 (0.0007) -[2023-10-09 09:06:59,121][23468] Updated weights for policy 0, policy_version 20973 (0.0009) -[2023-10-09 09:06:59,249][23469] Updated weights for policy 1, policy_version 21081 (0.0008) -[2023-10-09 09:06:59,491][23468] Updated weights for policy 0, policy_version 20983 (0.0008) -[2023-10-09 09:07:01,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 43089920. Throughput: 0: 1768.9, 1: 1797.8. Samples: 10780144. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:07:01,078][22500] Avg episode reward: [(0, '6.370'), (1, '6.070')] -[2023-10-09 09:07:03,099][23469] Updated weights for policy 1, policy_version 21091 (0.0009) -[2023-10-09 09:07:03,208][23468] Updated weights for policy 0, policy_version 20993 (0.0007) -[2023-10-09 09:07:03,473][23469] Updated weights for policy 1, policy_version 21101 (0.0008) -[2023-10-09 09:07:03,578][23468] Updated weights for policy 0, policy_version 21003 (0.0007) -[2023-10-09 09:07:03,842][23469] Updated weights for policy 1, policy_version 21111 (0.0008) -[2023-10-09 09:07:03,950][23468] Updated weights for policy 0, policy_version 21013 (0.0009) -[2023-10-09 09:07:04,320][23468] Updated weights for policy 0, policy_version 21023 (0.0007) -[2023-10-09 09:07:06,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 43155456. Throughput: 0: 1797.3, 1: 1810.7. Samples: 10791762. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:07:06,078][22500] Avg episode reward: [(0, '6.790'), (1, '6.260')] -[2023-10-09 09:07:07,707][23469] Updated weights for policy 1, policy_version 21121 (0.0009) -[2023-10-09 09:07:08,066][23468] Updated weights for policy 0, policy_version 21033 (0.0008) -[2023-10-09 09:07:08,068][23469] Updated weights for policy 1, policy_version 21131 (0.0008) -[2023-10-09 09:07:08,431][23469] Updated weights for policy 1, policy_version 21141 (0.0010) -[2023-10-09 09:07:08,450][23468] Updated weights for policy 0, policy_version 21043 (0.0009) -[2023-10-09 09:07:08,806][23469] Updated weights for policy 1, policy_version 21151 (0.0008) -[2023-10-09 09:07:08,823][23468] Updated weights for policy 0, policy_version 21053 (0.0009) -[2023-10-09 09:07:11,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 43220992. Throughput: 0: 1773.7, 1: 1789.6. Samples: 10812348. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:07:11,078][22500] Avg episode reward: [(0, '6.710'), (1, '6.110')] -[2023-10-09 09:07:12,576][23469] Updated weights for policy 1, policy_version 21161 (0.0008) -[2023-10-09 09:07:12,779][23468] Updated weights for policy 0, policy_version 21063 (0.0008) -[2023-10-09 09:07:12,944][23469] Updated weights for policy 1, policy_version 21171 (0.0007) -[2023-10-09 09:07:13,156][23468] Updated weights for policy 0, policy_version 21073 (0.0007) -[2023-10-09 09:07:13,316][23469] Updated weights for policy 1, policy_version 21181 (0.0007) -[2023-10-09 09:07:13,524][23468] Updated weights for policy 0, policy_version 21083 (0.0007) -[2023-10-09 09:07:16,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 43286528. Throughput: 0: 1773.4, 1: 1788.6. Samples: 10834602. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-09 09:07:16,078][22500] Avg episode reward: [(0, '6.200'), (1, '5.840')] -[2023-10-09 09:07:17,187][23469] Updated weights for policy 1, policy_version 21191 (0.0008) -[2023-10-09 09:07:17,201][23468] Updated weights for policy 0, policy_version 21093 (0.0008) -[2023-10-09 09:07:17,554][23469] Updated weights for policy 1, policy_version 21201 (0.0007) -[2023-10-09 09:07:17,571][23468] Updated weights for policy 0, policy_version 21103 (0.0008) -[2023-10-09 09:07:17,914][23469] Updated weights for policy 1, policy_version 21211 (0.0008) -[2023-10-09 09:07:17,947][23468] Updated weights for policy 0, policy_version 21113 (0.0007) -[2023-10-09 09:07:21,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 43352064. Throughput: 0: 1771.4, 1: 1783.6. Samples: 10844174. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-09 09:07:21,079][22500] Avg episode reward: [(0, '5.920'), (1, '5.830')] -[2023-10-09 09:07:21,652][23468] Updated weights for policy 0, policy_version 21123 (0.0008) -[2023-10-09 09:07:21,897][23469] Updated weights for policy 1, policy_version 21221 (0.0008) -[2023-10-09 09:07:22,019][23468] Updated weights for policy 0, policy_version 21133 (0.0007) -[2023-10-09 09:07:22,267][23469] Updated weights for policy 1, policy_version 21231 (0.0007) -[2023-10-09 09:07:22,383][23468] Updated weights for policy 0, policy_version 21143 (0.0009) -[2023-10-09 09:07:22,642][23469] Updated weights for policy 1, policy_version 21241 (0.0007) -[2023-10-09 09:07:26,001][23468] Updated weights for policy 0, policy_version 21153 (0.0008) -[2023-10-09 09:07:26,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 43417600. Throughput: 0: 1776.5, 1: 1780.8. Samples: 10866430. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-09 09:07:26,079][22500] Avg episode reward: [(0, '6.160'), (1, '5.810')] -[2023-10-09 09:07:26,314][23469] Updated weights for policy 1, policy_version 21251 (0.0007) -[2023-10-09 09:07:26,372][23468] Updated weights for policy 0, policy_version 21163 (0.0009) -[2023-10-09 09:07:26,724][23469] Updated weights for policy 1, policy_version 21261 (0.0009) -[2023-10-09 09:07:26,746][23468] Updated weights for policy 0, policy_version 21173 (0.0009) -[2023-10-09 09:07:27,086][23469] Updated weights for policy 1, policy_version 21271 (0.0007) -[2023-10-09 09:07:27,124][23468] Updated weights for policy 0, policy_version 21183 (0.0009) -[2023-10-09 09:07:30,791][23469] Updated weights for policy 1, policy_version 21281 (0.0007) -[2023-10-09 09:07:30,999][23468] Updated weights for policy 0, policy_version 21193 (0.0009) -[2023-10-09 09:07:31,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 43483136. Throughput: 0: 1790.7, 1: 1801.5. Samples: 10888430. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-09 09:07:31,078][22500] Avg episode reward: [(0, '6.280'), (1, '5.930')] -[2023-10-09 09:07:31,146][23469] Updated weights for policy 1, policy_version 21291 (0.0009) -[2023-10-09 09:07:31,372][23468] Updated weights for policy 0, policy_version 21203 (0.0009) -[2023-10-09 09:07:31,524][23469] Updated weights for policy 1, policy_version 21301 (0.0007) -[2023-10-09 09:07:31,734][23468] Updated weights for policy 0, policy_version 21213 (0.0010) -[2023-10-09 09:07:31,889][23469] Updated weights for policy 1, policy_version 21311 (0.0009) -[2023-10-09 09:07:35,614][23468] Updated weights for policy 0, policy_version 21223 (0.0008) -[2023-10-09 09:07:35,641][23469] Updated weights for policy 1, policy_version 21321 (0.0011) -[2023-10-09 09:07:35,986][23468] Updated weights for policy 0, policy_version 21233 (0.0008) -[2023-10-09 09:07:36,010][23469] Updated weights for policy 1, policy_version 21331 (0.0009) -[2023-10-09 09:07:36,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 43548672. Throughput: 0: 1773.2, 1: 1770.4. Samples: 10898052. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-09 09:07:36,078][22500] Avg episode reward: [(0, '6.430'), (1, '6.000')] -[2023-10-09 09:07:36,350][23468] Updated weights for policy 0, policy_version 21243 (0.0008) -[2023-10-09 09:07:36,376][23469] Updated weights for policy 1, policy_version 21341 (0.0008) -[2023-10-09 09:07:40,082][23468] Updated weights for policy 0, policy_version 21253 (0.0009) -[2023-10-09 09:07:40,104][23469] Updated weights for policy 1, policy_version 21351 (0.0010) -[2023-10-09 09:07:40,464][23468] Updated weights for policy 0, policy_version 21263 (0.0009) -[2023-10-09 09:07:40,469][23469] Updated weights for policy 1, policy_version 21361 (0.0008) -[2023-10-09 09:07:40,823][23468] Updated weights for policy 0, policy_version 21273 (0.0008) -[2023-10-09 09:07:40,846][23469] Updated weights for policy 1, policy_version 21371 (0.0007) -[2023-10-09 09:07:41,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 43646976. Throughput: 0: 1782.8, 1: 1800.2. Samples: 10920476. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-09 09:07:41,078][22500] Avg episode reward: [(0, '6.520'), (1, '5.710')] -[2023-10-09 09:07:44,560][23469] Updated weights for policy 1, policy_version 21381 (0.0007) -[2023-10-09 09:07:44,653][23468] Updated weights for policy 0, policy_version 21283 (0.0008) -[2023-10-09 09:07:44,930][23469] Updated weights for policy 1, policy_version 21391 (0.0007) -[2023-10-09 09:07:45,014][23468] Updated weights for policy 0, policy_version 21293 (0.0007) -[2023-10-09 09:07:45,293][23469] Updated weights for policy 1, policy_version 21401 (0.0007) -[2023-10-09 09:07:45,383][23468] Updated weights for policy 0, policy_version 21303 (0.0007) -[2023-10-09 09:07:46,078][22500] Fps is (10 sec: 19660.7, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 43745280. Throughput: 0: 1787.6, 1: 1773.9. Samples: 10940412. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-09 09:07:46,079][22500] Avg episode reward: [(0, '6.590'), (1, '5.920')] -[2023-10-09 09:07:49,018][23469] Updated weights for policy 1, policy_version 21411 (0.0008) -[2023-10-09 09:07:49,189][23468] Updated weights for policy 0, policy_version 21313 (0.0008) -[2023-10-09 09:07:49,383][23469] Updated weights for policy 1, policy_version 21421 (0.0008) -[2023-10-09 09:07:49,563][23468] Updated weights for policy 0, policy_version 21323 (0.0009) -[2023-10-09 09:07:49,755][23469] Updated weights for policy 1, policy_version 21431 (0.0008) -[2023-10-09 09:07:49,935][23468] Updated weights for policy 0, policy_version 21333 (0.0009) -[2023-10-09 09:07:50,304][23468] Updated weights for policy 0, policy_version 21343 (0.0008) -[2023-10-09 09:07:51,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 43810816. Throughput: 0: 1773.7, 1: 1794.6. Samples: 10952338. Policy #0 lag: (min: 27.0, avg: 27.8, max: 46.0) -[2023-10-09 09:07:51,078][22500] Avg episode reward: [(0, '6.640'), (1, '6.490')] -[2023-10-09 09:07:51,078][23343] Saving new best policy, reward=6.490! -[2023-10-09 09:07:53,596][23469] Updated weights for policy 1, policy_version 21441 (0.0007) -[2023-10-09 09:07:53,959][23469] Updated weights for policy 1, policy_version 21451 (0.0008) -[2023-10-09 09:07:54,089][23468] Updated weights for policy 0, policy_version 21353 (0.0007) -[2023-10-09 09:07:54,320][23469] Updated weights for policy 1, policy_version 21461 (0.0008) -[2023-10-09 09:07:54,467][23468] Updated weights for policy 0, policy_version 21363 (0.0007) -[2023-10-09 09:07:54,695][23469] Updated weights for policy 1, policy_version 21471 (0.0009) -[2023-10-09 09:07:54,843][23468] Updated weights for policy 0, policy_version 21373 (0.0008) -[2023-10-09 09:07:56,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 43876352. Throughput: 0: 1782.7, 1: 1774.6. Samples: 10972426. Policy #0 lag: (min: 27.0, avg: 27.8, max: 46.0) -[2023-10-09 09:07:56,079][22500] Avg episode reward: [(0, '6.760'), (1, '6.550')] -[2023-10-09 09:07:56,080][23343] Saving new best policy, reward=6.550! -[2023-10-09 09:07:58,665][23469] Updated weights for policy 1, policy_version 21481 (0.0009) -[2023-10-09 09:07:58,770][23468] Updated weights for policy 0, policy_version 21383 (0.0008) -[2023-10-09 09:07:59,041][23469] Updated weights for policy 1, policy_version 21491 (0.0009) -[2023-10-09 09:07:59,144][23468] Updated weights for policy 0, policy_version 21393 (0.0007) -[2023-10-09 09:07:59,408][23469] Updated weights for policy 1, policy_version 21501 (0.0009) -[2023-10-09 09:07:59,523][23468] Updated weights for policy 0, policy_version 21403 (0.0009) -[2023-10-09 09:08:01,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 43941888. Throughput: 0: 1762.1, 1: 1771.1. Samples: 10993596. Policy #0 lag: (min: 27.0, avg: 27.8, max: 46.0) -[2023-10-09 09:08:01,078][22500] Avg episode reward: [(0, '6.700'), (1, '6.690')] -[2023-10-09 09:08:01,087][23343] Saving new best policy, reward=6.690! -[2023-10-09 09:08:03,199][23469] Updated weights for policy 1, policy_version 21511 (0.0008) -[2023-10-09 09:08:03,200][23468] Updated weights for policy 0, policy_version 21413 (0.0008) -[2023-10-09 09:08:03,571][23469] Updated weights for policy 1, policy_version 21521 (0.0010) -[2023-10-09 09:08:03,584][23468] Updated weights for policy 0, policy_version 21423 (0.0010) -[2023-10-09 09:08:03,939][23469] Updated weights for policy 1, policy_version 21531 (0.0007) -[2023-10-09 09:08:03,952][23468] Updated weights for policy 0, policy_version 21433 (0.0008) -[2023-10-09 09:08:06,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 44007424. Throughput: 0: 1789.4, 1: 1781.9. Samples: 11004882. Policy #0 lag: (min: 27.0, avg: 27.8, max: 46.0) -[2023-10-09 09:08:06,078][22500] Avg episode reward: [(0, '6.520'), (1, '7.290')] -[2023-10-09 09:08:06,079][23343] Saving new best policy, reward=7.290! -[2023-10-09 09:08:07,669][23468] Updated weights for policy 0, policy_version 21443 (0.0008) -[2023-10-09 09:08:07,795][23469] Updated weights for policy 1, policy_version 21541 (0.0009) -[2023-10-09 09:08:08,036][23468] Updated weights for policy 0, policy_version 21453 (0.0008) -[2023-10-09 09:08:08,155][23469] Updated weights for policy 1, policy_version 21551 (0.0008) -[2023-10-09 09:08:08,417][23468] Updated weights for policy 0, policy_version 21463 (0.0007) -[2023-10-09 09:08:08,531][23469] Updated weights for policy 1, policy_version 21561 (0.0008) -[2023-10-09 09:08:11,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 44072960. Throughput: 0: 1759.9, 1: 1771.4. Samples: 11025338. Policy #0 lag: (min: 17.0, avg: 27.2, max: 49.0) -[2023-10-09 09:08:11,078][22500] Avg episode reward: [(0, '7.000'), (1, '6.890')] -[2023-10-09 09:08:12,288][23468] Updated weights for policy 0, policy_version 21473 (0.0009) -[2023-10-09 09:08:12,392][23469] Updated weights for policy 1, policy_version 21571 (0.0009) -[2023-10-09 09:08:12,660][23468] Updated weights for policy 0, policy_version 21483 (0.0008) -[2023-10-09 09:08:12,793][23469] Updated weights for policy 1, policy_version 21581 (0.0009) -[2023-10-09 09:08:13,031][23468] Updated weights for policy 0, policy_version 21493 (0.0007) -[2023-10-09 09:08:13,171][23469] Updated weights for policy 1, policy_version 21591 (0.0008) -[2023-10-09 09:08:13,413][23468] Updated weights for policy 0, policy_version 21503 (0.0007) -[2023-10-09 09:08:16,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 44138496. Throughput: 0: 1760.2, 1: 1767.3. Samples: 11047168. Policy #0 lag: (min: 17.0, avg: 27.2, max: 49.0) -[2023-10-09 09:08:16,078][22500] Avg episode reward: [(0, '6.530'), (1, '6.210')] -[2023-10-09 09:08:16,087][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000021600_22118400.pth... -[2023-10-09 09:08:16,087][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000021504_22020096.pth... -[2023-10-09 09:08:16,123][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000019840_20316160.pth -[2023-10-09 09:08:16,127][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000019936_20414464.pth -[2023-10-09 09:08:16,989][23469] Updated weights for policy 1, policy_version 21601 (0.0009) -[2023-10-09 09:08:17,225][23468] Updated weights for policy 0, policy_version 21513 (0.0007) -[2023-10-09 09:08:17,353][23469] Updated weights for policy 1, policy_version 21611 (0.0008) -[2023-10-09 09:08:17,595][23468] Updated weights for policy 0, policy_version 21523 (0.0007) -[2023-10-09 09:08:17,717][23469] Updated weights for policy 1, policy_version 21621 (0.0008) -[2023-10-09 09:08:17,968][23468] Updated weights for policy 0, policy_version 21533 (0.0009) -[2023-10-09 09:08:18,083][23469] Updated weights for policy 1, policy_version 21631 (0.0008) -[2023-10-09 09:08:21,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 44204032. Throughput: 0: 1758.6, 1: 1765.9. Samples: 11056656. Policy #0 lag: (min: 17.0, avg: 27.2, max: 49.0) -[2023-10-09 09:08:21,079][22500] Avg episode reward: [(0, '6.370'), (1, '5.970')] -[2023-10-09 09:08:21,750][23469] Updated weights for policy 1, policy_version 21641 (0.0009) -[2023-10-09 09:08:21,886][23468] Updated weights for policy 0, policy_version 21543 (0.0008) -[2023-10-09 09:08:22,112][23469] Updated weights for policy 1, policy_version 21651 (0.0007) -[2023-10-09 09:08:22,260][23468] Updated weights for policy 0, policy_version 21553 (0.0008) -[2023-10-09 09:08:22,478][23469] Updated weights for policy 1, policy_version 21661 (0.0007) -[2023-10-09 09:08:22,621][23468] Updated weights for policy 0, policy_version 21563 (0.0008) -[2023-10-09 09:08:26,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 44269568. Throughput: 0: 1754.7, 1: 1772.2. Samples: 11079186. Policy #0 lag: (min: 17.0, avg: 27.2, max: 49.0) -[2023-10-09 09:08:26,078][22500] Avg episode reward: [(0, '6.180'), (1, '5.800')] -[2023-10-09 09:08:26,195][23469] Updated weights for policy 1, policy_version 21671 (0.0008) -[2023-10-09 09:08:26,400][23468] Updated weights for policy 0, policy_version 21573 (0.0008) -[2023-10-09 09:08:26,564][23469] Updated weights for policy 1, policy_version 21681 (0.0009) -[2023-10-09 09:08:26,779][23468] Updated weights for policy 0, policy_version 21583 (0.0007) -[2023-10-09 09:08:26,937][23469] Updated weights for policy 1, policy_version 21691 (0.0008) -[2023-10-09 09:08:27,162][23468] Updated weights for policy 0, policy_version 21593 (0.0007) -[2023-10-09 09:08:30,668][23469] Updated weights for policy 1, policy_version 21701 (0.0008) -[2023-10-09 09:08:30,884][23468] Updated weights for policy 0, policy_version 21603 (0.0010) -[2023-10-09 09:08:31,038][23469] Updated weights for policy 1, policy_version 21711 (0.0009) -[2023-10-09 09:08:31,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 44335104. Throughput: 0: 1772.0, 1: 1798.8. Samples: 11101102. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:08:31,079][22500] Avg episode reward: [(0, '6.020'), (1, '6.090')] -[2023-10-09 09:08:31,262][23468] Updated weights for policy 0, policy_version 21613 (0.0010) -[2023-10-09 09:08:31,410][23469] Updated weights for policy 1, policy_version 21721 (0.0008) -[2023-10-09 09:08:31,641][23468] Updated weights for policy 0, policy_version 21623 (0.0008) -[2023-10-09 09:08:35,203][23469] Updated weights for policy 1, policy_version 21731 (0.0009) -[2023-10-09 09:08:35,428][23468] Updated weights for policy 0, policy_version 21633 (0.0007) -[2023-10-09 09:08:35,561][23469] Updated weights for policy 1, policy_version 21741 (0.0007) -[2023-10-09 09:08:35,795][23468] Updated weights for policy 0, policy_version 21643 (0.0007) -[2023-10-09 09:08:35,928][23469] Updated weights for policy 1, policy_version 21751 (0.0007) -[2023-10-09 09:08:36,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 44400640. Throughput: 0: 1761.1, 1: 1769.7. Samples: 11111224. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:08:36,078][22500] Avg episode reward: [(0, '6.240'), (1, '6.320')] -[2023-10-09 09:08:36,169][23468] Updated weights for policy 0, policy_version 21653 (0.0007) -[2023-10-09 09:08:36,544][23468] Updated weights for policy 0, policy_version 21663 (0.0009) -[2023-10-09 09:08:39,692][23469] Updated weights for policy 1, policy_version 21761 (0.0008) -[2023-10-09 09:08:40,061][23469] Updated weights for policy 1, policy_version 21771 (0.0010) -[2023-10-09 09:08:40,427][23469] Updated weights for policy 1, policy_version 21781 (0.0009) -[2023-10-09 09:08:40,444][23468] Updated weights for policy 0, policy_version 21673 (0.0008) -[2023-10-09 09:08:40,803][23469] Updated weights for policy 1, policy_version 21791 (0.0009) -[2023-10-09 09:08:40,821][23468] Updated weights for policy 0, policy_version 21683 (0.0009) -[2023-10-09 09:08:41,078][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 44498944. Throughput: 0: 1774.1, 1: 1797.6. Samples: 11133154. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:08:41,079][22500] Avg episode reward: [(0, '6.690'), (1, '6.360')] -[2023-10-09 09:08:41,191][23468] Updated weights for policy 0, policy_version 21693 (0.0009) -[2023-10-09 09:08:44,592][23469] Updated weights for policy 1, policy_version 21801 (0.0007) -[2023-10-09 09:08:44,971][23469] Updated weights for policy 1, policy_version 21811 (0.0007) -[2023-10-09 09:08:45,051][23468] Updated weights for policy 0, policy_version 21703 (0.0009) -[2023-10-09 09:08:45,333][23469] Updated weights for policy 1, policy_version 21821 (0.0008) -[2023-10-09 09:08:45,424][23468] Updated weights for policy 0, policy_version 21713 (0.0009) -[2023-10-09 09:08:45,795][23468] Updated weights for policy 0, policy_version 21723 (0.0009) -[2023-10-09 09:08:46,077][22500] Fps is (10 sec: 19660.8, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 44597248. Throughput: 0: 1784.7, 1: 1774.0. Samples: 11153734. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:08:46,078][22500] Avg episode reward: [(0, '6.520'), (1, '6.800')] -[2023-10-09 09:08:49,060][23469] Updated weights for policy 1, policy_version 21831 (0.0007) -[2023-10-09 09:08:49,339][23468] Updated weights for policy 0, policy_version 21733 (0.0008) -[2023-10-09 09:08:49,430][23469] Updated weights for policy 1, policy_version 21841 (0.0007) -[2023-10-09 09:08:49,715][23468] Updated weights for policy 0, policy_version 21743 (0.0008) -[2023-10-09 09:08:49,799][23469] Updated weights for policy 1, policy_version 21851 (0.0008) -[2023-10-09 09:08:50,092][23468] Updated weights for policy 0, policy_version 21753 (0.0009) -[2023-10-09 09:08:51,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 44662784. Throughput: 0: 1769.9, 1: 1798.6. Samples: 11165466. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:08:51,078][22500] Avg episode reward: [(0, '6.540'), (1, '6.420')] -[2023-10-09 09:08:53,491][23469] Updated weights for policy 1, policy_version 21861 (0.0010) -[2023-10-09 09:08:53,861][23468] Updated weights for policy 0, policy_version 21763 (0.0008) -[2023-10-09 09:08:53,864][23469] Updated weights for policy 1, policy_version 21871 (0.0008) -[2023-10-09 09:08:54,238][23469] Updated weights for policy 1, policy_version 21881 (0.0008) -[2023-10-09 09:08:54,239][23468] Updated weights for policy 0, policy_version 21773 (0.0008) -[2023-10-09 09:08:54,611][23468] Updated weights for policy 0, policy_version 21783 (0.0007) -[2023-10-09 09:08:56,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 44728320. Throughput: 0: 1781.7, 1: 1783.1. Samples: 11185754. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:08:56,078][22500] Avg episode reward: [(0, '6.810'), (1, '6.370')] -[2023-10-09 09:08:57,993][23469] Updated weights for policy 1, policy_version 21891 (0.0008) -[2023-10-09 09:08:58,405][23469] Updated weights for policy 1, policy_version 21901 (0.0007) -[2023-10-09 09:08:58,503][23468] Updated weights for policy 0, policy_version 21793 (0.0010) -[2023-10-09 09:08:58,774][23469] Updated weights for policy 1, policy_version 21911 (0.0009) -[2023-10-09 09:08:58,874][23468] Updated weights for policy 0, policy_version 21803 (0.0009) -[2023-10-09 09:08:59,245][23468] Updated weights for policy 0, policy_version 21813 (0.0009) -[2023-10-09 09:08:59,616][23468] Updated weights for policy 0, policy_version 21823 (0.0010) -[2023-10-09 09:09:01,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 44793856. Throughput: 0: 1760.8, 1: 1791.4. Samples: 11207018. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:09:01,079][22500] Avg episode reward: [(0, '6.720'), (1, '6.120')] -[2023-10-09 09:09:02,535][23469] Updated weights for policy 1, policy_version 21921 (0.0009) -[2023-10-09 09:09:02,900][23469] Updated weights for policy 1, policy_version 21931 (0.0011) -[2023-10-09 09:09:03,267][23469] Updated weights for policy 1, policy_version 21941 (0.0008) -[2023-10-09 09:09:03,386][23468] Updated weights for policy 0, policy_version 21833 (0.0008) -[2023-10-09 09:09:03,637][23469] Updated weights for policy 1, policy_version 21951 (0.0007) -[2023-10-09 09:09:03,767][23468] Updated weights for policy 0, policy_version 21843 (0.0008) -[2023-10-09 09:09:04,133][23468] Updated weights for policy 0, policy_version 21853 (0.0010) -[2023-10-09 09:09:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 44859392. Throughput: 0: 1788.3, 1: 1793.6. Samples: 11217842. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 09:09:06,079][22500] Avg episode reward: [(0, '6.690'), (1, '6.260')] -[2023-10-09 09:09:07,305][23469] Updated weights for policy 1, policy_version 21961 (0.0010) -[2023-10-09 09:09:07,680][23469] Updated weights for policy 1, policy_version 21971 (0.0009) -[2023-10-09 09:09:07,957][23468] Updated weights for policy 0, policy_version 21863 (0.0009) -[2023-10-09 09:09:08,048][23469] Updated weights for policy 1, policy_version 21981 (0.0007) -[2023-10-09 09:09:08,331][23468] Updated weights for policy 0, policy_version 21873 (0.0007) -[2023-10-09 09:09:08,707][23468] Updated weights for policy 0, policy_version 21883 (0.0007) -[2023-10-09 09:09:11,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 44924928. Throughput: 0: 1765.9, 1: 1787.6. Samples: 11239094. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 09:09:11,078][22500] Avg episode reward: [(0, '6.280'), (1, '6.160')] -[2023-10-09 09:09:11,809][23469] Updated weights for policy 1, policy_version 21991 (0.0007) -[2023-10-09 09:09:12,182][23469] Updated weights for policy 1, policy_version 22001 (0.0009) -[2023-10-09 09:09:12,545][23469] Updated weights for policy 1, policy_version 22011 (0.0008) -[2023-10-09 09:09:12,583][23468] Updated weights for policy 0, policy_version 21893 (0.0008) -[2023-10-09 09:09:12,970][23468] Updated weights for policy 0, policy_version 21903 (0.0009) -[2023-10-09 09:09:13,338][23468] Updated weights for policy 0, policy_version 21913 (0.0007) -[2023-10-09 09:09:16,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 44990464. Throughput: 0: 1768.2, 1: 1796.0. Samples: 11261488. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 09:09:16,079][22500] Avg episode reward: [(0, '6.860'), (1, '6.040')] -[2023-10-09 09:09:16,177][23469] Updated weights for policy 1, policy_version 22021 (0.0008) -[2023-10-09 09:09:16,546][23469] Updated weights for policy 1, policy_version 22031 (0.0007) -[2023-10-09 09:09:16,920][23469] Updated weights for policy 1, policy_version 22041 (0.0007) -[2023-10-09 09:09:17,066][23468] Updated weights for policy 0, policy_version 21923 (0.0007) -[2023-10-09 09:09:17,433][23468] Updated weights for policy 0, policy_version 21933 (0.0009) -[2023-10-09 09:09:17,800][23468] Updated weights for policy 0, policy_version 21943 (0.0010) -[2023-10-09 09:09:20,734][23469] Updated weights for policy 1, policy_version 22051 (0.0008) -[2023-10-09 09:09:21,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 45056000. Throughput: 0: 1764.4, 1: 1791.8. Samples: 11271254. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 09:09:21,078][22500] Avg episode reward: [(0, '6.950'), (1, '5.890')] -[2023-10-09 09:09:21,113][23469] Updated weights for policy 1, policy_version 22061 (0.0010) -[2023-10-09 09:09:21,473][23469] Updated weights for policy 1, policy_version 22071 (0.0007) -[2023-10-09 09:09:21,535][23468] Updated weights for policy 0, policy_version 21953 (0.0009) -[2023-10-09 09:09:21,903][23468] Updated weights for policy 0, policy_version 21963 (0.0008) -[2023-10-09 09:09:22,294][23468] Updated weights for policy 0, policy_version 21973 (0.0009) -[2023-10-09 09:09:22,671][23468] Updated weights for policy 0, policy_version 21983 (0.0007) -[2023-10-09 09:09:25,138][23469] Updated weights for policy 1, policy_version 22081 (0.0009) -[2023-10-09 09:09:25,513][23469] Updated weights for policy 1, policy_version 22091 (0.0008) -[2023-10-09 09:09:25,886][23469] Updated weights for policy 1, policy_version 22101 (0.0008) -[2023-10-09 09:09:26,077][22500] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 45121536. Throughput: 0: 1770.9, 1: 1797.0. Samples: 11293712. Policy #0 lag: (min: 18.0, avg: 22.3, max: 50.0) -[2023-10-09 09:09:26,078][22500] Avg episode reward: [(0, '6.800'), (1, '5.720')] -[2023-10-09 09:09:26,252][23469] Updated weights for policy 1, policy_version 22111 (0.0010) -[2023-10-09 09:09:26,521][23468] Updated weights for policy 0, policy_version 21993 (0.0009) -[2023-10-09 09:09:26,906][23468] Updated weights for policy 0, policy_version 22003 (0.0010) -[2023-10-09 09:09:27,279][23468] Updated weights for policy 0, policy_version 22013 (0.0010) -[2023-10-09 09:09:30,017][23469] Updated weights for policy 1, policy_version 22121 (0.0009) -[2023-10-09 09:09:30,391][23469] Updated weights for policy 1, policy_version 22131 (0.0008) -[2023-10-09 09:09:30,763][23469] Updated weights for policy 1, policy_version 22141 (0.0008) -[2023-10-09 09:09:31,018][23468] Updated weights for policy 0, policy_version 22023 (0.0008) -[2023-10-09 09:09:31,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 45219840. Throughput: 0: 1783.6, 1: 1796.2. Samples: 11314822. Policy #0 lag: (min: 18.0, avg: 22.3, max: 50.0) -[2023-10-09 09:09:31,078][22500] Avg episode reward: [(0, '6.830'), (1, '6.290')] -[2023-10-09 09:09:31,392][23468] Updated weights for policy 0, policy_version 22033 (0.0009) -[2023-10-09 09:09:31,772][23468] Updated weights for policy 0, policy_version 22043 (0.0009) -[2023-10-09 09:09:34,482][23469] Updated weights for policy 1, policy_version 22151 (0.0007) -[2023-10-09 09:09:34,848][23469] Updated weights for policy 1, policy_version 22161 (0.0008) -[2023-10-09 09:09:35,228][23469] Updated weights for policy 1, policy_version 22171 (0.0010) -[2023-10-09 09:09:35,697][23468] Updated weights for policy 0, policy_version 22053 (0.0010) -[2023-10-09 09:09:36,070][23468] Updated weights for policy 0, policy_version 22063 (0.0007) -[2023-10-09 09:09:36,077][22500] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 45285376. Throughput: 0: 1771.1, 1: 1794.2. Samples: 11325902. Policy #0 lag: (min: 18.0, avg: 22.3, max: 50.0) -[2023-10-09 09:09:36,079][22500] Avg episode reward: [(0, '6.340'), (1, '6.630')] -[2023-10-09 09:09:36,443][23468] Updated weights for policy 0, policy_version 22073 (0.0009) -[2023-10-09 09:09:39,080][23469] Updated weights for policy 1, policy_version 22181 (0.0009) -[2023-10-09 09:09:39,452][23469] Updated weights for policy 1, policy_version 22191 (0.0008) -[2023-10-09 09:09:39,819][23469] Updated weights for policy 1, policy_version 22201 (0.0009) -[2023-10-09 09:09:40,166][23468] Updated weights for policy 0, policy_version 22083 (0.0007) -[2023-10-09 09:09:40,545][23468] Updated weights for policy 0, policy_version 22093 (0.0009) -[2023-10-09 09:09:40,919][23468] Updated weights for policy 0, policy_version 22103 (0.0008) -[2023-10-09 09:09:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 45350912. Throughput: 0: 1782.4, 1: 1801.9. Samples: 11347044. Policy #0 lag: (min: 18.0, avg: 22.3, max: 50.0) -[2023-10-09 09:09:41,078][22500] Avg episode reward: [(0, '6.540'), (1, '6.360')] -[2023-10-09 09:09:43,649][23469] Updated weights for policy 1, policy_version 22211 (0.0010) -[2023-10-09 09:09:44,031][23469] Updated weights for policy 1, policy_version 22221 (0.0009) -[2023-10-09 09:09:44,400][23469] Updated weights for policy 1, policy_version 22231 (0.0008) -[2023-10-09 09:09:44,451][23468] Updated weights for policy 0, policy_version 22113 (0.0010) -[2023-10-09 09:09:44,822][23468] Updated weights for policy 0, policy_version 22123 (0.0007) -[2023-10-09 09:09:45,203][23468] Updated weights for policy 0, policy_version 22133 (0.0010) -[2023-10-09 09:09:45,564][23468] Updated weights for policy 0, policy_version 22143 (0.0008) -[2023-10-09 09:09:46,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 45449216. Throughput: 0: 1785.9, 1: 1789.5. Samples: 11367908. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-09 09:09:46,078][22500] Avg episode reward: [(0, '6.330'), (1, '6.130')] -[2023-10-09 09:09:48,267][23469] Updated weights for policy 1, policy_version 22241 (0.0008) -[2023-10-09 09:09:48,633][23469] Updated weights for policy 1, policy_version 22251 (0.0008) -[2023-10-09 09:09:49,000][23469] Updated weights for policy 1, policy_version 22261 (0.0009) -[2023-10-09 09:09:49,296][23468] Updated weights for policy 0, policy_version 22153 (0.0009) -[2023-10-09 09:09:49,372][23469] Updated weights for policy 1, policy_version 22271 (0.0009) -[2023-10-09 09:09:49,667][23468] Updated weights for policy 0, policy_version 22163 (0.0007) -[2023-10-09 09:09:50,033][23468] Updated weights for policy 0, policy_version 22173 (0.0007) -[2023-10-09 09:09:51,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 45514752. Throughput: 0: 1785.0, 1: 1805.7. Samples: 11379420. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-09 09:09:51,078][22500] Avg episode reward: [(0, '6.250'), (1, '6.020')] -[2023-10-09 09:09:53,202][23469] Updated weights for policy 1, policy_version 22281 (0.0008) -[2023-10-09 09:09:53,574][23469] Updated weights for policy 1, policy_version 22291 (0.0007) -[2023-10-09 09:09:53,862][23468] Updated weights for policy 0, policy_version 22183 (0.0008) -[2023-10-09 09:09:53,952][23469] Updated weights for policy 1, policy_version 22301 (0.0009) -[2023-10-09 09:09:54,231][23468] Updated weights for policy 0, policy_version 22193 (0.0007) -[2023-10-09 09:09:54,603][23468] Updated weights for policy 0, policy_version 22203 (0.0007) -[2023-10-09 09:09:56,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 45580288. Throughput: 0: 1793.0, 1: 1779.3. Samples: 11399848. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-09 09:09:56,078][22500] Avg episode reward: [(0, '6.220'), (1, '5.910')] -[2023-10-09 09:09:57,728][23469] Updated weights for policy 1, policy_version 22311 (0.0008) -[2023-10-09 09:09:58,088][23469] Updated weights for policy 1, policy_version 22321 (0.0012) -[2023-10-09 09:09:58,458][23469] Updated weights for policy 1, policy_version 22331 (0.0010) -[2023-10-09 09:09:58,563][23468] Updated weights for policy 0, policy_version 22213 (0.0008) -[2023-10-09 09:09:58,952][23468] Updated weights for policy 0, policy_version 22223 (0.0007) -[2023-10-09 09:09:59,330][23468] Updated weights for policy 0, policy_version 22233 (0.0007) -[2023-10-09 09:10:01,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 45645824. Throughput: 0: 1774.5, 1: 1776.6. Samples: 11421284. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-10-09 09:10:01,078][22500] Avg episode reward: [(0, '5.740'), (1, '5.980')] -[2023-10-09 09:10:02,197][23469] Updated weights for policy 1, policy_version 22341 (0.0007) -[2023-10-09 09:10:02,563][23469] Updated weights for policy 1, policy_version 22351 (0.0008) -[2023-10-09 09:10:02,938][23469] Updated weights for policy 1, policy_version 22361 (0.0008) -[2023-10-09 09:10:03,169][23468] Updated weights for policy 0, policy_version 22243 (0.0007) -[2023-10-09 09:10:03,542][23468] Updated weights for policy 0, policy_version 22253 (0.0008) -[2023-10-09 09:10:03,917][23468] Updated weights for policy 0, policy_version 22263 (0.0010) -[2023-10-09 09:10:06,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 45711360. Throughput: 0: 1803.4, 1: 1776.5. Samples: 11432352. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-10-09 09:10:06,079][22500] Avg episode reward: [(0, '5.870'), (1, '6.110')] -[2023-10-09 09:10:06,479][23469] Updated weights for policy 1, policy_version 22371 (0.0007) -[2023-10-09 09:10:06,855][23469] Updated weights for policy 1, policy_version 22381 (0.0008) -[2023-10-09 09:10:07,233][23469] Updated weights for policy 1, policy_version 22391 (0.0007) -[2023-10-09 09:10:07,694][23468] Updated weights for policy 0, policy_version 22273 (0.0008) -[2023-10-09 09:10:08,065][23468] Updated weights for policy 0, policy_version 22283 (0.0009) -[2023-10-09 09:10:08,443][23468] Updated weights for policy 0, policy_version 22293 (0.0009) -[2023-10-09 09:10:08,806][23468] Updated weights for policy 0, policy_version 22303 (0.0008) -[2023-10-09 09:10:10,932][23469] Updated weights for policy 1, policy_version 22401 (0.0009) -[2023-10-09 09:10:11,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 45776896. Throughput: 0: 1773.1, 1: 1782.5. Samples: 11453718. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-10-09 09:10:11,078][22500] Avg episode reward: [(0, '6.250'), (1, '5.970')] -[2023-10-09 09:10:11,304][23469] Updated weights for policy 1, policy_version 22411 (0.0009) -[2023-10-09 09:10:11,663][23469] Updated weights for policy 1, policy_version 22421 (0.0008) -[2023-10-09 09:10:12,045][23469] Updated weights for policy 1, policy_version 22431 (0.0010) -[2023-10-09 09:10:12,627][23468] Updated weights for policy 0, policy_version 22313 (0.0008) -[2023-10-09 09:10:12,997][23468] Updated weights for policy 0, policy_version 22323 (0.0007) -[2023-10-09 09:10:13,371][23468] Updated weights for policy 0, policy_version 22333 (0.0008) -[2023-10-09 09:10:15,966][23469] Updated weights for policy 1, policy_version 22441 (0.0010) -[2023-10-09 09:10:16,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 45842432. Throughput: 0: 1773.7, 1: 1805.0. Samples: 11475864. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-10-09 09:10:16,078][22500] Avg episode reward: [(0, '6.730'), (1, '5.910')] -[2023-10-09 09:10:16,085][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000022336_22872064.pth... -[2023-10-09 09:10:16,118][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000020672_21168128.pth -[2023-10-09 09:10:16,342][23469] Updated weights for policy 1, policy_version 22451 (0.0007) -[2023-10-09 09:10:16,721][23469] Updated weights for policy 1, policy_version 22461 (0.0008) -[2023-10-09 09:10:16,824][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000022464_23003136.pth... -[2023-10-09 09:10:16,856][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000020768_21266432.pth -[2023-10-09 09:10:17,076][23468] Updated weights for policy 0, policy_version 22343 (0.0008) -[2023-10-09 09:10:17,454][23468] Updated weights for policy 0, policy_version 22353 (0.0007) -[2023-10-09 09:10:17,831][23468] Updated weights for policy 0, policy_version 22363 (0.0008) -[2023-10-09 09:10:20,540][23469] Updated weights for policy 1, policy_version 22471 (0.0009) -[2023-10-09 09:10:20,912][23469] Updated weights for policy 1, policy_version 22481 (0.0008) -[2023-10-09 09:10:21,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 45907968. Throughput: 0: 1772.5, 1: 1775.4. Samples: 11485560. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:10:21,078][22500] Avg episode reward: [(0, '6.710'), (1, '5.700')] -[2023-10-09 09:10:21,278][23469] Updated weights for policy 1, policy_version 22491 (0.0008) -[2023-10-09 09:10:21,702][23468] Updated weights for policy 0, policy_version 22373 (0.0008) -[2023-10-09 09:10:22,082][23468] Updated weights for policy 0, policy_version 22383 (0.0007) -[2023-10-09 09:10:22,469][23468] Updated weights for policy 0, policy_version 22393 (0.0011) -[2023-10-09 09:10:25,096][23469] Updated weights for policy 1, policy_version 22501 (0.0008) -[2023-10-09 09:10:25,476][23469] Updated weights for policy 1, policy_version 22511 (0.0007) -[2023-10-09 09:10:25,846][23469] Updated weights for policy 1, policy_version 22521 (0.0009) -[2023-10-09 09:10:26,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 45973504. Throughput: 0: 1772.6, 1: 1796.9. Samples: 11507672. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:10:26,078][22500] Avg episode reward: [(0, '6.680'), (1, '5.830')] -[2023-10-09 09:10:26,274][23468] Updated weights for policy 0, policy_version 22403 (0.0008) -[2023-10-09 09:10:26,642][23468] Updated weights for policy 0, policy_version 22413 (0.0009) -[2023-10-09 09:10:27,016][23468] Updated weights for policy 0, policy_version 22423 (0.0007) -[2023-10-09 09:10:29,607][23469] Updated weights for policy 1, policy_version 22531 (0.0008) -[2023-10-09 09:10:30,012][23469] Updated weights for policy 1, policy_version 22541 (0.0009) -[2023-10-09 09:10:30,385][23469] Updated weights for policy 1, policy_version 22551 (0.0007) -[2023-10-09 09:10:30,769][23468] Updated weights for policy 0, policy_version 22433 (0.0009) -[2023-10-09 09:10:31,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 46071808. Throughput: 0: 1790.0, 1: 1779.8. Samples: 11528548. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:10:31,078][22500] Avg episode reward: [(0, '6.690'), (1, '5.890')] -[2023-10-09 09:10:31,149][23468] Updated weights for policy 0, policy_version 22443 (0.0009) -[2023-10-09 09:10:31,520][23468] Updated weights for policy 0, policy_version 22453 (0.0007) -[2023-10-09 09:10:31,889][23468] Updated weights for policy 0, policy_version 22463 (0.0008) -[2023-10-09 09:10:34,142][23469] Updated weights for policy 1, policy_version 22561 (0.0008) -[2023-10-09 09:10:34,514][23469] Updated weights for policy 1, policy_version 22571 (0.0011) -[2023-10-09 09:10:34,881][23469] Updated weights for policy 1, policy_version 22581 (0.0008) -[2023-10-09 09:10:35,254][23469] Updated weights for policy 1, policy_version 22591 (0.0010) -[2023-10-09 09:10:35,626][23468] Updated weights for policy 0, policy_version 22473 (0.0008) -[2023-10-09 09:10:35,990][23468] Updated weights for policy 0, policy_version 22483 (0.0007) -[2023-10-09 09:10:36,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 46137344. Throughput: 0: 1767.8, 1: 1797.0. Samples: 11539836. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:10:36,078][22500] Avg episode reward: [(0, '6.870'), (1, '6.000')] -[2023-10-09 09:10:36,372][23468] Updated weights for policy 0, policy_version 22493 (0.0009) -[2023-10-09 09:10:38,901][23469] Updated weights for policy 1, policy_version 22601 (0.0007) -[2023-10-09 09:10:39,275][23469] Updated weights for policy 1, policy_version 22611 (0.0008) -[2023-10-09 09:10:39,645][23469] Updated weights for policy 1, policy_version 22621 (0.0007) -[2023-10-09 09:10:40,109][23468] Updated weights for policy 0, policy_version 22503 (0.0008) -[2023-10-09 09:10:40,472][23468] Updated weights for policy 0, policy_version 22513 (0.0008) -[2023-10-09 09:10:40,853][23468] Updated weights for policy 0, policy_version 22523 (0.0009) -[2023-10-09 09:10:41,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 46235648. Throughput: 0: 1790.0, 1: 1791.1. Samples: 11560998. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 09:10:41,078][22500] Avg episode reward: [(0, '6.210'), (1, '5.940')] -[2023-10-09 09:10:43,447][23469] Updated weights for policy 1, policy_version 22631 (0.0008) -[2023-10-09 09:10:43,824][23469] Updated weights for policy 1, policy_version 22641 (0.0008) -[2023-10-09 09:10:44,190][23469] Updated weights for policy 1, policy_version 22651 (0.0008) -[2023-10-09 09:10:44,666][23468] Updated weights for policy 0, policy_version 22533 (0.0010) -[2023-10-09 09:10:45,055][23468] Updated weights for policy 0, policy_version 22543 (0.0008) -[2023-10-09 09:10:45,422][23468] Updated weights for policy 0, policy_version 22553 (0.0009) -[2023-10-09 09:10:46,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 46301184. Throughput: 0: 1786.4, 1: 1795.7. Samples: 11582482. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 09:10:46,078][22500] Avg episode reward: [(0, '6.770'), (1, '5.550')] -[2023-10-09 09:10:47,932][23469] Updated weights for policy 1, policy_version 22661 (0.0008) -[2023-10-09 09:10:48,302][23469] Updated weights for policy 1, policy_version 22671 (0.0009) -[2023-10-09 09:10:48,680][23469] Updated weights for policy 1, policy_version 22681 (0.0011) -[2023-10-09 09:10:49,316][23468] Updated weights for policy 0, policy_version 22563 (0.0010) -[2023-10-09 09:10:49,695][23468] Updated weights for policy 0, policy_version 22573 (0.0009) -[2023-10-09 09:10:50,073][23468] Updated weights for policy 0, policy_version 22583 (0.0008) -[2023-10-09 09:10:51,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 46366720. Throughput: 0: 1775.9, 1: 1799.6. Samples: 11593248. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 09:10:51,078][22500] Avg episode reward: [(0, '6.730'), (1, '5.480')] -[2023-10-09 09:10:52,316][23469] Updated weights for policy 1, policy_version 22691 (0.0009) -[2023-10-09 09:10:52,680][23469] Updated weights for policy 1, policy_version 22701 (0.0009) -[2023-10-09 09:10:53,054][23469] Updated weights for policy 1, policy_version 22711 (0.0008) -[2023-10-09 09:10:53,757][23468] Updated weights for policy 0, policy_version 22593 (0.0008) -[2023-10-09 09:10:54,134][23468] Updated weights for policy 0, policy_version 22603 (0.0008) -[2023-10-09 09:10:54,517][23468] Updated weights for policy 0, policy_version 22613 (0.0008) -[2023-10-09 09:10:54,886][23468] Updated weights for policy 0, policy_version 22623 (0.0007) -[2023-10-09 09:10:56,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 46432256. Throughput: 0: 1791.6, 1: 1792.0. Samples: 11614980. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:10:56,078][22500] Avg episode reward: [(0, '6.750'), (1, '5.660')] -[2023-10-09 09:10:56,818][23469] Updated weights for policy 1, policy_version 22721 (0.0008) -[2023-10-09 09:10:57,190][23469] Updated weights for policy 1, policy_version 22731 (0.0008) -[2023-10-09 09:10:57,562][23469] Updated weights for policy 1, policy_version 22741 (0.0008) -[2023-10-09 09:10:57,930][23469] Updated weights for policy 1, policy_version 22751 (0.0008) -[2023-10-09 09:10:58,568][23468] Updated weights for policy 0, policy_version 22633 (0.0008) -[2023-10-09 09:10:58,943][23468] Updated weights for policy 0, policy_version 22643 (0.0009) -[2023-10-09 09:10:59,320][23468] Updated weights for policy 0, policy_version 22653 (0.0008) -[2023-10-09 09:11:01,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 46497792. Throughput: 0: 1771.8, 1: 1795.2. Samples: 11636380. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:11:01,079][22500] Avg episode reward: [(0, '6.420'), (1, '5.830')] -[2023-10-09 09:11:01,777][23469] Updated weights for policy 1, policy_version 22761 (0.0009) -[2023-10-09 09:11:02,152][23469] Updated weights for policy 1, policy_version 22771 (0.0008) -[2023-10-09 09:11:02,509][23469] Updated weights for policy 1, policy_version 22781 (0.0008) -[2023-10-09 09:11:03,089][23468] Updated weights for policy 0, policy_version 22663 (0.0008) -[2023-10-09 09:11:03,461][23468] Updated weights for policy 0, policy_version 22673 (0.0010) -[2023-10-09 09:11:03,836][23468] Updated weights for policy 0, policy_version 22683 (0.0010) -[2023-10-09 09:11:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 46563328. Throughput: 0: 1795.0, 1: 1793.1. Samples: 11647024. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:11:06,078][22500] Avg episode reward: [(0, '6.100'), (1, '5.900')] -[2023-10-09 09:11:06,149][23469] Updated weights for policy 1, policy_version 22791 (0.0009) -[2023-10-09 09:11:06,525][23469] Updated weights for policy 1, policy_version 22801 (0.0007) -[2023-10-09 09:11:06,882][23469] Updated weights for policy 1, policy_version 22811 (0.0007) -[2023-10-09 09:11:07,608][23468] Updated weights for policy 0, policy_version 22693 (0.0010) -[2023-10-09 09:11:07,983][23468] Updated weights for policy 0, policy_version 22703 (0.0008) -[2023-10-09 09:11:08,360][23468] Updated weights for policy 0, policy_version 22713 (0.0007) -[2023-10-09 09:11:10,511][23469] Updated weights for policy 1, policy_version 22821 (0.0007) -[2023-10-09 09:11:10,886][23469] Updated weights for policy 1, policy_version 22831 (0.0008) -[2023-10-09 09:11:11,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 46628864. Throughput: 0: 1772.0, 1: 1802.7. Samples: 11668536. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:11:11,078][22500] Avg episode reward: [(0, '6.290'), (1, '6.000')] -[2023-10-09 09:11:11,258][23469] Updated weights for policy 1, policy_version 22841 (0.0008) -[2023-10-09 09:11:12,049][23468] Updated weights for policy 0, policy_version 22723 (0.0008) -[2023-10-09 09:11:12,419][23468] Updated weights for policy 0, policy_version 22733 (0.0008) -[2023-10-09 09:11:12,798][23468] Updated weights for policy 0, policy_version 22743 (0.0008) -[2023-10-09 09:11:15,113][23469] Updated weights for policy 1, policy_version 22851 (0.0008) -[2023-10-09 09:11:15,527][23469] Updated weights for policy 1, policy_version 22861 (0.0008) -[2023-10-09 09:11:15,904][23469] Updated weights for policy 1, policy_version 22871 (0.0007) -[2023-10-09 09:11:16,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 46694400. Throughput: 0: 1778.2, 1: 1809.0. Samples: 11689972. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-09 09:11:16,078][22500] Avg episode reward: [(0, '6.530'), (1, '6.020')] -[2023-10-09 09:11:16,557][23468] Updated weights for policy 0, policy_version 22753 (0.0007) -[2023-10-09 09:11:16,934][23468] Updated weights for policy 0, policy_version 22763 (0.0008) -[2023-10-09 09:11:17,311][23468] Updated weights for policy 0, policy_version 22773 (0.0008) -[2023-10-09 09:11:17,686][23468] Updated weights for policy 0, policy_version 22783 (0.0009) -[2023-10-09 09:11:19,577][23469] Updated weights for policy 1, policy_version 22881 (0.0010) -[2023-10-09 09:11:19,949][23469] Updated weights for policy 1, policy_version 22891 (0.0010) -[2023-10-09 09:11:20,323][23469] Updated weights for policy 1, policy_version 22901 (0.0008) -[2023-10-09 09:11:20,700][23469] Updated weights for policy 1, policy_version 22911 (0.0008) -[2023-10-09 09:11:21,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 46792704. Throughput: 0: 1778.6, 1: 1795.7. Samples: 11700680. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-09 09:11:21,078][22500] Avg episode reward: [(0, '6.650'), (1, '6.290')] -[2023-10-09 09:11:21,451][23468] Updated weights for policy 0, policy_version 22793 (0.0008) -[2023-10-09 09:11:21,825][23468] Updated weights for policy 0, policy_version 22803 (0.0008) -[2023-10-09 09:11:22,192][23468] Updated weights for policy 0, policy_version 22813 (0.0009) -[2023-10-09 09:11:24,417][23469] Updated weights for policy 1, policy_version 22921 (0.0008) -[2023-10-09 09:11:24,778][23469] Updated weights for policy 1, policy_version 22931 (0.0007) -[2023-10-09 09:11:25,155][23469] Updated weights for policy 1, policy_version 22941 (0.0009) -[2023-10-09 09:11:25,793][23468] Updated weights for policy 0, policy_version 22823 (0.0008) -[2023-10-09 09:11:26,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 46858240. Throughput: 0: 1780.9, 1: 1809.7. Samples: 11722574. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-09 09:11:26,078][22500] Avg episode reward: [(0, '6.320'), (1, '5.940')] -[2023-10-09 09:11:26,170][23468] Updated weights for policy 0, policy_version 22833 (0.0008) -[2023-10-09 09:11:26,547][23468] Updated weights for policy 0, policy_version 22843 (0.0007) -[2023-10-09 09:11:28,874][23469] Updated weights for policy 1, policy_version 22951 (0.0007) -[2023-10-09 09:11:29,247][23469] Updated weights for policy 1, policy_version 22961 (0.0009) -[2023-10-09 09:11:29,604][23469] Updated weights for policy 1, policy_version 22971 (0.0007) -[2023-10-09 09:11:30,174][23468] Updated weights for policy 0, policy_version 22853 (0.0008) -[2023-10-09 09:11:30,566][23468] Updated weights for policy 0, policy_version 22863 (0.0007) -[2023-10-09 09:11:30,946][23468] Updated weights for policy 0, policy_version 22873 (0.0010) -[2023-10-09 09:11:31,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 46923776. Throughput: 0: 1798.7, 1: 1793.2. Samples: 11744118. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-09 09:11:31,078][22500] Avg episode reward: [(0, '6.380'), (1, '5.750')] -[2023-10-09 09:11:33,449][23469] Updated weights for policy 1, policy_version 22981 (0.0008) -[2023-10-09 09:11:33,814][23469] Updated weights for policy 1, policy_version 22991 (0.0009) -[2023-10-09 09:11:34,194][23469] Updated weights for policy 1, policy_version 23001 (0.0008) -[2023-10-09 09:11:34,651][23468] Updated weights for policy 0, policy_version 22883 (0.0008) -[2023-10-09 09:11:35,021][23468] Updated weights for policy 0, policy_version 22893 (0.0008) -[2023-10-09 09:11:35,400][23468] Updated weights for policy 0, policy_version 22903 (0.0008) -[2023-10-09 09:11:36,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 47022080. Throughput: 0: 1791.3, 1: 1807.2. Samples: 11755182. Policy #0 lag: (min: 16.0, avg: 36.3, max: 48.0) -[2023-10-09 09:11:36,078][22500] Avg episode reward: [(0, '6.820'), (1, '5.620')] -[2023-10-09 09:11:37,915][23469] Updated weights for policy 1, policy_version 23011 (0.0008) -[2023-10-09 09:11:38,292][23469] Updated weights for policy 1, policy_version 23021 (0.0010) -[2023-10-09 09:11:38,665][23469] Updated weights for policy 1, policy_version 23031 (0.0009) -[2023-10-09 09:11:39,094][23468] Updated weights for policy 0, policy_version 22913 (0.0008) -[2023-10-09 09:11:39,459][23468] Updated weights for policy 0, policy_version 22923 (0.0007) -[2023-10-09 09:11:39,843][23468] Updated weights for policy 0, policy_version 22933 (0.0007) -[2023-10-09 09:11:40,215][23468] Updated weights for policy 0, policy_version 22943 (0.0009) -[2023-10-09 09:11:41,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 47087616. Throughput: 0: 1805.5, 1: 1791.2. Samples: 11776834. Policy #0 lag: (min: 16.0, avg: 36.3, max: 48.0) -[2023-10-09 09:11:41,079][22500] Avg episode reward: [(0, '7.110'), (1, '5.860')] -[2023-10-09 09:11:42,286][23469] Updated weights for policy 1, policy_version 23041 (0.0008) -[2023-10-09 09:11:42,657][23469] Updated weights for policy 1, policy_version 23051 (0.0009) -[2023-10-09 09:11:43,034][23469] Updated weights for policy 1, policy_version 23061 (0.0008) -[2023-10-09 09:11:43,399][23469] Updated weights for policy 1, policy_version 23071 (0.0008) -[2023-10-09 09:11:43,977][23468] Updated weights for policy 0, policy_version 22953 (0.0009) -[2023-10-09 09:11:44,342][23468] Updated weights for policy 0, policy_version 22963 (0.0009) -[2023-10-09 09:11:44,719][23468] Updated weights for policy 0, policy_version 22973 (0.0010) -[2023-10-09 09:11:46,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 47153152. Throughput: 0: 1796.4, 1: 1789.0. Samples: 11797720. Policy #0 lag: (min: 16.0, avg: 36.3, max: 48.0) -[2023-10-09 09:11:46,078][22500] Avg episode reward: [(0, '7.000'), (1, '5.830')] -[2023-10-09 09:11:47,326][23469] Updated weights for policy 1, policy_version 23081 (0.0011) -[2023-10-09 09:11:47,699][23469] Updated weights for policy 1, policy_version 23091 (0.0009) -[2023-10-09 09:11:48,061][23469] Updated weights for policy 1, policy_version 23101 (0.0009) -[2023-10-09 09:11:48,505][23468] Updated weights for policy 0, policy_version 22983 (0.0008) -[2023-10-09 09:11:48,877][23468] Updated weights for policy 0, policy_version 22993 (0.0009) -[2023-10-09 09:11:49,247][23468] Updated weights for policy 0, policy_version 23003 (0.0010) -[2023-10-09 09:11:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 47218688. Throughput: 0: 1810.2, 1: 1788.9. Samples: 11808984. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-09 09:11:51,078][22500] Avg episode reward: [(0, '6.930'), (1, '5.680')] -[2023-10-09 09:11:51,915][23469] Updated weights for policy 1, policy_version 23111 (0.0009) -[2023-10-09 09:11:52,284][23469] Updated weights for policy 1, policy_version 23121 (0.0008) -[2023-10-09 09:11:52,656][23469] Updated weights for policy 1, policy_version 23131 (0.0008) -[2023-10-09 09:11:53,176][23468] Updated weights for policy 0, policy_version 23013 (0.0007) -[2023-10-09 09:11:53,539][23468] Updated weights for policy 0, policy_version 23023 (0.0007) -[2023-10-09 09:11:53,919][23468] Updated weights for policy 0, policy_version 23033 (0.0009) -[2023-10-09 09:11:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 47284224. Throughput: 0: 1798.4, 1: 1784.9. Samples: 11829780. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-09 09:11:56,078][22500] Avg episode reward: [(0, '6.600'), (1, '5.870')] -[2023-10-09 09:11:56,634][23469] Updated weights for policy 1, policy_version 23141 (0.0009) -[2023-10-09 09:11:57,008][23469] Updated weights for policy 1, policy_version 23151 (0.0009) -[2023-10-09 09:11:57,376][23469] Updated weights for policy 1, policy_version 23161 (0.0009) -[2023-10-09 09:11:57,703][23468] Updated weights for policy 0, policy_version 23043 (0.0009) -[2023-10-09 09:11:58,075][23468] Updated weights for policy 0, policy_version 23053 (0.0008) -[2023-10-09 09:11:58,444][23468] Updated weights for policy 0, policy_version 23063 (0.0007) -[2023-10-09 09:12:01,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 47349760. Throughput: 0: 1795.2, 1: 1808.3. Samples: 11852130. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-09 09:12:01,078][22500] Avg episode reward: [(0, '6.540'), (1, '6.230')] -[2023-10-09 09:12:01,118][23469] Updated weights for policy 1, policy_version 23171 (0.0009) -[2023-10-09 09:12:01,514][23469] Updated weights for policy 1, policy_version 23181 (0.0010) -[2023-10-09 09:12:01,888][23469] Updated weights for policy 1, policy_version 23191 (0.0009) -[2023-10-09 09:12:02,110][23468] Updated weights for policy 0, policy_version 23073 (0.0009) -[2023-10-09 09:12:02,476][23468] Updated weights for policy 0, policy_version 23083 (0.0009) -[2023-10-09 09:12:02,854][23468] Updated weights for policy 0, policy_version 23093 (0.0010) -[2023-10-09 09:12:03,237][23468] Updated weights for policy 0, policy_version 23103 (0.0007) -[2023-10-09 09:12:05,548][23469] Updated weights for policy 1, policy_version 23201 (0.0009) -[2023-10-09 09:12:05,916][23469] Updated weights for policy 1, policy_version 23211 (0.0007) -[2023-10-09 09:12:06,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 47415296. Throughput: 0: 1797.4, 1: 1785.4. Samples: 11861906. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-09 09:12:06,078][22500] Avg episode reward: [(0, '6.950'), (1, '6.450')] -[2023-10-09 09:12:06,284][23469] Updated weights for policy 1, policy_version 23221 (0.0007) -[2023-10-09 09:12:06,650][23469] Updated weights for policy 1, policy_version 23231 (0.0009) -[2023-10-09 09:12:06,959][23468] Updated weights for policy 0, policy_version 23113 (0.0008) -[2023-10-09 09:12:07,329][23468] Updated weights for policy 0, policy_version 23123 (0.0007) -[2023-10-09 09:12:07,699][23468] Updated weights for policy 0, policy_version 23133 (0.0008) -[2023-10-09 09:12:10,381][23469] Updated weights for policy 1, policy_version 23241 (0.0007) -[2023-10-09 09:12:10,756][23469] Updated weights for policy 1, policy_version 23251 (0.0008) -[2023-10-09 09:12:11,078][22500] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 47480832. Throughput: 0: 1792.7, 1: 1800.1. Samples: 11884252. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:12:11,078][22500] Avg episode reward: [(0, '7.320'), (1, '6.380')] -[2023-10-09 09:12:11,127][23469] Updated weights for policy 1, policy_version 23261 (0.0007) -[2023-10-09 09:12:11,474][23468] Updated weights for policy 0, policy_version 23143 (0.0009) -[2023-10-09 09:12:11,844][23468] Updated weights for policy 0, policy_version 23153 (0.0008) -[2023-10-09 09:12:12,215][23468] Updated weights for policy 0, policy_version 23163 (0.0009) -[2023-10-09 09:12:14,811][23469] Updated weights for policy 1, policy_version 23271 (0.0007) -[2023-10-09 09:12:15,174][23469] Updated weights for policy 1, policy_version 23281 (0.0007) -[2023-10-09 09:12:15,549][23469] Updated weights for policy 1, policy_version 23291 (0.0009) -[2023-10-09 09:12:16,078][22500] Fps is (10 sec: 16383.5, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 47579136. Throughput: 0: 1797.9, 1: 1781.1. Samples: 11905172. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:12:16,079][22500] Avg episode reward: [(0, '7.040'), (1, '6.460')] -[2023-10-09 09:12:16,090][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000023296_23855104.pth... -[2023-10-09 09:12:16,113][23468] Updated weights for policy 0, policy_version 23173 (0.0010) -[2023-10-09 09:12:16,120][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000021600_22118400.pth -[2023-10-09 09:12:16,498][23468] Updated weights for policy 0, policy_version 23183 (0.0009) -[2023-10-09 09:12:16,873][23468] Updated weights for policy 0, policy_version 23193 (0.0009) -[2023-10-09 09:12:17,136][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000023200_23756800.pth... -[2023-10-09 09:12:17,173][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000021504_22020096.pth -[2023-10-09 09:12:19,135][23469] Updated weights for policy 1, policy_version 23301 (0.0009) -[2023-10-09 09:12:19,508][23469] Updated weights for policy 1, policy_version 23311 (0.0009) -[2023-10-09 09:12:19,884][23469] Updated weights for policy 1, policy_version 23321 (0.0008) -[2023-10-09 09:12:20,585][23468] Updated weights for policy 0, policy_version 23203 (0.0009) -[2023-10-09 09:12:20,967][23468] Updated weights for policy 0, policy_version 23213 (0.0008) -[2023-10-09 09:12:21,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 47644672. Throughput: 0: 1785.3, 1: 1792.9. Samples: 11916204. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:12:21,079][22500] Avg episode reward: [(0, '7.290'), (1, '6.260')] -[2023-10-09 09:12:21,339][23468] Updated weights for policy 0, policy_version 23223 (0.0009) -[2023-10-09 09:12:23,612][23469] Updated weights for policy 1, policy_version 23331 (0.0009) -[2023-10-09 09:12:23,977][23469] Updated weights for policy 1, policy_version 23341 (0.0010) -[2023-10-09 09:12:24,340][23469] Updated weights for policy 1, policy_version 23351 (0.0009) -[2023-10-09 09:12:25,197][23468] Updated weights for policy 0, policy_version 23233 (0.0009) -[2023-10-09 09:12:25,563][23468] Updated weights for policy 0, policy_version 23243 (0.0011) -[2023-10-09 09:12:25,944][23468] Updated weights for policy 0, policy_version 23253 (0.0009) -[2023-10-09 09:12:26,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 47710208. Throughput: 0: 1783.0, 1: 1775.7. Samples: 11936976. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:12:26,079][22500] Avg episode reward: [(0, '6.930'), (1, '5.760')] -[2023-10-09 09:12:26,315][23468] Updated weights for policy 0, policy_version 23263 (0.0009) -[2023-10-09 09:12:28,067][23469] Updated weights for policy 1, policy_version 23361 (0.0010) -[2023-10-09 09:12:28,439][23469] Updated weights for policy 1, policy_version 23371 (0.0010) -[2023-10-09 09:12:28,810][23469] Updated weights for policy 1, policy_version 23381 (0.0009) -[2023-10-09 09:12:29,180][23469] Updated weights for policy 1, policy_version 23391 (0.0008) -[2023-10-09 09:12:30,001][23468] Updated weights for policy 0, policy_version 23273 (0.0008) -[2023-10-09 09:12:30,373][23468] Updated weights for policy 0, policy_version 23283 (0.0009) -[2023-10-09 09:12:30,750][23468] Updated weights for policy 0, policy_version 23293 (0.0008) -[2023-10-09 09:12:31,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 47808512. Throughput: 0: 1796.9, 1: 1784.0. Samples: 11958862. Policy #0 lag: (min: 0.0, avg: 24.7, max: 32.0) -[2023-10-09 09:12:31,078][22500] Avg episode reward: [(0, '7.090'), (1, '5.710')] -[2023-10-09 09:12:32,989][23469] Updated weights for policy 1, policy_version 23401 (0.0008) -[2023-10-09 09:12:33,355][23469] Updated weights for policy 1, policy_version 23411 (0.0009) -[2023-10-09 09:12:33,724][23469] Updated weights for policy 1, policy_version 23421 (0.0009) -[2023-10-09 09:12:34,386][23468] Updated weights for policy 0, policy_version 23303 (0.0008) -[2023-10-09 09:12:34,757][23468] Updated weights for policy 0, policy_version 23313 (0.0008) -[2023-10-09 09:12:35,136][23468] Updated weights for policy 0, policy_version 23323 (0.0008) -[2023-10-09 09:12:36,077][22500] Fps is (10 sec: 16384.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 47874048. Throughput: 0: 1779.8, 1: 1787.6. Samples: 11969516. Policy #0 lag: (min: 0.0, avg: 24.7, max: 32.0) -[2023-10-09 09:12:36,078][22500] Avg episode reward: [(0, '7.090'), (1, '6.040')] -[2023-10-09 09:12:37,537][23469] Updated weights for policy 1, policy_version 23431 (0.0008) -[2023-10-09 09:12:37,910][23469] Updated weights for policy 1, policy_version 23441 (0.0008) -[2023-10-09 09:12:38,292][23469] Updated weights for policy 1, policy_version 23451 (0.0010) -[2023-10-09 09:12:38,829][23468] Updated weights for policy 0, policy_version 23333 (0.0008) -[2023-10-09 09:12:39,209][23468] Updated weights for policy 0, policy_version 23343 (0.0008) -[2023-10-09 09:12:39,570][23468] Updated weights for policy 0, policy_version 23353 (0.0008) -[2023-10-09 09:12:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 47939584. Throughput: 0: 1801.4, 1: 1787.8. Samples: 11991294. Policy #0 lag: (min: 0.0, avg: 24.7, max: 32.0) -[2023-10-09 09:12:41,078][22500] Avg episode reward: [(0, '7.820'), (1, '6.270')] -[2023-10-09 09:12:41,080][23265] Saving new best policy, reward=7.820! -[2023-10-09 09:12:41,933][23469] Updated weights for policy 1, policy_version 23461 (0.0008) -[2023-10-09 09:12:42,306][23469] Updated weights for policy 1, policy_version 23471 (0.0008) -[2023-10-09 09:12:42,674][23469] Updated weights for policy 1, policy_version 23481 (0.0008) -[2023-10-09 09:12:43,469][23468] Updated weights for policy 0, policy_version 23363 (0.0009) -[2023-10-09 09:12:43,845][23468] Updated weights for policy 0, policy_version 23373 (0.0008) -[2023-10-09 09:12:44,225][23468] Updated weights for policy 0, policy_version 23383 (0.0008) -[2023-10-09 09:12:46,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 48005120. Throughput: 0: 1780.5, 1: 1789.0. Samples: 12012756. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-09 09:12:46,079][22500] Avg episode reward: [(0, '7.630'), (1, '6.460')] -[2023-10-09 09:12:46,429][23469] Updated weights for policy 1, policy_version 23491 (0.0008) -[2023-10-09 09:12:46,841][23469] Updated weights for policy 1, policy_version 23501 (0.0008) -[2023-10-09 09:12:47,206][23469] Updated weights for policy 1, policy_version 23511 (0.0007) -[2023-10-09 09:12:47,902][23468] Updated weights for policy 0, policy_version 23393 (0.0009) -[2023-10-09 09:12:48,273][23468] Updated weights for policy 0, policy_version 23403 (0.0007) -[2023-10-09 09:12:48,654][23468] Updated weights for policy 0, policy_version 23413 (0.0007) -[2023-10-09 09:12:49,028][23468] Updated weights for policy 0, policy_version 23423 (0.0009) -[2023-10-09 09:12:50,948][23469] Updated weights for policy 1, policy_version 23521 (0.0008) -[2023-10-09 09:12:51,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 48070656. Throughput: 0: 1799.6, 1: 1788.1. Samples: 12023354. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-09 09:12:51,079][22500] Avg episode reward: [(0, '6.880'), (1, '6.500')] -[2023-10-09 09:12:51,323][23469] Updated weights for policy 1, policy_version 23531 (0.0009) -[2023-10-09 09:12:51,697][23469] Updated weights for policy 1, policy_version 23541 (0.0008) -[2023-10-09 09:12:52,065][23469] Updated weights for policy 1, policy_version 23551 (0.0009) -[2023-10-09 09:12:52,662][23468] Updated weights for policy 0, policy_version 23433 (0.0009) -[2023-10-09 09:12:53,029][23468] Updated weights for policy 0, policy_version 23443 (0.0007) -[2023-10-09 09:12:53,400][23468] Updated weights for policy 0, policy_version 23453 (0.0007) -[2023-10-09 09:12:55,847][23469] Updated weights for policy 1, policy_version 23561 (0.0010) -[2023-10-09 09:12:56,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 48136192. Throughput: 0: 1779.7, 1: 1789.2. Samples: 12044852. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-09 09:12:56,078][22500] Avg episode reward: [(0, '6.580'), (1, '6.200')] -[2023-10-09 09:12:56,214][23469] Updated weights for policy 1, policy_version 23571 (0.0009) -[2023-10-09 09:12:56,588][23469] Updated weights for policy 1, policy_version 23581 (0.0008) -[2023-10-09 09:12:57,143][23468] Updated weights for policy 0, policy_version 23463 (0.0008) -[2023-10-09 09:12:57,524][23468] Updated weights for policy 0, policy_version 23473 (0.0011) -[2023-10-09 09:12:57,901][23468] Updated weights for policy 0, policy_version 23483 (0.0009) -[2023-10-09 09:13:00,282][23469] Updated weights for policy 1, policy_version 23591 (0.0007) -[2023-10-09 09:13:00,647][23469] Updated weights for policy 1, policy_version 23601 (0.0010) -[2023-10-09 09:13:01,016][23469] Updated weights for policy 1, policy_version 23611 (0.0007) -[2023-10-09 09:13:01,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 48201728. Throughput: 0: 1782.4, 1: 1803.2. Samples: 12066524. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-09 09:13:01,079][22500] Avg episode reward: [(0, '6.810'), (1, '6.240')] -[2023-10-09 09:13:01,820][23468] Updated weights for policy 0, policy_version 23493 (0.0009) -[2023-10-09 09:13:02,211][23468] Updated weights for policy 0, policy_version 23503 (0.0008) -[2023-10-09 09:13:02,572][23468] Updated weights for policy 0, policy_version 23513 (0.0009) -[2023-10-09 09:13:04,716][23469] Updated weights for policy 1, policy_version 23621 (0.0007) -[2023-10-09 09:13:05,080][23469] Updated weights for policy 1, policy_version 23631 (0.0007) -[2023-10-09 09:13:05,458][23469] Updated weights for policy 1, policy_version 23641 (0.0011) -[2023-10-09 09:13:06,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 48300032. Throughput: 0: 1781.4, 1: 1792.5. Samples: 12077028. Policy #0 lag: (min: 8.0, avg: 27.7, max: 40.0) -[2023-10-09 09:13:06,078][22500] Avg episode reward: [(0, '6.890'), (1, '6.100')] -[2023-10-09 09:13:06,240][23468] Updated weights for policy 0, policy_version 23523 (0.0008) -[2023-10-09 09:13:06,611][23468] Updated weights for policy 0, policy_version 23533 (0.0008) -[2023-10-09 09:13:06,989][23468] Updated weights for policy 0, policy_version 23543 (0.0007) -[2023-10-09 09:13:09,139][23469] Updated weights for policy 1, policy_version 23651 (0.0010) -[2023-10-09 09:13:09,505][23469] Updated weights for policy 1, policy_version 23661 (0.0007) -[2023-10-09 09:13:09,874][23469] Updated weights for policy 1, policy_version 23671 (0.0011) -[2023-10-09 09:13:10,923][23468] Updated weights for policy 0, policy_version 23553 (0.0007) -[2023-10-09 09:13:11,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 48365568. Throughput: 0: 1781.5, 1: 1811.3. Samples: 12098652. Policy #0 lag: (min: 8.0, avg: 27.7, max: 40.0) -[2023-10-09 09:13:11,078][22500] Avg episode reward: [(0, '6.700'), (1, '5.830')] -[2023-10-09 09:13:11,292][23468] Updated weights for policy 0, policy_version 23563 (0.0008) -[2023-10-09 09:13:11,669][23468] Updated weights for policy 0, policy_version 23573 (0.0008) -[2023-10-09 09:13:12,040][23468] Updated weights for policy 0, policy_version 23583 (0.0009) -[2023-10-09 09:13:13,694][23469] Updated weights for policy 1, policy_version 23681 (0.0009) -[2023-10-09 09:13:14,061][23469] Updated weights for policy 1, policy_version 23691 (0.0010) -[2023-10-09 09:13:14,429][23469] Updated weights for policy 1, policy_version 23701 (0.0007) -[2023-10-09 09:13:14,805][23469] Updated weights for policy 1, policy_version 23711 (0.0007) -[2023-10-09 09:13:15,955][23468] Updated weights for policy 0, policy_version 23593 (0.0010) -[2023-10-09 09:13:16,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 48431104. Throughput: 0: 1786.8, 1: 1793.3. Samples: 12119970. Policy #0 lag: (min: 8.0, avg: 27.7, max: 40.0) -[2023-10-09 09:13:16,079][22500] Avg episode reward: [(0, '6.680'), (1, '5.950')] -[2023-10-09 09:13:16,334][23468] Updated weights for policy 0, policy_version 23603 (0.0009) -[2023-10-09 09:13:16,706][23468] Updated weights for policy 0, policy_version 23613 (0.0009) -[2023-10-09 09:13:18,803][23469] Updated weights for policy 1, policy_version 23721 (0.0007) -[2023-10-09 09:13:19,171][23469] Updated weights for policy 1, policy_version 23731 (0.0008) -[2023-10-09 09:13:19,544][23469] Updated weights for policy 1, policy_version 23741 (0.0009) -[2023-10-09 09:13:20,304][23468] Updated weights for policy 0, policy_version 23623 (0.0009) -[2023-10-09 09:13:20,679][23468] Updated weights for policy 0, policy_version 23633 (0.0009) -[2023-10-09 09:13:21,051][23468] Updated weights for policy 0, policy_version 23643 (0.0008) -[2023-10-09 09:13:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 48496640. Throughput: 0: 1766.5, 1: 1812.8. Samples: 12130584. Policy #0 lag: (min: 8.0, avg: 27.7, max: 40.0) -[2023-10-09 09:13:21,078][22500] Avg episode reward: [(0, '7.030'), (1, '5.790')] -[2023-10-09 09:13:23,316][23469] Updated weights for policy 1, policy_version 23751 (0.0011) -[2023-10-09 09:13:23,690][23469] Updated weights for policy 1, policy_version 23761 (0.0010) -[2023-10-09 09:13:24,067][23469] Updated weights for policy 1, policy_version 23771 (0.0011) -[2023-10-09 09:13:24,801][23468] Updated weights for policy 0, policy_version 23653 (0.0007) -[2023-10-09 09:13:25,180][23468] Updated weights for policy 0, policy_version 23663 (0.0007) -[2023-10-09 09:13:25,556][23468] Updated weights for policy 0, policy_version 23673 (0.0010) -[2023-10-09 09:13:26,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 48594944. Throughput: 0: 1784.2, 1: 1784.0. Samples: 12151864. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:13:26,078][22500] Avg episode reward: [(0, '6.930'), (1, '6.300')] -[2023-10-09 09:13:27,999][23469] Updated weights for policy 1, policy_version 23781 (0.0009) -[2023-10-09 09:13:28,368][23469] Updated weights for policy 1, policy_version 23791 (0.0008) -[2023-10-09 09:13:28,740][23469] Updated weights for policy 1, policy_version 23801 (0.0010) -[2023-10-09 09:13:29,356][23468] Updated weights for policy 0, policy_version 23683 (0.0010) -[2023-10-09 09:13:29,723][23468] Updated weights for policy 0, policy_version 23693 (0.0010) -[2023-10-09 09:13:30,091][23468] Updated weights for policy 0, policy_version 23703 (0.0011) -[2023-10-09 09:13:31,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 48660480. Throughput: 0: 1773.3, 1: 1778.9. Samples: 12172602. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:13:31,078][22500] Avg episode reward: [(0, '7.050'), (1, '5.690')] -[2023-10-09 09:13:32,527][23469] Updated weights for policy 1, policy_version 23811 (0.0010) -[2023-10-09 09:13:32,915][23469] Updated weights for policy 1, policy_version 23821 (0.0011) -[2023-10-09 09:13:33,283][23469] Updated weights for policy 1, policy_version 23831 (0.0010) -[2023-10-09 09:13:33,804][23468] Updated weights for policy 0, policy_version 23713 (0.0010) -[2023-10-09 09:13:34,171][23468] Updated weights for policy 0, policy_version 23723 (0.0011) -[2023-10-09 09:13:34,544][23468] Updated weights for policy 0, policy_version 23733 (0.0007) -[2023-10-09 09:13:34,922][23468] Updated weights for policy 0, policy_version 23743 (0.0009) -[2023-10-09 09:13:36,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 48726016. Throughput: 0: 1781.3, 1: 1779.3. Samples: 12183578. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:13:36,078][22500] Avg episode reward: [(0, '6.980'), (1, '5.790')] -[2023-10-09 09:13:37,032][23469] Updated weights for policy 1, policy_version 23841 (0.0007) -[2023-10-09 09:13:37,409][23469] Updated weights for policy 1, policy_version 23851 (0.0011) -[2023-10-09 09:13:37,780][23469] Updated weights for policy 1, policy_version 23861 (0.0010) -[2023-10-09 09:13:38,148][23469] Updated weights for policy 1, policy_version 23871 (0.0009) -[2023-10-09 09:13:38,770][23468] Updated weights for policy 0, policy_version 23753 (0.0010) -[2023-10-09 09:13:39,151][23468] Updated weights for policy 0, policy_version 23763 (0.0010) -[2023-10-09 09:13:39,521][23468] Updated weights for policy 0, policy_version 23773 (0.0010) -[2023-10-09 09:13:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 48791552. Throughput: 0: 1779.8, 1: 1781.8. Samples: 12205122. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:13:41,078][22500] Avg episode reward: [(0, '7.070'), (1, '5.920')] -[2023-10-09 09:13:41,742][23469] Updated weights for policy 1, policy_version 23881 (0.0010) -[2023-10-09 09:13:42,119][23469] Updated weights for policy 1, policy_version 23891 (0.0011) -[2023-10-09 09:13:42,492][23469] Updated weights for policy 1, policy_version 23901 (0.0007) -[2023-10-09 09:13:43,363][23468] Updated weights for policy 0, policy_version 23783 (0.0009) -[2023-10-09 09:13:43,725][23468] Updated weights for policy 0, policy_version 23793 (0.0011) -[2023-10-09 09:13:44,104][23468] Updated weights for policy 0, policy_version 23803 (0.0007) -[2023-10-09 09:13:45,992][23469] Updated weights for policy 1, policy_version 23911 (0.0007) -[2023-10-09 09:13:46,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 48857088. Throughput: 0: 1765.6, 1: 1802.9. Samples: 12227104. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:13:46,078][22500] Avg episode reward: [(0, '7.060'), (1, '6.510')] -[2023-10-09 09:13:46,363][23469] Updated weights for policy 1, policy_version 23921 (0.0007) -[2023-10-09 09:13:46,735][23469] Updated weights for policy 1, policy_version 23931 (0.0007) -[2023-10-09 09:13:48,066][23468] Updated weights for policy 0, policy_version 23813 (0.0007) -[2023-10-09 09:13:48,447][23468] Updated weights for policy 0, policy_version 23823 (0.0007) -[2023-10-09 09:13:48,817][23468] Updated weights for policy 0, policy_version 23833 (0.0010) -[2023-10-09 09:13:50,640][23469] Updated weights for policy 1, policy_version 23941 (0.0009) -[2023-10-09 09:13:51,009][23469] Updated weights for policy 1, policy_version 23951 (0.0009) -[2023-10-09 09:13:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 48922624. Throughput: 0: 1787.6, 1: 1782.2. Samples: 12237672. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:13:51,078][22500] Avg episode reward: [(0, '7.220'), (1, '6.420')] -[2023-10-09 09:13:51,385][23469] Updated weights for policy 1, policy_version 23961 (0.0009) -[2023-10-09 09:13:52,638][23468] Updated weights for policy 0, policy_version 23843 (0.0010) -[2023-10-09 09:13:53,014][23468] Updated weights for policy 0, policy_version 23853 (0.0009) -[2023-10-09 09:13:53,400][23468] Updated weights for policy 0, policy_version 23863 (0.0010) -[2023-10-09 09:13:55,045][23469] Updated weights for policy 1, policy_version 23971 (0.0008) -[2023-10-09 09:13:55,408][23469] Updated weights for policy 1, policy_version 23981 (0.0008) -[2023-10-09 09:13:55,781][23469] Updated weights for policy 1, policy_version 23991 (0.0008) -[2023-10-09 09:13:56,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 48988160. Throughput: 0: 1763.5, 1: 1799.1. Samples: 12258974. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:13:56,078][22500] Avg episode reward: [(0, '7.070'), (1, '6.120')] -[2023-10-09 09:13:57,117][23468] Updated weights for policy 0, policy_version 23873 (0.0008) -[2023-10-09 09:13:57,501][23468] Updated weights for policy 0, policy_version 23883 (0.0007) -[2023-10-09 09:13:57,889][23468] Updated weights for policy 0, policy_version 23893 (0.0009) -[2023-10-09 09:13:58,266][23468] Updated weights for policy 0, policy_version 23903 (0.0010) -[2023-10-09 09:13:59,531][23469] Updated weights for policy 1, policy_version 24001 (0.0008) -[2023-10-09 09:13:59,905][23469] Updated weights for policy 1, policy_version 24011 (0.0007) -[2023-10-09 09:14:00,264][23469] Updated weights for policy 1, policy_version 24021 (0.0008) -[2023-10-09 09:14:00,640][23469] Updated weights for policy 1, policy_version 24031 (0.0008) -[2023-10-09 09:14:01,078][22500] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 49086464. Throughput: 0: 1775.7, 1: 1780.4. Samples: 12279996. Policy #0 lag: (min: 13.0, avg: 13.9, max: 33.0) -[2023-10-09 09:14:01,079][22500] Avg episode reward: [(0, '6.800'), (1, '6.220')] -[2023-10-09 09:14:02,040][23468] Updated weights for policy 0, policy_version 23913 (0.0008) -[2023-10-09 09:14:02,422][23468] Updated weights for policy 0, policy_version 23923 (0.0008) -[2023-10-09 09:14:02,795][23468] Updated weights for policy 0, policy_version 23933 (0.0009) -[2023-10-09 09:14:04,427][23469] Updated weights for policy 1, policy_version 24041 (0.0007) -[2023-10-09 09:14:04,795][23469] Updated weights for policy 1, policy_version 24051 (0.0008) -[2023-10-09 09:14:05,156][23469] Updated weights for policy 1, policy_version 24061 (0.0007) -[2023-10-09 09:14:06,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 49152000. Throughput: 0: 1778.9, 1: 1794.1. Samples: 12291372. Policy #0 lag: (min: 13.0, avg: 13.9, max: 33.0) -[2023-10-09 09:14:06,078][22500] Avg episode reward: [(0, '7.170'), (1, '6.310')] -[2023-10-09 09:14:06,406][23468] Updated weights for policy 0, policy_version 23943 (0.0008) -[2023-10-09 09:14:06,788][23468] Updated weights for policy 0, policy_version 23953 (0.0007) -[2023-10-09 09:14:07,171][23468] Updated weights for policy 0, policy_version 23963 (0.0007) -[2023-10-09 09:14:08,889][23469] Updated weights for policy 1, policy_version 24071 (0.0008) -[2023-10-09 09:14:09,257][23469] Updated weights for policy 1, policy_version 24081 (0.0008) -[2023-10-09 09:14:09,621][23469] Updated weights for policy 1, policy_version 24091 (0.0009) -[2023-10-09 09:14:10,965][23468] Updated weights for policy 0, policy_version 23973 (0.0008) -[2023-10-09 09:14:11,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 49217536. Throughput: 0: 1778.2, 1: 1793.2. Samples: 12312578. Policy #0 lag: (min: 13.0, avg: 13.9, max: 33.0) -[2023-10-09 09:14:11,079][22500] Avg episode reward: [(0, '6.680'), (1, '6.140')] -[2023-10-09 09:14:11,350][23468] Updated weights for policy 0, policy_version 23983 (0.0010) -[2023-10-09 09:14:11,715][23468] Updated weights for policy 0, policy_version 23993 (0.0009) -[2023-10-09 09:14:13,399][23469] Updated weights for policy 1, policy_version 24101 (0.0010) -[2023-10-09 09:14:13,764][23469] Updated weights for policy 1, policy_version 24111 (0.0007) -[2023-10-09 09:14:14,138][23469] Updated weights for policy 1, policy_version 24121 (0.0008) -[2023-10-09 09:14:15,335][23468] Updated weights for policy 0, policy_version 24003 (0.0007) -[2023-10-09 09:14:15,707][23468] Updated weights for policy 0, policy_version 24013 (0.0008) -[2023-10-09 09:14:16,076][23468] Updated weights for policy 0, policy_version 24023 (0.0009) -[2023-10-09 09:14:16,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 49283072. Throughput: 0: 1812.8, 1: 1794.8. Samples: 12334946. Policy #0 lag: (min: 13.0, avg: 13.9, max: 33.0) -[2023-10-09 09:14:16,079][22500] Avg episode reward: [(0, '7.500'), (1, '6.020')] -[2023-10-09 09:14:16,089][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000024128_24707072.pth... -[2023-10-09 09:14:16,129][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000022464_23003136.pth -[2023-10-09 09:14:16,408][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000024032_24608768.pth... -[2023-10-09 09:14:16,442][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000022336_22872064.pth -[2023-10-09 09:14:17,996][23469] Updated weights for policy 1, policy_version 24131 (0.0007) -[2023-10-09 09:14:18,400][23469] Updated weights for policy 1, policy_version 24141 (0.0008) -[2023-10-09 09:14:18,776][23469] Updated weights for policy 1, policy_version 24151 (0.0007) -[2023-10-09 09:14:19,936][23468] Updated weights for policy 0, policy_version 24033 (0.0009) -[2023-10-09 09:14:20,307][23468] Updated weights for policy 0, policy_version 24043 (0.0009) -[2023-10-09 09:14:20,682][23468] Updated weights for policy 0, policy_version 24053 (0.0007) -[2023-10-09 09:14:21,055][23468] Updated weights for policy 0, policy_version 24063 (0.0007) -[2023-10-09 09:14:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 49348608. Throughput: 0: 1783.1, 1: 1805.9. Samples: 12345084. Policy #0 lag: (min: 21.0, avg: 27.6, max: 53.0) -[2023-10-09 09:14:21,079][22500] Avg episode reward: [(0, '6.860'), (1, '5.930')] -[2023-10-09 09:14:22,321][23469] Updated weights for policy 1, policy_version 24161 (0.0008) -[2023-10-09 09:14:22,687][23469] Updated weights for policy 1, policy_version 24171 (0.0007) -[2023-10-09 09:14:23,064][23469] Updated weights for policy 1, policy_version 24181 (0.0009) -[2023-10-09 09:14:23,436][23469] Updated weights for policy 1, policy_version 24191 (0.0008) -[2023-10-09 09:14:24,782][23468] Updated weights for policy 0, policy_version 24073 (0.0011) -[2023-10-09 09:14:25,156][23468] Updated weights for policy 0, policy_version 24083 (0.0008) -[2023-10-09 09:14:25,528][23468] Updated weights for policy 0, policy_version 24093 (0.0011) -[2023-10-09 09:14:26,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 49446912. Throughput: 0: 1804.3, 1: 1796.7. Samples: 12367164. Policy #0 lag: (min: 21.0, avg: 27.6, max: 53.0) -[2023-10-09 09:14:26,078][22500] Avg episode reward: [(0, '7.030'), (1, '6.120')] -[2023-10-09 09:14:27,140][23469] Updated weights for policy 1, policy_version 24201 (0.0009) -[2023-10-09 09:14:27,520][23469] Updated weights for policy 1, policy_version 24211 (0.0009) -[2023-10-09 09:14:27,873][23469] Updated weights for policy 1, policy_version 24221 (0.0008) -[2023-10-09 09:14:29,216][23468] Updated weights for policy 0, policy_version 24103 (0.0008) -[2023-10-09 09:14:29,596][23468] Updated weights for policy 0, policy_version 24113 (0.0007) -[2023-10-09 09:14:29,978][23468] Updated weights for policy 0, policy_version 24123 (0.0008) -[2023-10-09 09:14:31,078][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 49512448. Throughput: 0: 1782.8, 1: 1796.6. Samples: 12388178. Policy #0 lag: (min: 21.0, avg: 27.6, max: 53.0) -[2023-10-09 09:14:31,079][22500] Avg episode reward: [(0, '6.990'), (1, '6.540')] -[2023-10-09 09:14:31,574][23469] Updated weights for policy 1, policy_version 24231 (0.0009) -[2023-10-09 09:14:31,946][23469] Updated weights for policy 1, policy_version 24241 (0.0007) -[2023-10-09 09:14:32,321][23469] Updated weights for policy 1, policy_version 24251 (0.0007) -[2023-10-09 09:14:33,916][23468] Updated weights for policy 0, policy_version 24133 (0.0009) -[2023-10-09 09:14:34,306][23468] Updated weights for policy 0, policy_version 24143 (0.0009) -[2023-10-09 09:14:34,675][23468] Updated weights for policy 0, policy_version 24153 (0.0010) -[2023-10-09 09:14:36,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 49577984. Throughput: 0: 1794.4, 1: 1796.4. Samples: 12399260. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 09:14:36,078][22500] Avg episode reward: [(0, '7.280'), (1, '6.370')] -[2023-10-09 09:14:36,171][23469] Updated weights for policy 1, policy_version 24261 (0.0010) -[2023-10-09 09:14:36,534][23469] Updated weights for policy 1, policy_version 24271 (0.0008) -[2023-10-09 09:14:36,905][23469] Updated weights for policy 1, policy_version 24281 (0.0008) -[2023-10-09 09:14:38,408][23468] Updated weights for policy 0, policy_version 24163 (0.0009) -[2023-10-09 09:14:38,772][23468] Updated weights for policy 0, policy_version 24173 (0.0008) -[2023-10-09 09:14:39,153][23468] Updated weights for policy 0, policy_version 24183 (0.0008) -[2023-10-09 09:14:40,659][23469] Updated weights for policy 1, policy_version 24291 (0.0008) -[2023-10-09 09:14:41,030][23469] Updated weights for policy 1, policy_version 24301 (0.0008) -[2023-10-09 09:14:41,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 49643520. Throughput: 0: 1792.2, 1: 1801.1. Samples: 12420670. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 09:14:41,078][22500] Avg episode reward: [(0, '7.060'), (1, '6.250')] -[2023-10-09 09:14:41,401][23469] Updated weights for policy 1, policy_version 24311 (0.0008) -[2023-10-09 09:14:42,903][23468] Updated weights for policy 0, policy_version 24193 (0.0009) -[2023-10-09 09:14:43,272][23468] Updated weights for policy 0, policy_version 24203 (0.0008) -[2023-10-09 09:14:43,649][23468] Updated weights for policy 0, policy_version 24213 (0.0008) -[2023-10-09 09:14:44,026][23468] Updated weights for policy 0, policy_version 24223 (0.0007) -[2023-10-09 09:14:45,019][23469] Updated weights for policy 1, policy_version 24321 (0.0008) -[2023-10-09 09:14:45,397][23469] Updated weights for policy 1, policy_version 24331 (0.0008) -[2023-10-09 09:14:45,767][23469] Updated weights for policy 1, policy_version 24341 (0.0008) -[2023-10-09 09:14:46,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 49709056. Throughput: 0: 1786.8, 1: 1816.4. Samples: 12442144. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 09:14:46,078][22500] Avg episode reward: [(0, '7.060'), (1, '6.040')] -[2023-10-09 09:14:46,140][23469] Updated weights for policy 1, policy_version 24351 (0.0009) -[2023-10-09 09:14:47,707][23468] Updated weights for policy 0, policy_version 24233 (0.0009) -[2023-10-09 09:14:48,089][23468] Updated weights for policy 0, policy_version 24243 (0.0011) -[2023-10-09 09:14:48,460][23468] Updated weights for policy 0, policy_version 24253 (0.0010) -[2023-10-09 09:14:49,926][23469] Updated weights for policy 1, policy_version 24361 (0.0008) -[2023-10-09 09:14:50,291][23469] Updated weights for policy 1, policy_version 24371 (0.0008) -[2023-10-09 09:14:50,664][23469] Updated weights for policy 1, policy_version 24381 (0.0008) -[2023-10-09 09:14:51,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 49807360. Throughput: 0: 1794.9, 1: 1802.4. Samples: 12453250. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 09:14:51,078][22500] Avg episode reward: [(0, '7.000'), (1, '6.310')] -[2023-10-09 09:14:52,181][23468] Updated weights for policy 0, policy_version 24263 (0.0009) -[2023-10-09 09:14:52,552][23468] Updated weights for policy 0, policy_version 24273 (0.0009) -[2023-10-09 09:14:52,923][23468] Updated weights for policy 0, policy_version 24283 (0.0008) -[2023-10-09 09:14:54,361][23469] Updated weights for policy 1, policy_version 24391 (0.0009) -[2023-10-09 09:14:54,726][23469] Updated weights for policy 1, policy_version 24401 (0.0010) -[2023-10-09 09:14:55,096][23469] Updated weights for policy 1, policy_version 24411 (0.0010) -[2023-10-09 09:14:56,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 49872896. Throughput: 0: 1784.0, 1: 1816.6. Samples: 12474604. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:14:56,078][22500] Avg episode reward: [(0, '6.420'), (1, '6.150')] -[2023-10-09 09:14:56,670][23468] Updated weights for policy 0, policy_version 24293 (0.0009) -[2023-10-09 09:14:57,046][23468] Updated weights for policy 0, policy_version 24303 (0.0010) -[2023-10-09 09:14:57,418][23468] Updated weights for policy 0, policy_version 24313 (0.0009) -[2023-10-09 09:14:58,745][23469] Updated weights for policy 1, policy_version 24421 (0.0010) -[2023-10-09 09:14:59,121][23469] Updated weights for policy 1, policy_version 24431 (0.0007) -[2023-10-09 09:14:59,479][23469] Updated weights for policy 1, policy_version 24441 (0.0007) -[2023-10-09 09:15:01,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 49938432. Throughput: 0: 1781.6, 1: 1805.7. Samples: 12496376. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:15:01,078][22500] Avg episode reward: [(0, '6.040'), (1, '6.190')] -[2023-10-09 09:15:01,239][23468] Updated weights for policy 0, policy_version 24323 (0.0008) -[2023-10-09 09:15:01,605][23468] Updated weights for policy 0, policy_version 24333 (0.0009) -[2023-10-09 09:15:01,983][23468] Updated weights for policy 0, policy_version 24343 (0.0007) -[2023-10-09 09:15:03,159][23469] Updated weights for policy 1, policy_version 24451 (0.0008) -[2023-10-09 09:15:03,537][23469] Updated weights for policy 1, policy_version 24461 (0.0007) -[2023-10-09 09:15:03,902][23469] Updated weights for policy 1, policy_version 24471 (0.0009) -[2023-10-09 09:15:05,812][23468] Updated weights for policy 0, policy_version 24353 (0.0007) -[2023-10-09 09:15:06,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 50003968. Throughput: 0: 1779.9, 1: 1812.3. Samples: 12506734. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:15:06,078][22500] Avg episode reward: [(0, '6.540'), (1, '5.900')] -[2023-10-09 09:15:06,191][23468] Updated weights for policy 0, policy_version 24363 (0.0008) -[2023-10-09 09:15:06,560][23468] Updated weights for policy 0, policy_version 24373 (0.0008) -[2023-10-09 09:15:06,932][23468] Updated weights for policy 0, policy_version 24383 (0.0007) -[2023-10-09 09:15:07,768][23469] Updated weights for policy 1, policy_version 24481 (0.0009) -[2023-10-09 09:15:08,141][23469] Updated weights for policy 1, policy_version 24491 (0.0008) -[2023-10-09 09:15:08,502][23469] Updated weights for policy 1, policy_version 24501 (0.0007) -[2023-10-09 09:15:08,879][23469] Updated weights for policy 1, policy_version 24511 (0.0009) -[2023-10-09 09:15:10,603][23468] Updated weights for policy 0, policy_version 24393 (0.0007) -[2023-10-09 09:15:10,972][23468] Updated weights for policy 0, policy_version 24403 (0.0010) -[2023-10-09 09:15:11,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 50069504. Throughput: 0: 1785.5, 1: 1804.0. Samples: 12528688. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:15:11,078][22500] Avg episode reward: [(0, '6.530'), (1, '6.000')] -[2023-10-09 09:15:11,348][23468] Updated weights for policy 0, policy_version 24413 (0.0007) -[2023-10-09 09:15:12,643][23469] Updated weights for policy 1, policy_version 24521 (0.0008) -[2023-10-09 09:15:13,021][23469] Updated weights for policy 1, policy_version 24531 (0.0010) -[2023-10-09 09:15:13,386][23469] Updated weights for policy 1, policy_version 24541 (0.0007) -[2023-10-09 09:15:14,989][23468] Updated weights for policy 0, policy_version 24423 (0.0008) -[2023-10-09 09:15:15,366][23468] Updated weights for policy 0, policy_version 24433 (0.0007) -[2023-10-09 09:15:15,738][23468] Updated weights for policy 0, policy_version 24443 (0.0007) -[2023-10-09 09:15:16,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 50167808. Throughput: 0: 1808.1, 1: 1806.1. Samples: 12550814. Policy #0 lag: (min: 31.0, avg: 47.1, max: 48.0) -[2023-10-09 09:15:16,078][22500] Avg episode reward: [(0, '6.830'), (1, '5.900')] -[2023-10-09 09:15:17,035][23469] Updated weights for policy 1, policy_version 24551 (0.0009) -[2023-10-09 09:15:17,405][23469] Updated weights for policy 1, policy_version 24561 (0.0007) -[2023-10-09 09:15:17,775][23469] Updated weights for policy 1, policy_version 24571 (0.0008) -[2023-10-09 09:15:19,451][23468] Updated weights for policy 0, policy_version 24453 (0.0010) -[2023-10-09 09:15:19,829][23468] Updated weights for policy 0, policy_version 24463 (0.0010) -[2023-10-09 09:15:20,211][23468] Updated weights for policy 0, policy_version 24473 (0.0008) -[2023-10-09 09:15:21,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 50233344. Throughput: 0: 1796.6, 1: 1806.0. Samples: 12561378. Policy #0 lag: (min: 31.0, avg: 47.1, max: 48.0) -[2023-10-09 09:15:21,078][22500] Avg episode reward: [(0, '6.680'), (1, '5.920')] -[2023-10-09 09:15:21,616][23469] Updated weights for policy 1, policy_version 24581 (0.0009) -[2023-10-09 09:15:21,991][23469] Updated weights for policy 1, policy_version 24591 (0.0010) -[2023-10-09 09:15:22,363][23469] Updated weights for policy 1, policy_version 24601 (0.0007) -[2023-10-09 09:15:23,988][23468] Updated weights for policy 0, policy_version 24483 (0.0009) -[2023-10-09 09:15:24,358][23468] Updated weights for policy 0, policy_version 24493 (0.0008) -[2023-10-09 09:15:24,727][23468] Updated weights for policy 0, policy_version 24503 (0.0007) -[2023-10-09 09:15:26,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 50298880. Throughput: 0: 1805.2, 1: 1801.9. Samples: 12582988. Policy #0 lag: (min: 31.0, avg: 47.1, max: 48.0) -[2023-10-09 09:15:26,078][22500] Avg episode reward: [(0, '6.800'), (1, '5.800')] -[2023-10-09 09:15:26,098][23469] Updated weights for policy 1, policy_version 24611 (0.0008) -[2023-10-09 09:15:26,461][23469] Updated weights for policy 1, policy_version 24621 (0.0008) -[2023-10-09 09:15:26,831][23469] Updated weights for policy 1, policy_version 24631 (0.0007) -[2023-10-09 09:15:28,499][23468] Updated weights for policy 0, policy_version 24513 (0.0007) -[2023-10-09 09:15:28,862][23468] Updated weights for policy 0, policy_version 24523 (0.0009) -[2023-10-09 09:15:29,239][23468] Updated weights for policy 0, policy_version 24533 (0.0008) -[2023-10-09 09:15:29,611][23468] Updated weights for policy 0, policy_version 24543 (0.0009) -[2023-10-09 09:15:30,435][23469] Updated weights for policy 1, policy_version 24641 (0.0008) -[2023-10-09 09:15:30,804][23469] Updated weights for policy 1, policy_version 24651 (0.0010) -[2023-10-09 09:15:31,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 50364416. Throughput: 0: 1786.0, 1: 1814.7. Samples: 12604172. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 09:15:31,078][22500] Avg episode reward: [(0, '7.310'), (1, '5.880')] -[2023-10-09 09:15:31,180][23469] Updated weights for policy 1, policy_version 24661 (0.0011) -[2023-10-09 09:15:31,546][23469] Updated weights for policy 1, policy_version 24671 (0.0010) -[2023-10-09 09:15:33,220][23468] Updated weights for policy 0, policy_version 24553 (0.0010) -[2023-10-09 09:15:33,596][23468] Updated weights for policy 0, policy_version 24563 (0.0008) -[2023-10-09 09:15:33,973][23468] Updated weights for policy 0, policy_version 24573 (0.0007) -[2023-10-09 09:15:35,356][23469] Updated weights for policy 1, policy_version 24681 (0.0007) -[2023-10-09 09:15:35,716][23469] Updated weights for policy 1, policy_version 24691 (0.0010) -[2023-10-09 09:15:36,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 50429952. Throughput: 0: 1804.8, 1: 1804.1. Samples: 12615650. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 09:15:36,078][22500] Avg episode reward: [(0, '7.020'), (1, '6.170')] -[2023-10-09 09:15:36,084][23469] Updated weights for policy 1, policy_version 24701 (0.0010) -[2023-10-09 09:15:37,659][23468] Updated weights for policy 0, policy_version 24583 (0.0009) -[2023-10-09 09:15:38,028][23468] Updated weights for policy 0, policy_version 24593 (0.0009) -[2023-10-09 09:15:38,406][23468] Updated weights for policy 0, policy_version 24603 (0.0008) -[2023-10-09 09:15:39,776][23469] Updated weights for policy 1, policy_version 24711 (0.0008) -[2023-10-09 09:15:40,145][23469] Updated weights for policy 1, policy_version 24721 (0.0008) -[2023-10-09 09:15:40,513][23469] Updated weights for policy 1, policy_version 24731 (0.0010) -[2023-10-09 09:15:41,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 50528256. Throughput: 0: 1796.8, 1: 1810.9. Samples: 12636950. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 09:15:41,078][22500] Avg episode reward: [(0, '7.040'), (1, '6.390')] -[2023-10-09 09:15:42,154][23468] Updated weights for policy 0, policy_version 24613 (0.0007) -[2023-10-09 09:15:42,520][23468] Updated weights for policy 0, policy_version 24623 (0.0007) -[2023-10-09 09:15:42,889][23468] Updated weights for policy 0, policy_version 24633 (0.0007) -[2023-10-09 09:15:44,098][23469] Updated weights for policy 1, policy_version 24741 (0.0008) -[2023-10-09 09:15:44,464][23469] Updated weights for policy 1, policy_version 24751 (0.0007) -[2023-10-09 09:15:44,838][23469] Updated weights for policy 1, policy_version 24761 (0.0008) -[2023-10-09 09:15:46,078][22500] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 50593792. Throughput: 0: 1798.3, 1: 1799.7. Samples: 12658288. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 09:15:46,078][22500] Avg episode reward: [(0, '7.360'), (1, '6.030')] -[2023-10-09 09:15:46,743][23468] Updated weights for policy 0, policy_version 24643 (0.0008) -[2023-10-09 09:15:47,129][23468] Updated weights for policy 0, policy_version 24653 (0.0008) -[2023-10-09 09:15:47,499][23468] Updated weights for policy 0, policy_version 24663 (0.0010) -[2023-10-09 09:15:48,651][23469] Updated weights for policy 1, policy_version 24771 (0.0009) -[2023-10-09 09:15:49,056][23469] Updated weights for policy 1, policy_version 24781 (0.0008) -[2023-10-09 09:15:49,430][23469] Updated weights for policy 1, policy_version 24791 (0.0009) -[2023-10-09 09:15:51,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 50659328. Throughput: 0: 1795.6, 1: 1811.5. Samples: 12669054. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-09 09:15:51,078][22500] Avg episode reward: [(0, '7.260'), (1, '6.010')] -[2023-10-09 09:15:51,221][23468] Updated weights for policy 0, policy_version 24673 (0.0009) -[2023-10-09 09:15:51,603][23468] Updated weights for policy 0, policy_version 24683 (0.0010) -[2023-10-09 09:15:51,967][23468] Updated weights for policy 0, policy_version 24693 (0.0009) -[2023-10-09 09:15:52,338][23468] Updated weights for policy 0, policy_version 24703 (0.0008) -[2023-10-09 09:15:53,079][23469] Updated weights for policy 1, policy_version 24801 (0.0009) -[2023-10-09 09:15:53,449][23469] Updated weights for policy 1, policy_version 24811 (0.0007) -[2023-10-09 09:15:53,819][23469] Updated weights for policy 1, policy_version 24821 (0.0008) -[2023-10-09 09:15:54,199][23469] Updated weights for policy 1, policy_version 24831 (0.0007) -[2023-10-09 09:15:56,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 50724864. Throughput: 0: 1790.6, 1: 1801.6. Samples: 12690336. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-09 09:15:56,078][22500] Avg episode reward: [(0, '7.470'), (1, '5.940')] -[2023-10-09 09:15:56,162][23468] Updated weights for policy 0, policy_version 24713 (0.0010) -[2023-10-09 09:15:56,539][23468] Updated weights for policy 0, policy_version 24723 (0.0008) -[2023-10-09 09:15:56,910][23468] Updated weights for policy 0, policy_version 24733 (0.0007) -[2023-10-09 09:15:57,826][23469] Updated weights for policy 1, policy_version 24841 (0.0008) -[2023-10-09 09:15:58,190][23469] Updated weights for policy 1, policy_version 24851 (0.0009) -[2023-10-09 09:15:58,560][23469] Updated weights for policy 1, policy_version 24861 (0.0010) -[2023-10-09 09:16:00,699][23468] Updated weights for policy 0, policy_version 24743 (0.0008) -[2023-10-09 09:16:01,074][23468] Updated weights for policy 0, policy_version 24753 (0.0007) -[2023-10-09 09:16:01,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 50790400. Throughput: 0: 1802.2, 1: 1798.7. Samples: 12712856. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-09 09:16:01,078][22500] Avg episode reward: [(0, '7.210'), (1, '6.030')] -[2023-10-09 09:16:01,438][23468] Updated weights for policy 0, policy_version 24763 (0.0011) -[2023-10-09 09:16:02,442][23469] Updated weights for policy 1, policy_version 24871 (0.0009) -[2023-10-09 09:16:02,808][23469] Updated weights for policy 1, policy_version 24881 (0.0007) -[2023-10-09 09:16:03,175][23469] Updated weights for policy 1, policy_version 24891 (0.0008) -[2023-10-09 09:16:05,190][23468] Updated weights for policy 0, policy_version 24773 (0.0008) -[2023-10-09 09:16:05,580][23468] Updated weights for policy 0, policy_version 24783 (0.0008) -[2023-10-09 09:16:05,952][23468] Updated weights for policy 0, policy_version 24793 (0.0009) -[2023-10-09 09:16:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 50855936. Throughput: 0: 1785.2, 1: 1798.0. Samples: 12722622. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-09 09:16:06,078][22500] Avg episode reward: [(0, '7.350'), (1, '6.190')] -[2023-10-09 09:16:06,947][23469] Updated weights for policy 1, policy_version 24901 (0.0010) -[2023-10-09 09:16:07,319][23469] Updated weights for policy 1, policy_version 24911 (0.0009) -[2023-10-09 09:16:07,682][23469] Updated weights for policy 1, policy_version 24921 (0.0007) -[2023-10-09 09:16:09,604][23468] Updated weights for policy 0, policy_version 24803 (0.0009) -[2023-10-09 09:16:09,984][23468] Updated weights for policy 0, policy_version 24813 (0.0007) -[2023-10-09 09:16:10,360][23468] Updated weights for policy 0, policy_version 24823 (0.0009) -[2023-10-09 09:16:11,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 50954240. Throughput: 0: 1811.2, 1: 1793.9. Samples: 12745218. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 09:16:11,078][22500] Avg episode reward: [(0, '6.900'), (1, '6.120')] -[2023-10-09 09:16:11,463][23469] Updated weights for policy 1, policy_version 24931 (0.0008) -[2023-10-09 09:16:11,834][23469] Updated weights for policy 1, policy_version 24941 (0.0007) -[2023-10-09 09:16:12,201][23469] Updated weights for policy 1, policy_version 24951 (0.0008) -[2023-10-09 09:16:14,001][23468] Updated weights for policy 0, policy_version 24833 (0.0009) -[2023-10-09 09:16:14,386][23468] Updated weights for policy 0, policy_version 24843 (0.0009) -[2023-10-09 09:16:14,766][23468] Updated weights for policy 0, policy_version 24853 (0.0009) -[2023-10-09 09:16:15,148][23468] Updated weights for policy 0, policy_version 24863 (0.0007) -[2023-10-09 09:16:15,914][23469] Updated weights for policy 1, policy_version 24961 (0.0007) -[2023-10-09 09:16:16,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 51019776. Throughput: 0: 1799.1, 1: 1806.7. Samples: 12766430. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 09:16:16,078][22500] Avg episode reward: [(0, '6.880'), (1, '6.420')] -[2023-10-09 09:16:16,087][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000024864_25460736.pth... -[2023-10-09 09:16:16,116][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000023200_23756800.pth -[2023-10-09 09:16:16,120][23265] Saving a milestone ./train_atari/atari_berzerk_APPO/checkpoint_p0/milestones/checkpoint_000024864_25460736.pth -[2023-10-09 09:16:16,286][23469] Updated weights for policy 1, policy_version 24971 (0.0007) -[2023-10-09 09:16:16,649][23469] Updated weights for policy 1, policy_version 24981 (0.0008) -[2023-10-09 09:16:17,021][23469] Updated weights for policy 1, policy_version 24991 (0.0008) -[2023-10-09 09:16:17,057][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000024992_25591808.pth... -[2023-10-09 09:16:17,085][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000023296_23855104.pth -[2023-10-09 09:16:17,089][23343] Saving a milestone ./train_atari/atari_berzerk_APPO/checkpoint_p1/milestones/checkpoint_000024992_25591808.pth -[2023-10-09 09:16:18,860][23468] Updated weights for policy 0, policy_version 24873 (0.0008) -[2023-10-09 09:16:19,226][23468] Updated weights for policy 0, policy_version 24883 (0.0010) -[2023-10-09 09:16:19,606][23468] Updated weights for policy 0, policy_version 24893 (0.0010) -[2023-10-09 09:16:20,842][23469] Updated weights for policy 1, policy_version 25001 (0.0010) -[2023-10-09 09:16:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 51085312. Throughput: 0: 1804.8, 1: 1791.0. Samples: 12777460. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 09:16:21,078][22500] Avg episode reward: [(0, '7.170'), (1, '6.260')] -[2023-10-09 09:16:21,209][23469] Updated weights for policy 1, policy_version 25011 (0.0009) -[2023-10-09 09:16:21,579][23469] Updated weights for policy 1, policy_version 25021 (0.0007) -[2023-10-09 09:16:23,331][23468] Updated weights for policy 0, policy_version 24903 (0.0011) -[2023-10-09 09:16:23,710][23468] Updated weights for policy 0, policy_version 24913 (0.0008) -[2023-10-09 09:16:24,075][23468] Updated weights for policy 0, policy_version 24923 (0.0009) -[2023-10-09 09:16:25,277][23469] Updated weights for policy 1, policy_version 25031 (0.0009) -[2023-10-09 09:16:25,648][23469] Updated weights for policy 1, policy_version 25041 (0.0009) -[2023-10-09 09:16:26,032][23469] Updated weights for policy 1, policy_version 25051 (0.0010) -[2023-10-09 09:16:26,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 51150848. Throughput: 0: 1791.5, 1: 1801.3. Samples: 12798626. Policy #0 lag: (min: 29.0, avg: 36.3, max: 61.0) -[2023-10-09 09:16:26,079][22500] Avg episode reward: [(0, '7.220'), (1, '6.320')] -[2023-10-09 09:16:27,770][23468] Updated weights for policy 0, policy_version 24933 (0.0008) -[2023-10-09 09:16:28,137][23468] Updated weights for policy 0, policy_version 24943 (0.0008) -[2023-10-09 09:16:28,517][23468] Updated weights for policy 0, policy_version 24953 (0.0008) -[2023-10-09 09:16:29,729][23469] Updated weights for policy 1, policy_version 25061 (0.0008) -[2023-10-09 09:16:30,095][23469] Updated weights for policy 1, policy_version 25071 (0.0010) -[2023-10-09 09:16:30,465][23469] Updated weights for policy 1, policy_version 25081 (0.0009) -[2023-10-09 09:16:31,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 51249152. Throughput: 0: 1791.3, 1: 1797.6. Samples: 12819788. Policy #0 lag: (min: 29.0, avg: 36.3, max: 61.0) -[2023-10-09 09:16:31,078][22500] Avg episode reward: [(0, '6.950'), (1, '6.010')] -[2023-10-09 09:16:32,229][23468] Updated weights for policy 0, policy_version 24963 (0.0007) -[2023-10-09 09:16:32,601][23468] Updated weights for policy 0, policy_version 24973 (0.0008) -[2023-10-09 09:16:32,978][23468] Updated weights for policy 0, policy_version 24983 (0.0008) -[2023-10-09 09:16:34,246][23469] Updated weights for policy 1, policy_version 25091 (0.0009) -[2023-10-09 09:16:34,652][23469] Updated weights for policy 1, policy_version 25101 (0.0007) -[2023-10-09 09:16:35,024][23469] Updated weights for policy 1, policy_version 25111 (0.0007) -[2023-10-09 09:16:36,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 51314688. Throughput: 0: 1795.8, 1: 1806.0. Samples: 12831132. Policy #0 lag: (min: 29.0, avg: 36.3, max: 61.0) -[2023-10-09 09:16:36,078][22500] Avg episode reward: [(0, '6.670'), (1, '6.650')] -[2023-10-09 09:16:36,611][23468] Updated weights for policy 0, policy_version 24993 (0.0009) -[2023-10-09 09:16:36,992][23468] Updated weights for policy 0, policy_version 25003 (0.0008) -[2023-10-09 09:16:37,357][23468] Updated weights for policy 0, policy_version 25013 (0.0008) -[2023-10-09 09:16:37,728][23468] Updated weights for policy 0, policy_version 25023 (0.0008) -[2023-10-09 09:16:38,584][23469] Updated weights for policy 1, policy_version 25121 (0.0007) -[2023-10-09 09:16:38,946][23469] Updated weights for policy 1, policy_version 25131 (0.0007) -[2023-10-09 09:16:39,320][23469] Updated weights for policy 1, policy_version 25141 (0.0008) -[2023-10-09 09:16:39,693][23469] Updated weights for policy 1, policy_version 25151 (0.0008) -[2023-10-09 09:16:41,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 51380224. Throughput: 0: 1799.8, 1: 1796.3. Samples: 12852160. Policy #0 lag: (min: 29.0, avg: 36.3, max: 61.0) -[2023-10-09 09:16:41,078][22500] Avg episode reward: [(0, '6.660'), (1, '6.390')] -[2023-10-09 09:16:41,517][23468] Updated weights for policy 0, policy_version 25033 (0.0010) -[2023-10-09 09:16:41,892][23468] Updated weights for policy 0, policy_version 25043 (0.0007) -[2023-10-09 09:16:42,258][23468] Updated weights for policy 0, policy_version 25053 (0.0007) -[2023-10-09 09:16:43,416][23469] Updated weights for policy 1, policy_version 25161 (0.0011) -[2023-10-09 09:16:43,793][23469] Updated weights for policy 1, policy_version 25171 (0.0010) -[2023-10-09 09:16:44,165][23469] Updated weights for policy 1, policy_version 25181 (0.0007) -[2023-10-09 09:16:46,075][23468] Updated weights for policy 0, policy_version 25063 (0.0007) -[2023-10-09 09:16:46,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 51445760. Throughput: 0: 1798.9, 1: 1792.7. Samples: 12874478. Policy #0 lag: (min: 1.0, avg: 14.8, max: 33.0) -[2023-10-09 09:16:46,078][22500] Avg episode reward: [(0, '6.770'), (1, '6.390')] -[2023-10-09 09:16:46,452][23468] Updated weights for policy 0, policy_version 25073 (0.0007) -[2023-10-09 09:16:46,828][23468] Updated weights for policy 0, policy_version 25083 (0.0007) -[2023-10-09 09:16:48,026][23469] Updated weights for policy 1, policy_version 25191 (0.0009) -[2023-10-09 09:16:48,388][23469] Updated weights for policy 1, policy_version 25201 (0.0009) -[2023-10-09 09:16:48,764][23469] Updated weights for policy 1, policy_version 25211 (0.0009) -[2023-10-09 09:16:50,673][23468] Updated weights for policy 0, policy_version 25093 (0.0010) -[2023-10-09 09:16:51,056][23468] Updated weights for policy 0, policy_version 25103 (0.0008) -[2023-10-09 09:16:51,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 51511296. Throughput: 0: 1793.9, 1: 1798.6. Samples: 12884286. Policy #0 lag: (min: 1.0, avg: 14.8, max: 33.0) -[2023-10-09 09:16:51,079][22500] Avg episode reward: [(0, '6.910'), (1, '5.910')] -[2023-10-09 09:16:51,438][23468] Updated weights for policy 0, policy_version 25113 (0.0007) -[2023-10-09 09:16:52,358][23469] Updated weights for policy 1, policy_version 25221 (0.0008) -[2023-10-09 09:16:52,726][23469] Updated weights for policy 1, policy_version 25231 (0.0009) -[2023-10-09 09:16:53,093][23469] Updated weights for policy 1, policy_version 25241 (0.0008) -[2023-10-09 09:16:55,267][23468] Updated weights for policy 0, policy_version 25123 (0.0008) -[2023-10-09 09:16:55,650][23468] Updated weights for policy 0, policy_version 25133 (0.0008) -[2023-10-09 09:16:56,015][23468] Updated weights for policy 0, policy_version 25143 (0.0009) -[2023-10-09 09:16:56,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 51576832. Throughput: 0: 1785.2, 1: 1798.3. Samples: 12906478. Policy #0 lag: (min: 1.0, avg: 14.8, max: 33.0) -[2023-10-09 09:16:56,079][22500] Avg episode reward: [(0, '7.570'), (1, '6.210')] -[2023-10-09 09:16:56,966][23469] Updated weights for policy 1, policy_version 25251 (0.0007) -[2023-10-09 09:16:57,342][23469] Updated weights for policy 1, policy_version 25261 (0.0007) -[2023-10-09 09:16:57,712][23469] Updated weights for policy 1, policy_version 25271 (0.0008) -[2023-10-09 09:16:59,637][23468] Updated weights for policy 0, policy_version 25153 (0.0007) -[2023-10-09 09:17:00,012][23468] Updated weights for policy 0, policy_version 25163 (0.0009) -[2023-10-09 09:17:00,384][23468] Updated weights for policy 0, policy_version 25173 (0.0009) -[2023-10-09 09:17:00,772][23468] Updated weights for policy 0, policy_version 25183 (0.0011) -[2023-10-09 09:17:01,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 51675136. Throughput: 0: 1801.5, 1: 1794.5. Samples: 12928250. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-10-09 09:17:01,078][22500] Avg episode reward: [(0, '7.490'), (1, '6.520')] -[2023-10-09 09:17:01,395][23469] Updated weights for policy 1, policy_version 25281 (0.0008) -[2023-10-09 09:17:01,764][23469] Updated weights for policy 1, policy_version 25291 (0.0009) -[2023-10-09 09:17:02,125][23469] Updated weights for policy 1, policy_version 25301 (0.0010) -[2023-10-09 09:17:02,490][23469] Updated weights for policy 1, policy_version 25311 (0.0007) -[2023-10-09 09:17:04,466][23468] Updated weights for policy 0, policy_version 25193 (0.0011) -[2023-10-09 09:17:04,837][23468] Updated weights for policy 0, policy_version 25203 (0.0008) -[2023-10-09 09:17:05,219][23468] Updated weights for policy 0, policy_version 25213 (0.0009) -[2023-10-09 09:17:06,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14440.2). Total num frames: 51740672. Throughput: 0: 1788.6, 1: 1799.3. Samples: 12938914. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-10-09 09:17:06,078][22500] Avg episode reward: [(0, '6.920'), (1, '6.730')] -[2023-10-09 09:17:06,476][23469] Updated weights for policy 1, policy_version 25321 (0.0008) -[2023-10-09 09:17:06,857][23469] Updated weights for policy 1, policy_version 25331 (0.0008) -[2023-10-09 09:17:07,224][23469] Updated weights for policy 1, policy_version 25341 (0.0008) -[2023-10-09 09:17:09,013][23468] Updated weights for policy 0, policy_version 25223 (0.0010) -[2023-10-09 09:17:09,390][23468] Updated weights for policy 0, policy_version 25233 (0.0010) -[2023-10-09 09:17:09,763][23468] Updated weights for policy 0, policy_version 25243 (0.0011) -[2023-10-09 09:17:10,829][23469] Updated weights for policy 1, policy_version 25351 (0.0007) -[2023-10-09 09:17:11,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 51806208. Throughput: 0: 1802.0, 1: 1792.5. Samples: 12960376. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-10-09 09:17:11,078][22500] Avg episode reward: [(0, '6.970'), (1, '6.360')] -[2023-10-09 09:17:11,199][23469] Updated weights for policy 1, policy_version 25361 (0.0007) -[2023-10-09 09:17:11,572][23469] Updated weights for policy 1, policy_version 25371 (0.0007) -[2023-10-09 09:17:13,556][23468] Updated weights for policy 0, policy_version 25253 (0.0008) -[2023-10-09 09:17:13,930][23468] Updated weights for policy 0, policy_version 25263 (0.0010) -[2023-10-09 09:17:14,304][23468] Updated weights for policy 0, policy_version 25273 (0.0010) -[2023-10-09 09:17:15,337][23469] Updated weights for policy 1, policy_version 25381 (0.0008) -[2023-10-09 09:17:15,708][23469] Updated weights for policy 1, policy_version 25391 (0.0008) -[2023-10-09 09:17:16,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 51871744. Throughput: 0: 1779.6, 1: 1810.7. Samples: 12981352. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-10-09 09:17:16,078][22500] Avg episode reward: [(0, '7.130'), (1, '6.420')] -[2023-10-09 09:17:16,089][23469] Updated weights for policy 1, policy_version 25401 (0.0007) -[2023-10-09 09:17:18,159][23468] Updated weights for policy 0, policy_version 25283 (0.0009) -[2023-10-09 09:17:18,540][23468] Updated weights for policy 0, policy_version 25293 (0.0007) -[2023-10-09 09:17:18,911][23468] Updated weights for policy 0, policy_version 25303 (0.0008) -[2023-10-09 09:17:19,644][23469] Updated weights for policy 1, policy_version 25411 (0.0007) -[2023-10-09 09:17:20,006][23469] Updated weights for policy 1, policy_version 25421 (0.0007) -[2023-10-09 09:17:20,382][23469] Updated weights for policy 1, policy_version 25431 (0.0007) -[2023-10-09 09:17:21,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 51970048. Throughput: 0: 1802.9, 1: 1796.7. Samples: 12993116. Policy #0 lag: (min: 3.0, avg: 11.0, max: 35.0) -[2023-10-09 09:17:21,078][22500] Avg episode reward: [(0, '6.700'), (1, '6.580')] -[2023-10-09 09:17:22,587][23468] Updated weights for policy 0, policy_version 25313 (0.0007) -[2023-10-09 09:17:22,961][23468] Updated weights for policy 0, policy_version 25323 (0.0007) -[2023-10-09 09:17:23,333][23468] Updated weights for policy 0, policy_version 25333 (0.0008) -[2023-10-09 09:17:23,716][23468] Updated weights for policy 0, policy_version 25343 (0.0008) -[2023-10-09 09:17:24,180][23469] Updated weights for policy 1, policy_version 25441 (0.0008) -[2023-10-09 09:17:24,545][23469] Updated weights for policy 1, policy_version 25451 (0.0007) -[2023-10-09 09:17:24,923][23469] Updated weights for policy 1, policy_version 25461 (0.0007) -[2023-10-09 09:17:25,296][23469] Updated weights for policy 1, policy_version 25471 (0.0008) -[2023-10-09 09:17:26,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 52035584. Throughput: 0: 1773.3, 1: 1817.7. Samples: 13013754. Policy #0 lag: (min: 3.0, avg: 11.0, max: 35.0) -[2023-10-09 09:17:26,078][22500] Avg episode reward: [(0, '6.730'), (1, '6.580')] -[2023-10-09 09:17:27,472][23468] Updated weights for policy 0, policy_version 25353 (0.0007) -[2023-10-09 09:17:27,844][23468] Updated weights for policy 0, policy_version 25363 (0.0008) -[2023-10-09 09:17:28,223][23468] Updated weights for policy 0, policy_version 25373 (0.0007) -[2023-10-09 09:17:28,879][23469] Updated weights for policy 1, policy_version 25481 (0.0008) -[2023-10-09 09:17:29,239][23469] Updated weights for policy 1, policy_version 25491 (0.0008) -[2023-10-09 09:17:29,603][23469] Updated weights for policy 1, policy_version 25501 (0.0008) -[2023-10-09 09:17:31,078][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 52101120. Throughput: 0: 1773.2, 1: 1809.1. Samples: 13035682. Policy #0 lag: (min: 3.0, avg: 11.0, max: 35.0) -[2023-10-09 09:17:31,079][22500] Avg episode reward: [(0, '6.750'), (1, '6.380')] -[2023-10-09 09:17:32,055][23468] Updated weights for policy 0, policy_version 25383 (0.0009) -[2023-10-09 09:17:32,424][23468] Updated weights for policy 0, policy_version 25393 (0.0008) -[2023-10-09 09:17:32,804][23468] Updated weights for policy 0, policy_version 25403 (0.0008) -[2023-10-09 09:17:33,393][23469] Updated weights for policy 1, policy_version 25511 (0.0008) -[2023-10-09 09:17:33,762][23469] Updated weights for policy 1, policy_version 25521 (0.0009) -[2023-10-09 09:17:34,129][23469] Updated weights for policy 1, policy_version 25531 (0.0008) -[2023-10-09 09:17:36,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 52166656. Throughput: 0: 1775.6, 1: 1821.3. Samples: 13046144. Policy #0 lag: (min: 3.0, avg: 11.0, max: 35.0) -[2023-10-09 09:17:36,078][22500] Avg episode reward: [(0, '7.230'), (1, '6.440')] -[2023-10-09 09:17:36,566][23468] Updated weights for policy 0, policy_version 25413 (0.0011) -[2023-10-09 09:17:36,948][23468] Updated weights for policy 0, policy_version 25423 (0.0008) -[2023-10-09 09:17:37,327][23468] Updated weights for policy 0, policy_version 25433 (0.0010) -[2023-10-09 09:17:37,888][23469] Updated weights for policy 1, policy_version 25541 (0.0008) -[2023-10-09 09:17:38,257][23469] Updated weights for policy 1, policy_version 25551 (0.0009) -[2023-10-09 09:17:38,629][23469] Updated weights for policy 1, policy_version 25561 (0.0007) -[2023-10-09 09:17:41,014][23468] Updated weights for policy 0, policy_version 25443 (0.0008) -[2023-10-09 09:17:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 52232192. Throughput: 0: 1777.1, 1: 1806.5. Samples: 13067742. Policy #0 lag: (min: 31.0, avg: 31.8, max: 51.0) -[2023-10-09 09:17:41,078][22500] Avg episode reward: [(0, '7.020'), (1, '6.380')] -[2023-10-09 09:17:41,384][23468] Updated weights for policy 0, policy_version 25453 (0.0007) -[2023-10-09 09:17:41,762][23468] Updated weights for policy 0, policy_version 25463 (0.0009) -[2023-10-09 09:17:42,437][23469] Updated weights for policy 1, policy_version 25571 (0.0008) -[2023-10-09 09:17:42,802][23469] Updated weights for policy 1, policy_version 25581 (0.0008) -[2023-10-09 09:17:43,170][23469] Updated weights for policy 1, policy_version 25591 (0.0008) -[2023-10-09 09:17:45,696][23468] Updated weights for policy 0, policy_version 25473 (0.0009) -[2023-10-09 09:17:46,063][23468] Updated weights for policy 0, policy_version 25483 (0.0007) -[2023-10-09 09:17:46,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 52297728. Throughput: 0: 1798.6, 1: 1796.2. Samples: 13090016. Policy #0 lag: (min: 31.0, avg: 31.8, max: 51.0) -[2023-10-09 09:17:46,078][22500] Avg episode reward: [(0, '7.240'), (1, '6.120')] -[2023-10-09 09:17:46,442][23468] Updated weights for policy 0, policy_version 25493 (0.0008) -[2023-10-09 09:17:46,819][23468] Updated weights for policy 0, policy_version 25503 (0.0007) -[2023-10-09 09:17:46,938][23469] Updated weights for policy 1, policy_version 25601 (0.0007) -[2023-10-09 09:17:47,314][23469] Updated weights for policy 1, policy_version 25611 (0.0009) -[2023-10-09 09:17:47,691][23469] Updated weights for policy 1, policy_version 25621 (0.0007) -[2023-10-09 09:17:48,059][23469] Updated weights for policy 1, policy_version 25631 (0.0008) -[2023-10-09 09:17:50,657][23468] Updated weights for policy 0, policy_version 25513 (0.0010) -[2023-10-09 09:17:51,030][23468] Updated weights for policy 0, policy_version 25523 (0.0009) -[2023-10-09 09:17:51,078][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 52363264. Throughput: 0: 1776.3, 1: 1795.6. Samples: 13099652. Policy #0 lag: (min: 31.0, avg: 31.8, max: 51.0) -[2023-10-09 09:17:51,079][22500] Avg episode reward: [(0, '7.360'), (1, '6.080')] -[2023-10-09 09:17:51,398][23468] Updated weights for policy 0, policy_version 25533 (0.0009) -[2023-10-09 09:17:51,934][23469] Updated weights for policy 1, policy_version 25641 (0.0010) -[2023-10-09 09:17:52,310][23469] Updated weights for policy 1, policy_version 25651 (0.0007) -[2023-10-09 09:17:52,679][23469] Updated weights for policy 1, policy_version 25661 (0.0008) -[2023-10-09 09:17:54,980][23468] Updated weights for policy 0, policy_version 25543 (0.0010) -[2023-10-09 09:17:55,364][23468] Updated weights for policy 0, policy_version 25553 (0.0010) -[2023-10-09 09:17:55,737][23468] Updated weights for policy 0, policy_version 25563 (0.0010) -[2023-10-09 09:17:56,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 52461568. Throughput: 0: 1794.1, 1: 1795.6. Samples: 13121910. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 09:17:56,079][22500] Avg episode reward: [(0, '7.560'), (1, '6.000')] -[2023-10-09 09:17:56,504][23469] Updated weights for policy 1, policy_version 25671 (0.0010) -[2023-10-09 09:17:56,879][23469] Updated weights for policy 1, policy_version 25681 (0.0011) -[2023-10-09 09:17:57,241][23469] Updated weights for policy 1, policy_version 25691 (0.0008) -[2023-10-09 09:17:59,632][23468] Updated weights for policy 0, policy_version 25573 (0.0008) -[2023-10-09 09:18:00,012][23468] Updated weights for policy 0, policy_version 25583 (0.0009) -[2023-10-09 09:18:00,385][23468] Updated weights for policy 0, policy_version 25593 (0.0008) -[2023-10-09 09:18:00,986][23469] Updated weights for policy 1, policy_version 25701 (0.0009) -[2023-10-09 09:18:01,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 52527104. Throughput: 0: 1790.9, 1: 1808.5. Samples: 13143326. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 09:18:01,078][22500] Avg episode reward: [(0, '7.280'), (1, '6.230')] -[2023-10-09 09:18:01,349][23469] Updated weights for policy 1, policy_version 25711 (0.0007) -[2023-10-09 09:18:01,717][23469] Updated weights for policy 1, policy_version 25721 (0.0009) -[2023-10-09 09:18:04,125][23468] Updated weights for policy 0, policy_version 25603 (0.0009) -[2023-10-09 09:18:04,503][23468] Updated weights for policy 0, policy_version 25613 (0.0007) -[2023-10-09 09:18:04,870][23468] Updated weights for policy 0, policy_version 25623 (0.0007) -[2023-10-09 09:18:05,677][23469] Updated weights for policy 1, policy_version 25731 (0.0009) -[2023-10-09 09:18:06,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 52592640. Throughput: 0: 1788.1, 1: 1785.0. Samples: 13153906. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 09:18:06,078][22500] Avg episode reward: [(0, '6.900'), (1, '6.310')] -[2023-10-09 09:18:06,082][23469] Updated weights for policy 1, policy_version 25741 (0.0008) -[2023-10-09 09:18:06,453][23469] Updated weights for policy 1, policy_version 25751 (0.0008) -[2023-10-09 09:18:08,445][23468] Updated weights for policy 0, policy_version 25633 (0.0007) -[2023-10-09 09:18:08,818][23468] Updated weights for policy 0, policy_version 25643 (0.0009) -[2023-10-09 09:18:09,178][23468] Updated weights for policy 0, policy_version 25653 (0.0008) -[2023-10-09 09:18:09,550][23468] Updated weights for policy 0, policy_version 25663 (0.0009) -[2023-10-09 09:18:10,065][23469] Updated weights for policy 1, policy_version 25761 (0.0009) -[2023-10-09 09:18:10,434][23469] Updated weights for policy 1, policy_version 25771 (0.0008) -[2023-10-09 09:18:10,802][23469] Updated weights for policy 1, policy_version 25781 (0.0009) -[2023-10-09 09:18:11,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 52658176. Throughput: 0: 1794.5, 1: 1795.1. Samples: 13175284. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 09:18:11,078][22500] Avg episode reward: [(0, '6.490'), (1, '6.310')] -[2023-10-09 09:18:11,174][23469] Updated weights for policy 1, policy_version 25791 (0.0008) -[2023-10-09 09:18:13,254][23468] Updated weights for policy 0, policy_version 25673 (0.0007) -[2023-10-09 09:18:13,642][23468] Updated weights for policy 0, policy_version 25683 (0.0010) -[2023-10-09 09:18:14,014][23468] Updated weights for policy 0, policy_version 25693 (0.0008) -[2023-10-09 09:18:14,886][23469] Updated weights for policy 1, policy_version 25801 (0.0009) -[2023-10-09 09:18:15,255][23469] Updated weights for policy 1, policy_version 25811 (0.0009) -[2023-10-09 09:18:15,622][23469] Updated weights for policy 1, policy_version 25821 (0.0009) -[2023-10-09 09:18:16,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 52756480. Throughput: 0: 1788.1, 1: 1774.8. Samples: 13196014. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:18:16,078][22500] Avg episode reward: [(0, '7.000'), (1, '6.540')] -[2023-10-09 09:18:16,087][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000025696_26312704.pth... -[2023-10-09 09:18:16,087][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000025824_26443776.pth... -[2023-10-09 09:18:16,128][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000024032_24608768.pth -[2023-10-09 09:18:16,128][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000024128_24707072.pth -[2023-10-09 09:18:17,748][23468] Updated weights for policy 0, policy_version 25703 (0.0007) -[2023-10-09 09:18:18,125][23468] Updated weights for policy 0, policy_version 25713 (0.0009) -[2023-10-09 09:18:18,486][23468] Updated weights for policy 0, policy_version 25723 (0.0009) -[2023-10-09 09:18:19,196][23469] Updated weights for policy 1, policy_version 25831 (0.0007) -[2023-10-09 09:18:19,561][23469] Updated weights for policy 1, policy_version 25841 (0.0007) -[2023-10-09 09:18:19,935][23469] Updated weights for policy 1, policy_version 25851 (0.0007) -[2023-10-09 09:18:21,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 52822016. Throughput: 0: 1799.1, 1: 1794.9. Samples: 13207876. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:18:21,078][22500] Avg episode reward: [(0, '7.000'), (1, '6.720')] -[2023-10-09 09:18:22,232][23468] Updated weights for policy 0, policy_version 25733 (0.0009) -[2023-10-09 09:18:22,601][23468] Updated weights for policy 0, policy_version 25743 (0.0008) -[2023-10-09 09:18:22,983][23468] Updated weights for policy 0, policy_version 25753 (0.0008) -[2023-10-09 09:18:23,518][23469] Updated weights for policy 1, policy_version 25861 (0.0010) -[2023-10-09 09:18:23,886][23469] Updated weights for policy 1, policy_version 25871 (0.0010) -[2023-10-09 09:18:24,258][23469] Updated weights for policy 1, policy_version 25881 (0.0008) -[2023-10-09 09:18:26,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 52887552. Throughput: 0: 1786.0, 1: 1784.7. Samples: 13228420. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:18:26,078][22500] Avg episode reward: [(0, '7.150'), (1, '6.840')] -[2023-10-09 09:18:26,822][23468] Updated weights for policy 0, policy_version 25763 (0.0010) -[2023-10-09 09:18:27,187][23468] Updated weights for policy 0, policy_version 25773 (0.0008) -[2023-10-09 09:18:27,567][23468] Updated weights for policy 0, policy_version 25783 (0.0007) -[2023-10-09 09:18:28,014][23469] Updated weights for policy 1, policy_version 25891 (0.0010) -[2023-10-09 09:18:28,387][23469] Updated weights for policy 1, policy_version 25901 (0.0008) -[2023-10-09 09:18:28,762][23469] Updated weights for policy 1, policy_version 25911 (0.0011) -[2023-10-09 09:18:31,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 52953088. Throughput: 0: 1780.2, 1: 1792.6. Samples: 13250792. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:18:31,078][22500] Avg episode reward: [(0, '6.310'), (1, '6.650')] -[2023-10-09 09:18:31,429][23468] Updated weights for policy 0, policy_version 25793 (0.0007) -[2023-10-09 09:18:31,809][23468] Updated weights for policy 0, policy_version 25803 (0.0008) -[2023-10-09 09:18:32,179][23468] Updated weights for policy 0, policy_version 25813 (0.0009) -[2023-10-09 09:18:32,523][23469] Updated weights for policy 1, policy_version 25921 (0.0008) -[2023-10-09 09:18:32,550][23468] Updated weights for policy 0, policy_version 25823 (0.0008) -[2023-10-09 09:18:32,889][23469] Updated weights for policy 1, policy_version 25931 (0.0010) -[2023-10-09 09:18:33,268][23469] Updated weights for policy 1, policy_version 25941 (0.0010) -[2023-10-09 09:18:33,638][23469] Updated weights for policy 1, policy_version 25951 (0.0012) -[2023-10-09 09:18:36,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 53018624. Throughput: 0: 1784.6, 1: 1790.5. Samples: 13260532. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:18:36,078][22500] Avg episode reward: [(0, '6.430'), (1, '6.900')] -[2023-10-09 09:18:36,194][23468] Updated weights for policy 0, policy_version 25833 (0.0007) -[2023-10-09 09:18:36,564][23468] Updated weights for policy 0, policy_version 25843 (0.0007) -[2023-10-09 09:18:36,937][23468] Updated weights for policy 0, policy_version 25853 (0.0007) -[2023-10-09 09:18:37,271][23469] Updated weights for policy 1, policy_version 25961 (0.0009) -[2023-10-09 09:18:37,638][23469] Updated weights for policy 1, policy_version 25971 (0.0007) -[2023-10-09 09:18:38,010][23469] Updated weights for policy 1, policy_version 25981 (0.0007) -[2023-10-09 09:18:40,773][23468] Updated weights for policy 0, policy_version 25863 (0.0009) -[2023-10-09 09:18:41,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 53084160. Throughput: 0: 1784.4, 1: 1797.0. Samples: 13283070. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:18:41,078][22500] Avg episode reward: [(0, '6.940'), (1, '6.570')] -[2023-10-09 09:18:41,143][23468] Updated weights for policy 0, policy_version 25873 (0.0008) -[2023-10-09 09:18:41,518][23468] Updated weights for policy 0, policy_version 25883 (0.0007) -[2023-10-09 09:18:41,740][23469] Updated weights for policy 1, policy_version 25991 (0.0008) -[2023-10-09 09:18:42,110][23469] Updated weights for policy 1, policy_version 26001 (0.0010) -[2023-10-09 09:18:42,474][23469] Updated weights for policy 1, policy_version 26011 (0.0010) -[2023-10-09 09:18:45,244][23468] Updated weights for policy 0, policy_version 25893 (0.0008) -[2023-10-09 09:18:45,610][23468] Updated weights for policy 0, policy_version 25903 (0.0009) -[2023-10-09 09:18:45,983][23468] Updated weights for policy 0, policy_version 25913 (0.0007) -[2023-10-09 09:18:46,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 53149696. Throughput: 0: 1800.8, 1: 1796.3. Samples: 13305194. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:18:46,078][22500] Avg episode reward: [(0, '7.330'), (1, '6.680')] -[2023-10-09 09:18:46,207][23469] Updated weights for policy 1, policy_version 26021 (0.0009) -[2023-10-09 09:18:46,583][23469] Updated weights for policy 1, policy_version 26031 (0.0010) -[2023-10-09 09:18:46,944][23469] Updated weights for policy 1, policy_version 26041 (0.0008) -[2023-10-09 09:18:49,683][23468] Updated weights for policy 0, policy_version 25923 (0.0007) -[2023-10-09 09:18:50,051][23468] Updated weights for policy 0, policy_version 25933 (0.0007) -[2023-10-09 09:18:50,424][23468] Updated weights for policy 0, policy_version 25943 (0.0008) -[2023-10-09 09:18:50,968][23469] Updated weights for policy 1, policy_version 26051 (0.0009) -[2023-10-09 09:18:51,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 53248000. Throughput: 0: 1787.0, 1: 1795.4. Samples: 13315114. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:18:51,078][22500] Avg episode reward: [(0, '7.400'), (1, '6.650')] -[2023-10-09 09:18:51,368][23469] Updated weights for policy 1, policy_version 26061 (0.0008) -[2023-10-09 09:18:51,740][23469] Updated weights for policy 1, policy_version 26071 (0.0009) -[2023-10-09 09:18:54,374][23468] Updated weights for policy 0, policy_version 25953 (0.0008) -[2023-10-09 09:18:54,750][23468] Updated weights for policy 0, policy_version 25963 (0.0009) -[2023-10-09 09:18:55,125][23468] Updated weights for policy 0, policy_version 25973 (0.0009) -[2023-10-09 09:18:55,295][23469] Updated weights for policy 1, policy_version 26081 (0.0008) -[2023-10-09 09:18:55,494][23468] Updated weights for policy 0, policy_version 25983 (0.0008) -[2023-10-09 09:18:55,668][23469] Updated weights for policy 1, policy_version 26091 (0.0009) -[2023-10-09 09:18:56,031][23469] Updated weights for policy 1, policy_version 26101 (0.0008) -[2023-10-09 09:18:56,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 53313536. Throughput: 0: 1802.8, 1: 1797.6. Samples: 13337304. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:18:56,078][22500] Avg episode reward: [(0, '7.420'), (1, '6.630')] -[2023-10-09 09:18:56,406][23469] Updated weights for policy 1, policy_version 26111 (0.0009) -[2023-10-09 09:18:59,313][23468] Updated weights for policy 0, policy_version 25993 (0.0009) -[2023-10-09 09:18:59,687][23468] Updated weights for policy 0, policy_version 26003 (0.0008) -[2023-10-09 09:19:00,067][23468] Updated weights for policy 0, policy_version 26013 (0.0010) -[2023-10-09 09:19:00,180][23469] Updated weights for policy 1, policy_version 26121 (0.0008) -[2023-10-09 09:19:00,555][23469] Updated weights for policy 1, policy_version 26131 (0.0009) -[2023-10-09 09:19:00,923][23469] Updated weights for policy 1, policy_version 26141 (0.0009) -[2023-10-09 09:19:01,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 53411840. Throughput: 0: 1771.2, 1: 1808.3. Samples: 13357092. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:19:01,078][22500] Avg episode reward: [(0, '7.320'), (1, '6.480')] -[2023-10-09 09:19:03,822][23468] Updated weights for policy 0, policy_version 26023 (0.0008) -[2023-10-09 09:19:04,196][23468] Updated weights for policy 0, policy_version 26033 (0.0008) -[2023-10-09 09:19:04,576][23469] Updated weights for policy 1, policy_version 26151 (0.0008) -[2023-10-09 09:19:04,580][23468] Updated weights for policy 0, policy_version 26043 (0.0009) -[2023-10-09 09:19:04,948][23469] Updated weights for policy 1, policy_version 26161 (0.0009) -[2023-10-09 09:19:05,313][23469] Updated weights for policy 1, policy_version 26171 (0.0009) -[2023-10-09 09:19:06,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 53477376. Throughput: 0: 1793.7, 1: 1798.0. Samples: 13369504. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:19:06,078][22500] Avg episode reward: [(0, '7.250'), (1, '6.280')] -[2023-10-09 09:19:08,201][23468] Updated weights for policy 0, policy_version 26053 (0.0008) -[2023-10-09 09:19:08,578][23468] Updated weights for policy 0, policy_version 26063 (0.0007) -[2023-10-09 09:19:08,942][23468] Updated weights for policy 0, policy_version 26073 (0.0007) -[2023-10-09 09:19:09,194][23469] Updated weights for policy 1, policy_version 26181 (0.0008) -[2023-10-09 09:19:09,573][23469] Updated weights for policy 1, policy_version 26191 (0.0009) -[2023-10-09 09:19:09,945][23469] Updated weights for policy 1, policy_version 26201 (0.0011) -[2023-10-09 09:19:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14440.2). Total num frames: 53542912. Throughput: 0: 1776.4, 1: 1801.8. Samples: 13389438. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:19:11,078][22500] Avg episode reward: [(0, '7.210'), (1, '6.500')] -[2023-10-09 09:19:12,867][23468] Updated weights for policy 0, policy_version 26083 (0.0008) -[2023-10-09 09:19:13,265][23468] Updated weights for policy 0, policy_version 26093 (0.0007) -[2023-10-09 09:19:13,640][23468] Updated weights for policy 0, policy_version 26103 (0.0007) -[2023-10-09 09:19:13,719][23469] Updated weights for policy 1, policy_version 26211 (0.0008) -[2023-10-09 09:19:14,093][23469] Updated weights for policy 1, policy_version 26221 (0.0009) -[2023-10-09 09:19:14,451][23469] Updated weights for policy 1, policy_version 26231 (0.0007) -[2023-10-09 09:19:16,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 53608448. Throughput: 0: 1771.2, 1: 1787.9. Samples: 13410952. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:19:16,079][22500] Avg episode reward: [(0, '7.890'), (1, '6.700')] -[2023-10-09 09:19:16,092][23265] Saving new best policy, reward=7.890! -[2023-10-09 09:19:17,381][23468] Updated weights for policy 0, policy_version 26113 (0.0009) -[2023-10-09 09:19:17,754][23468] Updated weights for policy 0, policy_version 26123 (0.0009) -[2023-10-09 09:19:18,131][23468] Updated weights for policy 0, policy_version 26133 (0.0009) -[2023-10-09 09:19:18,189][23469] Updated weights for policy 1, policy_version 26241 (0.0007) -[2023-10-09 09:19:18,511][23468] Updated weights for policy 0, policy_version 26143 (0.0009) -[2023-10-09 09:19:18,561][23469] Updated weights for policy 1, policy_version 26251 (0.0007) -[2023-10-09 09:19:18,930][23469] Updated weights for policy 1, policy_version 26261 (0.0007) -[2023-10-09 09:19:19,303][23469] Updated weights for policy 1, policy_version 26271 (0.0007) -[2023-10-09 09:19:21,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 53673984. Throughput: 0: 1774.2, 1: 1805.6. Samples: 13421622. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:19:21,078][22500] Avg episode reward: [(0, '7.580'), (1, '6.650')] -[2023-10-09 09:19:22,253][23468] Updated weights for policy 0, policy_version 26153 (0.0008) -[2023-10-09 09:19:22,630][23468] Updated weights for policy 0, policy_version 26163 (0.0007) -[2023-10-09 09:19:22,997][23468] Updated weights for policy 0, policy_version 26173 (0.0007) -[2023-10-09 09:19:23,096][23469] Updated weights for policy 1, policy_version 26281 (0.0007) -[2023-10-09 09:19:23,466][23469] Updated weights for policy 1, policy_version 26291 (0.0009) -[2023-10-09 09:19:23,833][23469] Updated weights for policy 1, policy_version 26301 (0.0007) -[2023-10-09 09:19:26,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 53739520. Throughput: 0: 1771.7, 1: 1782.8. Samples: 13443022. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:19:26,078][22500] Avg episode reward: [(0, '7.470'), (1, '6.380')] -[2023-10-09 09:19:26,717][23468] Updated weights for policy 0, policy_version 26183 (0.0008) -[2023-10-09 09:19:27,087][23468] Updated weights for policy 0, policy_version 26193 (0.0011) -[2023-10-09 09:19:27,459][23468] Updated weights for policy 0, policy_version 26203 (0.0008) -[2023-10-09 09:19:27,587][23469] Updated weights for policy 1, policy_version 26311 (0.0007) -[2023-10-09 09:19:27,958][23469] Updated weights for policy 1, policy_version 26321 (0.0008) -[2023-10-09 09:19:28,327][23469] Updated weights for policy 1, policy_version 26331 (0.0008) -[2023-10-09 09:19:31,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 53805056. Throughput: 0: 1777.4, 1: 1784.5. Samples: 13465480. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:19:31,078][22500] Avg episode reward: [(0, '7.090'), (1, '6.330')] -[2023-10-09 09:19:31,309][23468] Updated weights for policy 0, policy_version 26213 (0.0007) -[2023-10-09 09:19:31,690][23468] Updated weights for policy 0, policy_version 26223 (0.0007) -[2023-10-09 09:19:32,034][23469] Updated weights for policy 1, policy_version 26341 (0.0007) -[2023-10-09 09:19:32,061][23468] Updated weights for policy 0, policy_version 26233 (0.0007) -[2023-10-09 09:19:32,404][23469] Updated weights for policy 1, policy_version 26351 (0.0007) -[2023-10-09 09:19:32,774][23469] Updated weights for policy 1, policy_version 26361 (0.0007) -[2023-10-09 09:19:35,734][23468] Updated weights for policy 0, policy_version 26243 (0.0007) -[2023-10-09 09:19:36,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 53870592. Throughput: 0: 1771.2, 1: 1785.8. Samples: 13475182. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:19:36,079][22500] Avg episode reward: [(0, '7.520'), (1, '7.100')] -[2023-10-09 09:19:36,112][23468] Updated weights for policy 0, policy_version 26253 (0.0007) -[2023-10-09 09:19:36,489][23468] Updated weights for policy 0, policy_version 26263 (0.0007) -[2023-10-09 09:19:36,627][23469] Updated weights for policy 1, policy_version 26371 (0.0007) -[2023-10-09 09:19:37,036][23469] Updated weights for policy 1, policy_version 26381 (0.0008) -[2023-10-09 09:19:37,414][23469] Updated weights for policy 1, policy_version 26391 (0.0007) -[2023-10-09 09:19:40,116][23468] Updated weights for policy 0, policy_version 26273 (0.0007) -[2023-10-09 09:19:40,480][23468] Updated weights for policy 0, policy_version 26283 (0.0007) -[2023-10-09 09:19:40,856][23468] Updated weights for policy 0, policy_version 26293 (0.0008) -[2023-10-09 09:19:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 53936128. Throughput: 0: 1777.6, 1: 1784.5. Samples: 13497598. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-09 09:19:41,078][22500] Avg episode reward: [(0, '7.470'), (1, '6.830')] -[2023-10-09 09:19:41,121][23469] Updated weights for policy 1, policy_version 26401 (0.0007) -[2023-10-09 09:19:41,222][23468] Updated weights for policy 0, policy_version 26303 (0.0010) -[2023-10-09 09:19:41,496][23469] Updated weights for policy 1, policy_version 26411 (0.0008) -[2023-10-09 09:19:41,861][23469] Updated weights for policy 1, policy_version 26421 (0.0007) -[2023-10-09 09:19:42,231][23469] Updated weights for policy 1, policy_version 26431 (0.0007) -[2023-10-09 09:19:45,045][23468] Updated weights for policy 0, policy_version 26313 (0.0008) -[2023-10-09 09:19:45,413][23468] Updated weights for policy 0, policy_version 26323 (0.0008) -[2023-10-09 09:19:45,790][23468] Updated weights for policy 0, policy_version 26333 (0.0009) -[2023-10-09 09:19:45,995][23469] Updated weights for policy 1, policy_version 26441 (0.0009) -[2023-10-09 09:19:46,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 54034432. Throughput: 0: 1796.7, 1: 1803.7. Samples: 13519112. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-09 09:19:46,078][22500] Avg episode reward: [(0, '6.730'), (1, '6.860')] -[2023-10-09 09:19:46,365][23469] Updated weights for policy 1, policy_version 26451 (0.0010) -[2023-10-09 09:19:46,731][23469] Updated weights for policy 1, policy_version 26461 (0.0010) -[2023-10-09 09:19:49,539][23468] Updated weights for policy 0, policy_version 26343 (0.0007) -[2023-10-09 09:19:49,922][23468] Updated weights for policy 0, policy_version 26353 (0.0007) -[2023-10-09 09:19:50,280][23468] Updated weights for policy 0, policy_version 26363 (0.0008) -[2023-10-09 09:19:50,382][23469] Updated weights for policy 1, policy_version 26471 (0.0009) -[2023-10-09 09:19:50,758][23469] Updated weights for policy 1, policy_version 26481 (0.0008) -[2023-10-09 09:19:51,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 54099968. Throughput: 0: 1779.6, 1: 1780.0. Samples: 13529686. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-09 09:19:51,078][22500] Avg episode reward: [(0, '7.100'), (1, '6.450')] -[2023-10-09 09:19:51,131][23469] Updated weights for policy 1, policy_version 26491 (0.0008) -[2023-10-09 09:19:54,119][23468] Updated weights for policy 0, policy_version 26373 (0.0008) -[2023-10-09 09:19:54,496][23468] Updated weights for policy 0, policy_version 26383 (0.0008) -[2023-10-09 09:19:54,870][23468] Updated weights for policy 0, policy_version 26393 (0.0007) -[2023-10-09 09:19:54,991][23469] Updated weights for policy 1, policy_version 26501 (0.0010) -[2023-10-09 09:19:55,363][23469] Updated weights for policy 1, policy_version 26511 (0.0009) -[2023-10-09 09:19:55,741][23469] Updated weights for policy 1, policy_version 26521 (0.0009) -[2023-10-09 09:19:56,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 54198272. Throughput: 0: 1798.5, 1: 1802.4. Samples: 13551480. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-09 09:19:56,078][22500] Avg episode reward: [(0, '6.910'), (1, '6.800')] -[2023-10-09 09:19:58,775][23468] Updated weights for policy 0, policy_version 26403 (0.0008) -[2023-10-09 09:19:59,163][23468] Updated weights for policy 0, policy_version 26413 (0.0011) -[2023-10-09 09:19:59,532][23469] Updated weights for policy 1, policy_version 26531 (0.0009) -[2023-10-09 09:19:59,538][23468] Updated weights for policy 0, policy_version 26423 (0.0008) -[2023-10-09 09:19:59,905][23469] Updated weights for policy 1, policy_version 26541 (0.0008) -[2023-10-09 09:20:00,275][23469] Updated weights for policy 1, policy_version 26551 (0.0008) -[2023-10-09 09:20:01,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 54263808. Throughput: 0: 1772.4, 1: 1781.4. Samples: 13570872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:20:01,079][22500] Avg episode reward: [(0, '7.310'), (1, '6.900')] -[2023-10-09 09:20:03,290][23468] Updated weights for policy 0, policy_version 26433 (0.0008) -[2023-10-09 09:20:03,664][23468] Updated weights for policy 0, policy_version 26443 (0.0008) -[2023-10-09 09:20:04,037][23468] Updated weights for policy 0, policy_version 26453 (0.0007) -[2023-10-09 09:20:04,092][23469] Updated weights for policy 1, policy_version 26561 (0.0008) -[2023-10-09 09:20:04,420][23468] Updated weights for policy 0, policy_version 26463 (0.0008) -[2023-10-09 09:20:04,460][23469] Updated weights for policy 1, policy_version 26571 (0.0008) -[2023-10-09 09:20:04,843][23469] Updated weights for policy 1, policy_version 26581 (0.0008) -[2023-10-09 09:20:05,205][23469] Updated weights for policy 1, policy_version 26591 (0.0009) -[2023-10-09 09:20:06,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 54329344. Throughput: 0: 1802.6, 1: 1794.8. Samples: 13583504. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:20:06,078][22500] Avg episode reward: [(0, '7.060'), (1, '6.370')] -[2023-10-09 09:20:08,242][23468] Updated weights for policy 0, policy_version 26473 (0.0007) -[2023-10-09 09:20:08,619][23468] Updated weights for policy 0, policy_version 26483 (0.0007) -[2023-10-09 09:20:08,977][23469] Updated weights for policy 1, policy_version 26601 (0.0008) -[2023-10-09 09:20:09,000][23468] Updated weights for policy 0, policy_version 26493 (0.0008) -[2023-10-09 09:20:09,345][23469] Updated weights for policy 1, policy_version 26611 (0.0010) -[2023-10-09 09:20:09,720][23469] Updated weights for policy 1, policy_version 26621 (0.0007) -[2023-10-09 09:20:11,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 54394880. Throughput: 0: 1774.8, 1: 1788.3. Samples: 13603362. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:20:11,078][22500] Avg episode reward: [(0, '6.350'), (1, '6.380')] -[2023-10-09 09:20:12,655][23468] Updated weights for policy 0, policy_version 26503 (0.0009) -[2023-10-09 09:20:13,033][23468] Updated weights for policy 0, policy_version 26513 (0.0010) -[2023-10-09 09:20:13,406][23468] Updated weights for policy 0, policy_version 26523 (0.0009) -[2023-10-09 09:20:13,468][23469] Updated weights for policy 1, policy_version 26631 (0.0008) -[2023-10-09 09:20:13,841][23469] Updated weights for policy 1, policy_version 26641 (0.0010) -[2023-10-09 09:20:14,213][23469] Updated weights for policy 1, policy_version 26651 (0.0008) -[2023-10-09 09:20:16,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 54460416. Throughput: 0: 1775.1, 1: 1784.9. Samples: 13625684. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:20:16,079][22500] Avg episode reward: [(0, '6.660'), (1, '6.690')] -[2023-10-09 09:20:16,089][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000026528_27164672.pth... -[2023-10-09 09:20:16,089][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000026656_27295744.pth... -[2023-10-09 09:20:16,118][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000024864_25460736.pth -[2023-10-09 09:20:16,130][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000024992_25591808.pth -[2023-10-09 09:20:17,197][23468] Updated weights for policy 0, policy_version 26533 (0.0010) -[2023-10-09 09:20:17,568][23468] Updated weights for policy 0, policy_version 26543 (0.0010) -[2023-10-09 09:20:17,904][23469] Updated weights for policy 1, policy_version 26661 (0.0009) -[2023-10-09 09:20:17,935][23468] Updated weights for policy 0, policy_version 26553 (0.0009) -[2023-10-09 09:20:18,275][23469] Updated weights for policy 1, policy_version 26671 (0.0008) -[2023-10-09 09:20:18,636][23469] Updated weights for policy 1, policy_version 26681 (0.0009) -[2023-10-09 09:20:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 54525952. Throughput: 0: 1772.1, 1: 1794.8. Samples: 13635690. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:20:21,078][22500] Avg episode reward: [(0, '6.740'), (1, '6.610')] -[2023-10-09 09:20:21,827][23468] Updated weights for policy 0, policy_version 26563 (0.0008) -[2023-10-09 09:20:22,194][23468] Updated weights for policy 0, policy_version 26573 (0.0007) -[2023-10-09 09:20:22,458][23469] Updated weights for policy 1, policy_version 26691 (0.0009) -[2023-10-09 09:20:22,576][23468] Updated weights for policy 0, policy_version 26583 (0.0007) -[2023-10-09 09:20:22,827][23469] Updated weights for policy 1, policy_version 26701 (0.0007) -[2023-10-09 09:20:23,195][23469] Updated weights for policy 1, policy_version 26711 (0.0007) -[2023-10-09 09:20:26,077][22500] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 54591488. Throughput: 0: 1768.4, 1: 1790.3. Samples: 13657738. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 09:20:26,078][22500] Avg episode reward: [(0, '6.500'), (1, '6.670')] -[2023-10-09 09:20:26,465][23468] Updated weights for policy 0, policy_version 26593 (0.0008) -[2023-10-09 09:20:26,838][23468] Updated weights for policy 0, policy_version 26603 (0.0010) -[2023-10-09 09:20:26,894][23469] Updated weights for policy 1, policy_version 26721 (0.0007) -[2023-10-09 09:20:27,206][23468] Updated weights for policy 0, policy_version 26613 (0.0008) -[2023-10-09 09:20:27,308][23469] Updated weights for policy 1, policy_version 26731 (0.0009) -[2023-10-09 09:20:27,579][23468] Updated weights for policy 0, policy_version 26623 (0.0007) -[2023-10-09 09:20:27,680][23469] Updated weights for policy 1, policy_version 26741 (0.0007) -[2023-10-09 09:20:28,045][23469] Updated weights for policy 1, policy_version 26751 (0.0008) -[2023-10-09 09:20:31,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 54657024. Throughput: 0: 1786.5, 1: 1785.6. Samples: 13679856. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 09:20:31,078][22500] Avg episode reward: [(0, '6.420'), (1, '6.560')] -[2023-10-09 09:20:31,290][23468] Updated weights for policy 0, policy_version 26633 (0.0011) -[2023-10-09 09:20:31,665][23468] Updated weights for policy 0, policy_version 26643 (0.0010) -[2023-10-09 09:20:31,874][23469] Updated weights for policy 1, policy_version 26761 (0.0008) -[2023-10-09 09:20:32,052][23468] Updated weights for policy 0, policy_version 26653 (0.0007) -[2023-10-09 09:20:32,237][23469] Updated weights for policy 1, policy_version 26771 (0.0009) -[2023-10-09 09:20:32,616][23469] Updated weights for policy 1, policy_version 26781 (0.0008) -[2023-10-09 09:20:35,832][23468] Updated weights for policy 0, policy_version 26663 (0.0007) -[2023-10-09 09:20:36,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 54722560. Throughput: 0: 1769.2, 1: 1780.0. Samples: 13689404. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 09:20:36,078][22500] Avg episode reward: [(0, '6.530'), (1, '6.540')] -[2023-10-09 09:20:36,204][23468] Updated weights for policy 0, policy_version 26673 (0.0008) -[2023-10-09 09:20:36,354][23469] Updated weights for policy 1, policy_version 26791 (0.0008) -[2023-10-09 09:20:36,585][23468] Updated weights for policy 0, policy_version 26683 (0.0008) -[2023-10-09 09:20:36,716][23469] Updated weights for policy 1, policy_version 26801 (0.0007) -[2023-10-09 09:20:37,097][23469] Updated weights for policy 1, policy_version 26811 (0.0009) -[2023-10-09 09:20:40,299][23468] Updated weights for policy 0, policy_version 26693 (0.0008) -[2023-10-09 09:20:40,675][23468] Updated weights for policy 0, policy_version 26703 (0.0008) -[2023-10-09 09:20:40,879][23469] Updated weights for policy 1, policy_version 26821 (0.0008) -[2023-10-09 09:20:41,045][23468] Updated weights for policy 0, policy_version 26713 (0.0008) -[2023-10-09 09:20:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 54788096. Throughput: 0: 1780.5, 1: 1780.1. Samples: 13711702. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 09:20:41,078][22500] Avg episode reward: [(0, '6.650'), (1, '6.560')] -[2023-10-09 09:20:41,239][23469] Updated weights for policy 1, policy_version 26831 (0.0008) -[2023-10-09 09:20:41,601][23469] Updated weights for policy 1, policy_version 26841 (0.0007) -[2023-10-09 09:20:44,977][23468] Updated weights for policy 0, policy_version 26723 (0.0008) -[2023-10-09 09:20:45,369][23468] Updated weights for policy 0, policy_version 26733 (0.0009) -[2023-10-09 09:20:45,378][23469] Updated weights for policy 1, policy_version 26851 (0.0010) -[2023-10-09 09:20:45,737][23469] Updated weights for policy 1, policy_version 26861 (0.0010) -[2023-10-09 09:20:45,747][23468] Updated weights for policy 0, policy_version 26743 (0.0009) -[2023-10-09 09:20:46,078][22500] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 14218.0). Total num frames: 54853632. Throughput: 0: 1799.2, 1: 1796.2. Samples: 13732664. Policy #0 lag: (min: 24.0, avg: 53.0, max: 56.0) -[2023-10-09 09:20:46,078][22500] Avg episode reward: [(0, '6.610'), (1, '6.740')] -[2023-10-09 09:20:46,109][23469] Updated weights for policy 1, policy_version 26871 (0.0007) -[2023-10-09 09:20:49,496][23468] Updated weights for policy 0, policy_version 26753 (0.0008) -[2023-10-09 09:20:49,864][23468] Updated weights for policy 0, policy_version 26763 (0.0008) -[2023-10-09 09:20:49,990][23469] Updated weights for policy 1, policy_version 26881 (0.0008) -[2023-10-09 09:20:50,235][23468] Updated weights for policy 0, policy_version 26773 (0.0008) -[2023-10-09 09:20:50,351][23469] Updated weights for policy 1, policy_version 26891 (0.0008) -[2023-10-09 09:20:50,612][23468] Updated weights for policy 0, policy_version 26783 (0.0007) -[2023-10-09 09:20:50,725][23469] Updated weights for policy 1, policy_version 26901 (0.0009) -[2023-10-09 09:20:51,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 54951936. Throughput: 0: 1771.6, 1: 1779.5. Samples: 13743304. Policy #0 lag: (min: 24.0, avg: 53.0, max: 56.0) -[2023-10-09 09:20:51,078][22500] Avg episode reward: [(0, '6.530'), (1, '6.650')] -[2023-10-09 09:20:51,101][23469] Updated weights for policy 1, policy_version 26911 (0.0008) -[2023-10-09 09:20:54,338][23468] Updated weights for policy 0, policy_version 26793 (0.0008) -[2023-10-09 09:20:54,712][23468] Updated weights for policy 0, policy_version 26803 (0.0009) -[2023-10-09 09:20:54,967][23469] Updated weights for policy 1, policy_version 26921 (0.0008) -[2023-10-09 09:20:55,089][23468] Updated weights for policy 0, policy_version 26813 (0.0007) -[2023-10-09 09:20:55,333][23469] Updated weights for policy 1, policy_version 26931 (0.0010) -[2023-10-09 09:20:55,704][23469] Updated weights for policy 1, policy_version 26941 (0.0008) -[2023-10-09 09:20:56,077][22500] Fps is (10 sec: 19660.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 55050240. Throughput: 0: 1793.0, 1: 1802.2. Samples: 13765144. Policy #0 lag: (min: 24.0, avg: 53.0, max: 56.0) -[2023-10-09 09:20:56,078][22500] Avg episode reward: [(0, '6.470'), (1, '6.780')] -[2023-10-09 09:20:58,792][23468] Updated weights for policy 0, policy_version 26823 (0.0007) -[2023-10-09 09:20:59,167][23468] Updated weights for policy 0, policy_version 26833 (0.0007) -[2023-10-09 09:20:59,495][23469] Updated weights for policy 1, policy_version 26951 (0.0008) -[2023-10-09 09:20:59,546][23468] Updated weights for policy 0, policy_version 26843 (0.0007) -[2023-10-09 09:20:59,872][23469] Updated weights for policy 1, policy_version 26961 (0.0009) -[2023-10-09 09:21:00,238][23469] Updated weights for policy 1, policy_version 26971 (0.0008) -[2023-10-09 09:21:01,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 55115776. Throughput: 0: 1768.7, 1: 1771.7. Samples: 13785002. Policy #0 lag: (min: 24.0, avg: 53.0, max: 56.0) -[2023-10-09 09:21:01,078][22500] Avg episode reward: [(0, '6.790'), (1, '6.500')] -[2023-10-09 09:21:03,436][23468] Updated weights for policy 0, policy_version 26853 (0.0008) -[2023-10-09 09:21:03,803][23469] Updated weights for policy 1, policy_version 26981 (0.0010) -[2023-10-09 09:21:03,814][23468] Updated weights for policy 0, policy_version 26863 (0.0009) -[2023-10-09 09:21:04,175][23469] Updated weights for policy 1, policy_version 26991 (0.0009) -[2023-10-09 09:21:04,184][23468] Updated weights for policy 0, policy_version 26873 (0.0007) -[2023-10-09 09:21:04,548][23469] Updated weights for policy 1, policy_version 27001 (0.0009) -[2023-10-09 09:21:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 55181312. Throughput: 0: 1796.6, 1: 1795.7. Samples: 13797344. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:21:06,079][22500] Avg episode reward: [(0, '7.080'), (1, '6.730')] -[2023-10-09 09:21:07,921][23468] Updated weights for policy 0, policy_version 26883 (0.0007) -[2023-10-09 09:21:08,269][23469] Updated weights for policy 1, policy_version 27011 (0.0008) -[2023-10-09 09:21:08,290][23468] Updated weights for policy 0, policy_version 26893 (0.0007) -[2023-10-09 09:21:08,639][23469] Updated weights for policy 1, policy_version 27021 (0.0008) -[2023-10-09 09:21:08,670][23468] Updated weights for policy 0, policy_version 26903 (0.0007) -[2023-10-09 09:21:09,005][23469] Updated weights for policy 1, policy_version 27031 (0.0009) -[2023-10-09 09:21:11,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 55246848. Throughput: 0: 1765.3, 1: 1774.9. Samples: 13817050. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:21:11,078][22500] Avg episode reward: [(0, '7.210'), (1, '6.580')] -[2023-10-09 09:21:12,418][23468] Updated weights for policy 0, policy_version 26913 (0.0008) -[2023-10-09 09:21:12,794][23468] Updated weights for policy 0, policy_version 26923 (0.0008) -[2023-10-09 09:21:12,960][23469] Updated weights for policy 1, policy_version 27041 (0.0008) -[2023-10-09 09:21:13,165][23468] Updated weights for policy 0, policy_version 26933 (0.0007) -[2023-10-09 09:21:13,374][23469] Updated weights for policy 1, policy_version 27051 (0.0009) -[2023-10-09 09:21:13,544][23468] Updated weights for policy 0, policy_version 26943 (0.0007) -[2023-10-09 09:21:13,744][23469] Updated weights for policy 1, policy_version 27061 (0.0008) -[2023-10-09 09:21:14,120][23469] Updated weights for policy 1, policy_version 27071 (0.0008) -[2023-10-09 09:21:16,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 55312384. Throughput: 0: 1767.4, 1: 1773.1. Samples: 13839178. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:21:16,079][22500] Avg episode reward: [(0, '7.080'), (1, '6.400')] -[2023-10-09 09:21:17,415][23468] Updated weights for policy 0, policy_version 26953 (0.0007) -[2023-10-09 09:21:17,780][23468] Updated weights for policy 0, policy_version 26963 (0.0008) -[2023-10-09 09:21:17,913][23469] Updated weights for policy 1, policy_version 27081 (0.0008) -[2023-10-09 09:21:18,155][23468] Updated weights for policy 0, policy_version 26973 (0.0010) -[2023-10-09 09:21:18,282][23469] Updated weights for policy 1, policy_version 27091 (0.0008) -[2023-10-09 09:21:18,660][23469] Updated weights for policy 1, policy_version 27101 (0.0007) -[2023-10-09 09:21:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 55377920. Throughput: 0: 1769.4, 1: 1782.4. Samples: 13849232. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:21:21,078][22500] Avg episode reward: [(0, '6.960'), (1, '6.850')] -[2023-10-09 09:21:21,881][23468] Updated weights for policy 0, policy_version 26983 (0.0007) -[2023-10-09 09:21:22,250][23468] Updated weights for policy 0, policy_version 26993 (0.0008) -[2023-10-09 09:21:22,428][23469] Updated weights for policy 1, policy_version 27111 (0.0010) -[2023-10-09 09:21:22,630][23468] Updated weights for policy 0, policy_version 27003 (0.0009) -[2023-10-09 09:21:22,801][23469] Updated weights for policy 1, policy_version 27121 (0.0007) -[2023-10-09 09:21:23,176][23469] Updated weights for policy 1, policy_version 27131 (0.0007) -[2023-10-09 09:21:26,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 55443456. Throughput: 0: 1767.2, 1: 1781.6. Samples: 13871400. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:21:26,078][22500] Avg episode reward: [(0, '6.970'), (1, '6.740')] -[2023-10-09 09:21:26,355][23468] Updated weights for policy 0, policy_version 27013 (0.0010) -[2023-10-09 09:21:26,722][23468] Updated weights for policy 0, policy_version 27023 (0.0010) -[2023-10-09 09:21:26,874][23469] Updated weights for policy 1, policy_version 27141 (0.0008) -[2023-10-09 09:21:27,103][23468] Updated weights for policy 0, policy_version 27033 (0.0008) -[2023-10-09 09:21:27,249][23469] Updated weights for policy 1, policy_version 27151 (0.0009) -[2023-10-09 09:21:27,628][23469] Updated weights for policy 1, policy_version 27161 (0.0008) -[2023-10-09 09:21:30,890][23468] Updated weights for policy 0, policy_version 27043 (0.0008) -[2023-10-09 09:21:31,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 55508992. Throughput: 0: 1784.1, 1: 1798.1. Samples: 13893862. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:21:31,078][22500] Avg episode reward: [(0, '6.400'), (1, '7.050')] -[2023-10-09 09:21:31,278][23468] Updated weights for policy 0, policy_version 27053 (0.0008) -[2023-10-09 09:21:31,471][23469] Updated weights for policy 1, policy_version 27171 (0.0007) -[2023-10-09 09:21:31,662][23468] Updated weights for policy 0, policy_version 27063 (0.0008) -[2023-10-09 09:21:31,840][23469] Updated weights for policy 1, policy_version 27181 (0.0008) -[2023-10-09 09:21:32,206][23469] Updated weights for policy 1, policy_version 27191 (0.0007) -[2023-10-09 09:21:35,325][23468] Updated weights for policy 0, policy_version 27073 (0.0008) -[2023-10-09 09:21:35,692][23468] Updated weights for policy 0, policy_version 27083 (0.0011) -[2023-10-09 09:21:35,981][23469] Updated weights for policy 1, policy_version 27201 (0.0009) -[2023-10-09 09:21:36,062][23468] Updated weights for policy 0, policy_version 27093 (0.0007) -[2023-10-09 09:21:36,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 55574528. Throughput: 0: 1775.2, 1: 1786.3. Samples: 13903570. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:21:36,078][22500] Avg episode reward: [(0, '6.080'), (1, '6.730')] -[2023-10-09 09:21:36,350][23469] Updated weights for policy 1, policy_version 27211 (0.0009) -[2023-10-09 09:21:36,434][23468] Updated weights for policy 0, policy_version 27103 (0.0007) -[2023-10-09 09:21:36,720][23469] Updated weights for policy 1, policy_version 27221 (0.0010) -[2023-10-09 09:21:37,088][23469] Updated weights for policy 1, policy_version 27231 (0.0009) -[2023-10-09 09:21:40,198][23468] Updated weights for policy 0, policy_version 27113 (0.0010) -[2023-10-09 09:21:40,568][23468] Updated weights for policy 0, policy_version 27123 (0.0007) -[2023-10-09 09:21:40,636][23469] Updated weights for policy 1, policy_version 27241 (0.0010) -[2023-10-09 09:21:40,935][23468] Updated weights for policy 0, policy_version 27133 (0.0009) -[2023-10-09 09:21:40,997][23469] Updated weights for policy 1, policy_version 27251 (0.0009) -[2023-10-09 09:21:41,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 55672832. Throughput: 0: 1785.7, 1: 1795.3. Samples: 13926290. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:21:41,078][22500] Avg episode reward: [(0, '6.760'), (1, '6.460')] -[2023-10-09 09:21:41,371][23469] Updated weights for policy 1, policy_version 27261 (0.0008) -[2023-10-09 09:21:44,671][23468] Updated weights for policy 0, policy_version 27143 (0.0009) -[2023-10-09 09:21:45,040][23468] Updated weights for policy 0, policy_version 27153 (0.0008) -[2023-10-09 09:21:45,068][23469] Updated weights for policy 1, policy_version 27271 (0.0007) -[2023-10-09 09:21:45,407][23468] Updated weights for policy 0, policy_version 27163 (0.0007) -[2023-10-09 09:21:45,438][23469] Updated weights for policy 1, policy_version 27281 (0.0008) -[2023-10-09 09:21:45,801][23469] Updated weights for policy 1, policy_version 27291 (0.0009) -[2023-10-09 09:21:46,077][22500] Fps is (10 sec: 19660.6, 60 sec: 15291.8, 300 sec: 14440.1). Total num frames: 55771136. Throughput: 0: 1793.2, 1: 1800.8. Samples: 13946730. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:21:46,078][22500] Avg episode reward: [(0, '6.840'), (1, '6.780')] -[2023-10-09 09:21:49,256][23468] Updated weights for policy 0, policy_version 27173 (0.0007) -[2023-10-09 09:21:49,628][23468] Updated weights for policy 0, policy_version 27183 (0.0007) -[2023-10-09 09:21:49,719][23469] Updated weights for policy 1, policy_version 27301 (0.0009) -[2023-10-09 09:21:49,993][23468] Updated weights for policy 0, policy_version 27193 (0.0008) -[2023-10-09 09:21:50,090][23469] Updated weights for policy 1, policy_version 27311 (0.0008) -[2023-10-09 09:21:50,458][23469] Updated weights for policy 1, policy_version 27321 (0.0008) -[2023-10-09 09:21:51,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 55836672. Throughput: 0: 1785.3, 1: 1790.1. Samples: 13958238. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:21:51,078][22500] Avg episode reward: [(0, '7.070'), (1, '6.200')] -[2023-10-09 09:21:53,696][23468] Updated weights for policy 0, policy_version 27203 (0.0008) -[2023-10-09 09:21:54,068][23468] Updated weights for policy 0, policy_version 27213 (0.0008) -[2023-10-09 09:21:54,254][23469] Updated weights for policy 1, policy_version 27331 (0.0007) -[2023-10-09 09:21:54,442][23468] Updated weights for policy 0, policy_version 27223 (0.0007) -[2023-10-09 09:21:54,622][23469] Updated weights for policy 1, policy_version 27341 (0.0007) -[2023-10-09 09:21:54,991][23469] Updated weights for policy 1, policy_version 27351 (0.0009) -[2023-10-09 09:21:56,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 55902208. Throughput: 0: 1801.8, 1: 1799.0. Samples: 13979086. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:21:56,078][22500] Avg episode reward: [(0, '7.120'), (1, '6.390')] -[2023-10-09 09:21:58,164][23468] Updated weights for policy 0, policy_version 27233 (0.0010) -[2023-10-09 09:21:58,536][23468] Updated weights for policy 0, policy_version 27243 (0.0008) -[2023-10-09 09:21:58,822][23469] Updated weights for policy 1, policy_version 27361 (0.0010) -[2023-10-09 09:21:58,911][23468] Updated weights for policy 0, policy_version 27253 (0.0009) -[2023-10-09 09:21:59,248][23469] Updated weights for policy 1, policy_version 27371 (0.0007) -[2023-10-09 09:21:59,286][23468] Updated weights for policy 0, policy_version 27263 (0.0008) -[2023-10-09 09:21:59,618][23469] Updated weights for policy 1, policy_version 27381 (0.0011) -[2023-10-09 09:21:59,989][23469] Updated weights for policy 1, policy_version 27391 (0.0007) -[2023-10-09 09:22:01,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 55967744. Throughput: 0: 1785.9, 1: 1783.0. Samples: 13999778. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:22:01,078][22500] Avg episode reward: [(0, '6.920'), (1, '6.040')] -[2023-10-09 09:22:03,107][23468] Updated weights for policy 0, policy_version 27273 (0.0007) -[2023-10-09 09:22:03,475][23468] Updated weights for policy 0, policy_version 27283 (0.0007) -[2023-10-09 09:22:03,731][23469] Updated weights for policy 1, policy_version 27401 (0.0007) -[2023-10-09 09:22:03,853][23468] Updated weights for policy 0, policy_version 27293 (0.0008) -[2023-10-09 09:22:04,101][23469] Updated weights for policy 1, policy_version 27411 (0.0009) -[2023-10-09 09:22:04,459][23469] Updated weights for policy 1, policy_version 27421 (0.0011) -[2023-10-09 09:22:06,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 56033280. Throughput: 0: 1801.6, 1: 1800.5. Samples: 14011326. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:22:06,078][22500] Avg episode reward: [(0, '6.740'), (1, '6.290')] -[2023-10-09 09:22:07,666][23468] Updated weights for policy 0, policy_version 27303 (0.0009) -[2023-10-09 09:22:08,037][23468] Updated weights for policy 0, policy_version 27313 (0.0009) -[2023-10-09 09:22:08,088][23469] Updated weights for policy 1, policy_version 27431 (0.0008) -[2023-10-09 09:22:08,413][23468] Updated weights for policy 0, policy_version 27323 (0.0008) -[2023-10-09 09:22:08,457][23469] Updated weights for policy 1, policy_version 27441 (0.0008) -[2023-10-09 09:22:08,833][23469] Updated weights for policy 1, policy_version 27451 (0.0007) -[2023-10-09 09:22:11,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 56098816. Throughput: 0: 1786.3, 1: 1782.6. Samples: 14032000. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:22:11,078][22500] Avg episode reward: [(0, '7.010'), (1, '6.190')] -[2023-10-09 09:22:12,094][23468] Updated weights for policy 0, policy_version 27333 (0.0007) -[2023-10-09 09:22:12,473][23468] Updated weights for policy 0, policy_version 27343 (0.0008) -[2023-10-09 09:22:12,648][23469] Updated weights for policy 1, policy_version 27461 (0.0008) -[2023-10-09 09:22:12,832][23468] Updated weights for policy 0, policy_version 27353 (0.0009) -[2023-10-09 09:22:13,009][23469] Updated weights for policy 1, policy_version 27471 (0.0007) -[2023-10-09 09:22:13,384][23469] Updated weights for policy 1, policy_version 27481 (0.0010) -[2023-10-09 09:22:16,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 56164352. Throughput: 0: 1786.7, 1: 1779.5. Samples: 14054342. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-09 09:22:16,078][22500] Avg episode reward: [(0, '7.480'), (1, '6.620')] -[2023-10-09 09:22:16,087][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000027360_28016640.pth... -[2023-10-09 09:22:16,087][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000027488_28147712.pth... -[2023-10-09 09:22:16,132][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000025696_26312704.pth -[2023-10-09 09:22:16,133][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000025824_26443776.pth -[2023-10-09 09:22:16,681][23468] Updated weights for policy 0, policy_version 27363 (0.0008) -[2023-10-09 09:22:17,062][23468] Updated weights for policy 0, policy_version 27373 (0.0009) -[2023-10-09 09:22:17,099][23469] Updated weights for policy 1, policy_version 27491 (0.0009) -[2023-10-09 09:22:17,440][23468] Updated weights for policy 0, policy_version 27383 (0.0009) -[2023-10-09 09:22:17,463][23469] Updated weights for policy 1, policy_version 27501 (0.0008) -[2023-10-09 09:22:17,830][23469] Updated weights for policy 1, policy_version 27511 (0.0008) -[2023-10-09 09:22:21,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 56229888. Throughput: 0: 1786.7, 1: 1777.7. Samples: 14063966. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-09 09:22:21,078][22500] Avg episode reward: [(0, '7.710'), (1, '6.530')] -[2023-10-09 09:22:21,297][23468] Updated weights for policy 0, policy_version 27393 (0.0007) -[2023-10-09 09:22:21,670][23468] Updated weights for policy 0, policy_version 27403 (0.0009) -[2023-10-09 09:22:21,746][23469] Updated weights for policy 1, policy_version 27521 (0.0008) -[2023-10-09 09:22:22,037][23468] Updated weights for policy 0, policy_version 27413 (0.0007) -[2023-10-09 09:22:22,108][23469] Updated weights for policy 1, policy_version 27531 (0.0007) -[2023-10-09 09:22:22,410][23468] Updated weights for policy 0, policy_version 27423 (0.0007) -[2023-10-09 09:22:22,483][23469] Updated weights for policy 1, policy_version 27541 (0.0008) -[2023-10-09 09:22:22,847][23469] Updated weights for policy 1, policy_version 27551 (0.0008) -[2023-10-09 09:22:26,039][23468] Updated weights for policy 0, policy_version 27433 (0.0007) -[2023-10-09 09:22:26,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 56295424. Throughput: 0: 1781.1, 1: 1769.6. Samples: 14086072. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-09 09:22:26,078][22500] Avg episode reward: [(0, '7.580'), (1, '6.230')] -[2023-10-09 09:22:26,414][23468] Updated weights for policy 0, policy_version 27443 (0.0009) -[2023-10-09 09:22:26,671][23469] Updated weights for policy 1, policy_version 27561 (0.0007) -[2023-10-09 09:22:26,790][23468] Updated weights for policy 0, policy_version 27453 (0.0007) -[2023-10-09 09:22:27,047][23469] Updated weights for policy 1, policy_version 27571 (0.0009) -[2023-10-09 09:22:27,417][23469] Updated weights for policy 1, policy_version 27581 (0.0009) -[2023-10-09 09:22:30,484][23468] Updated weights for policy 0, policy_version 27463 (0.0008) -[2023-10-09 09:22:30,860][23468] Updated weights for policy 0, policy_version 27473 (0.0007) -[2023-10-09 09:22:31,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 56360960. Throughput: 0: 1804.8, 1: 1791.8. Samples: 14108576. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-09 09:22:31,078][22500] Avg episode reward: [(0, '7.060'), (1, '6.280')] -[2023-10-09 09:22:31,229][23468] Updated weights for policy 0, policy_version 27483 (0.0007) -[2023-10-09 09:22:31,286][23469] Updated weights for policy 1, policy_version 27591 (0.0008) -[2023-10-09 09:22:31,656][23469] Updated weights for policy 1, policy_version 27601 (0.0008) -[2023-10-09 09:22:32,026][23469] Updated weights for policy 1, policy_version 27611 (0.0008) -[2023-10-09 09:22:35,072][23468] Updated weights for policy 0, policy_version 27493 (0.0007) -[2023-10-09 09:22:35,444][23468] Updated weights for policy 0, policy_version 27503 (0.0009) -[2023-10-09 09:22:35,738][23469] Updated weights for policy 1, policy_version 27621 (0.0008) -[2023-10-09 09:22:35,826][23468] Updated weights for policy 0, policy_version 27513 (0.0007) -[2023-10-09 09:22:36,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 56426496. Throughput: 0: 1788.4, 1: 1772.6. Samples: 14118482. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-09 09:22:36,078][22500] Avg episode reward: [(0, '6.980'), (1, '6.170')] -[2023-10-09 09:22:36,115][23469] Updated weights for policy 1, policy_version 27631 (0.0008) -[2023-10-09 09:22:36,477][23469] Updated weights for policy 1, policy_version 27641 (0.0007) -[2023-10-09 09:22:39,674][23468] Updated weights for policy 0, policy_version 27523 (0.0007) -[2023-10-09 09:22:40,058][23468] Updated weights for policy 0, policy_version 27533 (0.0007) -[2023-10-09 09:22:40,139][23469] Updated weights for policy 1, policy_version 27651 (0.0008) -[2023-10-09 09:22:40,437][23468] Updated weights for policy 0, policy_version 27543 (0.0008) -[2023-10-09 09:22:40,506][23469] Updated weights for policy 1, policy_version 27661 (0.0008) -[2023-10-09 09:22:40,885][23469] Updated weights for policy 1, policy_version 27671 (0.0008) -[2023-10-09 09:22:41,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 56524800. Throughput: 0: 1799.4, 1: 1792.6. Samples: 14140724. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:22:41,078][22500] Avg episode reward: [(0, '7.160'), (1, '6.650')] -[2023-10-09 09:22:44,142][23468] Updated weights for policy 0, policy_version 27553 (0.0008) -[2023-10-09 09:22:44,516][23468] Updated weights for policy 0, policy_version 27563 (0.0010) -[2023-10-09 09:22:44,635][23469] Updated weights for policy 1, policy_version 27681 (0.0008) -[2023-10-09 09:22:44,878][23468] Updated weights for policy 0, policy_version 27573 (0.0008) -[2023-10-09 09:22:45,076][23469] Updated weights for policy 1, policy_version 27691 (0.0008) -[2023-10-09 09:22:45,250][23468] Updated weights for policy 0, policy_version 27583 (0.0008) -[2023-10-09 09:22:45,441][23469] Updated weights for policy 1, policy_version 27701 (0.0009) -[2023-10-09 09:22:45,815][23469] Updated weights for policy 1, policy_version 27711 (0.0009) -[2023-10-09 09:22:46,077][22500] Fps is (10 sec: 19660.4, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 56623104. Throughput: 0: 1781.7, 1: 1785.0. Samples: 14160278. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:22:46,078][22500] Avg episode reward: [(0, '7.360'), (1, '6.650')] -[2023-10-09 09:22:49,060][23468] Updated weights for policy 0, policy_version 27593 (0.0010) -[2023-10-09 09:22:49,435][23468] Updated weights for policy 0, policy_version 27603 (0.0008) -[2023-10-09 09:22:49,643][23469] Updated weights for policy 1, policy_version 27721 (0.0008) -[2023-10-09 09:22:49,811][23468] Updated weights for policy 0, policy_version 27613 (0.0010) -[2023-10-09 09:22:50,012][23469] Updated weights for policy 1, policy_version 27731 (0.0007) -[2023-10-09 09:22:50,385][23469] Updated weights for policy 1, policy_version 27741 (0.0008) -[2023-10-09 09:22:51,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 56688640. Throughput: 0: 1796.6, 1: 1785.1. Samples: 14172502. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:22:51,078][22500] Avg episode reward: [(0, '7.430'), (1, '6.580')] -[2023-10-09 09:22:53,629][23468] Updated weights for policy 0, policy_version 27623 (0.0007) -[2023-10-09 09:22:54,001][23468] Updated weights for policy 0, policy_version 27633 (0.0009) -[2023-10-09 09:22:54,074][23469] Updated weights for policy 1, policy_version 27751 (0.0009) -[2023-10-09 09:22:54,371][23468] Updated weights for policy 0, policy_version 27643 (0.0009) -[2023-10-09 09:22:54,439][23469] Updated weights for policy 1, policy_version 27761 (0.0008) -[2023-10-09 09:22:54,814][23469] Updated weights for policy 1, policy_version 27771 (0.0009) -[2023-10-09 09:22:56,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 56754176. Throughput: 0: 1788.8, 1: 1780.5. Samples: 14192618. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:22:56,078][22500] Avg episode reward: [(0, '7.570'), (1, '6.220')] -[2023-10-09 09:22:58,081][23468] Updated weights for policy 0, policy_version 27653 (0.0008) -[2023-10-09 09:22:58,445][23468] Updated weights for policy 0, policy_version 27663 (0.0007) -[2023-10-09 09:22:58,605][23469] Updated weights for policy 1, policy_version 27781 (0.0007) -[2023-10-09 09:22:58,829][23468] Updated weights for policy 0, policy_version 27673 (0.0009) -[2023-10-09 09:22:58,987][23469] Updated weights for policy 1, policy_version 27791 (0.0008) -[2023-10-09 09:22:59,352][23469] Updated weights for policy 1, policy_version 27801 (0.0008) -[2023-10-09 09:23:01,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 56819712. Throughput: 0: 1776.7, 1: 1776.7. Samples: 14214246. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-09 09:23:01,079][22500] Avg episode reward: [(0, '7.340'), (1, '6.510')] -[2023-10-09 09:23:02,682][23468] Updated weights for policy 0, policy_version 27683 (0.0008) -[2023-10-09 09:23:03,071][23468] Updated weights for policy 0, policy_version 27693 (0.0009) -[2023-10-09 09:23:03,182][23469] Updated weights for policy 1, policy_version 27811 (0.0009) -[2023-10-09 09:23:03,439][23468] Updated weights for policy 0, policy_version 27703 (0.0008) -[2023-10-09 09:23:03,545][23469] Updated weights for policy 1, policy_version 27821 (0.0008) -[2023-10-09 09:23:03,913][23469] Updated weights for policy 1, policy_version 27831 (0.0009) -[2023-10-09 09:23:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 56885248. Throughput: 0: 1787.0, 1: 1794.9. Samples: 14225152. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-09 09:23:06,079][22500] Avg episode reward: [(0, '7.370'), (1, '6.140')] -[2023-10-09 09:23:07,328][23468] Updated weights for policy 0, policy_version 27713 (0.0008) -[2023-10-09 09:23:07,700][23468] Updated weights for policy 0, policy_version 27723 (0.0007) -[2023-10-09 09:23:07,762][23469] Updated weights for policy 1, policy_version 27841 (0.0007) -[2023-10-09 09:23:08,078][23468] Updated weights for policy 0, policy_version 27733 (0.0009) -[2023-10-09 09:23:08,129][23469] Updated weights for policy 1, policy_version 27851 (0.0010) -[2023-10-09 09:23:08,454][23468] Updated weights for policy 0, policy_version 27743 (0.0009) -[2023-10-09 09:23:08,501][23469] Updated weights for policy 1, policy_version 27861 (0.0008) -[2023-10-09 09:23:08,874][23469] Updated weights for policy 1, policy_version 27871 (0.0009) -[2023-10-09 09:23:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 56950784. Throughput: 0: 1772.4, 1: 1779.4. Samples: 14245900. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-09 09:23:11,078][22500] Avg episode reward: [(0, '7.110'), (1, '6.230')] -[2023-10-09 09:23:12,155][23468] Updated weights for policy 0, policy_version 27753 (0.0010) -[2023-10-09 09:23:12,532][23468] Updated weights for policy 0, policy_version 27763 (0.0009) -[2023-10-09 09:23:12,689][23469] Updated weights for policy 1, policy_version 27881 (0.0009) -[2023-10-09 09:23:12,900][23468] Updated weights for policy 0, policy_version 27773 (0.0008) -[2023-10-09 09:23:13,053][23469] Updated weights for policy 1, policy_version 27891 (0.0008) -[2023-10-09 09:23:13,428][23469] Updated weights for policy 1, policy_version 27901 (0.0009) -[2023-10-09 09:23:16,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 57016320. Throughput: 0: 1768.1, 1: 1782.7. Samples: 14268362. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-09 09:23:16,078][22500] Avg episode reward: [(0, '7.190'), (1, '6.170')] -[2023-10-09 09:23:16,711][23468] Updated weights for policy 0, policy_version 27783 (0.0009) -[2023-10-09 09:23:17,050][23469] Updated weights for policy 1, policy_version 27911 (0.0008) -[2023-10-09 09:23:17,075][23468] Updated weights for policy 0, policy_version 27793 (0.0008) -[2023-10-09 09:23:17,420][23469] Updated weights for policy 1, policy_version 27921 (0.0011) -[2023-10-09 09:23:17,450][23468] Updated weights for policy 0, policy_version 27803 (0.0008) -[2023-10-09 09:23:17,789][23469] Updated weights for policy 1, policy_version 27931 (0.0007) -[2023-10-09 09:23:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 57081856. Throughput: 0: 1764.5, 1: 1781.2. Samples: 14278038. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-09 09:23:21,078][22500] Avg episode reward: [(0, '7.070'), (1, '6.600')] -[2023-10-09 09:23:21,238][23468] Updated weights for policy 0, policy_version 27813 (0.0009) -[2023-10-09 09:23:21,567][23469] Updated weights for policy 1, policy_version 27941 (0.0009) -[2023-10-09 09:23:21,593][23468] Updated weights for policy 0, policy_version 27823 (0.0008) -[2023-10-09 09:23:21,949][23469] Updated weights for policy 1, policy_version 27951 (0.0009) -[2023-10-09 09:23:21,965][23468] Updated weights for policy 0, policy_version 27833 (0.0007) -[2023-10-09 09:23:22,319][23469] Updated weights for policy 1, policy_version 27961 (0.0008) -[2023-10-09 09:23:25,590][23468] Updated weights for policy 0, policy_version 27843 (0.0007) -[2023-10-09 09:23:25,973][23468] Updated weights for policy 0, policy_version 27853 (0.0009) -[2023-10-09 09:23:25,975][23469] Updated weights for policy 1, policy_version 27971 (0.0009) -[2023-10-09 09:23:26,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 57147392. Throughput: 0: 1776.9, 1: 1774.5. Samples: 14300534. Policy #0 lag: (min: 4.0, avg: 6.9, max: 36.0) -[2023-10-09 09:23:26,078][22500] Avg episode reward: [(0, '7.130'), (1, '6.440')] -[2023-10-09 09:23:26,342][23469] Updated weights for policy 1, policy_version 27981 (0.0007) -[2023-10-09 09:23:26,348][23468] Updated weights for policy 0, policy_version 27863 (0.0008) -[2023-10-09 09:23:26,708][23469] Updated weights for policy 1, policy_version 27991 (0.0007) -[2023-10-09 09:23:30,190][23468] Updated weights for policy 0, policy_version 27873 (0.0007) -[2023-10-09 09:23:30,538][23469] Updated weights for policy 1, policy_version 28001 (0.0007) -[2023-10-09 09:23:30,562][23468] Updated weights for policy 0, policy_version 27883 (0.0008) -[2023-10-09 09:23:30,899][23469] Updated weights for policy 1, policy_version 28011 (0.0009) -[2023-10-09 09:23:30,940][23468] Updated weights for policy 0, policy_version 27893 (0.0010) -[2023-10-09 09:23:31,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 57212928. Throughput: 0: 1797.9, 1: 1801.2. Samples: 14322234. Policy #0 lag: (min: 4.0, avg: 6.9, max: 36.0) -[2023-10-09 09:23:31,078][22500] Avg episode reward: [(0, '7.240'), (1, '6.450')] -[2023-10-09 09:23:31,267][23469] Updated weights for policy 1, policy_version 28021 (0.0008) -[2023-10-09 09:23:31,305][23468] Updated weights for policy 0, policy_version 27903 (0.0008) -[2023-10-09 09:23:31,634][23469] Updated weights for policy 1, policy_version 28031 (0.0008) -[2023-10-09 09:23:34,946][23468] Updated weights for policy 0, policy_version 27913 (0.0008) -[2023-10-09 09:23:35,166][23469] Updated weights for policy 1, policy_version 28041 (0.0008) -[2023-10-09 09:23:35,318][23468] Updated weights for policy 0, policy_version 27923 (0.0008) -[2023-10-09 09:23:35,538][23469] Updated weights for policy 1, policy_version 28051 (0.0010) -[2023-10-09 09:23:35,689][23468] Updated weights for policy 0, policy_version 27933 (0.0009) -[2023-10-09 09:23:35,908][23469] Updated weights for policy 1, policy_version 28061 (0.0007) -[2023-10-09 09:23:36,077][22500] Fps is (10 sec: 19660.5, 60 sec: 15291.7, 300 sec: 14440.1). Total num frames: 57344000. Throughput: 0: 1772.3, 1: 1787.5. Samples: 14332696. Policy #0 lag: (min: 4.0, avg: 6.9, max: 36.0) -[2023-10-09 09:23:36,079][22500] Avg episode reward: [(0, '7.440'), (1, '6.450')] -[2023-10-09 09:23:39,629][23468] Updated weights for policy 0, policy_version 27943 (0.0008) -[2023-10-09 09:23:39,702][23469] Updated weights for policy 1, policy_version 28071 (0.0008) -[2023-10-09 09:23:40,001][23468] Updated weights for policy 0, policy_version 27953 (0.0008) -[2023-10-09 09:23:40,065][23469] Updated weights for policy 1, policy_version 28081 (0.0008) -[2023-10-09 09:23:40,366][23468] Updated weights for policy 0, policy_version 27963 (0.0009) -[2023-10-09 09:23:40,438][23469] Updated weights for policy 1, policy_version 28091 (0.0009) -[2023-10-09 09:23:41,077][22500] Fps is (10 sec: 19660.9, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 57409536. Throughput: 0: 1798.8, 1: 1801.6. Samples: 14354636. Policy #0 lag: (min: 4.0, avg: 6.9, max: 36.0) -[2023-10-09 09:23:41,078][22500] Avg episode reward: [(0, '7.500'), (1, '6.370')] -[2023-10-09 09:23:44,100][23468] Updated weights for policy 0, policy_version 27973 (0.0009) -[2023-10-09 09:23:44,339][23469] Updated weights for policy 1, policy_version 28101 (0.0008) -[2023-10-09 09:23:44,475][23468] Updated weights for policy 0, policy_version 27983 (0.0007) -[2023-10-09 09:23:44,708][23469] Updated weights for policy 1, policy_version 28111 (0.0008) -[2023-10-09 09:23:44,849][23468] Updated weights for policy 0, policy_version 27993 (0.0007) -[2023-10-09 09:23:45,082][23469] Updated weights for policy 1, policy_version 28121 (0.0008) -[2023-10-09 09:23:46,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 57475072. Throughput: 0: 1772.1, 1: 1780.1. Samples: 14374096. Policy #0 lag: (min: 2.0, avg: 14.1, max: 34.0) -[2023-10-09 09:23:46,078][22500] Avg episode reward: [(0, '6.960'), (1, '6.750')] -[2023-10-09 09:23:48,625][23468] Updated weights for policy 0, policy_version 28003 (0.0008) -[2023-10-09 09:23:48,937][23469] Updated weights for policy 1, policy_version 28131 (0.0010) -[2023-10-09 09:23:49,016][23468] Updated weights for policy 0, policy_version 28013 (0.0008) -[2023-10-09 09:23:49,311][23469] Updated weights for policy 1, policy_version 28141 (0.0009) -[2023-10-09 09:23:49,391][23468] Updated weights for policy 0, policy_version 28023 (0.0007) -[2023-10-09 09:23:49,687][23469] Updated weights for policy 1, policy_version 28151 (0.0008) -[2023-10-09 09:23:51,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 57540608. Throughput: 0: 1796.2, 1: 1796.0. Samples: 14386800. Policy #0 lag: (min: 2.0, avg: 14.1, max: 34.0) -[2023-10-09 09:23:51,078][22500] Avg episode reward: [(0, '6.380'), (1, '6.040')] -[2023-10-09 09:23:53,211][23468] Updated weights for policy 0, policy_version 28033 (0.0007) -[2023-10-09 09:23:53,429][23469] Updated weights for policy 1, policy_version 28161 (0.0008) -[2023-10-09 09:23:53,581][23468] Updated weights for policy 0, policy_version 28043 (0.0008) -[2023-10-09 09:23:53,787][23469] Updated weights for policy 1, policy_version 28171 (0.0007) -[2023-10-09 09:23:53,956][23468] Updated weights for policy 0, policy_version 28053 (0.0008) -[2023-10-09 09:23:54,161][23469] Updated weights for policy 1, policy_version 28181 (0.0008) -[2023-10-09 09:23:54,331][23468] Updated weights for policy 0, policy_version 28063 (0.0007) -[2023-10-09 09:23:54,538][23469] Updated weights for policy 1, policy_version 28191 (0.0009) -[2023-10-09 09:23:56,078][22500] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 57606144. Throughput: 0: 1776.6, 1: 1780.1. Samples: 14405954. Policy #0 lag: (min: 2.0, avg: 14.1, max: 34.0) -[2023-10-09 09:23:56,079][22500] Avg episode reward: [(0, '6.730'), (1, '6.310')] -[2023-10-09 09:23:58,070][23468] Updated weights for policy 0, policy_version 28073 (0.0008) -[2023-10-09 09:23:58,444][23468] Updated weights for policy 0, policy_version 28083 (0.0008) -[2023-10-09 09:23:58,465][23469] Updated weights for policy 1, policy_version 28201 (0.0008) -[2023-10-09 09:23:58,809][23468] Updated weights for policy 0, policy_version 28093 (0.0007) -[2023-10-09 09:23:58,833][23469] Updated weights for policy 1, policy_version 28211 (0.0008) -[2023-10-09 09:23:59,190][23469] Updated weights for policy 1, policy_version 28221 (0.0010) -[2023-10-09 09:24:01,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 57671680. Throughput: 0: 1774.4, 1: 1777.3. Samples: 14428186. Policy #0 lag: (min: 2.0, avg: 14.1, max: 34.0) -[2023-10-09 09:24:01,078][22500] Avg episode reward: [(0, '6.590'), (1, '6.400')] -[2023-10-09 09:24:02,641][23468] Updated weights for policy 0, policy_version 28103 (0.0009) -[2023-10-09 09:24:02,828][23469] Updated weights for policy 1, policy_version 28231 (0.0008) -[2023-10-09 09:24:03,016][23468] Updated weights for policy 0, policy_version 28113 (0.0008) -[2023-10-09 09:24:03,194][23469] Updated weights for policy 1, policy_version 28241 (0.0008) -[2023-10-09 09:24:03,388][23468] Updated weights for policy 0, policy_version 28123 (0.0008) -[2023-10-09 09:24:03,566][23469] Updated weights for policy 1, policy_version 28251 (0.0008) -[2023-10-09 09:24:06,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 57737216. Throughput: 0: 1782.1, 1: 1779.4. Samples: 14438304. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:24:06,078][22500] Avg episode reward: [(0, '6.870'), (1, '6.690')] -[2023-10-09 09:24:07,198][23468] Updated weights for policy 0, policy_version 28133 (0.0008) -[2023-10-09 09:24:07,360][23469] Updated weights for policy 1, policy_version 28261 (0.0008) -[2023-10-09 09:24:07,568][23468] Updated weights for policy 0, policy_version 28143 (0.0007) -[2023-10-09 09:24:07,729][23469] Updated weights for policy 1, policy_version 28271 (0.0007) -[2023-10-09 09:24:07,932][23468] Updated weights for policy 0, policy_version 28153 (0.0007) -[2023-10-09 09:24:08,097][23469] Updated weights for policy 1, policy_version 28281 (0.0008) -[2023-10-09 09:24:11,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 57802752. Throughput: 0: 1763.0, 1: 1785.4. Samples: 14460214. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:24:11,078][22500] Avg episode reward: [(0, '6.920'), (1, '6.520')] -[2023-10-09 09:24:11,818][23468] Updated weights for policy 0, policy_version 28163 (0.0009) -[2023-10-09 09:24:11,885][23469] Updated weights for policy 1, policy_version 28291 (0.0008) -[2023-10-09 09:24:12,196][23468] Updated weights for policy 0, policy_version 28173 (0.0008) -[2023-10-09 09:24:12,248][23469] Updated weights for policy 1, policy_version 28301 (0.0008) -[2023-10-09 09:24:12,571][23468] Updated weights for policy 0, policy_version 28183 (0.0007) -[2023-10-09 09:24:12,616][23469] Updated weights for policy 1, policy_version 28311 (0.0008) -[2023-10-09 09:24:16,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 57868288. Throughput: 0: 1769.1, 1: 1786.5. Samples: 14482234. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:24:16,078][22500] Avg episode reward: [(0, '7.220'), (1, '6.850')] -[2023-10-09 09:24:16,087][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000028320_28999680.pth... -[2023-10-09 09:24:16,087][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000028192_28868608.pth... -[2023-10-09 09:24:16,123][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000026656_27295744.pth -[2023-10-09 09:24:16,134][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000026528_27164672.pth -[2023-10-09 09:24:16,405][23468] Updated weights for policy 0, policy_version 28193 (0.0009) -[2023-10-09 09:24:16,443][23469] Updated weights for policy 1, policy_version 28321 (0.0008) -[2023-10-09 09:24:16,774][23468] Updated weights for policy 0, policy_version 28203 (0.0007) -[2023-10-09 09:24:16,869][23469] Updated weights for policy 1, policy_version 28331 (0.0009) -[2023-10-09 09:24:17,145][23468] Updated weights for policy 0, policy_version 28213 (0.0007) -[2023-10-09 09:24:17,232][23469] Updated weights for policy 1, policy_version 28341 (0.0007) -[2023-10-09 09:24:17,515][23468] Updated weights for policy 0, policy_version 28223 (0.0007) -[2023-10-09 09:24:17,602][23469] Updated weights for policy 1, policy_version 28351 (0.0008) -[2023-10-09 09:24:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 57933824. Throughput: 0: 1761.4, 1: 1772.2. Samples: 14491708. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:24:21,079][22500] Avg episode reward: [(0, '7.120'), (1, '6.590')] -[2023-10-09 09:24:21,193][23468] Updated weights for policy 0, policy_version 28233 (0.0009) -[2023-10-09 09:24:21,346][23469] Updated weights for policy 1, policy_version 28361 (0.0008) -[2023-10-09 09:24:21,568][23468] Updated weights for policy 0, policy_version 28243 (0.0007) -[2023-10-09 09:24:21,720][23469] Updated weights for policy 1, policy_version 28371 (0.0009) -[2023-10-09 09:24:21,945][23468] Updated weights for policy 0, policy_version 28253 (0.0008) -[2023-10-09 09:24:22,077][23469] Updated weights for policy 1, policy_version 28381 (0.0008) -[2023-10-09 09:24:25,719][23468] Updated weights for policy 0, policy_version 28263 (0.0008) -[2023-10-09 09:24:25,851][23469] Updated weights for policy 1, policy_version 28391 (0.0008) -[2023-10-09 09:24:26,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 57999360. Throughput: 0: 1761.1, 1: 1780.2. Samples: 14513996. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:24:26,078][22500] Avg episode reward: [(0, '7.000'), (1, '7.070')] -[2023-10-09 09:24:26,082][23468] Updated weights for policy 0, policy_version 28273 (0.0009) -[2023-10-09 09:24:26,219][23469] Updated weights for policy 1, policy_version 28401 (0.0008) -[2023-10-09 09:24:26,463][23468] Updated weights for policy 0, policy_version 28283 (0.0007) -[2023-10-09 09:24:26,591][23469] Updated weights for policy 1, policy_version 28411 (0.0007) -[2023-10-09 09:24:30,306][23468] Updated weights for policy 0, policy_version 28293 (0.0008) -[2023-10-09 09:24:30,338][23469] Updated weights for policy 1, policy_version 28421 (0.0009) -[2023-10-09 09:24:30,669][23468] Updated weights for policy 0, policy_version 28303 (0.0010) -[2023-10-09 09:24:30,714][23469] Updated weights for policy 1, policy_version 28431 (0.0008) -[2023-10-09 09:24:31,040][23468] Updated weights for policy 0, policy_version 28313 (0.0008) -[2023-10-09 09:24:31,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 58064896. Throughput: 0: 1792.9, 1: 1792.4. Samples: 14535432. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:24:31,078][22500] Avg episode reward: [(0, '6.320'), (1, '6.470')] -[2023-10-09 09:24:31,079][23469] Updated weights for policy 1, policy_version 28441 (0.0007) -[2023-10-09 09:24:34,784][23469] Updated weights for policy 1, policy_version 28451 (0.0008) -[2023-10-09 09:24:34,849][23468] Updated weights for policy 0, policy_version 28323 (0.0007) -[2023-10-09 09:24:35,148][23469] Updated weights for policy 1, policy_version 28461 (0.0008) -[2023-10-09 09:24:35,231][23468] Updated weights for policy 0, policy_version 28333 (0.0008) -[2023-10-09 09:24:35,519][23469] Updated weights for policy 1, policy_version 28471 (0.0009) -[2023-10-09 09:24:35,605][23468] Updated weights for policy 0, policy_version 28343 (0.0008) -[2023-10-09 09:24:36,077][22500] Fps is (10 sec: 19660.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 58195968. Throughput: 0: 1766.5, 1: 1775.8. Samples: 14546204. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:24:36,079][22500] Avg episode reward: [(0, '6.580'), (1, '6.490')] -[2023-10-09 09:24:39,259][23468] Updated weights for policy 0, policy_version 28353 (0.0008) -[2023-10-09 09:24:39,266][23469] Updated weights for policy 1, policy_version 28481 (0.0007) -[2023-10-09 09:24:39,626][23468] Updated weights for policy 0, policy_version 28363 (0.0008) -[2023-10-09 09:24:39,633][23469] Updated weights for policy 1, policy_version 28491 (0.0007) -[2023-10-09 09:24:40,001][23469] Updated weights for policy 1, policy_version 28501 (0.0008) -[2023-10-09 09:24:40,003][23468] Updated weights for policy 0, policy_version 28373 (0.0007) -[2023-10-09 09:24:40,375][23469] Updated weights for policy 1, policy_version 28511 (0.0008) -[2023-10-09 09:24:40,377][23468] Updated weights for policy 0, policy_version 28383 (0.0007) -[2023-10-09 09:24:41,077][22500] Fps is (10 sec: 19660.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 58261504. Throughput: 0: 1803.5, 1: 1797.5. Samples: 14567998. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:24:41,078][22500] Avg episode reward: [(0, '6.740'), (1, '6.310')] -[2023-10-09 09:24:44,183][23468] Updated weights for policy 0, policy_version 28393 (0.0008) -[2023-10-09 09:24:44,259][23469] Updated weights for policy 1, policy_version 28521 (0.0009) -[2023-10-09 09:24:44,550][23468] Updated weights for policy 0, policy_version 28403 (0.0010) -[2023-10-09 09:24:44,637][23469] Updated weights for policy 1, policy_version 28531 (0.0009) -[2023-10-09 09:24:44,920][23468] Updated weights for policy 0, policy_version 28413 (0.0008) -[2023-10-09 09:24:45,008][23469] Updated weights for policy 1, policy_version 28541 (0.0007) -[2023-10-09 09:24:46,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 58327040. Throughput: 0: 1773.2, 1: 1776.8. Samples: 14587936. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:24:46,079][22500] Avg episode reward: [(0, '6.820'), (1, '6.290')] -[2023-10-09 09:24:48,689][23468] Updated weights for policy 0, policy_version 28423 (0.0008) -[2023-10-09 09:24:48,762][23469] Updated weights for policy 1, policy_version 28551 (0.0008) -[2023-10-09 09:24:49,063][23468] Updated weights for policy 0, policy_version 28433 (0.0007) -[2023-10-09 09:24:49,143][23469] Updated weights for policy 1, policy_version 28561 (0.0009) -[2023-10-09 09:24:49,440][23468] Updated weights for policy 0, policy_version 28443 (0.0007) -[2023-10-09 09:24:49,513][23469] Updated weights for policy 1, policy_version 28571 (0.0008) -[2023-10-09 09:24:51,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 58392576. Throughput: 0: 1798.3, 1: 1798.9. Samples: 14600180. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-09 09:24:51,078][22500] Avg episode reward: [(0, '7.030'), (1, '6.300')] -[2023-10-09 09:24:53,183][23469] Updated weights for policy 1, policy_version 28581 (0.0007) -[2023-10-09 09:24:53,205][23468] Updated weights for policy 0, policy_version 28453 (0.0009) -[2023-10-09 09:24:53,548][23469] Updated weights for policy 1, policy_version 28591 (0.0008) -[2023-10-09 09:24:53,587][23468] Updated weights for policy 0, policy_version 28463 (0.0008) -[2023-10-09 09:24:53,919][23469] Updated weights for policy 1, policy_version 28601 (0.0008) -[2023-10-09 09:24:53,949][23468] Updated weights for policy 0, policy_version 28473 (0.0008) -[2023-10-09 09:24:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 58458112. Throughput: 0: 1772.1, 1: 1773.6. Samples: 14619772. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-09 09:24:56,078][22500] Avg episode reward: [(0, '7.050'), (1, '6.730')] -[2023-10-09 09:24:57,736][23469] Updated weights for policy 1, policy_version 28611 (0.0007) -[2023-10-09 09:24:57,808][23468] Updated weights for policy 0, policy_version 28483 (0.0010) -[2023-10-09 09:24:58,104][23469] Updated weights for policy 1, policy_version 28621 (0.0008) -[2023-10-09 09:24:58,180][23468] Updated weights for policy 0, policy_version 28493 (0.0008) -[2023-10-09 09:24:58,474][23469] Updated weights for policy 1, policy_version 28631 (0.0007) -[2023-10-09 09:24:58,545][23468] Updated weights for policy 0, policy_version 28503 (0.0007) -[2023-10-09 09:25:01,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 58523648. Throughput: 0: 1772.3, 1: 1771.7. Samples: 14641712. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-09 09:25:01,079][22500] Avg episode reward: [(0, '7.040'), (1, '6.500')] -[2023-10-09 09:25:02,311][23468] Updated weights for policy 0, policy_version 28513 (0.0008) -[2023-10-09 09:25:02,357][23469] Updated weights for policy 1, policy_version 28641 (0.0007) -[2023-10-09 09:25:02,683][23468] Updated weights for policy 0, policy_version 28523 (0.0008) -[2023-10-09 09:25:02,767][23469] Updated weights for policy 1, policy_version 28651 (0.0010) -[2023-10-09 09:25:03,050][23468] Updated weights for policy 0, policy_version 28533 (0.0009) -[2023-10-09 09:25:03,136][23469] Updated weights for policy 1, policy_version 28661 (0.0007) -[2023-10-09 09:25:03,429][23468] Updated weights for policy 0, policy_version 28543 (0.0009) -[2023-10-09 09:25:03,512][23469] Updated weights for policy 1, policy_version 28671 (0.0009) -[2023-10-09 09:25:06,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 58589184. Throughput: 0: 1779.3, 1: 1770.0. Samples: 14651422. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-09 09:25:06,078][22500] Avg episode reward: [(0, '7.050'), (1, '6.210')] -[2023-10-09 09:25:07,180][23468] Updated weights for policy 0, policy_version 28553 (0.0007) -[2023-10-09 09:25:07,260][23469] Updated weights for policy 1, policy_version 28681 (0.0008) -[2023-10-09 09:25:07,553][23468] Updated weights for policy 0, policy_version 28563 (0.0009) -[2023-10-09 09:25:07,641][23469] Updated weights for policy 1, policy_version 28691 (0.0008) -[2023-10-09 09:25:07,928][23468] Updated weights for policy 0, policy_version 28573 (0.0008) -[2023-10-09 09:25:08,004][23469] Updated weights for policy 1, policy_version 28701 (0.0009) -[2023-10-09 09:25:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 58654720. Throughput: 0: 1773.3, 1: 1778.8. Samples: 14673838. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-09 09:25:11,078][22500] Avg episode reward: [(0, '7.110'), (1, '6.480')] -[2023-10-09 09:25:11,702][23469] Updated weights for policy 1, policy_version 28711 (0.0008) -[2023-10-09 09:25:11,795][23468] Updated weights for policy 0, policy_version 28583 (0.0008) -[2023-10-09 09:25:12,065][23469] Updated weights for policy 1, policy_version 28721 (0.0008) -[2023-10-09 09:25:12,169][23468] Updated weights for policy 0, policy_version 28593 (0.0007) -[2023-10-09 09:25:12,437][23469] Updated weights for policy 1, policy_version 28731 (0.0008) -[2023-10-09 09:25:12,539][23468] Updated weights for policy 0, policy_version 28603 (0.0007) -[2023-10-09 09:25:16,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 58720256. Throughput: 0: 1774.3, 1: 1793.4. Samples: 14695980. Policy #0 lag: (min: 17.0, avg: 22.1, max: 49.0) -[2023-10-09 09:25:16,079][22500] Avg episode reward: [(0, '7.110'), (1, '6.620')] -[2023-10-09 09:25:16,285][23469] Updated weights for policy 1, policy_version 28741 (0.0008) -[2023-10-09 09:25:16,333][23468] Updated weights for policy 0, policy_version 28613 (0.0008) -[2023-10-09 09:25:16,658][23469] Updated weights for policy 1, policy_version 28751 (0.0007) -[2023-10-09 09:25:16,700][23468] Updated weights for policy 0, policy_version 28623 (0.0009) -[2023-10-09 09:25:17,024][23469] Updated weights for policy 1, policy_version 28761 (0.0008) -[2023-10-09 09:25:17,075][23468] Updated weights for policy 0, policy_version 28633 (0.0011) -[2023-10-09 09:25:20,716][23469] Updated weights for policy 1, policy_version 28771 (0.0009) -[2023-10-09 09:25:21,040][23468] Updated weights for policy 0, policy_version 28643 (0.0009) -[2023-10-09 09:25:21,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 58785792. Throughput: 0: 1766.6, 1: 1776.2. Samples: 14705630. Policy #0 lag: (min: 17.0, avg: 22.1, max: 49.0) -[2023-10-09 09:25:21,078][22500] Avg episode reward: [(0, '6.960'), (1, '6.610')] -[2023-10-09 09:25:21,078][23469] Updated weights for policy 1, policy_version 28781 (0.0009) -[2023-10-09 09:25:21,412][23468] Updated weights for policy 0, policy_version 28653 (0.0008) -[2023-10-09 09:25:21,443][23469] Updated weights for policy 1, policy_version 28791 (0.0010) -[2023-10-09 09:25:21,786][23468] Updated weights for policy 0, policy_version 28663 (0.0007) -[2023-10-09 09:25:25,246][23469] Updated weights for policy 1, policy_version 28801 (0.0009) -[2023-10-09 09:25:25,621][23469] Updated weights for policy 1, policy_version 28811 (0.0009) -[2023-10-09 09:25:25,646][23468] Updated weights for policy 0, policy_version 28673 (0.0008) -[2023-10-09 09:25:25,990][23469] Updated weights for policy 1, policy_version 28821 (0.0009) -[2023-10-09 09:25:26,016][23468] Updated weights for policy 0, policy_version 28683 (0.0008) -[2023-10-09 09:25:26,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 58851328. Throughput: 0: 1761.3, 1: 1786.8. Samples: 14727664. Policy #0 lag: (min: 17.0, avg: 22.1, max: 49.0) -[2023-10-09 09:25:26,079][22500] Avg episode reward: [(0, '6.570'), (1, '6.460')] -[2023-10-09 09:25:26,358][23469] Updated weights for policy 1, policy_version 28831 (0.0007) -[2023-10-09 09:25:26,394][23468] Updated weights for policy 0, policy_version 28693 (0.0008) -[2023-10-09 09:25:26,769][23468] Updated weights for policy 0, policy_version 28703 (0.0008) -[2023-10-09 09:25:30,229][23469] Updated weights for policy 1, policy_version 28841 (0.0008) -[2023-10-09 09:25:30,603][23469] Updated weights for policy 1, policy_version 28851 (0.0008) -[2023-10-09 09:25:30,647][23468] Updated weights for policy 0, policy_version 28713 (0.0009) -[2023-10-09 09:25:30,976][23469] Updated weights for policy 1, policy_version 28861 (0.0008) -[2023-10-09 09:25:31,014][23468] Updated weights for policy 0, policy_version 28723 (0.0009) -[2023-10-09 09:25:31,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 58916864. Throughput: 0: 1786.9, 1: 1790.5. Samples: 14748916. Policy #0 lag: (min: 17.0, avg: 22.1, max: 49.0) -[2023-10-09 09:25:31,078][22500] Avg episode reward: [(0, '6.580'), (1, '6.670')] -[2023-10-09 09:25:31,389][23468] Updated weights for policy 0, policy_version 28733 (0.0008) -[2023-10-09 09:25:34,740][23469] Updated weights for policy 1, policy_version 28871 (0.0007) -[2023-10-09 09:25:35,082][23468] Updated weights for policy 0, policy_version 28743 (0.0008) -[2023-10-09 09:25:35,100][23469] Updated weights for policy 1, policy_version 28881 (0.0008) -[2023-10-09 09:25:35,466][23468] Updated weights for policy 0, policy_version 28753 (0.0009) -[2023-10-09 09:25:35,472][23469] Updated weights for policy 1, policy_version 28891 (0.0009) -[2023-10-09 09:25:35,845][23468] Updated weights for policy 0, policy_version 28763 (0.0009) -[2023-10-09 09:25:36,077][22500] Fps is (10 sec: 19661.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 59047936. Throughput: 0: 1754.6, 1: 1791.7. Samples: 14759766. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 09:25:36,078][22500] Avg episode reward: [(0, '7.140'), (1, '6.770')] -[2023-10-09 09:25:39,302][23469] Updated weights for policy 1, policy_version 28901 (0.0007) -[2023-10-09 09:25:39,671][23469] Updated weights for policy 1, policy_version 28911 (0.0008) -[2023-10-09 09:25:39,750][23468] Updated weights for policy 0, policy_version 28773 (0.0009) -[2023-10-09 09:25:40,038][23469] Updated weights for policy 1, policy_version 28921 (0.0007) -[2023-10-09 09:25:40,115][23468] Updated weights for policy 0, policy_version 28783 (0.0007) -[2023-10-09 09:25:40,488][23468] Updated weights for policy 0, policy_version 28793 (0.0010) -[2023-10-09 09:25:41,077][22500] Fps is (10 sec: 19660.8, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 59113472. Throughput: 0: 1789.4, 1: 1797.7. Samples: 14781190. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 09:25:41,078][22500] Avg episode reward: [(0, '7.500'), (1, '6.540')] -[2023-10-09 09:25:43,591][23469] Updated weights for policy 1, policy_version 28931 (0.0007) -[2023-10-09 09:25:43,955][23469] Updated weights for policy 1, policy_version 28941 (0.0008) -[2023-10-09 09:25:44,332][23469] Updated weights for policy 1, policy_version 28951 (0.0008) -[2023-10-09 09:25:44,355][23468] Updated weights for policy 0, policy_version 28803 (0.0011) -[2023-10-09 09:25:44,730][23468] Updated weights for policy 0, policy_version 28813 (0.0008) -[2023-10-09 09:25:45,102][23468] Updated weights for policy 0, policy_version 28823 (0.0007) -[2023-10-09 09:25:46,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 59179008. Throughput: 0: 1766.8, 1: 1791.3. Samples: 14801828. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 09:25:46,079][22500] Avg episode reward: [(0, '7.350'), (1, '6.480')] -[2023-10-09 09:25:48,233][23469] Updated weights for policy 1, policy_version 28961 (0.0007) -[2023-10-09 09:25:48,643][23469] Updated weights for policy 1, policy_version 28971 (0.0007) -[2023-10-09 09:25:48,871][23468] Updated weights for policy 0, policy_version 28833 (0.0009) -[2023-10-09 09:25:49,015][23469] Updated weights for policy 1, policy_version 28981 (0.0008) -[2023-10-09 09:25:49,233][23468] Updated weights for policy 0, policy_version 28843 (0.0007) -[2023-10-09 09:25:49,384][23469] Updated weights for policy 1, policy_version 28991 (0.0008) -[2023-10-09 09:25:49,601][23468] Updated weights for policy 0, policy_version 28853 (0.0009) -[2023-10-09 09:25:49,982][23468] Updated weights for policy 0, policy_version 28863 (0.0009) -[2023-10-09 09:25:51,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 59244544. Throughput: 0: 1782.1, 1: 1810.5. Samples: 14813088. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 09:25:51,078][22500] Avg episode reward: [(0, '7.070'), (1, '6.690')] -[2023-10-09 09:25:53,214][23469] Updated weights for policy 1, policy_version 29001 (0.0008) -[2023-10-09 09:25:53,593][23469] Updated weights for policy 1, policy_version 29011 (0.0009) -[2023-10-09 09:25:53,788][23468] Updated weights for policy 0, policy_version 28873 (0.0008) -[2023-10-09 09:25:53,965][23469] Updated weights for policy 1, policy_version 29021 (0.0009) -[2023-10-09 09:25:54,146][23468] Updated weights for policy 0, policy_version 28883 (0.0008) -[2023-10-09 09:25:54,519][23468] Updated weights for policy 0, policy_version 28893 (0.0012) -[2023-10-09 09:25:56,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 59310080. Throughput: 0: 1764.9, 1: 1781.5. Samples: 14833424. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 09:25:56,078][22500] Avg episode reward: [(0, '7.060'), (1, '6.680')] -[2023-10-09 09:25:57,579][23469] Updated weights for policy 1, policy_version 29031 (0.0008) -[2023-10-09 09:25:57,948][23469] Updated weights for policy 1, policy_version 29041 (0.0010) -[2023-10-09 09:25:58,158][23468] Updated weights for policy 0, policy_version 28903 (0.0009) -[2023-10-09 09:25:58,317][23469] Updated weights for policy 1, policy_version 29051 (0.0009) -[2023-10-09 09:25:58,530][23468] Updated weights for policy 0, policy_version 28913 (0.0008) -[2023-10-09 09:25:58,916][23468] Updated weights for policy 0, policy_version 28923 (0.0008) -[2023-10-09 09:26:01,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 59375616. Throughput: 0: 1761.5, 1: 1788.2. Samples: 14855716. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:26:01,078][22500] Avg episode reward: [(0, '7.120'), (1, '6.670')] -[2023-10-09 09:26:02,101][23469] Updated weights for policy 1, policy_version 29061 (0.0009) -[2023-10-09 09:26:02,479][23469] Updated weights for policy 1, policy_version 29071 (0.0008) -[2023-10-09 09:26:02,701][23468] Updated weights for policy 0, policy_version 28933 (0.0008) -[2023-10-09 09:26:02,847][23469] Updated weights for policy 1, policy_version 29081 (0.0007) -[2023-10-09 09:26:03,080][23468] Updated weights for policy 0, policy_version 28943 (0.0008) -[2023-10-09 09:26:03,447][23468] Updated weights for policy 0, policy_version 28953 (0.0009) -[2023-10-09 09:26:06,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 59441152. Throughput: 0: 1773.5, 1: 1789.6. Samples: 14865968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:26:06,078][22500] Avg episode reward: [(0, '7.240'), (1, '7.050')] -[2023-10-09 09:26:06,682][23469] Updated weights for policy 1, policy_version 29091 (0.0007) -[2023-10-09 09:26:07,045][23469] Updated weights for policy 1, policy_version 29101 (0.0009) -[2023-10-09 09:26:07,414][23469] Updated weights for policy 1, policy_version 29111 (0.0007) -[2023-10-09 09:26:07,556][23468] Updated weights for policy 0, policy_version 28963 (0.0008) -[2023-10-09 09:26:07,954][23468] Updated weights for policy 0, policy_version 28973 (0.0007) -[2023-10-09 09:26:08,321][23468] Updated weights for policy 0, policy_version 28983 (0.0007) -[2023-10-09 09:26:11,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 59506688. Throughput: 0: 1755.5, 1: 1788.3. Samples: 14887134. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:26:11,078][22500] Avg episode reward: [(0, '7.260'), (1, '7.020')] -[2023-10-09 09:26:11,169][23469] Updated weights for policy 1, policy_version 29121 (0.0008) -[2023-10-09 09:26:11,532][23469] Updated weights for policy 1, policy_version 29131 (0.0007) -[2023-10-09 09:26:11,901][23469] Updated weights for policy 1, policy_version 29141 (0.0008) -[2023-10-09 09:26:11,954][23468] Updated weights for policy 0, policy_version 28993 (0.0007) -[2023-10-09 09:26:12,272][23469] Updated weights for policy 1, policy_version 29151 (0.0007) -[2023-10-09 09:26:12,329][23468] Updated weights for policy 0, policy_version 29003 (0.0009) -[2023-10-09 09:26:12,707][23468] Updated weights for policy 0, policy_version 29013 (0.0012) -[2023-10-09 09:26:13,077][23468] Updated weights for policy 0, policy_version 29023 (0.0008) -[2023-10-09 09:26:15,988][23469] Updated weights for policy 1, policy_version 29161 (0.0007) -[2023-10-09 09:26:16,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 59572224. Throughput: 0: 1762.8, 1: 1809.2. Samples: 14909658. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:26:16,078][22500] Avg episode reward: [(0, '6.520'), (1, '7.010')] -[2023-10-09 09:26:16,087][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000029024_29720576.pth... -[2023-10-09 09:26:16,124][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000027360_28016640.pth -[2023-10-09 09:26:16,358][23469] Updated weights for policy 1, policy_version 29171 (0.0007) -[2023-10-09 09:26:16,720][23469] Updated weights for policy 1, policy_version 29181 (0.0008) -[2023-10-09 09:26:16,806][23468] Updated weights for policy 0, policy_version 29033 (0.0008) -[2023-10-09 09:26:16,830][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000029184_29884416.pth... -[2023-10-09 09:26:16,859][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000027488_28147712.pth -[2023-10-09 09:26:17,178][23468] Updated weights for policy 0, policy_version 29043 (0.0009) -[2023-10-09 09:26:17,552][23468] Updated weights for policy 0, policy_version 29053 (0.0008) -[2023-10-09 09:26:20,347][23469] Updated weights for policy 1, policy_version 29191 (0.0008) -[2023-10-09 09:26:20,710][23469] Updated weights for policy 1, policy_version 29201 (0.0007) -[2023-10-09 09:26:21,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 59637760. Throughput: 0: 1762.9, 1: 1788.7. Samples: 14919590. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:26:21,078][22500] Avg episode reward: [(0, '6.920'), (1, '6.590')] -[2023-10-09 09:26:21,082][23469] Updated weights for policy 1, policy_version 29211 (0.0008) -[2023-10-09 09:26:21,337][23468] Updated weights for policy 0, policy_version 29063 (0.0008) -[2023-10-09 09:26:21,714][23468] Updated weights for policy 0, policy_version 29073 (0.0008) -[2023-10-09 09:26:22,083][23468] Updated weights for policy 0, policy_version 29083 (0.0008) -[2023-10-09 09:26:24,886][23469] Updated weights for policy 1, policy_version 29221 (0.0010) -[2023-10-09 09:26:25,263][23469] Updated weights for policy 1, policy_version 29231 (0.0008) -[2023-10-09 09:26:25,623][23469] Updated weights for policy 1, policy_version 29241 (0.0008) -[2023-10-09 09:26:25,796][23468] Updated weights for policy 0, policy_version 29093 (0.0007) -[2023-10-09 09:26:26,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 59736064. Throughput: 0: 1764.5, 1: 1802.5. Samples: 14941706. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-09 09:26:26,078][22500] Avg episode reward: [(0, '7.030'), (1, '6.660')] -[2023-10-09 09:26:26,173][23468] Updated weights for policy 0, policy_version 29103 (0.0008) -[2023-10-09 09:26:26,550][23468] Updated weights for policy 0, policy_version 29113 (0.0007) -[2023-10-09 09:26:29,420][23469] Updated weights for policy 1, policy_version 29251 (0.0008) -[2023-10-09 09:26:29,799][23469] Updated weights for policy 1, policy_version 29261 (0.0009) -[2023-10-09 09:26:30,163][23469] Updated weights for policy 1, policy_version 29271 (0.0008) -[2023-10-09 09:26:30,194][23468] Updated weights for policy 0, policy_version 29123 (0.0007) -[2023-10-09 09:26:30,569][23468] Updated weights for policy 0, policy_version 29133 (0.0007) -[2023-10-09 09:26:30,943][23468] Updated weights for policy 0, policy_version 29143 (0.0010) -[2023-10-09 09:26:31,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 59801600. Throughput: 0: 1790.7, 1: 1780.4. Samples: 14962526. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-09 09:26:31,078][22500] Avg episode reward: [(0, '7.340'), (1, '7.130')] -[2023-10-09 09:26:34,028][23469] Updated weights for policy 1, policy_version 29281 (0.0009) -[2023-10-09 09:26:34,408][23469] Updated weights for policy 1, policy_version 29291 (0.0008) -[2023-10-09 09:26:34,750][23468] Updated weights for policy 0, policy_version 29153 (0.0010) -[2023-10-09 09:26:34,782][23469] Updated weights for policy 1, policy_version 29301 (0.0007) -[2023-10-09 09:26:35,126][23468] Updated weights for policy 0, policy_version 29163 (0.0007) -[2023-10-09 09:26:35,156][23469] Updated weights for policy 1, policy_version 29311 (0.0007) -[2023-10-09 09:26:35,501][23468] Updated weights for policy 0, policy_version 29173 (0.0009) -[2023-10-09 09:26:35,867][23468] Updated weights for policy 0, policy_version 29183 (0.0009) -[2023-10-09 09:26:36,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 59899904. Throughput: 0: 1776.3, 1: 1799.0. Samples: 14973976. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-09 09:26:36,078][22500] Avg episode reward: [(0, '7.060'), (1, '7.370')] -[2023-10-09 09:26:36,079][23343] Saving new best policy, reward=7.370! -[2023-10-09 09:26:38,904][23469] Updated weights for policy 1, policy_version 29321 (0.0010) -[2023-10-09 09:26:39,278][23469] Updated weights for policy 1, policy_version 29331 (0.0007) -[2023-10-09 09:26:39,649][23469] Updated weights for policy 1, policy_version 29341 (0.0007) -[2023-10-09 09:26:39,679][23468] Updated weights for policy 0, policy_version 29193 (0.0008) -[2023-10-09 09:26:40,058][23468] Updated weights for policy 0, policy_version 29203 (0.0010) -[2023-10-09 09:26:40,426][23468] Updated weights for policy 0, policy_version 29213 (0.0009) -[2023-10-09 09:26:41,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 59965440. Throughput: 0: 1798.0, 1: 1789.6. Samples: 14994866. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-09 09:26:41,078][22500] Avg episode reward: [(0, '6.980'), (1, '7.060')] -[2023-10-09 09:26:43,326][23469] Updated weights for policy 1, policy_version 29351 (0.0007) -[2023-10-09 09:26:43,706][23469] Updated weights for policy 1, policy_version 29361 (0.0011) -[2023-10-09 09:26:44,075][23469] Updated weights for policy 1, policy_version 29371 (0.0009) -[2023-10-09 09:26:44,207][23468] Updated weights for policy 0, policy_version 29223 (0.0008) -[2023-10-09 09:26:44,585][23468] Updated weights for policy 0, policy_version 29233 (0.0007) -[2023-10-09 09:26:44,966][23468] Updated weights for policy 0, policy_version 29243 (0.0008) -[2023-10-09 09:26:46,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 60030976. Throughput: 0: 1768.8, 1: 1789.1. Samples: 15015822. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-09 09:26:46,079][22500] Avg episode reward: [(0, '7.510'), (1, '6.190')] -[2023-10-09 09:26:47,719][23469] Updated weights for policy 1, policy_version 29381 (0.0009) -[2023-10-09 09:26:48,088][23469] Updated weights for policy 1, policy_version 29391 (0.0008) -[2023-10-09 09:26:48,454][23469] Updated weights for policy 1, policy_version 29401 (0.0007) -[2023-10-09 09:26:48,756][23468] Updated weights for policy 0, policy_version 29253 (0.0008) -[2023-10-09 09:26:49,134][23468] Updated weights for policy 0, policy_version 29263 (0.0007) -[2023-10-09 09:26:49,505][23468] Updated weights for policy 0, policy_version 29273 (0.0007) -[2023-10-09 09:26:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 60096512. Throughput: 0: 1787.9, 1: 1790.7. Samples: 15027004. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-09 09:26:51,078][22500] Avg episode reward: [(0, '7.740'), (1, '6.520')] -[2023-10-09 09:26:52,210][23469] Updated weights for policy 1, policy_version 29411 (0.0008) -[2023-10-09 09:26:52,566][23469] Updated weights for policy 1, policy_version 29421 (0.0008) -[2023-10-09 09:26:52,930][23469] Updated weights for policy 1, policy_version 29431 (0.0008) -[2023-10-09 09:26:53,415][23468] Updated weights for policy 0, policy_version 29283 (0.0008) -[2023-10-09 09:26:53,788][23468] Updated weights for policy 0, policy_version 29293 (0.0008) -[2023-10-09 09:26:54,161][23468] Updated weights for policy 0, policy_version 29303 (0.0009) -[2023-10-09 09:26:56,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 60162048. Throughput: 0: 1785.5, 1: 1792.0. Samples: 15048122. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-09 09:26:56,078][22500] Avg episode reward: [(0, '7.050'), (1, '6.670')] -[2023-10-09 09:26:56,795][23469] Updated weights for policy 1, policy_version 29441 (0.0008) -[2023-10-09 09:26:57,163][23469] Updated weights for policy 1, policy_version 29451 (0.0009) -[2023-10-09 09:26:57,530][23469] Updated weights for policy 1, policy_version 29461 (0.0007) -[2023-10-09 09:26:57,826][23468] Updated weights for policy 0, policy_version 29313 (0.0009) -[2023-10-09 09:26:57,910][23469] Updated weights for policy 1, policy_version 29471 (0.0008) -[2023-10-09 09:26:58,233][23468] Updated weights for policy 0, policy_version 29323 (0.0007) -[2023-10-09 09:26:58,607][23468] Updated weights for policy 0, policy_version 29333 (0.0008) -[2023-10-09 09:26:58,978][23468] Updated weights for policy 0, policy_version 29343 (0.0008) -[2023-10-09 09:27:01,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 60227584. Throughput: 0: 1773.5, 1: 1786.9. Samples: 15069878. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-09 09:27:01,079][22500] Avg episode reward: [(0, '7.160'), (1, '6.770')] -[2023-10-09 09:27:01,823][23469] Updated weights for policy 1, policy_version 29481 (0.0009) -[2023-10-09 09:27:02,199][23469] Updated weights for policy 1, policy_version 29491 (0.0008) -[2023-10-09 09:27:02,559][23469] Updated weights for policy 1, policy_version 29501 (0.0008) -[2023-10-09 09:27:02,670][23468] Updated weights for policy 0, policy_version 29353 (0.0010) -[2023-10-09 09:27:03,043][23468] Updated weights for policy 0, policy_version 29363 (0.0009) -[2023-10-09 09:27:03,417][23468] Updated weights for policy 0, policy_version 29373 (0.0008) -[2023-10-09 09:27:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 60293120. Throughput: 0: 1782.4, 1: 1783.7. Samples: 15080062. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-09 09:27:06,078][22500] Avg episode reward: [(0, '6.970'), (1, '6.620')] -[2023-10-09 09:27:06,244][23469] Updated weights for policy 1, policy_version 29511 (0.0007) -[2023-10-09 09:27:06,623][23469] Updated weights for policy 1, policy_version 29521 (0.0007) -[2023-10-09 09:27:06,995][23469] Updated weights for policy 1, policy_version 29531 (0.0009) -[2023-10-09 09:27:07,222][23468] Updated weights for policy 0, policy_version 29383 (0.0008) -[2023-10-09 09:27:07,588][23468] Updated weights for policy 0, policy_version 29393 (0.0010) -[2023-10-09 09:27:07,960][23468] Updated weights for policy 0, policy_version 29403 (0.0008) -[2023-10-09 09:27:10,780][23469] Updated weights for policy 1, policy_version 29541 (0.0008) -[2023-10-09 09:27:11,078][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 60358656. Throughput: 0: 1775.1, 1: 1789.5. Samples: 15102116. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-09 09:27:11,079][22500] Avg episode reward: [(0, '7.190'), (1, '6.590')] -[2023-10-09 09:27:11,149][23469] Updated weights for policy 1, policy_version 29551 (0.0009) -[2023-10-09 09:27:11,525][23469] Updated weights for policy 1, policy_version 29561 (0.0007) -[2023-10-09 09:27:11,862][23468] Updated weights for policy 0, policy_version 29413 (0.0009) -[2023-10-09 09:27:12,232][23468] Updated weights for policy 0, policy_version 29423 (0.0009) -[2023-10-09 09:27:12,610][23468] Updated weights for policy 0, policy_version 29433 (0.0007) -[2023-10-09 09:27:15,181][23469] Updated weights for policy 1, policy_version 29571 (0.0009) -[2023-10-09 09:27:15,546][23469] Updated weights for policy 1, policy_version 29581 (0.0010) -[2023-10-09 09:27:15,928][23469] Updated weights for policy 1, policy_version 29591 (0.0009) -[2023-10-09 09:27:16,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 60424192. Throughput: 0: 1771.8, 1: 1802.7. Samples: 15123378. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-09 09:27:16,078][22500] Avg episode reward: [(0, '7.220'), (1, '6.600')] -[2023-10-09 09:27:16,297][23468] Updated weights for policy 0, policy_version 29443 (0.0007) -[2023-10-09 09:27:16,672][23468] Updated weights for policy 0, policy_version 29453 (0.0007) -[2023-10-09 09:27:17,044][23468] Updated weights for policy 0, policy_version 29463 (0.0007) -[2023-10-09 09:27:19,705][23469] Updated weights for policy 1, policy_version 29601 (0.0008) -[2023-10-09 09:27:20,149][23469] Updated weights for policy 1, policy_version 29611 (0.0009) -[2023-10-09 09:27:20,515][23469] Updated weights for policy 1, policy_version 29621 (0.0009) -[2023-10-09 09:27:20,860][23468] Updated weights for policy 0, policy_version 29473 (0.0009) -[2023-10-09 09:27:20,891][23469] Updated weights for policy 1, policy_version 29631 (0.0008) -[2023-10-09 09:27:21,077][22500] Fps is (10 sec: 16384.5, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 60522496. Throughput: 0: 1767.2, 1: 1788.2. Samples: 15133970. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-09 09:27:21,078][22500] Avg episode reward: [(0, '7.450'), (1, '6.750')] -[2023-10-09 09:27:21,237][23468] Updated weights for policy 0, policy_version 29483 (0.0010) -[2023-10-09 09:27:21,623][23468] Updated weights for policy 0, policy_version 29493 (0.0011) -[2023-10-09 09:27:21,994][23468] Updated weights for policy 0, policy_version 29503 (0.0008) -[2023-10-09 09:27:24,635][23469] Updated weights for policy 1, policy_version 29641 (0.0008) -[2023-10-09 09:27:25,016][23469] Updated weights for policy 1, policy_version 29651 (0.0011) -[2023-10-09 09:27:25,386][23469] Updated weights for policy 1, policy_version 29661 (0.0007) -[2023-10-09 09:27:25,693][23468] Updated weights for policy 0, policy_version 29513 (0.0008) -[2023-10-09 09:27:26,071][23468] Updated weights for policy 0, policy_version 29523 (0.0009) -[2023-10-09 09:27:26,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 60588032. Throughput: 0: 1771.7, 1: 1799.3. Samples: 15155564. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-09 09:27:26,078][22500] Avg episode reward: [(0, '7.110'), (1, '6.650')] -[2023-10-09 09:27:26,446][23468] Updated weights for policy 0, policy_version 29533 (0.0009) -[2023-10-09 09:27:29,024][23469] Updated weights for policy 1, policy_version 29671 (0.0008) -[2023-10-09 09:27:29,387][23469] Updated weights for policy 1, policy_version 29681 (0.0007) -[2023-10-09 09:27:29,760][23469] Updated weights for policy 1, policy_version 29691 (0.0008) -[2023-10-09 09:27:30,210][23468] Updated weights for policy 0, policy_version 29543 (0.0008) -[2023-10-09 09:27:30,583][23468] Updated weights for policy 0, policy_version 29553 (0.0007) -[2023-10-09 09:27:30,958][23468] Updated weights for policy 0, policy_version 29563 (0.0010) -[2023-10-09 09:27:31,078][22500] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 60653568. Throughput: 0: 1794.8, 1: 1784.5. Samples: 15176892. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-09 09:27:31,079][22500] Avg episode reward: [(0, '7.080'), (1, '6.750')] -[2023-10-09 09:27:33,561][23469] Updated weights for policy 1, policy_version 29701 (0.0008) -[2023-10-09 09:27:33,931][23469] Updated weights for policy 1, policy_version 29711 (0.0008) -[2023-10-09 09:27:34,300][23469] Updated weights for policy 1, policy_version 29721 (0.0010) -[2023-10-09 09:27:34,595][23468] Updated weights for policy 0, policy_version 29573 (0.0008) -[2023-10-09 09:27:34,966][23468] Updated weights for policy 0, policy_version 29583 (0.0011) -[2023-10-09 09:27:35,345][23468] Updated weights for policy 0, policy_version 29593 (0.0010) -[2023-10-09 09:27:36,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 60751872. Throughput: 0: 1776.3, 1: 1799.8. Samples: 15187926. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-09 09:27:36,078][22500] Avg episode reward: [(0, '7.140'), (1, '7.140')] -[2023-10-09 09:27:37,998][23469] Updated weights for policy 1, policy_version 29731 (0.0010) -[2023-10-09 09:27:38,376][23469] Updated weights for policy 1, policy_version 29741 (0.0010) -[2023-10-09 09:27:38,745][23469] Updated weights for policy 1, policy_version 29751 (0.0009) -[2023-10-09 09:27:39,074][23468] Updated weights for policy 0, policy_version 29603 (0.0008) -[2023-10-09 09:27:39,435][23468] Updated weights for policy 0, policy_version 29613 (0.0008) -[2023-10-09 09:27:39,814][23468] Updated weights for policy 0, policy_version 29623 (0.0009) -[2023-10-09 09:27:41,078][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 60817408. Throughput: 0: 1795.9, 1: 1779.1. Samples: 15208996. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-09 09:27:41,079][22500] Avg episode reward: [(0, '6.820'), (1, '7.450')] -[2023-10-09 09:27:41,080][23343] Saving new best policy, reward=7.450! -[2023-10-09 09:27:42,548][23469] Updated weights for policy 1, policy_version 29761 (0.0008) -[2023-10-09 09:27:42,913][23469] Updated weights for policy 1, policy_version 29771 (0.0007) -[2023-10-09 09:27:43,289][23469] Updated weights for policy 1, policy_version 29781 (0.0007) -[2023-10-09 09:27:43,594][23468] Updated weights for policy 0, policy_version 29633 (0.0009) -[2023-10-09 09:27:43,650][23469] Updated weights for policy 1, policy_version 29791 (0.0007) -[2023-10-09 09:27:44,005][23468] Updated weights for policy 0, policy_version 29643 (0.0010) -[2023-10-09 09:27:44,367][23468] Updated weights for policy 0, policy_version 29653 (0.0010) -[2023-10-09 09:27:44,737][23468] Updated weights for policy 0, policy_version 29663 (0.0009) -[2023-10-09 09:27:46,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 60882944. Throughput: 0: 1781.7, 1: 1782.6. Samples: 15230270. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-09 09:27:46,079][22500] Avg episode reward: [(0, '6.930'), (1, '7.100')] -[2023-10-09 09:27:47,560][23469] Updated weights for policy 1, policy_version 29801 (0.0011) -[2023-10-09 09:27:47,924][23469] Updated weights for policy 1, policy_version 29811 (0.0010) -[2023-10-09 09:27:48,298][23469] Updated weights for policy 1, policy_version 29821 (0.0008) -[2023-10-09 09:27:48,649][23468] Updated weights for policy 0, policy_version 29673 (0.0008) -[2023-10-09 09:27:49,031][23468] Updated weights for policy 0, policy_version 29683 (0.0007) -[2023-10-09 09:27:49,409][23468] Updated weights for policy 0, policy_version 29693 (0.0009) -[2023-10-09 09:27:51,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 60948480. Throughput: 0: 1800.9, 1: 1779.6. Samples: 15241186. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-09 09:27:51,078][22500] Avg episode reward: [(0, '7.050'), (1, '6.410')] -[2023-10-09 09:27:52,112][23469] Updated weights for policy 1, policy_version 29831 (0.0008) -[2023-10-09 09:27:52,483][23469] Updated weights for policy 1, policy_version 29841 (0.0008) -[2023-10-09 09:27:52,859][23469] Updated weights for policy 1, policy_version 29851 (0.0010) -[2023-10-09 09:27:53,257][23468] Updated weights for policy 0, policy_version 29703 (0.0009) -[2023-10-09 09:27:53,638][23468] Updated weights for policy 0, policy_version 29713 (0.0008) -[2023-10-09 09:27:54,003][23468] Updated weights for policy 0, policy_version 29723 (0.0008) -[2023-10-09 09:27:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 61014016. Throughput: 0: 1770.5, 1: 1781.3. Samples: 15261948. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-09 09:27:56,078][22500] Avg episode reward: [(0, '7.140'), (1, '6.150')] -[2023-10-09 09:27:56,540][23469] Updated weights for policy 1, policy_version 29861 (0.0009) -[2023-10-09 09:27:56,918][23469] Updated weights for policy 1, policy_version 29871 (0.0010) -[2023-10-09 09:27:57,284][23469] Updated weights for policy 1, policy_version 29881 (0.0008) -[2023-10-09 09:27:57,828][23468] Updated weights for policy 0, policy_version 29733 (0.0009) -[2023-10-09 09:27:58,198][23468] Updated weights for policy 0, policy_version 29743 (0.0011) -[2023-10-09 09:27:58,573][23468] Updated weights for policy 0, policy_version 29753 (0.0011) -[2023-10-09 09:28:00,985][23469] Updated weights for policy 1, policy_version 29891 (0.0011) -[2023-10-09 09:28:01,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 61079552. Throughput: 0: 1769.4, 1: 1799.9. Samples: 15283998. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-09 09:28:01,079][22500] Avg episode reward: [(0, '6.930'), (1, '6.420')] -[2023-10-09 09:28:01,356][23469] Updated weights for policy 1, policy_version 29901 (0.0010) -[2023-10-09 09:28:01,732][23469] Updated weights for policy 1, policy_version 29911 (0.0010) -[2023-10-09 09:28:02,396][23468] Updated weights for policy 0, policy_version 29763 (0.0008) -[2023-10-09 09:28:02,770][23468] Updated weights for policy 0, policy_version 29773 (0.0007) -[2023-10-09 09:28:03,145][23468] Updated weights for policy 0, policy_version 29783 (0.0008) -[2023-10-09 09:28:05,571][23469] Updated weights for policy 1, policy_version 29921 (0.0010) -[2023-10-09 09:28:06,010][23469] Updated weights for policy 1, policy_version 29931 (0.0008) -[2023-10-09 09:28:06,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 61145088. Throughput: 0: 1776.1, 1: 1781.5. Samples: 15294060. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-09 09:28:06,078][22500] Avg episode reward: [(0, '6.780'), (1, '6.790')] -[2023-10-09 09:28:06,385][23469] Updated weights for policy 1, policy_version 29941 (0.0009) -[2023-10-09 09:28:06,752][23469] Updated weights for policy 1, policy_version 29951 (0.0007) -[2023-10-09 09:28:06,973][23468] Updated weights for policy 0, policy_version 29793 (0.0011) -[2023-10-09 09:28:07,351][23468] Updated weights for policy 0, policy_version 29803 (0.0008) -[2023-10-09 09:28:07,721][23468] Updated weights for policy 0, policy_version 29813 (0.0008) -[2023-10-09 09:28:08,098][23468] Updated weights for policy 0, policy_version 29823 (0.0010) -[2023-10-09 09:28:10,443][23469] Updated weights for policy 1, policy_version 29961 (0.0008) -[2023-10-09 09:28:10,819][23469] Updated weights for policy 1, policy_version 29971 (0.0009) -[2023-10-09 09:28:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 61210624. Throughput: 0: 1761.2, 1: 1798.5. Samples: 15315754. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-09 09:28:11,078][22500] Avg episode reward: [(0, '7.190'), (1, '6.790')] -[2023-10-09 09:28:11,185][23469] Updated weights for policy 1, policy_version 29981 (0.0008) -[2023-10-09 09:28:12,045][23468] Updated weights for policy 0, policy_version 29833 (0.0010) -[2023-10-09 09:28:12,419][23468] Updated weights for policy 0, policy_version 29843 (0.0009) -[2023-10-09 09:28:12,776][23468] Updated weights for policy 0, policy_version 29853 (0.0008) -[2023-10-09 09:28:14,932][23469] Updated weights for policy 1, policy_version 29991 (0.0008) -[2023-10-09 09:28:15,301][23469] Updated weights for policy 1, policy_version 30001 (0.0010) -[2023-10-09 09:28:15,672][23469] Updated weights for policy 1, policy_version 30011 (0.0008) -[2023-10-09 09:28:16,078][22500] Fps is (10 sec: 16383.5, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 61308928. Throughput: 0: 1767.2, 1: 1782.1. Samples: 15336608. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-09 09:28:16,079][22500] Avg episode reward: [(0, '6.750'), (1, '6.550')] -[2023-10-09 09:28:16,088][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000030016_30736384.pth... -[2023-10-09 09:28:16,088][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000029856_30572544.pth... -[2023-10-09 09:28:16,117][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000028320_28999680.pth -[2023-10-09 09:28:16,131][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000028192_28868608.pth -[2023-10-09 09:28:16,532][23468] Updated weights for policy 0, policy_version 29863 (0.0008) -[2023-10-09 09:28:16,909][23468] Updated weights for policy 0, policy_version 29873 (0.0009) -[2023-10-09 09:28:17,274][23468] Updated weights for policy 0, policy_version 29883 (0.0008) -[2023-10-09 09:28:19,360][23469] Updated weights for policy 1, policy_version 30021 (0.0008) -[2023-10-09 09:28:19,723][23469] Updated weights for policy 1, policy_version 30031 (0.0011) -[2023-10-09 09:28:20,099][23469] Updated weights for policy 1, policy_version 30041 (0.0008) -[2023-10-09 09:28:21,013][23468] Updated weights for policy 0, policy_version 29893 (0.0009) -[2023-10-09 09:28:21,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 61374464. Throughput: 0: 1756.8, 1: 1797.1. Samples: 15347850. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-09 09:28:21,078][22500] Avg episode reward: [(0, '7.250'), (1, '6.560')] -[2023-10-09 09:28:21,385][23468] Updated weights for policy 0, policy_version 29903 (0.0009) -[2023-10-09 09:28:21,760][23468] Updated weights for policy 0, policy_version 29913 (0.0008) -[2023-10-09 09:28:23,783][23469] Updated weights for policy 1, policy_version 30051 (0.0011) -[2023-10-09 09:28:24,145][23469] Updated weights for policy 1, policy_version 30061 (0.0010) -[2023-10-09 09:28:24,517][23469] Updated weights for policy 1, policy_version 30071 (0.0009) -[2023-10-09 09:28:25,672][23468] Updated weights for policy 0, policy_version 29923 (0.0009) -[2023-10-09 09:28:26,042][23468] Updated weights for policy 0, policy_version 29933 (0.0007) -[2023-10-09 09:28:26,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 61440000. Throughput: 0: 1762.4, 1: 1788.5. Samples: 15368784. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-09 09:28:26,078][22500] Avg episode reward: [(0, '7.320'), (1, '6.510')] -[2023-10-09 09:28:26,412][23468] Updated weights for policy 0, policy_version 29943 (0.0008) -[2023-10-09 09:28:28,320][23469] Updated weights for policy 1, policy_version 30081 (0.0008) -[2023-10-09 09:28:28,688][23469] Updated weights for policy 1, policy_version 30091 (0.0007) -[2023-10-09 09:28:29,061][23469] Updated weights for policy 1, policy_version 30101 (0.0010) -[2023-10-09 09:28:29,431][23469] Updated weights for policy 1, policy_version 30111 (0.0008) -[2023-10-09 09:28:30,262][23468] Updated weights for policy 0, policy_version 29953 (0.0009) -[2023-10-09 09:28:30,668][23468] Updated weights for policy 0, policy_version 29963 (0.0008) -[2023-10-09 09:28:31,041][23468] Updated weights for policy 0, policy_version 29973 (0.0009) -[2023-10-09 09:28:31,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 61505536. Throughput: 0: 1785.2, 1: 1781.8. Samples: 15390784. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-09 09:28:31,078][22500] Avg episode reward: [(0, '7.520'), (1, '6.500')] -[2023-10-09 09:28:31,423][23468] Updated weights for policy 0, policy_version 29983 (0.0008) -[2023-10-09 09:28:33,211][23469] Updated weights for policy 1, policy_version 30121 (0.0009) -[2023-10-09 09:28:33,574][23469] Updated weights for policy 1, policy_version 30131 (0.0009) -[2023-10-09 09:28:33,946][23469] Updated weights for policy 1, policy_version 30141 (0.0010) -[2023-10-09 09:28:35,190][23468] Updated weights for policy 0, policy_version 29993 (0.0008) -[2023-10-09 09:28:35,563][23468] Updated weights for policy 0, policy_version 30003 (0.0008) -[2023-10-09 09:28:35,931][23468] Updated weights for policy 0, policy_version 30013 (0.0007) -[2023-10-09 09:28:36,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 61603840. Throughput: 0: 1760.5, 1: 1790.2. Samples: 15400966. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-09 09:28:36,078][22500] Avg episode reward: [(0, '8.050'), (1, '6.680')] -[2023-10-09 09:28:36,079][23265] Saving new best policy, reward=8.050! -[2023-10-09 09:28:37,654][23469] Updated weights for policy 1, policy_version 30151 (0.0009) -[2023-10-09 09:28:38,016][23469] Updated weights for policy 1, policy_version 30161 (0.0007) -[2023-10-09 09:28:38,391][23469] Updated weights for policy 1, policy_version 30171 (0.0009) -[2023-10-09 09:28:39,685][23468] Updated weights for policy 0, policy_version 30023 (0.0009) -[2023-10-09 09:28:40,064][23468] Updated weights for policy 0, policy_version 30033 (0.0009) -[2023-10-09 09:28:40,439][23468] Updated weights for policy 0, policy_version 30043 (0.0008) -[2023-10-09 09:28:41,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 61669376. Throughput: 0: 1799.7, 1: 1778.1. Samples: 15422948. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 09:28:41,078][22500] Avg episode reward: [(0, '7.950'), (1, '6.610')] -[2023-10-09 09:28:42,251][23469] Updated weights for policy 1, policy_version 30181 (0.0008) -[2023-10-09 09:28:42,619][23469] Updated weights for policy 1, policy_version 30191 (0.0011) -[2023-10-09 09:28:42,985][23469] Updated weights for policy 1, policy_version 30201 (0.0010) -[2023-10-09 09:28:44,130][23468] Updated weights for policy 0, policy_version 30053 (0.0007) -[2023-10-09 09:28:44,506][23468] Updated weights for policy 0, policy_version 30063 (0.0009) -[2023-10-09 09:28:44,883][23468] Updated weights for policy 0, policy_version 30073 (0.0008) -[2023-10-09 09:28:46,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 61734912. Throughput: 0: 1774.0, 1: 1780.6. Samples: 15443958. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 09:28:46,079][22500] Avg episode reward: [(0, '7.870'), (1, '6.540')] -[2023-10-09 09:28:46,698][23469] Updated weights for policy 1, policy_version 30211 (0.0008) -[2023-10-09 09:28:47,069][23469] Updated weights for policy 1, policy_version 30221 (0.0007) -[2023-10-09 09:28:47,439][23469] Updated weights for policy 1, policy_version 30231 (0.0008) -[2023-10-09 09:28:48,513][23468] Updated weights for policy 0, policy_version 30083 (0.0007) -[2023-10-09 09:28:48,881][23468] Updated weights for policy 0, policy_version 30093 (0.0010) -[2023-10-09 09:28:49,263][23468] Updated weights for policy 0, policy_version 30103 (0.0007) -[2023-10-09 09:28:51,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 61800448. Throughput: 0: 1804.6, 1: 1780.4. Samples: 15455386. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 09:28:51,078][22500] Avg episode reward: [(0, '7.450'), (1, '6.810')] -[2023-10-09 09:28:51,250][23469] Updated weights for policy 1, policy_version 30241 (0.0009) -[2023-10-09 09:28:51,655][23469] Updated weights for policy 1, policy_version 30251 (0.0009) -[2023-10-09 09:28:52,034][23469] Updated weights for policy 1, policy_version 30261 (0.0011) -[2023-10-09 09:28:52,407][23469] Updated weights for policy 1, policy_version 30271 (0.0007) -[2023-10-09 09:28:52,791][23468] Updated weights for policy 0, policy_version 30113 (0.0008) -[2023-10-09 09:28:53,160][23468] Updated weights for policy 0, policy_version 30123 (0.0010) -[2023-10-09 09:28:53,529][23468] Updated weights for policy 0, policy_version 30133 (0.0008) -[2023-10-09 09:28:53,903][23468] Updated weights for policy 0, policy_version 30143 (0.0008) -[2023-10-09 09:28:56,056][23469] Updated weights for policy 1, policy_version 30281 (0.0010) -[2023-10-09 09:28:56,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 61865984. Throughput: 0: 1786.2, 1: 1782.8. Samples: 15476358. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 09:28:56,078][22500] Avg episode reward: [(0, '6.720'), (1, '6.810')] -[2023-10-09 09:28:56,421][23469] Updated weights for policy 1, policy_version 30291 (0.0010) -[2023-10-09 09:28:56,796][23469] Updated weights for policy 1, policy_version 30301 (0.0009) -[2023-10-09 09:28:57,580][23468] Updated weights for policy 0, policy_version 30153 (0.0007) -[2023-10-09 09:28:57,966][23468] Updated weights for policy 0, policy_version 30163 (0.0009) -[2023-10-09 09:28:58,340][23468] Updated weights for policy 0, policy_version 30173 (0.0008) -[2023-10-09 09:29:00,472][23469] Updated weights for policy 1, policy_version 30311 (0.0008) -[2023-10-09 09:29:00,837][23469] Updated weights for policy 1, policy_version 30321 (0.0008) -[2023-10-09 09:29:01,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 61931520. Throughput: 0: 1790.5, 1: 1806.0. Samples: 15498452. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 09:29:01,078][22500] Avg episode reward: [(0, '6.800'), (1, '6.850')] -[2023-10-09 09:29:01,202][23469] Updated weights for policy 1, policy_version 30331 (0.0007) -[2023-10-09 09:29:02,165][23468] Updated weights for policy 0, policy_version 30183 (0.0009) -[2023-10-09 09:29:02,535][23468] Updated weights for policy 0, policy_version 30193 (0.0008) -[2023-10-09 09:29:02,913][23468] Updated weights for policy 0, policy_version 30203 (0.0008) -[2023-10-09 09:29:04,854][23469] Updated weights for policy 1, policy_version 30341 (0.0007) -[2023-10-09 09:29:05,222][23469] Updated weights for policy 1, policy_version 30351 (0.0008) -[2023-10-09 09:29:05,588][23469] Updated weights for policy 1, policy_version 30361 (0.0009) -[2023-10-09 09:29:06,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 62029824. Throughput: 0: 1787.5, 1: 1793.6. Samples: 15509000. Policy #0 lag: (min: 26.0, avg: 32.1, max: 58.0) -[2023-10-09 09:29:06,078][22500] Avg episode reward: [(0, '6.590'), (1, '6.880')] -[2023-10-09 09:29:06,541][23468] Updated weights for policy 0, policy_version 30213 (0.0007) -[2023-10-09 09:29:06,910][23468] Updated weights for policy 0, policy_version 30223 (0.0007) -[2023-10-09 09:29:07,296][23468] Updated weights for policy 0, policy_version 30233 (0.0008) -[2023-10-09 09:29:09,403][23469] Updated weights for policy 1, policy_version 30371 (0.0008) -[2023-10-09 09:29:09,777][23469] Updated weights for policy 1, policy_version 30381 (0.0008) -[2023-10-09 09:29:10,154][23469] Updated weights for policy 1, policy_version 30391 (0.0007) -[2023-10-09 09:29:11,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 62095360. Throughput: 0: 1788.4, 1: 1811.2. Samples: 15530766. Policy #0 lag: (min: 26.0, avg: 32.1, max: 58.0) -[2023-10-09 09:29:11,078][22500] Avg episode reward: [(0, '6.610'), (1, '6.740')] -[2023-10-09 09:29:11,081][23468] Updated weights for policy 0, policy_version 30243 (0.0007) -[2023-10-09 09:29:11,451][23468] Updated weights for policy 0, policy_version 30253 (0.0007) -[2023-10-09 09:29:11,818][23468] Updated weights for policy 0, policy_version 30263 (0.0009) -[2023-10-09 09:29:13,910][23469] Updated weights for policy 1, policy_version 30401 (0.0008) -[2023-10-09 09:29:14,293][23469] Updated weights for policy 1, policy_version 30411 (0.0009) -[2023-10-09 09:29:14,665][23469] Updated weights for policy 1, policy_version 30421 (0.0008) -[2023-10-09 09:29:15,033][23469] Updated weights for policy 1, policy_version 30431 (0.0011) -[2023-10-09 09:29:15,610][23468] Updated weights for policy 0, policy_version 30273 (0.0010) -[2023-10-09 09:29:15,977][23468] Updated weights for policy 0, policy_version 30283 (0.0007) -[2023-10-09 09:29:16,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 62160896. Throughput: 0: 1796.1, 1: 1795.1. Samples: 15552392. Policy #0 lag: (min: 26.0, avg: 32.1, max: 58.0) -[2023-10-09 09:29:16,079][22500] Avg episode reward: [(0, '6.980'), (1, '6.770')] -[2023-10-09 09:29:16,359][23468] Updated weights for policy 0, policy_version 30293 (0.0008) -[2023-10-09 09:29:16,729][23468] Updated weights for policy 0, policy_version 30303 (0.0007) -[2023-10-09 09:29:18,780][23469] Updated weights for policy 1, policy_version 30441 (0.0008) -[2023-10-09 09:29:19,155][23469] Updated weights for policy 1, policy_version 30451 (0.0008) -[2023-10-09 09:29:19,520][23469] Updated weights for policy 1, policy_version 30461 (0.0007) -[2023-10-09 09:29:20,492][23468] Updated weights for policy 0, policy_version 30313 (0.0010) -[2023-10-09 09:29:20,865][23468] Updated weights for policy 0, policy_version 30323 (0.0010) -[2023-10-09 09:29:21,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 62226432. Throughput: 0: 1791.2, 1: 1815.3. Samples: 15563256. Policy #0 lag: (min: 26.0, avg: 32.1, max: 58.0) -[2023-10-09 09:29:21,078][22500] Avg episode reward: [(0, '6.810'), (1, '7.010')] -[2023-10-09 09:29:21,244][23468] Updated weights for policy 0, policy_version 30333 (0.0008) -[2023-10-09 09:29:23,456][23469] Updated weights for policy 1, policy_version 30471 (0.0008) -[2023-10-09 09:29:23,835][23469] Updated weights for policy 1, policy_version 30481 (0.0008) -[2023-10-09 09:29:24,196][23469] Updated weights for policy 1, policy_version 30491 (0.0009) -[2023-10-09 09:29:25,146][23468] Updated weights for policy 0, policy_version 30343 (0.0008) -[2023-10-09 09:29:25,524][23468] Updated weights for policy 0, policy_version 30353 (0.0007) -[2023-10-09 09:29:25,899][23468] Updated weights for policy 0, policy_version 30363 (0.0007) -[2023-10-09 09:29:26,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 62291968. Throughput: 0: 1789.2, 1: 1790.3. Samples: 15584024. Policy #0 lag: (min: 26.0, avg: 32.1, max: 58.0) -[2023-10-09 09:29:26,078][22500] Avg episode reward: [(0, '7.270'), (1, '6.390')] -[2023-10-09 09:29:28,026][23469] Updated weights for policy 1, policy_version 30501 (0.0010) -[2023-10-09 09:29:28,389][23469] Updated weights for policy 1, policy_version 30511 (0.0010) -[2023-10-09 09:29:28,755][23469] Updated weights for policy 1, policy_version 30521 (0.0009) -[2023-10-09 09:29:29,533][23468] Updated weights for policy 0, policy_version 30373 (0.0008) -[2023-10-09 09:29:29,906][23468] Updated weights for policy 0, policy_version 30383 (0.0008) -[2023-10-09 09:29:30,278][23468] Updated weights for policy 0, policy_version 30393 (0.0011) -[2023-10-09 09:29:31,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 62390272. Throughput: 0: 1796.2, 1: 1790.4. Samples: 15605356. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:29:31,078][22500] Avg episode reward: [(0, '7.130'), (1, '6.690')] -[2023-10-09 09:29:32,455][23469] Updated weights for policy 1, policy_version 30531 (0.0008) -[2023-10-09 09:29:32,822][23469] Updated weights for policy 1, policy_version 30541 (0.0008) -[2023-10-09 09:29:33,190][23469] Updated weights for policy 1, policy_version 30551 (0.0007) -[2023-10-09 09:29:34,209][23468] Updated weights for policy 0, policy_version 30403 (0.0008) -[2023-10-09 09:29:34,584][23468] Updated weights for policy 0, policy_version 30413 (0.0007) -[2023-10-09 09:29:34,965][23468] Updated weights for policy 0, policy_version 30423 (0.0010) -[2023-10-09 09:29:36,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 62455808. Throughput: 0: 1779.6, 1: 1793.2. Samples: 15616162. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:29:36,079][22500] Avg episode reward: [(0, '6.980'), (1, '6.630')] -[2023-10-09 09:29:36,883][23469] Updated weights for policy 1, policy_version 30561 (0.0008) -[2023-10-09 09:29:37,304][23469] Updated weights for policy 1, policy_version 30571 (0.0008) -[2023-10-09 09:29:37,672][23469] Updated weights for policy 1, policy_version 30581 (0.0007) -[2023-10-09 09:29:38,036][23469] Updated weights for policy 1, policy_version 30591 (0.0008) -[2023-10-09 09:29:38,770][23468] Updated weights for policy 0, policy_version 30433 (0.0009) -[2023-10-09 09:29:39,149][23468] Updated weights for policy 0, policy_version 30443 (0.0011) -[2023-10-09 09:29:39,526][23468] Updated weights for policy 0, policy_version 30453 (0.0009) -[2023-10-09 09:29:39,908][23468] Updated weights for policy 0, policy_version 30463 (0.0007) -[2023-10-09 09:29:41,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 62521344. Throughput: 0: 1792.2, 1: 1795.4. Samples: 15637798. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:29:41,078][22500] Avg episode reward: [(0, '6.550'), (1, '6.900')] -[2023-10-09 09:29:41,839][23469] Updated weights for policy 1, policy_version 30601 (0.0008) -[2023-10-09 09:29:42,207][23469] Updated weights for policy 1, policy_version 30611 (0.0007) -[2023-10-09 09:29:42,585][23469] Updated weights for policy 1, policy_version 30621 (0.0007) -[2023-10-09 09:29:43,643][23468] Updated weights for policy 0, policy_version 30473 (0.0009) -[2023-10-09 09:29:44,008][23468] Updated weights for policy 0, policy_version 30483 (0.0010) -[2023-10-09 09:29:44,384][23468] Updated weights for policy 0, policy_version 30493 (0.0007) -[2023-10-09 09:29:46,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 62586880. Throughput: 0: 1778.2, 1: 1803.8. Samples: 15659644. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:29:46,079][22500] Avg episode reward: [(0, '7.100'), (1, '6.740')] -[2023-10-09 09:29:46,092][23469] Updated weights for policy 1, policy_version 30631 (0.0007) -[2023-10-09 09:29:46,461][23469] Updated weights for policy 1, policy_version 30641 (0.0007) -[2023-10-09 09:29:46,828][23469] Updated weights for policy 1, policy_version 30651 (0.0007) -[2023-10-09 09:29:48,025][23468] Updated weights for policy 0, policy_version 30503 (0.0009) -[2023-10-09 09:29:48,391][23468] Updated weights for policy 0, policy_version 30513 (0.0008) -[2023-10-09 09:29:48,776][23468] Updated weights for policy 0, policy_version 30523 (0.0007) -[2023-10-09 09:29:50,642][23469] Updated weights for policy 1, policy_version 30661 (0.0007) -[2023-10-09 09:29:51,006][23469] Updated weights for policy 1, policy_version 30671 (0.0007) -[2023-10-09 09:29:51,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 62652416. Throughput: 0: 1803.3, 1: 1782.9. Samples: 15670380. Policy #0 lag: (min: 16.0, avg: 39.1, max: 48.0) -[2023-10-09 09:29:51,078][22500] Avg episode reward: [(0, '7.420'), (1, '6.890')] -[2023-10-09 09:29:51,378][23469] Updated weights for policy 1, policy_version 30681 (0.0007) -[2023-10-09 09:29:52,550][23468] Updated weights for policy 0, policy_version 30533 (0.0010) -[2023-10-09 09:29:52,911][23468] Updated weights for policy 0, policy_version 30543 (0.0008) -[2023-10-09 09:29:53,284][23468] Updated weights for policy 0, policy_version 30553 (0.0008) -[2023-10-09 09:29:55,027][23469] Updated weights for policy 1, policy_version 30691 (0.0008) -[2023-10-09 09:29:55,404][23469] Updated weights for policy 1, policy_version 30701 (0.0008) -[2023-10-09 09:29:55,766][23469] Updated weights for policy 1, policy_version 30711 (0.0008) -[2023-10-09 09:29:56,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 62717952. Throughput: 0: 1783.3, 1: 1800.8. Samples: 15692052. Policy #0 lag: (min: 16.0, avg: 39.1, max: 48.0) -[2023-10-09 09:29:56,078][22500] Avg episode reward: [(0, '7.260'), (1, '6.430')] -[2023-10-09 09:29:57,060][23468] Updated weights for policy 0, policy_version 30563 (0.0008) -[2023-10-09 09:29:57,434][23468] Updated weights for policy 0, policy_version 30573 (0.0010) -[2023-10-09 09:29:57,804][23468] Updated weights for policy 0, policy_version 30583 (0.0011) -[2023-10-09 09:29:59,389][23469] Updated weights for policy 1, policy_version 30721 (0.0008) -[2023-10-09 09:29:59,757][23469] Updated weights for policy 1, policy_version 30731 (0.0007) -[2023-10-09 09:30:00,135][23469] Updated weights for policy 1, policy_version 30741 (0.0008) -[2023-10-09 09:30:00,507][23469] Updated weights for policy 1, policy_version 30751 (0.0008) -[2023-10-09 09:30:01,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 62816256. Throughput: 0: 1778.1, 1: 1793.3. Samples: 15713104. Policy #0 lag: (min: 16.0, avg: 39.1, max: 48.0) -[2023-10-09 09:30:01,078][22500] Avg episode reward: [(0, '6.550'), (1, '6.960')] -[2023-10-09 09:30:01,612][23468] Updated weights for policy 0, policy_version 30593 (0.0009) -[2023-10-09 09:30:02,014][23468] Updated weights for policy 0, policy_version 30603 (0.0010) -[2023-10-09 09:30:02,385][23468] Updated weights for policy 0, policy_version 30613 (0.0011) -[2023-10-09 09:30:02,760][23468] Updated weights for policy 0, policy_version 30623 (0.0009) -[2023-10-09 09:30:04,232][23469] Updated weights for policy 1, policy_version 30761 (0.0008) -[2023-10-09 09:30:04,616][23469] Updated weights for policy 1, policy_version 30771 (0.0009) -[2023-10-09 09:30:04,984][23469] Updated weights for policy 1, policy_version 30781 (0.0008) -[2023-10-09 09:30:06,077][22500] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 62881792. Throughput: 0: 1777.1, 1: 1800.7. Samples: 15724258. Policy #0 lag: (min: 16.0, avg: 39.1, max: 48.0) -[2023-10-09 09:30:06,079][22500] Avg episode reward: [(0, '6.930'), (1, '6.820')] -[2023-10-09 09:30:06,514][23468] Updated weights for policy 0, policy_version 30633 (0.0008) -[2023-10-09 09:30:06,885][23468] Updated weights for policy 0, policy_version 30643 (0.0007) -[2023-10-09 09:30:07,263][23468] Updated weights for policy 0, policy_version 30653 (0.0008) -[2023-10-09 09:30:08,692][23469] Updated weights for policy 1, policy_version 30791 (0.0009) -[2023-10-09 09:30:09,069][23469] Updated weights for policy 1, policy_version 30801 (0.0007) -[2023-10-09 09:30:09,432][23469] Updated weights for policy 1, policy_version 30811 (0.0008) -[2023-10-09 09:30:10,976][23468] Updated weights for policy 0, policy_version 30663 (0.0010) -[2023-10-09 09:30:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 62947328. Throughput: 0: 1779.3, 1: 1801.3. Samples: 15745154. Policy #0 lag: (min: 16.0, avg: 39.1, max: 48.0) -[2023-10-09 09:30:11,078][22500] Avg episode reward: [(0, '7.160'), (1, '6.780')] -[2023-10-09 09:30:11,350][23468] Updated weights for policy 0, policy_version 30673 (0.0010) -[2023-10-09 09:30:11,730][23468] Updated weights for policy 0, policy_version 30683 (0.0010) -[2023-10-09 09:30:13,178][23469] Updated weights for policy 1, policy_version 30821 (0.0007) -[2023-10-09 09:30:13,555][23469] Updated weights for policy 1, policy_version 30831 (0.0010) -[2023-10-09 09:30:13,924][23469] Updated weights for policy 1, policy_version 30841 (0.0009) -[2023-10-09 09:30:15,472][23468] Updated weights for policy 0, policy_version 30693 (0.0010) -[2023-10-09 09:30:15,849][23468] Updated weights for policy 0, policy_version 30703 (0.0008) -[2023-10-09 09:30:16,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 63012864. Throughput: 0: 1800.8, 1: 1803.3. Samples: 15767542. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:30:16,079][22500] Avg episode reward: [(0, '7.600'), (1, '6.800')] -[2023-10-09 09:30:16,090][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000030848_31588352.pth... -[2023-10-09 09:30:16,129][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000029184_29884416.pth -[2023-10-09 09:30:16,221][23468] Updated weights for policy 0, policy_version 30713 (0.0009) -[2023-10-09 09:30:16,482][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000030720_31457280.pth... -[2023-10-09 09:30:16,511][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000029024_29720576.pth -[2023-10-09 09:30:17,624][23469] Updated weights for policy 1, policy_version 30851 (0.0009) -[2023-10-09 09:30:17,993][23469] Updated weights for policy 1, policy_version 30861 (0.0009) -[2023-10-09 09:30:18,354][23469] Updated weights for policy 1, policy_version 30871 (0.0011) -[2023-10-09 09:30:19,961][23468] Updated weights for policy 0, policy_version 30723 (0.0008) -[2023-10-09 09:30:20,340][23468] Updated weights for policy 0, policy_version 30733 (0.0008) -[2023-10-09 09:30:20,701][23468] Updated weights for policy 0, policy_version 30743 (0.0008) -[2023-10-09 09:30:21,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 63111168. Throughput: 0: 1782.7, 1: 1805.2. Samples: 15777614. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:30:21,078][22500] Avg episode reward: [(0, '7.170'), (1, '6.310')] -[2023-10-09 09:30:22,164][23469] Updated weights for policy 1, policy_version 30881 (0.0009) -[2023-10-09 09:30:22,547][23469] Updated weights for policy 1, policy_version 30891 (0.0010) -[2023-10-09 09:30:22,908][23469] Updated weights for policy 1, policy_version 30901 (0.0007) -[2023-10-09 09:30:23,280][23469] Updated weights for policy 1, policy_version 30911 (0.0007) -[2023-10-09 09:30:24,657][23468] Updated weights for policy 0, policy_version 30753 (0.0009) -[2023-10-09 09:30:25,036][23468] Updated weights for policy 0, policy_version 30763 (0.0008) -[2023-10-09 09:30:25,411][23468] Updated weights for policy 0, policy_version 30773 (0.0008) -[2023-10-09 09:30:25,776][23468] Updated weights for policy 0, policy_version 30783 (0.0010) -[2023-10-09 09:30:26,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 63176704. Throughput: 0: 1793.9, 1: 1806.5. Samples: 15799814. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:30:26,079][22500] Avg episode reward: [(0, '6.960'), (1, '6.590')] -[2023-10-09 09:30:26,926][23469] Updated weights for policy 1, policy_version 30921 (0.0007) -[2023-10-09 09:30:27,286][23469] Updated weights for policy 1, policy_version 30931 (0.0009) -[2023-10-09 09:30:27,664][23469] Updated weights for policy 1, policy_version 30941 (0.0009) -[2023-10-09 09:30:29,527][23468] Updated weights for policy 0, policy_version 30793 (0.0008) -[2023-10-09 09:30:29,900][23468] Updated weights for policy 0, policy_version 30803 (0.0009) -[2023-10-09 09:30:30,281][23468] Updated weights for policy 0, policy_version 30813 (0.0008) -[2023-10-09 09:30:31,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 63242240. Throughput: 0: 1778.1, 1: 1806.2. Samples: 15820936. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:30:31,078][22500] Avg episode reward: [(0, '6.820'), (1, '6.730')] -[2023-10-09 09:30:31,371][23469] Updated weights for policy 1, policy_version 30951 (0.0008) -[2023-10-09 09:30:31,731][23469] Updated weights for policy 1, policy_version 30961 (0.0010) -[2023-10-09 09:30:32,101][23469] Updated weights for policy 1, policy_version 30971 (0.0010) -[2023-10-09 09:30:34,150][23468] Updated weights for policy 0, policy_version 30823 (0.0008) -[2023-10-09 09:30:34,527][23468] Updated weights for policy 0, policy_version 30833 (0.0008) -[2023-10-09 09:30:34,897][23468] Updated weights for policy 0, policy_version 30843 (0.0009) -[2023-10-09 09:30:36,077][23469] Updated weights for policy 1, policy_version 30981 (0.0010) -[2023-10-09 09:30:36,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 63307776. Throughput: 0: 1779.6, 1: 1807.5. Samples: 15831800. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:30:36,078][22500] Avg episode reward: [(0, '6.660'), (1, '6.870')] -[2023-10-09 09:30:36,442][23469] Updated weights for policy 1, policy_version 30991 (0.0011) -[2023-10-09 09:30:36,815][23469] Updated weights for policy 1, policy_version 31001 (0.0011) -[2023-10-09 09:30:40,481][23468] Updated weights for policy 0, policy_version 30853 (0.0011) -[2023-10-09 09:30:40,863][23468] Updated weights for policy 0, policy_version 30863 (0.0012) -[2023-10-09 09:30:41,078][22500] Fps is (10 sec: 9829.9, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 63340544. Throughput: 0: 1734.6, 1: 1745.2. Samples: 15848646. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:30:41,078][22500] Avg episode reward: [(0, '6.480'), (1, '6.890')] -[2023-10-09 09:30:41,239][23468] Updated weights for policy 0, policy_version 30873 (0.0011) -[2023-10-09 09:30:42,733][23469] Updated weights for policy 1, policy_version 31011 (0.0011) -[2023-10-09 09:30:43,109][23469] Updated weights for policy 1, policy_version 31021 (0.0011) -[2023-10-09 09:30:43,479][23469] Updated weights for policy 1, policy_version 31031 (0.0011) -[2023-10-09 09:30:46,077][22500] Fps is (10 sec: 9830.4, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 63406080. Throughput: 0: 1635.1, 1: 1676.7. Samples: 15862136. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:30:46,078][22500] Avg episode reward: [(0, '6.380'), (1, '6.680')] -[2023-10-09 09:30:47,566][23468] Updated weights for policy 0, policy_version 30883 (0.0011) -[2023-10-09 09:30:47,957][23468] Updated weights for policy 0, policy_version 30893 (0.0011) -[2023-10-09 09:30:48,332][23468] Updated weights for policy 0, policy_version 30903 (0.0011) -[2023-10-09 09:30:49,578][23469] Updated weights for policy 1, policy_version 31041 (0.0011) -[2023-10-09 09:30:49,957][23469] Updated weights for policy 1, policy_version 31051 (0.0011) -[2023-10-09 09:30:50,330][23469] Updated weights for policy 1, policy_version 31061 (0.0011) -[2023-10-09 09:30:50,702][23469] Updated weights for policy 1, policy_version 31071 (0.0011) -[2023-10-09 09:30:51,077][22500] Fps is (10 sec: 13107.7, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 63471616. Throughput: 0: 1604.7, 1: 1619.0. Samples: 15869326. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:30:51,078][22500] Avg episode reward: [(0, '6.350'), (1, '6.720')] -[2023-10-09 09:30:54,716][23468] Updated weights for policy 0, policy_version 30913 (0.0012) -[2023-10-09 09:30:55,088][23468] Updated weights for policy 0, policy_version 30923 (0.0011) -[2023-10-09 09:30:55,465][23468] Updated weights for policy 0, policy_version 30933 (0.0011) -[2023-10-09 09:30:55,839][23468] Updated weights for policy 0, policy_version 30943 (0.0010) -[2023-10-09 09:30:56,077][22500] Fps is (10 sec: 9830.5, 60 sec: 13107.2, 300 sec: 13995.8). Total num frames: 63504384. Throughput: 0: 1514.2, 1: 1555.8. Samples: 15883304. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:30:56,078][22500] Avg episode reward: [(0, '6.660'), (1, '6.930')] -[2023-10-09 09:30:56,774][23469] Updated weights for policy 1, policy_version 31081 (0.0011) -[2023-10-09 09:30:57,149][23469] Updated weights for policy 1, policy_version 31091 (0.0009) -[2023-10-09 09:30:57,517][23469] Updated weights for policy 1, policy_version 31101 (0.0011) -[2023-10-09 09:31:01,077][22500] Fps is (10 sec: 6553.6, 60 sec: 12015.0, 300 sec: 13884.7). Total num frames: 63537152. Throughput: 0: 1437.3, 1: 1469.2. Samples: 15898334. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:31:01,078][22500] Avg episode reward: [(0, '6.610'), (1, '6.690')] -[2023-10-09 09:31:01,443][23468] Updated weights for policy 0, policy_version 30953 (0.0010) -[2023-10-09 09:31:01,819][23468] Updated weights for policy 0, policy_version 30963 (0.0011) -[2023-10-09 09:31:02,196][23468] Updated weights for policy 0, policy_version 30973 (0.0011) -[2023-10-09 09:31:03,201][23469] Updated weights for policy 1, policy_version 31111 (0.0011) -[2023-10-09 09:31:03,576][23469] Updated weights for policy 1, policy_version 31121 (0.0011) -[2023-10-09 09:31:03,941][23469] Updated weights for policy 1, policy_version 31131 (0.0011) -[2023-10-09 09:31:06,077][22500] Fps is (10 sec: 9830.3, 60 sec: 12015.0, 300 sec: 13884.7). Total num frames: 63602688. Throughput: 0: 1402.1, 1: 1438.8. Samples: 15905456. Policy #0 lag: (min: 13.0, avg: 20.4, max: 45.0) -[2023-10-09 09:31:06,078][22500] Avg episode reward: [(0, '7.260'), (1, '6.760')] -[2023-10-09 09:31:07,835][23468] Updated weights for policy 0, policy_version 30983 (0.0011) -[2023-10-09 09:31:08,199][23468] Updated weights for policy 0, policy_version 30993 (0.0011) -[2023-10-09 09:31:08,572][23468] Updated weights for policy 0, policy_version 31003 (0.0012) -[2023-10-09 09:31:09,608][23469] Updated weights for policy 1, policy_version 31141 (0.0011) -[2023-10-09 09:31:10,013][23469] Updated weights for policy 1, policy_version 31151 (0.0011) -[2023-10-09 09:31:10,372][23469] Updated weights for policy 1, policy_version 31161 (0.0010) -[2023-10-09 09:31:11,077][22500] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 13884.7). Total num frames: 63668224. Throughput: 0: 1328.5, 1: 1362.8. Samples: 15920922. Policy #0 lag: (min: 13.0, avg: 20.4, max: 45.0) -[2023-10-09 09:31:11,078][22500] Avg episode reward: [(0, '7.300'), (1, '6.810')] -[2023-10-09 09:31:13,960][23468] Updated weights for policy 0, policy_version 31013 (0.0011) -[2023-10-09 09:31:14,330][23468] Updated weights for policy 0, policy_version 31023 (0.0011) -[2023-10-09 09:31:14,696][23468] Updated weights for policy 0, policy_version 31033 (0.0011) -[2023-10-09 09:31:15,544][23469] Updated weights for policy 1, policy_version 31171 (0.0011) -[2023-10-09 09:31:15,917][23469] Updated weights for policy 1, policy_version 31181 (0.0011) -[2023-10-09 09:31:16,077][22500] Fps is (10 sec: 9830.4, 60 sec: 11468.8, 300 sec: 13773.7). Total num frames: 63700992. Throughput: 0: 1289.6, 1: 1290.8. Samples: 15937056. Policy #0 lag: (min: 13.0, avg: 20.4, max: 45.0) -[2023-10-09 09:31:16,078][22500] Avg episode reward: [(0, '7.200'), (1, '7.000')] -[2023-10-09 09:31:16,280][23469] Updated weights for policy 1, policy_version 31191 (0.0011) -[2023-10-09 09:31:19,550][23468] Updated weights for policy 0, policy_version 31043 (0.0011) -[2023-10-09 09:31:19,922][23468] Updated weights for policy 0, policy_version 31053 (0.0011) -[2023-10-09 09:31:20,297][23468] Updated weights for policy 0, policy_version 31063 (0.0011) -[2023-10-09 09:31:21,066][23469] Updated weights for policy 1, policy_version 31201 (0.0011) -[2023-10-09 09:31:21,077][22500] Fps is (10 sec: 9830.5, 60 sec: 10922.7, 300 sec: 13662.6). Total num frames: 63766528. Throughput: 0: 1260.2, 1: 1275.5. Samples: 15945906. Policy #0 lag: (min: 13.0, avg: 20.4, max: 45.0) -[2023-10-09 09:31:21,078][22500] Avg episode reward: [(0, '7.460'), (1, '7.030')] -[2023-10-09 09:31:21,434][23469] Updated weights for policy 1, policy_version 31211 (0.0011) -[2023-10-09 09:31:21,807][23469] Updated weights for policy 1, policy_version 31221 (0.0011) -[2023-10-09 09:31:22,175][23469] Updated weights for policy 1, policy_version 31231 (0.0012) -[2023-10-09 09:31:25,026][23468] Updated weights for policy 0, policy_version 31073 (0.0011) -[2023-10-09 09:31:25,388][23468] Updated weights for policy 0, policy_version 31083 (0.0011) -[2023-10-09 09:31:25,765][23468] Updated weights for policy 0, policy_version 31093 (0.0011) -[2023-10-09 09:31:26,077][22500] Fps is (10 sec: 9830.4, 60 sec: 10376.6, 300 sec: 13551.5). Total num frames: 63799296. Throughput: 0: 1276.2, 1: 1279.8. Samples: 15963664. Policy #0 lag: (min: 13.0, avg: 20.4, max: 45.0) -[2023-10-09 09:31:26,078][22500] Avg episode reward: [(0, '7.170'), (1, '7.150')] -[2023-10-09 09:31:26,143][23468] Updated weights for policy 0, policy_version 31103 (0.0011) -[2023-10-09 09:31:26,903][23469] Updated weights for policy 1, policy_version 31241 (0.0010) -[2023-10-09 09:31:27,267][23469] Updated weights for policy 1, policy_version 31251 (0.0010) -[2023-10-09 09:31:27,633][23469] Updated weights for policy 1, policy_version 31261 (0.0010) -[2023-10-09 09:31:30,866][23468] Updated weights for policy 0, policy_version 31113 (0.0011) -[2023-10-09 09:31:31,077][22500] Fps is (10 sec: 9830.4, 60 sec: 10376.5, 300 sec: 13440.4). Total num frames: 63864832. Throughput: 0: 1323.7, 1: 1329.7. Samples: 15981540. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 09:31:31,078][22500] Avg episode reward: [(0, '7.200'), (1, '7.460')] -[2023-10-09 09:31:31,089][23343] Saving new best policy, reward=7.460! -[2023-10-09 09:31:31,237][23468] Updated weights for policy 0, policy_version 31123 (0.0011) -[2023-10-09 09:31:31,617][23468] Updated weights for policy 0, policy_version 31133 (0.0011) -[2023-10-09 09:31:32,493][23469] Updated weights for policy 1, policy_version 31271 (0.0010) -[2023-10-09 09:31:32,865][23469] Updated weights for policy 1, policy_version 31281 (0.0011) -[2023-10-09 09:31:33,229][23469] Updated weights for policy 1, policy_version 31291 (0.0009) -[2023-10-09 09:31:36,077][22500] Fps is (10 sec: 13107.2, 60 sec: 10376.5, 300 sec: 13440.4). Total num frames: 63930368. Throughput: 0: 1338.3, 1: 1331.5. Samples: 15989466. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 09:31:36,078][22500] Avg episode reward: [(0, '6.800'), (1, '7.440')] -[2023-10-09 09:31:36,261][23468] Updated weights for policy 0, policy_version 31143 (0.0009) -[2023-10-09 09:31:36,630][23468] Updated weights for policy 0, policy_version 31153 (0.0010) -[2023-10-09 09:31:37,005][23468] Updated weights for policy 0, policy_version 31163 (0.0010) -[2023-10-09 09:31:37,747][23469] Updated weights for policy 1, policy_version 31301 (0.0010) -[2023-10-09 09:31:38,121][23469] Updated weights for policy 1, policy_version 31311 (0.0010) -[2023-10-09 09:31:38,493][23469] Updated weights for policy 1, policy_version 31321 (0.0010) -[2023-10-09 09:31:41,077][22500] Fps is (10 sec: 13107.3, 60 sec: 10922.7, 300 sec: 13440.4). Total num frames: 63995904. Throughput: 0: 1388.1, 1: 1388.8. Samples: 16008268. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 09:31:41,078][22500] Avg episode reward: [(0, '6.420'), (1, '7.250')] -[2023-10-09 09:31:41,323][23468] Updated weights for policy 0, policy_version 31173 (0.0010) -[2023-10-09 09:31:41,692][23468] Updated weights for policy 0, policy_version 31183 (0.0011) -[2023-10-09 09:31:42,061][23468] Updated weights for policy 0, policy_version 31193 (0.0012) -[2023-10-09 09:31:42,929][23469] Updated weights for policy 1, policy_version 31331 (0.0010) -[2023-10-09 09:31:43,307][23469] Updated weights for policy 1, policy_version 31341 (0.0011) -[2023-10-09 09:31:43,673][23469] Updated weights for policy 1, policy_version 31351 (0.0011) -[2023-10-09 09:31:46,077][22500] Fps is (10 sec: 13107.3, 60 sec: 10922.7, 300 sec: 13440.4). Total num frames: 64061440. Throughput: 0: 1426.8, 1: 1433.3. Samples: 16027038. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 09:31:46,078][22500] Avg episode reward: [(0, '6.120'), (1, '7.080')] -[2023-10-09 09:31:46,573][23468] Updated weights for policy 0, policy_version 31203 (0.0010) -[2023-10-09 09:31:46,939][23468] Updated weights for policy 0, policy_version 31213 (0.0010) -[2023-10-09 09:31:47,311][23468] Updated weights for policy 0, policy_version 31223 (0.0009) -[2023-10-09 09:31:47,997][23469] Updated weights for policy 1, policy_version 31361 (0.0011) -[2023-10-09 09:31:48,362][23469] Updated weights for policy 1, policy_version 31371 (0.0010) -[2023-10-09 09:31:48,730][23469] Updated weights for policy 1, policy_version 31381 (0.0010) -[2023-10-09 09:31:49,107][23469] Updated weights for policy 1, policy_version 31391 (0.0011) -[2023-10-09 09:31:51,077][22500] Fps is (10 sec: 13107.1, 60 sec: 10922.7, 300 sec: 13440.4). Total num frames: 64126976. Throughput: 0: 1444.6, 1: 1457.5. Samples: 16036050. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:31:51,078][22500] Avg episode reward: [(0, '7.160'), (1, '6.620')] -[2023-10-09 09:31:51,850][23468] Updated weights for policy 0, policy_version 31233 (0.0010) -[2023-10-09 09:31:52,227][23468] Updated weights for policy 0, policy_version 31243 (0.0010) -[2023-10-09 09:31:52,595][23468] Updated weights for policy 0, policy_version 31253 (0.0010) -[2023-10-09 09:31:52,967][23468] Updated weights for policy 0, policy_version 31263 (0.0011) -[2023-10-09 09:31:53,675][23469] Updated weights for policy 1, policy_version 31401 (0.0010) -[2023-10-09 09:31:54,049][23469] Updated weights for policy 1, policy_version 31411 (0.0009) -[2023-10-09 09:31:54,416][23469] Updated weights for policy 1, policy_version 31421 (0.0012) -[2023-10-09 09:31:56,077][22500] Fps is (10 sec: 13107.1, 60 sec: 11468.8, 300 sec: 13440.4). Total num frames: 64192512. Throughput: 0: 1485.6, 1: 1480.6. Samples: 16054402. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:31:56,078][22500] Avg episode reward: [(0, '7.140'), (1, '6.820')] -[2023-10-09 09:31:57,570][23468] Updated weights for policy 0, policy_version 31273 (0.0011) -[2023-10-09 09:31:57,949][23468] Updated weights for policy 0, policy_version 31283 (0.0009) -[2023-10-09 09:31:58,320][23468] Updated weights for policy 0, policy_version 31293 (0.0009) -[2023-10-09 09:31:59,040][23469] Updated weights for policy 1, policy_version 31431 (0.0010) -[2023-10-09 09:31:59,417][23469] Updated weights for policy 1, policy_version 31441 (0.0010) -[2023-10-09 09:31:59,797][23469] Updated weights for policy 1, policy_version 31451 (0.0011) -[2023-10-09 09:32:01,077][22500] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 13440.4). Total num frames: 64258048. Throughput: 0: 1511.7, 1: 1506.7. Samples: 16072886. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:32:01,078][22500] Avg episode reward: [(0, '7.720'), (1, '7.020')] -[2023-10-09 09:32:02,798][23468] Updated weights for policy 0, policy_version 31303 (0.0010) -[2023-10-09 09:32:03,160][23468] Updated weights for policy 0, policy_version 31313 (0.0011) -[2023-10-09 09:32:03,536][23468] Updated weights for policy 0, policy_version 31323 (0.0010) -[2023-10-09 09:32:04,363][23469] Updated weights for policy 1, policy_version 31461 (0.0011) -[2023-10-09 09:32:04,740][23469] Updated weights for policy 1, policy_version 31471 (0.0010) -[2023-10-09 09:32:05,099][23469] Updated weights for policy 1, policy_version 31481 (0.0011) -[2023-10-09 09:32:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 13440.4). Total num frames: 64323584. Throughput: 0: 1506.0, 1: 1527.6. Samples: 16082422. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:32:06,078][22500] Avg episode reward: [(0, '6.970'), (1, '6.750')] -[2023-10-09 09:32:08,173][23468] Updated weights for policy 0, policy_version 31333 (0.0011) -[2023-10-09 09:32:08,539][23468] Updated weights for policy 0, policy_version 31343 (0.0010) -[2023-10-09 09:32:08,908][23468] Updated weights for policy 0, policy_version 31353 (0.0011) -[2023-10-09 09:32:09,589][23469] Updated weights for policy 1, policy_version 31491 (0.0011) -[2023-10-09 09:32:09,952][23469] Updated weights for policy 1, policy_version 31501 (0.0011) -[2023-10-09 09:32:10,322][23469] Updated weights for policy 1, policy_version 31511 (0.0011) -[2023-10-09 09:32:11,078][22500] Fps is (10 sec: 13106.1, 60 sec: 12014.8, 300 sec: 13440.4). Total num frames: 64389120. Throughput: 0: 1504.3, 1: 1536.9. Samples: 16100520. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 09:32:11,079][22500] Avg episode reward: [(0, '6.700'), (1, '6.830')] -[2023-10-09 09:32:13,605][23468] Updated weights for policy 0, policy_version 31363 (0.0011) -[2023-10-09 09:32:13,971][23468] Updated weights for policy 0, policy_version 31373 (0.0011) -[2023-10-09 09:32:14,343][23468] Updated weights for policy 0, policy_version 31383 (0.0011) -[2023-10-09 09:32:14,924][23469] Updated weights for policy 1, policy_version 31521 (0.0011) -[2023-10-09 09:32:15,295][23469] Updated weights for policy 1, policy_version 31531 (0.0011) -[2023-10-09 09:32:15,658][23469] Updated weights for policy 1, policy_version 31541 (0.0011) -[2023-10-09 09:32:16,036][23469] Updated weights for policy 1, policy_version 31551 (0.0010) -[2023-10-09 09:32:16,077][22500] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 13329.3). Total num frames: 64454656. Throughput: 0: 1507.2, 1: 1530.2. Samples: 16118226. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 09:32:16,078][22500] Avg episode reward: [(0, '6.600'), (1, '6.730')] -[2023-10-09 09:32:16,089][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000031552_32309248.pth... -[2023-10-09 09:32:16,089][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000031392_32145408.pth... -[2023-10-09 09:32:16,131][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000029856_30572544.pth -[2023-10-09 09:32:16,132][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000030016_30736384.pth -[2023-10-09 09:32:18,747][23468] Updated weights for policy 0, policy_version 31393 (0.0010) -[2023-10-09 09:32:19,128][23468] Updated weights for policy 0, policy_version 31403 (0.0010) -[2023-10-09 09:32:19,495][23468] Updated weights for policy 0, policy_version 31413 (0.0010) -[2023-10-09 09:32:19,875][23468] Updated weights for policy 0, policy_version 31423 (0.0010) -[2023-10-09 09:32:20,249][23469] Updated weights for policy 1, policy_version 31561 (0.0010) -[2023-10-09 09:32:20,622][23469] Updated weights for policy 1, policy_version 31571 (0.0010) -[2023-10-09 09:32:20,988][23469] Updated weights for policy 1, policy_version 31581 (0.0011) -[2023-10-09 09:32:21,077][22500] Fps is (10 sec: 9831.3, 60 sec: 12014.9, 300 sec: 13218.3). Total num frames: 64487424. Throughput: 0: 1540.5, 1: 1560.4. Samples: 16129004. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 09:32:21,078][22500] Avg episode reward: [(0, '7.050'), (1, '6.990')] -[2023-10-09 09:32:24,847][23468] Updated weights for policy 0, policy_version 31433 (0.0011) -[2023-10-09 09:32:25,226][23468] Updated weights for policy 0, policy_version 31443 (0.0011) -[2023-10-09 09:32:25,597][23468] Updated weights for policy 0, policy_version 31453 (0.0011) -[2023-10-09 09:32:25,644][23469] Updated weights for policy 1, policy_version 31591 (0.0011) -[2023-10-09 09:32:26,023][23469] Updated weights for policy 1, policy_version 31601 (0.0012) -[2023-10-09 09:32:26,077][22500] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 13218.3). Total num frames: 64552960. Throughput: 0: 1530.6, 1: 1559.3. Samples: 16147314. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 09:32:26,078][22500] Avg episode reward: [(0, '7.060'), (1, '7.130')] -[2023-10-09 09:32:26,383][23469] Updated weights for policy 1, policy_version 31611 (0.0011) -[2023-10-09 09:32:29,765][23468] Updated weights for policy 0, policy_version 31463 (0.0010) -[2023-10-09 09:32:30,131][23468] Updated weights for policy 0, policy_version 31473 (0.0008) -[2023-10-09 09:32:30,431][23469] Updated weights for policy 1, policy_version 31621 (0.0010) -[2023-10-09 09:32:30,502][23468] Updated weights for policy 0, policy_version 31483 (0.0010) -[2023-10-09 09:32:30,798][23469] Updated weights for policy 1, policy_version 31631 (0.0009) -[2023-10-09 09:32:31,077][22500] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 13107.2). Total num frames: 64618496. Throughput: 0: 1526.8, 1: 1564.8. Samples: 16166162. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:32:31,078][22500] Avg episode reward: [(0, '7.290'), (1, '7.260')] -[2023-10-09 09:32:31,164][23469] Updated weights for policy 1, policy_version 31641 (0.0010) -[2023-10-09 09:32:34,786][23468] Updated weights for policy 0, policy_version 31493 (0.0010) -[2023-10-09 09:32:35,155][23468] Updated weights for policy 0, policy_version 31503 (0.0014) -[2023-10-09 09:32:35,531][23468] Updated weights for policy 0, policy_version 31513 (0.0010) -[2023-10-09 09:32:35,536][23469] Updated weights for policy 1, policy_version 31651 (0.0010) -[2023-10-09 09:32:35,895][23469] Updated weights for policy 1, policy_version 31661 (0.0010) -[2023-10-09 09:32:36,077][22500] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 13107.2). Total num frames: 64684032. Throughput: 0: 1549.5, 1: 1568.4. Samples: 16176354. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:32:36,078][22500] Avg episode reward: [(0, '7.040'), (1, '7.140')] -[2023-10-09 09:32:36,261][23469] Updated weights for policy 1, policy_version 31671 (0.0011) -[2023-10-09 09:32:39,966][23468] Updated weights for policy 0, policy_version 31523 (0.0010) -[2023-10-09 09:32:40,340][23468] Updated weights for policy 0, policy_version 31533 (0.0011) -[2023-10-09 09:32:40,674][23469] Updated weights for policy 1, policy_version 31681 (0.0010) -[2023-10-09 09:32:40,711][23468] Updated weights for policy 0, policy_version 31543 (0.0011) -[2023-10-09 09:32:41,038][23469] Updated weights for policy 1, policy_version 31691 (0.0011) -[2023-10-09 09:32:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 13107.2). Total num frames: 64749568. Throughput: 0: 1551.9, 1: 1580.5. Samples: 16195362. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:32:41,078][22500] Avg episode reward: [(0, '6.730'), (1, '7.070')] -[2023-10-09 09:32:41,413][23469] Updated weights for policy 1, policy_version 31701 (0.0010) -[2023-10-09 09:32:41,779][23469] Updated weights for policy 1, policy_version 31711 (0.0010) -[2023-10-09 09:32:45,205][23468] Updated weights for policy 0, policy_version 31553 (0.0011) -[2023-10-09 09:32:45,580][23468] Updated weights for policy 0, policy_version 31563 (0.0012) -[2023-10-09 09:32:45,951][23468] Updated weights for policy 0, policy_version 31573 (0.0011) -[2023-10-09 09:32:46,077][22500] Fps is (10 sec: 9830.4, 60 sec: 12014.9, 300 sec: 12996.1). Total num frames: 64782336. Throughput: 0: 1556.9, 1: 1585.0. Samples: 16214270. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:32:46,078][22500] Avg episode reward: [(0, '6.720'), (1, '6.780')] -[2023-10-09 09:32:46,319][23468] Updated weights for policy 0, policy_version 31583 (0.0009) -[2023-10-09 09:32:46,396][23469] Updated weights for policy 1, policy_version 31721 (0.0009) -[2023-10-09 09:32:46,774][23469] Updated weights for policy 1, policy_version 31731 (0.0011) -[2023-10-09 09:32:47,146][23469] Updated weights for policy 1, policy_version 31741 (0.0011) -[2023-10-09 09:32:50,477][23468] Updated weights for policy 0, policy_version 31593 (0.0009) -[2023-10-09 09:32:50,843][23468] Updated weights for policy 0, policy_version 31603 (0.0010) -[2023-10-09 09:32:50,954][23469] Updated weights for policy 1, policy_version 31751 (0.0009) -[2023-10-09 09:32:51,077][22500] Fps is (10 sec: 9830.5, 60 sec: 12015.0, 300 sec: 12996.1). Total num frames: 64847872. Throughput: 0: 1556.6, 1: 1566.5. Samples: 16222962. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:32:51,078][22500] Avg episode reward: [(0, '6.700'), (1, '6.680')] -[2023-10-09 09:32:51,215][23468] Updated weights for policy 0, policy_version 31613 (0.0010) -[2023-10-09 09:32:51,329][23469] Updated weights for policy 1, policy_version 31761 (0.0011) -[2023-10-09 09:32:51,693][23469] Updated weights for policy 1, policy_version 31771 (0.0010) -[2023-10-09 09:32:56,077][22500] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12996.1). Total num frames: 64913408. Throughput: 0: 1554.4, 1: 1557.5. Samples: 16240550. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:32:56,078][22500] Avg episode reward: [(0, '6.350'), (1, '6.750')] -[2023-10-09 09:32:57,171][23468] Updated weights for policy 0, policy_version 31623 (0.0011) -[2023-10-09 09:32:57,544][23468] Updated weights for policy 0, policy_version 31633 (0.0011) -[2023-10-09 09:32:57,909][23469] Updated weights for policy 1, policy_version 31781 (0.0010) -[2023-10-09 09:32:57,911][23468] Updated weights for policy 0, policy_version 31643 (0.0011) -[2023-10-09 09:32:58,286][23469] Updated weights for policy 1, policy_version 31791 (0.0010) -[2023-10-09 09:32:58,659][23469] Updated weights for policy 1, policy_version 31801 (0.0011) -[2023-10-09 09:33:01,077][22500] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12996.1). Total num frames: 64978944. Throughput: 0: 1500.9, 1: 1514.8. Samples: 16253930. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-09 09:33:01,078][22500] Avg episode reward: [(0, '6.250'), (1, '6.890')] -[2023-10-09 09:33:04,106][23468] Updated weights for policy 0, policy_version 31653 (0.0011) -[2023-10-09 09:33:04,480][23468] Updated weights for policy 0, policy_version 31663 (0.0010) -[2023-10-09 09:33:04,841][23469] Updated weights for policy 1, policy_version 31811 (0.0011) -[2023-10-09 09:33:04,851][23468] Updated weights for policy 0, policy_version 31673 (0.0012) -[2023-10-09 09:33:05,214][23469] Updated weights for policy 1, policy_version 31821 (0.0011) -[2023-10-09 09:33:05,596][23469] Updated weights for policy 1, policy_version 31831 (0.0011) -[2023-10-09 09:33:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12996.1). Total num frames: 65044480. Throughput: 0: 1462.5, 1: 1480.2. Samples: 16261426. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-09 09:33:06,078][22500] Avg episode reward: [(0, '6.330'), (1, '7.160')] -[2023-10-09 09:33:11,046][23468] Updated weights for policy 0, policy_version 31683 (0.0010) -[2023-10-09 09:33:11,079][22500] Fps is (10 sec: 6552.4, 60 sec: 10922.5, 300 sec: 12662.8). Total num frames: 65044480. Throughput: 0: 1417.4, 1: 1425.8. Samples: 16275264. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-09 09:33:11,080][22500] Avg episode reward: [(0, '6.450'), (1, '7.200')] -[2023-10-09 09:33:11,457][23468] Updated weights for policy 0, policy_version 31693 (0.0011) -[2023-10-09 09:33:11,821][23468] Updated weights for policy 0, policy_version 31703 (0.0011) -[2023-10-09 09:33:12,060][23469] Updated weights for policy 1, policy_version 31841 (0.0011) -[2023-10-09 09:33:12,426][23469] Updated weights for policy 1, policy_version 31851 (0.0011) -[2023-10-09 09:33:12,795][23469] Updated weights for policy 1, policy_version 31861 (0.0011) -[2023-10-09 09:33:13,165][23469] Updated weights for policy 1, policy_version 31871 (0.0012) -[2023-10-09 09:33:16,077][22500] Fps is (10 sec: 6553.6, 60 sec: 10922.7, 300 sec: 12662.9). Total num frames: 65110016. Throughput: 0: 1371.9, 1: 1372.4. Samples: 16289656. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-09 09:33:16,078][22500] Avg episode reward: [(0, '6.760'), (1, '7.310')] -[2023-10-09 09:33:17,316][23468] Updated weights for policy 0, policy_version 31713 (0.0011) -[2023-10-09 09:33:17,693][23468] Updated weights for policy 0, policy_version 31723 (0.0011) -[2023-10-09 09:33:18,065][23468] Updated weights for policy 0, policy_version 31733 (0.0011) -[2023-10-09 09:33:18,435][23469] Updated weights for policy 1, policy_version 31881 (0.0011) -[2023-10-09 09:33:18,440][23468] Updated weights for policy 0, policy_version 31743 (0.0011) -[2023-10-09 09:33:18,810][23469] Updated weights for policy 1, policy_version 31891 (0.0011) -[2023-10-09 09:33:19,186][23469] Updated weights for policy 1, policy_version 31901 (0.0011) -[2023-10-09 09:33:21,077][22500] Fps is (10 sec: 13109.6, 60 sec: 11468.8, 300 sec: 12662.9). Total num frames: 65175552. Throughput: 0: 1339.9, 1: 1351.9. Samples: 16297484. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-09 09:33:21,078][22500] Avg episode reward: [(0, '6.960'), (1, '7.270')] -[2023-10-09 09:33:24,053][23468] Updated weights for policy 0, policy_version 31753 (0.0011) -[2023-10-09 09:33:24,433][23468] Updated weights for policy 0, policy_version 31763 (0.0011) -[2023-10-09 09:33:24,592][23469] Updated weights for policy 1, policy_version 31911 (0.0011) -[2023-10-09 09:33:24,815][23468] Updated weights for policy 0, policy_version 31773 (0.0011) -[2023-10-09 09:33:24,970][23469] Updated weights for policy 1, policy_version 31921 (0.0010) -[2023-10-09 09:33:25,328][23469] Updated weights for policy 1, policy_version 31931 (0.0011) -[2023-10-09 09:33:26,078][22500] Fps is (10 sec: 13106.7, 60 sec: 11468.7, 300 sec: 12662.9). Total num frames: 65241088. Throughput: 0: 1304.8, 1: 1317.6. Samples: 16313372. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 09:33:26,078][22500] Avg episode reward: [(0, '6.570'), (1, '6.870')] -[2023-10-09 09:33:30,303][23468] Updated weights for policy 0, policy_version 31783 (0.0012) -[2023-10-09 09:33:30,681][23468] Updated weights for policy 0, policy_version 31793 (0.0011) -[2023-10-09 09:33:30,702][23469] Updated weights for policy 1, policy_version 31941 (0.0011) -[2023-10-09 09:33:31,049][23468] Updated weights for policy 0, policy_version 31803 (0.0011) -[2023-10-09 09:33:31,071][23469] Updated weights for policy 1, policy_version 31951 (0.0011) -[2023-10-09 09:33:31,077][22500] Fps is (10 sec: 6553.6, 60 sec: 10376.5, 300 sec: 12329.6). Total num frames: 65241088. Throughput: 0: 1273.6, 1: 1286.4. Samples: 16329474. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 09:33:31,078][22500] Avg episode reward: [(0, '6.820'), (1, '6.720')] -[2023-10-09 09:33:31,437][23469] Updated weights for policy 1, policy_version 31961 (0.0011) -[2023-10-09 09:33:35,992][23468] Updated weights for policy 0, policy_version 31813 (0.0011) -[2023-10-09 09:33:36,077][22500] Fps is (10 sec: 6553.8, 60 sec: 10376.5, 300 sec: 12329.6). Total num frames: 65306624. Throughput: 0: 1261.6, 1: 1278.9. Samples: 16337282. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 09:33:36,078][22500] Avg episode reward: [(0, '6.680'), (1, '6.870')] -[2023-10-09 09:33:36,368][23468] Updated weights for policy 0, policy_version 31823 (0.0011) -[2023-10-09 09:33:36,501][23469] Updated weights for policy 1, policy_version 31971 (0.0011) -[2023-10-09 09:33:36,739][23468] Updated weights for policy 0, policy_version 31833 (0.0010) -[2023-10-09 09:33:36,900][23469] Updated weights for policy 1, policy_version 31981 (0.0010) -[2023-10-09 09:33:37,281][23469] Updated weights for policy 1, policy_version 31991 (0.0010) -[2023-10-09 09:33:41,077][22500] Fps is (10 sec: 13107.3, 60 sec: 10376.5, 300 sec: 12329.7). Total num frames: 65372160. Throughput: 0: 1263.1, 1: 1277.5. Samples: 16354876. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 09:33:41,078][22500] Avg episode reward: [(0, '6.790'), (1, '6.790')] -[2023-10-09 09:33:41,452][23468] Updated weights for policy 0, policy_version 31843 (0.0010) -[2023-10-09 09:33:41,819][23468] Updated weights for policy 0, policy_version 31853 (0.0011) -[2023-10-09 09:33:41,957][23469] Updated weights for policy 1, policy_version 32001 (0.0010) -[2023-10-09 09:33:42,191][23468] Updated weights for policy 0, policy_version 31863 (0.0011) -[2023-10-09 09:33:42,320][23469] Updated weights for policy 1, policy_version 32011 (0.0010) -[2023-10-09 09:33:42,687][23469] Updated weights for policy 1, policy_version 32021 (0.0010) -[2023-10-09 09:33:43,056][23469] Updated weights for policy 1, policy_version 32031 (0.0010) -[2023-10-09 09:33:46,077][22500] Fps is (10 sec: 13107.2, 60 sec: 10922.7, 300 sec: 12329.7). Total num frames: 65437696. Throughput: 0: 1314.2, 1: 1319.7. Samples: 16372454. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 09:33:46,078][22500] Avg episode reward: [(0, '6.910'), (1, '6.890')] -[2023-10-09 09:33:47,081][23468] Updated weights for policy 0, policy_version 31873 (0.0010) -[2023-10-09 09:33:47,447][23468] Updated weights for policy 0, policy_version 31883 (0.0011) -[2023-10-09 09:33:47,830][23468] Updated weights for policy 0, policy_version 31893 (0.0012) -[2023-10-09 09:33:48,041][23469] Updated weights for policy 1, policy_version 32041 (0.0011) -[2023-10-09 09:33:48,204][23468] Updated weights for policy 0, policy_version 31903 (0.0010) -[2023-10-09 09:33:48,399][23469] Updated weights for policy 1, policy_version 32051 (0.0011) -[2023-10-09 09:33:48,773][23469] Updated weights for policy 1, policy_version 32061 (0.0010) -[2023-10-09 09:33:51,078][22500] Fps is (10 sec: 13106.8, 60 sec: 10922.6, 300 sec: 12329.6). Total num frames: 65503232. Throughput: 0: 1313.2, 1: 1324.4. Samples: 16380118. Policy #0 lag: (min: 12.0, avg: 12.3, max: 24.0) -[2023-10-09 09:33:51,078][22500] Avg episode reward: [(0, '6.750'), (1, '6.660')] -[2023-10-09 09:33:53,227][23468] Updated weights for policy 0, policy_version 31913 (0.0010) -[2023-10-09 09:33:53,602][23468] Updated weights for policy 0, policy_version 31923 (0.0010) -[2023-10-09 09:33:53,657][23469] Updated weights for policy 1, policy_version 32071 (0.0009) -[2023-10-09 09:33:53,967][23468] Updated weights for policy 0, policy_version 31933 (0.0010) -[2023-10-09 09:33:54,025][23469] Updated weights for policy 1, policy_version 32081 (0.0010) -[2023-10-09 09:33:54,397][23469] Updated weights for policy 1, policy_version 32091 (0.0011) -[2023-10-09 09:33:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 10922.7, 300 sec: 12329.7). Total num frames: 65568768. Throughput: 0: 1351.0, 1: 1359.8. Samples: 16397244. Policy #0 lag: (min: 12.0, avg: 12.3, max: 24.0) -[2023-10-09 09:33:56,078][22500] Avg episode reward: [(0, '7.140'), (1, '6.590')] -[2023-10-09 09:33:58,991][23468] Updated weights for policy 0, policy_version 31943 (0.0012) -[2023-10-09 09:33:59,303][23469] Updated weights for policy 1, policy_version 32101 (0.0010) -[2023-10-09 09:33:59,363][23468] Updated weights for policy 0, policy_version 31953 (0.0009) -[2023-10-09 09:33:59,674][23469] Updated weights for policy 1, policy_version 32111 (0.0009) -[2023-10-09 09:33:59,729][23468] Updated weights for policy 0, policy_version 31963 (0.0010) -[2023-10-09 09:34:00,048][23469] Updated weights for policy 1, policy_version 32121 (0.0010) -[2023-10-09 09:34:01,077][22500] Fps is (10 sec: 13107.6, 60 sec: 10922.7, 300 sec: 12218.6). Total num frames: 65634304. Throughput: 0: 1379.7, 1: 1387.2. Samples: 16414166. Policy #0 lag: (min: 12.0, avg: 12.3, max: 24.0) -[2023-10-09 09:34:01,078][22500] Avg episode reward: [(0, '6.990'), (1, '6.850')] -[2023-10-09 09:34:04,325][23468] Updated weights for policy 0, policy_version 31973 (0.0010) -[2023-10-09 09:34:04,559][23469] Updated weights for policy 1, policy_version 32131 (0.0011) -[2023-10-09 09:34:04,698][23468] Updated weights for policy 0, policy_version 31983 (0.0010) -[2023-10-09 09:34:04,937][23469] Updated weights for policy 1, policy_version 32141 (0.0010) -[2023-10-09 09:34:05,070][23468] Updated weights for policy 0, policy_version 31993 (0.0010) -[2023-10-09 09:34:05,296][23469] Updated weights for policy 1, policy_version 32151 (0.0010) -[2023-10-09 09:34:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 10922.7, 300 sec: 12218.6). Total num frames: 65699840. Throughput: 0: 1408.0, 1: 1412.2. Samples: 16424392. Policy #0 lag: (min: 12.0, avg: 12.3, max: 24.0) -[2023-10-09 09:34:06,078][22500] Avg episode reward: [(0, '6.520'), (1, '6.880')] -[2023-10-09 09:34:09,722][23468] Updated weights for policy 0, policy_version 32003 (0.0010) -[2023-10-09 09:34:09,999][23469] Updated weights for policy 1, policy_version 32161 (0.0010) -[2023-10-09 09:34:10,102][23468] Updated weights for policy 0, policy_version 32013 (0.0009) -[2023-10-09 09:34:10,363][23469] Updated weights for policy 1, policy_version 32171 (0.0009) -[2023-10-09 09:34:10,469][23468] Updated weights for policy 0, policy_version 32023 (0.0010) -[2023-10-09 09:34:10,736][23469] Updated weights for policy 1, policy_version 32181 (0.0011) -[2023-10-09 09:34:11,077][22500] Fps is (10 sec: 9830.3, 60 sec: 11469.1, 300 sec: 12107.5). Total num frames: 65732608. Throughput: 0: 1431.7, 1: 1438.5. Samples: 16442530. Policy #0 lag: (min: 38.0, avg: 54.9, max: 56.0) -[2023-10-09 09:34:11,078][22500] Avg episode reward: [(0, '6.770'), (1, '7.150')] -[2023-10-09 09:34:11,102][23469] Updated weights for policy 1, policy_version 32191 (0.0011) -[2023-10-09 09:34:14,905][23468] Updated weights for policy 0, policy_version 32033 (0.0010) -[2023-10-09 09:34:15,269][23468] Updated weights for policy 0, policy_version 32043 (0.0011) -[2023-10-09 09:34:15,493][23469] Updated weights for policy 1, policy_version 32201 (0.0011) -[2023-10-09 09:34:15,642][23468] Updated weights for policy 0, policy_version 32053 (0.0010) -[2023-10-09 09:34:15,851][23469] Updated weights for policy 1, policy_version 32211 (0.0010) -[2023-10-09 09:34:16,015][23468] Updated weights for policy 0, policy_version 32063 (0.0010) -[2023-10-09 09:34:16,077][22500] Fps is (10 sec: 9830.3, 60 sec: 11468.8, 300 sec: 12107.5). Total num frames: 65798144. Throughput: 0: 1458.1, 1: 1460.6. Samples: 16460816. Policy #0 lag: (min: 38.0, avg: 54.9, max: 56.0) -[2023-10-09 09:34:16,078][22500] Avg episode reward: [(0, '6.500'), (1, '7.400')] -[2023-10-09 09:34:16,086][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000032064_32833536.pth... -[2023-10-09 09:34:16,121][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000030720_31457280.pth -[2023-10-09 09:34:16,220][23469] Updated weights for policy 1, policy_version 32221 (0.0010) -[2023-10-09 09:34:16,331][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000032224_32997376.pth... -[2023-10-09 09:34:16,368][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000030848_31588352.pth -[2023-10-09 09:34:20,444][23468] Updated weights for policy 0, policy_version 32073 (0.0011) -[2023-10-09 09:34:20,819][23468] Updated weights for policy 0, policy_version 32083 (0.0011) -[2023-10-09 09:34:20,849][23469] Updated weights for policy 1, policy_version 32231 (0.0010) -[2023-10-09 09:34:21,077][22500] Fps is (10 sec: 9830.6, 60 sec: 10922.7, 300 sec: 11996.4). Total num frames: 65830912. Throughput: 0: 1472.2, 1: 1476.2. Samples: 16469960. Policy #0 lag: (min: 38.0, avg: 54.9, max: 56.0) -[2023-10-09 09:34:21,078][22500] Avg episode reward: [(0, '7.020'), (1, '7.090')] -[2023-10-09 09:34:21,183][23468] Updated weights for policy 0, policy_version 32093 (0.0009) -[2023-10-09 09:34:21,226][23469] Updated weights for policy 1, policy_version 32241 (0.0010) -[2023-10-09 09:34:21,596][23469] Updated weights for policy 1, policy_version 32251 (0.0011) -[2023-10-09 09:34:26,011][23468] Updated weights for policy 0, policy_version 32103 (0.0009) -[2023-10-09 09:34:26,077][22500] Fps is (10 sec: 9830.5, 60 sec: 10922.8, 300 sec: 11885.3). Total num frames: 65896448. Throughput: 0: 1479.7, 1: 1481.8. Samples: 16488142. Policy #0 lag: (min: 38.0, avg: 54.9, max: 56.0) -[2023-10-09 09:34:26,078][22500] Avg episode reward: [(0, '7.130'), (1, '6.950')] -[2023-10-09 09:34:26,328][23469] Updated weights for policy 1, policy_version 32261 (0.0011) -[2023-10-09 09:34:26,378][23468] Updated weights for policy 0, policy_version 32113 (0.0011) -[2023-10-09 09:34:26,704][23469] Updated weights for policy 1, policy_version 32271 (0.0011) -[2023-10-09 09:34:26,749][23468] Updated weights for policy 0, policy_version 32123 (0.0011) -[2023-10-09 09:34:27,069][23469] Updated weights for policy 1, policy_version 32281 (0.0011) -[2023-10-09 09:34:31,077][22500] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 11885.3). Total num frames: 65961984. Throughput: 0: 1479.0, 1: 1490.4. Samples: 16506076. Policy #0 lag: (min: 38.0, avg: 54.9, max: 56.0) -[2023-10-09 09:34:31,078][22500] Avg episode reward: [(0, '6.810'), (1, '6.450')] -[2023-10-09 09:34:31,456][23468] Updated weights for policy 0, policy_version 32133 (0.0011) -[2023-10-09 09:34:31,746][23469] Updated weights for policy 1, policy_version 32291 (0.0010) -[2023-10-09 09:34:31,842][23468] Updated weights for policy 0, policy_version 32143 (0.0012) -[2023-10-09 09:34:32,123][23469] Updated weights for policy 1, policy_version 32301 (0.0010) -[2023-10-09 09:34:32,205][23468] Updated weights for policy 0, policy_version 32153 (0.0009) -[2023-10-09 09:34:32,492][23469] Updated weights for policy 1, policy_version 32311 (0.0010) -[2023-10-09 09:34:36,077][22500] Fps is (10 sec: 13107.1, 60 sec: 12015.0, 300 sec: 11885.3). Total num frames: 66027520. Throughput: 0: 1485.5, 1: 1492.2. Samples: 16514114. Policy #0 lag: (min: 30.0, avg: 30.7, max: 43.0) -[2023-10-09 09:34:36,078][22500] Avg episode reward: [(0, '6.850'), (1, '6.300')] -[2023-10-09 09:34:36,836][23468] Updated weights for policy 0, policy_version 32163 (0.0010) -[2023-10-09 09:34:37,036][23469] Updated weights for policy 1, policy_version 32321 (0.0011) -[2023-10-09 09:34:37,202][23468] Updated weights for policy 0, policy_version 32173 (0.0010) -[2023-10-09 09:34:37,399][23469] Updated weights for policy 1, policy_version 32331 (0.0010) -[2023-10-09 09:34:37,581][23468] Updated weights for policy 0, policy_version 32183 (0.0011) -[2023-10-09 09:34:37,767][23469] Updated weights for policy 1, policy_version 32341 (0.0010) -[2023-10-09 09:34:38,135][23469] Updated weights for policy 1, policy_version 32351 (0.0010) -[2023-10-09 09:34:41,078][22500] Fps is (10 sec: 13106.9, 60 sec: 12014.9, 300 sec: 11885.3). Total num frames: 66093056. Throughput: 0: 1489.7, 1: 1497.9. Samples: 16531690. Policy #0 lag: (min: 30.0, avg: 30.7, max: 43.0) -[2023-10-09 09:34:41,078][22500] Avg episode reward: [(0, '7.070'), (1, '6.220')] -[2023-10-09 09:34:43,037][23468] Updated weights for policy 0, policy_version 32193 (0.0010) -[2023-10-09 09:34:43,410][23468] Updated weights for policy 0, policy_version 32203 (0.0011) -[2023-10-09 09:34:43,490][23469] Updated weights for policy 1, policy_version 32361 (0.0011) -[2023-10-09 09:34:43,785][23468] Updated weights for policy 0, policy_version 32213 (0.0011) -[2023-10-09 09:34:43,858][23469] Updated weights for policy 1, policy_version 32371 (0.0011) -[2023-10-09 09:34:44,149][23468] Updated weights for policy 0, policy_version 32223 (0.0010) -[2023-10-09 09:34:44,229][23469] Updated weights for policy 1, policy_version 32381 (0.0009) -[2023-10-09 09:34:46,077][22500] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 11885.3). Total num frames: 66158592. Throughput: 0: 1482.9, 1: 1492.6. Samples: 16548064. Policy #0 lag: (min: 30.0, avg: 30.7, max: 43.0) -[2023-10-09 09:34:46,078][22500] Avg episode reward: [(0, '7.090'), (1, '6.280')] -[2023-10-09 09:34:48,861][23468] Updated weights for policy 0, policy_version 32233 (0.0010) -[2023-10-09 09:34:48,885][23469] Updated weights for policy 1, policy_version 32391 (0.0010) -[2023-10-09 09:34:49,229][23468] Updated weights for policy 0, policy_version 32243 (0.0010) -[2023-10-09 09:34:49,249][23469] Updated weights for policy 1, policy_version 32401 (0.0010) -[2023-10-09 09:34:49,595][23468] Updated weights for policy 0, policy_version 32253 (0.0010) -[2023-10-09 09:34:49,608][23469] Updated weights for policy 1, policy_version 32411 (0.0011) -[2023-10-09 09:34:51,077][22500] Fps is (10 sec: 13107.5, 60 sec: 12015.0, 300 sec: 11885.3). Total num frames: 66224128. Throughput: 0: 1483.8, 1: 1489.9. Samples: 16558208. Policy #0 lag: (min: 30.0, avg: 30.7, max: 43.0) -[2023-10-09 09:34:51,078][22500] Avg episode reward: [(0, '6.860'), (1, '6.420')] -[2023-10-09 09:34:54,836][23468] Updated weights for policy 0, policy_version 32263 (0.0011) -[2023-10-09 09:34:54,846][23469] Updated weights for policy 1, policy_version 32421 (0.0011) -[2023-10-09 09:34:55,209][23468] Updated weights for policy 0, policy_version 32273 (0.0010) -[2023-10-09 09:34:55,210][23469] Updated weights for policy 1, policy_version 32431 (0.0011) -[2023-10-09 09:34:55,574][23468] Updated weights for policy 0, policy_version 32283 (0.0013) -[2023-10-09 09:34:55,584][23469] Updated weights for policy 1, policy_version 32441 (0.0011) -[2023-10-09 09:34:56,077][22500] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 11774.3). Total num frames: 66289664. Throughput: 0: 1458.2, 1: 1464.7. Samples: 16574060. Policy #0 lag: (min: 29.0, avg: 38.8, max: 61.0) -[2023-10-09 09:34:56,078][22500] Avg episode reward: [(0, '6.510'), (1, '6.970')] -[2023-10-09 09:35:00,416][23469] Updated weights for policy 1, policy_version 32451 (0.0009) -[2023-10-09 09:35:00,464][23468] Updated weights for policy 0, policy_version 32293 (0.0011) -[2023-10-09 09:35:00,786][23469] Updated weights for policy 1, policy_version 32461 (0.0010) -[2023-10-09 09:35:00,840][23468] Updated weights for policy 0, policy_version 32303 (0.0010) -[2023-10-09 09:35:01,077][22500] Fps is (10 sec: 6553.6, 60 sec: 10922.7, 300 sec: 11552.1). Total num frames: 66289664. Throughput: 0: 1444.3, 1: 1450.1. Samples: 16591064. Policy #0 lag: (min: 29.0, avg: 38.8, max: 61.0) -[2023-10-09 09:35:01,078][22500] Avg episode reward: [(0, '6.440'), (1, '7.220')] -[2023-10-09 09:35:01,162][23469] Updated weights for policy 1, policy_version 32471 (0.0010) -[2023-10-09 09:35:01,209][23468] Updated weights for policy 0, policy_version 32313 (0.0011) -[2023-10-09 09:35:05,925][23469] Updated weights for policy 1, policy_version 32481 (0.0011) -[2023-10-09 09:35:06,059][23468] Updated weights for policy 0, policy_version 32323 (0.0011) -[2023-10-09 09:35:06,077][22500] Fps is (10 sec: 6553.6, 60 sec: 10922.7, 300 sec: 11552.1). Total num frames: 66355200. Throughput: 0: 1433.2, 1: 1442.6. Samples: 16599372. Policy #0 lag: (min: 29.0, avg: 38.8, max: 61.0) -[2023-10-09 09:35:06,078][22500] Avg episode reward: [(0, '6.610'), (1, '6.970')] -[2023-10-09 09:35:06,357][23469] Updated weights for policy 1, policy_version 32491 (0.0011) -[2023-10-09 09:35:06,434][23468] Updated weights for policy 0, policy_version 32333 (0.0010) -[2023-10-09 09:35:06,717][23469] Updated weights for policy 1, policy_version 32501 (0.0009) -[2023-10-09 09:35:06,806][23468] Updated weights for policy 0, policy_version 32343 (0.0010) -[2023-10-09 09:35:07,087][23469] Updated weights for policy 1, policy_version 32511 (0.0010) -[2023-10-09 09:35:11,077][22500] Fps is (10 sec: 13107.2, 60 sec: 11468.8, 300 sec: 11552.1). Total num frames: 66420736. Throughput: 0: 1421.2, 1: 1435.1. Samples: 16616674. Policy #0 lag: (min: 29.0, avg: 38.8, max: 61.0) -[2023-10-09 09:35:11,078][22500] Avg episode reward: [(0, '6.320'), (1, '6.190')] -[2023-10-09 09:35:11,502][23468] Updated weights for policy 0, policy_version 32353 (0.0010) -[2023-10-09 09:35:11,794][23469] Updated weights for policy 1, policy_version 32521 (0.0011) -[2023-10-09 09:35:11,868][23468] Updated weights for policy 0, policy_version 32363 (0.0011) -[2023-10-09 09:35:12,167][23469] Updated weights for policy 1, policy_version 32531 (0.0010) -[2023-10-09 09:35:12,244][23468] Updated weights for policy 0, policy_version 32373 (0.0011) -[2023-10-09 09:35:12,539][23469] Updated weights for policy 1, policy_version 32541 (0.0010) -[2023-10-09 09:35:12,606][23468] Updated weights for policy 0, policy_version 32383 (0.0010) -[2023-10-09 09:35:16,077][22500] Fps is (10 sec: 13107.1, 60 sec: 11468.8, 300 sec: 11441.0). Total num frames: 66486272. Throughput: 0: 1425.8, 1: 1436.6. Samples: 16634884. Policy #0 lag: (min: 29.0, avg: 38.8, max: 61.0) -[2023-10-09 09:35:16,078][22500] Avg episode reward: [(0, '6.780'), (1, '6.130')] -[2023-10-09 09:35:17,222][23469] Updated weights for policy 1, policy_version 32551 (0.0010) -[2023-10-09 09:35:17,352][23468] Updated weights for policy 0, policy_version 32393 (0.0010) -[2023-10-09 09:35:17,599][23469] Updated weights for policy 1, policy_version 32561 (0.0010) -[2023-10-09 09:35:17,722][23468] Updated weights for policy 0, policy_version 32403 (0.0010) -[2023-10-09 09:35:17,960][23469] Updated weights for policy 1, policy_version 32571 (0.0010) -[2023-10-09 09:35:18,090][23468] Updated weights for policy 0, policy_version 32413 (0.0011) -[2023-10-09 09:35:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 11441.0). Total num frames: 66551808. Throughput: 0: 1423.5, 1: 1439.3. Samples: 16642942. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 09:35:21,078][22500] Avg episode reward: [(0, '6.970'), (1, '6.680')] -[2023-10-09 09:35:22,502][23469] Updated weights for policy 1, policy_version 32581 (0.0010) -[2023-10-09 09:35:22,737][23468] Updated weights for policy 0, policy_version 32423 (0.0011) -[2023-10-09 09:35:22,865][23469] Updated weights for policy 1, policy_version 32591 (0.0010) -[2023-10-09 09:35:23,107][23468] Updated weights for policy 0, policy_version 32433 (0.0010) -[2023-10-09 09:35:23,241][23469] Updated weights for policy 1, policy_version 32601 (0.0011) -[2023-10-09 09:35:23,483][23468] Updated weights for policy 0, policy_version 32443 (0.0010) -[2023-10-09 09:35:26,077][22500] Fps is (10 sec: 13107.3, 60 sec: 12014.9, 300 sec: 11441.0). Total num frames: 66617344. Throughput: 0: 1430.9, 1: 1450.1. Samples: 16661336. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 09:35:26,078][22500] Avg episode reward: [(0, '7.260'), (1, '6.950')] -[2023-10-09 09:35:27,869][23469] Updated weights for policy 1, policy_version 32611 (0.0010) -[2023-10-09 09:35:28,186][23468] Updated weights for policy 0, policy_version 32453 (0.0009) -[2023-10-09 09:35:28,239][23469] Updated weights for policy 1, policy_version 32621 (0.0011) -[2023-10-09 09:35:28,562][23468] Updated weights for policy 0, policy_version 32463 (0.0011) -[2023-10-09 09:35:28,611][23469] Updated weights for policy 1, policy_version 32631 (0.0011) -[2023-10-09 09:35:28,950][23468] Updated weights for policy 0, policy_version 32473 (0.0011) -[2023-10-09 09:35:31,077][22500] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 11441.0). Total num frames: 66682880. Throughput: 0: 1439.8, 1: 1449.7. Samples: 16678092. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 09:35:31,078][22500] Avg episode reward: [(0, '6.730'), (1, '7.310')] -[2023-10-09 09:35:34,516][23469] Updated weights for policy 1, policy_version 32641 (0.0011) -[2023-10-09 09:35:34,892][23469] Updated weights for policy 1, policy_version 32651 (0.0011) -[2023-10-09 09:35:34,990][23468] Updated weights for policy 0, policy_version 32483 (0.0010) -[2023-10-09 09:35:35,253][23469] Updated weights for policy 1, policy_version 32661 (0.0011) -[2023-10-09 09:35:35,380][23468] Updated weights for policy 0, policy_version 32493 (0.0010) -[2023-10-09 09:35:35,627][23469] Updated weights for policy 1, policy_version 32671 (0.0012) -[2023-10-09 09:35:35,747][23468] Updated weights for policy 0, policy_version 32503 (0.0011) -[2023-10-09 09:35:36,079][22500] Fps is (10 sec: 13104.9, 60 sec: 12014.6, 300 sec: 11552.1). Total num frames: 66748416. Throughput: 0: 1411.6, 1: 1424.3. Samples: 16685826. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 09:35:36,080][22500] Avg episode reward: [(0, '6.790'), (1, '7.000')] -[2023-10-09 09:35:41,077][22500] Fps is (10 sec: 6553.5, 60 sec: 10922.7, 300 sec: 11329.9). Total num frames: 66748416. Throughput: 0: 1394.5, 1: 1404.0. Samples: 16699990. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 09:35:41,079][22500] Avg episode reward: [(0, '6.900'), (1, '6.690')] -[2023-10-09 09:35:41,503][23468] Updated weights for policy 0, policy_version 32513 (0.0010) -[2023-10-09 09:35:41,549][23469] Updated weights for policy 1, policy_version 32681 (0.0009) -[2023-10-09 09:35:41,869][23468] Updated weights for policy 0, policy_version 32523 (0.0008) -[2023-10-09 09:35:41,917][23469] Updated weights for policy 1, policy_version 32691 (0.0008) -[2023-10-09 09:35:42,231][23468] Updated weights for policy 0, policy_version 32533 (0.0008) -[2023-10-09 09:35:42,273][23469] Updated weights for policy 1, policy_version 32701 (0.0009) -[2023-10-09 09:35:42,606][23468] Updated weights for policy 0, policy_version 32543 (0.0008) -[2023-10-09 09:35:46,077][22500] Fps is (10 sec: 6554.8, 60 sec: 10922.7, 300 sec: 11330.0). Total num frames: 66813952. Throughput: 0: 1421.9, 1: 1443.2. Samples: 16719992. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:35:46,078][22500] Avg episode reward: [(0, '6.730'), (1, '6.760')] -[2023-10-09 09:35:46,094][23469] Updated weights for policy 1, policy_version 32711 (0.0009) -[2023-10-09 09:35:46,357][23468] Updated weights for policy 0, policy_version 32553 (0.0009) -[2023-10-09 09:35:46,471][23469] Updated weights for policy 1, policy_version 32721 (0.0008) -[2023-10-09 09:35:46,722][23468] Updated weights for policy 0, policy_version 32563 (0.0008) -[2023-10-09 09:35:46,830][23469] Updated weights for policy 1, policy_version 32731 (0.0008) -[2023-10-09 09:35:47,096][23468] Updated weights for policy 0, policy_version 32573 (0.0009) -[2023-10-09 09:35:50,672][23469] Updated weights for policy 1, policy_version 32741 (0.0009) -[2023-10-09 09:35:51,059][23469] Updated weights for policy 1, policy_version 32751 (0.0010) -[2023-10-09 09:35:51,076][23468] Updated weights for policy 0, policy_version 32583 (0.0008) -[2023-10-09 09:35:51,077][22500] Fps is (10 sec: 13107.4, 60 sec: 10922.7, 300 sec: 11441.0). Total num frames: 66879488. Throughput: 0: 1437.8, 1: 1455.3. Samples: 16729560. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:35:51,078][22500] Avg episode reward: [(0, '6.600'), (1, '6.590')] -[2023-10-09 09:35:51,437][23469] Updated weights for policy 1, policy_version 32761 (0.0008) -[2023-10-09 09:35:51,452][23468] Updated weights for policy 0, policy_version 32593 (0.0008) -[2023-10-09 09:35:51,829][23468] Updated weights for policy 0, policy_version 32603 (0.0010) -[2023-10-09 09:35:55,091][23469] Updated weights for policy 1, policy_version 32771 (0.0008) -[2023-10-09 09:35:55,466][23469] Updated weights for policy 1, policy_version 32781 (0.0009) -[2023-10-09 09:35:55,525][23468] Updated weights for policy 0, policy_version 32613 (0.0007) -[2023-10-09 09:35:55,836][23469] Updated weights for policy 1, policy_version 32791 (0.0008) -[2023-10-09 09:35:55,905][23468] Updated weights for policy 0, policy_version 32623 (0.0008) -[2023-10-09 09:35:56,077][22500] Fps is (10 sec: 13107.0, 60 sec: 10922.7, 300 sec: 11552.1). Total num frames: 66945024. Throughput: 0: 1492.8, 1: 1510.1. Samples: 16751808. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:35:56,078][22500] Avg episode reward: [(0, '6.710'), (1, '6.910')] -[2023-10-09 09:35:56,276][23468] Updated weights for policy 0, policy_version 32633 (0.0009) -[2023-10-09 09:35:59,727][23469] Updated weights for policy 1, policy_version 32801 (0.0008) -[2023-10-09 09:36:00,036][23468] Updated weights for policy 0, policy_version 32643 (0.0009) -[2023-10-09 09:36:00,108][23469] Updated weights for policy 1, policy_version 32811 (0.0007) -[2023-10-09 09:36:00,413][23468] Updated weights for policy 0, policy_version 32653 (0.0010) -[2023-10-09 09:36:00,472][23469] Updated weights for policy 1, policy_version 32821 (0.0007) -[2023-10-09 09:36:00,786][23468] Updated weights for policy 0, policy_version 32663 (0.0009) -[2023-10-09 09:36:00,842][23469] Updated weights for policy 1, policy_version 32831 (0.0010) -[2023-10-09 09:36:01,078][22500] Fps is (10 sec: 16383.6, 60 sec: 12561.0, 300 sec: 11663.2). Total num frames: 67043328. Throughput: 0: 1529.3, 1: 1529.1. Samples: 16772512. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:36:01,079][22500] Avg episode reward: [(0, '7.120'), (1, '6.820')] -[2023-10-09 09:36:04,551][23469] Updated weights for policy 1, policy_version 32841 (0.0008) -[2023-10-09 09:36:04,564][23468] Updated weights for policy 0, policy_version 32673 (0.0011) -[2023-10-09 09:36:04,917][23469] Updated weights for policy 1, policy_version 32851 (0.0008) -[2023-10-09 09:36:04,933][23468] Updated weights for policy 0, policy_version 32683 (0.0009) -[2023-10-09 09:36:05,283][23469] Updated weights for policy 1, policy_version 32861 (0.0008) -[2023-10-09 09:36:05,313][23468] Updated weights for policy 0, policy_version 32693 (0.0009) -[2023-10-09 09:36:05,686][23468] Updated weights for policy 0, policy_version 32703 (0.0009) -[2023-10-09 09:36:06,077][22500] Fps is (10 sec: 19660.8, 60 sec: 13107.2, 300 sec: 11774.3). Total num frames: 67141632. Throughput: 0: 1559.1, 1: 1575.7. Samples: 16784008. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 09:36:06,078][22500] Avg episode reward: [(0, '7.470'), (1, '7.010')] -[2023-10-09 09:36:09,066][23469] Updated weights for policy 1, policy_version 32871 (0.0009) -[2023-10-09 09:36:09,439][23468] Updated weights for policy 0, policy_version 32713 (0.0007) -[2023-10-09 09:36:09,439][23469] Updated weights for policy 1, policy_version 32881 (0.0008) -[2023-10-09 09:36:09,808][23468] Updated weights for policy 0, policy_version 32723 (0.0008) -[2023-10-09 09:36:09,815][23469] Updated weights for policy 1, policy_version 32891 (0.0008) -[2023-10-09 09:36:10,177][23468] Updated weights for policy 0, policy_version 32733 (0.0011) -[2023-10-09 09:36:11,077][22500] Fps is (10 sec: 16384.4, 60 sec: 13107.2, 300 sec: 11885.3). Total num frames: 67207168. Throughput: 0: 1598.0, 1: 1592.5. Samples: 16804910. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 09:36:11,078][22500] Avg episode reward: [(0, '7.710'), (1, '7.020')] -[2023-10-09 09:36:13,551][23469] Updated weights for policy 1, policy_version 32901 (0.0009) -[2023-10-09 09:36:13,930][23469] Updated weights for policy 1, policy_version 32911 (0.0009) -[2023-10-09 09:36:14,036][23468] Updated weights for policy 0, policy_version 32743 (0.0008) -[2023-10-09 09:36:14,289][23469] Updated weights for policy 1, policy_version 32921 (0.0008) -[2023-10-09 09:36:14,407][23468] Updated weights for policy 0, policy_version 32753 (0.0007) -[2023-10-09 09:36:14,784][23468] Updated weights for policy 0, policy_version 32763 (0.0008) -[2023-10-09 09:36:16,077][22500] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 11885.3). Total num frames: 67272704. Throughput: 0: 1625.8, 1: 1647.5. Samples: 16825392. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 09:36:16,078][22500] Avg episode reward: [(0, '8.290'), (1, '6.550')] -[2023-10-09 09:36:16,087][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000032768_33554432.pth... -[2023-10-09 09:36:16,088][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000032928_33718272.pth... -[2023-10-09 09:36:16,122][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000031552_32309248.pth -[2023-10-09 09:36:16,125][23343] Saving a milestone ./train_atari/atari_berzerk_APPO/checkpoint_p1/milestones/checkpoint_000032928_33718272.pth -[2023-10-09 09:36:16,127][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000031392_32145408.pth -[2023-10-09 09:36:16,131][23265] Saving new best policy, reward=8.290! -[2023-10-09 09:36:16,176][23265] Saving a milestone ./train_atari/atari_berzerk_APPO/checkpoint_p0/milestones/checkpoint_000032768_33554432.pth -[2023-10-09 09:36:18,107][23469] Updated weights for policy 1, policy_version 32931 (0.0009) -[2023-10-09 09:36:18,488][23469] Updated weights for policy 1, policy_version 32941 (0.0008) -[2023-10-09 09:36:18,495][23468] Updated weights for policy 0, policy_version 32773 (0.0007) -[2023-10-09 09:36:18,861][23469] Updated weights for policy 1, policy_version 32951 (0.0008) -[2023-10-09 09:36:18,869][23468] Updated weights for policy 0, policy_version 32783 (0.0008) -[2023-10-09 09:36:19,249][23468] Updated weights for policy 0, policy_version 32793 (0.0007) -[2023-10-09 09:36:21,077][22500] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 11996.4). Total num frames: 67338240. Throughput: 0: 1682.4, 1: 1676.5. Samples: 16836968. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 09:36:21,078][22500] Avg episode reward: [(0, '7.650'), (1, '6.440')] -[2023-10-09 09:36:22,620][23469] Updated weights for policy 1, policy_version 32961 (0.0009) -[2023-10-09 09:36:22,990][23469] Updated weights for policy 1, policy_version 32971 (0.0011) -[2023-10-09 09:36:23,358][23469] Updated weights for policy 1, policy_version 32981 (0.0010) -[2023-10-09 09:36:23,401][23468] Updated weights for policy 0, policy_version 32803 (0.0010) -[2023-10-09 09:36:23,730][23469] Updated weights for policy 1, policy_version 32991 (0.0010) -[2023-10-09 09:36:23,780][23468] Updated weights for policy 0, policy_version 32813 (0.0011) -[2023-10-09 09:36:24,151][23468] Updated weights for policy 0, policy_version 32823 (0.0012) -[2023-10-09 09:36:26,077][22500] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 11996.4). Total num frames: 67403776. Throughput: 0: 1724.3, 1: 1731.8. Samples: 16855514. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 09:36:26,078][22500] Avg episode reward: [(0, '7.120'), (1, '6.340')] -[2023-10-09 09:36:29,575][23469] Updated weights for policy 1, policy_version 33001 (0.0011) -[2023-10-09 09:36:29,941][23469] Updated weights for policy 1, policy_version 33011 (0.0011) -[2023-10-09 09:36:30,305][23469] Updated weights for policy 1, policy_version 33021 (0.0015) -[2023-10-09 09:36:30,315][23468] Updated weights for policy 0, policy_version 32833 (0.0010) -[2023-10-09 09:36:30,698][23468] Updated weights for policy 0, policy_version 32843 (0.0010) -[2023-10-09 09:36:31,066][23468] Updated weights for policy 0, policy_version 32853 (0.0010) -[2023-10-09 09:36:31,077][22500] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 11885.3). Total num frames: 67436544. Throughput: 0: 1675.7, 1: 1663.2. Samples: 16870242. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 09:36:31,078][22500] Avg episode reward: [(0, '6.480'), (1, '6.410')] -[2023-10-09 09:36:31,435][23468] Updated weights for policy 0, policy_version 32863 (0.0011) -[2023-10-09 09:36:36,073][23469] Updated weights for policy 1, policy_version 33031 (0.0009) -[2023-10-09 09:36:36,077][22500] Fps is (10 sec: 6553.6, 60 sec: 12015.3, 300 sec: 11774.3). Total num frames: 67469312. Throughput: 0: 1643.3, 1: 1643.1. Samples: 16877450. Policy #0 lag: (min: 11.0, avg: 17.2, max: 43.0) -[2023-10-09 09:36:36,078][22500] Avg episode reward: [(0, '6.670'), (1, '6.550')] -[2023-10-09 09:36:36,447][23469] Updated weights for policy 1, policy_version 33041 (0.0009) -[2023-10-09 09:36:36,736][23468] Updated weights for policy 0, policy_version 32873 (0.0009) -[2023-10-09 09:36:36,816][23469] Updated weights for policy 1, policy_version 33051 (0.0007) -[2023-10-09 09:36:37,110][23468] Updated weights for policy 0, policy_version 32883 (0.0008) -[2023-10-09 09:36:37,486][23468] Updated weights for policy 0, policy_version 32893 (0.0007) -[2023-10-09 09:36:40,934][23469] Updated weights for policy 1, policy_version 33061 (0.0009) -[2023-10-09 09:36:41,077][22500] Fps is (10 sec: 9830.5, 60 sec: 13107.2, 300 sec: 11774.3). Total num frames: 67534848. Throughput: 0: 1608.8, 1: 1614.0. Samples: 16896836. Policy #0 lag: (min: 11.0, avg: 17.2, max: 43.0) -[2023-10-09 09:36:41,078][22500] Avg episode reward: [(0, '6.550'), (1, '6.820')] -[2023-10-09 09:36:41,316][23469] Updated weights for policy 1, policy_version 33071 (0.0008) -[2023-10-09 09:36:41,413][23468] Updated weights for policy 0, policy_version 32903 (0.0008) -[2023-10-09 09:36:41,683][23469] Updated weights for policy 1, policy_version 33081 (0.0009) -[2023-10-09 09:36:41,792][23468] Updated weights for policy 0, policy_version 32913 (0.0008) -[2023-10-09 09:36:42,160][23468] Updated weights for policy 0, policy_version 32923 (0.0009) -[2023-10-09 09:36:45,432][23469] Updated weights for policy 1, policy_version 33091 (0.0009) -[2023-10-09 09:36:45,796][23469] Updated weights for policy 1, policy_version 33101 (0.0010) -[2023-10-09 09:36:45,856][23468] Updated weights for policy 0, policy_version 32933 (0.0008) -[2023-10-09 09:36:46,078][22500] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 11774.3). Total num frames: 67600384. Throughput: 0: 1615.2, 1: 1623.3. Samples: 16918244. Policy #0 lag: (min: 11.0, avg: 17.2, max: 43.0) -[2023-10-09 09:36:46,079][22500] Avg episode reward: [(0, '6.570'), (1, '6.750')] -[2023-10-09 09:36:46,162][23469] Updated weights for policy 1, policy_version 33111 (0.0007) -[2023-10-09 09:36:46,222][23468] Updated weights for policy 0, policy_version 32943 (0.0009) -[2023-10-09 09:36:46,607][23468] Updated weights for policy 0, policy_version 32953 (0.0011) -[2023-10-09 09:36:49,993][23469] Updated weights for policy 1, policy_version 33121 (0.0008) -[2023-10-09 09:36:50,358][23469] Updated weights for policy 1, policy_version 33131 (0.0007) -[2023-10-09 09:36:50,375][23468] Updated weights for policy 0, policy_version 32963 (0.0011) -[2023-10-09 09:36:50,726][23469] Updated weights for policy 1, policy_version 33141 (0.0007) -[2023-10-09 09:36:50,741][23468] Updated weights for policy 0, policy_version 32973 (0.0008) -[2023-10-09 09:36:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 11774.3). Total num frames: 67665920. Throughput: 0: 1603.6, 1: 1605.7. Samples: 16928430. Policy #0 lag: (min: 11.0, avg: 17.2, max: 43.0) -[2023-10-09 09:36:51,078][22500] Avg episode reward: [(0, '6.760'), (1, '6.690')] -[2023-10-09 09:36:51,095][23469] Updated weights for policy 1, policy_version 33151 (0.0008) -[2023-10-09 09:36:51,117][23468] Updated weights for policy 0, policy_version 32983 (0.0007) -[2023-10-09 09:36:54,822][23469] Updated weights for policy 1, policy_version 33161 (0.0007) -[2023-10-09 09:36:54,889][23468] Updated weights for policy 0, policy_version 32993 (0.0008) -[2023-10-09 09:36:55,182][23469] Updated weights for policy 1, policy_version 33171 (0.0009) -[2023-10-09 09:36:55,255][23468] Updated weights for policy 0, policy_version 33003 (0.0009) -[2023-10-09 09:36:55,555][23469] Updated weights for policy 1, policy_version 33181 (0.0008) -[2023-10-09 09:36:55,625][23468] Updated weights for policy 0, policy_version 33013 (0.0009) -[2023-10-09 09:36:56,005][23468] Updated weights for policy 0, policy_version 33023 (0.0011) -[2023-10-09 09:36:56,077][22500] Fps is (10 sec: 19661.0, 60 sec: 14199.4, 300 sec: 11996.4). Total num frames: 67796992. Throughput: 0: 1609.7, 1: 1624.7. Samples: 16950462. Policy #0 lag: (min: 13.0, avg: 14.9, max: 43.0) -[2023-10-09 09:36:56,078][22500] Avg episode reward: [(0, '7.130'), (1, '6.480')] -[2023-10-09 09:36:59,496][23469] Updated weights for policy 1, policy_version 33191 (0.0009) -[2023-10-09 09:36:59,863][23469] Updated weights for policy 1, policy_version 33201 (0.0007) -[2023-10-09 09:36:59,911][23468] Updated weights for policy 0, policy_version 33033 (0.0009) -[2023-10-09 09:37:00,231][23469] Updated weights for policy 1, policy_version 33211 (0.0007) -[2023-10-09 09:37:00,279][23468] Updated weights for policy 0, policy_version 33043 (0.0008) -[2023-10-09 09:37:00,648][23468] Updated weights for policy 0, policy_version 33053 (0.0009) -[2023-10-09 09:37:01,077][22500] Fps is (10 sec: 19660.5, 60 sec: 13653.4, 300 sec: 11996.4). Total num frames: 67862528. Throughput: 0: 1617.7, 1: 1602.4. Samples: 16970298. Policy #0 lag: (min: 13.0, avg: 14.9, max: 43.0) -[2023-10-09 09:37:01,078][22500] Avg episode reward: [(0, '7.270'), (1, '6.520')] -[2023-10-09 09:37:04,054][23469] Updated weights for policy 1, policy_version 33221 (0.0007) -[2023-10-09 09:37:04,337][23468] Updated weights for policy 0, policy_version 33063 (0.0009) -[2023-10-09 09:37:04,430][23469] Updated weights for policy 1, policy_version 33231 (0.0008) -[2023-10-09 09:37:04,713][23468] Updated weights for policy 0, policy_version 33073 (0.0008) -[2023-10-09 09:37:04,793][23469] Updated weights for policy 1, policy_version 33241 (0.0009) -[2023-10-09 09:37:05,091][23468] Updated weights for policy 0, policy_version 33083 (0.0008) -[2023-10-09 09:37:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 11996.5). Total num frames: 67928064. Throughput: 0: 1602.1, 1: 1623.2. Samples: 16982106. Policy #0 lag: (min: 13.0, avg: 14.9, max: 43.0) -[2023-10-09 09:37:06,079][22500] Avg episode reward: [(0, '7.750'), (1, '6.790')] -[2023-10-09 09:37:08,653][23469] Updated weights for policy 1, policy_version 33251 (0.0008) -[2023-10-09 09:37:09,021][23469] Updated weights for policy 1, policy_version 33261 (0.0009) -[2023-10-09 09:37:09,081][23468] Updated weights for policy 0, policy_version 33093 (0.0009) -[2023-10-09 09:37:09,401][23469] Updated weights for policy 1, policy_version 33271 (0.0009) -[2023-10-09 09:37:09,469][23468] Updated weights for policy 0, policy_version 33103 (0.0007) -[2023-10-09 09:37:09,837][23468] Updated weights for policy 0, policy_version 33113 (0.0009) -[2023-10-09 09:37:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 11996.4). Total num frames: 67993600. Throughput: 0: 1631.7, 1: 1623.3. Samples: 17001988. Policy #0 lag: (min: 13.0, avg: 14.9, max: 43.0) -[2023-10-09 09:37:11,078][22500] Avg episode reward: [(0, '7.460'), (1, '6.850')] -[2023-10-09 09:37:13,369][23469] Updated weights for policy 1, policy_version 33281 (0.0008) -[2023-10-09 09:37:13,715][23468] Updated weights for policy 0, policy_version 33123 (0.0008) -[2023-10-09 09:37:13,733][23469] Updated weights for policy 1, policy_version 33291 (0.0009) -[2023-10-09 09:37:14,091][23468] Updated weights for policy 0, policy_version 33133 (0.0008) -[2023-10-09 09:37:14,108][23469] Updated weights for policy 1, policy_version 33301 (0.0009) -[2023-10-09 09:37:14,457][23468] Updated weights for policy 0, policy_version 33143 (0.0008) -[2023-10-09 09:37:14,465][23469] Updated weights for policy 1, policy_version 33311 (0.0008) -[2023-10-09 09:37:16,078][22500] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12107.5). Total num frames: 68059136. Throughput: 0: 1677.6, 1: 1705.7. Samples: 17022492. Policy #0 lag: (min: 13.0, avg: 14.9, max: 43.0) -[2023-10-09 09:37:16,079][22500] Avg episode reward: [(0, '7.460'), (1, '6.650')] -[2023-10-09 09:37:18,172][23469] Updated weights for policy 1, policy_version 33321 (0.0008) -[2023-10-09 09:37:18,363][23468] Updated weights for policy 0, policy_version 33153 (0.0008) -[2023-10-09 09:37:18,543][23469] Updated weights for policy 1, policy_version 33331 (0.0010) -[2023-10-09 09:37:18,740][23468] Updated weights for policy 0, policy_version 33163 (0.0007) -[2023-10-09 09:37:18,921][23469] Updated weights for policy 1, policy_version 33341 (0.0007) -[2023-10-09 09:37:19,113][23468] Updated weights for policy 0, policy_version 33173 (0.0008) -[2023-10-09 09:37:19,487][23468] Updated weights for policy 0, policy_version 33183 (0.0010) -[2023-10-09 09:37:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12107.5). Total num frames: 68124672. Throughput: 0: 1740.5, 1: 1731.7. Samples: 17033698. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 09:37:21,078][22500] Avg episode reward: [(0, '7.270'), (1, '6.820')] -[2023-10-09 09:37:22,653][23469] Updated weights for policy 1, policy_version 33351 (0.0007) -[2023-10-09 09:37:23,016][23469] Updated weights for policy 1, policy_version 33361 (0.0008) -[2023-10-09 09:37:23,328][23468] Updated weights for policy 0, policy_version 33193 (0.0008) -[2023-10-09 09:37:23,383][23469] Updated weights for policy 1, policy_version 33371 (0.0010) -[2023-10-09 09:37:23,697][23468] Updated weights for policy 0, policy_version 33203 (0.0007) -[2023-10-09 09:37:24,062][23468] Updated weights for policy 0, policy_version 33213 (0.0008) -[2023-10-09 09:37:26,077][22500] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12107.5). Total num frames: 68190208. Throughput: 0: 1743.6, 1: 1753.7. Samples: 17054216. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 09:37:26,079][22500] Avg episode reward: [(0, '7.130'), (1, '6.380')] -[2023-10-09 09:37:27,284][23469] Updated weights for policy 1, policy_version 33381 (0.0009) -[2023-10-09 09:37:27,673][23469] Updated weights for policy 1, policy_version 33391 (0.0010) -[2023-10-09 09:37:27,848][23468] Updated weights for policy 0, policy_version 33223 (0.0008) -[2023-10-09 09:37:28,034][23469] Updated weights for policy 1, policy_version 33401 (0.0008) -[2023-10-09 09:37:28,224][23468] Updated weights for policy 0, policy_version 33233 (0.0009) -[2023-10-09 09:37:28,594][23468] Updated weights for policy 0, policy_version 33243 (0.0008) -[2023-10-09 09:37:31,078][22500] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 12107.5). Total num frames: 68255744. Throughput: 0: 1747.6, 1: 1765.6. Samples: 17076340. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 09:37:31,079][22500] Avg episode reward: [(0, '7.030'), (1, '6.690')] -[2023-10-09 09:37:31,953][23469] Updated weights for policy 1, policy_version 33411 (0.0009) -[2023-10-09 09:37:32,320][23469] Updated weights for policy 1, policy_version 33421 (0.0008) -[2023-10-09 09:37:32,387][23468] Updated weights for policy 0, policy_version 33253 (0.0008) -[2023-10-09 09:37:32,692][23469] Updated weights for policy 1, policy_version 33431 (0.0007) -[2023-10-09 09:37:32,758][23468] Updated weights for policy 0, policy_version 33263 (0.0008) -[2023-10-09 09:37:33,131][23468] Updated weights for policy 0, policy_version 33273 (0.0009) -[2023-10-09 09:37:36,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 12107.5). Total num frames: 68321280. Throughput: 0: 1753.2, 1: 1750.8. Samples: 17086108. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 09:37:36,078][22500] Avg episode reward: [(0, '7.110'), (1, '6.870')] -[2023-10-09 09:37:36,390][23469] Updated weights for policy 1, policy_version 33441 (0.0008) -[2023-10-09 09:37:36,757][23469] Updated weights for policy 1, policy_version 33451 (0.0007) -[2023-10-09 09:37:37,055][23468] Updated weights for policy 0, policy_version 33283 (0.0009) -[2023-10-09 09:37:37,124][23469] Updated weights for policy 1, policy_version 33461 (0.0008) -[2023-10-09 09:37:37,422][23468] Updated weights for policy 0, policy_version 33293 (0.0007) -[2023-10-09 09:37:37,492][23469] Updated weights for policy 1, policy_version 33471 (0.0007) -[2023-10-09 09:37:37,802][23468] Updated weights for policy 0, policy_version 33303 (0.0007) -[2023-10-09 09:37:41,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 12218.6). Total num frames: 68386816. Throughput: 0: 1744.5, 1: 1761.2. Samples: 17108220. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 09:37:41,078][22500] Avg episode reward: [(0, '6.820'), (1, '7.180')] -[2023-10-09 09:37:41,334][23469] Updated weights for policy 1, policy_version 33481 (0.0008) -[2023-10-09 09:37:41,520][23468] Updated weights for policy 0, policy_version 33313 (0.0009) -[2023-10-09 09:37:41,706][23469] Updated weights for policy 1, policy_version 33491 (0.0008) -[2023-10-09 09:37:41,892][23468] Updated weights for policy 0, policy_version 33323 (0.0008) -[2023-10-09 09:37:42,068][23469] Updated weights for policy 1, policy_version 33501 (0.0008) -[2023-10-09 09:37:42,263][23468] Updated weights for policy 0, policy_version 33333 (0.0007) -[2023-10-09 09:37:42,627][23468] Updated weights for policy 0, policy_version 33343 (0.0009) -[2023-10-09 09:37:45,809][23469] Updated weights for policy 1, policy_version 33511 (0.0008) -[2023-10-09 09:37:46,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 12218.6). Total num frames: 68452352. Throughput: 0: 1767.3, 1: 1785.4. Samples: 17130170. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:37:46,078][22500] Avg episode reward: [(0, '6.640'), (1, '7.010')] -[2023-10-09 09:37:46,184][23469] Updated weights for policy 1, policy_version 33521 (0.0008) -[2023-10-09 09:37:46,533][23468] Updated weights for policy 0, policy_version 33353 (0.0009) -[2023-10-09 09:37:46,562][23469] Updated weights for policy 1, policy_version 33531 (0.0007) -[2023-10-09 09:37:46,905][23468] Updated weights for policy 0, policy_version 33363 (0.0008) -[2023-10-09 09:37:47,289][23468] Updated weights for policy 0, policy_version 33373 (0.0007) -[2023-10-09 09:37:50,275][23469] Updated weights for policy 1, policy_version 33541 (0.0008) -[2023-10-09 09:37:50,648][23469] Updated weights for policy 1, policy_version 33551 (0.0008) -[2023-10-09 09:37:51,022][23469] Updated weights for policy 1, policy_version 33561 (0.0010) -[2023-10-09 09:37:51,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 12218.6). Total num frames: 68517888. Throughput: 0: 1745.8, 1: 1760.6. Samples: 17139894. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:37:51,078][22500] Avg episode reward: [(0, '6.940'), (1, '7.050')] -[2023-10-09 09:37:51,169][23468] Updated weights for policy 0, policy_version 33383 (0.0007) -[2023-10-09 09:37:51,539][23468] Updated weights for policy 0, policy_version 33393 (0.0010) -[2023-10-09 09:37:51,910][23468] Updated weights for policy 0, policy_version 33403 (0.0011) -[2023-10-09 09:37:54,883][23469] Updated weights for policy 1, policy_version 33571 (0.0008) -[2023-10-09 09:37:55,255][23469] Updated weights for policy 1, policy_version 33581 (0.0008) -[2023-10-09 09:37:55,631][23469] Updated weights for policy 1, policy_version 33591 (0.0010) -[2023-10-09 09:37:55,986][23468] Updated weights for policy 0, policy_version 33413 (0.0008) -[2023-10-09 09:37:56,077][22500] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 12329.7). Total num frames: 68616192. Throughput: 0: 1750.3, 1: 1787.8. Samples: 17161202. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:37:56,078][22500] Avg episode reward: [(0, '7.650'), (1, '7.190')] -[2023-10-09 09:37:56,371][23468] Updated weights for policy 0, policy_version 33423 (0.0007) -[2023-10-09 09:37:56,741][23468] Updated weights for policy 0, policy_version 33433 (0.0008) -[2023-10-09 09:37:59,393][23469] Updated weights for policy 1, policy_version 33601 (0.0007) -[2023-10-09 09:37:59,765][23469] Updated weights for policy 1, policy_version 33611 (0.0008) -[2023-10-09 09:38:00,128][23469] Updated weights for policy 1, policy_version 33621 (0.0007) -[2023-10-09 09:38:00,361][23468] Updated weights for policy 0, policy_version 33443 (0.0007) -[2023-10-09 09:38:00,506][23469] Updated weights for policy 1, policy_version 33631 (0.0008) -[2023-10-09 09:38:00,736][23468] Updated weights for policy 0, policy_version 33453 (0.0009) -[2023-10-09 09:38:01,077][22500] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 12329.7). Total num frames: 68681728. Throughput: 0: 1780.5, 1: 1762.8. Samples: 17181940. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:38:01,078][22500] Avg episode reward: [(0, '7.670'), (1, '7.450')] -[2023-10-09 09:38:01,117][23468] Updated weights for policy 0, policy_version 33463 (0.0009) -[2023-10-09 09:38:04,267][23469] Updated weights for policy 1, policy_version 33641 (0.0010) -[2023-10-09 09:38:04,648][23469] Updated weights for policy 1, policy_version 33651 (0.0009) -[2023-10-09 09:38:04,810][23468] Updated weights for policy 0, policy_version 33473 (0.0009) -[2023-10-09 09:38:05,022][23469] Updated weights for policy 1, policy_version 33661 (0.0007) -[2023-10-09 09:38:05,171][23468] Updated weights for policy 0, policy_version 33483 (0.0009) -[2023-10-09 09:38:05,549][23468] Updated weights for policy 0, policy_version 33493 (0.0010) -[2023-10-09 09:38:05,921][23468] Updated weights for policy 0, policy_version 33503 (0.0010) -[2023-10-09 09:38:06,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 12663.0). Total num frames: 68780032. Throughput: 0: 1759.3, 1: 1794.5. Samples: 17193622. Policy #0 lag: (min: 17.0, avg: 26.6, max: 49.0) -[2023-10-09 09:38:06,078][22500] Avg episode reward: [(0, '8.270'), (1, '7.570')] -[2023-10-09 09:38:06,080][23343] Saving new best policy, reward=7.570! -[2023-10-09 09:38:08,805][23469] Updated weights for policy 1, policy_version 33671 (0.0008) -[2023-10-09 09:38:09,169][23469] Updated weights for policy 1, policy_version 33681 (0.0008) -[2023-10-09 09:38:09,542][23469] Updated weights for policy 1, policy_version 33691 (0.0009) -[2023-10-09 09:38:09,692][23468] Updated weights for policy 0, policy_version 33513 (0.0009) -[2023-10-09 09:38:10,065][23468] Updated weights for policy 0, policy_version 33523 (0.0010) -[2023-10-09 09:38:10,440][23468] Updated weights for policy 0, policy_version 33533 (0.0011) -[2023-10-09 09:38:11,078][22500] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 12662.9). Total num frames: 68845568. Throughput: 0: 1796.6, 1: 1766.7. Samples: 17214566. Policy #0 lag: (min: 17.0, avg: 26.6, max: 49.0) -[2023-10-09 09:38:11,079][22500] Avg episode reward: [(0, '7.670'), (1, '7.400')] -[2023-10-09 09:38:13,914][23469] Updated weights for policy 1, policy_version 33701 (0.0012) -[2023-10-09 09:38:14,281][23469] Updated weights for policy 1, policy_version 33711 (0.0011) -[2023-10-09 09:38:14,661][23469] Updated weights for policy 1, policy_version 33721 (0.0011) -[2023-10-09 09:38:15,461][23468] Updated weights for policy 0, policy_version 33543 (0.0010) -[2023-10-09 09:38:15,840][23468] Updated weights for policy 0, policy_version 33553 (0.0010) -[2023-10-09 09:38:16,078][22500] Fps is (10 sec: 9830.3, 60 sec: 13653.3, 300 sec: 12551.8). Total num frames: 68878336. Throughput: 0: 1733.5, 1: 1722.8. Samples: 17231876. Policy #0 lag: (min: 17.0, avg: 26.6, max: 49.0) -[2023-10-09 09:38:16,078][22500] Avg episode reward: [(0, '7.980'), (1, '7.250')] -[2023-10-09 09:38:16,088][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000033728_34537472.pth... -[2023-10-09 09:38:16,130][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000032224_32997376.pth -[2023-10-09 09:38:16,209][23468] Updated weights for policy 0, policy_version 33563 (0.0011) -[2023-10-09 09:38:16,389][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000033568_34373632.pth... -[2023-10-09 09:38:16,430][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000032064_32833536.pth -[2023-10-09 09:38:20,717][23469] Updated weights for policy 1, policy_version 33731 (0.0011) -[2023-10-09 09:38:21,077][22500] Fps is (10 sec: 6553.6, 60 sec: 13107.2, 300 sec: 12440.7). Total num frames: 68911104. Throughput: 0: 1697.6, 1: 1707.2. Samples: 17239324. Policy #0 lag: (min: 17.0, avg: 26.6, max: 49.0) -[2023-10-09 09:38:21,078][22500] Avg episode reward: [(0, '8.060'), (1, '6.870')] -[2023-10-09 09:38:21,086][23469] Updated weights for policy 1, policy_version 33741 (0.0009) -[2023-10-09 09:38:21,462][23469] Updated weights for policy 1, policy_version 33751 (0.0009) -[2023-10-09 09:38:21,645][23468] Updated weights for policy 0, policy_version 33573 (0.0010) -[2023-10-09 09:38:22,007][23468] Updated weights for policy 0, policy_version 33583 (0.0008) -[2023-10-09 09:38:22,380][23468] Updated weights for policy 0, policy_version 33593 (0.0010) -[2023-10-09 09:38:25,138][23469] Updated weights for policy 1, policy_version 33761 (0.0009) -[2023-10-09 09:38:25,506][23469] Updated weights for policy 1, policy_version 33771 (0.0009) -[2023-10-09 09:38:25,879][23469] Updated weights for policy 1, policy_version 33781 (0.0008) -[2023-10-09 09:38:26,077][22500] Fps is (10 sec: 9830.6, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 68976640. Throughput: 0: 1661.0, 1: 1669.7. Samples: 17258100. Policy #0 lag: (min: 17.0, avg: 26.6, max: 49.0) -[2023-10-09 09:38:26,078][22500] Avg episode reward: [(0, '8.190'), (1, '6.980')] -[2023-10-09 09:38:26,248][23469] Updated weights for policy 1, policy_version 33791 (0.0007) -[2023-10-09 09:38:26,302][23468] Updated weights for policy 0, policy_version 33603 (0.0008) -[2023-10-09 09:38:26,666][23468] Updated weights for policy 0, policy_version 33613 (0.0007) -[2023-10-09 09:38:27,036][23468] Updated weights for policy 0, policy_version 33623 (0.0009) -[2023-10-09 09:38:29,885][23469] Updated weights for policy 1, policy_version 33801 (0.0008) -[2023-10-09 09:38:30,246][23469] Updated weights for policy 1, policy_version 33811 (0.0010) -[2023-10-09 09:38:30,619][23469] Updated weights for policy 1, policy_version 33821 (0.0009) -[2023-10-09 09:38:30,844][23468] Updated weights for policy 0, policy_version 33633 (0.0011) -[2023-10-09 09:38:31,077][22500] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 12774.0). Total num frames: 69074944. Throughput: 0: 1658.1, 1: 1650.3. Samples: 17279048. Policy #0 lag: (min: 17.0, avg: 26.6, max: 49.0) -[2023-10-09 09:38:31,078][22500] Avg episode reward: [(0, '7.830'), (1, '6.900')] -[2023-10-09 09:38:31,202][23468] Updated weights for policy 0, policy_version 33643 (0.0009) -[2023-10-09 09:38:31,581][23468] Updated weights for policy 0, policy_version 33653 (0.0009) -[2023-10-09 09:38:31,947][23468] Updated weights for policy 0, policy_version 33663 (0.0008) -[2023-10-09 09:38:34,338][23469] Updated weights for policy 1, policy_version 33831 (0.0007) -[2023-10-09 09:38:34,699][23469] Updated weights for policy 1, policy_version 33841 (0.0007) -[2023-10-09 09:38:35,074][23469] Updated weights for policy 1, policy_version 33851 (0.0008) -[2023-10-09 09:38:35,734][23468] Updated weights for policy 0, policy_version 33673 (0.0010) -[2023-10-09 09:38:36,077][22500] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 12774.0). Total num frames: 69140480. Throughput: 0: 1659.5, 1: 1680.3. Samples: 17290182. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 09:38:36,078][22500] Avg episode reward: [(0, '6.780'), (1, '7.120')] -[2023-10-09 09:38:36,104][23468] Updated weights for policy 0, policy_version 33683 (0.0010) -[2023-10-09 09:38:36,482][23468] Updated weights for policy 0, policy_version 33693 (0.0008) -[2023-10-09 09:38:38,922][23469] Updated weights for policy 1, policy_version 33861 (0.0009) -[2023-10-09 09:38:39,290][23469] Updated weights for policy 1, policy_version 33871 (0.0008) -[2023-10-09 09:38:39,658][23469] Updated weights for policy 1, policy_version 33881 (0.0011) -[2023-10-09 09:38:40,432][23468] Updated weights for policy 0, policy_version 33703 (0.0009) -[2023-10-09 09:38:40,806][23468] Updated weights for policy 0, policy_version 33713 (0.0010) -[2023-10-09 09:38:41,077][22500] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 12774.0). Total num frames: 69206016. Throughput: 0: 1665.6, 1: 1658.8. Samples: 17310798. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 09:38:41,078][22500] Avg episode reward: [(0, '6.790'), (1, '6.240')] -[2023-10-09 09:38:41,177][23468] Updated weights for policy 0, policy_version 33723 (0.0007) -[2023-10-09 09:38:43,696][23469] Updated weights for policy 1, policy_version 33891 (0.0009) -[2023-10-09 09:38:44,063][23469] Updated weights for policy 1, policy_version 33901 (0.0010) -[2023-10-09 09:38:44,433][23469] Updated weights for policy 1, policy_version 33911 (0.0009) -[2023-10-09 09:38:44,939][23468] Updated weights for policy 0, policy_version 33733 (0.0007) -[2023-10-09 09:38:45,319][23468] Updated weights for policy 0, policy_version 33743 (0.0010) -[2023-10-09 09:38:45,686][23468] Updated weights for policy 0, policy_version 33753 (0.0011) -[2023-10-09 09:38:46,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 12885.1). Total num frames: 69304320. Throughput: 0: 1644.8, 1: 1675.4. Samples: 17331350. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 09:38:46,078][22500] Avg episode reward: [(0, '7.230'), (1, '6.750')] -[2023-10-09 09:38:48,287][23469] Updated weights for policy 1, policy_version 33921 (0.0008) -[2023-10-09 09:38:48,663][23469] Updated weights for policy 1, policy_version 33931 (0.0008) -[2023-10-09 09:38:49,033][23469] Updated weights for policy 1, policy_version 33941 (0.0008) -[2023-10-09 09:38:49,406][23469] Updated weights for policy 1, policy_version 33951 (0.0008) -[2023-10-09 09:38:49,585][23468] Updated weights for policy 0, policy_version 33763 (0.0009) -[2023-10-09 09:38:49,963][23468] Updated weights for policy 0, policy_version 33773 (0.0007) -[2023-10-09 09:38:50,342][23468] Updated weights for policy 0, policy_version 33783 (0.0008) -[2023-10-09 09:38:51,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 12885.0). Total num frames: 69369856. Throughput: 0: 1649.8, 1: 1656.1. Samples: 17342384. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 09:38:51,078][22500] Avg episode reward: [(0, '7.220'), (1, '6.690')] -[2023-10-09 09:38:53,764][23469] Updated weights for policy 1, policy_version 33961 (0.0011) -[2023-10-09 09:38:54,150][23469] Updated weights for policy 1, policy_version 33971 (0.0011) -[2023-10-09 09:38:54,523][23469] Updated weights for policy 1, policy_version 33981 (0.0011) -[2023-10-09 09:38:55,881][23468] Updated weights for policy 0, policy_version 33793 (0.0009) -[2023-10-09 09:38:56,077][22500] Fps is (10 sec: 9830.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 69402624. Throughput: 0: 1591.1, 1: 1632.6. Samples: 17359632. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 09:38:56,078][22500] Avg episode reward: [(0, '7.090'), (1, '6.770')] -[2023-10-09 09:38:56,264][23468] Updated weights for policy 0, policy_version 33803 (0.0010) -[2023-10-09 09:38:56,627][23468] Updated weights for policy 0, policy_version 33813 (0.0011) -[2023-10-09 09:38:56,997][23468] Updated weights for policy 0, policy_version 33823 (0.0011) -[2023-10-09 09:38:58,920][23469] Updated weights for policy 1, policy_version 33991 (0.0010) -[2023-10-09 09:38:59,308][23469] Updated weights for policy 1, policy_version 34001 (0.0009) -[2023-10-09 09:38:59,690][23469] Updated weights for policy 1, policy_version 34011 (0.0008) -[2023-10-09 09:39:00,939][23468] Updated weights for policy 0, policy_version 33833 (0.0008) -[2023-10-09 09:39:01,077][22500] Fps is (10 sec: 9830.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 69468160. Throughput: 0: 1613.1, 1: 1656.6. Samples: 17379014. Policy #0 lag: (min: 16.0, avg: 26.7, max: 48.0) -[2023-10-09 09:39:01,078][22500] Avg episode reward: [(0, '6.550'), (1, '7.190')] -[2023-10-09 09:39:01,320][23468] Updated weights for policy 0, policy_version 33843 (0.0009) -[2023-10-09 09:39:01,698][23468] Updated weights for policy 0, policy_version 33853 (0.0010) -[2023-10-09 09:39:03,506][23469] Updated weights for policy 1, policy_version 34021 (0.0008) -[2023-10-09 09:39:03,873][23469] Updated weights for policy 1, policy_version 34031 (0.0010) -[2023-10-09 09:39:04,240][23469] Updated weights for policy 1, policy_version 34041 (0.0011) -[2023-10-09 09:39:05,794][23468] Updated weights for policy 0, policy_version 33863 (0.0009) -[2023-10-09 09:39:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12885.0). Total num frames: 69533696. Throughput: 0: 1643.5, 1: 1691.4. Samples: 17389396. Policy #0 lag: (min: 16.0, avg: 26.7, max: 48.0) -[2023-10-09 09:39:06,078][22500] Avg episode reward: [(0, '6.770'), (1, '7.150')] -[2023-10-09 09:39:06,165][23468] Updated weights for policy 0, policy_version 33873 (0.0009) -[2023-10-09 09:39:06,535][23468] Updated weights for policy 0, policy_version 33883 (0.0008) -[2023-10-09 09:39:08,091][23469] Updated weights for policy 1, policy_version 34051 (0.0007) -[2023-10-09 09:39:08,454][23469] Updated weights for policy 1, policy_version 34061 (0.0010) -[2023-10-09 09:39:08,825][23469] Updated weights for policy 1, policy_version 34071 (0.0008) -[2023-10-09 09:39:10,361][23468] Updated weights for policy 0, policy_version 33893 (0.0008) -[2023-10-09 09:39:10,740][23468] Updated weights for policy 0, policy_version 33903 (0.0010) -[2023-10-09 09:39:11,077][22500] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12885.0). Total num frames: 69599232. Throughput: 0: 1683.8, 1: 1700.7. Samples: 17410400. Policy #0 lag: (min: 16.0, avg: 26.7, max: 48.0) -[2023-10-09 09:39:11,078][22500] Avg episode reward: [(0, '6.860'), (1, '6.910')] -[2023-10-09 09:39:11,109][23468] Updated weights for policy 0, policy_version 33913 (0.0010) -[2023-10-09 09:39:12,663][23469] Updated weights for policy 1, policy_version 34081 (0.0009) -[2023-10-09 09:39:13,032][23469] Updated weights for policy 1, policy_version 34091 (0.0007) -[2023-10-09 09:39:13,406][23469] Updated weights for policy 1, policy_version 34101 (0.0010) -[2023-10-09 09:39:13,779][23469] Updated weights for policy 1, policy_version 34111 (0.0009) -[2023-10-09 09:39:15,109][23468] Updated weights for policy 0, policy_version 33923 (0.0010) -[2023-10-09 09:39:15,486][23468] Updated weights for policy 0, policy_version 33933 (0.0007) -[2023-10-09 09:39:15,857][23468] Updated weights for policy 0, policy_version 33943 (0.0010) -[2023-10-09 09:39:16,078][22500] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12996.1). Total num frames: 69664768. Throughput: 0: 1669.6, 1: 1724.8. Samples: 17431798. Policy #0 lag: (min: 16.0, avg: 26.7, max: 48.0) -[2023-10-09 09:39:16,079][22500] Avg episode reward: [(0, '7.450'), (1, '6.600')] -[2023-10-09 09:39:17,702][23469] Updated weights for policy 1, policy_version 34121 (0.0010) -[2023-10-09 09:39:18,087][23469] Updated weights for policy 1, policy_version 34131 (0.0010) -[2023-10-09 09:39:18,446][23469] Updated weights for policy 1, policy_version 34141 (0.0011) -[2023-10-09 09:39:19,724][23468] Updated weights for policy 0, policy_version 33953 (0.0008) -[2023-10-09 09:39:20,091][23468] Updated weights for policy 0, policy_version 33963 (0.0010) -[2023-10-09 09:39:20,476][23468] Updated weights for policy 0, policy_version 33973 (0.0009) -[2023-10-09 09:39:20,849][23468] Updated weights for policy 0, policy_version 33983 (0.0008) -[2023-10-09 09:39:21,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13107.2). Total num frames: 69763072. Throughput: 0: 1677.9, 1: 1691.7. Samples: 17441814. Policy #0 lag: (min: 29.0, avg: 37.0, max: 61.0) -[2023-10-09 09:39:21,078][22500] Avg episode reward: [(0, '7.300'), (1, '6.860')] -[2023-10-09 09:39:22,346][23469] Updated weights for policy 1, policy_version 34151 (0.0010) -[2023-10-09 09:39:22,717][23469] Updated weights for policy 1, policy_version 34161 (0.0010) -[2023-10-09 09:39:23,081][23469] Updated weights for policy 1, policy_version 34171 (0.0008) -[2023-10-09 09:39:24,614][23468] Updated weights for policy 0, policy_version 33993 (0.0010) -[2023-10-09 09:39:24,989][23468] Updated weights for policy 0, policy_version 34003 (0.0010) -[2023-10-09 09:39:25,354][23468] Updated weights for policy 0, policy_version 34013 (0.0009) -[2023-10-09 09:39:26,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 13107.2). Total num frames: 69828608. Throughput: 0: 1682.0, 1: 1714.4. Samples: 17463632. Policy #0 lag: (min: 29.0, avg: 37.0, max: 61.0) -[2023-10-09 09:39:26,078][22500] Avg episode reward: [(0, '7.260'), (1, '7.270')] -[2023-10-09 09:39:27,030][23469] Updated weights for policy 1, policy_version 34181 (0.0011) -[2023-10-09 09:39:27,399][23469] Updated weights for policy 1, policy_version 34191 (0.0008) -[2023-10-09 09:39:27,767][23469] Updated weights for policy 1, policy_version 34201 (0.0007) -[2023-10-09 09:39:29,180][23468] Updated weights for policy 0, policy_version 34023 (0.0009) -[2023-10-09 09:39:29,563][23468] Updated weights for policy 0, policy_version 34033 (0.0009) -[2023-10-09 09:39:29,941][23468] Updated weights for policy 0, policy_version 34043 (0.0009) -[2023-10-09 09:39:31,077][22500] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13107.2). Total num frames: 69894144. Throughput: 0: 1667.2, 1: 1724.2. Samples: 17483960. Policy #0 lag: (min: 29.0, avg: 37.0, max: 61.0) -[2023-10-09 09:39:31,078][22500] Avg episode reward: [(0, '6.720'), (1, '6.760')] -[2023-10-09 09:39:31,501][23469] Updated weights for policy 1, policy_version 34211 (0.0008) -[2023-10-09 09:39:31,875][23469] Updated weights for policy 1, policy_version 34221 (0.0011) -[2023-10-09 09:39:32,238][23469] Updated weights for policy 1, policy_version 34231 (0.0011) -[2023-10-09 09:39:33,708][23468] Updated weights for policy 0, policy_version 34053 (0.0009) -[2023-10-09 09:39:34,083][23468] Updated weights for policy 0, policy_version 34063 (0.0011) -[2023-10-09 09:39:34,454][23468] Updated weights for policy 0, policy_version 34073 (0.0009) -[2023-10-09 09:39:36,077][22500] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13107.2). Total num frames: 69959680. Throughput: 0: 1682.7, 1: 1704.0. Samples: 17494784. Policy #0 lag: (min: 29.0, avg: 37.0, max: 61.0) -[2023-10-09 09:39:36,078][22500] Avg episode reward: [(0, '6.770'), (1, '6.590')] -[2023-10-09 09:39:36,082][23469] Updated weights for policy 1, policy_version 34241 (0.0011) -[2023-10-09 09:39:36,459][23469] Updated weights for policy 1, policy_version 34251 (0.0009) -[2023-10-09 09:39:36,824][23469] Updated weights for policy 1, policy_version 34261 (0.0009) -[2023-10-09 09:39:37,184][23469] Updated weights for policy 1, policy_version 34271 (0.0008) -[2023-10-09 09:39:38,379][23468] Updated weights for policy 0, policy_version 34083 (0.0010) -[2023-10-09 09:39:38,761][23468] Updated weights for policy 0, policy_version 34093 (0.0008) -[2023-10-09 09:39:39,131][23468] Updated weights for policy 0, policy_version 34103 (0.0009) -[2023-10-09 09:39:40,908][23469] Updated weights for policy 1, policy_version 34281 (0.0009) -[2023-10-09 09:39:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13107.2). Total num frames: 70025216. Throughput: 0: 1703.1, 1: 1764.7. Samples: 17515684. Policy #0 lag: (min: 29.0, avg: 37.0, max: 61.0) -[2023-10-09 09:39:41,078][22500] Avg episode reward: [(0, '6.840'), (1, '6.620')] -[2023-10-09 09:39:41,286][23469] Updated weights for policy 1, policy_version 34291 (0.0009) -[2023-10-09 09:39:41,656][23469] Updated weights for policy 1, policy_version 34301 (0.0008) -[2023-10-09 09:39:43,005][23468] Updated weights for policy 0, policy_version 34113 (0.0008) -[2023-10-09 09:39:43,375][23468] Updated weights for policy 0, policy_version 34123 (0.0009) -[2023-10-09 09:39:43,764][23468] Updated weights for policy 0, policy_version 34133 (0.0010) -[2023-10-09 09:39:44,134][23468] Updated weights for policy 0, policy_version 34143 (0.0007) -[2023-10-09 09:39:45,480][23469] Updated weights for policy 1, policy_version 34311 (0.0008) -[2023-10-09 09:39:45,850][23469] Updated weights for policy 1, policy_version 34321 (0.0007) -[2023-10-09 09:39:46,077][22500] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13107.2). Total num frames: 70090752. Throughput: 0: 1727.4, 1: 1773.3. Samples: 17536548. Policy #0 lag: (min: 1.0, avg: 10.8, max: 33.0) -[2023-10-09 09:39:46,078][22500] Avg episode reward: [(0, '7.130'), (1, '6.960')] -[2023-10-09 09:39:46,221][23469] Updated weights for policy 1, policy_version 34331 (0.0007) -[2023-10-09 09:39:48,002][23468] Updated weights for policy 0, policy_version 34153 (0.0008) -[2023-10-09 09:39:48,383][23468] Updated weights for policy 0, policy_version 34163 (0.0007) -[2023-10-09 09:39:48,752][23468] Updated weights for policy 0, policy_version 34173 (0.0008) -[2023-10-09 09:39:50,143][23469] Updated weights for policy 1, policy_version 34341 (0.0008) -[2023-10-09 09:39:50,505][23469] Updated weights for policy 1, policy_version 34351 (0.0009) -[2023-10-09 09:39:50,887][23469] Updated weights for policy 1, policy_version 34361 (0.0009) -[2023-10-09 09:39:51,077][22500] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13107.2). Total num frames: 70156288. Throughput: 0: 1743.2, 1: 1768.1. Samples: 17547402. Policy #0 lag: (min: 1.0, avg: 10.8, max: 33.0) -[2023-10-09 09:39:51,078][22500] Avg episode reward: [(0, '7.070'), (1, '6.930')] -[2023-10-09 09:39:52,540][23468] Updated weights for policy 0, policy_version 34183 (0.0008) -[2023-10-09 09:39:52,901][23468] Updated weights for policy 0, policy_version 34193 (0.0007) -[2023-10-09 09:39:53,275][23468] Updated weights for policy 0, policy_version 34203 (0.0009) -[2023-10-09 09:39:54,574][23469] Updated weights for policy 1, policy_version 34371 (0.0007) -[2023-10-09 09:39:54,948][23469] Updated weights for policy 1, policy_version 34381 (0.0007) -[2023-10-09 09:39:55,309][23469] Updated weights for policy 1, policy_version 34391 (0.0008) -[2023-10-09 09:39:56,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13440.4). Total num frames: 70254592. Throughput: 0: 1728.4, 1: 1787.0. Samples: 17568592. Policy #0 lag: (min: 1.0, avg: 10.8, max: 33.0) -[2023-10-09 09:39:56,078][22500] Avg episode reward: [(0, '7.660'), (1, '6.860')] -[2023-10-09 09:39:57,118][23468] Updated weights for policy 0, policy_version 34213 (0.0007) -[2023-10-09 09:39:57,491][23468] Updated weights for policy 0, policy_version 34223 (0.0010) -[2023-10-09 09:39:57,875][23468] Updated weights for policy 0, policy_version 34233 (0.0009) -[2023-10-09 09:39:59,018][23469] Updated weights for policy 1, policy_version 34401 (0.0008) -[2023-10-09 09:39:59,387][23469] Updated weights for policy 1, policy_version 34411 (0.0007) -[2023-10-09 09:39:59,762][23469] Updated weights for policy 1, policy_version 34421 (0.0007) -[2023-10-09 09:40:00,135][23469] Updated weights for policy 1, policy_version 34431 (0.0008) -[2023-10-09 09:40:01,078][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13440.4). Total num frames: 70320128. Throughput: 0: 1737.6, 1: 1762.2. Samples: 17589290. Policy #0 lag: (min: 1.0, avg: 10.8, max: 33.0) -[2023-10-09 09:40:01,078][22500] Avg episode reward: [(0, '7.540'), (1, '7.170')] -[2023-10-09 09:40:01,645][23468] Updated weights for policy 0, policy_version 34243 (0.0010) -[2023-10-09 09:40:02,014][23468] Updated weights for policy 0, policy_version 34253 (0.0009) -[2023-10-09 09:40:02,381][23468] Updated weights for policy 0, policy_version 34263 (0.0007) -[2023-10-09 09:40:03,887][23469] Updated weights for policy 1, policy_version 34441 (0.0009) -[2023-10-09 09:40:04,249][23469] Updated weights for policy 1, policy_version 34451 (0.0011) -[2023-10-09 09:40:04,620][23469] Updated weights for policy 1, policy_version 34461 (0.0011) -[2023-10-09 09:40:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13440.4). Total num frames: 70385664. Throughput: 0: 1729.0, 1: 1792.0. Samples: 17600258. Policy #0 lag: (min: 1.0, avg: 10.8, max: 33.0) -[2023-10-09 09:40:06,079][22500] Avg episode reward: [(0, '7.690'), (1, '7.020')] -[2023-10-09 09:40:06,389][23468] Updated weights for policy 0, policy_version 34273 (0.0008) -[2023-10-09 09:40:06,756][23468] Updated weights for policy 0, policy_version 34283 (0.0009) -[2023-10-09 09:40:07,134][23468] Updated weights for policy 0, policy_version 34293 (0.0007) -[2023-10-09 09:40:07,508][23468] Updated weights for policy 0, policy_version 34303 (0.0008) -[2023-10-09 09:40:08,488][23469] Updated weights for policy 1, policy_version 34471 (0.0008) -[2023-10-09 09:40:08,873][23469] Updated weights for policy 1, policy_version 34481 (0.0007) -[2023-10-09 09:40:09,234][23469] Updated weights for policy 1, policy_version 34491 (0.0007) -[2023-10-09 09:40:11,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13440.4). Total num frames: 70451200. Throughput: 0: 1725.1, 1: 1771.1. Samples: 17620962. Policy #0 lag: (min: 23.0, avg: 30.1, max: 55.0) -[2023-10-09 09:40:11,079][22500] Avg episode reward: [(0, '7.500'), (1, '7.240')] -[2023-10-09 09:40:11,542][23468] Updated weights for policy 0, policy_version 34313 (0.0009) -[2023-10-09 09:40:11,918][23468] Updated weights for policy 0, policy_version 34323 (0.0010) -[2023-10-09 09:40:12,292][23468] Updated weights for policy 0, policy_version 34333 (0.0011) -[2023-10-09 09:40:12,850][23469] Updated weights for policy 1, policy_version 34501 (0.0009) -[2023-10-09 09:40:13,214][23469] Updated weights for policy 1, policy_version 34511 (0.0008) -[2023-10-09 09:40:13,576][23469] Updated weights for policy 1, policy_version 34521 (0.0008) -[2023-10-09 09:40:16,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13440.4). Total num frames: 70516736. Throughput: 0: 1759.8, 1: 1772.1. Samples: 17642896. Policy #0 lag: (min: 23.0, avg: 30.1, max: 55.0) -[2023-10-09 09:40:16,079][22500] Avg episode reward: [(0, '6.960'), (1, '7.500')] -[2023-10-09 09:40:16,089][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000034528_35356672.pth... -[2023-10-09 09:40:16,120][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000032928_33718272.pth -[2023-10-09 09:40:16,192][23468] Updated weights for policy 0, policy_version 34343 (0.0011) -[2023-10-09 09:40:16,570][23468] Updated weights for policy 0, policy_version 34353 (0.0009) -[2023-10-09 09:40:16,951][23468] Updated weights for policy 0, policy_version 34363 (0.0009) -[2023-10-09 09:40:17,122][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000034368_35192832.pth... -[2023-10-09 09:40:17,152][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000032768_33554432.pth -[2023-10-09 09:40:17,453][23469] Updated weights for policy 1, policy_version 34531 (0.0008) -[2023-10-09 09:40:17,829][23469] Updated weights for policy 1, policy_version 34541 (0.0008) -[2023-10-09 09:40:18,192][23469] Updated weights for policy 1, policy_version 34551 (0.0009) -[2023-10-09 09:40:20,833][23468] Updated weights for policy 0, policy_version 34373 (0.0008) -[2023-10-09 09:40:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 70582272. Throughput: 0: 1729.2, 1: 1771.9. Samples: 17652332. Policy #0 lag: (min: 23.0, avg: 30.1, max: 55.0) -[2023-10-09 09:40:21,079][22500] Avg episode reward: [(0, '7.350'), (1, '7.480')] -[2023-10-09 09:40:21,206][23468] Updated weights for policy 0, policy_version 34383 (0.0009) -[2023-10-09 09:40:21,579][23468] Updated weights for policy 0, policy_version 34393 (0.0008) -[2023-10-09 09:40:21,892][23469] Updated weights for policy 1, policy_version 34561 (0.0008) -[2023-10-09 09:40:22,257][23469] Updated weights for policy 1, policy_version 34571 (0.0010) -[2023-10-09 09:40:22,635][23469] Updated weights for policy 1, policy_version 34581 (0.0007) -[2023-10-09 09:40:23,003][23469] Updated weights for policy 1, policy_version 34591 (0.0009) -[2023-10-09 09:40:25,281][23468] Updated weights for policy 0, policy_version 34403 (0.0009) -[2023-10-09 09:40:25,646][23468] Updated weights for policy 0, policy_version 34413 (0.0009) -[2023-10-09 09:40:26,021][23468] Updated weights for policy 0, policy_version 34423 (0.0009) -[2023-10-09 09:40:26,077][22500] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 70647808. Throughput: 0: 1759.3, 1: 1770.8. Samples: 17674540. Policy #0 lag: (min: 23.0, avg: 30.1, max: 55.0) -[2023-10-09 09:40:26,078][22500] Avg episode reward: [(0, '7.240'), (1, '7.290')] -[2023-10-09 09:40:26,804][23469] Updated weights for policy 1, policy_version 34601 (0.0007) -[2023-10-09 09:40:27,183][23469] Updated weights for policy 1, policy_version 34611 (0.0008) -[2023-10-09 09:40:27,553][23469] Updated weights for policy 1, policy_version 34621 (0.0008) -[2023-10-09 09:40:29,836][23468] Updated weights for policy 0, policy_version 34433 (0.0009) -[2023-10-09 09:40:30,200][23468] Updated weights for policy 0, policy_version 34443 (0.0009) -[2023-10-09 09:40:30,581][23468] Updated weights for policy 0, policy_version 34453 (0.0008) -[2023-10-09 09:40:30,956][23468] Updated weights for policy 0, policy_version 34463 (0.0009) -[2023-10-09 09:40:31,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 13551.6). Total num frames: 70746112. Throughput: 0: 1762.8, 1: 1789.0. Samples: 17696376. Policy #0 lag: (min: 20.0, avg: 22.1, max: 47.0) -[2023-10-09 09:40:31,078][22500] Avg episode reward: [(0, '7.860'), (1, '7.010')] -[2023-10-09 09:40:31,509][23469] Updated weights for policy 1, policy_version 34631 (0.0008) -[2023-10-09 09:40:31,885][23469] Updated weights for policy 1, policy_version 34641 (0.0007) -[2023-10-09 09:40:32,252][23469] Updated weights for policy 1, policy_version 34651 (0.0008) -[2023-10-09 09:40:34,685][23468] Updated weights for policy 0, policy_version 34473 (0.0009) -[2023-10-09 09:40:35,067][23468] Updated weights for policy 0, policy_version 34483 (0.0009) -[2023-10-09 09:40:35,434][23468] Updated weights for policy 0, policy_version 34493 (0.0009) -[2023-10-09 09:40:35,960][23469] Updated weights for policy 1, policy_version 34661 (0.0007) -[2023-10-09 09:40:36,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 70811648. Throughput: 0: 1763.2, 1: 1774.8. Samples: 17706614. Policy #0 lag: (min: 20.0, avg: 22.1, max: 47.0) -[2023-10-09 09:40:36,078][22500] Avg episode reward: [(0, '7.520'), (1, '7.360')] -[2023-10-09 09:40:36,335][23469] Updated weights for policy 1, policy_version 34671 (0.0008) -[2023-10-09 09:40:36,700][23469] Updated weights for policy 1, policy_version 34681 (0.0009) -[2023-10-09 09:40:39,036][23468] Updated weights for policy 0, policy_version 34503 (0.0011) -[2023-10-09 09:40:39,404][23468] Updated weights for policy 0, policy_version 34513 (0.0011) -[2023-10-09 09:40:39,778][23468] Updated weights for policy 0, policy_version 34523 (0.0010) -[2023-10-09 09:40:40,492][23469] Updated weights for policy 1, policy_version 34691 (0.0008) -[2023-10-09 09:40:40,862][23469] Updated weights for policy 1, policy_version 34701 (0.0009) -[2023-10-09 09:40:41,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 70877184. Throughput: 0: 1767.0, 1: 1777.7. Samples: 17728104. Policy #0 lag: (min: 20.0, avg: 22.1, max: 47.0) -[2023-10-09 09:40:41,078][22500] Avg episode reward: [(0, '7.020'), (1, '6.780')] -[2023-10-09 09:40:41,223][23469] Updated weights for policy 1, policy_version 34711 (0.0009) -[2023-10-09 09:40:43,859][23468] Updated weights for policy 0, policy_version 34533 (0.0009) -[2023-10-09 09:40:44,221][23468] Updated weights for policy 0, policy_version 34543 (0.0011) -[2023-10-09 09:40:44,592][23468] Updated weights for policy 0, policy_version 34553 (0.0008) -[2023-10-09 09:40:45,259][23469] Updated weights for policy 1, policy_version 34721 (0.0011) -[2023-10-09 09:40:45,627][23469] Updated weights for policy 1, policy_version 34731 (0.0008) -[2023-10-09 09:40:45,986][23469] Updated weights for policy 1, policy_version 34741 (0.0008) -[2023-10-09 09:40:46,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 70942720. Throughput: 0: 1746.4, 1: 1784.5. Samples: 17748182. Policy #0 lag: (min: 20.0, avg: 22.1, max: 47.0) -[2023-10-09 09:40:46,078][22500] Avg episode reward: [(0, '7.020'), (1, '6.520')] -[2023-10-09 09:40:46,362][23469] Updated weights for policy 1, policy_version 34751 (0.0010) -[2023-10-09 09:40:48,527][23468] Updated weights for policy 0, policy_version 34563 (0.0008) -[2023-10-09 09:40:48,899][23468] Updated weights for policy 0, policy_version 34573 (0.0008) -[2023-10-09 09:40:49,281][23468] Updated weights for policy 0, policy_version 34583 (0.0008) -[2023-10-09 09:40:50,223][23469] Updated weights for policy 1, policy_version 34761 (0.0008) -[2023-10-09 09:40:50,591][23469] Updated weights for policy 1, policy_version 34771 (0.0010) -[2023-10-09 09:40:50,961][23469] Updated weights for policy 1, policy_version 34781 (0.0010) -[2023-10-09 09:40:51,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 13884.7). Total num frames: 71041024. Throughput: 0: 1775.9, 1: 1766.9. Samples: 17759684. Policy #0 lag: (min: 20.0, avg: 22.1, max: 47.0) -[2023-10-09 09:40:51,078][22500] Avg episode reward: [(0, '7.140'), (1, '6.500')] -[2023-10-09 09:40:54,231][23468] Updated weights for policy 0, policy_version 34593 (0.0009) -[2023-10-09 09:40:54,602][23468] Updated weights for policy 0, policy_version 34603 (0.0010) -[2023-10-09 09:40:54,987][23468] Updated weights for policy 0, policy_version 34613 (0.0011) -[2023-10-09 09:40:55,366][23468] Updated weights for policy 0, policy_version 34623 (0.0010) -[2023-10-09 09:40:56,077][22500] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 71073792. Throughput: 0: 1720.8, 1: 1733.8. Samples: 17776418. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-09 09:40:56,078][22500] Avg episode reward: [(0, '6.980'), (1, '6.760')] -[2023-10-09 09:40:56,585][23469] Updated weights for policy 1, policy_version 34791 (0.0011) -[2023-10-09 09:40:56,959][23469] Updated weights for policy 1, policy_version 34801 (0.0010) -[2023-10-09 09:40:57,321][23469] Updated weights for policy 1, policy_version 34811 (0.0010) -[2023-10-09 09:41:00,904][23468] Updated weights for policy 0, policy_version 34633 (0.0008) -[2023-10-09 09:41:01,077][22500] Fps is (10 sec: 6553.5, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 71106560. Throughput: 0: 1648.1, 1: 1672.5. Samples: 17792324. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-09 09:41:01,079][22500] Avg episode reward: [(0, '7.670'), (1, '6.870')] -[2023-10-09 09:41:01,272][23468] Updated weights for policy 0, policy_version 34643 (0.0008) -[2023-10-09 09:41:01,647][23468] Updated weights for policy 0, policy_version 34653 (0.0008) -[2023-10-09 09:41:01,931][23469] Updated weights for policy 1, policy_version 34821 (0.0011) -[2023-10-09 09:41:02,308][23469] Updated weights for policy 1, policy_version 34831 (0.0007) -[2023-10-09 09:41:02,684][23469] Updated weights for policy 1, policy_version 34841 (0.0008) -[2023-10-09 09:41:05,593][23468] Updated weights for policy 0, policy_version 34663 (0.0010) -[2023-10-09 09:41:05,969][23468] Updated weights for policy 0, policy_version 34673 (0.0010) -[2023-10-09 09:41:06,077][22500] Fps is (10 sec: 9830.5, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 71172096. Throughput: 0: 1651.3, 1: 1674.9. Samples: 17802008. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-09 09:41:06,078][22500] Avg episode reward: [(0, '7.380'), (1, '6.610')] -[2023-10-09 09:41:06,347][23468] Updated weights for policy 0, policy_version 34683 (0.0008) -[2023-10-09 09:41:06,546][23469] Updated weights for policy 1, policy_version 34851 (0.0008) -[2023-10-09 09:41:06,921][23469] Updated weights for policy 1, policy_version 34861 (0.0007) -[2023-10-09 09:41:07,278][23469] Updated weights for policy 1, policy_version 34871 (0.0009) -[2023-10-09 09:41:10,190][23468] Updated weights for policy 0, policy_version 34693 (0.0007) -[2023-10-09 09:41:10,565][23468] Updated weights for policy 0, policy_version 34703 (0.0008) -[2023-10-09 09:41:10,924][23468] Updated weights for policy 0, policy_version 34713 (0.0008) -[2023-10-09 09:41:11,064][23469] Updated weights for policy 1, policy_version 34881 (0.0007) -[2023-10-09 09:41:11,077][22500] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 71237632. Throughput: 0: 1645.0, 1: 1671.2. Samples: 17823768. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-09 09:41:11,078][22500] Avg episode reward: [(0, '7.510'), (1, '6.520')] -[2023-10-09 09:41:11,439][23469] Updated weights for policy 1, policy_version 34891 (0.0008) -[2023-10-09 09:41:11,801][23469] Updated weights for policy 1, policy_version 34901 (0.0009) -[2023-10-09 09:41:12,176][23469] Updated weights for policy 1, policy_version 34911 (0.0008) -[2023-10-09 09:41:14,789][23468] Updated weights for policy 0, policy_version 34723 (0.0009) -[2023-10-09 09:41:15,161][23468] Updated weights for policy 0, policy_version 34733 (0.0008) -[2023-10-09 09:41:15,525][23468] Updated weights for policy 0, policy_version 34743 (0.0009) -[2023-10-09 09:41:15,892][23469] Updated weights for policy 1, policy_version 34921 (0.0008) -[2023-10-09 09:41:16,077][22500] Fps is (10 sec: 16383.8, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 71335936. Throughput: 0: 1639.2, 1: 1668.8. Samples: 17845236. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-09 09:41:16,078][22500] Avg episode reward: [(0, '6.990'), (1, '6.570')] -[2023-10-09 09:41:16,267][23469] Updated weights for policy 1, policy_version 34931 (0.0008) -[2023-10-09 09:41:16,631][23469] Updated weights for policy 1, policy_version 34941 (0.0007) -[2023-10-09 09:41:19,481][23468] Updated weights for policy 0, policy_version 34753 (0.0008) -[2023-10-09 09:41:19,855][23468] Updated weights for policy 0, policy_version 34763 (0.0007) -[2023-10-09 09:41:20,236][23468] Updated weights for policy 0, policy_version 34773 (0.0007) -[2023-10-09 09:41:20,402][23469] Updated weights for policy 1, policy_version 34951 (0.0008) -[2023-10-09 09:41:20,606][23468] Updated weights for policy 0, policy_version 34783 (0.0008) -[2023-10-09 09:41:20,784][23469] Updated weights for policy 1, policy_version 34961 (0.0009) -[2023-10-09 09:41:21,077][22500] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 71401472. Throughput: 0: 1635.9, 1: 1672.5. Samples: 17855494. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 09:41:21,078][22500] Avg episode reward: [(0, '7.300'), (1, '6.360')] -[2023-10-09 09:41:21,152][23469] Updated weights for policy 1, policy_version 34971 (0.0007) -[2023-10-09 09:41:24,388][23468] Updated weights for policy 0, policy_version 34793 (0.0008) -[2023-10-09 09:41:24,754][23468] Updated weights for policy 0, policy_version 34803 (0.0008) -[2023-10-09 09:41:24,969][23469] Updated weights for policy 1, policy_version 34981 (0.0008) -[2023-10-09 09:41:25,130][23468] Updated weights for policy 0, policy_version 34813 (0.0008) -[2023-10-09 09:41:25,343][23469] Updated weights for policy 1, policy_version 34991 (0.0011) -[2023-10-09 09:41:25,716][23469] Updated weights for policy 1, policy_version 35001 (0.0009) -[2023-10-09 09:41:26,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 71499776. Throughput: 0: 1643.3, 1: 1671.0. Samples: 17877248. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 09:41:26,079][22500] Avg episode reward: [(0, '7.270'), (1, '6.790')] -[2023-10-09 09:41:29,073][23468] Updated weights for policy 0, policy_version 34823 (0.0009) -[2023-10-09 09:41:29,437][23468] Updated weights for policy 0, policy_version 34833 (0.0008) -[2023-10-09 09:41:29,453][23469] Updated weights for policy 1, policy_version 35011 (0.0010) -[2023-10-09 09:41:29,809][23469] Updated weights for policy 1, policy_version 35021 (0.0008) -[2023-10-09 09:41:29,814][23468] Updated weights for policy 0, policy_version 34843 (0.0009) -[2023-10-09 09:41:30,182][23469] Updated weights for policy 1, policy_version 35031 (0.0010) -[2023-10-09 09:41:31,077][22500] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 71565312. Throughput: 0: 1637.6, 1: 1653.6. Samples: 17896284. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 09:41:31,078][22500] Avg episode reward: [(0, '7.440'), (1, '6.890')] -[2023-10-09 09:41:33,519][23468] Updated weights for policy 0, policy_version 34853 (0.0008) -[2023-10-09 09:41:33,897][23468] Updated weights for policy 0, policy_version 34863 (0.0008) -[2023-10-09 09:41:34,051][23469] Updated weights for policy 1, policy_version 35041 (0.0010) -[2023-10-09 09:41:34,258][23468] Updated weights for policy 0, policy_version 34873 (0.0009) -[2023-10-09 09:41:34,422][23469] Updated weights for policy 1, policy_version 35051 (0.0008) -[2023-10-09 09:41:34,790][23469] Updated weights for policy 1, policy_version 35061 (0.0007) -[2023-10-09 09:41:35,154][23469] Updated weights for policy 1, policy_version 35071 (0.0008) -[2023-10-09 09:41:36,077][22500] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 71630848. Throughput: 0: 1643.7, 1: 1674.5. Samples: 17909006. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 09:41:36,078][22500] Avg episode reward: [(0, '7.290'), (1, '7.510')] -[2023-10-09 09:41:38,056][23468] Updated weights for policy 0, policy_version 34883 (0.0009) -[2023-10-09 09:41:38,449][23468] Updated weights for policy 0, policy_version 34893 (0.0010) -[2023-10-09 09:41:38,814][23468] Updated weights for policy 0, policy_version 34903 (0.0008) -[2023-10-09 09:41:39,033][23469] Updated weights for policy 1, policy_version 35081 (0.0008) -[2023-10-09 09:41:39,391][23469] Updated weights for policy 1, policy_version 35091 (0.0010) -[2023-10-09 09:41:39,756][23469] Updated weights for policy 1, policy_version 35101 (0.0010) -[2023-10-09 09:41:41,077][22500] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 71696384. Throughput: 0: 1672.8, 1: 1700.7. Samples: 17928228. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 09:41:41,078][22500] Avg episode reward: [(0, '7.680'), (1, '7.320')] -[2023-10-09 09:41:42,585][23468] Updated weights for policy 0, policy_version 34913 (0.0007) -[2023-10-09 09:41:42,962][23468] Updated weights for policy 0, policy_version 34923 (0.0009) -[2023-10-09 09:41:43,330][23468] Updated weights for policy 0, policy_version 34933 (0.0008) -[2023-10-09 09:41:43,410][23469] Updated weights for policy 1, policy_version 35111 (0.0008) -[2023-10-09 09:41:43,702][23468] Updated weights for policy 0, policy_version 34943 (0.0007) -[2023-10-09 09:41:43,772][23469] Updated weights for policy 1, policy_version 35121 (0.0008) -[2023-10-09 09:41:44,138][23469] Updated weights for policy 1, policy_version 35131 (0.0009) -[2023-10-09 09:41:46,077][22500] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 71761920. Throughput: 0: 1748.3, 1: 1762.1. Samples: 17950294. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 09:41:46,078][22500] Avg episode reward: [(0, '7.850'), (1, '7.600')] -[2023-10-09 09:41:46,086][23343] Saving new best policy, reward=7.600! -[2023-10-09 09:41:47,465][23468] Updated weights for policy 0, policy_version 34953 (0.0007) -[2023-10-09 09:41:47,833][23468] Updated weights for policy 0, policy_version 34963 (0.0009) -[2023-10-09 09:41:47,979][23469] Updated weights for policy 1, policy_version 35141 (0.0008) -[2023-10-09 09:41:48,201][23468] Updated weights for policy 0, policy_version 34973 (0.0008) -[2023-10-09 09:41:48,342][23469] Updated weights for policy 1, policy_version 35151 (0.0009) -[2023-10-09 09:41:48,713][23469] Updated weights for policy 1, policy_version 35161 (0.0010) -[2023-10-09 09:41:51,077][22500] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13662.6). Total num frames: 71827456. Throughput: 0: 1750.6, 1: 1770.2. Samples: 17960446. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 09:41:51,078][22500] Avg episode reward: [(0, '7.430'), (1, '7.120')] -[2023-10-09 09:41:52,262][23468] Updated weights for policy 0, policy_version 34983 (0.0008) -[2023-10-09 09:41:52,598][23469] Updated weights for policy 1, policy_version 35171 (0.0009) -[2023-10-09 09:41:52,639][23468] Updated weights for policy 0, policy_version 34993 (0.0007) -[2023-10-09 09:41:52,967][23469] Updated weights for policy 1, policy_version 35181 (0.0007) -[2023-10-09 09:41:53,019][23468] Updated weights for policy 0, policy_version 35003 (0.0009) -[2023-10-09 09:41:53,350][23469] Updated weights for policy 1, policy_version 35191 (0.0008) -[2023-10-09 09:41:56,077][22500] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 71892992. Throughput: 0: 1746.4, 1: 1768.2. Samples: 17981928. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 09:41:56,079][22500] Avg episode reward: [(0, '7.280'), (1, '7.400')] -[2023-10-09 09:41:56,992][23469] Updated weights for policy 1, policy_version 35201 (0.0009) -[2023-10-09 09:41:57,021][23468] Updated weights for policy 0, policy_version 35013 (0.0009) -[2023-10-09 09:41:57,361][23469] Updated weights for policy 1, policy_version 35211 (0.0008) -[2023-10-09 09:41:57,389][23468] Updated weights for policy 0, policy_version 35023 (0.0007) -[2023-10-09 09:41:57,717][23469] Updated weights for policy 1, policy_version 35221 (0.0008) -[2023-10-09 09:41:57,762][23468] Updated weights for policy 0, policy_version 35033 (0.0008) -[2023-10-09 09:41:58,093][23469] Updated weights for policy 1, policy_version 35231 (0.0008) -[2023-10-09 09:42:01,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 71958528. Throughput: 0: 1760.3, 1: 1771.8. Samples: 18004180. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 09:42:01,079][22500] Avg episode reward: [(0, '7.130'), (1, '7.130')] -[2023-10-09 09:42:01,627][23468] Updated weights for policy 0, policy_version 35043 (0.0007) -[2023-10-09 09:42:01,949][23469] Updated weights for policy 1, policy_version 35241 (0.0007) -[2023-10-09 09:42:01,992][23468] Updated weights for policy 0, policy_version 35053 (0.0008) -[2023-10-09 09:42:02,318][23469] Updated weights for policy 1, policy_version 35251 (0.0009) -[2023-10-09 09:42:02,363][23468] Updated weights for policy 0, policy_version 35063 (0.0007) -[2023-10-09 09:42:02,691][23469] Updated weights for policy 1, policy_version 35261 (0.0007) -[2023-10-09 09:42:06,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 72024064. Throughput: 0: 1746.9, 1: 1773.5. Samples: 18013914. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 09:42:06,078][22500] Avg episode reward: [(0, '7.100'), (1, '7.390')] -[2023-10-09 09:42:06,089][23468] Updated weights for policy 0, policy_version 35073 (0.0009) -[2023-10-09 09:42:06,459][23468] Updated weights for policy 0, policy_version 35083 (0.0010) -[2023-10-09 09:42:06,563][23469] Updated weights for policy 1, policy_version 35271 (0.0009) -[2023-10-09 09:42:06,837][23468] Updated weights for policy 0, policy_version 35093 (0.0008) -[2023-10-09 09:42:06,940][23469] Updated weights for policy 1, policy_version 35281 (0.0007) -[2023-10-09 09:42:07,199][23468] Updated weights for policy 0, policy_version 35103 (0.0009) -[2023-10-09 09:42:07,310][23469] Updated weights for policy 1, policy_version 35291 (0.0010) -[2023-10-09 09:42:10,886][23468] Updated weights for policy 0, policy_version 35113 (0.0010) -[2023-10-09 09:42:11,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 72089600. Throughput: 0: 1751.8, 1: 1772.7. Samples: 18035850. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 09:42:11,078][22500] Avg episode reward: [(0, '7.110'), (1, '7.010')] -[2023-10-09 09:42:11,100][23469] Updated weights for policy 1, policy_version 35301 (0.0008) -[2023-10-09 09:42:11,265][23468] Updated weights for policy 0, policy_version 35123 (0.0009) -[2023-10-09 09:42:11,470][23469] Updated weights for policy 1, policy_version 35311 (0.0007) -[2023-10-09 09:42:11,632][23468] Updated weights for policy 0, policy_version 35133 (0.0007) -[2023-10-09 09:42:11,838][23469] Updated weights for policy 1, policy_version 35321 (0.0007) -[2023-10-09 09:42:15,358][23468] Updated weights for policy 0, policy_version 35143 (0.0008) -[2023-10-09 09:42:15,536][23469] Updated weights for policy 1, policy_version 35331 (0.0008) -[2023-10-09 09:42:15,735][23468] Updated weights for policy 0, policy_version 35153 (0.0007) -[2023-10-09 09:42:15,912][23469] Updated weights for policy 1, policy_version 35341 (0.0009) -[2023-10-09 09:42:16,077][22500] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 72155136. Throughput: 0: 1781.5, 1: 1802.3. Samples: 18057554. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 09:42:16,078][22500] Avg episode reward: [(0, '7.250'), (1, '7.030')] -[2023-10-09 09:42:16,111][23468] Updated weights for policy 0, policy_version 35163 (0.0008) -[2023-10-09 09:42:16,280][23469] Updated weights for policy 1, policy_version 35351 (0.0009) -[2023-10-09 09:42:16,295][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000035168_36012032.pth... -[2023-10-09 09:42:16,325][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000033568_34373632.pth -[2023-10-09 09:42:16,603][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000035360_36208640.pth... -[2023-10-09 09:42:16,632][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000033728_34537472.pth -[2023-10-09 09:42:19,904][23468] Updated weights for policy 0, policy_version 35173 (0.0008) -[2023-10-09 09:42:20,018][23469] Updated weights for policy 1, policy_version 35361 (0.0008) -[2023-10-09 09:42:20,285][23468] Updated weights for policy 0, policy_version 35183 (0.0009) -[2023-10-09 09:42:20,382][23469] Updated weights for policy 1, policy_version 35371 (0.0009) -[2023-10-09 09:42:20,647][23468] Updated weights for policy 0, policy_version 35193 (0.0007) -[2023-10-09 09:42:20,749][23469] Updated weights for policy 1, policy_version 35381 (0.0009) -[2023-10-09 09:42:21,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 72253440. Throughput: 0: 1757.2, 1: 1776.5. Samples: 18068020. Policy #0 lag: (min: 18.0, avg: 43.8, max: 48.0) -[2023-10-09 09:42:21,078][22500] Avg episode reward: [(0, '7.140'), (1, '7.030')] -[2023-10-09 09:42:21,121][23469] Updated weights for policy 1, policy_version 35391 (0.0007) -[2023-10-09 09:42:24,506][23468] Updated weights for policy 0, policy_version 35203 (0.0008) -[2023-10-09 09:42:24,870][23468] Updated weights for policy 0, policy_version 35213 (0.0007) -[2023-10-09 09:42:24,910][23469] Updated weights for policy 1, policy_version 35401 (0.0008) -[2023-10-09 09:42:25,250][23468] Updated weights for policy 0, policy_version 35223 (0.0007) -[2023-10-09 09:42:25,290][23469] Updated weights for policy 1, policy_version 35411 (0.0010) -[2023-10-09 09:42:25,656][23469] Updated weights for policy 1, policy_version 35421 (0.0009) -[2023-10-09 09:42:26,077][22500] Fps is (10 sec: 19661.0, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 72351744. Throughput: 0: 1789.6, 1: 1802.9. Samples: 18089892. Policy #0 lag: (min: 18.0, avg: 43.8, max: 48.0) -[2023-10-09 09:42:26,078][22500] Avg episode reward: [(0, '7.330'), (1, '7.430')] -[2023-10-09 09:42:29,002][23468] Updated weights for policy 0, policy_version 35233 (0.0008) -[2023-10-09 09:42:29,377][23468] Updated weights for policy 0, policy_version 35243 (0.0009) -[2023-10-09 09:42:29,395][23469] Updated weights for policy 1, policy_version 35431 (0.0008) -[2023-10-09 09:42:29,735][23468] Updated weights for policy 0, policy_version 35253 (0.0007) -[2023-10-09 09:42:29,770][23469] Updated weights for policy 1, policy_version 35441 (0.0008) -[2023-10-09 09:42:30,114][23468] Updated weights for policy 0, policy_version 35263 (0.0008) -[2023-10-09 09:42:30,143][23469] Updated weights for policy 1, policy_version 35451 (0.0010) -[2023-10-09 09:42:31,077][22500] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 72417280. Throughput: 0: 1753.0, 1: 1782.4. Samples: 18109388. Policy #0 lag: (min: 18.0, avg: 43.8, max: 48.0) -[2023-10-09 09:42:31,078][22500] Avg episode reward: [(0, '7.250'), (1, '7.910')] -[2023-10-09 09:42:31,088][23343] Saving new best policy, reward=7.910! -[2023-10-09 09:42:33,899][23469] Updated weights for policy 1, policy_version 35461 (0.0007) -[2023-10-09 09:42:33,947][23468] Updated weights for policy 0, policy_version 35273 (0.0008) -[2023-10-09 09:42:34,278][23469] Updated weights for policy 1, policy_version 35471 (0.0007) -[2023-10-09 09:42:34,321][23468] Updated weights for policy 0, policy_version 35283 (0.0009) -[2023-10-09 09:42:34,655][23469] Updated weights for policy 1, policy_version 35481 (0.0007) -[2023-10-09 09:42:34,700][23468] Updated weights for policy 0, policy_version 35293 (0.0009) -[2023-10-09 09:42:36,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 72482816. Throughput: 0: 1780.4, 1: 1808.8. Samples: 18121956. Policy #0 lag: (min: 18.0, avg: 43.8, max: 48.0) -[2023-10-09 09:42:36,078][22500] Avg episode reward: [(0, '7.430'), (1, '7.620')] -[2023-10-09 09:42:38,521][23469] Updated weights for policy 1, policy_version 35491 (0.0009) -[2023-10-09 09:42:38,747][23468] Updated weights for policy 0, policy_version 35303 (0.0007) -[2023-10-09 09:42:38,892][23469] Updated weights for policy 1, policy_version 35501 (0.0007) -[2023-10-09 09:42:39,117][23468] Updated weights for policy 0, policy_version 35313 (0.0007) -[2023-10-09 09:42:39,267][23469] Updated weights for policy 1, policy_version 35511 (0.0009) -[2023-10-09 09:42:39,490][23468] Updated weights for policy 0, policy_version 35323 (0.0008) -[2023-10-09 09:42:41,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 72548352. Throughput: 0: 1759.3, 1: 1778.2. Samples: 18141116. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-09 09:42:41,078][22500] Avg episode reward: [(0, '7.060'), (1, '7.120')] -[2023-10-09 09:42:43,051][23469] Updated weights for policy 1, policy_version 35521 (0.0007) -[2023-10-09 09:42:43,254][23468] Updated weights for policy 0, policy_version 35333 (0.0008) -[2023-10-09 09:42:43,422][23469] Updated weights for policy 1, policy_version 35531 (0.0009) -[2023-10-09 09:42:43,634][23468] Updated weights for policy 0, policy_version 35343 (0.0008) -[2023-10-09 09:42:43,784][23469] Updated weights for policy 1, policy_version 35541 (0.0008) -[2023-10-09 09:42:44,010][23468] Updated weights for policy 0, policy_version 35353 (0.0009) -[2023-10-09 09:42:44,152][23469] Updated weights for policy 1, policy_version 35551 (0.0007) -[2023-10-09 09:42:46,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 72613888. Throughput: 0: 1752.2, 1: 1781.5. Samples: 18163198. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-09 09:42:46,078][22500] Avg episode reward: [(0, '7.560'), (1, '6.720')] -[2023-10-09 09:42:48,050][23468] Updated weights for policy 0, policy_version 35363 (0.0011) -[2023-10-09 09:42:48,079][23469] Updated weights for policy 1, policy_version 35561 (0.0009) -[2023-10-09 09:42:48,428][23468] Updated weights for policy 0, policy_version 35373 (0.0010) -[2023-10-09 09:42:48,434][23469] Updated weights for policy 1, policy_version 35571 (0.0008) -[2023-10-09 09:42:48,804][23469] Updated weights for policy 1, policy_version 35581 (0.0008) -[2023-10-09 09:42:48,819][23468] Updated weights for policy 0, policy_version 35383 (0.0009) -[2023-10-09 09:42:51,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 72679424. Throughput: 0: 1767.0, 1: 1776.8. Samples: 18173388. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-09 09:42:51,078][22500] Avg episode reward: [(0, '7.820'), (1, '6.570')] -[2023-10-09 09:42:52,629][23469] Updated weights for policy 1, policy_version 35591 (0.0009) -[2023-10-09 09:42:52,669][23468] Updated weights for policy 0, policy_version 35393 (0.0009) -[2023-10-09 09:42:52,998][23469] Updated weights for policy 1, policy_version 35601 (0.0007) -[2023-10-09 09:42:53,050][23468] Updated weights for policy 0, policy_version 35403 (0.0007) -[2023-10-09 09:42:53,368][23469] Updated weights for policy 1, policy_version 35611 (0.0008) -[2023-10-09 09:42:53,414][23468] Updated weights for policy 0, policy_version 35413 (0.0007) -[2023-10-09 09:42:53,789][23468] Updated weights for policy 0, policy_version 35423 (0.0007) -[2023-10-09 09:42:56,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 72744960. Throughput: 0: 1746.4, 1: 1770.2. Samples: 18194100. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-09 09:42:56,078][22500] Avg episode reward: [(0, '8.300'), (1, '7.050')] -[2023-10-09 09:42:56,079][23265] Saving new best policy, reward=8.300! -[2023-10-09 09:42:57,332][23469] Updated weights for policy 1, policy_version 35621 (0.0009) -[2023-10-09 09:42:57,596][23468] Updated weights for policy 0, policy_version 35433 (0.0007) -[2023-10-09 09:42:57,718][23469] Updated weights for policy 1, policy_version 35631 (0.0008) -[2023-10-09 09:42:57,975][23468] Updated weights for policy 0, policy_version 35443 (0.0007) -[2023-10-09 09:42:58,085][23469] Updated weights for policy 1, policy_version 35641 (0.0010) -[2023-10-09 09:42:58,342][23468] Updated weights for policy 0, policy_version 35453 (0.0008) -[2023-10-09 09:43:01,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 72810496. Throughput: 0: 1746.0, 1: 1780.8. Samples: 18216262. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-09 09:43:01,078][22500] Avg episode reward: [(0, '7.740'), (1, '6.870')] -[2023-10-09 09:43:01,682][23469] Updated weights for policy 1, policy_version 35651 (0.0007) -[2023-10-09 09:43:02,056][23469] Updated weights for policy 1, policy_version 35661 (0.0007) -[2023-10-09 09:43:02,237][23468] Updated weights for policy 0, policy_version 35463 (0.0009) -[2023-10-09 09:43:02,428][23469] Updated weights for policy 1, policy_version 35671 (0.0009) -[2023-10-09 09:43:02,615][23468] Updated weights for policy 0, policy_version 35473 (0.0007) -[2023-10-09 09:43:02,982][23468] Updated weights for policy 0, policy_version 35483 (0.0008) -[2023-10-09 09:43:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 72876032. Throughput: 0: 1737.1, 1: 1770.0. Samples: 18225836. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 09:43:06,078][22500] Avg episode reward: [(0, '8.130'), (1, '7.590')] -[2023-10-09 09:43:06,302][23469] Updated weights for policy 1, policy_version 35681 (0.0007) -[2023-10-09 09:43:06,632][23468] Updated weights for policy 0, policy_version 35493 (0.0008) -[2023-10-09 09:43:06,671][23469] Updated weights for policy 1, policy_version 35691 (0.0007) -[2023-10-09 09:43:07,009][23468] Updated weights for policy 0, policy_version 35503 (0.0008) -[2023-10-09 09:43:07,039][23469] Updated weights for policy 1, policy_version 35701 (0.0009) -[2023-10-09 09:43:07,373][23468] Updated weights for policy 0, policy_version 35513 (0.0008) -[2023-10-09 09:43:07,411][23469] Updated weights for policy 1, policy_version 35711 (0.0010) -[2023-10-09 09:43:11,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 72941568. Throughput: 0: 1739.7, 1: 1774.8. Samples: 18248046. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 09:43:11,078][22500] Avg episode reward: [(0, '8.050'), (1, '7.210')] -[2023-10-09 09:43:11,094][23468] Updated weights for policy 0, policy_version 35523 (0.0008) -[2023-10-09 09:43:11,156][23469] Updated weights for policy 1, policy_version 35721 (0.0008) -[2023-10-09 09:43:11,466][23468] Updated weights for policy 0, policy_version 35533 (0.0008) -[2023-10-09 09:43:11,526][23469] Updated weights for policy 1, policy_version 35731 (0.0008) -[2023-10-09 09:43:11,838][23468] Updated weights for policy 0, policy_version 35543 (0.0008) -[2023-10-09 09:43:11,898][23469] Updated weights for policy 1, policy_version 35741 (0.0007) -[2023-10-09 09:43:15,544][23469] Updated weights for policy 1, policy_version 35751 (0.0009) -[2023-10-09 09:43:15,598][23468] Updated weights for policy 0, policy_version 35553 (0.0007) -[2023-10-09 09:43:15,908][23469] Updated weights for policy 1, policy_version 35761 (0.0008) -[2023-10-09 09:43:15,959][23468] Updated weights for policy 0, policy_version 35563 (0.0007) -[2023-10-09 09:43:16,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 73007104. Throughput: 0: 1781.8, 1: 1792.1. Samples: 18270214. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 09:43:16,079][22500] Avg episode reward: [(0, '7.790'), (1, '7.460')] -[2023-10-09 09:43:16,267][23469] Updated weights for policy 1, policy_version 35771 (0.0008) -[2023-10-09 09:43:16,338][23468] Updated weights for policy 0, policy_version 35573 (0.0008) -[2023-10-09 09:43:16,720][23468] Updated weights for policy 0, policy_version 35583 (0.0010) -[2023-10-09 09:43:20,094][23469] Updated weights for policy 1, policy_version 35781 (0.0009) -[2023-10-09 09:43:20,454][23468] Updated weights for policy 0, policy_version 35593 (0.0007) -[2023-10-09 09:43:20,455][23469] Updated weights for policy 1, policy_version 35791 (0.0007) -[2023-10-09 09:43:20,828][23469] Updated weights for policy 1, policy_version 35801 (0.0007) -[2023-10-09 09:43:20,832][23468] Updated weights for policy 0, policy_version 35603 (0.0007) -[2023-10-09 09:43:21,077][22500] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 73072640. Throughput: 0: 1752.3, 1: 1771.2. Samples: 18280514. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 09:43:21,079][22500] Avg episode reward: [(0, '7.880'), (1, '7.070')] -[2023-10-09 09:43:21,201][23468] Updated weights for policy 0, policy_version 35613 (0.0009) -[2023-10-09 09:43:24,761][23469] Updated weights for policy 1, policy_version 35811 (0.0010) -[2023-10-09 09:43:25,046][23468] Updated weights for policy 0, policy_version 35623 (0.0008) -[2023-10-09 09:43:25,123][23469] Updated weights for policy 1, policy_version 35821 (0.0008) -[2023-10-09 09:43:25,425][23468] Updated weights for policy 0, policy_version 35633 (0.0008) -[2023-10-09 09:43:25,483][23469] Updated weights for policy 1, policy_version 35831 (0.0008) -[2023-10-09 09:43:25,788][23468] Updated weights for policy 0, policy_version 35643 (0.0007) -[2023-10-09 09:43:26,077][22500] Fps is (10 sec: 19661.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 73203712. Throughput: 0: 1787.2, 1: 1796.1. Samples: 18302362. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 09:43:26,078][22500] Avg episode reward: [(0, '7.190'), (1, '7.000')] -[2023-10-09 09:43:29,087][23469] Updated weights for policy 1, policy_version 35841 (0.0008) -[2023-10-09 09:43:29,455][23469] Updated weights for policy 1, policy_version 35851 (0.0010) -[2023-10-09 09:43:29,565][23468] Updated weights for policy 0, policy_version 35653 (0.0007) -[2023-10-09 09:43:29,827][23469] Updated weights for policy 1, policy_version 35861 (0.0007) -[2023-10-09 09:43:29,939][23468] Updated weights for policy 0, policy_version 35663 (0.0008) -[2023-10-09 09:43:30,197][23469] Updated weights for policy 1, policy_version 35871 (0.0008) -[2023-10-09 09:43:30,304][23468] Updated weights for policy 0, policy_version 35673 (0.0008) -[2023-10-09 09:43:31,077][22500] Fps is (10 sec: 19661.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 73269248. Throughput: 0: 1770.9, 1: 1762.5. Samples: 18322204. Policy #0 lag: (min: 19.0, avg: 26.3, max: 51.0) -[2023-10-09 09:43:31,078][22500] Avg episode reward: [(0, '7.220'), (1, '6.860')] -[2023-10-09 09:43:33,967][23468] Updated weights for policy 0, policy_version 35683 (0.0009) -[2023-10-09 09:43:34,052][23469] Updated weights for policy 1, policy_version 35881 (0.0008) -[2023-10-09 09:43:34,339][23468] Updated weights for policy 0, policy_version 35693 (0.0007) -[2023-10-09 09:43:34,412][23469] Updated weights for policy 1, policy_version 35891 (0.0009) -[2023-10-09 09:43:34,712][23468] Updated weights for policy 0, policy_version 35703 (0.0008) -[2023-10-09 09:43:34,795][23469] Updated weights for policy 1, policy_version 35901 (0.0009) -[2023-10-09 09:43:36,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 73334784. Throughput: 0: 1788.4, 1: 1791.9. Samples: 18334504. Policy #0 lag: (min: 19.0, avg: 26.3, max: 51.0) -[2023-10-09 09:43:36,078][22500] Avg episode reward: [(0, '7.120'), (1, '7.280')] -[2023-10-09 09:43:38,362][23468] Updated weights for policy 0, policy_version 35713 (0.0008) -[2023-10-09 09:43:38,594][23469] Updated weights for policy 1, policy_version 35911 (0.0009) -[2023-10-09 09:43:38,731][23468] Updated weights for policy 0, policy_version 35723 (0.0009) -[2023-10-09 09:43:38,960][23469] Updated weights for policy 1, policy_version 35921 (0.0008) -[2023-10-09 09:43:39,102][23468] Updated weights for policy 0, policy_version 35733 (0.0008) -[2023-10-09 09:43:39,329][23469] Updated weights for policy 1, policy_version 35931 (0.0007) -[2023-10-09 09:43:39,481][23468] Updated weights for policy 0, policy_version 35743 (0.0009) -[2023-10-09 09:43:41,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 73400320. Throughput: 0: 1789.9, 1: 1772.0. Samples: 18354386. Policy #0 lag: (min: 19.0, avg: 26.3, max: 51.0) -[2023-10-09 09:43:41,078][22500] Avg episode reward: [(0, '7.070'), (1, '7.610')] -[2023-10-09 09:43:43,079][23469] Updated weights for policy 1, policy_version 35941 (0.0007) -[2023-10-09 09:43:43,344][23468] Updated weights for policy 0, policy_version 35753 (0.0007) -[2023-10-09 09:43:43,474][23469] Updated weights for policy 1, policy_version 35951 (0.0009) -[2023-10-09 09:43:43,717][23468] Updated weights for policy 0, policy_version 35763 (0.0007) -[2023-10-09 09:43:43,833][23469] Updated weights for policy 1, policy_version 35961 (0.0007) -[2023-10-09 09:43:44,082][23468] Updated weights for policy 0, policy_version 35773 (0.0009) -[2023-10-09 09:43:46,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 73465856. Throughput: 0: 1782.8, 1: 1762.0. Samples: 18375774. Policy #0 lag: (min: 19.0, avg: 26.3, max: 51.0) -[2023-10-09 09:43:46,078][22500] Avg episode reward: [(0, '7.600'), (1, '7.480')] -[2023-10-09 09:43:48,023][23469] Updated weights for policy 1, policy_version 35971 (0.0009) -[2023-10-09 09:43:48,396][23469] Updated weights for policy 1, policy_version 35981 (0.0010) -[2023-10-09 09:43:48,481][23468] Updated weights for policy 0, policy_version 35783 (0.0009) -[2023-10-09 09:43:48,763][23469] Updated weights for policy 1, policy_version 35991 (0.0009) -[2023-10-09 09:43:48,848][23468] Updated weights for policy 0, policy_version 35793 (0.0010) -[2023-10-09 09:43:49,225][23468] Updated weights for policy 0, policy_version 35803 (0.0010) -[2023-10-09 09:43:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 73531392. Throughput: 0: 1782.9, 1: 1754.7. Samples: 18385028. Policy #0 lag: (min: 19.0, avg: 26.3, max: 51.0) -[2023-10-09 09:43:51,078][22500] Avg episode reward: [(0, '7.820'), (1, '7.540')] -[2023-10-09 09:43:53,319][23469] Updated weights for policy 1, policy_version 36001 (0.0011) -[2023-10-09 09:43:53,696][23469] Updated weights for policy 1, policy_version 36011 (0.0010) -[2023-10-09 09:43:53,823][23468] Updated weights for policy 0, policy_version 35813 (0.0010) -[2023-10-09 09:43:54,053][23469] Updated weights for policy 1, policy_version 36021 (0.0010) -[2023-10-09 09:43:54,194][23468] Updated weights for policy 0, policy_version 35823 (0.0010) -[2023-10-09 09:43:54,432][23469] Updated weights for policy 1, policy_version 36031 (0.0009) -[2023-10-09 09:43:54,559][23468] Updated weights for policy 0, policy_version 35833 (0.0009) -[2023-10-09 09:43:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 73596928. Throughput: 0: 1728.0, 1: 1710.7. Samples: 18402788. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:43:56,078][22500] Avg episode reward: [(0, '7.630'), (1, '7.550')] -[2023-10-09 09:43:59,039][23469] Updated weights for policy 1, policy_version 36041 (0.0011) -[2023-10-09 09:43:59,220][23468] Updated weights for policy 0, policy_version 35843 (0.0011) -[2023-10-09 09:43:59,408][23469] Updated weights for policy 1, policy_version 36051 (0.0010) -[2023-10-09 09:43:59,591][23468] Updated weights for policy 0, policy_version 35853 (0.0011) -[2023-10-09 09:43:59,781][23469] Updated weights for policy 1, policy_version 36061 (0.0011) -[2023-10-09 09:43:59,959][23468] Updated weights for policy 0, policy_version 35863 (0.0011) -[2023-10-09 09:44:01,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 73662464. Throughput: 0: 1667.6, 1: 1674.7. Samples: 18420618. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:44:01,078][22500] Avg episode reward: [(0, '7.510'), (1, '7.670')] -[2023-10-09 09:44:03,964][23469] Updated weights for policy 1, policy_version 36071 (0.0010) -[2023-10-09 09:44:04,182][23468] Updated weights for policy 0, policy_version 35873 (0.0011) -[2023-10-09 09:44:04,337][23469] Updated weights for policy 1, policy_version 36081 (0.0009) -[2023-10-09 09:44:04,562][23468] Updated weights for policy 0, policy_version 35883 (0.0009) -[2023-10-09 09:44:04,709][23469] Updated weights for policy 1, policy_version 36091 (0.0009) -[2023-10-09 09:44:04,929][23468] Updated weights for policy 0, policy_version 35893 (0.0008) -[2023-10-09 09:44:05,310][23468] Updated weights for policy 0, policy_version 35903 (0.0009) -[2023-10-09 09:44:06,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 73728000. Throughput: 0: 1685.3, 1: 1681.5. Samples: 18432016. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:44:06,078][22500] Avg episode reward: [(0, '7.720'), (1, '7.240')] -[2023-10-09 09:44:09,154][23469] Updated weights for policy 1, policy_version 36101 (0.0009) -[2023-10-09 09:44:09,523][23469] Updated weights for policy 1, policy_version 36111 (0.0009) -[2023-10-09 09:44:09,898][23469] Updated weights for policy 1, policy_version 36121 (0.0009) -[2023-10-09 09:44:09,902][23468] Updated weights for policy 0, policy_version 35913 (0.0010) -[2023-10-09 09:44:10,280][23468] Updated weights for policy 0, policy_version 35923 (0.0011) -[2023-10-09 09:44:10,646][23468] Updated weights for policy 0, policy_version 35933 (0.0010) -[2023-10-09 09:44:11,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 73793536. Throughput: 0: 1646.0, 1: 1638.5. Samples: 18450166. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:44:11,078][22500] Avg episode reward: [(0, '7.180'), (1, '6.870')] -[2023-10-09 09:44:14,326][23469] Updated weights for policy 1, policy_version 36131 (0.0010) -[2023-10-09 09:44:14,694][23469] Updated weights for policy 1, policy_version 36141 (0.0011) -[2023-10-09 09:44:15,067][23469] Updated weights for policy 1, policy_version 36151 (0.0011) -[2023-10-09 09:44:15,312][23468] Updated weights for policy 0, policy_version 35943 (0.0010) -[2023-10-09 09:44:15,699][23468] Updated weights for policy 0, policy_version 35953 (0.0011) -[2023-10-09 09:44:16,063][23468] Updated weights for policy 0, policy_version 35963 (0.0011) -[2023-10-09 09:44:16,077][22500] Fps is (10 sec: 9830.2, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 73826304. Throughput: 0: 1624.1, 1: 1616.8. Samples: 18468046. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:44:16,078][22500] Avg episode reward: [(0, '7.180'), (1, '6.610')] -[2023-10-09 09:44:16,088][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000036160_37027840.pth... -[2023-10-09 09:44:16,126][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000034528_35356672.pth -[2023-10-09 09:44:16,250][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000035968_36831232.pth... -[2023-10-09 09:44:16,292][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000034368_35192832.pth -[2023-10-09 09:44:19,720][23469] Updated weights for policy 1, policy_version 36161 (0.0011) -[2023-10-09 09:44:20,093][23469] Updated weights for policy 1, policy_version 36171 (0.0010) -[2023-10-09 09:44:20,468][23469] Updated weights for policy 1, policy_version 36181 (0.0011) -[2023-10-09 09:44:20,657][23468] Updated weights for policy 0, policy_version 35973 (0.0010) -[2023-10-09 09:44:20,839][23469] Updated weights for policy 1, policy_version 36191 (0.0010) -[2023-10-09 09:44:21,028][23468] Updated weights for policy 0, policy_version 35983 (0.0011) -[2023-10-09 09:44:21,077][22500] Fps is (10 sec: 9830.4, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 73891840. Throughput: 0: 1581.3, 1: 1594.8. Samples: 18477426. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:44:21,078][22500] Avg episode reward: [(0, '6.900'), (1, '7.150')] -[2023-10-09 09:44:21,403][23468] Updated weights for policy 0, policy_version 35993 (0.0010) -[2023-10-09 09:44:24,931][23469] Updated weights for policy 1, policy_version 36201 (0.0008) -[2023-10-09 09:44:25,301][23469] Updated weights for policy 1, policy_version 36211 (0.0008) -[2023-10-09 09:44:25,405][23468] Updated weights for policy 0, policy_version 36003 (0.0010) -[2023-10-09 09:44:25,662][23469] Updated weights for policy 1, policy_version 36221 (0.0010) -[2023-10-09 09:44:25,775][23468] Updated weights for policy 0, policy_version 36013 (0.0010) -[2023-10-09 09:44:26,077][22500] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 13773.7). Total num frames: 73957376. Throughput: 0: 1574.4, 1: 1597.7. Samples: 18497128. Policy #0 lag: (min: 0.0, avg: 24.7, max: 32.0) -[2023-10-09 09:44:26,078][22500] Avg episode reward: [(0, '7.260'), (1, '7.230')] -[2023-10-09 09:44:26,143][23468] Updated weights for policy 0, policy_version 36023 (0.0009) -[2023-10-09 09:44:29,627][23469] Updated weights for policy 1, policy_version 36231 (0.0008) -[2023-10-09 09:44:29,959][23468] Updated weights for policy 0, policy_version 36033 (0.0010) -[2023-10-09 09:44:30,018][23469] Updated weights for policy 1, policy_version 36241 (0.0007) -[2023-10-09 09:44:30,329][23468] Updated weights for policy 0, policy_version 36043 (0.0008) -[2023-10-09 09:44:30,396][23469] Updated weights for policy 1, policy_version 36251 (0.0009) -[2023-10-09 09:44:30,705][23468] Updated weights for policy 0, policy_version 36053 (0.0008) -[2023-10-09 09:44:31,077][22500] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 13773.7). Total num frames: 74022912. Throughput: 0: 1579.2, 1: 1570.3. Samples: 18517502. Policy #0 lag: (min: 0.0, avg: 24.7, max: 32.0) -[2023-10-09 09:44:31,079][22500] Avg episode reward: [(0, '8.020'), (1, '7.570')] -[2023-10-09 09:44:31,081][23468] Updated weights for policy 0, policy_version 36063 (0.0007) -[2023-10-09 09:44:34,004][23469] Updated weights for policy 1, policy_version 36261 (0.0009) -[2023-10-09 09:44:34,364][23469] Updated weights for policy 1, policy_version 36271 (0.0008) -[2023-10-09 09:44:34,735][23469] Updated weights for policy 1, policy_version 36281 (0.0007) -[2023-10-09 09:44:34,761][23468] Updated weights for policy 0, policy_version 36073 (0.0008) -[2023-10-09 09:44:35,124][23468] Updated weights for policy 0, policy_version 36083 (0.0008) -[2023-10-09 09:44:35,503][23468] Updated weights for policy 0, policy_version 36093 (0.0008) -[2023-10-09 09:44:36,077][22500] Fps is (10 sec: 16383.9, 60 sec: 13107.2, 300 sec: 13884.7). Total num frames: 74121216. Throughput: 0: 1589.2, 1: 1618.4. Samples: 18529370. Policy #0 lag: (min: 0.0, avg: 24.7, max: 32.0) -[2023-10-09 09:44:36,078][22500] Avg episode reward: [(0, '7.620'), (1, '7.380')] -[2023-10-09 09:44:38,533][23469] Updated weights for policy 1, policy_version 36291 (0.0009) -[2023-10-09 09:44:38,914][23469] Updated weights for policy 1, policy_version 36301 (0.0011) -[2023-10-09 09:44:39,227][23468] Updated weights for policy 0, policy_version 36103 (0.0007) -[2023-10-09 09:44:39,269][23469] Updated weights for policy 1, policy_version 36311 (0.0009) -[2023-10-09 09:44:39,595][23468] Updated weights for policy 0, policy_version 36113 (0.0007) -[2023-10-09 09:44:39,966][23468] Updated weights for policy 0, policy_version 36123 (0.0008) -[2023-10-09 09:44:41,077][22500] Fps is (10 sec: 16384.4, 60 sec: 13107.2, 300 sec: 13884.7). Total num frames: 74186752. Throughput: 0: 1635.6, 1: 1635.1. Samples: 18549968. Policy #0 lag: (min: 0.0, avg: 24.7, max: 32.0) -[2023-10-09 09:44:41,078][22500] Avg episode reward: [(0, '8.140'), (1, '7.240')] -[2023-10-09 09:44:43,069][23469] Updated weights for policy 1, policy_version 36321 (0.0008) -[2023-10-09 09:44:43,445][23469] Updated weights for policy 1, policy_version 36331 (0.0007) -[2023-10-09 09:44:43,800][23468] Updated weights for policy 0, policy_version 36133 (0.0010) -[2023-10-09 09:44:43,804][23469] Updated weights for policy 1, policy_version 36341 (0.0008) -[2023-10-09 09:44:44,172][23469] Updated weights for policy 1, policy_version 36351 (0.0007) -[2023-10-09 09:44:44,175][23468] Updated weights for policy 0, policy_version 36143 (0.0009) -[2023-10-09 09:44:44,552][23468] Updated weights for policy 0, policy_version 36153 (0.0009) -[2023-10-09 09:44:46,077][22500] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13884.7). Total num frames: 74252288. Throughput: 0: 1666.5, 1: 1682.7. Samples: 18571334. Policy #0 lag: (min: 31.0, avg: 31.9, max: 52.0) -[2023-10-09 09:44:46,079][22500] Avg episode reward: [(0, '7.360'), (1, '6.880')] -[2023-10-09 09:44:47,983][23469] Updated weights for policy 1, policy_version 36361 (0.0007) -[2023-10-09 09:44:48,258][23468] Updated weights for policy 0, policy_version 36163 (0.0007) -[2023-10-09 09:44:48,346][23469] Updated weights for policy 1, policy_version 36371 (0.0008) -[2023-10-09 09:44:48,619][23468] Updated weights for policy 0, policy_version 36173 (0.0008) -[2023-10-09 09:44:48,720][23469] Updated weights for policy 1, policy_version 36381 (0.0008) -[2023-10-09 09:44:48,992][23468] Updated weights for policy 0, policy_version 36183 (0.0008) -[2023-10-09 09:44:51,077][22500] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 74317824. Throughput: 0: 1678.2, 1: 1660.3. Samples: 18582252. Policy #0 lag: (min: 31.0, avg: 31.9, max: 52.0) -[2023-10-09 09:44:51,079][22500] Avg episode reward: [(0, '7.760'), (1, '7.410')] -[2023-10-09 09:44:52,544][23469] Updated weights for policy 1, policy_version 36391 (0.0007) -[2023-10-09 09:44:52,746][23468] Updated weights for policy 0, policy_version 36193 (0.0008) -[2023-10-09 09:44:52,906][23469] Updated weights for policy 1, policy_version 36401 (0.0007) -[2023-10-09 09:44:53,126][23468] Updated weights for policy 0, policy_version 36203 (0.0007) -[2023-10-09 09:44:53,284][23469] Updated weights for policy 1, policy_version 36411 (0.0007) -[2023-10-09 09:44:53,499][23468] Updated weights for policy 0, policy_version 36213 (0.0008) -[2023-10-09 09:44:53,863][23468] Updated weights for policy 0, policy_version 36223 (0.0011) -[2023-10-09 09:44:56,077][22500] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 74383360. Throughput: 0: 1686.7, 1: 1709.0. Samples: 18602970. Policy #0 lag: (min: 31.0, avg: 31.9, max: 52.0) -[2023-10-09 09:44:56,079][22500] Avg episode reward: [(0, '7.560'), (1, '7.290')] -[2023-10-09 09:44:57,092][23469] Updated weights for policy 1, policy_version 36421 (0.0008) -[2023-10-09 09:44:57,456][23469] Updated weights for policy 1, policy_version 36431 (0.0007) -[2023-10-09 09:44:57,687][23468] Updated weights for policy 0, policy_version 36233 (0.0008) -[2023-10-09 09:44:57,829][23469] Updated weights for policy 1, policy_version 36441 (0.0008) -[2023-10-09 09:44:58,058][23468] Updated weights for policy 0, policy_version 36243 (0.0008) -[2023-10-09 09:44:58,435][23468] Updated weights for policy 0, policy_version 36253 (0.0007) -[2023-10-09 09:45:01,078][22500] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 74448896. Throughput: 0: 1738.0, 1: 1758.0. Samples: 18625366. Policy #0 lag: (min: 31.0, avg: 31.9, max: 52.0) -[2023-10-09 09:45:01,079][22500] Avg episode reward: [(0, '7.350'), (1, '7.190')] -[2023-10-09 09:45:01,600][23469] Updated weights for policy 1, policy_version 36451 (0.0008) -[2023-10-09 09:45:01,968][23469] Updated weights for policy 1, policy_version 36461 (0.0009) -[2023-10-09 09:45:02,328][23468] Updated weights for policy 0, policy_version 36263 (0.0009) -[2023-10-09 09:45:02,329][23469] Updated weights for policy 1, policy_version 36471 (0.0007) -[2023-10-09 09:45:02,705][23468] Updated weights for policy 0, policy_version 36273 (0.0009) -[2023-10-09 09:45:03,084][23468] Updated weights for policy 0, policy_version 36283 (0.0008) -[2023-10-09 09:45:05,963][23469] Updated weights for policy 1, policy_version 36481 (0.0008) -[2023-10-09 09:45:06,077][22500] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 74514432. Throughput: 0: 1748.3, 1: 1755.1. Samples: 18635080. Policy #0 lag: (min: 31.0, avg: 31.9, max: 52.0) -[2023-10-09 09:45:06,078][22500] Avg episode reward: [(0, '8.150'), (1, '7.370')] -[2023-10-09 09:45:06,333][23469] Updated weights for policy 1, policy_version 36491 (0.0010) -[2023-10-09 09:45:06,701][23469] Updated weights for policy 1, policy_version 36501 (0.0011) -[2023-10-09 09:45:06,771][23468] Updated weights for policy 0, policy_version 36293 (0.0008) -[2023-10-09 09:45:07,071][23469] Updated weights for policy 1, policy_version 36511 (0.0008) -[2023-10-09 09:45:07,141][23468] Updated weights for policy 0, policy_version 36303 (0.0008) -[2023-10-09 09:45:07,524][23468] Updated weights for policy 0, policy_version 36313 (0.0010) -[2023-10-09 09:45:10,945][23469] Updated weights for policy 1, policy_version 36521 (0.0010) -[2023-10-09 09:45:11,078][22500] Fps is (10 sec: 13107.1, 60 sec: 13107.1, 300 sec: 13773.7). Total num frames: 74579968. Throughput: 0: 1780.0, 1: 1782.2. Samples: 18657428. Policy #0 lag: (min: 31.0, avg: 31.9, max: 52.0) -[2023-10-09 09:45:11,079][22500] Avg episode reward: [(0, '7.740'), (1, '7.400')] -[2023-10-09 09:45:11,315][23469] Updated weights for policy 1, policy_version 36531 (0.0009) -[2023-10-09 09:45:11,406][23468] Updated weights for policy 0, policy_version 36323 (0.0007) -[2023-10-09 09:45:11,680][23469] Updated weights for policy 1, policy_version 36541 (0.0007) -[2023-10-09 09:45:11,773][23468] Updated weights for policy 0, policy_version 36333 (0.0009) -[2023-10-09 09:45:12,147][23468] Updated weights for policy 0, policy_version 36343 (0.0009) -[2023-10-09 09:45:15,571][23469] Updated weights for policy 1, policy_version 36551 (0.0008) -[2023-10-09 09:45:15,803][23468] Updated weights for policy 0, policy_version 36353 (0.0007) -[2023-10-09 09:45:15,942][23469] Updated weights for policy 1, policy_version 36561 (0.0010) -[2023-10-09 09:45:16,077][22500] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 74645504. Throughput: 0: 1787.4, 1: 1799.6. Samples: 18678918. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:45:16,078][22500] Avg episode reward: [(0, '8.120'), (1, '7.470')] -[2023-10-09 09:45:16,180][23468] Updated weights for policy 0, policy_version 36363 (0.0008) -[2023-10-09 09:45:16,309][23469] Updated weights for policy 1, policy_version 36571 (0.0008) -[2023-10-09 09:45:16,546][23468] Updated weights for policy 0, policy_version 36373 (0.0009) -[2023-10-09 09:45:16,913][23468] Updated weights for policy 0, policy_version 36383 (0.0007) -[2023-10-09 09:45:20,117][23469] Updated weights for policy 1, policy_version 36581 (0.0010) -[2023-10-09 09:45:20,477][23469] Updated weights for policy 1, policy_version 36591 (0.0009) -[2023-10-09 09:45:20,634][23468] Updated weights for policy 0, policy_version 36393 (0.0007) -[2023-10-09 09:45:20,846][23469] Updated weights for policy 1, policy_version 36601 (0.0008) -[2023-10-09 09:45:20,997][23468] Updated weights for policy 0, policy_version 36403 (0.0009) -[2023-10-09 09:45:21,077][22500] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 74711040. Throughput: 0: 1778.0, 1: 1776.4. Samples: 18689318. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:45:21,078][22500] Avg episode reward: [(0, '7.850'), (1, '6.930')] -[2023-10-09 09:45:21,368][23468] Updated weights for policy 0, policy_version 36413 (0.0009) -[2023-10-09 09:45:24,735][23469] Updated weights for policy 1, policy_version 36611 (0.0008) -[2023-10-09 09:45:25,108][23469] Updated weights for policy 1, policy_version 36621 (0.0008) -[2023-10-09 09:45:25,280][23468] Updated weights for policy 0, policy_version 36423 (0.0007) -[2023-10-09 09:45:25,477][23469] Updated weights for policy 1, policy_version 36631 (0.0009) -[2023-10-09 09:45:25,654][23468] Updated weights for policy 0, policy_version 36433 (0.0007) -[2023-10-09 09:45:26,030][23468] Updated weights for policy 0, policy_version 36443 (0.0007) -[2023-10-09 09:45:26,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 74809344. Throughput: 0: 1786.4, 1: 1801.7. Samples: 18711432. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:45:26,078][22500] Avg episode reward: [(0, '7.720'), (1, '7.140')] -[2023-10-09 09:45:29,122][23469] Updated weights for policy 1, policy_version 36641 (0.0008) -[2023-10-09 09:45:29,494][23469] Updated weights for policy 1, policy_version 36651 (0.0009) -[2023-10-09 09:45:29,870][23469] Updated weights for policy 1, policy_version 36661 (0.0008) -[2023-10-09 09:45:29,947][23468] Updated weights for policy 0, policy_version 36453 (0.0007) -[2023-10-09 09:45:30,238][23469] Updated weights for policy 1, policy_version 36671 (0.0010) -[2023-10-09 09:45:30,318][23468] Updated weights for policy 0, policy_version 36463 (0.0008) -[2023-10-09 09:45:30,681][23468] Updated weights for policy 0, policy_version 36473 (0.0009) -[2023-10-09 09:45:31,077][22500] Fps is (10 sec: 19660.7, 60 sec: 14745.6, 300 sec: 13884.7). Total num frames: 74907648. Throughput: 0: 1791.3, 1: 1767.5. Samples: 18731482. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:45:31,078][22500] Avg episode reward: [(0, '7.790'), (1, '7.290')] -[2023-10-09 09:45:34,204][23469] Updated weights for policy 1, policy_version 36681 (0.0009) -[2023-10-09 09:45:34,387][23468] Updated weights for policy 0, policy_version 36483 (0.0009) -[2023-10-09 09:45:34,569][23469] Updated weights for policy 1, policy_version 36691 (0.0008) -[2023-10-09 09:45:34,761][23468] Updated weights for policy 0, policy_version 36493 (0.0008) -[2023-10-09 09:45:34,936][23469] Updated weights for policy 1, policy_version 36701 (0.0007) -[2023-10-09 09:45:35,140][23468] Updated weights for policy 0, policy_version 36503 (0.0008) -[2023-10-09 09:45:36,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 74973184. Throughput: 0: 1776.8, 1: 1797.2. Samples: 18743078. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:45:36,078][22500] Avg episode reward: [(0, '7.610'), (1, '7.340')] -[2023-10-09 09:45:38,624][23469] Updated weights for policy 1, policy_version 36711 (0.0009) -[2023-10-09 09:45:38,910][23468] Updated weights for policy 0, policy_version 36513 (0.0010) -[2023-10-09 09:45:38,999][23469] Updated weights for policy 1, policy_version 36721 (0.0010) -[2023-10-09 09:45:39,277][23468] Updated weights for policy 0, policy_version 36523 (0.0008) -[2023-10-09 09:45:39,366][23469] Updated weights for policy 1, policy_version 36731 (0.0009) -[2023-10-09 09:45:39,648][23468] Updated weights for policy 0, policy_version 36533 (0.0009) -[2023-10-09 09:45:40,018][23468] Updated weights for policy 0, policy_version 36543 (0.0008) -[2023-10-09 09:45:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 75038720. Throughput: 0: 1796.9, 1: 1770.0. Samples: 18763478. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 09:45:41,078][22500] Avg episode reward: [(0, '7.700'), (1, '7.370')] -[2023-10-09 09:45:43,272][23469] Updated weights for policy 1, policy_version 36741 (0.0008) -[2023-10-09 09:45:43,646][23469] Updated weights for policy 1, policy_version 36751 (0.0009) -[2023-10-09 09:45:43,771][23468] Updated weights for policy 0, policy_version 36553 (0.0008) -[2023-10-09 09:45:44,016][23469] Updated weights for policy 1, policy_version 36761 (0.0010) -[2023-10-09 09:45:44,135][23468] Updated weights for policy 0, policy_version 36563 (0.0008) -[2023-10-09 09:45:44,511][23468] Updated weights for policy 0, policy_version 36573 (0.0009) -[2023-10-09 09:45:46,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 75104256. Throughput: 0: 1772.4, 1: 1769.6. Samples: 18784756. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 09:45:46,079][22500] Avg episode reward: [(0, '7.910'), (1, '7.560')] -[2023-10-09 09:45:47,853][23469] Updated weights for policy 1, policy_version 36771 (0.0008) -[2023-10-09 09:45:48,211][23469] Updated weights for policy 1, policy_version 36781 (0.0007) -[2023-10-09 09:45:48,429][23468] Updated weights for policy 0, policy_version 36583 (0.0008) -[2023-10-09 09:45:48,584][23469] Updated weights for policy 1, policy_version 36791 (0.0009) -[2023-10-09 09:45:48,801][23468] Updated weights for policy 0, policy_version 36593 (0.0008) -[2023-10-09 09:45:49,181][23468] Updated weights for policy 0, policy_version 36603 (0.0007) -[2023-10-09 09:45:51,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 75169792. Throughput: 0: 1798.9, 1: 1769.1. Samples: 18795638. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 09:45:51,078][22500] Avg episode reward: [(0, '7.600'), (1, '7.730')] -[2023-10-09 09:45:52,394][23469] Updated weights for policy 1, policy_version 36801 (0.0008) -[2023-10-09 09:45:52,764][23469] Updated weights for policy 1, policy_version 36811 (0.0007) -[2023-10-09 09:45:53,016][23468] Updated weights for policy 0, policy_version 36613 (0.0008) -[2023-10-09 09:45:53,139][23469] Updated weights for policy 1, policy_version 36821 (0.0008) -[2023-10-09 09:45:53,387][23468] Updated weights for policy 0, policy_version 36623 (0.0007) -[2023-10-09 09:45:53,515][23469] Updated weights for policy 1, policy_version 36831 (0.0009) -[2023-10-09 09:45:53,770][23468] Updated weights for policy 0, policy_version 36633 (0.0009) -[2023-10-09 09:45:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 75235328. Throughput: 0: 1764.5, 1: 1767.1. Samples: 18816352. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 09:45:56,078][22500] Avg episode reward: [(0, '7.730'), (1, '7.490')] -[2023-10-09 09:45:57,196][23469] Updated weights for policy 1, policy_version 36841 (0.0007) -[2023-10-09 09:45:57,562][23469] Updated weights for policy 1, policy_version 36851 (0.0008) -[2023-10-09 09:45:57,680][23468] Updated weights for policy 0, policy_version 36643 (0.0009) -[2023-10-09 09:45:57,926][23469] Updated weights for policy 1, policy_version 36861 (0.0009) -[2023-10-09 09:45:58,048][23468] Updated weights for policy 0, policy_version 36653 (0.0008) -[2023-10-09 09:45:58,424][23468] Updated weights for policy 0, policy_version 36663 (0.0007) -[2023-10-09 09:46:01,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 75300864. Throughput: 0: 1766.3, 1: 1788.0. Samples: 18838862. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 09:46:01,078][22500] Avg episode reward: [(0, '7.760'), (1, '7.180')] -[2023-10-09 09:46:01,756][23469] Updated weights for policy 1, policy_version 36871 (0.0008) -[2023-10-09 09:46:02,134][23469] Updated weights for policy 1, policy_version 36881 (0.0009) -[2023-10-09 09:46:02,196][23468] Updated weights for policy 0, policy_version 36673 (0.0008) -[2023-10-09 09:46:02,504][23469] Updated weights for policy 1, policy_version 36891 (0.0010) -[2023-10-09 09:46:02,572][23468] Updated weights for policy 0, policy_version 36683 (0.0007) -[2023-10-09 09:46:02,947][23468] Updated weights for policy 0, policy_version 36693 (0.0007) -[2023-10-09 09:46:03,332][23468] Updated weights for policy 0, policy_version 36703 (0.0009) -[2023-10-09 09:46:06,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 75366400. Throughput: 0: 1767.2, 1: 1769.5. Samples: 18848470. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 09:46:06,078][22500] Avg episode reward: [(0, '7.800'), (1, '7.330')] -[2023-10-09 09:46:06,369][23469] Updated weights for policy 1, policy_version 36901 (0.0009) -[2023-10-09 09:46:06,743][23469] Updated weights for policy 1, policy_version 36911 (0.0011) -[2023-10-09 09:46:07,111][23469] Updated weights for policy 1, policy_version 36921 (0.0008) -[2023-10-09 09:46:07,249][23468] Updated weights for policy 0, policy_version 36713 (0.0008) -[2023-10-09 09:46:07,618][23468] Updated weights for policy 0, policy_version 36723 (0.0009) -[2023-10-09 09:46:07,992][23468] Updated weights for policy 0, policy_version 36733 (0.0007) -[2023-10-09 09:46:10,815][23469] Updated weights for policy 1, policy_version 36931 (0.0009) -[2023-10-09 09:46:11,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 75431936. Throughput: 0: 1754.6, 1: 1774.2. Samples: 18870226. Policy #0 lag: (min: 27.0, avg: 27.3, max: 38.0) -[2023-10-09 09:46:11,079][22500] Avg episode reward: [(0, '7.770'), (1, '7.350')] -[2023-10-09 09:46:11,179][23469] Updated weights for policy 1, policy_version 36941 (0.0009) -[2023-10-09 09:46:11,552][23469] Updated weights for policy 1, policy_version 36951 (0.0008) -[2023-10-09 09:46:11,899][23468] Updated weights for policy 0, policy_version 36743 (0.0008) -[2023-10-09 09:46:12,262][23468] Updated weights for policy 0, policy_version 36753 (0.0007) -[2023-10-09 09:46:12,644][23468] Updated weights for policy 0, policy_version 36763 (0.0009) -[2023-10-09 09:46:15,241][23469] Updated weights for policy 1, policy_version 36961 (0.0008) -[2023-10-09 09:46:15,615][23469] Updated weights for policy 1, policy_version 36971 (0.0008) -[2023-10-09 09:46:15,984][23469] Updated weights for policy 1, policy_version 36981 (0.0008) -[2023-10-09 09:46:16,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 75497472. Throughput: 0: 1766.9, 1: 1796.4. Samples: 18891832. Policy #0 lag: (min: 27.0, avg: 27.3, max: 38.0) -[2023-10-09 09:46:16,079][22500] Avg episode reward: [(0, '8.070'), (1, '6.970')] -[2023-10-09 09:46:16,087][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000036768_37650432.pth... -[2023-10-09 09:46:16,118][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000035168_36012032.pth -[2023-10-09 09:46:16,357][23469] Updated weights for policy 1, policy_version 36991 (0.0008) -[2023-10-09 09:46:16,393][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000036992_37879808.pth... -[2023-10-09 09:46:16,433][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000035360_36208640.pth -[2023-10-09 09:46:16,450][23468] Updated weights for policy 0, policy_version 36773 (0.0010) -[2023-10-09 09:46:16,824][23468] Updated weights for policy 0, policy_version 36783 (0.0009) -[2023-10-09 09:46:17,190][23468] Updated weights for policy 0, policy_version 36793 (0.0009) -[2023-10-09 09:46:20,118][23469] Updated weights for policy 1, policy_version 37001 (0.0008) -[2023-10-09 09:46:20,491][23469] Updated weights for policy 1, policy_version 37011 (0.0008) -[2023-10-09 09:46:20,862][23469] Updated weights for policy 1, policy_version 37021 (0.0009) -[2023-10-09 09:46:21,077][22500] Fps is (10 sec: 16384.5, 60 sec: 14745.6, 300 sec: 13884.8). Total num frames: 75595776. Throughput: 0: 1751.6, 1: 1787.3. Samples: 18902328. Policy #0 lag: (min: 27.0, avg: 27.3, max: 38.0) -[2023-10-09 09:46:21,078][22500] Avg episode reward: [(0, '7.650'), (1, '7.440')] -[2023-10-09 09:46:21,146][23468] Updated weights for policy 0, policy_version 36803 (0.0010) -[2023-10-09 09:46:21,531][23468] Updated weights for policy 0, policy_version 36813 (0.0010) -[2023-10-09 09:46:21,893][23468] Updated weights for policy 0, policy_version 36823 (0.0009) -[2023-10-09 09:46:24,479][23469] Updated weights for policy 1, policy_version 37031 (0.0010) -[2023-10-09 09:46:24,845][23469] Updated weights for policy 1, policy_version 37041 (0.0008) -[2023-10-09 09:46:25,216][23469] Updated weights for policy 1, policy_version 37051 (0.0008) -[2023-10-09 09:46:25,659][23468] Updated weights for policy 0, policy_version 36833 (0.0009) -[2023-10-09 09:46:26,021][23468] Updated weights for policy 0, policy_version 36843 (0.0010) -[2023-10-09 09:46:26,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 75661312. Throughput: 0: 1756.2, 1: 1806.3. Samples: 18923790. Policy #0 lag: (min: 27.0, avg: 27.3, max: 38.0) -[2023-10-09 09:46:26,078][22500] Avg episode reward: [(0, '8.100'), (1, '7.660')] -[2023-10-09 09:46:26,397][23468] Updated weights for policy 0, policy_version 36853 (0.0010) -[2023-10-09 09:46:26,766][23468] Updated weights for policy 0, policy_version 36863 (0.0010) -[2023-10-09 09:46:28,940][23469] Updated weights for policy 1, policy_version 37061 (0.0008) -[2023-10-09 09:46:29,309][23469] Updated weights for policy 1, policy_version 37071 (0.0009) -[2023-10-09 09:46:29,686][23469] Updated weights for policy 1, policy_version 37081 (0.0009) -[2023-10-09 09:46:30,541][23468] Updated weights for policy 0, policy_version 36873 (0.0008) -[2023-10-09 09:46:30,912][23468] Updated weights for policy 0, policy_version 36883 (0.0007) -[2023-10-09 09:46:31,077][22500] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 75726848. Throughput: 0: 1779.3, 1: 1791.7. Samples: 18945448. Policy #0 lag: (min: 27.0, avg: 27.3, max: 38.0) -[2023-10-09 09:46:31,078][22500] Avg episode reward: [(0, '7.210'), (1, '7.760')] -[2023-10-09 09:46:31,294][23468] Updated weights for policy 0, policy_version 36893 (0.0009) -[2023-10-09 09:46:33,378][23469] Updated weights for policy 1, policy_version 37091 (0.0009) -[2023-10-09 09:46:33,749][23469] Updated weights for policy 1, policy_version 37101 (0.0008) -[2023-10-09 09:46:34,112][23469] Updated weights for policy 1, policy_version 37111 (0.0009) -[2023-10-09 09:46:35,136][23468] Updated weights for policy 0, policy_version 36903 (0.0009) -[2023-10-09 09:46:35,517][23468] Updated weights for policy 0, policy_version 36913 (0.0008) -[2023-10-09 09:46:35,883][23468] Updated weights for policy 0, policy_version 36923 (0.0009) -[2023-10-09 09:46:36,078][22500] Fps is (10 sec: 16382.3, 60 sec: 14199.2, 300 sec: 13995.8). Total num frames: 75825152. Throughput: 0: 1756.3, 1: 1811.0. Samples: 18956170. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 09:46:36,080][22500] Avg episode reward: [(0, '7.050'), (1, '8.080')] -[2023-10-09 09:46:36,082][23343] Saving new best policy, reward=8.080! -[2023-10-09 09:46:37,898][23469] Updated weights for policy 1, policy_version 37121 (0.0007) -[2023-10-09 09:46:38,269][23469] Updated weights for policy 1, policy_version 37131 (0.0009) -[2023-10-09 09:46:38,640][23469] Updated weights for policy 1, policy_version 37141 (0.0010) -[2023-10-09 09:46:39,013][23469] Updated weights for policy 1, policy_version 37151 (0.0009) -[2023-10-09 09:46:39,390][23468] Updated weights for policy 0, policy_version 36933 (0.0007) -[2023-10-09 09:46:39,771][23468] Updated weights for policy 0, policy_version 36943 (0.0008) -[2023-10-09 09:46:40,138][23468] Updated weights for policy 0, policy_version 36953 (0.0007) -[2023-10-09 09:46:41,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 75890688. Throughput: 0: 1789.4, 1: 1796.3. Samples: 18977708. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 09:46:41,078][22500] Avg episode reward: [(0, '7.050'), (1, '7.340')] -[2023-10-09 09:46:42,814][23469] Updated weights for policy 1, policy_version 37161 (0.0009) -[2023-10-09 09:46:43,187][23469] Updated weights for policy 1, policy_version 37171 (0.0009) -[2023-10-09 09:46:43,568][23469] Updated weights for policy 1, policy_version 37181 (0.0009) -[2023-10-09 09:46:43,828][23468] Updated weights for policy 0, policy_version 36963 (0.0008) -[2023-10-09 09:46:44,205][23468] Updated weights for policy 0, policy_version 36973 (0.0009) -[2023-10-09 09:46:44,587][23468] Updated weights for policy 0, policy_version 36983 (0.0007) -[2023-10-09 09:46:46,078][22500] Fps is (10 sec: 13108.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 75956224. Throughput: 0: 1758.9, 1: 1796.9. Samples: 18998872. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 09:46:46,079][22500] Avg episode reward: [(0, '7.510'), (1, '7.300')] -[2023-10-09 09:46:47,282][23469] Updated weights for policy 1, policy_version 37191 (0.0008) -[2023-10-09 09:46:47,661][23469] Updated weights for policy 1, policy_version 37201 (0.0007) -[2023-10-09 09:46:48,035][23469] Updated weights for policy 1, policy_version 37211 (0.0008) -[2023-10-09 09:46:48,314][23468] Updated weights for policy 0, policy_version 36993 (0.0009) -[2023-10-09 09:46:48,684][23468] Updated weights for policy 0, policy_version 37003 (0.0007) -[2023-10-09 09:46:49,065][23468] Updated weights for policy 0, policy_version 37013 (0.0009) -[2023-10-09 09:46:49,438][23468] Updated weights for policy 0, policy_version 37023 (0.0008) -[2023-10-09 09:46:51,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 76021760. Throughput: 0: 1791.0, 1: 1795.4. Samples: 19009858. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 09:46:51,078][22500] Avg episode reward: [(0, '7.520'), (1, '6.450')] -[2023-10-09 09:46:51,572][23469] Updated weights for policy 1, policy_version 37221 (0.0008) -[2023-10-09 09:46:51,949][23469] Updated weights for policy 1, policy_version 37231 (0.0008) -[2023-10-09 09:46:52,323][23469] Updated weights for policy 1, policy_version 37241 (0.0011) -[2023-10-09 09:46:53,234][23468] Updated weights for policy 0, policy_version 37033 (0.0009) -[2023-10-09 09:46:53,605][23468] Updated weights for policy 0, policy_version 37043 (0.0007) -[2023-10-09 09:46:53,980][23468] Updated weights for policy 0, policy_version 37053 (0.0009) -[2023-10-09 09:46:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 76087296. Throughput: 0: 1768.3, 1: 1805.0. Samples: 19031022. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 09:46:56,078][22500] Avg episode reward: [(0, '7.230'), (1, '6.740')] -[2023-10-09 09:46:56,121][23469] Updated weights for policy 1, policy_version 37251 (0.0010) -[2023-10-09 09:46:56,491][23469] Updated weights for policy 1, policy_version 37261 (0.0007) -[2023-10-09 09:46:56,859][23469] Updated weights for policy 1, policy_version 37271 (0.0007) -[2023-10-09 09:46:57,703][23468] Updated weights for policy 0, policy_version 37063 (0.0008) -[2023-10-09 09:46:58,071][23468] Updated weights for policy 0, policy_version 37073 (0.0008) -[2023-10-09 09:46:58,444][23468] Updated weights for policy 0, policy_version 37083 (0.0010) -[2023-10-09 09:47:00,655][23469] Updated weights for policy 1, policy_version 37281 (0.0008) -[2023-10-09 09:47:01,031][23469] Updated weights for policy 1, policy_version 37291 (0.0009) -[2023-10-09 09:47:01,078][22500] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 76152832. Throughput: 0: 1773.6, 1: 1806.6. Samples: 19052938. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 09:47:01,079][22500] Avg episode reward: [(0, '7.030'), (1, '7.110')] -[2023-10-09 09:47:01,405][23469] Updated weights for policy 1, policy_version 37301 (0.0009) -[2023-10-09 09:47:01,777][23469] Updated weights for policy 1, policy_version 37311 (0.0009) -[2023-10-09 09:47:02,252][23468] Updated weights for policy 0, policy_version 37093 (0.0010) -[2023-10-09 09:47:02,619][23468] Updated weights for policy 0, policy_version 37103 (0.0010) -[2023-10-09 09:47:02,987][23468] Updated weights for policy 0, policy_version 37113 (0.0011) -[2023-10-09 09:47:05,383][23469] Updated weights for policy 1, policy_version 37321 (0.0009) -[2023-10-09 09:47:05,754][23469] Updated weights for policy 1, policy_version 37331 (0.0008) -[2023-10-09 09:47:06,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 76218368. Throughput: 0: 1773.9, 1: 1796.8. Samples: 19063012. Policy #0 lag: (min: 31.0, avg: 36.2, max: 63.0) -[2023-10-09 09:47:06,078][22500] Avg episode reward: [(0, '7.260'), (1, '7.250')] -[2023-10-09 09:47:06,122][23469] Updated weights for policy 1, policy_version 37341 (0.0010) -[2023-10-09 09:47:06,860][23468] Updated weights for policy 0, policy_version 37123 (0.0009) -[2023-10-09 09:47:07,247][23468] Updated weights for policy 0, policy_version 37133 (0.0010) -[2023-10-09 09:47:07,632][23468] Updated weights for policy 0, policy_version 37143 (0.0011) -[2023-10-09 09:47:09,990][23469] Updated weights for policy 1, policy_version 37351 (0.0009) -[2023-10-09 09:47:10,363][23469] Updated weights for policy 1, policy_version 37361 (0.0009) -[2023-10-09 09:47:10,745][23469] Updated weights for policy 1, policy_version 37371 (0.0009) -[2023-10-09 09:47:11,077][22500] Fps is (10 sec: 16384.6, 60 sec: 14745.7, 300 sec: 14106.9). Total num frames: 76316672. Throughput: 0: 1776.9, 1: 1808.1. Samples: 19085116. Policy #0 lag: (min: 31.0, avg: 36.2, max: 63.0) -[2023-10-09 09:47:11,078][22500] Avg episode reward: [(0, '7.400'), (1, '7.010')] -[2023-10-09 09:47:11,402][23468] Updated weights for policy 0, policy_version 37153 (0.0009) -[2023-10-09 09:47:11,784][23468] Updated weights for policy 0, policy_version 37163 (0.0008) -[2023-10-09 09:47:12,145][23468] Updated weights for policy 0, policy_version 37173 (0.0010) -[2023-10-09 09:47:12,528][23468] Updated weights for policy 0, policy_version 37183 (0.0011) -[2023-10-09 09:47:14,431][23469] Updated weights for policy 1, policy_version 37381 (0.0010) -[2023-10-09 09:47:14,804][23469] Updated weights for policy 1, policy_version 37391 (0.0009) -[2023-10-09 09:47:15,186][23469] Updated weights for policy 1, policy_version 37401 (0.0008) -[2023-10-09 09:47:16,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.7, 300 sec: 13995.8). Total num frames: 76382208. Throughput: 0: 1774.4, 1: 1793.2. Samples: 19105994. Policy #0 lag: (min: 31.0, avg: 36.2, max: 63.0) -[2023-10-09 09:47:16,078][22500] Avg episode reward: [(0, '7.710'), (1, '7.580')] -[2023-10-09 09:47:16,222][23468] Updated weights for policy 0, policy_version 37193 (0.0010) -[2023-10-09 09:47:16,597][23468] Updated weights for policy 0, policy_version 37203 (0.0010) -[2023-10-09 09:47:16,960][23468] Updated weights for policy 0, policy_version 37213 (0.0010) -[2023-10-09 09:47:18,972][23469] Updated weights for policy 1, policy_version 37411 (0.0009) -[2023-10-09 09:47:19,341][23469] Updated weights for policy 1, policy_version 37421 (0.0008) -[2023-10-09 09:47:19,713][23469] Updated weights for policy 1, policy_version 37431 (0.0008) -[2023-10-09 09:47:20,960][23468] Updated weights for policy 0, policy_version 37223 (0.0009) -[2023-10-09 09:47:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 76447744. Throughput: 0: 1772.2, 1: 1805.9. Samples: 19117178. Policy #0 lag: (min: 31.0, avg: 36.2, max: 63.0) -[2023-10-09 09:47:21,078][22500] Avg episode reward: [(0, '7.980'), (1, '7.570')] -[2023-10-09 09:47:21,344][23468] Updated weights for policy 0, policy_version 37233 (0.0008) -[2023-10-09 09:47:21,710][23468] Updated weights for policy 0, policy_version 37243 (0.0009) -[2023-10-09 09:47:23,348][23469] Updated weights for policy 1, policy_version 37441 (0.0007) -[2023-10-09 09:47:23,724][23469] Updated weights for policy 1, policy_version 37451 (0.0009) -[2023-10-09 09:47:24,093][23469] Updated weights for policy 1, policy_version 37461 (0.0008) -[2023-10-09 09:47:24,455][23469] Updated weights for policy 1, policy_version 37471 (0.0007) -[2023-10-09 09:47:25,416][23468] Updated weights for policy 0, policy_version 37253 (0.0009) -[2023-10-09 09:47:25,789][23468] Updated weights for policy 0, policy_version 37263 (0.0010) -[2023-10-09 09:47:26,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 76513280. Throughput: 0: 1765.2, 1: 1788.1. Samples: 19137610. Policy #0 lag: (min: 31.0, avg: 36.2, max: 63.0) -[2023-10-09 09:47:26,078][22500] Avg episode reward: [(0, '7.570'), (1, '7.800')] -[2023-10-09 09:47:26,158][23468] Updated weights for policy 0, policy_version 37273 (0.0010) -[2023-10-09 09:47:28,235][23469] Updated weights for policy 1, policy_version 37481 (0.0009) -[2023-10-09 09:47:28,602][23469] Updated weights for policy 1, policy_version 37491 (0.0010) -[2023-10-09 09:47:28,968][23469] Updated weights for policy 1, policy_version 37501 (0.0011) -[2023-10-09 09:47:29,890][23468] Updated weights for policy 0, policy_version 37283 (0.0009) -[2023-10-09 09:47:30,259][23468] Updated weights for policy 0, policy_version 37293 (0.0007) -[2023-10-09 09:47:30,633][23468] Updated weights for policy 0, policy_version 37303 (0.0007) -[2023-10-09 09:47:31,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 13995.8). Total num frames: 76611584. Throughput: 0: 1781.5, 1: 1795.7. Samples: 19159846. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-09 09:47:31,078][22500] Avg episode reward: [(0, '7.660'), (1, '7.450')] -[2023-10-09 09:47:32,835][23469] Updated weights for policy 1, policy_version 37511 (0.0010) -[2023-10-09 09:47:33,211][23469] Updated weights for policy 1, policy_version 37521 (0.0008) -[2023-10-09 09:47:33,579][23469] Updated weights for policy 1, policy_version 37531 (0.0007) -[2023-10-09 09:47:34,359][23468] Updated weights for policy 0, policy_version 37313 (0.0008) -[2023-10-09 09:47:34,739][23468] Updated weights for policy 0, policy_version 37323 (0.0008) -[2023-10-09 09:47:35,117][23468] Updated weights for policy 0, policy_version 37333 (0.0010) -[2023-10-09 09:47:35,503][23468] Updated weights for policy 0, policy_version 37343 (0.0008) -[2023-10-09 09:47:36,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.7, 300 sec: 13995.8). Total num frames: 76677120. Throughput: 0: 1759.1, 1: 1799.5. Samples: 19169996. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-09 09:47:36,078][22500] Avg episode reward: [(0, '7.710'), (1, '7.860')] -[2023-10-09 09:47:37,437][23469] Updated weights for policy 1, policy_version 37541 (0.0008) -[2023-10-09 09:47:37,798][23469] Updated weights for policy 1, policy_version 37551 (0.0009) -[2023-10-09 09:47:38,164][23469] Updated weights for policy 1, policy_version 37561 (0.0009) -[2023-10-09 09:47:39,303][23468] Updated weights for policy 0, policy_version 37353 (0.0008) -[2023-10-09 09:47:39,677][23468] Updated weights for policy 0, policy_version 37363 (0.0009) -[2023-10-09 09:47:40,047][23468] Updated weights for policy 0, policy_version 37373 (0.0009) -[2023-10-09 09:47:41,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 76742656. Throughput: 0: 1786.9, 1: 1789.6. Samples: 19191968. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-09 09:47:41,078][22500] Avg episode reward: [(0, '7.780'), (1, '7.670')] -[2023-10-09 09:47:41,822][23469] Updated weights for policy 1, policy_version 37571 (0.0009) -[2023-10-09 09:47:42,192][23469] Updated weights for policy 1, policy_version 37581 (0.0009) -[2023-10-09 09:47:42,573][23469] Updated weights for policy 1, policy_version 37591 (0.0010) -[2023-10-09 09:47:43,911][23468] Updated weights for policy 0, policy_version 37383 (0.0009) -[2023-10-09 09:47:44,284][23468] Updated weights for policy 0, policy_version 37393 (0.0010) -[2023-10-09 09:47:44,653][23468] Updated weights for policy 0, policy_version 37403 (0.0010) -[2023-10-09 09:47:46,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 76808192. Throughput: 0: 1759.7, 1: 1795.6. Samples: 19212926. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-09 09:47:46,078][22500] Avg episode reward: [(0, '7.880'), (1, '7.800')] -[2023-10-09 09:47:46,180][23469] Updated weights for policy 1, policy_version 37601 (0.0008) -[2023-10-09 09:47:46,552][23469] Updated weights for policy 1, policy_version 37611 (0.0008) -[2023-10-09 09:47:46,924][23469] Updated weights for policy 1, policy_version 37621 (0.0008) -[2023-10-09 09:47:47,292][23469] Updated weights for policy 1, policy_version 37631 (0.0007) -[2023-10-09 09:47:48,425][23468] Updated weights for policy 0, policy_version 37413 (0.0009) -[2023-10-09 09:47:48,805][23468] Updated weights for policy 0, policy_version 37423 (0.0009) -[2023-10-09 09:47:49,177][23468] Updated weights for policy 0, policy_version 37433 (0.0010) -[2023-10-09 09:47:50,990][23469] Updated weights for policy 1, policy_version 37641 (0.0009) -[2023-10-09 09:47:51,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 76873728. Throughput: 0: 1793.2, 1: 1786.3. Samples: 19224090. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-09 09:47:51,078][22500] Avg episode reward: [(0, '7.580'), (1, '7.660')] -[2023-10-09 09:47:51,371][23469] Updated weights for policy 1, policy_version 37651 (0.0009) -[2023-10-09 09:47:51,739][23469] Updated weights for policy 1, policy_version 37661 (0.0009) -[2023-10-09 09:47:52,996][23468] Updated weights for policy 0, policy_version 37443 (0.0010) -[2023-10-09 09:47:53,372][23468] Updated weights for policy 0, policy_version 37453 (0.0007) -[2023-10-09 09:47:53,747][23468] Updated weights for policy 0, policy_version 37463 (0.0007) -[2023-10-09 09:47:55,693][23469] Updated weights for policy 1, policy_version 37671 (0.0011) -[2023-10-09 09:47:56,067][23469] Updated weights for policy 1, policy_version 37681 (0.0010) -[2023-10-09 09:47:56,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 76939264. Throughput: 0: 1769.7, 1: 1788.7. Samples: 19245242. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-09 09:47:56,078][22500] Avg episode reward: [(0, '7.900'), (1, '7.410')] -[2023-10-09 09:47:56,427][23469] Updated weights for policy 1, policy_version 37691 (0.0009) -[2023-10-09 09:47:57,559][23468] Updated weights for policy 0, policy_version 37473 (0.0009) -[2023-10-09 09:47:57,939][23468] Updated weights for policy 0, policy_version 37483 (0.0008) -[2023-10-09 09:47:58,310][23468] Updated weights for policy 0, policy_version 37493 (0.0008) -[2023-10-09 09:47:58,689][23468] Updated weights for policy 0, policy_version 37503 (0.0008) -[2023-10-09 09:48:00,116][23469] Updated weights for policy 1, policy_version 37701 (0.0010) -[2023-10-09 09:48:00,490][23469] Updated weights for policy 1, policy_version 37711 (0.0010) -[2023-10-09 09:48:00,846][23469] Updated weights for policy 1, policy_version 37721 (0.0008) -[2023-10-09 09:48:01,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.6, 300 sec: 13995.8). Total num frames: 77004800. Throughput: 0: 1769.9, 1: 1796.9. Samples: 19266500. Policy #0 lag: (min: 8.0, avg: 35.5, max: 40.0) -[2023-10-09 09:48:01,078][22500] Avg episode reward: [(0, '7.960'), (1, '6.810')] -[2023-10-09 09:48:02,300][23468] Updated weights for policy 0, policy_version 37513 (0.0010) -[2023-10-09 09:48:02,677][23468] Updated weights for policy 0, policy_version 37523 (0.0009) -[2023-10-09 09:48:03,048][23468] Updated weights for policy 0, policy_version 37533 (0.0010) -[2023-10-09 09:48:04,890][23469] Updated weights for policy 1, policy_version 37731 (0.0008) -[2023-10-09 09:48:05,268][23469] Updated weights for policy 1, policy_version 37741 (0.0007) -[2023-10-09 09:48:05,632][23469] Updated weights for policy 1, policy_version 37751 (0.0007) -[2023-10-09 09:48:06,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14106.9). Total num frames: 77103104. Throughput: 0: 1770.7, 1: 1782.2. Samples: 19277060. Policy #0 lag: (min: 8.0, avg: 35.5, max: 40.0) -[2023-10-09 09:48:06,078][22500] Avg episode reward: [(0, '7.890'), (1, '7.140')] -[2023-10-09 09:48:07,004][23468] Updated weights for policy 0, policy_version 37543 (0.0010) -[2023-10-09 09:48:07,395][23468] Updated weights for policy 0, policy_version 37553 (0.0011) -[2023-10-09 09:48:07,768][23468] Updated weights for policy 0, policy_version 37563 (0.0010) -[2023-10-09 09:48:09,303][23469] Updated weights for policy 1, policy_version 37761 (0.0008) -[2023-10-09 09:48:09,680][23469] Updated weights for policy 1, policy_version 37771 (0.0011) -[2023-10-09 09:48:10,051][23469] Updated weights for policy 1, policy_version 37781 (0.0010) -[2023-10-09 09:48:10,420][23469] Updated weights for policy 1, policy_version 37791 (0.0009) -[2023-10-09 09:48:11,078][22500] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 77168640. Throughput: 0: 1774.2, 1: 1806.7. Samples: 19298752. Policy #0 lag: (min: 8.0, avg: 35.5, max: 40.0) -[2023-10-09 09:48:11,079][22500] Avg episode reward: [(0, '7.260'), (1, '7.010')] -[2023-10-09 09:48:11,660][23468] Updated weights for policy 0, policy_version 37573 (0.0010) -[2023-10-09 09:48:12,022][23468] Updated weights for policy 0, policy_version 37583 (0.0008) -[2023-10-09 09:48:12,402][23468] Updated weights for policy 0, policy_version 37593 (0.0010) -[2023-10-09 09:48:14,185][23469] Updated weights for policy 1, policy_version 37801 (0.0010) -[2023-10-09 09:48:14,559][23469] Updated weights for policy 1, policy_version 37811 (0.0009) -[2023-10-09 09:48:14,937][23469] Updated weights for policy 1, policy_version 37821 (0.0009) -[2023-10-09 09:48:16,055][23468] Updated weights for policy 0, policy_version 37603 (0.0008) -[2023-10-09 09:48:16,078][22500] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 77234176. Throughput: 0: 1787.8, 1: 1775.6. Samples: 19320196. Policy #0 lag: (min: 8.0, avg: 35.5, max: 40.0) -[2023-10-09 09:48:16,079][22500] Avg episode reward: [(0, '7.230'), (1, '7.240')] -[2023-10-09 09:48:16,090][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000037824_38731776.pth... -[2023-10-09 09:48:16,127][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000036160_37027840.pth -[2023-10-09 09:48:16,430][23468] Updated weights for policy 0, policy_version 37613 (0.0007) -[2023-10-09 09:48:16,805][23468] Updated weights for policy 0, policy_version 37623 (0.0011) -[2023-10-09 09:48:17,143][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000037632_38535168.pth... -[2023-10-09 09:48:17,181][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000035968_36831232.pth -[2023-10-09 09:48:18,714][23469] Updated weights for policy 1, policy_version 37831 (0.0009) -[2023-10-09 09:48:19,084][23469] Updated weights for policy 1, policy_version 37841 (0.0011) -[2023-10-09 09:48:19,468][23469] Updated weights for policy 1, policy_version 37851 (0.0010) -[2023-10-09 09:48:20,457][23468] Updated weights for policy 0, policy_version 37633 (0.0008) -[2023-10-09 09:48:20,837][23468] Updated weights for policy 0, policy_version 37643 (0.0009) -[2023-10-09 09:48:21,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 77299712. Throughput: 0: 1779.1, 1: 1801.4. Samples: 19331118. Policy #0 lag: (min: 8.0, avg: 35.5, max: 40.0) -[2023-10-09 09:48:21,078][22500] Avg episode reward: [(0, '7.480'), (1, '7.220')] -[2023-10-09 09:48:21,201][23468] Updated weights for policy 0, policy_version 37653 (0.0008) -[2023-10-09 09:48:21,580][23468] Updated weights for policy 0, policy_version 37663 (0.0010) -[2023-10-09 09:48:23,153][23469] Updated weights for policy 1, policy_version 37861 (0.0008) -[2023-10-09 09:48:23,522][23469] Updated weights for policy 1, policy_version 37871 (0.0007) -[2023-10-09 09:48:23,895][23469] Updated weights for policy 1, policy_version 37881 (0.0007) -[2023-10-09 09:48:25,143][23468] Updated weights for policy 0, policy_version 37673 (0.0008) -[2023-10-09 09:48:25,519][23468] Updated weights for policy 0, policy_version 37683 (0.0009) -[2023-10-09 09:48:25,888][23468] Updated weights for policy 0, policy_version 37693 (0.0009) -[2023-10-09 09:48:26,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 13995.8). Total num frames: 77398016. Throughput: 0: 1790.9, 1: 1780.6. Samples: 19352684. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:48:26,078][22500] Avg episode reward: [(0, '7.650'), (1, '7.470')] -[2023-10-09 09:48:27,672][23469] Updated weights for policy 1, policy_version 37891 (0.0010) -[2023-10-09 09:48:28,038][23469] Updated weights for policy 1, policy_version 37901 (0.0012) -[2023-10-09 09:48:28,414][23469] Updated weights for policy 1, policy_version 37911 (0.0011) -[2023-10-09 09:48:29,660][23468] Updated weights for policy 0, policy_version 37703 (0.0010) -[2023-10-09 09:48:30,045][23468] Updated weights for policy 0, policy_version 37713 (0.0009) -[2023-10-09 09:48:30,417][23468] Updated weights for policy 0, policy_version 37723 (0.0010) -[2023-10-09 09:48:31,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 77463552. Throughput: 0: 1799.1, 1: 1778.6. Samples: 19373922. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:48:31,078][22500] Avg episode reward: [(0, '7.790'), (1, '7.830')] -[2023-10-09 09:48:32,225][23469] Updated weights for policy 1, policy_version 37921 (0.0009) -[2023-10-09 09:48:32,587][23469] Updated weights for policy 1, policy_version 37931 (0.0007) -[2023-10-09 09:48:32,956][23469] Updated weights for policy 1, policy_version 37941 (0.0007) -[2023-10-09 09:48:33,323][23469] Updated weights for policy 1, policy_version 37951 (0.0009) -[2023-10-09 09:48:34,153][23468] Updated weights for policy 0, policy_version 37733 (0.0008) -[2023-10-09 09:48:34,528][23468] Updated weights for policy 0, policy_version 37743 (0.0010) -[2023-10-09 09:48:34,893][23468] Updated weights for policy 0, policy_version 37753 (0.0007) -[2023-10-09 09:48:36,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 77529088. Throughput: 0: 1791.0, 1: 1777.6. Samples: 19384676. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:48:36,078][22500] Avg episode reward: [(0, '7.550'), (1, '8.200')] -[2023-10-09 09:48:36,079][23343] Saving new best policy, reward=8.200! -[2023-10-09 09:48:37,032][23469] Updated weights for policy 1, policy_version 37961 (0.0011) -[2023-10-09 09:48:37,399][23469] Updated weights for policy 1, policy_version 37971 (0.0011) -[2023-10-09 09:48:37,768][23469] Updated weights for policy 1, policy_version 37981 (0.0010) -[2023-10-09 09:48:38,619][23468] Updated weights for policy 0, policy_version 37763 (0.0008) -[2023-10-09 09:48:38,990][23468] Updated weights for policy 0, policy_version 37773 (0.0009) -[2023-10-09 09:48:39,368][23468] Updated weights for policy 0, policy_version 37783 (0.0011) -[2023-10-09 09:48:41,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 77594624. Throughput: 0: 1798.1, 1: 1782.9. Samples: 19406390. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:48:41,078][22500] Avg episode reward: [(0, '7.320'), (1, '8.050')] -[2023-10-09 09:48:41,460][23469] Updated weights for policy 1, policy_version 37991 (0.0008) -[2023-10-09 09:48:41,829][23469] Updated weights for policy 1, policy_version 38001 (0.0008) -[2023-10-09 09:48:42,194][23469] Updated weights for policy 1, policy_version 38011 (0.0007) -[2023-10-09 09:48:43,186][23468] Updated weights for policy 0, policy_version 37793 (0.0008) -[2023-10-09 09:48:43,567][23468] Updated weights for policy 0, policy_version 37803 (0.0008) -[2023-10-09 09:48:43,933][23468] Updated weights for policy 0, policy_version 37813 (0.0008) -[2023-10-09 09:48:44,315][23468] Updated weights for policy 0, policy_version 37823 (0.0009) -[2023-10-09 09:48:45,968][23469] Updated weights for policy 1, policy_version 38021 (0.0007) -[2023-10-09 09:48:46,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 77660160. Throughput: 0: 1791.5, 1: 1808.8. Samples: 19428518. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:48:46,078][22500] Avg episode reward: [(0, '7.480'), (1, '7.700')] -[2023-10-09 09:48:46,339][23469] Updated weights for policy 1, policy_version 38031 (0.0010) -[2023-10-09 09:48:46,705][23469] Updated weights for policy 1, policy_version 38041 (0.0007) -[2023-10-09 09:48:48,104][23468] Updated weights for policy 0, policy_version 37833 (0.0010) -[2023-10-09 09:48:48,479][23468] Updated weights for policy 0, policy_version 37843 (0.0010) -[2023-10-09 09:48:48,847][23468] Updated weights for policy 0, policy_version 37853 (0.0009) -[2023-10-09 09:48:50,477][23469] Updated weights for policy 1, policy_version 38051 (0.0008) -[2023-10-09 09:48:50,847][23469] Updated weights for policy 1, policy_version 38061 (0.0010) -[2023-10-09 09:48:51,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 77725696. Throughput: 0: 1811.1, 1: 1788.4. Samples: 19439040. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:48:51,078][22500] Avg episode reward: [(0, '7.760'), (1, '7.650')] -[2023-10-09 09:48:51,209][23469] Updated weights for policy 1, policy_version 38071 (0.0008) -[2023-10-09 09:48:52,683][23468] Updated weights for policy 0, policy_version 37863 (0.0008) -[2023-10-09 09:48:53,056][23468] Updated weights for policy 0, policy_version 37873 (0.0007) -[2023-10-09 09:48:53,432][23468] Updated weights for policy 0, policy_version 37883 (0.0008) -[2023-10-09 09:48:54,966][23469] Updated weights for policy 1, policy_version 38081 (0.0007) -[2023-10-09 09:48:55,334][23469] Updated weights for policy 1, policy_version 38091 (0.0009) -[2023-10-09 09:48:55,696][23469] Updated weights for policy 1, policy_version 38101 (0.0011) -[2023-10-09 09:48:56,065][23469] Updated weights for policy 1, policy_version 38111 (0.0009) -[2023-10-09 09:48:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 77791232. Throughput: 0: 1791.4, 1: 1801.1. Samples: 19460416. Policy #0 lag: (min: 25.0, avg: 41.1, max: 57.0) -[2023-10-09 09:48:56,078][22500] Avg episode reward: [(0, '7.910'), (1, '7.720')] -[2023-10-09 09:48:57,229][23468] Updated weights for policy 0, policy_version 37893 (0.0007) -[2023-10-09 09:48:57,609][23468] Updated weights for policy 0, policy_version 37903 (0.0010) -[2023-10-09 09:48:57,988][23468] Updated weights for policy 0, policy_version 37913 (0.0010) -[2023-10-09 09:48:59,944][23469] Updated weights for policy 1, policy_version 38121 (0.0007) -[2023-10-09 09:49:00,306][23469] Updated weights for policy 1, policy_version 38131 (0.0009) -[2023-10-09 09:49:00,673][23469] Updated weights for policy 1, policy_version 38141 (0.0009) -[2023-10-09 09:49:01,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.5, 300 sec: 14106.9). Total num frames: 77889536. Throughput: 0: 1788.8, 1: 1787.2. Samples: 19481116. Policy #0 lag: (min: 25.0, avg: 41.1, max: 57.0) -[2023-10-09 09:49:01,079][22500] Avg episode reward: [(0, '7.810'), (1, '7.510')] -[2023-10-09 09:49:01,807][23468] Updated weights for policy 0, policy_version 37923 (0.0009) -[2023-10-09 09:49:02,172][23468] Updated weights for policy 0, policy_version 37933 (0.0007) -[2023-10-09 09:49:02,546][23468] Updated weights for policy 0, policy_version 37943 (0.0007) -[2023-10-09 09:49:04,584][23469] Updated weights for policy 1, policy_version 38151 (0.0009) -[2023-10-09 09:49:04,970][23469] Updated weights for policy 1, policy_version 38161 (0.0007) -[2023-10-09 09:49:05,343][23469] Updated weights for policy 1, policy_version 38171 (0.0009) -[2023-10-09 09:49:06,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 77955072. Throughput: 0: 1783.5, 1: 1789.1. Samples: 19491884. Policy #0 lag: (min: 25.0, avg: 41.1, max: 57.0) -[2023-10-09 09:49:06,078][22500] Avg episode reward: [(0, '7.860'), (1, '7.370')] -[2023-10-09 09:49:06,236][23468] Updated weights for policy 0, policy_version 37953 (0.0009) -[2023-10-09 09:49:06,606][23468] Updated weights for policy 0, policy_version 37963 (0.0008) -[2023-10-09 09:49:06,992][23468] Updated weights for policy 0, policy_version 37973 (0.0008) -[2023-10-09 09:49:07,369][23468] Updated weights for policy 0, policy_version 37983 (0.0009) -[2023-10-09 09:49:09,111][23469] Updated weights for policy 1, policy_version 38181 (0.0009) -[2023-10-09 09:49:09,485][23469] Updated weights for policy 1, policy_version 38191 (0.0007) -[2023-10-09 09:49:09,851][23469] Updated weights for policy 1, policy_version 38201 (0.0007) -[2023-10-09 09:49:11,058][23468] Updated weights for policy 0, policy_version 37993 (0.0009) -[2023-10-09 09:49:11,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 78020608. Throughput: 0: 1785.4, 1: 1782.7. Samples: 19513248. Policy #0 lag: (min: 25.0, avg: 41.1, max: 57.0) -[2023-10-09 09:49:11,078][22500] Avg episode reward: [(0, '8.290'), (1, '7.210')] -[2023-10-09 09:49:11,435][23468] Updated weights for policy 0, policy_version 38003 (0.0007) -[2023-10-09 09:49:11,802][23468] Updated weights for policy 0, policy_version 38013 (0.0009) -[2023-10-09 09:49:13,617][23469] Updated weights for policy 1, policy_version 38211 (0.0007) -[2023-10-09 09:49:13,979][23469] Updated weights for policy 1, policy_version 38221 (0.0007) -[2023-10-09 09:49:14,350][23469] Updated weights for policy 1, policy_version 38231 (0.0007) -[2023-10-09 09:49:15,542][23468] Updated weights for policy 0, policy_version 38023 (0.0010) -[2023-10-09 09:49:15,912][23468] Updated weights for policy 0, policy_version 38033 (0.0009) -[2023-10-09 09:49:16,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 78086144. Throughput: 0: 1808.0, 1: 1776.4. Samples: 19535222. Policy #0 lag: (min: 25.0, avg: 41.1, max: 57.0) -[2023-10-09 09:49:16,078][22500] Avg episode reward: [(0, '7.790'), (1, '6.590')] -[2023-10-09 09:49:16,283][23468] Updated weights for policy 0, policy_version 38043 (0.0007) -[2023-10-09 09:49:18,140][23469] Updated weights for policy 1, policy_version 38241 (0.0007) -[2023-10-09 09:49:18,510][23469] Updated weights for policy 1, policy_version 38251 (0.0007) -[2023-10-09 09:49:18,872][23469] Updated weights for policy 1, policy_version 38261 (0.0007) -[2023-10-09 09:49:19,245][23469] Updated weights for policy 1, policy_version 38271 (0.0007) -[2023-10-09 09:49:20,087][23468] Updated weights for policy 0, policy_version 38053 (0.0007) -[2023-10-09 09:49:20,454][23468] Updated weights for policy 0, policy_version 38063 (0.0009) -[2023-10-09 09:49:20,833][23468] Updated weights for policy 0, policy_version 38073 (0.0007) -[2023-10-09 09:49:21,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 78151680. Throughput: 0: 1785.1, 1: 1793.8. Samples: 19545728. Policy #0 lag: (min: 25.0, avg: 41.1, max: 57.0) -[2023-10-09 09:49:21,078][22500] Avg episode reward: [(0, '7.870'), (1, '6.960')] -[2023-10-09 09:49:22,919][23469] Updated weights for policy 1, policy_version 38281 (0.0008) -[2023-10-09 09:49:23,275][23469] Updated weights for policy 1, policy_version 38291 (0.0007) -[2023-10-09 09:49:23,650][23469] Updated weights for policy 1, policy_version 38301 (0.0009) -[2023-10-09 09:49:24,503][23468] Updated weights for policy 0, policy_version 38083 (0.0007) -[2023-10-09 09:49:24,878][23468] Updated weights for policy 0, policy_version 38093 (0.0008) -[2023-10-09 09:49:25,257][23468] Updated weights for policy 0, policy_version 38103 (0.0008) -[2023-10-09 09:49:26,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 78249984. Throughput: 0: 1808.4, 1: 1780.3. Samples: 19567882. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) -[2023-10-09 09:49:26,078][22500] Avg episode reward: [(0, '7.930'), (1, '7.030')] -[2023-10-09 09:49:27,398][23469] Updated weights for policy 1, policy_version 38311 (0.0008) -[2023-10-09 09:49:27,776][23469] Updated weights for policy 1, policy_version 38321 (0.0009) -[2023-10-09 09:49:28,140][23469] Updated weights for policy 1, policy_version 38331 (0.0009) -[2023-10-09 09:49:28,972][23468] Updated weights for policy 0, policy_version 38113 (0.0009) -[2023-10-09 09:49:29,348][23468] Updated weights for policy 0, policy_version 38123 (0.0007) -[2023-10-09 09:49:29,714][23468] Updated weights for policy 0, policy_version 38133 (0.0008) -[2023-10-09 09:49:30,085][23468] Updated weights for policy 0, policy_version 38143 (0.0007) -[2023-10-09 09:49:31,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 78315520. Throughput: 0: 1781.0, 1: 1778.8. Samples: 19588710. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) -[2023-10-09 09:49:31,078][22500] Avg episode reward: [(0, '8.440'), (1, '7.640')] -[2023-10-09 09:49:31,085][23265] Saving new best policy, reward=8.440! -[2023-10-09 09:49:31,948][23469] Updated weights for policy 1, policy_version 38341 (0.0011) -[2023-10-09 09:49:32,313][23469] Updated weights for policy 1, policy_version 38351 (0.0009) -[2023-10-09 09:49:32,682][23469] Updated weights for policy 1, policy_version 38361 (0.0007) -[2023-10-09 09:49:33,854][23468] Updated weights for policy 0, policy_version 38153 (0.0008) -[2023-10-09 09:49:34,227][23468] Updated weights for policy 0, policy_version 38163 (0.0007) -[2023-10-09 09:49:34,597][23468] Updated weights for policy 0, policy_version 38173 (0.0007) -[2023-10-09 09:49:36,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 78381056. Throughput: 0: 1794.8, 1: 1778.1. Samples: 19599820. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) -[2023-10-09 09:49:36,078][22500] Avg episode reward: [(0, '8.140'), (1, '7.980')] -[2023-10-09 09:49:36,440][23469] Updated weights for policy 1, policy_version 38371 (0.0008) -[2023-10-09 09:49:36,807][23469] Updated weights for policy 1, policy_version 38381 (0.0008) -[2023-10-09 09:49:37,177][23469] Updated weights for policy 1, policy_version 38391 (0.0009) -[2023-10-09 09:49:38,251][23468] Updated weights for policy 0, policy_version 38183 (0.0008) -[2023-10-09 09:49:38,623][23468] Updated weights for policy 0, policy_version 38193 (0.0008) -[2023-10-09 09:49:38,990][23468] Updated weights for policy 0, policy_version 38203 (0.0010) -[2023-10-09 09:49:40,986][23469] Updated weights for policy 1, policy_version 38401 (0.0008) -[2023-10-09 09:49:41,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 78446592. Throughput: 0: 1791.6, 1: 1777.2. Samples: 19621012. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) -[2023-10-09 09:49:41,079][22500] Avg episode reward: [(0, '8.020'), (1, '7.740')] -[2023-10-09 09:49:41,362][23469] Updated weights for policy 1, policy_version 38411 (0.0008) -[2023-10-09 09:49:41,724][23469] Updated weights for policy 1, policy_version 38421 (0.0008) -[2023-10-09 09:49:42,094][23469] Updated weights for policy 1, policy_version 38431 (0.0010) -[2023-10-09 09:49:42,844][23468] Updated weights for policy 0, policy_version 38213 (0.0010) -[2023-10-09 09:49:43,230][23468] Updated weights for policy 0, policy_version 38223 (0.0009) -[2023-10-09 09:49:43,597][23468] Updated weights for policy 0, policy_version 38233 (0.0007) -[2023-10-09 09:49:45,786][23469] Updated weights for policy 1, policy_version 38441 (0.0011) -[2023-10-09 09:49:46,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 78512128. Throughput: 0: 1792.2, 1: 1805.8. Samples: 19643028. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) -[2023-10-09 09:49:46,078][22500] Avg episode reward: [(0, '7.510'), (1, '7.590')] -[2023-10-09 09:49:46,160][23469] Updated weights for policy 1, policy_version 38451 (0.0009) -[2023-10-09 09:49:46,534][23469] Updated weights for policy 1, policy_version 38461 (0.0007) -[2023-10-09 09:49:47,297][23468] Updated weights for policy 0, policy_version 38243 (0.0007) -[2023-10-09 09:49:47,677][23468] Updated weights for policy 0, policy_version 38253 (0.0008) -[2023-10-09 09:49:48,053][23468] Updated weights for policy 0, policy_version 38263 (0.0010) -[2023-10-09 09:49:50,298][23469] Updated weights for policy 1, policy_version 38471 (0.0008) -[2023-10-09 09:49:50,679][23469] Updated weights for policy 1, policy_version 38481 (0.0007) -[2023-10-09 09:49:51,060][23469] Updated weights for policy 1, policy_version 38491 (0.0011) -[2023-10-09 09:49:51,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 78577664. Throughput: 0: 1799.1, 1: 1789.8. Samples: 19653386. Policy #0 lag: (min: 10.0, avg: 12.3, max: 42.0) -[2023-10-09 09:49:51,078][22500] Avg episode reward: [(0, '7.940'), (1, '7.340')] -[2023-10-09 09:49:51,877][23468] Updated weights for policy 0, policy_version 38273 (0.0008) -[2023-10-09 09:49:52,252][23468] Updated weights for policy 0, policy_version 38283 (0.0010) -[2023-10-09 09:49:52,623][23468] Updated weights for policy 0, policy_version 38293 (0.0008) -[2023-10-09 09:49:52,992][23468] Updated weights for policy 0, policy_version 38303 (0.0008) -[2023-10-09 09:49:54,622][23469] Updated weights for policy 1, policy_version 38501 (0.0008) -[2023-10-09 09:49:54,997][23469] Updated weights for policy 1, policy_version 38511 (0.0009) -[2023-10-09 09:49:55,359][23469] Updated weights for policy 1, policy_version 38521 (0.0008) -[2023-10-09 09:49:56,078][22500] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 78675968. Throughput: 0: 1781.5, 1: 1815.3. Samples: 19675104. Policy #0 lag: (min: 10.0, avg: 12.3, max: 42.0) -[2023-10-09 09:49:56,079][22500] Avg episode reward: [(0, '7.600'), (1, '7.140')] -[2023-10-09 09:49:56,816][23468] Updated weights for policy 0, policy_version 38313 (0.0010) -[2023-10-09 09:49:57,192][23468] Updated weights for policy 0, policy_version 38323 (0.0008) -[2023-10-09 09:49:57,559][23468] Updated weights for policy 0, policy_version 38333 (0.0007) -[2023-10-09 09:49:58,929][23469] Updated weights for policy 1, policy_version 38531 (0.0008) -[2023-10-09 09:49:59,302][23469] Updated weights for policy 1, policy_version 38541 (0.0009) -[2023-10-09 09:49:59,671][23469] Updated weights for policy 1, policy_version 38551 (0.0008) -[2023-10-09 09:50:01,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 78741504. Throughput: 0: 1779.5, 1: 1805.6. Samples: 19696548. Policy #0 lag: (min: 10.0, avg: 12.3, max: 42.0) -[2023-10-09 09:50:01,078][22500] Avg episode reward: [(0, '8.390'), (1, '7.440')] -[2023-10-09 09:50:01,415][23468] Updated weights for policy 0, policy_version 38343 (0.0008) -[2023-10-09 09:50:01,785][23468] Updated weights for policy 0, policy_version 38353 (0.0009) -[2023-10-09 09:50:02,160][23468] Updated weights for policy 0, policy_version 38363 (0.0009) -[2023-10-09 09:50:03,301][23469] Updated weights for policy 1, policy_version 38561 (0.0008) -[2023-10-09 09:50:03,672][23469] Updated weights for policy 1, policy_version 38571 (0.0009) -[2023-10-09 09:50:04,040][23469] Updated weights for policy 1, policy_version 38581 (0.0010) -[2023-10-09 09:50:04,405][23469] Updated weights for policy 1, policy_version 38591 (0.0010) -[2023-10-09 09:50:05,931][23468] Updated weights for policy 0, policy_version 38373 (0.0008) -[2023-10-09 09:50:06,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 78807040. Throughput: 0: 1777.5, 1: 1812.0. Samples: 19707252. Policy #0 lag: (min: 10.0, avg: 12.3, max: 42.0) -[2023-10-09 09:50:06,078][22500] Avg episode reward: [(0, '8.320'), (1, '7.350')] -[2023-10-09 09:50:06,299][23468] Updated weights for policy 0, policy_version 38383 (0.0008) -[2023-10-09 09:50:06,679][23468] Updated weights for policy 0, policy_version 38393 (0.0009) -[2023-10-09 09:50:08,212][23469] Updated weights for policy 1, policy_version 38601 (0.0007) -[2023-10-09 09:50:08,577][23469] Updated weights for policy 1, policy_version 38611 (0.0009) -[2023-10-09 09:50:08,955][23469] Updated weights for policy 1, policy_version 38621 (0.0009) -[2023-10-09 09:50:10,506][23468] Updated weights for policy 0, policy_version 38403 (0.0008) -[2023-10-09 09:50:10,885][23468] Updated weights for policy 0, policy_version 38413 (0.0009) -[2023-10-09 09:50:11,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 78872576. Throughput: 0: 1770.1, 1: 1800.9. Samples: 19728576. Policy #0 lag: (min: 10.0, avg: 12.3, max: 42.0) -[2023-10-09 09:50:11,078][22500] Avg episode reward: [(0, '7.980'), (1, '7.150')] -[2023-10-09 09:50:11,254][23468] Updated weights for policy 0, policy_version 38423 (0.0007) -[2023-10-09 09:50:12,761][23469] Updated weights for policy 1, policy_version 38631 (0.0008) -[2023-10-09 09:50:13,132][23469] Updated weights for policy 1, policy_version 38641 (0.0007) -[2023-10-09 09:50:13,494][23469] Updated weights for policy 1, policy_version 38651 (0.0009) -[2023-10-09 09:50:15,138][23468] Updated weights for policy 0, policy_version 38433 (0.0008) -[2023-10-09 09:50:15,506][23468] Updated weights for policy 0, policy_version 38443 (0.0009) -[2023-10-09 09:50:15,878][23468] Updated weights for policy 0, policy_version 38453 (0.0007) -[2023-10-09 09:50:16,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 78938112. Throughput: 0: 1800.7, 1: 1803.2. Samples: 19750888. Policy #0 lag: (min: 10.0, avg: 12.3, max: 42.0) -[2023-10-09 09:50:16,079][22500] Avg episode reward: [(0, '8.010'), (1, '6.660')] -[2023-10-09 09:50:16,088][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000038656_39583744.pth... -[2023-10-09 09:50:16,123][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000036992_37879808.pth -[2023-10-09 09:50:16,255][23468] Updated weights for policy 0, policy_version 38463 (0.0009) -[2023-10-09 09:50:16,292][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000038464_39387136.pth... -[2023-10-09 09:50:16,321][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000036768_37650432.pth -[2023-10-09 09:50:17,136][23469] Updated weights for policy 1, policy_version 38661 (0.0007) -[2023-10-09 09:50:17,506][23469] Updated weights for policy 1, policy_version 38671 (0.0007) -[2023-10-09 09:50:17,876][23469] Updated weights for policy 1, policy_version 38681 (0.0007) -[2023-10-09 09:50:19,978][23468] Updated weights for policy 0, policy_version 38473 (0.0007) -[2023-10-09 09:50:20,357][23468] Updated weights for policy 0, policy_version 38483 (0.0009) -[2023-10-09 09:50:20,729][23468] Updated weights for policy 0, policy_version 38493 (0.0008) -[2023-10-09 09:50:21,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 79036416. Throughput: 0: 1774.2, 1: 1807.8. Samples: 19761010. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:50:21,078][22500] Avg episode reward: [(0, '7.830'), (1, '6.820')] -[2023-10-09 09:50:21,643][23469] Updated weights for policy 1, policy_version 38691 (0.0009) -[2023-10-09 09:50:22,012][23469] Updated weights for policy 1, policy_version 38701 (0.0009) -[2023-10-09 09:50:22,377][23469] Updated weights for policy 1, policy_version 38711 (0.0009) -[2023-10-09 09:50:24,350][23468] Updated weights for policy 0, policy_version 38503 (0.0009) -[2023-10-09 09:50:24,721][23468] Updated weights for policy 0, policy_version 38513 (0.0010) -[2023-10-09 09:50:25,103][23468] Updated weights for policy 0, policy_version 38523 (0.0008) -[2023-10-09 09:50:26,007][23469] Updated weights for policy 1, policy_version 38721 (0.0008) -[2023-10-09 09:50:26,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 79101952. Throughput: 0: 1800.8, 1: 1807.8. Samples: 19783398. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:50:26,078][22500] Avg episode reward: [(0, '7.590'), (1, '7.050')] -[2023-10-09 09:50:26,372][23469] Updated weights for policy 1, policy_version 38731 (0.0008) -[2023-10-09 09:50:26,741][23469] Updated weights for policy 1, policy_version 38741 (0.0008) -[2023-10-09 09:50:27,122][23469] Updated weights for policy 1, policy_version 38751 (0.0011) -[2023-10-09 09:50:28,737][23468] Updated weights for policy 0, policy_version 38533 (0.0010) -[2023-10-09 09:50:29,125][23468] Updated weights for policy 0, policy_version 38543 (0.0009) -[2023-10-09 09:50:29,506][23468] Updated weights for policy 0, policy_version 38553 (0.0009) -[2023-10-09 09:50:31,011][23469] Updated weights for policy 1, policy_version 38761 (0.0010) -[2023-10-09 09:50:31,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 79167488. Throughput: 0: 1775.4, 1: 1810.9. Samples: 19804412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:50:31,078][22500] Avg episode reward: [(0, '7.860'), (1, '7.540')] -[2023-10-09 09:50:31,375][23469] Updated weights for policy 1, policy_version 38771 (0.0007) -[2023-10-09 09:50:31,743][23469] Updated weights for policy 1, policy_version 38781 (0.0009) -[2023-10-09 09:50:33,279][23468] Updated weights for policy 0, policy_version 38563 (0.0008) -[2023-10-09 09:50:33,654][23468] Updated weights for policy 0, policy_version 38573 (0.0010) -[2023-10-09 09:50:34,032][23468] Updated weights for policy 0, policy_version 38583 (0.0008) -[2023-10-09 09:50:35,595][23469] Updated weights for policy 1, policy_version 38791 (0.0010) -[2023-10-09 09:50:35,971][23469] Updated weights for policy 1, policy_version 38801 (0.0010) -[2023-10-09 09:50:36,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 79233024. Throughput: 0: 1796.1, 1: 1805.2. Samples: 19815444. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:50:36,078][22500] Avg episode reward: [(0, '7.760'), (1, '7.580')] -[2023-10-09 09:50:36,342][23469] Updated weights for policy 1, policy_version 38811 (0.0010) -[2023-10-09 09:50:37,693][23468] Updated weights for policy 0, policy_version 38593 (0.0009) -[2023-10-09 09:50:38,057][23468] Updated weights for policy 0, policy_version 38603 (0.0007) -[2023-10-09 09:50:38,430][23468] Updated weights for policy 0, policy_version 38613 (0.0009) -[2023-10-09 09:50:38,802][23468] Updated weights for policy 0, policy_version 38623 (0.0009) -[2023-10-09 09:50:39,895][23469] Updated weights for policy 1, policy_version 38821 (0.0009) -[2023-10-09 09:50:40,268][23469] Updated weights for policy 1, policy_version 38831 (0.0009) -[2023-10-09 09:50:40,643][23469] Updated weights for policy 1, policy_version 38841 (0.0010) -[2023-10-09 09:50:41,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 79331328. Throughput: 0: 1775.9, 1: 1807.3. Samples: 19836350. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:50:41,078][22500] Avg episode reward: [(0, '7.700'), (1, '7.460')] -[2023-10-09 09:50:42,686][23468] Updated weights for policy 0, policy_version 38633 (0.0008) -[2023-10-09 09:50:43,058][23468] Updated weights for policy 0, policy_version 38643 (0.0007) -[2023-10-09 09:50:43,430][23468] Updated weights for policy 0, policy_version 38653 (0.0008) -[2023-10-09 09:50:44,312][23469] Updated weights for policy 1, policy_version 38851 (0.0008) -[2023-10-09 09:50:44,687][23469] Updated weights for policy 1, policy_version 38861 (0.0007) -[2023-10-09 09:50:45,057][23469] Updated weights for policy 1, policy_version 38871 (0.0007) -[2023-10-09 09:50:46,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 79396864. Throughput: 0: 1777.9, 1: 1797.8. Samples: 19857454. Policy #0 lag: (min: 1.0, avg: 11.1, max: 33.0) -[2023-10-09 09:50:46,078][22500] Avg episode reward: [(0, '7.630'), (1, '7.230')] -[2023-10-09 09:50:47,087][23468] Updated weights for policy 0, policy_version 38663 (0.0009) -[2023-10-09 09:50:47,471][23468] Updated weights for policy 0, policy_version 38673 (0.0008) -[2023-10-09 09:50:47,839][23468] Updated weights for policy 0, policy_version 38683 (0.0008) -[2023-10-09 09:50:48,840][23469] Updated weights for policy 1, policy_version 38881 (0.0009) -[2023-10-09 09:50:49,202][23469] Updated weights for policy 1, policy_version 38891 (0.0008) -[2023-10-09 09:50:49,569][23469] Updated weights for policy 1, policy_version 38901 (0.0008) -[2023-10-09 09:50:49,944][23469] Updated weights for policy 1, policy_version 38911 (0.0007) -[2023-10-09 09:50:51,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 79462400. Throughput: 0: 1778.6, 1: 1810.8. Samples: 19868774. Policy #0 lag: (min: 1.0, avg: 11.1, max: 33.0) -[2023-10-09 09:50:51,079][22500] Avg episode reward: [(0, '7.820'), (1, '6.780')] -[2023-10-09 09:50:51,746][23468] Updated weights for policy 0, policy_version 38693 (0.0009) -[2023-10-09 09:50:52,129][23468] Updated weights for policy 0, policy_version 38703 (0.0009) -[2023-10-09 09:50:52,497][23468] Updated weights for policy 0, policy_version 38713 (0.0009) -[2023-10-09 09:50:53,646][23469] Updated weights for policy 1, policy_version 38921 (0.0010) -[2023-10-09 09:50:54,010][23469] Updated weights for policy 1, policy_version 38931 (0.0007) -[2023-10-09 09:50:54,383][23469] Updated weights for policy 1, policy_version 38941 (0.0007) -[2023-10-09 09:50:56,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 79527936. Throughput: 0: 1777.7, 1: 1798.1. Samples: 19889488. Policy #0 lag: (min: 1.0, avg: 11.1, max: 33.0) -[2023-10-09 09:50:56,078][22500] Avg episode reward: [(0, '7.420'), (1, '6.630')] -[2023-10-09 09:50:56,273][23468] Updated weights for policy 0, policy_version 38723 (0.0008) -[2023-10-09 09:50:56,652][23468] Updated weights for policy 0, policy_version 38733 (0.0008) -[2023-10-09 09:50:57,023][23468] Updated weights for policy 0, policy_version 38743 (0.0007) -[2023-10-09 09:50:58,176][23469] Updated weights for policy 1, policy_version 38951 (0.0010) -[2023-10-09 09:50:58,548][23469] Updated weights for policy 1, policy_version 38961 (0.0010) -[2023-10-09 09:50:58,916][23469] Updated weights for policy 1, policy_version 38971 (0.0008) -[2023-10-09 09:51:00,782][23468] Updated weights for policy 0, policy_version 38753 (0.0009) -[2023-10-09 09:51:01,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 79593472. Throughput: 0: 1783.2, 1: 1792.8. Samples: 19911806. Policy #0 lag: (min: 1.0, avg: 11.1, max: 33.0) -[2023-10-09 09:51:01,078][22500] Avg episode reward: [(0, '7.510'), (1, '7.010')] -[2023-10-09 09:51:01,139][23468] Updated weights for policy 0, policy_version 38763 (0.0010) -[2023-10-09 09:51:01,516][23468] Updated weights for policy 0, policy_version 38773 (0.0009) -[2023-10-09 09:51:01,893][23468] Updated weights for policy 0, policy_version 38783 (0.0008) -[2023-10-09 09:51:02,623][23469] Updated weights for policy 1, policy_version 38981 (0.0009) -[2023-10-09 09:51:02,991][23469] Updated weights for policy 1, policy_version 38991 (0.0007) -[2023-10-09 09:51:03,363][23469] Updated weights for policy 1, policy_version 39001 (0.0008) -[2023-10-09 09:51:05,737][23468] Updated weights for policy 0, policy_version 38793 (0.0009) -[2023-10-09 09:51:06,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 79659008. Throughput: 0: 1775.9, 1: 1790.1. Samples: 19921478. Policy #0 lag: (min: 1.0, avg: 11.1, max: 33.0) -[2023-10-09 09:51:06,078][22500] Avg episode reward: [(0, '8.050'), (1, '7.360')] -[2023-10-09 09:51:06,124][23468] Updated weights for policy 0, policy_version 38803 (0.0007) -[2023-10-09 09:51:06,492][23468] Updated weights for policy 0, policy_version 38813 (0.0009) -[2023-10-09 09:51:07,121][23469] Updated weights for policy 1, policy_version 39011 (0.0007) -[2023-10-09 09:51:07,487][23469] Updated weights for policy 1, policy_version 39021 (0.0007) -[2023-10-09 09:51:07,859][23469] Updated weights for policy 1, policy_version 39031 (0.0009) -[2023-10-09 09:51:10,212][23468] Updated weights for policy 0, policy_version 38823 (0.0009) -[2023-10-09 09:51:10,585][23468] Updated weights for policy 0, policy_version 38833 (0.0009) -[2023-10-09 09:51:10,961][23468] Updated weights for policy 0, policy_version 38843 (0.0010) -[2023-10-09 09:51:11,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 79724544. Throughput: 0: 1777.3, 1: 1795.4. Samples: 19944168. Policy #0 lag: (min: 1.0, avg: 11.1, max: 33.0) -[2023-10-09 09:51:11,079][22500] Avg episode reward: [(0, '7.680'), (1, '7.610')] -[2023-10-09 09:51:11,485][23469] Updated weights for policy 1, policy_version 39041 (0.0008) -[2023-10-09 09:51:11,852][23469] Updated weights for policy 1, policy_version 39051 (0.0008) -[2023-10-09 09:51:12,226][23469] Updated weights for policy 1, policy_version 39061 (0.0008) -[2023-10-09 09:51:12,587][23469] Updated weights for policy 1, policy_version 39071 (0.0008) -[2023-10-09 09:51:14,851][23468] Updated weights for policy 0, policy_version 38853 (0.0009) -[2023-10-09 09:51:15,232][23468] Updated weights for policy 0, policy_version 38863 (0.0007) -[2023-10-09 09:51:15,597][23468] Updated weights for policy 0, policy_version 38873 (0.0010) -[2023-10-09 09:51:16,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 79822848. Throughput: 0: 1782.4, 1: 1802.4. Samples: 19965726. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-09 09:51:16,078][22500] Avg episode reward: [(0, '7.030'), (1, '7.360')] -[2023-10-09 09:51:16,357][23469] Updated weights for policy 1, policy_version 39081 (0.0010) -[2023-10-09 09:51:16,723][23469] Updated weights for policy 1, policy_version 39091 (0.0007) -[2023-10-09 09:51:17,100][23469] Updated weights for policy 1, policy_version 39101 (0.0008) -[2023-10-09 09:51:19,393][23468] Updated weights for policy 0, policy_version 38883 (0.0008) -[2023-10-09 09:51:19,764][23468] Updated weights for policy 0, policy_version 38893 (0.0011) -[2023-10-09 09:51:20,141][23468] Updated weights for policy 0, policy_version 38903 (0.0010) -[2023-10-09 09:51:20,881][23469] Updated weights for policy 1, policy_version 39111 (0.0008) -[2023-10-09 09:51:21,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 79888384. Throughput: 0: 1776.2, 1: 1800.1. Samples: 19976380. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-09 09:51:21,078][22500] Avg episode reward: [(0, '6.960'), (1, '6.960')] -[2023-10-09 09:51:21,250][23469] Updated weights for policy 1, policy_version 39121 (0.0008) -[2023-10-09 09:51:21,617][23469] Updated weights for policy 1, policy_version 39131 (0.0010) -[2023-10-09 09:51:23,718][23468] Updated weights for policy 0, policy_version 38913 (0.0009) -[2023-10-09 09:51:24,093][23468] Updated weights for policy 0, policy_version 38923 (0.0009) -[2023-10-09 09:51:24,467][23468] Updated weights for policy 0, policy_version 38933 (0.0010) -[2023-10-09 09:51:24,843][23468] Updated weights for policy 0, policy_version 38943 (0.0008) -[2023-10-09 09:51:25,379][23469] Updated weights for policy 1, policy_version 39141 (0.0010) -[2023-10-09 09:51:25,746][23469] Updated weights for policy 1, policy_version 39151 (0.0007) -[2023-10-09 09:51:26,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 79953920. Throughput: 0: 1793.8, 1: 1804.6. Samples: 19998278. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-09 09:51:26,078][22500] Avg episode reward: [(0, '7.580'), (1, '7.480')] -[2023-10-09 09:51:26,119][23469] Updated weights for policy 1, policy_version 39161 (0.0008) -[2023-10-09 09:51:28,510][23468] Updated weights for policy 0, policy_version 38953 (0.0007) -[2023-10-09 09:51:28,883][23468] Updated weights for policy 0, policy_version 38963 (0.0009) -[2023-10-09 09:51:29,260][23468] Updated weights for policy 0, policy_version 38973 (0.0009) -[2023-10-09 09:51:29,835][23469] Updated weights for policy 1, policy_version 39171 (0.0007) -[2023-10-09 09:51:30,208][23469] Updated weights for policy 1, policy_version 39181 (0.0008) -[2023-10-09 09:51:30,570][23469] Updated weights for policy 1, policy_version 39191 (0.0009) -[2023-10-09 09:51:31,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 80052224. Throughput: 0: 1779.2, 1: 1808.0. Samples: 20018882. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-09 09:51:31,078][22500] Avg episode reward: [(0, '8.430'), (1, '7.250')] -[2023-10-09 09:51:33,090][23468] Updated weights for policy 0, policy_version 38983 (0.0009) -[2023-10-09 09:51:33,468][23468] Updated weights for policy 0, policy_version 38993 (0.0010) -[2023-10-09 09:51:33,839][23468] Updated weights for policy 0, policy_version 39003 (0.0007) -[2023-10-09 09:51:34,298][23469] Updated weights for policy 1, policy_version 39201 (0.0008) -[2023-10-09 09:51:34,670][23469] Updated weights for policy 1, policy_version 39211 (0.0008) -[2023-10-09 09:51:35,032][23469] Updated weights for policy 1, policy_version 39221 (0.0011) -[2023-10-09 09:51:35,406][23469] Updated weights for policy 1, policy_version 39231 (0.0008) -[2023-10-09 09:51:36,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 80117760. Throughput: 0: 1798.8, 1: 1801.9. Samples: 20030806. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-09 09:51:36,078][22500] Avg episode reward: [(0, '8.390'), (1, '7.130')] -[2023-10-09 09:51:37,700][23468] Updated weights for policy 0, policy_version 39013 (0.0008) -[2023-10-09 09:51:38,077][23468] Updated weights for policy 0, policy_version 39023 (0.0009) -[2023-10-09 09:51:38,444][23468] Updated weights for policy 0, policy_version 39033 (0.0009) -[2023-10-09 09:51:39,042][23469] Updated weights for policy 1, policy_version 39241 (0.0009) -[2023-10-09 09:51:39,415][23469] Updated weights for policy 1, policy_version 39251 (0.0008) -[2023-10-09 09:51:39,784][23469] Updated weights for policy 1, policy_version 39261 (0.0008) -[2023-10-09 09:51:41,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 80183296. Throughput: 0: 1780.0, 1: 1808.9. Samples: 20050988. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-09 09:51:41,078][22500] Avg episode reward: [(0, '8.040'), (1, '7.370')] -[2023-10-09 09:51:42,176][23468] Updated weights for policy 0, policy_version 39043 (0.0007) -[2023-10-09 09:51:42,549][23468] Updated weights for policy 0, policy_version 39053 (0.0007) -[2023-10-09 09:51:42,925][23468] Updated weights for policy 0, policy_version 39063 (0.0007) -[2023-10-09 09:51:43,664][23469] Updated weights for policy 1, policy_version 39271 (0.0008) -[2023-10-09 09:51:44,041][23469] Updated weights for policy 1, policy_version 39281 (0.0010) -[2023-10-09 09:51:44,407][23469] Updated weights for policy 1, policy_version 39291 (0.0008) -[2023-10-09 09:51:46,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 80248832. Throughput: 0: 1783.5, 1: 1802.7. Samples: 20073190. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-09 09:51:46,079][22500] Avg episode reward: [(0, '7.450'), (1, '8.000')] -[2023-10-09 09:51:46,652][23468] Updated weights for policy 0, policy_version 39073 (0.0007) -[2023-10-09 09:51:47,024][23468] Updated weights for policy 0, policy_version 39083 (0.0008) -[2023-10-09 09:51:47,399][23468] Updated weights for policy 0, policy_version 39093 (0.0008) -[2023-10-09 09:51:47,777][23468] Updated weights for policy 0, policy_version 39103 (0.0011) -[2023-10-09 09:51:48,167][23469] Updated weights for policy 1, policy_version 39301 (0.0007) -[2023-10-09 09:51:48,547][23469] Updated weights for policy 1, policy_version 39311 (0.0007) -[2023-10-09 09:51:48,914][23469] Updated weights for policy 1, policy_version 39321 (0.0007) -[2023-10-09 09:51:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 80314368. Throughput: 0: 1783.2, 1: 1815.4. Samples: 20083414. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-09 09:51:51,078][22500] Avg episode reward: [(0, '7.760'), (1, '7.840')] -[2023-10-09 09:51:51,639][23468] Updated weights for policy 0, policy_version 39113 (0.0008) -[2023-10-09 09:51:52,004][23468] Updated weights for policy 0, policy_version 39123 (0.0010) -[2023-10-09 09:51:52,385][23468] Updated weights for policy 0, policy_version 39133 (0.0008) -[2023-10-09 09:51:52,650][23469] Updated weights for policy 1, policy_version 39331 (0.0008) -[2023-10-09 09:51:53,022][23469] Updated weights for policy 1, policy_version 39341 (0.0008) -[2023-10-09 09:51:53,380][23469] Updated weights for policy 1, policy_version 39351 (0.0008) -[2023-10-09 09:51:56,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 80379904. Throughput: 0: 1778.2, 1: 1802.2. Samples: 20105288. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-09 09:51:56,078][22500] Avg episode reward: [(0, '7.850'), (1, '7.710')] -[2023-10-09 09:51:56,244][23468] Updated weights for policy 0, policy_version 39143 (0.0008) -[2023-10-09 09:51:56,622][23468] Updated weights for policy 0, policy_version 39153 (0.0007) -[2023-10-09 09:51:56,998][23468] Updated weights for policy 0, policy_version 39163 (0.0007) -[2023-10-09 09:51:57,153][23469] Updated weights for policy 1, policy_version 39361 (0.0008) -[2023-10-09 09:51:57,527][23469] Updated weights for policy 1, policy_version 39371 (0.0010) -[2023-10-09 09:51:57,895][23469] Updated weights for policy 1, policy_version 39381 (0.0010) -[2023-10-09 09:51:58,254][23469] Updated weights for policy 1, policy_version 39391 (0.0010) -[2023-10-09 09:52:00,965][23468] Updated weights for policy 0, policy_version 39173 (0.0007) -[2023-10-09 09:52:01,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 80445440. Throughput: 0: 1795.5, 1: 1796.8. Samples: 20127378. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-09 09:52:01,078][22500] Avg episode reward: [(0, '7.990'), (1, '7.510')] -[2023-10-09 09:52:01,357][23468] Updated weights for policy 0, policy_version 39183 (0.0007) -[2023-10-09 09:52:01,739][23468] Updated weights for policy 0, policy_version 39193 (0.0008) -[2023-10-09 09:52:01,994][23469] Updated weights for policy 1, policy_version 39401 (0.0009) -[2023-10-09 09:52:02,374][23469] Updated weights for policy 1, policy_version 39411 (0.0009) -[2023-10-09 09:52:02,740][23469] Updated weights for policy 1, policy_version 39421 (0.0008) -[2023-10-09 09:52:05,438][23468] Updated weights for policy 0, policy_version 39203 (0.0009) -[2023-10-09 09:52:05,810][23468] Updated weights for policy 0, policy_version 39213 (0.0007) -[2023-10-09 09:52:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 80510976. Throughput: 0: 1775.1, 1: 1796.3. Samples: 20137090. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-09 09:52:06,078][22500] Avg episode reward: [(0, '7.040'), (1, '7.520')] -[2023-10-09 09:52:06,187][23468] Updated weights for policy 0, policy_version 39223 (0.0010) -[2023-10-09 09:52:06,703][23469] Updated weights for policy 1, policy_version 39431 (0.0009) -[2023-10-09 09:52:07,090][23469] Updated weights for policy 1, policy_version 39441 (0.0009) -[2023-10-09 09:52:07,461][23469] Updated weights for policy 1, policy_version 39451 (0.0008) -[2023-10-09 09:52:09,803][23468] Updated weights for policy 0, policy_version 39233 (0.0010) -[2023-10-09 09:52:10,179][23468] Updated weights for policy 0, policy_version 39243 (0.0008) -[2023-10-09 09:52:10,565][23468] Updated weights for policy 0, policy_version 39253 (0.0009) -[2023-10-09 09:52:10,933][23468] Updated weights for policy 0, policy_version 39263 (0.0009) -[2023-10-09 09:52:11,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 80609280. Throughput: 0: 1793.8, 1: 1783.5. Samples: 20159254. Policy #0 lag: (min: 23.0, avg: 23.3, max: 34.0) -[2023-10-09 09:52:11,078][22500] Avg episode reward: [(0, '7.350'), (1, '7.540')] -[2023-10-09 09:52:11,205][23469] Updated weights for policy 1, policy_version 39461 (0.0007) -[2023-10-09 09:52:11,581][23469] Updated weights for policy 1, policy_version 39471 (0.0008) -[2023-10-09 09:52:11,946][23469] Updated weights for policy 1, policy_version 39481 (0.0011) -[2023-10-09 09:52:14,630][23468] Updated weights for policy 0, policy_version 39273 (0.0008) -[2023-10-09 09:52:14,995][23468] Updated weights for policy 0, policy_version 39283 (0.0007) -[2023-10-09 09:52:15,370][23468] Updated weights for policy 0, policy_version 39293 (0.0008) -[2023-10-09 09:52:15,605][23469] Updated weights for policy 1, policy_version 39491 (0.0009) -[2023-10-09 09:52:15,978][23469] Updated weights for policy 1, policy_version 39501 (0.0009) -[2023-10-09 09:52:16,078][22500] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 80674816. Throughput: 0: 1780.3, 1: 1806.7. Samples: 20180302. Policy #0 lag: (min: 23.0, avg: 23.3, max: 34.0) -[2023-10-09 09:52:16,079][22500] Avg episode reward: [(0, '7.490'), (1, '7.410')] -[2023-10-09 09:52:16,088][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000039296_40239104.pth... -[2023-10-09 09:52:16,122][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000037632_38535168.pth -[2023-10-09 09:52:16,335][23469] Updated weights for policy 1, policy_version 39511 (0.0008) -[2023-10-09 09:52:16,664][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000039520_40468480.pth... -[2023-10-09 09:52:16,693][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000037824_38731776.pth -[2023-10-09 09:52:19,256][23468] Updated weights for policy 0, policy_version 39303 (0.0007) -[2023-10-09 09:52:19,626][23468] Updated weights for policy 0, policy_version 39313 (0.0008) -[2023-10-09 09:52:19,896][23469] Updated weights for policy 1, policy_version 39521 (0.0010) -[2023-10-09 09:52:20,005][23468] Updated weights for policy 0, policy_version 39323 (0.0007) -[2023-10-09 09:52:20,278][23469] Updated weights for policy 1, policy_version 39531 (0.0010) -[2023-10-09 09:52:20,644][23469] Updated weights for policy 1, policy_version 39541 (0.0010) -[2023-10-09 09:52:21,010][23469] Updated weights for policy 1, policy_version 39551 (0.0010) -[2023-10-09 09:52:21,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 80773120. Throughput: 0: 1786.6, 1: 1785.1. Samples: 20191532. Policy #0 lag: (min: 23.0, avg: 23.3, max: 34.0) -[2023-10-09 09:52:21,078][22500] Avg episode reward: [(0, '7.340'), (1, '7.250')] -[2023-10-09 09:52:23,731][23468] Updated weights for policy 0, policy_version 39333 (0.0008) -[2023-10-09 09:52:24,097][23468] Updated weights for policy 0, policy_version 39343 (0.0007) -[2023-10-09 09:52:24,466][23468] Updated weights for policy 0, policy_version 39353 (0.0007) -[2023-10-09 09:52:24,873][23469] Updated weights for policy 1, policy_version 39561 (0.0008) -[2023-10-09 09:52:25,237][23469] Updated weights for policy 1, policy_version 39571 (0.0008) -[2023-10-09 09:52:25,606][23469] Updated weights for policy 1, policy_version 39581 (0.0009) -[2023-10-09 09:52:26,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 80838656. Throughput: 0: 1791.0, 1: 1805.0. Samples: 20212808. Policy #0 lag: (min: 23.0, avg: 23.3, max: 34.0) -[2023-10-09 09:52:26,078][22500] Avg episode reward: [(0, '7.670'), (1, '6.960')] -[2023-10-09 09:52:28,230][23468] Updated weights for policy 0, policy_version 39363 (0.0008) -[2023-10-09 09:52:28,604][23468] Updated weights for policy 0, policy_version 39373 (0.0007) -[2023-10-09 09:52:28,985][23468] Updated weights for policy 0, policy_version 39383 (0.0009) -[2023-10-09 09:52:29,258][23469] Updated weights for policy 1, policy_version 39591 (0.0008) -[2023-10-09 09:52:29,622][23469] Updated weights for policy 1, policy_version 39601 (0.0008) -[2023-10-09 09:52:29,998][23469] Updated weights for policy 1, policy_version 39611 (0.0010) -[2023-10-09 09:52:31,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 80904192. Throughput: 0: 1774.7, 1: 1780.8. Samples: 20233184. Policy #0 lag: (min: 23.0, avg: 23.3, max: 34.0) -[2023-10-09 09:52:31,078][22500] Avg episode reward: [(0, '7.970'), (1, '7.210')] -[2023-10-09 09:52:32,700][23468] Updated weights for policy 0, policy_version 39393 (0.0008) -[2023-10-09 09:52:33,076][23468] Updated weights for policy 0, policy_version 39403 (0.0008) -[2023-10-09 09:52:33,445][23468] Updated weights for policy 0, policy_version 39413 (0.0008) -[2023-10-09 09:52:33,815][23468] Updated weights for policy 0, policy_version 39423 (0.0007) -[2023-10-09 09:52:33,951][23469] Updated weights for policy 1, policy_version 39621 (0.0009) -[2023-10-09 09:52:34,322][23469] Updated weights for policy 1, policy_version 39631 (0.0011) -[2023-10-09 09:52:34,698][23469] Updated weights for policy 1, policy_version 39641 (0.0009) -[2023-10-09 09:52:36,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 80969728. Throughput: 0: 1793.6, 1: 1796.4. Samples: 20244964. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-09 09:52:36,078][22500] Avg episode reward: [(0, '8.330'), (1, '7.140')] -[2023-10-09 09:52:37,644][23468] Updated weights for policy 0, policy_version 39433 (0.0007) -[2023-10-09 09:52:38,006][23468] Updated weights for policy 0, policy_version 39443 (0.0009) -[2023-10-09 09:52:38,383][23468] Updated weights for policy 0, policy_version 39453 (0.0010) -[2023-10-09 09:52:38,546][23469] Updated weights for policy 1, policy_version 39651 (0.0007) -[2023-10-09 09:52:38,913][23469] Updated weights for policy 1, policy_version 39661 (0.0009) -[2023-10-09 09:52:39,293][23469] Updated weights for policy 1, policy_version 39671 (0.0009) -[2023-10-09 09:52:41,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 81035264. Throughput: 0: 1777.7, 1: 1768.9. Samples: 20264886. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-09 09:52:41,078][22500] Avg episode reward: [(0, '7.970'), (1, '7.480')] -[2023-10-09 09:52:42,094][23468] Updated weights for policy 0, policy_version 39463 (0.0009) -[2023-10-09 09:52:42,466][23468] Updated weights for policy 0, policy_version 39473 (0.0009) -[2023-10-09 09:52:42,846][23468] Updated weights for policy 0, policy_version 39483 (0.0007) -[2023-10-09 09:52:43,117][23469] Updated weights for policy 1, policy_version 39681 (0.0008) -[2023-10-09 09:52:43,490][23469] Updated weights for policy 1, policy_version 39691 (0.0007) -[2023-10-09 09:52:43,855][23469] Updated weights for policy 1, policy_version 39701 (0.0009) -[2023-10-09 09:52:44,226][23469] Updated weights for policy 1, policy_version 39711 (0.0007) -[2023-10-09 09:52:46,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 81100800. Throughput: 0: 1783.3, 1: 1773.2. Samples: 20287420. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-09 09:52:46,078][22500] Avg episode reward: [(0, '7.640'), (1, '7.290')] -[2023-10-09 09:52:46,692][23468] Updated weights for policy 0, policy_version 39493 (0.0008) -[2023-10-09 09:52:47,078][23468] Updated weights for policy 0, policy_version 39503 (0.0007) -[2023-10-09 09:52:47,445][23468] Updated weights for policy 0, policy_version 39513 (0.0007) -[2023-10-09 09:52:47,823][23469] Updated weights for policy 1, policy_version 39721 (0.0008) -[2023-10-09 09:52:48,192][23469] Updated weights for policy 1, policy_version 39731 (0.0008) -[2023-10-09 09:52:48,565][23469] Updated weights for policy 1, policy_version 39741 (0.0009) -[2023-10-09 09:52:51,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 81166336. Throughput: 0: 1782.2, 1: 1774.4. Samples: 20297138. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-09 09:52:51,078][22500] Avg episode reward: [(0, '8.120'), (1, '7.360')] -[2023-10-09 09:52:51,254][23468] Updated weights for policy 0, policy_version 39523 (0.0008) -[2023-10-09 09:52:51,620][23468] Updated weights for policy 0, policy_version 39533 (0.0009) -[2023-10-09 09:52:51,999][23468] Updated weights for policy 0, policy_version 39543 (0.0007) -[2023-10-09 09:52:52,279][23469] Updated weights for policy 1, policy_version 39751 (0.0007) -[2023-10-09 09:52:52,648][23469] Updated weights for policy 1, policy_version 39761 (0.0007) -[2023-10-09 09:52:53,028][23469] Updated weights for policy 1, policy_version 39771 (0.0007) -[2023-10-09 09:52:55,770][23468] Updated weights for policy 0, policy_version 39553 (0.0008) -[2023-10-09 09:52:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 81231872. Throughput: 0: 1772.3, 1: 1784.3. Samples: 20319298. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-09 09:52:56,078][22500] Avg episode reward: [(0, '8.320'), (1, '7.490')] -[2023-10-09 09:52:56,147][23468] Updated weights for policy 0, policy_version 39563 (0.0008) -[2023-10-09 09:52:56,527][23468] Updated weights for policy 0, policy_version 39573 (0.0010) -[2023-10-09 09:52:56,875][23469] Updated weights for policy 1, policy_version 39781 (0.0007) -[2023-10-09 09:52:56,895][23468] Updated weights for policy 0, policy_version 39583 (0.0009) -[2023-10-09 09:52:57,263][23469] Updated weights for policy 1, policy_version 39791 (0.0007) -[2023-10-09 09:52:57,643][23469] Updated weights for policy 1, policy_version 39801 (0.0009) -[2023-10-09 09:53:00,664][23468] Updated weights for policy 0, policy_version 39593 (0.0008) -[2023-10-09 09:53:01,028][23468] Updated weights for policy 0, policy_version 39603 (0.0011) -[2023-10-09 09:53:01,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 81297408. Throughput: 0: 1797.4, 1: 1779.5. Samples: 20341262. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-09 09:53:01,078][22500] Avg episode reward: [(0, '8.630'), (1, '8.350')] -[2023-10-09 09:53:01,085][23343] Saving new best policy, reward=8.350! -[2023-10-09 09:53:01,405][23468] Updated weights for policy 0, policy_version 39613 (0.0009) -[2023-10-09 09:53:01,491][23469] Updated weights for policy 1, policy_version 39811 (0.0008) -[2023-10-09 09:53:01,512][23265] Saving new best policy, reward=8.630! -[2023-10-09 09:53:01,858][23469] Updated weights for policy 1, policy_version 39821 (0.0008) -[2023-10-09 09:53:02,229][23469] Updated weights for policy 1, policy_version 39831 (0.0007) -[2023-10-09 09:53:05,290][23468] Updated weights for policy 0, policy_version 39623 (0.0008) -[2023-10-09 09:53:05,665][23468] Updated weights for policy 0, policy_version 39633 (0.0008) -[2023-10-09 09:53:06,026][23469] Updated weights for policy 1, policy_version 39841 (0.0007) -[2023-10-09 09:53:06,042][23468] Updated weights for policy 0, policy_version 39643 (0.0007) -[2023-10-09 09:53:06,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 81362944. Throughput: 0: 1774.1, 1: 1772.8. Samples: 20351144. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:53:06,078][22500] Avg episode reward: [(0, '8.180'), (1, '7.870')] -[2023-10-09 09:53:06,394][23469] Updated weights for policy 1, policy_version 39851 (0.0008) -[2023-10-09 09:53:06,756][23469] Updated weights for policy 1, policy_version 39861 (0.0010) -[2023-10-09 09:53:07,121][23469] Updated weights for policy 1, policy_version 39871 (0.0011) -[2023-10-09 09:53:11,077][22500] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 14218.0). Total num frames: 81428480. Throughput: 0: 1744.9, 1: 1731.1. Samples: 20369228. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:53:11,078][22500] Avg episode reward: [(0, '8.710'), (1, '8.310')] -[2023-10-09 09:53:11,080][23265] Saving new best policy, reward=8.710! -[2023-10-09 09:53:11,520][23468] Updated weights for policy 0, policy_version 39653 (0.0009) -[2023-10-09 09:53:11,895][23468] Updated weights for policy 0, policy_version 39663 (0.0012) -[2023-10-09 09:53:12,263][23468] Updated weights for policy 0, policy_version 39673 (0.0011) -[2023-10-09 09:53:12,836][23469] Updated weights for policy 1, policy_version 39881 (0.0011) -[2023-10-09 09:53:13,208][23469] Updated weights for policy 1, policy_version 39891 (0.0010) -[2023-10-09 09:53:13,576][23469] Updated weights for policy 1, policy_version 39901 (0.0011) -[2023-10-09 09:53:16,077][22500] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 14218.0). Total num frames: 81494016. Throughput: 0: 1666.3, 1: 1678.0. Samples: 20383676. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:53:16,078][22500] Avg episode reward: [(0, '8.570'), (1, '8.300')] -[2023-10-09 09:53:17,118][23468] Updated weights for policy 0, policy_version 39683 (0.0009) -[2023-10-09 09:53:17,485][23468] Updated weights for policy 0, policy_version 39693 (0.0007) -[2023-10-09 09:53:17,861][23468] Updated weights for policy 0, policy_version 39703 (0.0008) -[2023-10-09 09:53:18,014][23469] Updated weights for policy 1, policy_version 39911 (0.0010) -[2023-10-09 09:53:18,375][23469] Updated weights for policy 1, policy_version 39921 (0.0009) -[2023-10-09 09:53:18,744][23469] Updated weights for policy 1, policy_version 39931 (0.0008) -[2023-10-09 09:53:21,077][22500] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 14106.9). Total num frames: 81559552. Throughput: 0: 1648.0, 1: 1657.2. Samples: 20393696. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:53:21,079][22500] Avg episode reward: [(0, '8.640'), (1, '7.710')] -[2023-10-09 09:53:21,700][23468] Updated weights for policy 0, policy_version 39713 (0.0008) -[2023-10-09 09:53:22,074][23468] Updated weights for policy 0, policy_version 39723 (0.0009) -[2023-10-09 09:53:22,456][23468] Updated weights for policy 0, policy_version 39733 (0.0008) -[2023-10-09 09:53:22,642][23469] Updated weights for policy 1, policy_version 39941 (0.0008) -[2023-10-09 09:53:22,832][23468] Updated weights for policy 0, policy_version 39743 (0.0007) -[2023-10-09 09:53:23,010][23469] Updated weights for policy 1, policy_version 39951 (0.0007) -[2023-10-09 09:53:23,378][23469] Updated weights for policy 1, policy_version 39961 (0.0007) -[2023-10-09 09:53:26,077][22500] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 14106.9). Total num frames: 81625088. Throughput: 0: 1666.8, 1: 1682.1. Samples: 20415588. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:53:26,078][22500] Avg episode reward: [(0, '8.260'), (1, '7.040')] -[2023-10-09 09:53:26,680][23468] Updated weights for policy 0, policy_version 39753 (0.0007) -[2023-10-09 09:53:27,046][23468] Updated weights for policy 0, policy_version 39763 (0.0008) -[2023-10-09 09:53:27,242][23469] Updated weights for policy 1, policy_version 39971 (0.0007) -[2023-10-09 09:53:27,424][23468] Updated weights for policy 0, policy_version 39773 (0.0008) -[2023-10-09 09:53:27,603][23469] Updated weights for policy 1, policy_version 39981 (0.0008) -[2023-10-09 09:53:27,972][23469] Updated weights for policy 1, policy_version 39991 (0.0007) -[2023-10-09 09:53:31,067][23468] Updated weights for policy 0, policy_version 39783 (0.0008) -[2023-10-09 09:53:31,077][22500] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 14106.9). Total num frames: 81690624. Throughput: 0: 1669.5, 1: 1677.1. Samples: 20438016. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:53:31,078][22500] Avg episode reward: [(0, '7.930'), (1, '7.040')] -[2023-10-09 09:53:31,437][23468] Updated weights for policy 0, policy_version 39793 (0.0008) -[2023-10-09 09:53:31,807][23469] Updated weights for policy 1, policy_version 40001 (0.0009) -[2023-10-09 09:53:31,818][23468] Updated weights for policy 0, policy_version 39803 (0.0010) -[2023-10-09 09:53:32,169][23469] Updated weights for policy 1, policy_version 40011 (0.0007) -[2023-10-09 09:53:32,541][23469] Updated weights for policy 1, policy_version 40021 (0.0008) -[2023-10-09 09:53:32,908][23469] Updated weights for policy 1, policy_version 40031 (0.0008) -[2023-10-09 09:53:35,458][23468] Updated weights for policy 0, policy_version 39813 (0.0009) -[2023-10-09 09:53:35,835][23468] Updated weights for policy 0, policy_version 39823 (0.0009) -[2023-10-09 09:53:36,077][22500] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 14106.9). Total num frames: 81756160. Throughput: 0: 1673.8, 1: 1675.7. Samples: 20447866. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 09:53:36,078][22500] Avg episode reward: [(0, '8.090'), (1, '7.660')] -[2023-10-09 09:53:36,199][23468] Updated weights for policy 0, policy_version 39833 (0.0009) -[2023-10-09 09:53:36,565][23469] Updated weights for policy 1, policy_version 40041 (0.0007) -[2023-10-09 09:53:36,930][23469] Updated weights for policy 1, policy_version 40051 (0.0008) -[2023-10-09 09:53:37,307][23469] Updated weights for policy 1, policy_version 40061 (0.0010) -[2023-10-09 09:53:39,992][23468] Updated weights for policy 0, policy_version 39843 (0.0008) -[2023-10-09 09:53:40,368][23468] Updated weights for policy 0, policy_version 39853 (0.0009) -[2023-10-09 09:53:40,728][23468] Updated weights for policy 0, policy_version 39863 (0.0008) -[2023-10-09 09:53:41,077][22500] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 14218.0). Total num frames: 81854464. Throughput: 0: 1679.6, 1: 1675.3. Samples: 20470268. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 09:53:41,078][22500] Avg episode reward: [(0, '7.540'), (1, '7.710')] -[2023-10-09 09:53:41,165][23469] Updated weights for policy 1, policy_version 40071 (0.0009) -[2023-10-09 09:53:41,544][23469] Updated weights for policy 1, policy_version 40081 (0.0009) -[2023-10-09 09:53:41,909][23469] Updated weights for policy 1, policy_version 40091 (0.0007) -[2023-10-09 09:53:44,478][23468] Updated weights for policy 0, policy_version 39873 (0.0010) -[2023-10-09 09:53:44,851][23468] Updated weights for policy 0, policy_version 39883 (0.0010) -[2023-10-09 09:53:45,230][23468] Updated weights for policy 0, policy_version 39893 (0.0008) -[2023-10-09 09:53:45,564][23469] Updated weights for policy 1, policy_version 40101 (0.0008) -[2023-10-09 09:53:45,593][23468] Updated weights for policy 0, policy_version 39903 (0.0007) -[2023-10-09 09:53:45,928][23469] Updated weights for policy 1, policy_version 40111 (0.0007) -[2023-10-09 09:53:46,078][22500] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 14218.0). Total num frames: 81920000. Throughput: 0: 1660.5, 1: 1676.2. Samples: 20491414. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 09:53:46,078][22500] Avg episode reward: [(0, '7.600'), (1, '7.880')] -[2023-10-09 09:53:46,304][23469] Updated weights for policy 1, policy_version 40121 (0.0007) -[2023-10-09 09:53:49,365][23468] Updated weights for policy 0, policy_version 39913 (0.0007) -[2023-10-09 09:53:49,729][23468] Updated weights for policy 0, policy_version 39923 (0.0008) -[2023-10-09 09:53:50,053][23469] Updated weights for policy 1, policy_version 40131 (0.0007) -[2023-10-09 09:53:50,102][23468] Updated weights for policy 0, policy_version 39933 (0.0008) -[2023-10-09 09:53:50,432][23469] Updated weights for policy 1, policy_version 40141 (0.0009) -[2023-10-09 09:53:50,792][23469] Updated weights for policy 1, policy_version 40151 (0.0009) -[2023-10-09 09:53:51,077][22500] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 14218.0). Total num frames: 81985536. Throughput: 0: 1681.7, 1: 1682.4. Samples: 20502528. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 09:53:51,078][22500] Avg episode reward: [(0, '6.970'), (1, '6.620')] -[2023-10-09 09:53:55,033][23468] Updated weights for policy 0, policy_version 39943 (0.0010) -[2023-10-09 09:53:55,417][23468] Updated weights for policy 0, policy_version 39953 (0.0011) -[2023-10-09 09:53:55,804][23468] Updated weights for policy 0, policy_version 39963 (0.0011) -[2023-10-09 09:53:56,078][22500] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 82051072. Throughput: 0: 1682.6, 1: 1675.9. Samples: 20520362. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 09:53:56,079][22500] Avg episode reward: [(0, '7.630'), (1, '6.850')] -[2023-10-09 09:53:56,208][23469] Updated weights for policy 1, policy_version 40161 (0.0010) -[2023-10-09 09:53:56,576][23469] Updated weights for policy 1, policy_version 40171 (0.0007) -[2023-10-09 09:53:56,946][23469] Updated weights for policy 1, policy_version 40181 (0.0007) -[2023-10-09 09:53:57,319][23469] Updated weights for policy 1, policy_version 40191 (0.0007) -[2023-10-09 09:53:59,858][23468] Updated weights for policy 0, policy_version 39973 (0.0009) -[2023-10-09 09:54:00,226][23468] Updated weights for policy 0, policy_version 39983 (0.0009) -[2023-10-09 09:54:00,592][23468] Updated weights for policy 0, policy_version 39993 (0.0009) -[2023-10-09 09:54:01,077][22500] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 82116608. Throughput: 0: 1737.2, 1: 1734.7. Samples: 20539914. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-09 09:54:01,078][22500] Avg episode reward: [(0, '7.350'), (1, '6.530')] -[2023-10-09 09:54:01,177][23469] Updated weights for policy 1, policy_version 40201 (0.0007) -[2023-10-09 09:54:01,543][23469] Updated weights for policy 1, policy_version 40211 (0.0009) -[2023-10-09 09:54:01,908][23469] Updated weights for policy 1, policy_version 40221 (0.0008) -[2023-10-09 09:54:04,421][23468] Updated weights for policy 0, policy_version 40003 (0.0009) -[2023-10-09 09:54:04,789][23468] Updated weights for policy 0, policy_version 40013 (0.0007) -[2023-10-09 09:54:05,160][23468] Updated weights for policy 0, policy_version 40023 (0.0009) -[2023-10-09 09:54:05,532][23469] Updated weights for policy 1, policy_version 40231 (0.0008) -[2023-10-09 09:54:05,900][23469] Updated weights for policy 1, policy_version 40241 (0.0009) -[2023-10-09 09:54:06,077][22500] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 82182144. Throughput: 0: 1757.1, 1: 1727.4. Samples: 20550496. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-09 09:54:06,078][22500] Avg episode reward: [(0, '7.680'), (1, '6.990')] -[2023-10-09 09:54:06,277][23469] Updated weights for policy 1, policy_version 40251 (0.0012) -[2023-10-09 09:54:08,923][23468] Updated weights for policy 0, policy_version 40033 (0.0008) -[2023-10-09 09:54:09,292][23468] Updated weights for policy 0, policy_version 40043 (0.0007) -[2023-10-09 09:54:09,665][23468] Updated weights for policy 0, policy_version 40053 (0.0007) -[2023-10-09 09:54:10,054][23468] Updated weights for policy 0, policy_version 40063 (0.0008) -[2023-10-09 09:54:10,125][23469] Updated weights for policy 1, policy_version 40261 (0.0008) -[2023-10-09 09:54:10,493][23469] Updated weights for policy 1, policy_version 40271 (0.0009) -[2023-10-09 09:54:10,870][23469] Updated weights for policy 1, policy_version 40281 (0.0008) -[2023-10-09 09:54:11,078][22500] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 82247680. Throughput: 0: 1741.6, 1: 1737.7. Samples: 20572160. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-09 09:54:11,079][22500] Avg episode reward: [(0, '7.120'), (1, '6.520')] -[2023-10-09 09:54:13,772][23468] Updated weights for policy 0, policy_version 40073 (0.0007) -[2023-10-09 09:54:14,144][23468] Updated weights for policy 0, policy_version 40083 (0.0008) -[2023-10-09 09:54:14,520][23468] Updated weights for policy 0, policy_version 40093 (0.0007) -[2023-10-09 09:54:14,628][23469] Updated weights for policy 1, policy_version 40291 (0.0008) -[2023-10-09 09:54:15,001][23469] Updated weights for policy 1, policy_version 40301 (0.0009) -[2023-10-09 09:54:15,381][23469] Updated weights for policy 1, policy_version 40311 (0.0008) -[2023-10-09 09:54:16,078][22500] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 82345984. Throughput: 0: 1716.6, 1: 1711.7. Samples: 20592290. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-09 09:54:16,079][22500] Avg episode reward: [(0, '7.340'), (1, '7.070')] -[2023-10-09 09:54:16,089][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000040320_41287680.pth... -[2023-10-09 09:54:16,090][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000040096_41058304.pth... -[2023-10-09 09:54:16,118][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000038656_39583744.pth -[2023-10-09 09:54:16,121][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000038464_39387136.pth -[2023-10-09 09:54:18,354][23468] Updated weights for policy 0, policy_version 40103 (0.0008) -[2023-10-09 09:54:18,734][23468] Updated weights for policy 0, policy_version 40113 (0.0007) -[2023-10-09 09:54:19,115][23468] Updated weights for policy 0, policy_version 40123 (0.0009) -[2023-10-09 09:54:19,174][23469] Updated weights for policy 1, policy_version 40321 (0.0007) -[2023-10-09 09:54:19,546][23469] Updated weights for policy 1, policy_version 40331 (0.0010) -[2023-10-09 09:54:19,902][23469] Updated weights for policy 1, policy_version 40341 (0.0009) -[2023-10-09 09:54:20,271][23469] Updated weights for policy 1, policy_version 40351 (0.0007) -[2023-10-09 09:54:21,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 82411520. Throughput: 0: 1738.4, 1: 1740.6. Samples: 20604418. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-09 09:54:21,078][22500] Avg episode reward: [(0, '7.600'), (1, '7.300')] -[2023-10-09 09:54:23,058][23468] Updated weights for policy 0, policy_version 40133 (0.0008) -[2023-10-09 09:54:23,441][23468] Updated weights for policy 0, policy_version 40143 (0.0010) -[2023-10-09 09:54:23,813][23468] Updated weights for policy 0, policy_version 40153 (0.0011) -[2023-10-09 09:54:24,188][23469] Updated weights for policy 1, policy_version 40361 (0.0011) -[2023-10-09 09:54:24,560][23469] Updated weights for policy 1, policy_version 40371 (0.0010) -[2023-10-09 09:54:24,939][23469] Updated weights for policy 1, policy_version 40381 (0.0010) -[2023-10-09 09:54:26,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 82477056. Throughput: 0: 1700.5, 1: 1707.5. Samples: 20623626. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-09 09:54:26,078][22500] Avg episode reward: [(0, '8.150'), (1, '7.740')] -[2023-10-09 09:54:27,595][23468] Updated weights for policy 0, policy_version 40163 (0.0009) -[2023-10-09 09:54:27,971][23468] Updated weights for policy 0, policy_version 40173 (0.0011) -[2023-10-09 09:54:28,346][23468] Updated weights for policy 0, policy_version 40183 (0.0010) -[2023-10-09 09:54:28,828][23469] Updated weights for policy 1, policy_version 40391 (0.0010) -[2023-10-09 09:54:29,210][23469] Updated weights for policy 1, policy_version 40401 (0.0009) -[2023-10-09 09:54:29,584][23469] Updated weights for policy 1, policy_version 40411 (0.0010) -[2023-10-09 09:54:31,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 82542592. Throughput: 0: 1714.9, 1: 1697.9. Samples: 20644988. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:54:31,078][22500] Avg episode reward: [(0, '8.680'), (1, '7.790')] -[2023-10-09 09:54:32,266][23468] Updated weights for policy 0, policy_version 40193 (0.0008) -[2023-10-09 09:54:32,648][23468] Updated weights for policy 0, policy_version 40203 (0.0008) -[2023-10-09 09:54:33,030][23468] Updated weights for policy 0, policy_version 40213 (0.0009) -[2023-10-09 09:54:33,367][23469] Updated weights for policy 1, policy_version 40421 (0.0008) -[2023-10-09 09:54:33,407][23468] Updated weights for policy 0, policy_version 40223 (0.0009) -[2023-10-09 09:54:33,736][23469] Updated weights for policy 1, policy_version 40431 (0.0009) -[2023-10-09 09:54:34,113][23469] Updated weights for policy 1, policy_version 40441 (0.0010) -[2023-10-09 09:54:36,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 82608128. Throughput: 0: 1691.7, 1: 1708.0. Samples: 20655512. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:54:36,079][22500] Avg episode reward: [(0, '8.090'), (1, '7.570')] -[2023-10-09 09:54:37,273][23468] Updated weights for policy 0, policy_version 40233 (0.0007) -[2023-10-09 09:54:37,642][23468] Updated weights for policy 0, policy_version 40243 (0.0007) -[2023-10-09 09:54:37,890][23469] Updated weights for policy 1, policy_version 40451 (0.0008) -[2023-10-09 09:54:38,023][23468] Updated weights for policy 0, policy_version 40253 (0.0007) -[2023-10-09 09:54:38,257][23469] Updated weights for policy 1, policy_version 40461 (0.0007) -[2023-10-09 09:54:38,625][23469] Updated weights for policy 1, policy_version 40471 (0.0008) -[2023-10-09 09:54:41,077][22500] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 82673664. Throughput: 0: 1726.7, 1: 1740.8. Samples: 20676402. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:54:41,078][22500] Avg episode reward: [(0, '8.390'), (1, '7.510')] -[2023-10-09 09:54:41,912][23468] Updated weights for policy 0, policy_version 40263 (0.0007) -[2023-10-09 09:54:42,290][23468] Updated weights for policy 0, policy_version 40273 (0.0009) -[2023-10-09 09:54:42,545][23469] Updated weights for policy 1, policy_version 40481 (0.0008) -[2023-10-09 09:54:42,655][23468] Updated weights for policy 0, policy_version 40283 (0.0008) -[2023-10-09 09:54:42,919][23469] Updated weights for policy 1, policy_version 40491 (0.0008) -[2023-10-09 09:54:43,276][23469] Updated weights for policy 1, policy_version 40501 (0.0010) -[2023-10-09 09:54:43,652][23469] Updated weights for policy 1, policy_version 40511 (0.0011) -[2023-10-09 09:54:46,077][22500] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 82739200. Throughput: 0: 1760.7, 1: 1760.9. Samples: 20698386. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:54:46,078][22500] Avg episode reward: [(0, '8.140'), (1, '7.400')] -[2023-10-09 09:54:46,487][23468] Updated weights for policy 0, policy_version 40293 (0.0009) -[2023-10-09 09:54:46,847][23468] Updated weights for policy 0, policy_version 40303 (0.0009) -[2023-10-09 09:54:47,224][23468] Updated weights for policy 0, policy_version 40313 (0.0007) -[2023-10-09 09:54:47,593][23469] Updated weights for policy 1, policy_version 40521 (0.0007) -[2023-10-09 09:54:47,963][23469] Updated weights for policy 1, policy_version 40531 (0.0009) -[2023-10-09 09:54:48,330][23469] Updated weights for policy 1, policy_version 40541 (0.0007) -[2023-10-09 09:54:51,007][23468] Updated weights for policy 0, policy_version 40323 (0.0009) -[2023-10-09 09:54:51,077][22500] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13995.8). Total num frames: 82804736. Throughput: 0: 1737.7, 1: 1755.0. Samples: 20707668. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:54:51,078][22500] Avg episode reward: [(0, '8.150'), (1, '7.440')] -[2023-10-09 09:54:51,371][23468] Updated weights for policy 0, policy_version 40333 (0.0009) -[2023-10-09 09:54:51,743][23468] Updated weights for policy 0, policy_version 40343 (0.0009) -[2023-10-09 09:54:51,963][23469] Updated weights for policy 1, policy_version 40551 (0.0008) -[2023-10-09 09:54:52,341][23469] Updated weights for policy 1, policy_version 40561 (0.0007) -[2023-10-09 09:54:52,720][23469] Updated weights for policy 1, policy_version 40571 (0.0008) -[2023-10-09 09:54:55,620][23468] Updated weights for policy 0, policy_version 40353 (0.0009) -[2023-10-09 09:54:55,992][23468] Updated weights for policy 0, policy_version 40363 (0.0007) -[2023-10-09 09:54:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13995.8). Total num frames: 82870272. Throughput: 0: 1742.3, 1: 1754.4. Samples: 20729508. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:54:56,078][22500] Avg episode reward: [(0, '7.980'), (1, '7.770')] -[2023-10-09 09:54:56,371][23468] Updated weights for policy 0, policy_version 40373 (0.0009) -[2023-10-09 09:54:56,631][23469] Updated weights for policy 1, policy_version 40581 (0.0007) -[2023-10-09 09:54:56,733][23468] Updated weights for policy 0, policy_version 40383 (0.0008) -[2023-10-09 09:54:56,998][23469] Updated weights for policy 1, policy_version 40591 (0.0007) -[2023-10-09 09:54:57,370][23469] Updated weights for policy 1, policy_version 40601 (0.0007) -[2023-10-09 09:55:00,576][23468] Updated weights for policy 0, policy_version 40393 (0.0008) -[2023-10-09 09:55:00,958][23468] Updated weights for policy 0, policy_version 40403 (0.0010) -[2023-10-09 09:55:01,077][22500] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13995.8). Total num frames: 82935808. Throughput: 0: 1761.3, 1: 1779.4. Samples: 20751622. Policy #0 lag: (min: 11.0, avg: 11.1, max: 19.0) -[2023-10-09 09:55:01,078][22500] Avg episode reward: [(0, '7.990'), (1, '7.400')] -[2023-10-09 09:55:01,199][23469] Updated weights for policy 1, policy_version 40611 (0.0008) -[2023-10-09 09:55:01,317][23468] Updated weights for policy 0, policy_version 40413 (0.0008) -[2023-10-09 09:55:01,572][23469] Updated weights for policy 1, policy_version 40621 (0.0008) -[2023-10-09 09:55:01,942][23469] Updated weights for policy 1, policy_version 40631 (0.0009) -[2023-10-09 09:55:05,064][23468] Updated weights for policy 0, policy_version 40423 (0.0009) -[2023-10-09 09:55:05,444][23468] Updated weights for policy 0, policy_version 40433 (0.0009) -[2023-10-09 09:55:05,586][23469] Updated weights for policy 1, policy_version 40641 (0.0009) -[2023-10-09 09:55:05,808][23468] Updated weights for policy 0, policy_version 40443 (0.0009) -[2023-10-09 09:55:05,951][23469] Updated weights for policy 1, policy_version 40651 (0.0007) -[2023-10-09 09:55:06,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 83034112. Throughput: 0: 1739.7, 1: 1751.5. Samples: 20761522. Policy #0 lag: (min: 11.0, avg: 11.1, max: 19.0) -[2023-10-09 09:55:06,078][22500] Avg episode reward: [(0, '7.850'), (1, '7.410')] -[2023-10-09 09:55:06,319][23469] Updated weights for policy 1, policy_version 40661 (0.0007) -[2023-10-09 09:55:06,690][23469] Updated weights for policy 1, policy_version 40671 (0.0008) -[2023-10-09 09:55:09,652][23468] Updated weights for policy 0, policy_version 40453 (0.0008) -[2023-10-09 09:55:10,024][23468] Updated weights for policy 0, policy_version 40463 (0.0009) -[2023-10-09 09:55:10,394][23468] Updated weights for policy 0, policy_version 40473 (0.0008) -[2023-10-09 09:55:10,536][23469] Updated weights for policy 1, policy_version 40681 (0.0009) -[2023-10-09 09:55:10,902][23469] Updated weights for policy 1, policy_version 40691 (0.0010) -[2023-10-09 09:55:11,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14199.6, 300 sec: 14106.9). Total num frames: 83099648. Throughput: 0: 1773.5, 1: 1785.7. Samples: 20783788. Policy #0 lag: (min: 11.0, avg: 11.1, max: 19.0) -[2023-10-09 09:55:11,078][22500] Avg episode reward: [(0, '7.640'), (1, '6.960')] -[2023-10-09 09:55:11,269][23469] Updated weights for policy 1, policy_version 40701 (0.0010) -[2023-10-09 09:55:14,237][23468] Updated weights for policy 0, policy_version 40483 (0.0008) -[2023-10-09 09:55:14,610][23468] Updated weights for policy 0, policy_version 40493 (0.0007) -[2023-10-09 09:55:14,976][23468] Updated weights for policy 0, policy_version 40503 (0.0009) -[2023-10-09 09:55:15,000][23469] Updated weights for policy 1, policy_version 40711 (0.0009) -[2023-10-09 09:55:15,368][23469] Updated weights for policy 1, policy_version 40721 (0.0009) -[2023-10-09 09:55:15,732][23469] Updated weights for policy 1, policy_version 40731 (0.0009) -[2023-10-09 09:55:16,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 83197952. Throughput: 0: 1741.6, 1: 1774.0. Samples: 20803188. Policy #0 lag: (min: 11.0, avg: 11.1, max: 19.0) -[2023-10-09 09:55:16,078][22500] Avg episode reward: [(0, '6.860'), (1, '7.380')] -[2023-10-09 09:55:18,938][23468] Updated weights for policy 0, policy_version 40513 (0.0007) -[2023-10-09 09:55:19,319][23468] Updated weights for policy 0, policy_version 40523 (0.0008) -[2023-10-09 09:55:19,572][23469] Updated weights for policy 1, policy_version 40741 (0.0008) -[2023-10-09 09:55:19,684][23468] Updated weights for policy 0, policy_version 40533 (0.0008) -[2023-10-09 09:55:19,947][23469] Updated weights for policy 1, policy_version 40751 (0.0007) -[2023-10-09 09:55:20,059][23468] Updated weights for policy 0, policy_version 40543 (0.0008) -[2023-10-09 09:55:20,312][23469] Updated weights for policy 1, policy_version 40761 (0.0008) -[2023-10-09 09:55:21,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 83263488. Throughput: 0: 1763.6, 1: 1781.7. Samples: 20815054. Policy #0 lag: (min: 11.0, avg: 11.1, max: 19.0) -[2023-10-09 09:55:21,078][22500] Avg episode reward: [(0, '7.190'), (1, '7.870')] -[2023-10-09 09:55:23,866][23468] Updated weights for policy 0, policy_version 40553 (0.0008) -[2023-10-09 09:55:24,023][23469] Updated weights for policy 1, policy_version 40771 (0.0010) -[2023-10-09 09:55:24,238][23468] Updated weights for policy 0, policy_version 40563 (0.0010) -[2023-10-09 09:55:24,400][23469] Updated weights for policy 1, policy_version 40781 (0.0010) -[2023-10-09 09:55:24,612][23468] Updated weights for policy 0, policy_version 40573 (0.0009) -[2023-10-09 09:55:24,762][23469] Updated weights for policy 1, policy_version 40791 (0.0010) -[2023-10-09 09:55:26,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 83329024. Throughput: 0: 1751.5, 1: 1781.1. Samples: 20835370. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:55:26,078][22500] Avg episode reward: [(0, '7.650'), (1, '7.980')] -[2023-10-09 09:55:28,548][23468] Updated weights for policy 0, policy_version 40583 (0.0011) -[2023-10-09 09:55:28,611][23469] Updated weights for policy 1, policy_version 40801 (0.0009) -[2023-10-09 09:55:28,919][23468] Updated weights for policy 0, policy_version 40593 (0.0009) -[2023-10-09 09:55:28,976][23469] Updated weights for policy 1, policy_version 40811 (0.0007) -[2023-10-09 09:55:29,295][23468] Updated weights for policy 0, policy_version 40603 (0.0010) -[2023-10-09 09:55:29,348][23469] Updated weights for policy 1, policy_version 40821 (0.0007) -[2023-10-09 09:55:29,714][23469] Updated weights for policy 1, policy_version 40831 (0.0008) -[2023-10-09 09:55:31,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 83394560. Throughput: 0: 1734.6, 1: 1771.4. Samples: 20856156. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:55:31,079][22500] Avg episode reward: [(0, '8.110'), (1, '8.040')] -[2023-10-09 09:55:33,336][23468] Updated weights for policy 0, policy_version 40613 (0.0009) -[2023-10-09 09:55:33,441][23469] Updated weights for policy 1, policy_version 40841 (0.0007) -[2023-10-09 09:55:33,710][23468] Updated weights for policy 0, policy_version 40623 (0.0009) -[2023-10-09 09:55:33,810][23469] Updated weights for policy 1, policy_version 40851 (0.0007) -[2023-10-09 09:55:34,076][23468] Updated weights for policy 0, policy_version 40633 (0.0010) -[2023-10-09 09:55:34,182][23469] Updated weights for policy 1, policy_version 40861 (0.0007) -[2023-10-09 09:55:36,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 83460096. Throughput: 0: 1761.1, 1: 1798.0. Samples: 20867828. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:55:36,078][22500] Avg episode reward: [(0, '7.730'), (1, '7.930')] -[2023-10-09 09:55:37,820][23468] Updated weights for policy 0, policy_version 40643 (0.0007) -[2023-10-09 09:55:38,009][23469] Updated weights for policy 1, policy_version 40871 (0.0007) -[2023-10-09 09:55:38,185][23468] Updated weights for policy 0, policy_version 40653 (0.0008) -[2023-10-09 09:55:38,373][23469] Updated weights for policy 1, policy_version 40881 (0.0008) -[2023-10-09 09:55:38,556][23468] Updated weights for policy 0, policy_version 40663 (0.0008) -[2023-10-09 09:55:38,740][23469] Updated weights for policy 1, policy_version 40891 (0.0009) -[2023-10-09 09:55:41,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 83525632. Throughput: 0: 1738.0, 1: 1787.2. Samples: 20888140. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:55:41,078][22500] Avg episode reward: [(0, '7.280'), (1, '7.450')] -[2023-10-09 09:55:42,468][23469] Updated weights for policy 1, policy_version 40901 (0.0010) -[2023-10-09 09:55:42,491][23468] Updated weights for policy 0, policy_version 40673 (0.0008) -[2023-10-09 09:55:42,845][23469] Updated weights for policy 1, policy_version 40911 (0.0007) -[2023-10-09 09:55:42,855][23468] Updated weights for policy 0, policy_version 40683 (0.0008) -[2023-10-09 09:55:43,210][23469] Updated weights for policy 1, policy_version 40921 (0.0007) -[2023-10-09 09:55:43,227][23468] Updated weights for policy 0, policy_version 40693 (0.0009) -[2023-10-09 09:55:43,603][23468] Updated weights for policy 0, policy_version 40703 (0.0008) -[2023-10-09 09:55:46,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 83591168. Throughput: 0: 1736.1, 1: 1788.5. Samples: 20910230. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:55:46,078][22500] Avg episode reward: [(0, '7.880'), (1, '7.510')] -[2023-10-09 09:55:46,898][23469] Updated weights for policy 1, policy_version 40931 (0.0007) -[2023-10-09 09:55:47,270][23469] Updated weights for policy 1, policy_version 40941 (0.0007) -[2023-10-09 09:55:47,517][23468] Updated weights for policy 0, policy_version 40713 (0.0008) -[2023-10-09 09:55:47,635][23469] Updated weights for policy 1, policy_version 40951 (0.0007) -[2023-10-09 09:55:47,889][23468] Updated weights for policy 0, policy_version 40723 (0.0007) -[2023-10-09 09:55:48,270][23468] Updated weights for policy 0, policy_version 40733 (0.0008) -[2023-10-09 09:55:51,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 83656704. Throughput: 0: 1739.7, 1: 1788.4. Samples: 20920290. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:55:51,079][22500] Avg episode reward: [(0, '8.010'), (1, '7.630')] -[2023-10-09 09:55:51,458][23469] Updated weights for policy 1, policy_version 40961 (0.0007) -[2023-10-09 09:55:51,824][23469] Updated weights for policy 1, policy_version 40971 (0.0009) -[2023-10-09 09:55:51,993][23468] Updated weights for policy 0, policy_version 40743 (0.0008) -[2023-10-09 09:55:52,191][23469] Updated weights for policy 1, policy_version 40981 (0.0007) -[2023-10-09 09:55:52,360][23468] Updated weights for policy 0, policy_version 40753 (0.0011) -[2023-10-09 09:55:52,566][23469] Updated weights for policy 1, policy_version 40991 (0.0007) -[2023-10-09 09:55:52,745][23468] Updated weights for policy 0, policy_version 40763 (0.0007) -[2023-10-09 09:55:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 83722240. Throughput: 0: 1736.1, 1: 1786.1. Samples: 20942288. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:55:56,078][22500] Avg episode reward: [(0, '8.480'), (1, '7.770')] -[2023-10-09 09:55:56,620][23469] Updated weights for policy 1, policy_version 41001 (0.0008) -[2023-10-09 09:55:56,983][23469] Updated weights for policy 1, policy_version 41011 (0.0007) -[2023-10-09 09:55:57,054][23468] Updated weights for policy 0, policy_version 40773 (0.0007) -[2023-10-09 09:55:57,358][23469] Updated weights for policy 1, policy_version 41021 (0.0007) -[2023-10-09 09:55:57,441][23468] Updated weights for policy 0, policy_version 40783 (0.0008) -[2023-10-09 09:55:57,811][23468] Updated weights for policy 0, policy_version 40793 (0.0008) -[2023-10-09 09:56:01,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 83787776. Throughput: 0: 1756.7, 1: 1802.5. Samples: 20963350. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:56:01,078][22500] Avg episode reward: [(0, '7.580'), (1, '7.880')] -[2023-10-09 09:56:01,198][23469] Updated weights for policy 1, policy_version 41031 (0.0009) -[2023-10-09 09:56:01,478][23468] Updated weights for policy 0, policy_version 40803 (0.0010) -[2023-10-09 09:56:01,590][23469] Updated weights for policy 1, policy_version 41041 (0.0008) -[2023-10-09 09:56:01,843][23468] Updated weights for policy 0, policy_version 40813 (0.0009) -[2023-10-09 09:56:01,960][23469] Updated weights for policy 1, policy_version 41051 (0.0007) -[2023-10-09 09:56:02,222][23468] Updated weights for policy 0, policy_version 40823 (0.0008) -[2023-10-09 09:56:05,662][23469] Updated weights for policy 1, policy_version 41061 (0.0008) -[2023-10-09 09:56:05,920][23468] Updated weights for policy 0, policy_version 40833 (0.0008) -[2023-10-09 09:56:06,033][23469] Updated weights for policy 1, policy_version 41071 (0.0007) -[2023-10-09 09:56:06,077][22500] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 83853312. Throughput: 0: 1733.5, 1: 1775.0. Samples: 20972936. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:56:06,078][22500] Avg episode reward: [(0, '7.730'), (1, '7.390')] -[2023-10-09 09:56:06,296][23468] Updated weights for policy 0, policy_version 40843 (0.0007) -[2023-10-09 09:56:06,401][23469] Updated weights for policy 1, policy_version 41081 (0.0008) -[2023-10-09 09:56:06,662][23468] Updated weights for policy 0, policy_version 40853 (0.0007) -[2023-10-09 09:56:07,036][23468] Updated weights for policy 0, policy_version 40863 (0.0007) -[2023-10-09 09:56:10,168][23469] Updated weights for policy 1, policy_version 41091 (0.0008) -[2023-10-09 09:56:10,544][23469] Updated weights for policy 1, policy_version 41101 (0.0007) -[2023-10-09 09:56:10,917][23469] Updated weights for policy 1, policy_version 41111 (0.0008) -[2023-10-09 09:56:10,941][23468] Updated weights for policy 0, policy_version 40873 (0.0008) -[2023-10-09 09:56:11,077][22500] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 83918848. Throughput: 0: 1756.9, 1: 1796.6. Samples: 20995280. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:56:11,078][22500] Avg episode reward: [(0, '7.600'), (1, '7.650')] -[2023-10-09 09:56:11,317][23468] Updated weights for policy 0, policy_version 40883 (0.0009) -[2023-10-09 09:56:11,686][23468] Updated weights for policy 0, policy_version 40893 (0.0007) -[2023-10-09 09:56:14,582][23469] Updated weights for policy 1, policy_version 41121 (0.0010) -[2023-10-09 09:56:14,959][23469] Updated weights for policy 1, policy_version 41131 (0.0007) -[2023-10-09 09:56:15,340][23469] Updated weights for policy 1, policy_version 41141 (0.0007) -[2023-10-09 09:56:15,435][23468] Updated weights for policy 0, policy_version 40903 (0.0008) -[2023-10-09 09:56:15,707][23469] Updated weights for policy 1, policy_version 41151 (0.0008) -[2023-10-09 09:56:15,807][23468] Updated weights for policy 0, policy_version 40913 (0.0010) -[2023-10-09 09:56:16,077][22500] Fps is (10 sec: 16384.3, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 84017152. Throughput: 0: 1770.8, 1: 1780.0. Samples: 21015940. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:56:16,078][22500] Avg episode reward: [(0, '7.840'), (1, '7.590')] -[2023-10-09 09:56:16,085][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000041152_42139648.pth... -[2023-10-09 09:56:16,120][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000039520_40468480.pth -[2023-10-09 09:56:16,124][23343] Saving a milestone ./train_atari/atari_berzerk_APPO/checkpoint_p1/milestones/checkpoint_000041152_42139648.pth -[2023-10-09 09:56:16,182][23468] Updated weights for policy 0, policy_version 40923 (0.0007) -[2023-10-09 09:56:16,366][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000040928_41910272.pth... -[2023-10-09 09:56:16,394][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000039296_40239104.pth -[2023-10-09 09:56:16,398][23265] Saving a milestone ./train_atari/atari_berzerk_APPO/checkpoint_p0/milestones/checkpoint_000040928_41910272.pth -[2023-10-09 09:56:19,507][23469] Updated weights for policy 1, policy_version 41161 (0.0009) -[2023-10-09 09:56:19,877][23469] Updated weights for policy 1, policy_version 41171 (0.0008) -[2023-10-09 09:56:19,922][23468] Updated weights for policy 0, policy_version 40933 (0.0007) -[2023-10-09 09:56:20,246][23469] Updated weights for policy 1, policy_version 41181 (0.0008) -[2023-10-09 09:56:20,297][23468] Updated weights for policy 0, policy_version 40943 (0.0008) -[2023-10-09 09:56:20,668][23468] Updated weights for policy 0, policy_version 40953 (0.0008) -[2023-10-09 09:56:21,077][22500] Fps is (10 sec: 19661.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 84115456. Throughput: 0: 1751.2, 1: 1790.4. Samples: 21027198. Policy #0 lag: (min: 18.0, avg: 25.5, max: 50.0) -[2023-10-09 09:56:21,078][22500] Avg episode reward: [(0, '7.900'), (1, '7.720')] -[2023-10-09 09:56:23,991][23469] Updated weights for policy 1, policy_version 41191 (0.0009) -[2023-10-09 09:56:24,361][23469] Updated weights for policy 1, policy_version 41201 (0.0008) -[2023-10-09 09:56:24,462][23468] Updated weights for policy 0, policy_version 40963 (0.0009) -[2023-10-09 09:56:24,727][23469] Updated weights for policy 1, policy_version 41211 (0.0008) -[2023-10-09 09:56:24,836][23468] Updated weights for policy 0, policy_version 40973 (0.0007) -[2023-10-09 09:56:25,210][23468] Updated weights for policy 0, policy_version 40983 (0.0007) -[2023-10-09 09:56:26,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 84180992. Throughput: 0: 1782.7, 1: 1774.7. Samples: 21048224. Policy #0 lag: (min: 18.0, avg: 25.5, max: 50.0) -[2023-10-09 09:56:26,078][22500] Avg episode reward: [(0, '8.220'), (1, '7.740')] -[2023-10-09 09:56:28,576][23469] Updated weights for policy 1, policy_version 41221 (0.0008) -[2023-10-09 09:56:28,934][23469] Updated weights for policy 1, policy_version 41231 (0.0008) -[2023-10-09 09:56:28,934][23468] Updated weights for policy 0, policy_version 40993 (0.0008) -[2023-10-09 09:56:29,305][23468] Updated weights for policy 0, policy_version 41003 (0.0009) -[2023-10-09 09:56:29,309][23469] Updated weights for policy 1, policy_version 41241 (0.0008) -[2023-10-09 09:56:29,671][23468] Updated weights for policy 0, policy_version 41013 (0.0007) -[2023-10-09 09:56:30,039][23468] Updated weights for policy 0, policy_version 41023 (0.0007) -[2023-10-09 09:56:31,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 84246528. Throughput: 0: 1753.0, 1: 1766.4. Samples: 21068602. Policy #0 lag: (min: 18.0, avg: 25.5, max: 50.0) -[2023-10-09 09:56:31,078][22500] Avg episode reward: [(0, '7.820'), (1, '8.030')] -[2023-10-09 09:56:33,037][23469] Updated weights for policy 1, policy_version 41251 (0.0007) -[2023-10-09 09:56:33,410][23469] Updated weights for policy 1, policy_version 41261 (0.0008) -[2023-10-09 09:56:33,785][23469] Updated weights for policy 1, policy_version 41271 (0.0007) -[2023-10-09 09:56:33,880][23468] Updated weights for policy 0, policy_version 41033 (0.0007) -[2023-10-09 09:56:34,250][23468] Updated weights for policy 0, policy_version 41043 (0.0008) -[2023-10-09 09:56:34,635][23468] Updated weights for policy 0, policy_version 41053 (0.0008) -[2023-10-09 09:56:36,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 84312064. Throughput: 0: 1778.1, 1: 1778.4. Samples: 21080334. Policy #0 lag: (min: 18.0, avg: 25.5, max: 50.0) -[2023-10-09 09:56:36,078][22500] Avg episode reward: [(0, '8.040'), (1, '8.410')] -[2023-10-09 09:56:36,080][23343] Saving new best policy, reward=8.410! -[2023-10-09 09:56:37,525][23469] Updated weights for policy 1, policy_version 41281 (0.0008) -[2023-10-09 09:56:37,898][23469] Updated weights for policy 1, policy_version 41291 (0.0008) -[2023-10-09 09:56:38,264][23469] Updated weights for policy 1, policy_version 41301 (0.0007) -[2023-10-09 09:56:38,331][23468] Updated weights for policy 0, policy_version 41063 (0.0009) -[2023-10-09 09:56:38,632][23469] Updated weights for policy 1, policy_version 41311 (0.0007) -[2023-10-09 09:56:38,695][23468] Updated weights for policy 0, policy_version 41073 (0.0008) -[2023-10-09 09:56:39,061][23468] Updated weights for policy 0, policy_version 41083 (0.0009) -[2023-10-09 09:56:41,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 84377600. Throughput: 0: 1750.6, 1: 1773.3. Samples: 21100864. Policy #0 lag: (min: 18.0, avg: 25.5, max: 50.0) -[2023-10-09 09:56:41,079][22500] Avg episode reward: [(0, '7.720'), (1, '8.230')] -[2023-10-09 09:56:42,478][23469] Updated weights for policy 1, policy_version 41321 (0.0010) -[2023-10-09 09:56:42,855][23469] Updated weights for policy 1, policy_version 41331 (0.0008) -[2023-10-09 09:56:42,920][23468] Updated weights for policy 0, policy_version 41093 (0.0008) -[2023-10-09 09:56:43,223][23469] Updated weights for policy 1, policy_version 41341 (0.0009) -[2023-10-09 09:56:43,299][23468] Updated weights for policy 0, policy_version 41103 (0.0008) -[2023-10-09 09:56:43,674][23468] Updated weights for policy 0, policy_version 41113 (0.0009) -[2023-10-09 09:56:46,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 84443136. Throughput: 0: 1765.5, 1: 1780.9. Samples: 21122940. Policy #0 lag: (min: 18.0, avg: 25.5, max: 50.0) -[2023-10-09 09:56:46,079][22500] Avg episode reward: [(0, '7.730'), (1, '8.270')] -[2023-10-09 09:56:47,084][23469] Updated weights for policy 1, policy_version 41351 (0.0007) -[2023-10-09 09:56:47,415][23468] Updated weights for policy 0, policy_version 41123 (0.0008) -[2023-10-09 09:56:47,459][23469] Updated weights for policy 1, policy_version 41361 (0.0007) -[2023-10-09 09:56:47,784][23468] Updated weights for policy 0, policy_version 41133 (0.0009) -[2023-10-09 09:56:47,830][23469] Updated weights for policy 1, policy_version 41371 (0.0009) -[2023-10-09 09:56:48,161][23468] Updated weights for policy 0, policy_version 41143 (0.0009) -[2023-10-09 09:56:51,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 84508672. Throughput: 0: 1774.2, 1: 1779.4. Samples: 21132848. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:56:51,078][22500] Avg episode reward: [(0, '7.900'), (1, '7.840')] -[2023-10-09 09:56:51,623][23469] Updated weights for policy 1, policy_version 41381 (0.0008) -[2023-10-09 09:56:51,930][23468] Updated weights for policy 0, policy_version 41153 (0.0008) -[2023-10-09 09:56:51,994][23469] Updated weights for policy 1, policy_version 41391 (0.0009) -[2023-10-09 09:56:52,291][23468] Updated weights for policy 0, policy_version 41163 (0.0007) -[2023-10-09 09:56:52,363][23469] Updated weights for policy 1, policy_version 41401 (0.0007) -[2023-10-09 09:56:52,661][23468] Updated weights for policy 0, policy_version 41173 (0.0008) -[2023-10-09 09:56:53,031][23468] Updated weights for policy 0, policy_version 41183 (0.0010) -[2023-10-09 09:56:56,030][23469] Updated weights for policy 1, policy_version 41411 (0.0007) -[2023-10-09 09:56:56,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 84574208. Throughput: 0: 1767.7, 1: 1779.9. Samples: 21154922. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:56:56,078][22500] Avg episode reward: [(0, '8.020'), (1, '7.880')] -[2023-10-09 09:56:56,406][23469] Updated weights for policy 1, policy_version 41421 (0.0009) -[2023-10-09 09:56:56,765][23469] Updated weights for policy 1, policy_version 41431 (0.0009) -[2023-10-09 09:56:56,766][23468] Updated weights for policy 0, policy_version 41193 (0.0008) -[2023-10-09 09:56:57,128][23468] Updated weights for policy 0, policy_version 41203 (0.0007) -[2023-10-09 09:56:57,496][23468] Updated weights for policy 0, policy_version 41213 (0.0008) -[2023-10-09 09:57:00,596][23469] Updated weights for policy 1, policy_version 41441 (0.0008) -[2023-10-09 09:57:00,966][23469] Updated weights for policy 1, policy_version 41451 (0.0008) -[2023-10-09 09:57:01,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 84639744. Throughput: 0: 1780.0, 1: 1802.8. Samples: 21177166. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:57:01,078][22500] Avg episode reward: [(0, '8.090'), (1, '7.350')] -[2023-10-09 09:57:01,119][23468] Updated weights for policy 0, policy_version 41223 (0.0007) -[2023-10-09 09:57:01,346][23469] Updated weights for policy 1, policy_version 41461 (0.0008) -[2023-10-09 09:57:01,482][23468] Updated weights for policy 0, policy_version 41233 (0.0010) -[2023-10-09 09:57:01,713][23469] Updated weights for policy 1, policy_version 41471 (0.0008) -[2023-10-09 09:57:01,847][23468] Updated weights for policy 0, policy_version 41243 (0.0007) -[2023-10-09 09:57:05,437][23469] Updated weights for policy 1, policy_version 41481 (0.0008) -[2023-10-09 09:57:05,592][23468] Updated weights for policy 0, policy_version 41253 (0.0009) -[2023-10-09 09:57:05,806][23469] Updated weights for policy 1, policy_version 41491 (0.0007) -[2023-10-09 09:57:05,958][23468] Updated weights for policy 0, policy_version 41263 (0.0009) -[2023-10-09 09:57:06,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 84705280. Throughput: 0: 1777.3, 1: 1777.5. Samples: 21187168. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:57:06,078][22500] Avg episode reward: [(0, '8.070'), (1, '7.230')] -[2023-10-09 09:57:06,165][23469] Updated weights for policy 1, policy_version 41501 (0.0007) -[2023-10-09 09:57:06,330][23468] Updated weights for policy 0, policy_version 41273 (0.0008) -[2023-10-09 09:57:09,965][23469] Updated weights for policy 1, policy_version 41511 (0.0009) -[2023-10-09 09:57:10,198][23468] Updated weights for policy 0, policy_version 41283 (0.0008) -[2023-10-09 09:57:10,332][23469] Updated weights for policy 1, policy_version 41521 (0.0009) -[2023-10-09 09:57:10,568][23468] Updated weights for policy 0, policy_version 41293 (0.0010) -[2023-10-09 09:57:10,697][23469] Updated weights for policy 1, policy_version 41531 (0.0008) -[2023-10-09 09:57:10,954][23468] Updated weights for policy 0, policy_version 41303 (0.0008) -[2023-10-09 09:57:11,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 13995.8). Total num frames: 84803584. Throughput: 0: 1775.5, 1: 1800.4. Samples: 21209142. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:57:11,078][22500] Avg episode reward: [(0, '8.190'), (1, '7.280')] -[2023-10-09 09:57:14,653][23469] Updated weights for policy 1, policy_version 41541 (0.0008) -[2023-10-09 09:57:14,830][23468] Updated weights for policy 0, policy_version 41313 (0.0007) -[2023-10-09 09:57:15,025][23469] Updated weights for policy 1, policy_version 41551 (0.0007) -[2023-10-09 09:57:15,196][23468] Updated weights for policy 0, policy_version 41323 (0.0009) -[2023-10-09 09:57:15,390][23469] Updated weights for policy 1, policy_version 41561 (0.0008) -[2023-10-09 09:57:15,576][23468] Updated weights for policy 0, policy_version 41333 (0.0009) -[2023-10-09 09:57:15,937][23468] Updated weights for policy 0, policy_version 41343 (0.0008) -[2023-10-09 09:57:16,077][22500] Fps is (10 sec: 19661.2, 60 sec: 14745.6, 300 sec: 13995.8). Total num frames: 84901888. Throughput: 0: 1797.3, 1: 1774.3. Samples: 21229324. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-09 09:57:16,078][22500] Avg episode reward: [(0, '9.020'), (1, '7.030')] -[2023-10-09 09:57:16,085][23265] Saving new best policy, reward=9.020! -[2023-10-09 09:57:18,954][23469] Updated weights for policy 1, policy_version 41571 (0.0007) -[2023-10-09 09:57:19,319][23469] Updated weights for policy 1, policy_version 41581 (0.0007) -[2023-10-09 09:57:19,671][23468] Updated weights for policy 0, policy_version 41353 (0.0008) -[2023-10-09 09:57:19,690][23469] Updated weights for policy 1, policy_version 41591 (0.0008) -[2023-10-09 09:57:20,044][23468] Updated weights for policy 0, policy_version 41363 (0.0007) -[2023-10-09 09:57:20,419][23468] Updated weights for policy 0, policy_version 41373 (0.0011) -[2023-10-09 09:57:21,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 84967424. Throughput: 0: 1779.8, 1: 1801.9. Samples: 21241510. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-09 09:57:21,078][22500] Avg episode reward: [(0, '9.020'), (1, '7.560')] -[2023-10-09 09:57:23,462][23469] Updated weights for policy 1, policy_version 41601 (0.0007) -[2023-10-09 09:57:23,830][23469] Updated weights for policy 1, policy_version 41611 (0.0007) -[2023-10-09 09:57:24,203][23469] Updated weights for policy 1, policy_version 41621 (0.0007) -[2023-10-09 09:57:24,242][23468] Updated weights for policy 0, policy_version 41383 (0.0009) -[2023-10-09 09:57:24,573][23469] Updated weights for policy 1, policy_version 41631 (0.0009) -[2023-10-09 09:57:24,611][23468] Updated weights for policy 0, policy_version 41393 (0.0008) -[2023-10-09 09:57:24,978][23468] Updated weights for policy 0, policy_version 41403 (0.0008) -[2023-10-09 09:57:26,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 85032960. Throughput: 0: 1804.1, 1: 1777.1. Samples: 21262016. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-09 09:57:26,078][22500] Avg episode reward: [(0, '8.750'), (1, '6.950')] -[2023-10-09 09:57:28,194][23469] Updated weights for policy 1, policy_version 41641 (0.0008) -[2023-10-09 09:57:28,566][23469] Updated weights for policy 1, policy_version 41651 (0.0008) -[2023-10-09 09:57:28,846][23468] Updated weights for policy 0, policy_version 41413 (0.0010) -[2023-10-09 09:57:28,926][23469] Updated weights for policy 1, policy_version 41661 (0.0007) -[2023-10-09 09:57:29,226][23468] Updated weights for policy 0, policy_version 41423 (0.0010) -[2023-10-09 09:57:29,611][23468] Updated weights for policy 0, policy_version 41433 (0.0010) -[2023-10-09 09:57:31,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 85098496. Throughput: 0: 1781.9, 1: 1782.0. Samples: 21283316. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-09 09:57:31,079][22500] Avg episode reward: [(0, '8.490'), (1, '7.160')] -[2023-10-09 09:57:32,921][23469] Updated weights for policy 1, policy_version 41671 (0.0011) -[2023-10-09 09:57:33,318][23469] Updated weights for policy 1, policy_version 41681 (0.0009) -[2023-10-09 09:57:33,364][23468] Updated weights for policy 0, policy_version 41443 (0.0008) -[2023-10-09 09:57:33,683][23469] Updated weights for policy 1, policy_version 41691 (0.0010) -[2023-10-09 09:57:33,725][23468] Updated weights for policy 0, policy_version 41453 (0.0007) -[2023-10-09 09:57:34,104][23468] Updated weights for policy 0, policy_version 41463 (0.0008) -[2023-10-09 09:57:36,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 85164032. Throughput: 0: 1805.9, 1: 1781.1. Samples: 21294262. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-09 09:57:36,078][22500] Avg episode reward: [(0, '8.540'), (1, '7.410')] -[2023-10-09 09:57:37,484][23469] Updated weights for policy 1, policy_version 41701 (0.0008) -[2023-10-09 09:57:37,847][23469] Updated weights for policy 1, policy_version 41711 (0.0009) -[2023-10-09 09:57:37,908][23468] Updated weights for policy 0, policy_version 41473 (0.0010) -[2023-10-09 09:57:38,216][23469] Updated weights for policy 1, policy_version 41721 (0.0010) -[2023-10-09 09:57:38,277][23468] Updated weights for policy 0, policy_version 41483 (0.0007) -[2023-10-09 09:57:38,654][23468] Updated weights for policy 0, policy_version 41493 (0.0007) -[2023-10-09 09:57:39,028][23468] Updated weights for policy 0, policy_version 41503 (0.0007) -[2023-10-09 09:57:41,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 85229568. Throughput: 0: 1780.6, 1: 1774.4. Samples: 21314896. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-09 09:57:41,078][22500] Avg episode reward: [(0, '8.730'), (1, '7.640')] -[2023-10-09 09:57:41,997][23469] Updated weights for policy 1, policy_version 41731 (0.0008) -[2023-10-09 09:57:42,362][23469] Updated weights for policy 1, policy_version 41741 (0.0008) -[2023-10-09 09:57:42,674][23468] Updated weights for policy 0, policy_version 41513 (0.0009) -[2023-10-09 09:57:42,735][23469] Updated weights for policy 1, policy_version 41751 (0.0007) -[2023-10-09 09:57:43,052][23468] Updated weights for policy 0, policy_version 41523 (0.0007) -[2023-10-09 09:57:43,431][23468] Updated weights for policy 0, policy_version 41533 (0.0008) -[2023-10-09 09:57:46,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 85295104. Throughput: 0: 1773.7, 1: 1779.5. Samples: 21337058. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 09:57:46,079][22500] Avg episode reward: [(0, '8.640'), (1, '7.690')] -[2023-10-09 09:57:46,582][23469] Updated weights for policy 1, policy_version 41761 (0.0009) -[2023-10-09 09:57:46,956][23469] Updated weights for policy 1, policy_version 41771 (0.0011) -[2023-10-09 09:57:47,321][23469] Updated weights for policy 1, policy_version 41781 (0.0008) -[2023-10-09 09:57:47,357][23468] Updated weights for policy 0, policy_version 41543 (0.0009) -[2023-10-09 09:57:47,693][23469] Updated weights for policy 1, policy_version 41791 (0.0008) -[2023-10-09 09:57:47,723][23468] Updated weights for policy 0, policy_version 41553 (0.0008) -[2023-10-09 09:57:48,099][23468] Updated weights for policy 0, policy_version 41563 (0.0009) -[2023-10-09 09:57:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 85360640. Throughput: 0: 1772.9, 1: 1769.8. Samples: 21346590. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 09:57:51,078][22500] Avg episode reward: [(0, '7.970'), (1, '7.440')] -[2023-10-09 09:57:51,554][23469] Updated weights for policy 1, policy_version 41801 (0.0008) -[2023-10-09 09:57:51,920][23469] Updated weights for policy 1, policy_version 41811 (0.0009) -[2023-10-09 09:57:51,922][23468] Updated weights for policy 0, policy_version 41573 (0.0008) -[2023-10-09 09:57:52,288][23469] Updated weights for policy 1, policy_version 41821 (0.0008) -[2023-10-09 09:57:52,301][23468] Updated weights for policy 0, policy_version 41583 (0.0007) -[2023-10-09 09:57:52,681][23468] Updated weights for policy 0, policy_version 41593 (0.0007) -[2023-10-09 09:57:56,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.6, 300 sec: 13995.8). Total num frames: 85426176. Throughput: 0: 1777.7, 1: 1770.0. Samples: 21368788. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 09:57:56,078][22500] Avg episode reward: [(0, '8.510'), (1, '7.430')] -[2023-10-09 09:57:56,135][23469] Updated weights for policy 1, policy_version 41831 (0.0009) -[2023-10-09 09:57:56,265][23468] Updated weights for policy 0, policy_version 41603 (0.0007) -[2023-10-09 09:57:56,493][23469] Updated weights for policy 1, policy_version 41841 (0.0008) -[2023-10-09 09:57:56,646][23468] Updated weights for policy 0, policy_version 41613 (0.0008) -[2023-10-09 09:57:56,868][23469] Updated weights for policy 1, policy_version 41851 (0.0010) -[2023-10-09 09:57:57,016][23468] Updated weights for policy 0, policy_version 41623 (0.0009) -[2023-10-09 09:58:00,562][23469] Updated weights for policy 1, policy_version 41861 (0.0009) -[2023-10-09 09:58:00,934][23469] Updated weights for policy 1, policy_version 41871 (0.0010) -[2023-10-09 09:58:00,971][23468] Updated weights for policy 0, policy_version 41633 (0.0007) -[2023-10-09 09:58:01,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 85491712. Throughput: 0: 1787.4, 1: 1799.6. Samples: 21390738. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 09:58:01,078][22500] Avg episode reward: [(0, '8.160'), (1, '6.970')] -[2023-10-09 09:58:01,307][23469] Updated weights for policy 1, policy_version 41881 (0.0009) -[2023-10-09 09:58:01,352][23468] Updated weights for policy 0, policy_version 41643 (0.0009) -[2023-10-09 09:58:01,719][23468] Updated weights for policy 0, policy_version 41653 (0.0008) -[2023-10-09 09:58:02,091][23468] Updated weights for policy 0, policy_version 41663 (0.0009) -[2023-10-09 09:58:04,798][23469] Updated weights for policy 1, policy_version 41891 (0.0008) -[2023-10-09 09:58:05,170][23469] Updated weights for policy 1, policy_version 41901 (0.0007) -[2023-10-09 09:58:05,531][23469] Updated weights for policy 1, policy_version 41911 (0.0011) -[2023-10-09 09:58:05,790][23468] Updated weights for policy 0, policy_version 41673 (0.0008) -[2023-10-09 09:58:06,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14106.9). Total num frames: 85590016. Throughput: 0: 1773.8, 1: 1771.2. Samples: 21401032. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 09:58:06,078][22500] Avg episode reward: [(0, '8.080'), (1, '7.270')] -[2023-10-09 09:58:06,167][23468] Updated weights for policy 0, policy_version 41683 (0.0010) -[2023-10-09 09:58:06,549][23468] Updated weights for policy 0, policy_version 41693 (0.0009) -[2023-10-09 09:58:09,323][23469] Updated weights for policy 1, policy_version 41921 (0.0009) -[2023-10-09 09:58:09,709][23469] Updated weights for policy 1, policy_version 41931 (0.0010) -[2023-10-09 09:58:10,074][23469] Updated weights for policy 1, policy_version 41941 (0.0009) -[2023-10-09 09:58:10,338][23468] Updated weights for policy 0, policy_version 41703 (0.0008) -[2023-10-09 09:58:10,445][23469] Updated weights for policy 1, policy_version 41951 (0.0008) -[2023-10-09 09:58:10,721][23468] Updated weights for policy 0, policy_version 41713 (0.0010) -[2023-10-09 09:58:11,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 85655552. Throughput: 0: 1780.7, 1: 1787.7. Samples: 21422596. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 09:58:11,078][22500] Avg episode reward: [(0, '7.990'), (1, '7.080')] -[2023-10-09 09:58:11,102][23468] Updated weights for policy 0, policy_version 41723 (0.0010) -[2023-10-09 09:58:14,411][23469] Updated weights for policy 1, policy_version 41961 (0.0007) -[2023-10-09 09:58:14,788][23469] Updated weights for policy 1, policy_version 41971 (0.0010) -[2023-10-09 09:58:14,904][23468] Updated weights for policy 0, policy_version 41733 (0.0010) -[2023-10-09 09:58:15,161][23469] Updated weights for policy 1, policy_version 41981 (0.0009) -[2023-10-09 09:58:15,277][23468] Updated weights for policy 0, policy_version 41743 (0.0008) -[2023-10-09 09:58:15,652][23468] Updated weights for policy 0, policy_version 41753 (0.0011) -[2023-10-09 09:58:16,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 85753856. Throughput: 0: 1793.6, 1: 1760.5. Samples: 21443248. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:58:16,078][22500] Avg episode reward: [(0, '8.030'), (1, '7.580')] -[2023-10-09 09:58:16,084][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000041984_42991616.pth... -[2023-10-09 09:58:16,085][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000041760_42762240.pth... -[2023-10-09 09:58:16,115][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000040320_41287680.pth -[2023-10-09 09:58:16,115][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000040096_41058304.pth -[2023-10-09 09:58:18,977][23469] Updated weights for policy 1, policy_version 41991 (0.0009) -[2023-10-09 09:58:19,359][23469] Updated weights for policy 1, policy_version 42001 (0.0010) -[2023-10-09 09:58:19,581][23468] Updated weights for policy 0, policy_version 41763 (0.0010) -[2023-10-09 09:58:19,725][23469] Updated weights for policy 1, policy_version 42011 (0.0008) -[2023-10-09 09:58:19,960][23468] Updated weights for policy 0, policy_version 41773 (0.0008) -[2023-10-09 09:58:20,340][23468] Updated weights for policy 0, policy_version 41783 (0.0009) -[2023-10-09 09:58:21,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 85819392. Throughput: 0: 1769.6, 1: 1794.3. Samples: 21454636. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:58:21,078][22500] Avg episode reward: [(0, '8.030'), (1, '7.310')] -[2023-10-09 09:58:23,474][23469] Updated weights for policy 1, policy_version 42021 (0.0010) -[2023-10-09 09:58:23,851][23469] Updated weights for policy 1, policy_version 42031 (0.0009) -[2023-10-09 09:58:24,213][23469] Updated weights for policy 1, policy_version 42041 (0.0007) -[2023-10-09 09:58:24,339][23468] Updated weights for policy 0, policy_version 41793 (0.0009) -[2023-10-09 09:58:24,708][23468] Updated weights for policy 0, policy_version 41803 (0.0009) -[2023-10-09 09:58:25,089][23468] Updated weights for policy 0, policy_version 41813 (0.0007) -[2023-10-09 09:58:25,461][23468] Updated weights for policy 0, policy_version 41823 (0.0009) -[2023-10-09 09:58:26,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 85884928. Throughput: 0: 1794.2, 1: 1766.6. Samples: 21475130. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:58:26,078][22500] Avg episode reward: [(0, '7.980'), (1, '7.660')] -[2023-10-09 09:58:27,920][23469] Updated weights for policy 1, policy_version 42051 (0.0007) -[2023-10-09 09:58:28,291][23469] Updated weights for policy 1, policy_version 42061 (0.0010) -[2023-10-09 09:58:28,659][23469] Updated weights for policy 1, policy_version 42071 (0.0009) -[2023-10-09 09:58:29,127][23468] Updated weights for policy 0, policy_version 41833 (0.0008) -[2023-10-09 09:58:29,517][23468] Updated weights for policy 0, policy_version 41843 (0.0009) -[2023-10-09 09:58:29,887][23468] Updated weights for policy 0, policy_version 41853 (0.0008) -[2023-10-09 09:58:31,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 85950464. Throughput: 0: 1764.0, 1: 1775.5. Samples: 21496334. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:58:31,078][22500] Avg episode reward: [(0, '8.430'), (1, '7.660')] -[2023-10-09 09:58:32,391][23469] Updated weights for policy 1, policy_version 42081 (0.0009) -[2023-10-09 09:58:32,768][23469] Updated weights for policy 1, policy_version 42091 (0.0009) -[2023-10-09 09:58:33,138][23469] Updated weights for policy 1, policy_version 42101 (0.0009) -[2023-10-09 09:58:33,513][23469] Updated weights for policy 1, policy_version 42111 (0.0007) -[2023-10-09 09:58:33,643][23468] Updated weights for policy 0, policy_version 41863 (0.0009) -[2023-10-09 09:58:34,012][23468] Updated weights for policy 0, policy_version 41873 (0.0010) -[2023-10-09 09:58:34,386][23468] Updated weights for policy 0, policy_version 41883 (0.0009) -[2023-10-09 09:58:36,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 86016000. Throughput: 0: 1795.8, 1: 1774.4. Samples: 21507248. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 09:58:36,078][22500] Avg episode reward: [(0, '8.400'), (1, '7.780')] -[2023-10-09 09:58:37,339][23469] Updated weights for policy 1, policy_version 42121 (0.0009) -[2023-10-09 09:58:37,711][23469] Updated weights for policy 1, policy_version 42131 (0.0008) -[2023-10-09 09:58:38,082][23469] Updated weights for policy 1, policy_version 42141 (0.0009) -[2023-10-09 09:58:38,190][23468] Updated weights for policy 0, policy_version 41893 (0.0007) -[2023-10-09 09:58:38,564][23468] Updated weights for policy 0, policy_version 41903 (0.0009) -[2023-10-09 09:58:38,932][23468] Updated weights for policy 0, policy_version 41913 (0.0008) -[2023-10-09 09:58:41,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 86081536. Throughput: 0: 1761.4, 1: 1777.6. Samples: 21528046. Policy #0 lag: (min: 6.0, avg: 12.8, max: 38.0) -[2023-10-09 09:58:41,079][22500] Avg episode reward: [(0, '8.430'), (1, '7.790')] -[2023-10-09 09:58:41,949][23469] Updated weights for policy 1, policy_version 42151 (0.0009) -[2023-10-09 09:58:42,320][23469] Updated weights for policy 1, policy_version 42161 (0.0009) -[2023-10-09 09:58:42,622][23468] Updated weights for policy 0, policy_version 41923 (0.0008) -[2023-10-09 09:58:42,703][23469] Updated weights for policy 1, policy_version 42171 (0.0010) -[2023-10-09 09:58:42,992][23468] Updated weights for policy 0, policy_version 41933 (0.0007) -[2023-10-09 09:58:43,372][23468] Updated weights for policy 0, policy_version 41943 (0.0008) -[2023-10-09 09:58:46,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 86147072. Throughput: 0: 1760.8, 1: 1779.4. Samples: 21550046. Policy #0 lag: (min: 6.0, avg: 12.8, max: 38.0) -[2023-10-09 09:58:46,078][22500] Avg episode reward: [(0, '8.080'), (1, '7.440')] -[2023-10-09 09:58:46,607][23469] Updated weights for policy 1, policy_version 42181 (0.0008) -[2023-10-09 09:58:46,964][23469] Updated weights for policy 1, policy_version 42191 (0.0009) -[2023-10-09 09:58:47,154][23468] Updated weights for policy 0, policy_version 41953 (0.0008) -[2023-10-09 09:58:47,331][23469] Updated weights for policy 1, policy_version 42201 (0.0008) -[2023-10-09 09:58:47,530][23468] Updated weights for policy 0, policy_version 41963 (0.0009) -[2023-10-09 09:58:47,897][23468] Updated weights for policy 0, policy_version 41973 (0.0009) -[2023-10-09 09:58:48,276][23468] Updated weights for policy 0, policy_version 41983 (0.0008) -[2023-10-09 09:58:51,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 86212608. Throughput: 0: 1762.2, 1: 1763.2. Samples: 21559678. Policy #0 lag: (min: 6.0, avg: 12.8, max: 38.0) -[2023-10-09 09:58:51,078][22500] Avg episode reward: [(0, '8.410'), (1, '7.330')] -[2023-10-09 09:58:51,345][23469] Updated weights for policy 1, policy_version 42211 (0.0008) -[2023-10-09 09:58:51,703][23469] Updated weights for policy 1, policy_version 42221 (0.0011) -[2023-10-09 09:58:52,092][23469] Updated weights for policy 1, policy_version 42231 (0.0010) -[2023-10-09 09:58:52,607][23468] Updated weights for policy 0, policy_version 41993 (0.0010) -[2023-10-09 09:58:52,979][23468] Updated weights for policy 0, policy_version 42003 (0.0010) -[2023-10-09 09:58:53,364][23468] Updated weights for policy 0, policy_version 42013 (0.0010) -[2023-10-09 09:58:56,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 86278144. Throughput: 0: 1718.2, 1: 1725.5. Samples: 21577564. Policy #0 lag: (min: 6.0, avg: 12.8, max: 38.0) -[2023-10-09 09:58:56,078][22500] Avg episode reward: [(0, '8.650'), (1, '7.870')] -[2023-10-09 09:58:57,807][23469] Updated weights for policy 1, policy_version 42241 (0.0010) -[2023-10-09 09:58:58,176][23469] Updated weights for policy 1, policy_version 42251 (0.0011) -[2023-10-09 09:58:58,550][23469] Updated weights for policy 1, policy_version 42261 (0.0011) -[2023-10-09 09:58:58,933][23469] Updated weights for policy 1, policy_version 42271 (0.0015) -[2023-10-09 09:58:59,263][23468] Updated weights for policy 0, policy_version 42023 (0.0010) -[2023-10-09 09:58:59,650][23468] Updated weights for policy 0, policy_version 42033 (0.0007) -[2023-10-09 09:59:00,034][23468] Updated weights for policy 0, policy_version 42043 (0.0008) -[2023-10-09 09:59:01,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 86343680. Throughput: 0: 1642.2, 1: 1688.9. Samples: 21593148. Policy #0 lag: (min: 6.0, avg: 12.8, max: 38.0) -[2023-10-09 09:59:01,078][22500] Avg episode reward: [(0, '7.890'), (1, '7.870')] -[2023-10-09 09:59:02,935][23469] Updated weights for policy 1, policy_version 42281 (0.0009) -[2023-10-09 09:59:03,296][23469] Updated weights for policy 1, policy_version 42291 (0.0007) -[2023-10-09 09:59:03,668][23469] Updated weights for policy 1, policy_version 42301 (0.0008) -[2023-10-09 09:59:03,891][23468] Updated weights for policy 0, policy_version 42053 (0.0009) -[2023-10-09 09:59:04,269][23468] Updated weights for policy 0, policy_version 42063 (0.0008) -[2023-10-09 09:59:04,652][23468] Updated weights for policy 0, policy_version 42073 (0.0008) -[2023-10-09 09:59:06,077][22500] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 86409216. Throughput: 0: 1667.3, 1: 1664.2. Samples: 21604554. Policy #0 lag: (min: 6.0, avg: 12.8, max: 38.0) -[2023-10-09 09:59:06,078][22500] Avg episode reward: [(0, '7.920'), (1, '8.270')] -[2023-10-09 09:59:07,582][23469] Updated weights for policy 1, policy_version 42311 (0.0009) -[2023-10-09 09:59:07,964][23469] Updated weights for policy 1, policy_version 42321 (0.0009) -[2023-10-09 09:59:08,321][23469] Updated weights for policy 1, policy_version 42331 (0.0010) -[2023-10-09 09:59:08,504][23468] Updated weights for policy 0, policy_version 42083 (0.0007) -[2023-10-09 09:59:08,863][23468] Updated weights for policy 0, policy_version 42093 (0.0008) -[2023-10-09 09:59:09,237][23468] Updated weights for policy 0, policy_version 42103 (0.0010) -[2023-10-09 09:59:11,077][22500] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13995.8). Total num frames: 86474752. Throughput: 0: 1652.5, 1: 1687.9. Samples: 21625444. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 09:59:11,078][22500] Avg episode reward: [(0, '7.570'), (1, '8.280')] -[2023-10-09 09:59:12,090][23469] Updated weights for policy 1, policy_version 42341 (0.0007) -[2023-10-09 09:59:12,460][23469] Updated weights for policy 1, policy_version 42351 (0.0007) -[2023-10-09 09:59:12,841][23469] Updated weights for policy 1, policy_version 42361 (0.0008) -[2023-10-09 09:59:13,033][23468] Updated weights for policy 0, policy_version 42113 (0.0010) -[2023-10-09 09:59:13,404][23468] Updated weights for policy 0, policy_version 42123 (0.0007) -[2023-10-09 09:59:13,769][23468] Updated weights for policy 0, policy_version 42133 (0.0008) -[2023-10-09 09:59:14,141][23468] Updated weights for policy 0, policy_version 42143 (0.0010) -[2023-10-09 09:59:16,077][22500] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13995.8). Total num frames: 86540288. Throughput: 0: 1676.6, 1: 1682.5. Samples: 21647494. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 09:59:16,078][22500] Avg episode reward: [(0, '7.730'), (1, '7.780')] -[2023-10-09 09:59:16,578][23469] Updated weights for policy 1, policy_version 42371 (0.0007) -[2023-10-09 09:59:16,951][23469] Updated weights for policy 1, policy_version 42381 (0.0008) -[2023-10-09 09:59:17,324][23469] Updated weights for policy 1, policy_version 42391 (0.0007) -[2023-10-09 09:59:17,826][23468] Updated weights for policy 0, policy_version 42153 (0.0008) -[2023-10-09 09:59:18,204][23468] Updated weights for policy 0, policy_version 42163 (0.0010) -[2023-10-09 09:59:18,569][23468] Updated weights for policy 0, policy_version 42173 (0.0008) -[2023-10-09 09:59:21,077][22500] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13995.8). Total num frames: 86605824. Throughput: 0: 1660.0, 1: 1684.1. Samples: 21657736. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 09:59:21,078][22500] Avg episode reward: [(0, '8.700'), (1, '7.580')] -[2023-10-09 09:59:21,139][23469] Updated weights for policy 1, policy_version 42401 (0.0009) -[2023-10-09 09:59:21,506][23469] Updated weights for policy 1, policy_version 42411 (0.0010) -[2023-10-09 09:59:21,880][23469] Updated weights for policy 1, policy_version 42421 (0.0009) -[2023-10-09 09:59:22,245][23469] Updated weights for policy 1, policy_version 42431 (0.0007) -[2023-10-09 09:59:22,396][23468] Updated weights for policy 0, policy_version 42183 (0.0008) -[2023-10-09 09:59:22,775][23468] Updated weights for policy 0, policy_version 42193 (0.0009) -[2023-10-09 09:59:23,149][23468] Updated weights for policy 0, policy_version 42203 (0.0009) -[2023-10-09 09:59:25,937][23469] Updated weights for policy 1, policy_version 42441 (0.0008) -[2023-10-09 09:59:26,077][22500] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13995.8). Total num frames: 86671360. Throughput: 0: 1677.9, 1: 1685.2. Samples: 21679388. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 09:59:26,078][22500] Avg episode reward: [(0, '8.400'), (1, '7.440')] -[2023-10-09 09:59:26,309][23469] Updated weights for policy 1, policy_version 42451 (0.0008) -[2023-10-09 09:59:26,677][23469] Updated weights for policy 1, policy_version 42461 (0.0008) -[2023-10-09 09:59:26,797][23468] Updated weights for policy 0, policy_version 42213 (0.0008) -[2023-10-09 09:59:27,182][23468] Updated weights for policy 0, policy_version 42223 (0.0009) -[2023-10-09 09:59:27,542][23468] Updated weights for policy 0, policy_version 42233 (0.0009) -[2023-10-09 09:59:30,351][23469] Updated weights for policy 1, policy_version 42471 (0.0008) -[2023-10-09 09:59:30,721][23469] Updated weights for policy 1, policy_version 42481 (0.0009) -[2023-10-09 09:59:31,078][22500] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13995.8). Total num frames: 86736896. Throughput: 0: 1677.3, 1: 1679.7. Samples: 21701112. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 09:59:31,079][22500] Avg episode reward: [(0, '8.750'), (1, '7.700')] -[2023-10-09 09:59:31,091][23469] Updated weights for policy 1, policy_version 42491 (0.0008) -[2023-10-09 09:59:31,329][23468] Updated weights for policy 0, policy_version 42243 (0.0009) -[2023-10-09 09:59:31,691][23468] Updated weights for policy 0, policy_version 42253 (0.0008) -[2023-10-09 09:59:32,064][23468] Updated weights for policy 0, policy_version 42263 (0.0008) -[2023-10-09 09:59:34,805][23469] Updated weights for policy 1, policy_version 42501 (0.0008) -[2023-10-09 09:59:35,179][23469] Updated weights for policy 1, policy_version 42511 (0.0009) -[2023-10-09 09:59:35,545][23469] Updated weights for policy 1, policy_version 42521 (0.0010) -[2023-10-09 09:59:35,810][23468] Updated weights for policy 0, policy_version 42273 (0.0007) -[2023-10-09 09:59:36,077][22500] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 86835200. Throughput: 0: 1676.6, 1: 1702.1. Samples: 21711718. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 09:59:36,078][22500] Avg episode reward: [(0, '8.480'), (1, '7.800')] -[2023-10-09 09:59:36,189][23468] Updated weights for policy 0, policy_version 42283 (0.0008) -[2023-10-09 09:59:36,559][23468] Updated weights for policy 0, policy_version 42293 (0.0007) -[2023-10-09 09:59:36,931][23468] Updated weights for policy 0, policy_version 42303 (0.0007) -[2023-10-09 09:59:39,437][23469] Updated weights for policy 1, policy_version 42531 (0.0009) -[2023-10-09 09:59:39,818][23469] Updated weights for policy 1, policy_version 42541 (0.0009) -[2023-10-09 09:59:40,185][23469] Updated weights for policy 1, policy_version 42551 (0.0009) -[2023-10-09 09:59:40,519][23468] Updated weights for policy 0, policy_version 42313 (0.0009) -[2023-10-09 09:59:40,895][23468] Updated weights for policy 0, policy_version 42323 (0.0009) -[2023-10-09 09:59:41,077][22500] Fps is (10 sec: 16384.3, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 86900736. Throughput: 0: 1730.9, 1: 1742.9. Samples: 21733884. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 09:59:41,078][22500] Avg episode reward: [(0, '8.550'), (1, '7.940')] -[2023-10-09 09:59:41,267][23468] Updated weights for policy 0, policy_version 42333 (0.0009) -[2023-10-09 09:59:43,858][23469] Updated weights for policy 1, policy_version 42561 (0.0008) -[2023-10-09 09:59:44,228][23469] Updated weights for policy 1, policy_version 42571 (0.0009) -[2023-10-09 09:59:44,604][23469] Updated weights for policy 1, policy_version 42581 (0.0008) -[2023-10-09 09:59:44,980][23469] Updated weights for policy 1, policy_version 42591 (0.0008) -[2023-10-09 09:59:45,045][23468] Updated weights for policy 0, policy_version 42343 (0.0007) -[2023-10-09 09:59:45,420][23468] Updated weights for policy 0, policy_version 42353 (0.0011) -[2023-10-09 09:59:45,792][23468] Updated weights for policy 0, policy_version 42363 (0.0010) -[2023-10-09 09:59:46,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 86999040. Throughput: 0: 1809.5, 1: 1785.5. Samples: 21754922. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-09 09:59:46,078][22500] Avg episode reward: [(0, '8.370'), (1, '7.910')] -[2023-10-09 09:59:48,630][23469] Updated weights for policy 1, policy_version 42601 (0.0010) -[2023-10-09 09:59:49,000][23469] Updated weights for policy 1, policy_version 42611 (0.0009) -[2023-10-09 09:59:49,365][23469] Updated weights for policy 1, policy_version 42621 (0.0009) -[2023-10-09 09:59:49,686][23468] Updated weights for policy 0, policy_version 42373 (0.0008) -[2023-10-09 09:59:50,063][23468] Updated weights for policy 0, policy_version 42383 (0.0007) -[2023-10-09 09:59:50,443][23468] Updated weights for policy 0, policy_version 42393 (0.0007) -[2023-10-09 09:59:51,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 87064576. Throughput: 0: 1789.1, 1: 1797.2. Samples: 21765938. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-09 09:59:51,078][22500] Avg episode reward: [(0, '7.950'), (1, '7.710')] -[2023-10-09 09:59:53,172][23469] Updated weights for policy 1, policy_version 42631 (0.0010) -[2023-10-09 09:59:53,544][23469] Updated weights for policy 1, policy_version 42641 (0.0008) -[2023-10-09 09:59:53,918][23469] Updated weights for policy 1, policy_version 42651 (0.0009) -[2023-10-09 09:59:54,320][23468] Updated weights for policy 0, policy_version 42403 (0.0008) -[2023-10-09 09:59:54,691][23468] Updated weights for policy 0, policy_version 42413 (0.0010) -[2023-10-09 09:59:55,074][23468] Updated weights for policy 0, policy_version 42423 (0.0007) -[2023-10-09 09:59:56,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 87130112. Throughput: 0: 1805.7, 1: 1784.6. Samples: 21787008. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-09 09:59:56,078][22500] Avg episode reward: [(0, '7.860'), (1, '7.110')] -[2023-10-09 09:59:57,729][23469] Updated weights for policy 1, policy_version 42661 (0.0010) -[2023-10-09 09:59:58,123][23469] Updated weights for policy 1, policy_version 42671 (0.0011) -[2023-10-09 09:59:58,485][23469] Updated weights for policy 1, policy_version 42681 (0.0009) -[2023-10-09 09:59:58,560][23468] Updated weights for policy 0, policy_version 42433 (0.0008) -[2023-10-09 09:59:58,937][23468] Updated weights for policy 0, policy_version 42443 (0.0007) -[2023-10-09 09:59:59,317][23468] Updated weights for policy 0, policy_version 42453 (0.0010) -[2023-10-09 09:59:59,689][23468] Updated weights for policy 0, policy_version 42463 (0.0011) -[2023-10-09 10:00:01,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 87195648. Throughput: 0: 1785.6, 1: 1788.8. Samples: 21808346. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-09 10:00:01,079][22500] Avg episode reward: [(0, '7.330'), (1, '7.430')] -[2023-10-09 10:00:02,234][23469] Updated weights for policy 1, policy_version 42691 (0.0011) -[2023-10-09 10:00:02,600][23469] Updated weights for policy 1, policy_version 42701 (0.0011) -[2023-10-09 10:00:02,965][23469] Updated weights for policy 1, policy_version 42711 (0.0011) -[2023-10-09 10:00:03,523][23468] Updated weights for policy 0, policy_version 42473 (0.0008) -[2023-10-09 10:00:03,895][23468] Updated weights for policy 0, policy_version 42483 (0.0008) -[2023-10-09 10:00:04,278][23468] Updated weights for policy 0, policy_version 42493 (0.0009) -[2023-10-09 10:00:06,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 87261184. Throughput: 0: 1801.4, 1: 1791.4. Samples: 21819410. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-09 10:00:06,079][22500] Avg episode reward: [(0, '7.620'), (1, '7.580')] -[2023-10-09 10:00:06,802][23469] Updated weights for policy 1, policy_version 42721 (0.0009) -[2023-10-09 10:00:07,178][23469] Updated weights for policy 1, policy_version 42731 (0.0010) -[2023-10-09 10:00:07,543][23469] Updated weights for policy 1, policy_version 42741 (0.0010) -[2023-10-09 10:00:07,908][23469] Updated weights for policy 1, policy_version 42751 (0.0009) -[2023-10-09 10:00:08,024][23468] Updated weights for policy 0, policy_version 42503 (0.0007) -[2023-10-09 10:00:08,396][23468] Updated weights for policy 0, policy_version 42513 (0.0011) -[2023-10-09 10:00:08,775][23468] Updated weights for policy 0, policy_version 42523 (0.0009) -[2023-10-09 10:00:11,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 87326720. Throughput: 0: 1788.9, 1: 1789.7. Samples: 21840426. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-09 10:00:11,078][22500] Avg episode reward: [(0, '7.910'), (1, '8.030')] -[2023-10-09 10:00:11,643][23469] Updated weights for policy 1, policy_version 42761 (0.0008) -[2023-10-09 10:00:12,006][23469] Updated weights for policy 1, policy_version 42771 (0.0008) -[2023-10-09 10:00:12,381][23469] Updated weights for policy 1, policy_version 42781 (0.0008) -[2023-10-09 10:00:12,394][23468] Updated weights for policy 0, policy_version 42533 (0.0007) -[2023-10-09 10:00:12,774][23468] Updated weights for policy 0, policy_version 42543 (0.0008) -[2023-10-09 10:00:13,141][23468] Updated weights for policy 0, policy_version 42553 (0.0008) -[2023-10-09 10:00:16,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 87392256. Throughput: 0: 1795.1, 1: 1802.3. Samples: 21862996. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-09 10:00:16,079][22500] Avg episode reward: [(0, '8.720'), (1, '7.620')] -[2023-10-09 10:00:16,087][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000042560_43581440.pth... -[2023-10-09 10:00:16,122][23469] Updated weights for policy 1, policy_version 42791 (0.0008) -[2023-10-09 10:00:16,123][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000040928_41910272.pth -[2023-10-09 10:00:16,486][23469] Updated weights for policy 1, policy_version 42801 (0.0007) -[2023-10-09 10:00:16,854][23469] Updated weights for policy 1, policy_version 42811 (0.0009) -[2023-10-09 10:00:16,862][23468] Updated weights for policy 0, policy_version 42563 (0.0009) -[2023-10-09 10:00:17,038][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000042816_43843584.pth... -[2023-10-09 10:00:17,067][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000041152_42139648.pth -[2023-10-09 10:00:17,226][23468] Updated weights for policy 0, policy_version 42573 (0.0007) -[2023-10-09 10:00:17,602][23468] Updated weights for policy 0, policy_version 42583 (0.0009) -[2023-10-09 10:00:20,609][23469] Updated weights for policy 1, policy_version 42821 (0.0008) -[2023-10-09 10:00:20,976][23469] Updated weights for policy 1, policy_version 42831 (0.0009) -[2023-10-09 10:00:21,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 87457792. Throughput: 0: 1793.6, 1: 1782.2. Samples: 21872630. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-09 10:00:21,078][22500] Avg episode reward: [(0, '8.970'), (1, '7.500')] -[2023-10-09 10:00:21,347][23469] Updated weights for policy 1, policy_version 42841 (0.0008) -[2023-10-09 10:00:21,395][23468] Updated weights for policy 0, policy_version 42593 (0.0007) -[2023-10-09 10:00:21,769][23468] Updated weights for policy 0, policy_version 42603 (0.0009) -[2023-10-09 10:00:22,134][23468] Updated weights for policy 0, policy_version 42613 (0.0010) -[2023-10-09 10:00:22,516][23468] Updated weights for policy 0, policy_version 42623 (0.0010) -[2023-10-09 10:00:25,064][23469] Updated weights for policy 1, policy_version 42851 (0.0009) -[2023-10-09 10:00:25,440][23469] Updated weights for policy 1, policy_version 42861 (0.0009) -[2023-10-09 10:00:25,802][23469] Updated weights for policy 1, policy_version 42871 (0.0009) -[2023-10-09 10:00:26,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 87523328. Throughput: 0: 1783.0, 1: 1797.4. Samples: 21895004. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-09 10:00:26,078][22500] Avg episode reward: [(0, '9.180'), (1, '7.720')] -[2023-10-09 10:00:26,385][23468] Updated weights for policy 0, policy_version 42633 (0.0009) -[2023-10-09 10:00:26,755][23468] Updated weights for policy 0, policy_version 42643 (0.0009) -[2023-10-09 10:00:27,129][23468] Updated weights for policy 0, policy_version 42653 (0.0009) -[2023-10-09 10:00:27,234][23265] Saving new best policy, reward=9.180! -[2023-10-09 10:00:29,436][23469] Updated weights for policy 1, policy_version 42881 (0.0009) -[2023-10-09 10:00:29,805][23469] Updated weights for policy 1, policy_version 42891 (0.0008) -[2023-10-09 10:00:30,182][23469] Updated weights for policy 1, policy_version 42901 (0.0008) -[2023-10-09 10:00:30,541][23469] Updated weights for policy 1, policy_version 42911 (0.0010) -[2023-10-09 10:00:31,029][23468] Updated weights for policy 0, policy_version 42663 (0.0007) -[2023-10-09 10:00:31,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14106.9). Total num frames: 87621632. Throughput: 0: 1787.4, 1: 1787.5. Samples: 21915792. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-09 10:00:31,078][22500] Avg episode reward: [(0, '8.940'), (1, '7.420')] -[2023-10-09 10:00:31,418][23468] Updated weights for policy 0, policy_version 42673 (0.0010) -[2023-10-09 10:00:31,787][23468] Updated weights for policy 0, policy_version 42683 (0.0008) -[2023-10-09 10:00:34,319][23469] Updated weights for policy 1, policy_version 42921 (0.0008) -[2023-10-09 10:00:34,686][23469] Updated weights for policy 1, policy_version 42931 (0.0010) -[2023-10-09 10:00:35,049][23469] Updated weights for policy 1, policy_version 42941 (0.0010) -[2023-10-09 10:00:35,523][23468] Updated weights for policy 0, policy_version 42693 (0.0009) -[2023-10-09 10:00:35,891][23468] Updated weights for policy 0, policy_version 42703 (0.0010) -[2023-10-09 10:00:36,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 87687168. Throughput: 0: 1772.6, 1: 1804.5. Samples: 21926910. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-09 10:00:36,078][22500] Avg episode reward: [(0, '8.600'), (1, '7.400')] -[2023-10-09 10:00:36,262][23468] Updated weights for policy 0, policy_version 42713 (0.0010) -[2023-10-09 10:00:38,750][23469] Updated weights for policy 1, policy_version 42951 (0.0008) -[2023-10-09 10:00:39,115][23469] Updated weights for policy 1, policy_version 42961 (0.0009) -[2023-10-09 10:00:39,489][23469] Updated weights for policy 1, policy_version 42971 (0.0010) -[2023-10-09 10:00:40,105][23468] Updated weights for policy 0, policy_version 42723 (0.0009) -[2023-10-09 10:00:40,475][23468] Updated weights for policy 0, policy_version 42733 (0.0007) -[2023-10-09 10:00:40,850][23468] Updated weights for policy 0, policy_version 42743 (0.0009) -[2023-10-09 10:00:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 87752704. Throughput: 0: 1785.2, 1: 1796.4. Samples: 21948180. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-09 10:00:41,078][22500] Avg episode reward: [(0, '7.680'), (1, '7.500')] -[2023-10-09 10:00:43,443][23469] Updated weights for policy 1, policy_version 42981 (0.0008) -[2023-10-09 10:00:43,833][23469] Updated weights for policy 1, policy_version 42991 (0.0007) -[2023-10-09 10:00:44,204][23469] Updated weights for policy 1, policy_version 43001 (0.0009) -[2023-10-09 10:00:44,595][23468] Updated weights for policy 0, policy_version 42753 (0.0007) -[2023-10-09 10:00:44,971][23468] Updated weights for policy 0, policy_version 42763 (0.0010) -[2023-10-09 10:00:45,347][23468] Updated weights for policy 0, policy_version 42773 (0.0007) -[2023-10-09 10:00:45,714][23468] Updated weights for policy 0, policy_version 42783 (0.0009) -[2023-10-09 10:00:46,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 87851008. Throughput: 0: 1791.6, 1: 1790.1. Samples: 21969518. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 10:00:46,078][22500] Avg episode reward: [(0, '8.110'), (1, '7.950')] -[2023-10-09 10:00:47,906][23469] Updated weights for policy 1, policy_version 43011 (0.0009) -[2023-10-09 10:00:48,271][23469] Updated weights for policy 1, policy_version 43021 (0.0008) -[2023-10-09 10:00:48,648][23469] Updated weights for policy 1, policy_version 43031 (0.0008) -[2023-10-09 10:00:49,482][23468] Updated weights for policy 0, policy_version 42793 (0.0009) -[2023-10-09 10:00:49,857][23468] Updated weights for policy 0, policy_version 42803 (0.0007) -[2023-10-09 10:00:50,226][23468] Updated weights for policy 0, policy_version 42813 (0.0007) -[2023-10-09 10:00:51,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 87916544. Throughput: 0: 1779.6, 1: 1795.7. Samples: 21980294. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 10:00:51,078][22500] Avg episode reward: [(0, '8.200'), (1, '7.870')] -[2023-10-09 10:00:53,132][23469] Updated weights for policy 1, policy_version 43041 (0.0009) -[2023-10-09 10:00:53,491][23469] Updated weights for policy 1, policy_version 43051 (0.0011) -[2023-10-09 10:00:53,857][23469] Updated weights for policy 1, policy_version 43061 (0.0011) -[2023-10-09 10:00:54,238][23469] Updated weights for policy 1, policy_version 43071 (0.0011) -[2023-10-09 10:00:55,703][23468] Updated weights for policy 0, policy_version 42823 (0.0008) -[2023-10-09 10:00:56,076][23468] Updated weights for policy 0, policy_version 42833 (0.0009) -[2023-10-09 10:00:56,077][22500] Fps is (10 sec: 9830.4, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 87949312. Throughput: 0: 1748.2, 1: 1739.4. Samples: 21997370. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 10:00:56,078][22500] Avg episode reward: [(0, '8.570'), (1, '7.990')] -[2023-10-09 10:00:56,456][23468] Updated weights for policy 0, policy_version 42843 (0.0009) -[2023-10-09 10:00:58,573][23469] Updated weights for policy 1, policy_version 43081 (0.0009) -[2023-10-09 10:00:58,952][23469] Updated weights for policy 1, policy_version 43091 (0.0010) -[2023-10-09 10:00:59,313][23469] Updated weights for policy 1, policy_version 43101 (0.0007) -[2023-10-09 10:01:00,164][23468] Updated weights for policy 0, policy_version 42853 (0.0009) -[2023-10-09 10:01:00,537][23468] Updated weights for policy 0, policy_version 42863 (0.0008) -[2023-10-09 10:01:00,911][23468] Updated weights for policy 0, policy_version 42873 (0.0009) -[2023-10-09 10:01:01,077][22500] Fps is (10 sec: 9830.4, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 88014848. Throughput: 0: 1722.6, 1: 1728.0. Samples: 22018274. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 10:01:01,078][22500] Avg episode reward: [(0, '9.140'), (1, '7.720')] -[2023-10-09 10:01:03,138][23469] Updated weights for policy 1, policy_version 43111 (0.0007) -[2023-10-09 10:01:03,514][23469] Updated weights for policy 1, policy_version 43121 (0.0007) -[2023-10-09 10:01:03,879][23469] Updated weights for policy 1, policy_version 43131 (0.0009) -[2023-10-09 10:01:04,759][23468] Updated weights for policy 0, policy_version 42883 (0.0008) -[2023-10-09 10:01:05,128][23468] Updated weights for policy 0, policy_version 42893 (0.0009) -[2023-10-09 10:01:05,494][23468] Updated weights for policy 0, policy_version 42903 (0.0009) -[2023-10-09 10:01:06,078][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 88113152. Throughput: 0: 1729.2, 1: 1739.0. Samples: 22028700. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 10:01:06,079][22500] Avg episode reward: [(0, '9.240'), (1, '7.810')] -[2023-10-09 10:01:06,080][23265] Saving new best policy, reward=9.240! -[2023-10-09 10:01:07,578][23469] Updated weights for policy 1, policy_version 43141 (0.0008) -[2023-10-09 10:01:07,940][23469] Updated weights for policy 1, policy_version 43151 (0.0007) -[2023-10-09 10:01:08,315][23469] Updated weights for policy 1, policy_version 43161 (0.0009) -[2023-10-09 10:01:09,094][23468] Updated weights for policy 0, policy_version 42913 (0.0009) -[2023-10-09 10:01:09,459][23468] Updated weights for policy 0, policy_version 42923 (0.0008) -[2023-10-09 10:01:09,841][23468] Updated weights for policy 0, policy_version 42933 (0.0008) -[2023-10-09 10:01:10,213][23468] Updated weights for policy 0, policy_version 42943 (0.0010) -[2023-10-09 10:01:11,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 88178688. Throughput: 0: 1727.6, 1: 1727.3. Samples: 22050474. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 10:01:11,078][22500] Avg episode reward: [(0, '9.080'), (1, '8.110')] -[2023-10-09 10:01:12,213][23469] Updated weights for policy 1, policy_version 43171 (0.0009) -[2023-10-09 10:01:12,573][23469] Updated weights for policy 1, policy_version 43181 (0.0008) -[2023-10-09 10:01:12,943][23469] Updated weights for policy 1, policy_version 43191 (0.0007) -[2023-10-09 10:01:13,779][23468] Updated weights for policy 0, policy_version 42953 (0.0010) -[2023-10-09 10:01:14,150][23468] Updated weights for policy 0, policy_version 42963 (0.0011) -[2023-10-09 10:01:14,523][23468] Updated weights for policy 0, policy_version 42973 (0.0010) -[2023-10-09 10:01:16,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 88244224. Throughput: 0: 1701.6, 1: 1757.9. Samples: 22071472. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:01:16,078][22500] Avg episode reward: [(0, '8.200'), (1, '8.100')] -[2023-10-09 10:01:16,589][23469] Updated weights for policy 1, policy_version 43201 (0.0007) -[2023-10-09 10:01:16,957][23469] Updated weights for policy 1, policy_version 43211 (0.0007) -[2023-10-09 10:01:17,329][23469] Updated weights for policy 1, policy_version 43221 (0.0009) -[2023-10-09 10:01:17,699][23469] Updated weights for policy 1, policy_version 43231 (0.0010) -[2023-10-09 10:01:18,821][23468] Updated weights for policy 0, policy_version 42983 (0.0010) -[2023-10-09 10:01:19,187][23468] Updated weights for policy 0, policy_version 42993 (0.0009) -[2023-10-09 10:01:19,553][23468] Updated weights for policy 0, policy_version 43003 (0.0010) -[2023-10-09 10:01:21,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 88309760. Throughput: 0: 1740.4, 1: 1722.3. Samples: 22082734. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:01:21,079][22500] Avg episode reward: [(0, '6.990'), (1, '7.440')] -[2023-10-09 10:01:21,535][23469] Updated weights for policy 1, policy_version 43241 (0.0007) -[2023-10-09 10:01:21,910][23469] Updated weights for policy 1, policy_version 43251 (0.0011) -[2023-10-09 10:01:22,281][23469] Updated weights for policy 1, policy_version 43261 (0.0008) -[2023-10-09 10:01:23,447][23468] Updated weights for policy 0, policy_version 43013 (0.0008) -[2023-10-09 10:01:23,822][23468] Updated weights for policy 0, policy_version 43023 (0.0007) -[2023-10-09 10:01:24,198][23468] Updated weights for policy 0, policy_version 43033 (0.0007) -[2023-10-09 10:01:25,976][23469] Updated weights for policy 1, policy_version 43271 (0.0009) -[2023-10-09 10:01:26,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 88375296. Throughput: 0: 1700.0, 1: 1755.9. Samples: 22103694. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:01:26,078][22500] Avg episode reward: [(0, '7.110'), (1, '7.460')] -[2023-10-09 10:01:26,344][23469] Updated weights for policy 1, policy_version 43281 (0.0008) -[2023-10-09 10:01:26,710][23469] Updated weights for policy 1, policy_version 43291 (0.0008) -[2023-10-09 10:01:28,019][23468] Updated weights for policy 0, policy_version 43043 (0.0009) -[2023-10-09 10:01:28,393][23468] Updated weights for policy 0, policy_version 43053 (0.0010) -[2023-10-09 10:01:28,764][23468] Updated weights for policy 0, policy_version 43063 (0.0009) -[2023-10-09 10:01:30,621][23469] Updated weights for policy 1, policy_version 43301 (0.0008) -[2023-10-09 10:01:31,016][23469] Updated weights for policy 1, policy_version 43311 (0.0009) -[2023-10-09 10:01:31,077][22500] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 88440832. Throughput: 0: 1712.6, 1: 1744.3. Samples: 22125082. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:01:31,078][22500] Avg episode reward: [(0, '7.600'), (1, '7.750')] -[2023-10-09 10:01:31,385][23469] Updated weights for policy 1, policy_version 43321 (0.0007) -[2023-10-09 10:01:32,354][23468] Updated weights for policy 0, policy_version 43073 (0.0008) -[2023-10-09 10:01:32,721][23468] Updated weights for policy 0, policy_version 43083 (0.0007) -[2023-10-09 10:01:33,095][23468] Updated weights for policy 0, policy_version 43093 (0.0009) -[2023-10-09 10:01:33,467][23468] Updated weights for policy 0, policy_version 43103 (0.0007) -[2023-10-09 10:01:34,882][23469] Updated weights for policy 1, policy_version 43331 (0.0008) -[2023-10-09 10:01:35,253][23469] Updated weights for policy 1, policy_version 43341 (0.0008) -[2023-10-09 10:01:35,621][23469] Updated weights for policy 1, policy_version 43351 (0.0008) -[2023-10-09 10:01:36,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 88539136. Throughput: 0: 1704.0, 1: 1749.9. Samples: 22135718. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:01:36,078][22500] Avg episode reward: [(0, '7.870'), (1, '7.720')] -[2023-10-09 10:01:37,054][23468] Updated weights for policy 0, policy_version 43113 (0.0007) -[2023-10-09 10:01:37,428][23468] Updated weights for policy 0, policy_version 43123 (0.0009) -[2023-10-09 10:01:37,803][23468] Updated weights for policy 0, policy_version 43133 (0.0009) -[2023-10-09 10:01:39,391][23469] Updated weights for policy 1, policy_version 43361 (0.0008) -[2023-10-09 10:01:39,760][23469] Updated weights for policy 1, policy_version 43371 (0.0008) -[2023-10-09 10:01:40,129][23469] Updated weights for policy 1, policy_version 43381 (0.0010) -[2023-10-09 10:01:40,496][23469] Updated weights for policy 1, policy_version 43391 (0.0011) -[2023-10-09 10:01:41,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 88604672. Throughput: 0: 1753.1, 1: 1800.1. Samples: 22157266. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:01:41,078][22500] Avg episode reward: [(0, '7.800'), (1, '7.620')] -[2023-10-09 10:01:41,573][23468] Updated weights for policy 0, policy_version 43143 (0.0008) -[2023-10-09 10:01:41,945][23468] Updated weights for policy 0, policy_version 43153 (0.0008) -[2023-10-09 10:01:42,323][23468] Updated weights for policy 0, policy_version 43163 (0.0010) -[2023-10-09 10:01:44,427][23469] Updated weights for policy 1, policy_version 43401 (0.0007) -[2023-10-09 10:01:44,801][23469] Updated weights for policy 1, policy_version 43411 (0.0009) -[2023-10-09 10:01:45,175][23469] Updated weights for policy 1, policy_version 43421 (0.0008) -[2023-10-09 10:01:46,009][23468] Updated weights for policy 0, policy_version 43173 (0.0009) -[2023-10-09 10:01:46,078][22500] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 88670208. Throughput: 0: 1782.8, 1: 1782.6. Samples: 22178718. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:01:46,079][22500] Avg episode reward: [(0, '7.540'), (1, '7.160')] -[2023-10-09 10:01:46,385][23468] Updated weights for policy 0, policy_version 43183 (0.0009) -[2023-10-09 10:01:46,761][23468] Updated weights for policy 0, policy_version 43193 (0.0009) -[2023-10-09 10:01:48,840][23469] Updated weights for policy 1, policy_version 43431 (0.0009) -[2023-10-09 10:01:49,214][23469] Updated weights for policy 1, policy_version 43441 (0.0010) -[2023-10-09 10:01:49,586][23469] Updated weights for policy 1, policy_version 43451 (0.0008) -[2023-10-09 10:01:50,571][23468] Updated weights for policy 0, policy_version 43203 (0.0008) -[2023-10-09 10:01:50,941][23468] Updated weights for policy 0, policy_version 43213 (0.0009) -[2023-10-09 10:01:51,077][22500] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 88735744. Throughput: 0: 1773.4, 1: 1799.8. Samples: 22189496. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:01:51,078][22500] Avg episode reward: [(0, '7.810'), (1, '7.400')] -[2023-10-09 10:01:51,321][23468] Updated weights for policy 0, policy_version 43223 (0.0007) -[2023-10-09 10:01:53,524][23469] Updated weights for policy 1, policy_version 43461 (0.0009) -[2023-10-09 10:01:53,894][23469] Updated weights for policy 1, policy_version 43471 (0.0009) -[2023-10-09 10:01:54,255][23469] Updated weights for policy 1, policy_version 43481 (0.0010) -[2023-10-09 10:01:54,994][23468] Updated weights for policy 0, policy_version 43233 (0.0007) -[2023-10-09 10:01:55,370][23468] Updated weights for policy 0, policy_version 43243 (0.0009) -[2023-10-09 10:01:55,739][23468] Updated weights for policy 0, policy_version 43253 (0.0010) -[2023-10-09 10:01:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 88801280. Throughput: 0: 1782.0, 1: 1779.2. Samples: 22210730. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:01:56,079][22500] Avg episode reward: [(0, '7.930'), (1, '7.520')] -[2023-10-09 10:01:56,127][23468] Updated weights for policy 0, policy_version 43263 (0.0009) -[2023-10-09 10:01:58,010][23469] Updated weights for policy 1, policy_version 43491 (0.0008) -[2023-10-09 10:01:58,377][23469] Updated weights for policy 1, policy_version 43501 (0.0008) -[2023-10-09 10:01:58,746][23469] Updated weights for policy 1, policy_version 43511 (0.0008) -[2023-10-09 10:01:59,938][23468] Updated weights for policy 0, policy_version 43273 (0.0007) -[2023-10-09 10:02:00,313][23468] Updated weights for policy 0, policy_version 43283 (0.0009) -[2023-10-09 10:02:00,692][23468] Updated weights for policy 0, policy_version 43293 (0.0008) -[2023-10-09 10:02:01,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 88899584. Throughput: 0: 1798.1, 1: 1779.3. Samples: 22232456. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:02:01,078][22500] Avg episode reward: [(0, '8.330'), (1, '7.730')] -[2023-10-09 10:02:02,656][23469] Updated weights for policy 1, policy_version 43521 (0.0007) -[2023-10-09 10:02:03,023][23469] Updated weights for policy 1, policy_version 43531 (0.0009) -[2023-10-09 10:02:03,402][23469] Updated weights for policy 1, policy_version 43541 (0.0007) -[2023-10-09 10:02:03,781][23469] Updated weights for policy 1, policy_version 43551 (0.0008) -[2023-10-09 10:02:04,613][23468] Updated weights for policy 0, policy_version 43303 (0.0008) -[2023-10-09 10:02:05,010][23468] Updated weights for policy 0, policy_version 43313 (0.0008) -[2023-10-09 10:02:05,379][23468] Updated weights for policy 0, policy_version 43323 (0.0008) -[2023-10-09 10:02:06,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 88965120. Throughput: 0: 1776.0, 1: 1782.8. Samples: 22242878. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:02:06,078][22500] Avg episode reward: [(0, '8.240'), (1, '7.600')] -[2023-10-09 10:02:07,346][23469] Updated weights for policy 1, policy_version 43561 (0.0007) -[2023-10-09 10:02:07,724][23469] Updated weights for policy 1, policy_version 43571 (0.0008) -[2023-10-09 10:02:08,094][23469] Updated weights for policy 1, policy_version 43581 (0.0008) -[2023-10-09 10:02:09,121][23468] Updated weights for policy 0, policy_version 43333 (0.0009) -[2023-10-09 10:02:09,497][23468] Updated weights for policy 0, policy_version 43343 (0.0007) -[2023-10-09 10:02:09,864][23468] Updated weights for policy 0, policy_version 43353 (0.0007) -[2023-10-09 10:02:11,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 89030656. Throughput: 0: 1796.4, 1: 1784.0. Samples: 22264814. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:02:11,078][22500] Avg episode reward: [(0, '8.160'), (1, '8.000')] -[2023-10-09 10:02:11,716][23469] Updated weights for policy 1, policy_version 43591 (0.0009) -[2023-10-09 10:02:12,088][23469] Updated weights for policy 1, policy_version 43601 (0.0008) -[2023-10-09 10:02:12,448][23469] Updated weights for policy 1, policy_version 43611 (0.0008) -[2023-10-09 10:02:13,592][23468] Updated weights for policy 0, policy_version 43363 (0.0007) -[2023-10-09 10:02:13,963][23468] Updated weights for policy 0, policy_version 43373 (0.0009) -[2023-10-09 10:02:14,346][23468] Updated weights for policy 0, policy_version 43383 (0.0007) -[2023-10-09 10:02:16,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 89096192. Throughput: 0: 1782.9, 1: 1800.4. Samples: 22286334. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:02:16,079][22500] Avg episode reward: [(0, '7.430'), (1, '7.380')] -[2023-10-09 10:02:16,092][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000043392_44433408.pth... -[2023-10-09 10:02:16,124][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000041760_42762240.pth -[2023-10-09 10:02:16,249][23469] Updated weights for policy 1, policy_version 43621 (0.0008) -[2023-10-09 10:02:16,631][23469] Updated weights for policy 1, policy_version 43631 (0.0009) -[2023-10-09 10:02:17,003][23469] Updated weights for policy 1, policy_version 43641 (0.0007) -[2023-10-09 10:02:17,266][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000043648_44695552.pth... -[2023-10-09 10:02:17,305][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000041984_42991616.pth -[2023-10-09 10:02:18,072][23468] Updated weights for policy 0, policy_version 43393 (0.0008) -[2023-10-09 10:02:18,432][23468] Updated weights for policy 0, policy_version 43403 (0.0010) -[2023-10-09 10:02:18,817][23468] Updated weights for policy 0, policy_version 43413 (0.0008) -[2023-10-09 10:02:19,178][23468] Updated weights for policy 0, policy_version 43423 (0.0009) -[2023-10-09 10:02:20,711][23469] Updated weights for policy 1, policy_version 43651 (0.0007) -[2023-10-09 10:02:21,072][23469] Updated weights for policy 1, policy_version 43661 (0.0009) -[2023-10-09 10:02:21,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 89161728. Throughput: 0: 1802.7, 1: 1789.7. Samples: 22297376. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-09 10:02:21,078][22500] Avg episode reward: [(0, '7.960'), (1, '7.270')] -[2023-10-09 10:02:21,444][23469] Updated weights for policy 1, policy_version 43671 (0.0008) -[2023-10-09 10:02:22,978][23468] Updated weights for policy 0, policy_version 43433 (0.0008) -[2023-10-09 10:02:23,356][23468] Updated weights for policy 0, policy_version 43443 (0.0008) -[2023-10-09 10:02:23,722][23468] Updated weights for policy 0, policy_version 43453 (0.0008) -[2023-10-09 10:02:25,088][23469] Updated weights for policy 1, policy_version 43681 (0.0009) -[2023-10-09 10:02:25,455][23469] Updated weights for policy 1, policy_version 43691 (0.0009) -[2023-10-09 10:02:25,827][23469] Updated weights for policy 1, policy_version 43701 (0.0007) -[2023-10-09 10:02:26,077][22500] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 89227264. Throughput: 0: 1786.5, 1: 1804.4. Samples: 22318856. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-09 10:02:26,078][22500] Avg episode reward: [(0, '8.110'), (1, '7.010')] -[2023-10-09 10:02:26,190][23469] Updated weights for policy 1, policy_version 43711 (0.0007) -[2023-10-09 10:02:27,512][23468] Updated weights for policy 0, policy_version 43463 (0.0008) -[2023-10-09 10:02:27,891][23468] Updated weights for policy 0, policy_version 43473 (0.0009) -[2023-10-09 10:02:28,258][23468] Updated weights for policy 0, policy_version 43483 (0.0007) -[2023-10-09 10:02:29,815][23469] Updated weights for policy 1, policy_version 43721 (0.0009) -[2023-10-09 10:02:30,190][23469] Updated weights for policy 1, policy_version 43731 (0.0008) -[2023-10-09 10:02:30,553][23469] Updated weights for policy 1, policy_version 43741 (0.0007) -[2023-10-09 10:02:31,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14106.9). Total num frames: 89325568. Throughput: 0: 1772.2, 1: 1802.3. Samples: 22339572. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-09 10:02:31,078][22500] Avg episode reward: [(0, '8.480'), (1, '7.380')] -[2023-10-09 10:02:32,035][23468] Updated weights for policy 0, policy_version 43493 (0.0008) -[2023-10-09 10:02:32,396][23468] Updated weights for policy 0, policy_version 43503 (0.0008) -[2023-10-09 10:02:32,771][23468] Updated weights for policy 0, policy_version 43513 (0.0009) -[2023-10-09 10:02:34,317][23469] Updated weights for policy 1, policy_version 43751 (0.0008) -[2023-10-09 10:02:34,695][23469] Updated weights for policy 1, policy_version 43761 (0.0007) -[2023-10-09 10:02:35,064][23469] Updated weights for policy 1, policy_version 43771 (0.0007) -[2023-10-09 10:02:36,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 89391104. Throughput: 0: 1774.0, 1: 1809.8. Samples: 22350770. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-09 10:02:36,078][22500] Avg episode reward: [(0, '8.770'), (1, '7.910')] -[2023-10-09 10:02:36,537][23468] Updated weights for policy 0, policy_version 43523 (0.0009) -[2023-10-09 10:02:36,915][23468] Updated weights for policy 0, policy_version 43533 (0.0011) -[2023-10-09 10:02:37,297][23468] Updated weights for policy 0, policy_version 43543 (0.0011) -[2023-10-09 10:02:38,801][23469] Updated weights for policy 1, policy_version 43781 (0.0008) -[2023-10-09 10:02:39,169][23469] Updated weights for policy 1, policy_version 43791 (0.0008) -[2023-10-09 10:02:39,543][23469] Updated weights for policy 1, policy_version 43801 (0.0008) -[2023-10-09 10:02:41,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 89456640. Throughput: 0: 1766.0, 1: 1810.5. Samples: 22371670. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-09 10:02:41,078][22500] Avg episode reward: [(0, '8.620'), (1, '8.220')] -[2023-10-09 10:02:41,134][23468] Updated weights for policy 0, policy_version 43553 (0.0011) -[2023-10-09 10:02:41,509][23468] Updated weights for policy 0, policy_version 43563 (0.0007) -[2023-10-09 10:02:41,891][23468] Updated weights for policy 0, policy_version 43573 (0.0007) -[2023-10-09 10:02:42,260][23468] Updated weights for policy 0, policy_version 43583 (0.0007) -[2023-10-09 10:02:43,189][23469] Updated weights for policy 1, policy_version 43811 (0.0007) -[2023-10-09 10:02:43,575][23469] Updated weights for policy 1, policy_version 43821 (0.0008) -[2023-10-09 10:02:43,940][23469] Updated weights for policy 1, policy_version 43831 (0.0008) -[2023-10-09 10:02:46,026][23468] Updated weights for policy 0, policy_version 43593 (0.0008) -[2023-10-09 10:02:46,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 89522176. Throughput: 0: 1785.1, 1: 1804.8. Samples: 22394000. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-09 10:02:46,078][22500] Avg episode reward: [(0, '8.830'), (1, '8.390')] -[2023-10-09 10:02:46,397][23468] Updated weights for policy 0, policy_version 43603 (0.0007) -[2023-10-09 10:02:46,770][23468] Updated weights for policy 0, policy_version 43613 (0.0007) -[2023-10-09 10:02:47,540][23469] Updated weights for policy 1, policy_version 43841 (0.0008) -[2023-10-09 10:02:47,906][23469] Updated weights for policy 1, policy_version 43851 (0.0009) -[2023-10-09 10:02:48,277][23469] Updated weights for policy 1, policy_version 43861 (0.0011) -[2023-10-09 10:02:48,640][23469] Updated weights for policy 1, policy_version 43871 (0.0010) -[2023-10-09 10:02:50,464][23468] Updated weights for policy 0, policy_version 43623 (0.0009) -[2023-10-09 10:02:50,843][23468] Updated weights for policy 0, policy_version 43633 (0.0007) -[2023-10-09 10:02:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 89587712. Throughput: 0: 1771.6, 1: 1807.1. Samples: 22403920. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-09 10:02:51,078][22500] Avg episode reward: [(0, '8.390'), (1, '8.550')] -[2023-10-09 10:02:51,078][23343] Saving new best policy, reward=8.550! -[2023-10-09 10:02:51,205][23468] Updated weights for policy 0, policy_version 43643 (0.0007) -[2023-10-09 10:02:52,577][23469] Updated weights for policy 1, policy_version 43881 (0.0008) -[2023-10-09 10:02:52,953][23469] Updated weights for policy 1, policy_version 43891 (0.0008) -[2023-10-09 10:02:53,327][23469] Updated weights for policy 1, policy_version 43901 (0.0008) -[2023-10-09 10:02:55,001][23468] Updated weights for policy 0, policy_version 43653 (0.0009) -[2023-10-09 10:02:55,375][23468] Updated weights for policy 0, policy_version 43663 (0.0007) -[2023-10-09 10:02:55,745][23468] Updated weights for policy 0, policy_version 43673 (0.0007) -[2023-10-09 10:02:56,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 89686016. Throughput: 0: 1786.4, 1: 1803.6. Samples: 22426364. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 10:02:56,078][22500] Avg episode reward: [(0, '8.830'), (1, '7.850')] -[2023-10-09 10:02:57,021][23469] Updated weights for policy 1, policy_version 43911 (0.0008) -[2023-10-09 10:02:57,386][23469] Updated weights for policy 1, policy_version 43921 (0.0008) -[2023-10-09 10:02:57,763][23469] Updated weights for policy 1, policy_version 43931 (0.0011) -[2023-10-09 10:02:59,479][23468] Updated weights for policy 0, policy_version 43683 (0.0007) -[2023-10-09 10:02:59,853][23468] Updated weights for policy 0, policy_version 43693 (0.0008) -[2023-10-09 10:03:00,223][23468] Updated weights for policy 0, policy_version 43703 (0.0009) -[2023-10-09 10:03:01,078][22500] Fps is (10 sec: 16383.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 89751552. Throughput: 0: 1784.1, 1: 1802.6. Samples: 22447736. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 10:03:01,079][22500] Avg episode reward: [(0, '9.270'), (1, '8.350')] -[2023-10-09 10:03:01,089][23265] Saving new best policy, reward=9.270! -[2023-10-09 10:03:01,553][23469] Updated weights for policy 1, policy_version 43941 (0.0007) -[2023-10-09 10:03:01,952][23469] Updated weights for policy 1, policy_version 43951 (0.0009) -[2023-10-09 10:03:02,326][23469] Updated weights for policy 1, policy_version 43961 (0.0008) -[2023-10-09 10:03:04,009][23468] Updated weights for policy 0, policy_version 43713 (0.0010) -[2023-10-09 10:03:04,384][23468] Updated weights for policy 0, policy_version 43723 (0.0008) -[2023-10-09 10:03:04,749][23468] Updated weights for policy 0, policy_version 43733 (0.0008) -[2023-10-09 10:03:05,124][23468] Updated weights for policy 0, policy_version 43743 (0.0008) -[2023-10-09 10:03:05,901][23469] Updated weights for policy 1, policy_version 43971 (0.0009) -[2023-10-09 10:03:06,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 89817088. Throughput: 0: 1779.9, 1: 1798.6. Samples: 22458406. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 10:03:06,078][22500] Avg episode reward: [(0, '8.940'), (1, '7.730')] -[2023-10-09 10:03:06,273][23469] Updated weights for policy 1, policy_version 43981 (0.0009) -[2023-10-09 10:03:06,663][23469] Updated weights for policy 1, policy_version 43991 (0.0010) -[2023-10-09 10:03:08,849][23468] Updated weights for policy 0, policy_version 43753 (0.0008) -[2023-10-09 10:03:09,219][23468] Updated weights for policy 0, policy_version 43763 (0.0007) -[2023-10-09 10:03:09,583][23468] Updated weights for policy 0, policy_version 43773 (0.0007) -[2023-10-09 10:03:10,334][23469] Updated weights for policy 1, policy_version 44001 (0.0009) -[2023-10-09 10:03:10,711][23469] Updated weights for policy 1, policy_version 44011 (0.0009) -[2023-10-09 10:03:11,077][22500] Fps is (10 sec: 13107.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 89882624. Throughput: 0: 1788.0, 1: 1796.5. Samples: 22480158. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 10:03:11,078][22500] Avg episode reward: [(0, '7.950'), (1, '7.520')] -[2023-10-09 10:03:11,079][23469] Updated weights for policy 1, policy_version 44021 (0.0009) -[2023-10-09 10:03:11,442][23469] Updated weights for policy 1, policy_version 44031 (0.0009) -[2023-10-09 10:03:13,417][23468] Updated weights for policy 0, policy_version 43783 (0.0008) -[2023-10-09 10:03:13,786][23468] Updated weights for policy 0, policy_version 43793 (0.0008) -[2023-10-09 10:03:14,163][23468] Updated weights for policy 0, policy_version 43803 (0.0009) -[2023-10-09 10:03:15,192][23469] Updated weights for policy 1, policy_version 44041 (0.0010) -[2023-10-09 10:03:15,559][23469] Updated weights for policy 1, policy_version 44051 (0.0011) -[2023-10-09 10:03:15,925][23469] Updated weights for policy 1, policy_version 44061 (0.0011) -[2023-10-09 10:03:16,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14106.9). Total num frames: 89980928. Throughput: 0: 1781.6, 1: 1798.2. Samples: 22500664. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 10:03:16,078][22500] Avg episode reward: [(0, '7.950'), (1, '6.870')] -[2023-10-09 10:03:17,687][23468] Updated weights for policy 0, policy_version 43813 (0.0008) -[2023-10-09 10:03:18,061][23468] Updated weights for policy 0, policy_version 43823 (0.0009) -[2023-10-09 10:03:18,444][23468] Updated weights for policy 0, policy_version 43833 (0.0011) -[2023-10-09 10:03:19,723][23469] Updated weights for policy 1, policy_version 44071 (0.0008) -[2023-10-09 10:03:20,090][23469] Updated weights for policy 1, policy_version 44081 (0.0007) -[2023-10-09 10:03:20,453][23469] Updated weights for policy 1, policy_version 44091 (0.0010) -[2023-10-09 10:03:21,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14106.9). Total num frames: 90046464. Throughput: 0: 1797.2, 1: 1786.8. Samples: 22512048. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 10:03:21,078][22500] Avg episode reward: [(0, '7.320'), (1, '7.190')] -[2023-10-09 10:03:22,328][23468] Updated weights for policy 0, policy_version 43843 (0.0009) -[2023-10-09 10:03:22,705][23468] Updated weights for policy 0, policy_version 43853 (0.0007) -[2023-10-09 10:03:23,077][23468] Updated weights for policy 0, policy_version 43863 (0.0007) -[2023-10-09 10:03:24,376][23469] Updated weights for policy 1, policy_version 44101 (0.0010) -[2023-10-09 10:03:24,741][23469] Updated weights for policy 1, policy_version 44111 (0.0007) -[2023-10-09 10:03:25,105][23469] Updated weights for policy 1, policy_version 44121 (0.0007) -[2023-10-09 10:03:26,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14745.5, 300 sec: 14106.9). Total num frames: 90112000. Throughput: 0: 1786.8, 1: 1798.9. Samples: 22533030. Policy #0 lag: (min: 7.0, avg: 12.4, max: 39.0) -[2023-10-09 10:03:26,079][22500] Avg episode reward: [(0, '7.500'), (1, '7.530')] -[2023-10-09 10:03:26,923][23468] Updated weights for policy 0, policy_version 43873 (0.0007) -[2023-10-09 10:03:27,311][23468] Updated weights for policy 0, policy_version 43883 (0.0010) -[2023-10-09 10:03:27,683][23468] Updated weights for policy 0, policy_version 43893 (0.0010) -[2023-10-09 10:03:28,058][23468] Updated weights for policy 0, policy_version 43903 (0.0008) -[2023-10-09 10:03:28,858][23469] Updated weights for policy 1, policy_version 44131 (0.0008) -[2023-10-09 10:03:29,223][23469] Updated weights for policy 1, policy_version 44141 (0.0007) -[2023-10-09 10:03:29,599][23469] Updated weights for policy 1, policy_version 44151 (0.0007) -[2023-10-09 10:03:31,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 90177536. Throughput: 0: 1790.3, 1: 1787.2. Samples: 22554986. Policy #0 lag: (min: 7.0, avg: 12.4, max: 39.0) -[2023-10-09 10:03:31,078][22500] Avg episode reward: [(0, '7.110'), (1, '7.790')] -[2023-10-09 10:03:31,579][23468] Updated weights for policy 0, policy_version 43913 (0.0008) -[2023-10-09 10:03:31,959][23468] Updated weights for policy 0, policy_version 43923 (0.0009) -[2023-10-09 10:03:32,327][23468] Updated weights for policy 0, policy_version 43933 (0.0008) -[2023-10-09 10:03:33,323][23469] Updated weights for policy 1, policy_version 44161 (0.0007) -[2023-10-09 10:03:33,689][23469] Updated weights for policy 1, policy_version 44171 (0.0008) -[2023-10-09 10:03:34,060][23469] Updated weights for policy 1, policy_version 44181 (0.0008) -[2023-10-09 10:03:34,436][23469] Updated weights for policy 1, policy_version 44191 (0.0007) -[2023-10-09 10:03:36,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 90243072. Throughput: 0: 1784.3, 1: 1803.7. Samples: 22565380. Policy #0 lag: (min: 7.0, avg: 12.4, max: 39.0) -[2023-10-09 10:03:36,078][22500] Avg episode reward: [(0, '7.200'), (1, '7.770')] -[2023-10-09 10:03:36,195][23468] Updated weights for policy 0, policy_version 43943 (0.0009) -[2023-10-09 10:03:36,570][23468] Updated weights for policy 0, policy_version 43953 (0.0007) -[2023-10-09 10:03:36,945][23468] Updated weights for policy 0, policy_version 43963 (0.0008) -[2023-10-09 10:03:38,088][23469] Updated weights for policy 1, policy_version 44201 (0.0010) -[2023-10-09 10:03:38,453][23469] Updated weights for policy 1, policy_version 44211 (0.0010) -[2023-10-09 10:03:38,822][23469] Updated weights for policy 1, policy_version 44221 (0.0010) -[2023-10-09 10:03:40,811][23468] Updated weights for policy 0, policy_version 43973 (0.0010) -[2023-10-09 10:03:41,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 90308608. Throughput: 0: 1781.6, 1: 1783.8. Samples: 22586810. Policy #0 lag: (min: 7.0, avg: 12.4, max: 39.0) -[2023-10-09 10:03:41,078][22500] Avg episode reward: [(0, '7.720'), (1, '7.620')] -[2023-10-09 10:03:41,178][23468] Updated weights for policy 0, policy_version 43983 (0.0009) -[2023-10-09 10:03:41,554][23468] Updated weights for policy 0, policy_version 43993 (0.0010) -[2023-10-09 10:03:42,763][23469] Updated weights for policy 1, policy_version 44231 (0.0008) -[2023-10-09 10:03:43,129][23469] Updated weights for policy 1, policy_version 44241 (0.0008) -[2023-10-09 10:03:43,499][23469] Updated weights for policy 1, policy_version 44251 (0.0009) -[2023-10-09 10:03:45,266][23468] Updated weights for policy 0, policy_version 44003 (0.0011) -[2023-10-09 10:03:45,645][23468] Updated weights for policy 0, policy_version 44013 (0.0008) -[2023-10-09 10:03:46,021][23468] Updated weights for policy 0, policy_version 44023 (0.0007) -[2023-10-09 10:03:46,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 90374144. Throughput: 0: 1802.3, 1: 1786.6. Samples: 22609236. Policy #0 lag: (min: 7.0, avg: 12.4, max: 39.0) -[2023-10-09 10:03:46,078][22500] Avg episode reward: [(0, '7.300'), (1, '7.180')] -[2023-10-09 10:03:47,142][23469] Updated weights for policy 1, policy_version 44261 (0.0009) -[2023-10-09 10:03:47,518][23469] Updated weights for policy 1, policy_version 44271 (0.0009) -[2023-10-09 10:03:47,894][23469] Updated weights for policy 1, policy_version 44281 (0.0008) -[2023-10-09 10:03:49,817][23468] Updated weights for policy 0, policy_version 44033 (0.0007) -[2023-10-09 10:03:50,183][23468] Updated weights for policy 0, policy_version 44043 (0.0009) -[2023-10-09 10:03:50,551][23468] Updated weights for policy 0, policy_version 44053 (0.0008) -[2023-10-09 10:03:50,922][23468] Updated weights for policy 0, policy_version 44063 (0.0010) -[2023-10-09 10:03:51,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 90472448. Throughput: 0: 1781.0, 1: 1793.4. Samples: 22619254. Policy #0 lag: (min: 7.0, avg: 12.4, max: 39.0) -[2023-10-09 10:03:51,078][22500] Avg episode reward: [(0, '7.500'), (1, '7.070')] -[2023-10-09 10:03:51,692][23469] Updated weights for policy 1, policy_version 44291 (0.0008) -[2023-10-09 10:03:52,061][23469] Updated weights for policy 1, policy_version 44301 (0.0012) -[2023-10-09 10:03:52,430][23469] Updated weights for policy 1, policy_version 44311 (0.0008) -[2023-10-09 10:03:54,732][23468] Updated weights for policy 0, policy_version 44073 (0.0009) -[2023-10-09 10:03:55,109][23468] Updated weights for policy 0, policy_version 44083 (0.0010) -[2023-10-09 10:03:55,478][23468] Updated weights for policy 0, policy_version 44093 (0.0008) -[2023-10-09 10:03:56,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 90537984. Throughput: 0: 1796.2, 1: 1789.2. Samples: 22641504. Policy #0 lag: (min: 24.0, avg: 49.2, max: 56.0) -[2023-10-09 10:03:56,078][22500] Avg episode reward: [(0, '6.830'), (1, '7.450')] -[2023-10-09 10:03:56,141][23469] Updated weights for policy 1, policy_version 44321 (0.0008) -[2023-10-09 10:03:56,513][23469] Updated weights for policy 1, policy_version 44331 (0.0008) -[2023-10-09 10:03:56,881][23469] Updated weights for policy 1, policy_version 44341 (0.0009) -[2023-10-09 10:03:57,250][23469] Updated weights for policy 1, policy_version 44351 (0.0008) -[2023-10-09 10:03:59,174][23468] Updated weights for policy 0, policy_version 44103 (0.0010) -[2023-10-09 10:03:59,557][23468] Updated weights for policy 0, policy_version 44113 (0.0007) -[2023-10-09 10:03:59,931][23468] Updated weights for policy 0, policy_version 44123 (0.0007) -[2023-10-09 10:04:00,932][23469] Updated weights for policy 1, policy_version 44361 (0.0008) -[2023-10-09 10:04:01,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 90603520. Throughput: 0: 1776.1, 1: 1815.2. Samples: 22662274. Policy #0 lag: (min: 24.0, avg: 49.2, max: 56.0) -[2023-10-09 10:04:01,079][22500] Avg episode reward: [(0, '7.490'), (1, '7.600')] -[2023-10-09 10:04:01,302][23469] Updated weights for policy 1, policy_version 44371 (0.0008) -[2023-10-09 10:04:01,669][23469] Updated weights for policy 1, policy_version 44381 (0.0008) -[2023-10-09 10:04:03,738][23468] Updated weights for policy 0, policy_version 44133 (0.0011) -[2023-10-09 10:04:04,108][23468] Updated weights for policy 0, policy_version 44143 (0.0010) -[2023-10-09 10:04:04,476][23468] Updated weights for policy 0, policy_version 44153 (0.0007) -[2023-10-09 10:04:05,418][23469] Updated weights for policy 1, policy_version 44391 (0.0009) -[2023-10-09 10:04:05,784][23469] Updated weights for policy 1, policy_version 44401 (0.0009) -[2023-10-09 10:04:06,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 90669056. Throughput: 0: 1793.9, 1: 1794.3. Samples: 22673520. Policy #0 lag: (min: 24.0, avg: 49.2, max: 56.0) -[2023-10-09 10:04:06,078][22500] Avg episode reward: [(0, '7.720'), (1, '7.640')] -[2023-10-09 10:04:06,158][23469] Updated weights for policy 1, policy_version 44411 (0.0010) -[2023-10-09 10:04:08,363][23468] Updated weights for policy 0, policy_version 44163 (0.0007) -[2023-10-09 10:04:08,735][23468] Updated weights for policy 0, policy_version 44173 (0.0007) -[2023-10-09 10:04:09,108][23468] Updated weights for policy 0, policy_version 44183 (0.0010) -[2023-10-09 10:04:09,833][23469] Updated weights for policy 1, policy_version 44421 (0.0009) -[2023-10-09 10:04:10,216][23469] Updated weights for policy 1, policy_version 44431 (0.0010) -[2023-10-09 10:04:10,579][23469] Updated weights for policy 1, policy_version 44441 (0.0009) -[2023-10-09 10:04:11,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 90767360. Throughput: 0: 1780.1, 1: 1812.5. Samples: 22694698. Policy #0 lag: (min: 24.0, avg: 49.2, max: 56.0) -[2023-10-09 10:04:11,078][22500] Avg episode reward: [(0, '8.010'), (1, '7.130')] -[2023-10-09 10:04:13,044][23468] Updated weights for policy 0, policy_version 44193 (0.0008) -[2023-10-09 10:04:13,424][23468] Updated weights for policy 0, policy_version 44203 (0.0011) -[2023-10-09 10:04:13,796][23468] Updated weights for policy 0, policy_version 44213 (0.0008) -[2023-10-09 10:04:14,173][23468] Updated weights for policy 0, policy_version 44223 (0.0008) -[2023-10-09 10:04:14,285][23469] Updated weights for policy 1, policy_version 44451 (0.0009) -[2023-10-09 10:04:14,654][23469] Updated weights for policy 1, policy_version 44461 (0.0007) -[2023-10-09 10:04:15,016][23469] Updated weights for policy 1, policy_version 44471 (0.0008) -[2023-10-09 10:04:16,078][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 90832896. Throughput: 0: 1763.3, 1: 1798.7. Samples: 22715276. Policy #0 lag: (min: 24.0, avg: 49.2, max: 56.0) -[2023-10-09 10:04:16,079][22500] Avg episode reward: [(0, '8.400'), (1, '7.230')] -[2023-10-09 10:04:16,090][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000044480_45547520.pth... -[2023-10-09 10:04:16,090][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000044224_45285376.pth... -[2023-10-09 10:04:16,126][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000042816_43843584.pth -[2023-10-09 10:04:16,128][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000042560_43581440.pth -[2023-10-09 10:04:17,794][23468] Updated weights for policy 0, policy_version 44233 (0.0009) -[2023-10-09 10:04:18,170][23468] Updated weights for policy 0, policy_version 44243 (0.0007) -[2023-10-09 10:04:18,539][23468] Updated weights for policy 0, policy_version 44253 (0.0008) -[2023-10-09 10:04:18,740][23469] Updated weights for policy 1, policy_version 44481 (0.0008) -[2023-10-09 10:04:19,105][23469] Updated weights for policy 1, policy_version 44491 (0.0007) -[2023-10-09 10:04:19,481][23469] Updated weights for policy 1, policy_version 44501 (0.0007) -[2023-10-09 10:04:19,852][23469] Updated weights for policy 1, policy_version 44511 (0.0007) -[2023-10-09 10:04:21,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 90898432. Throughput: 0: 1778.9, 1: 1809.9. Samples: 22726876. Policy #0 lag: (min: 24.0, avg: 49.2, max: 56.0) -[2023-10-09 10:04:21,079][22500] Avg episode reward: [(0, '8.080'), (1, '7.240')] -[2023-10-09 10:04:22,286][23468] Updated weights for policy 0, policy_version 44263 (0.0007) -[2023-10-09 10:04:22,649][23468] Updated weights for policy 0, policy_version 44273 (0.0007) -[2023-10-09 10:04:23,029][23468] Updated weights for policy 0, policy_version 44283 (0.0007) -[2023-10-09 10:04:23,550][23469] Updated weights for policy 1, policy_version 44521 (0.0008) -[2023-10-09 10:04:23,914][23469] Updated weights for policy 1, policy_version 44531 (0.0007) -[2023-10-09 10:04:24,283][23469] Updated weights for policy 1, policy_version 44541 (0.0007) -[2023-10-09 10:04:26,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 90963968. Throughput: 0: 1770.7, 1: 1803.5. Samples: 22747650. Policy #0 lag: (min: 24.0, avg: 49.2, max: 56.0) -[2023-10-09 10:04:26,078][22500] Avg episode reward: [(0, '8.190'), (1, '7.410')] -[2023-10-09 10:04:26,892][23468] Updated weights for policy 0, policy_version 44293 (0.0007) -[2023-10-09 10:04:27,284][23468] Updated weights for policy 0, policy_version 44303 (0.0007) -[2023-10-09 10:04:27,662][23468] Updated weights for policy 0, policy_version 44313 (0.0010) -[2023-10-09 10:04:28,053][23469] Updated weights for policy 1, policy_version 44551 (0.0009) -[2023-10-09 10:04:28,419][23469] Updated weights for policy 1, policy_version 44561 (0.0011) -[2023-10-09 10:04:28,788][23469] Updated weights for policy 1, policy_version 44571 (0.0010) -[2023-10-09 10:04:31,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 91029504. Throughput: 0: 1773.6, 1: 1798.5. Samples: 22769982. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 10:04:31,078][22500] Avg episode reward: [(0, '7.780'), (1, '8.070')] -[2023-10-09 10:04:31,272][23468] Updated weights for policy 0, policy_version 44323 (0.0008) -[2023-10-09 10:04:31,650][23468] Updated weights for policy 0, policy_version 44333 (0.0009) -[2023-10-09 10:04:32,023][23468] Updated weights for policy 0, policy_version 44343 (0.0008) -[2023-10-09 10:04:32,621][23469] Updated weights for policy 1, policy_version 44581 (0.0008) -[2023-10-09 10:04:33,022][23469] Updated weights for policy 1, policy_version 44591 (0.0009) -[2023-10-09 10:04:33,394][23469] Updated weights for policy 1, policy_version 44601 (0.0008) -[2023-10-09 10:04:35,844][23468] Updated weights for policy 0, policy_version 44353 (0.0007) -[2023-10-09 10:04:36,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 91095040. Throughput: 0: 1767.6, 1: 1794.4. Samples: 22779548. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 10:04:36,078][22500] Avg episode reward: [(0, '8.520'), (1, '8.480')] -[2023-10-09 10:04:36,216][23468] Updated weights for policy 0, policy_version 44363 (0.0010) -[2023-10-09 10:04:36,592][23468] Updated weights for policy 0, policy_version 44373 (0.0008) -[2023-10-09 10:04:36,958][23468] Updated weights for policy 0, policy_version 44383 (0.0007) -[2023-10-09 10:04:37,045][23469] Updated weights for policy 1, policy_version 44611 (0.0008) -[2023-10-09 10:04:37,424][23469] Updated weights for policy 1, policy_version 44621 (0.0010) -[2023-10-09 10:04:37,793][23469] Updated weights for policy 1, policy_version 44631 (0.0007) -[2023-10-09 10:04:40,721][23468] Updated weights for policy 0, policy_version 44393 (0.0007) -[2023-10-09 10:04:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 91160576. Throughput: 0: 1771.6, 1: 1793.5. Samples: 22801934. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 10:04:41,078][22500] Avg episode reward: [(0, '8.340'), (1, '8.340')] -[2023-10-09 10:04:41,104][23468] Updated weights for policy 0, policy_version 44403 (0.0010) -[2023-10-09 10:04:41,473][23468] Updated weights for policy 0, policy_version 44413 (0.0008) -[2023-10-09 10:04:41,668][23469] Updated weights for policy 1, policy_version 44641 (0.0009) -[2023-10-09 10:04:42,045][23469] Updated weights for policy 1, policy_version 44651 (0.0007) -[2023-10-09 10:04:42,421][23469] Updated weights for policy 1, policy_version 44661 (0.0007) -[2023-10-09 10:04:42,794][23469] Updated weights for policy 1, policy_version 44671 (0.0008) -[2023-10-09 10:04:45,216][23468] Updated weights for policy 0, policy_version 44423 (0.0009) -[2023-10-09 10:04:45,578][23468] Updated weights for policy 0, policy_version 44433 (0.0009) -[2023-10-09 10:04:45,956][23468] Updated weights for policy 0, policy_version 44443 (0.0009) -[2023-10-09 10:04:46,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 91226112. Throughput: 0: 1802.0, 1: 1792.6. Samples: 22824034. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 10:04:46,079][22500] Avg episode reward: [(0, '8.370'), (1, '7.570')] -[2023-10-09 10:04:46,610][23469] Updated weights for policy 1, policy_version 44681 (0.0007) -[2023-10-09 10:04:46,983][23469] Updated weights for policy 1, policy_version 44691 (0.0007) -[2023-10-09 10:04:47,342][23469] Updated weights for policy 1, policy_version 44701 (0.0009) -[2023-10-09 10:04:49,778][23468] Updated weights for policy 0, policy_version 44453 (0.0008) -[2023-10-09 10:04:50,146][23468] Updated weights for policy 0, policy_version 44463 (0.0009) -[2023-10-09 10:04:50,523][23468] Updated weights for policy 0, policy_version 44473 (0.0009) -[2023-10-09 10:04:51,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 91324416. Throughput: 0: 1780.7, 1: 1788.1. Samples: 22834116. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 10:04:51,079][22500] Avg episode reward: [(0, '7.610'), (1, '8.030')] -[2023-10-09 10:04:51,248][23469] Updated weights for policy 1, policy_version 44711 (0.0008) -[2023-10-09 10:04:51,613][23469] Updated weights for policy 1, policy_version 44721 (0.0008) -[2023-10-09 10:04:51,987][23469] Updated weights for policy 1, policy_version 44731 (0.0008) -[2023-10-09 10:04:54,203][23468] Updated weights for policy 0, policy_version 44483 (0.0009) -[2023-10-09 10:04:54,567][23468] Updated weights for policy 0, policy_version 44493 (0.0007) -[2023-10-09 10:04:54,931][23468] Updated weights for policy 0, policy_version 44503 (0.0007) -[2023-10-09 10:04:55,770][23469] Updated weights for policy 1, policy_version 44741 (0.0010) -[2023-10-09 10:04:56,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 91389952. Throughput: 0: 1801.6, 1: 1786.4. Samples: 22856160. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 10:04:56,079][22500] Avg episode reward: [(0, '8.020'), (1, '7.980')] -[2023-10-09 10:04:56,141][23469] Updated weights for policy 1, policy_version 44751 (0.0010) -[2023-10-09 10:04:56,517][23469] Updated weights for policy 1, policy_version 44761 (0.0007) -[2023-10-09 10:04:58,753][23468] Updated weights for policy 0, policy_version 44513 (0.0008) -[2023-10-09 10:04:59,122][23468] Updated weights for policy 0, policy_version 44523 (0.0009) -[2023-10-09 10:04:59,492][23468] Updated weights for policy 0, policy_version 44533 (0.0011) -[2023-10-09 10:04:59,869][23468] Updated weights for policy 0, policy_version 44543 (0.0010) -[2023-10-09 10:05:00,227][23469] Updated weights for policy 1, policy_version 44771 (0.0008) -[2023-10-09 10:05:00,589][23469] Updated weights for policy 1, policy_version 44781 (0.0010) -[2023-10-09 10:05:00,963][23469] Updated weights for policy 1, policy_version 44791 (0.0011) -[2023-10-09 10:05:01,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 91455488. Throughput: 0: 1782.4, 1: 1803.1. Samples: 22876622. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-09 10:05:01,078][22500] Avg episode reward: [(0, '8.250'), (1, '7.810')] -[2023-10-09 10:05:03,562][23468] Updated weights for policy 0, policy_version 44553 (0.0008) -[2023-10-09 10:05:03,918][23468] Updated weights for policy 0, policy_version 44563 (0.0010) -[2023-10-09 10:05:04,293][23468] Updated weights for policy 0, policy_version 44573 (0.0010) -[2023-10-09 10:05:04,855][23469] Updated weights for policy 1, policy_version 44801 (0.0007) -[2023-10-09 10:05:05,215][23469] Updated weights for policy 1, policy_version 44811 (0.0008) -[2023-10-09 10:05:05,589][23469] Updated weights for policy 1, policy_version 44821 (0.0009) -[2023-10-09 10:05:05,964][23469] Updated weights for policy 1, policy_version 44831 (0.0010) -[2023-10-09 10:05:06,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 91553792. Throughput: 0: 1805.4, 1: 1787.6. Samples: 22888560. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-09 10:05:06,079][22500] Avg episode reward: [(0, '8.520'), (1, '7.750')] -[2023-10-09 10:05:08,016][23468] Updated weights for policy 0, policy_version 44583 (0.0008) -[2023-10-09 10:05:08,392][23468] Updated weights for policy 0, policy_version 44593 (0.0007) -[2023-10-09 10:05:08,761][23468] Updated weights for policy 0, policy_version 44603 (0.0010) -[2023-10-09 10:05:09,687][23469] Updated weights for policy 1, policy_version 44841 (0.0008) -[2023-10-09 10:05:10,054][23469] Updated weights for policy 1, policy_version 44851 (0.0007) -[2023-10-09 10:05:10,421][23469] Updated weights for policy 1, policy_version 44861 (0.0007) -[2023-10-09 10:05:11,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 91619328. Throughput: 0: 1783.5, 1: 1799.1. Samples: 22908868. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-09 10:05:11,078][22500] Avg episode reward: [(0, '7.610'), (1, '7.360')] -[2023-10-09 10:05:12,544][23468] Updated weights for policy 0, policy_version 44613 (0.0010) -[2023-10-09 10:05:12,942][23468] Updated weights for policy 0, policy_version 44623 (0.0011) -[2023-10-09 10:05:13,316][23468] Updated weights for policy 0, policy_version 44633 (0.0009) -[2023-10-09 10:05:14,194][23469] Updated weights for policy 1, policy_version 44871 (0.0009) -[2023-10-09 10:05:14,566][23469] Updated weights for policy 1, policy_version 44881 (0.0007) -[2023-10-09 10:05:14,928][23469] Updated weights for policy 1, policy_version 44891 (0.0007) -[2023-10-09 10:05:16,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 91684864. Throughput: 0: 1782.1, 1: 1778.8. Samples: 22930222. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-09 10:05:16,078][22500] Avg episode reward: [(0, '7.470'), (1, '7.480')] -[2023-10-09 10:05:17,116][23468] Updated weights for policy 0, policy_version 44643 (0.0007) -[2023-10-09 10:05:17,498][23468] Updated weights for policy 0, policy_version 44653 (0.0008) -[2023-10-09 10:05:17,876][23468] Updated weights for policy 0, policy_version 44663 (0.0010) -[2023-10-09 10:05:18,789][23469] Updated weights for policy 1, policy_version 44901 (0.0008) -[2023-10-09 10:05:19,193][23469] Updated weights for policy 1, policy_version 44911 (0.0009) -[2023-10-09 10:05:19,563][23469] Updated weights for policy 1, policy_version 44921 (0.0011) -[2023-10-09 10:05:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 91750400. Throughput: 0: 1784.1, 1: 1802.7. Samples: 22940950. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-09 10:05:21,078][22500] Avg episode reward: [(0, '7.630'), (1, '7.180')] -[2023-10-09 10:05:21,646][23468] Updated weights for policy 0, policy_version 44673 (0.0011) -[2023-10-09 10:05:22,016][23468] Updated weights for policy 0, policy_version 44683 (0.0009) -[2023-10-09 10:05:22,382][23468] Updated weights for policy 0, policy_version 44693 (0.0008) -[2023-10-09 10:05:22,749][23468] Updated weights for policy 0, policy_version 44703 (0.0008) -[2023-10-09 10:05:23,225][23469] Updated weights for policy 1, policy_version 44931 (0.0010) -[2023-10-09 10:05:23,601][23469] Updated weights for policy 1, policy_version 44941 (0.0008) -[2023-10-09 10:05:23,963][23469] Updated weights for policy 1, policy_version 44951 (0.0007) -[2023-10-09 10:05:26,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 91815936. Throughput: 0: 1786.3, 1: 1771.3. Samples: 22962028. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-09 10:05:26,078][22500] Avg episode reward: [(0, '7.640'), (1, '7.200')] -[2023-10-09 10:05:26,557][23468] Updated weights for policy 0, policy_version 44713 (0.0008) -[2023-10-09 10:05:26,932][23468] Updated weights for policy 0, policy_version 44723 (0.0010) -[2023-10-09 10:05:27,306][23468] Updated weights for policy 0, policy_version 44733 (0.0010) -[2023-10-09 10:05:27,699][23469] Updated weights for policy 1, policy_version 44961 (0.0008) -[2023-10-09 10:05:28,057][23469] Updated weights for policy 1, policy_version 44971 (0.0008) -[2023-10-09 10:05:28,433][23469] Updated weights for policy 1, policy_version 44981 (0.0009) -[2023-10-09 10:05:28,793][23469] Updated weights for policy 1, policy_version 44991 (0.0008) -[2023-10-09 10:05:30,889][23468] Updated weights for policy 0, policy_version 44743 (0.0010) -[2023-10-09 10:05:31,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 91881472. Throughput: 0: 1794.3, 1: 1776.2. Samples: 22984704. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-09 10:05:31,078][22500] Avg episode reward: [(0, '8.230'), (1, '7.590')] -[2023-10-09 10:05:31,259][23468] Updated weights for policy 0, policy_version 44753 (0.0008) -[2023-10-09 10:05:31,633][23468] Updated weights for policy 0, policy_version 44763 (0.0009) -[2023-10-09 10:05:32,566][23469] Updated weights for policy 1, policy_version 45001 (0.0007) -[2023-10-09 10:05:32,935][23469] Updated weights for policy 1, policy_version 45011 (0.0010) -[2023-10-09 10:05:33,305][23469] Updated weights for policy 1, policy_version 45021 (0.0008) -[2023-10-09 10:05:35,468][23468] Updated weights for policy 0, policy_version 44773 (0.0009) -[2023-10-09 10:05:35,840][23468] Updated weights for policy 0, policy_version 44783 (0.0008) -[2023-10-09 10:05:36,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 91947008. Throughput: 0: 1784.0, 1: 1779.2. Samples: 22994460. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:05:36,079][22500] Avg episode reward: [(0, '8.920'), (1, '7.660')] -[2023-10-09 10:05:36,215][23468] Updated weights for policy 0, policy_version 44793 (0.0007) -[2023-10-09 10:05:37,112][23469] Updated weights for policy 1, policy_version 45031 (0.0009) -[2023-10-09 10:05:37,469][23469] Updated weights for policy 1, policy_version 45041 (0.0011) -[2023-10-09 10:05:37,842][23469] Updated weights for policy 1, policy_version 45051 (0.0008) -[2023-10-09 10:05:40,045][23468] Updated weights for policy 0, policy_version 44803 (0.0007) -[2023-10-09 10:05:40,410][23468] Updated weights for policy 0, policy_version 44813 (0.0010) -[2023-10-09 10:05:40,778][23468] Updated weights for policy 0, policy_version 44823 (0.0007) -[2023-10-09 10:05:41,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 92012544. Throughput: 0: 1789.3, 1: 1778.0. Samples: 23016690. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:05:41,078][22500] Avg episode reward: [(0, '8.940'), (1, '7.980')] -[2023-10-09 10:05:41,655][23469] Updated weights for policy 1, policy_version 45061 (0.0009) -[2023-10-09 10:05:42,023][23469] Updated weights for policy 1, policy_version 45071 (0.0007) -[2023-10-09 10:05:42,389][23469] Updated weights for policy 1, policy_version 45081 (0.0007) -[2023-10-09 10:05:44,514][23468] Updated weights for policy 0, policy_version 44833 (0.0009) -[2023-10-09 10:05:44,886][23468] Updated weights for policy 0, policy_version 44843 (0.0010) -[2023-10-09 10:05:45,261][23468] Updated weights for policy 0, policy_version 44853 (0.0010) -[2023-10-09 10:05:45,643][23468] Updated weights for policy 0, policy_version 44863 (0.0009) -[2023-10-09 10:05:46,078][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 92110848. Throughput: 0: 1791.9, 1: 1788.5. Samples: 23037742. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:05:46,079][22500] Avg episode reward: [(0, '7.900'), (1, '7.630')] -[2023-10-09 10:05:46,142][23469] Updated weights for policy 1, policy_version 45091 (0.0007) -[2023-10-09 10:05:46,512][23469] Updated weights for policy 1, policy_version 45101 (0.0007) -[2023-10-09 10:05:46,877][23469] Updated weights for policy 1, policy_version 45111 (0.0007) -[2023-10-09 10:05:49,523][23468] Updated weights for policy 0, policy_version 44873 (0.0007) -[2023-10-09 10:05:49,903][23468] Updated weights for policy 0, policy_version 44883 (0.0007) -[2023-10-09 10:05:50,277][23468] Updated weights for policy 0, policy_version 44893 (0.0008) -[2023-10-09 10:05:50,563][23469] Updated weights for policy 1, policy_version 45121 (0.0008) -[2023-10-09 10:05:50,930][23469] Updated weights for policy 1, policy_version 45131 (0.0009) -[2023-10-09 10:05:51,078][22500] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 92176384. Throughput: 0: 1779.0, 1: 1773.2. Samples: 23048412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:05:51,079][22500] Avg episode reward: [(0, '7.570'), (1, '7.890')] -[2023-10-09 10:05:51,295][23469] Updated weights for policy 1, policy_version 45141 (0.0009) -[2023-10-09 10:05:51,679][23469] Updated weights for policy 1, policy_version 45151 (0.0008) -[2023-10-09 10:05:53,933][23468] Updated weights for policy 0, policy_version 44903 (0.0009) -[2023-10-09 10:05:54,294][23468] Updated weights for policy 0, policy_version 44913 (0.0011) -[2023-10-09 10:05:54,664][23468] Updated weights for policy 0, policy_version 44923 (0.0011) -[2023-10-09 10:05:55,409][23469] Updated weights for policy 1, policy_version 45161 (0.0009) -[2023-10-09 10:05:55,781][23469] Updated weights for policy 1, policy_version 45171 (0.0008) -[2023-10-09 10:05:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 92241920. Throughput: 0: 1799.0, 1: 1790.6. Samples: 23070400. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:05:56,078][22500] Avg episode reward: [(0, '8.220'), (1, '7.810')] -[2023-10-09 10:05:56,150][23469] Updated weights for policy 1, policy_version 45181 (0.0007) -[2023-10-09 10:05:58,483][23468] Updated weights for policy 0, policy_version 44933 (0.0010) -[2023-10-09 10:05:58,877][23468] Updated weights for policy 0, policy_version 44943 (0.0009) -[2023-10-09 10:05:59,250][23468] Updated weights for policy 0, policy_version 44953 (0.0009) -[2023-10-09 10:05:59,865][23469] Updated weights for policy 1, policy_version 45191 (0.0008) -[2023-10-09 10:06:00,235][23469] Updated weights for policy 1, policy_version 45201 (0.0007) -[2023-10-09 10:06:00,608][23469] Updated weights for policy 1, policy_version 45211 (0.0009) -[2023-10-09 10:06:01,078][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 92340224. Throughput: 0: 1780.1, 1: 1785.7. Samples: 23090686. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:06:01,078][22500] Avg episode reward: [(0, '8.300'), (1, '7.640')] -[2023-10-09 10:06:02,928][23468] Updated weights for policy 0, policy_version 44963 (0.0008) -[2023-10-09 10:06:03,300][23468] Updated weights for policy 0, policy_version 44973 (0.0008) -[2023-10-09 10:06:03,672][23468] Updated weights for policy 0, policy_version 44983 (0.0008) -[2023-10-09 10:06:04,487][23469] Updated weights for policy 1, policy_version 45221 (0.0007) -[2023-10-09 10:06:04,903][23469] Updated weights for policy 1, policy_version 45231 (0.0007) -[2023-10-09 10:06:05,264][23469] Updated weights for policy 1, policy_version 45241 (0.0008) -[2023-10-09 10:06:06,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 92405760. Throughput: 0: 1801.0, 1: 1791.0. Samples: 23102590. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-09 10:06:06,079][22500] Avg episode reward: [(0, '8.140'), (1, '8.020')] -[2023-10-09 10:06:07,459][23468] Updated weights for policy 0, policy_version 44993 (0.0010) -[2023-10-09 10:06:07,843][23468] Updated weights for policy 0, policy_version 45003 (0.0007) -[2023-10-09 10:06:08,214][23468] Updated weights for policy 0, policy_version 45013 (0.0007) -[2023-10-09 10:06:08,591][23468] Updated weights for policy 0, policy_version 45023 (0.0007) -[2023-10-09 10:06:09,166][23469] Updated weights for policy 1, policy_version 45251 (0.0010) -[2023-10-09 10:06:09,531][23469] Updated weights for policy 1, policy_version 45261 (0.0009) -[2023-10-09 10:06:09,906][23469] Updated weights for policy 1, policy_version 45271 (0.0009) -[2023-10-09 10:06:11,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 92471296. Throughput: 0: 1782.1, 1: 1792.3. Samples: 23122876. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-09 10:06:11,078][22500] Avg episode reward: [(0, '7.310'), (1, '7.730')] -[2023-10-09 10:06:12,285][23468] Updated weights for policy 0, policy_version 45033 (0.0009) -[2023-10-09 10:06:12,655][23468] Updated weights for policy 0, policy_version 45043 (0.0009) -[2023-10-09 10:06:13,039][23468] Updated weights for policy 0, policy_version 45053 (0.0009) -[2023-10-09 10:06:13,638][23469] Updated weights for policy 1, policy_version 45281 (0.0008) -[2023-10-09 10:06:13,995][23469] Updated weights for policy 1, policy_version 45291 (0.0010) -[2023-10-09 10:06:14,362][23469] Updated weights for policy 1, policy_version 45301 (0.0010) -[2023-10-09 10:06:14,735][23469] Updated weights for policy 1, policy_version 45311 (0.0009) -[2023-10-09 10:06:16,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 92536832. Throughput: 0: 1779.6, 1: 1773.9. Samples: 23144610. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-09 10:06:16,078][22500] Avg episode reward: [(0, '7.880'), (1, '7.800')] -[2023-10-09 10:06:16,087][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000045312_46399488.pth... -[2023-10-09 10:06:16,088][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000045056_46137344.pth... -[2023-10-09 10:06:16,122][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000043392_44433408.pth -[2023-10-09 10:06:16,128][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000043648_44695552.pth -[2023-10-09 10:06:16,840][23468] Updated weights for policy 0, policy_version 45063 (0.0008) -[2023-10-09 10:06:17,208][23468] Updated weights for policy 0, policy_version 45073 (0.0007) -[2023-10-09 10:06:17,587][23468] Updated weights for policy 0, policy_version 45083 (0.0007) -[2023-10-09 10:06:18,400][23469] Updated weights for policy 1, policy_version 45321 (0.0010) -[2023-10-09 10:06:18,768][23469] Updated weights for policy 1, policy_version 45331 (0.0010) -[2023-10-09 10:06:19,146][23469] Updated weights for policy 1, policy_version 45341 (0.0009) -[2023-10-09 10:06:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 92602368. Throughput: 0: 1777.7, 1: 1791.4. Samples: 23155070. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-09 10:06:21,078][22500] Avg episode reward: [(0, '8.320'), (1, '7.220')] -[2023-10-09 10:06:21,385][23468] Updated weights for policy 0, policy_version 45093 (0.0007) -[2023-10-09 10:06:21,758][23468] Updated weights for policy 0, policy_version 45103 (0.0009) -[2023-10-09 10:06:22,137][23468] Updated weights for policy 0, policy_version 45113 (0.0010) -[2023-10-09 10:06:23,086][23469] Updated weights for policy 1, policy_version 45351 (0.0009) -[2023-10-09 10:06:23,444][23469] Updated weights for policy 1, policy_version 45361 (0.0008) -[2023-10-09 10:06:23,817][23469] Updated weights for policy 1, policy_version 45371 (0.0010) -[2023-10-09 10:06:25,900][23468] Updated weights for policy 0, policy_version 45123 (0.0009) -[2023-10-09 10:06:26,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 92667904. Throughput: 0: 1779.2, 1: 1773.2. Samples: 23176550. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-09 10:06:26,078][22500] Avg episode reward: [(0, '8.620'), (1, '7.010')] -[2023-10-09 10:06:26,271][23468] Updated weights for policy 0, policy_version 45133 (0.0008) -[2023-10-09 10:06:26,636][23468] Updated weights for policy 0, policy_version 45143 (0.0007) -[2023-10-09 10:06:27,456][23469] Updated weights for policy 1, policy_version 45381 (0.0010) -[2023-10-09 10:06:27,828][23469] Updated weights for policy 1, policy_version 45391 (0.0009) -[2023-10-09 10:06:28,190][23469] Updated weights for policy 1, policy_version 45401 (0.0011) -[2023-10-09 10:06:30,371][23468] Updated weights for policy 0, policy_version 45153 (0.0009) -[2023-10-09 10:06:30,742][23468] Updated weights for policy 0, policy_version 45163 (0.0011) -[2023-10-09 10:06:31,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 92733440. Throughput: 0: 1806.3, 1: 1776.5. Samples: 23198966. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-09 10:06:31,078][22500] Avg episode reward: [(0, '8.640'), (1, '7.170')] -[2023-10-09 10:06:31,113][23468] Updated weights for policy 0, policy_version 45173 (0.0009) -[2023-10-09 10:06:31,482][23468] Updated weights for policy 0, policy_version 45183 (0.0008) -[2023-10-09 10:06:31,952][23469] Updated weights for policy 1, policy_version 45411 (0.0009) -[2023-10-09 10:06:32,332][23469] Updated weights for policy 1, policy_version 45421 (0.0008) -[2023-10-09 10:06:32,708][23469] Updated weights for policy 1, policy_version 45431 (0.0009) -[2023-10-09 10:06:35,288][23468] Updated weights for policy 0, policy_version 45193 (0.0010) -[2023-10-09 10:06:35,662][23468] Updated weights for policy 0, policy_version 45203 (0.0011) -[2023-10-09 10:06:36,040][23468] Updated weights for policy 0, policy_version 45213 (0.0010) -[2023-10-09 10:06:36,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 92798976. Throughput: 0: 1786.0, 1: 1778.5. Samples: 23208812. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-09 10:06:36,079][22500] Avg episode reward: [(0, '8.660'), (1, '7.290')] -[2023-10-09 10:06:36,472][23469] Updated weights for policy 1, policy_version 45441 (0.0009) -[2023-10-09 10:06:36,837][23469] Updated weights for policy 1, policy_version 45451 (0.0009) -[2023-10-09 10:06:37,208][23469] Updated weights for policy 1, policy_version 45461 (0.0011) -[2023-10-09 10:06:37,581][23469] Updated weights for policy 1, policy_version 45471 (0.0010) -[2023-10-09 10:06:39,789][23468] Updated weights for policy 0, policy_version 45223 (0.0010) -[2023-10-09 10:06:40,158][23468] Updated weights for policy 0, policy_version 45233 (0.0009) -[2023-10-09 10:06:40,540][23468] Updated weights for policy 0, policy_version 45243 (0.0008) -[2023-10-09 10:06:41,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 92897280. Throughput: 0: 1793.9, 1: 1776.7. Samples: 23231076. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-09 10:06:41,078][22500] Avg episode reward: [(0, '8.830'), (1, '7.910')] -[2023-10-09 10:06:41,218][23469] Updated weights for policy 1, policy_version 45481 (0.0007) -[2023-10-09 10:06:41,590][23469] Updated weights for policy 1, policy_version 45491 (0.0008) -[2023-10-09 10:06:41,950][23469] Updated weights for policy 1, policy_version 45501 (0.0011) -[2023-10-09 10:06:44,387][23468] Updated weights for policy 0, policy_version 45253 (0.0008) -[2023-10-09 10:06:44,774][23468] Updated weights for policy 0, policy_version 45263 (0.0007) -[2023-10-09 10:06:45,147][23468] Updated weights for policy 0, policy_version 45273 (0.0008) -[2023-10-09 10:06:45,688][23469] Updated weights for policy 1, policy_version 45511 (0.0011) -[2023-10-09 10:06:46,059][23469] Updated weights for policy 1, policy_version 45521 (0.0009) -[2023-10-09 10:06:46,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 92962816. Throughput: 0: 1785.6, 1: 1796.6. Samples: 23251886. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-09 10:06:46,078][22500] Avg episode reward: [(0, '8.460'), (1, '7.620')] -[2023-10-09 10:06:46,426][23469] Updated weights for policy 1, policy_version 45531 (0.0007) -[2023-10-09 10:06:48,886][23468] Updated weights for policy 0, policy_version 45283 (0.0009) -[2023-10-09 10:06:49,263][23468] Updated weights for policy 0, policy_version 45293 (0.0010) -[2023-10-09 10:06:49,629][23468] Updated weights for policy 0, policy_version 45303 (0.0007) -[2023-10-09 10:06:50,232][23469] Updated weights for policy 1, policy_version 45541 (0.0010) -[2023-10-09 10:06:50,615][23469] Updated weights for policy 1, policy_version 45551 (0.0011) -[2023-10-09 10:06:50,980][23469] Updated weights for policy 1, policy_version 45561 (0.0010) -[2023-10-09 10:06:51,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 93028352. Throughput: 0: 1793.0, 1: 1778.4. Samples: 23263304. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-09 10:06:51,078][22500] Avg episode reward: [(0, '8.190'), (1, '7.980')] -[2023-10-09 10:06:53,444][23468] Updated weights for policy 0, policy_version 45313 (0.0007) -[2023-10-09 10:06:53,824][23468] Updated weights for policy 0, policy_version 45323 (0.0007) -[2023-10-09 10:06:54,191][23468] Updated weights for policy 0, policy_version 45333 (0.0007) -[2023-10-09 10:06:54,567][23468] Updated weights for policy 0, policy_version 45343 (0.0008) -[2023-10-09 10:06:54,702][23469] Updated weights for policy 1, policy_version 45571 (0.0009) -[2023-10-09 10:06:55,073][23469] Updated weights for policy 1, policy_version 45581 (0.0007) -[2023-10-09 10:06:55,442][23469] Updated weights for policy 1, policy_version 45591 (0.0011) -[2023-10-09 10:06:56,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 93126656. Throughput: 0: 1784.0, 1: 1806.1. Samples: 23284430. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-09 10:06:56,078][22500] Avg episode reward: [(0, '8.840'), (1, '7.690')] -[2023-10-09 10:06:58,306][23468] Updated weights for policy 0, policy_version 45353 (0.0009) -[2023-10-09 10:06:58,677][23468] Updated weights for policy 0, policy_version 45363 (0.0007) -[2023-10-09 10:06:59,054][23468] Updated weights for policy 0, policy_version 45373 (0.0010) -[2023-10-09 10:06:59,309][23469] Updated weights for policy 1, policy_version 45601 (0.0008) -[2023-10-09 10:06:59,671][23469] Updated weights for policy 1, policy_version 45611 (0.0008) -[2023-10-09 10:07:00,041][23469] Updated weights for policy 1, policy_version 45621 (0.0007) -[2023-10-09 10:07:00,408][23469] Updated weights for policy 1, policy_version 45631 (0.0007) -[2023-10-09 10:07:01,078][22500] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 93192192. Throughput: 0: 1778.3, 1: 1794.1. Samples: 23305368. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-09 10:07:01,079][22500] Avg episode reward: [(0, '8.400'), (1, '7.500')] -[2023-10-09 10:07:02,656][23468] Updated weights for policy 0, policy_version 45383 (0.0010) -[2023-10-09 10:07:03,023][23468] Updated weights for policy 0, policy_version 45393 (0.0010) -[2023-10-09 10:07:03,403][23468] Updated weights for policy 0, policy_version 45403 (0.0010) -[2023-10-09 10:07:04,029][23469] Updated weights for policy 1, policy_version 45641 (0.0009) -[2023-10-09 10:07:04,409][23469] Updated weights for policy 1, policy_version 45651 (0.0009) -[2023-10-09 10:07:04,784][23469] Updated weights for policy 1, policy_version 45661 (0.0008) -[2023-10-09 10:07:06,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 93257728. Throughput: 0: 1788.1, 1: 1804.1. Samples: 23316720. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-09 10:07:06,079][22500] Avg episode reward: [(0, '8.790'), (1, '7.490')] -[2023-10-09 10:07:07,100][23468] Updated weights for policy 0, policy_version 45413 (0.0009) -[2023-10-09 10:07:07,469][23468] Updated weights for policy 0, policy_version 45423 (0.0010) -[2023-10-09 10:07:07,848][23468] Updated weights for policy 0, policy_version 45433 (0.0008) -[2023-10-09 10:07:08,606][23469] Updated weights for policy 1, policy_version 45671 (0.0008) -[2023-10-09 10:07:08,980][23469] Updated weights for policy 1, policy_version 45681 (0.0008) -[2023-10-09 10:07:09,359][23469] Updated weights for policy 1, policy_version 45691 (0.0009) -[2023-10-09 10:07:11,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 93323264. Throughput: 0: 1782.0, 1: 1792.7. Samples: 23337410. Policy #0 lag: (min: 9.0, avg: 20.2, max: 41.0) -[2023-10-09 10:07:11,079][22500] Avg episode reward: [(0, '7.910'), (1, '7.660')] -[2023-10-09 10:07:11,590][23468] Updated weights for policy 0, policy_version 45443 (0.0008) -[2023-10-09 10:07:11,961][23468] Updated weights for policy 0, policy_version 45453 (0.0008) -[2023-10-09 10:07:12,341][23468] Updated weights for policy 0, policy_version 45463 (0.0007) -[2023-10-09 10:07:13,246][23469] Updated weights for policy 1, policy_version 45701 (0.0008) -[2023-10-09 10:07:13,617][23469] Updated weights for policy 1, policy_version 45711 (0.0010) -[2023-10-09 10:07:13,988][23469] Updated weights for policy 1, policy_version 45721 (0.0011) -[2023-10-09 10:07:16,078][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 93388800. Throughput: 0: 1783.1, 1: 1792.1. Samples: 23359852. Policy #0 lag: (min: 9.0, avg: 20.2, max: 41.0) -[2023-10-09 10:07:16,078][22500] Avg episode reward: [(0, '8.630'), (1, '7.250')] -[2023-10-09 10:07:16,132][23468] Updated weights for policy 0, policy_version 45473 (0.0008) -[2023-10-09 10:07:16,503][23468] Updated weights for policy 0, policy_version 45483 (0.0010) -[2023-10-09 10:07:16,880][23468] Updated weights for policy 0, policy_version 45493 (0.0010) -[2023-10-09 10:07:17,254][23468] Updated weights for policy 0, policy_version 45503 (0.0009) -[2023-10-09 10:07:17,615][23469] Updated weights for policy 1, policy_version 45731 (0.0009) -[2023-10-09 10:07:17,982][23469] Updated weights for policy 1, policy_version 45741 (0.0009) -[2023-10-09 10:07:18,353][23469] Updated weights for policy 1, policy_version 45751 (0.0010) -[2023-10-09 10:07:21,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 93454336. Throughput: 0: 1780.5, 1: 1792.4. Samples: 23369594. Policy #0 lag: (min: 9.0, avg: 20.2, max: 41.0) -[2023-10-09 10:07:21,078][22500] Avg episode reward: [(0, '8.300'), (1, '7.290')] -[2023-10-09 10:07:21,161][23468] Updated weights for policy 0, policy_version 45513 (0.0009) -[2023-10-09 10:07:21,541][23468] Updated weights for policy 0, policy_version 45523 (0.0007) -[2023-10-09 10:07:21,913][23468] Updated weights for policy 0, policy_version 45533 (0.0009) -[2023-10-09 10:07:22,281][23469] Updated weights for policy 1, policy_version 45761 (0.0008) -[2023-10-09 10:07:22,651][23469] Updated weights for policy 1, policy_version 45771 (0.0007) -[2023-10-09 10:07:23,023][23469] Updated weights for policy 1, policy_version 45781 (0.0008) -[2023-10-09 10:07:23,395][23469] Updated weights for policy 1, policy_version 45791 (0.0008) -[2023-10-09 10:07:25,518][23468] Updated weights for policy 0, policy_version 45543 (0.0008) -[2023-10-09 10:07:25,893][23468] Updated weights for policy 0, policy_version 45553 (0.0010) -[2023-10-09 10:07:26,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 93519872. Throughput: 0: 1784.9, 1: 1791.3. Samples: 23392004. Policy #0 lag: (min: 9.0, avg: 20.2, max: 41.0) -[2023-10-09 10:07:26,078][22500] Avg episode reward: [(0, '8.860'), (1, '7.320')] -[2023-10-09 10:07:26,260][23468] Updated weights for policy 0, policy_version 45563 (0.0007) -[2023-10-09 10:07:27,162][23469] Updated weights for policy 1, policy_version 45801 (0.0007) -[2023-10-09 10:07:27,527][23469] Updated weights for policy 1, policy_version 45811 (0.0007) -[2023-10-09 10:07:27,899][23469] Updated weights for policy 1, policy_version 45821 (0.0008) -[2023-10-09 10:07:30,244][23468] Updated weights for policy 0, policy_version 45573 (0.0009) -[2023-10-09 10:07:30,628][23468] Updated weights for policy 0, policy_version 45583 (0.0011) -[2023-10-09 10:07:31,000][23468] Updated weights for policy 0, policy_version 45593 (0.0009) -[2023-10-09 10:07:31,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 93585408. Throughput: 0: 1803.9, 1: 1797.0. Samples: 23413928. Policy #0 lag: (min: 9.0, avg: 20.2, max: 41.0) -[2023-10-09 10:07:31,078][22500] Avg episode reward: [(0, '8.700'), (1, '7.970')] -[2023-10-09 10:07:31,744][23469] Updated weights for policy 1, policy_version 45831 (0.0010) -[2023-10-09 10:07:32,118][23469] Updated weights for policy 1, policy_version 45841 (0.0011) -[2023-10-09 10:07:32,486][23469] Updated weights for policy 1, policy_version 45851 (0.0008) -[2023-10-09 10:07:34,600][23468] Updated weights for policy 0, policy_version 45603 (0.0007) -[2023-10-09 10:07:34,988][23468] Updated weights for policy 0, policy_version 45613 (0.0011) -[2023-10-09 10:07:35,364][23468] Updated weights for policy 0, policy_version 45623 (0.0010) -[2023-10-09 10:07:36,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 93683712. Throughput: 0: 1785.9, 1: 1785.7. Samples: 23424026. Policy #0 lag: (min: 9.0, avg: 20.2, max: 41.0) -[2023-10-09 10:07:36,078][22500] Avg episode reward: [(0, '8.710'), (1, '8.160')] -[2023-10-09 10:07:36,253][23469] Updated weights for policy 1, policy_version 45861 (0.0007) -[2023-10-09 10:07:36,654][23469] Updated weights for policy 1, policy_version 45871 (0.0007) -[2023-10-09 10:07:37,028][23469] Updated weights for policy 1, policy_version 45881 (0.0008) -[2023-10-09 10:07:39,029][23468] Updated weights for policy 0, policy_version 45633 (0.0008) -[2023-10-09 10:07:39,396][23468] Updated weights for policy 0, policy_version 45643 (0.0007) -[2023-10-09 10:07:39,774][23468] Updated weights for policy 0, policy_version 45653 (0.0008) -[2023-10-09 10:07:40,147][23468] Updated weights for policy 0, policy_version 45663 (0.0007) -[2023-10-09 10:07:40,809][23469] Updated weights for policy 1, policy_version 45891 (0.0008) -[2023-10-09 10:07:41,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 93749248. Throughput: 0: 1804.9, 1: 1782.3. Samples: 23445854. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 10:07:41,078][22500] Avg episode reward: [(0, '9.100'), (1, '8.370')] -[2023-10-09 10:07:41,176][23469] Updated weights for policy 1, policy_version 45901 (0.0007) -[2023-10-09 10:07:41,557][23469] Updated weights for policy 1, policy_version 45911 (0.0008) -[2023-10-09 10:07:43,907][23468] Updated weights for policy 0, policy_version 45673 (0.0010) -[2023-10-09 10:07:44,282][23468] Updated weights for policy 0, policy_version 45683 (0.0007) -[2023-10-09 10:07:44,665][23468] Updated weights for policy 0, policy_version 45693 (0.0008) -[2023-10-09 10:07:45,249][23469] Updated weights for policy 1, policy_version 45921 (0.0008) -[2023-10-09 10:07:45,628][23469] Updated weights for policy 1, policy_version 45931 (0.0008) -[2023-10-09 10:07:46,001][23469] Updated weights for policy 1, policy_version 45941 (0.0008) -[2023-10-09 10:07:46,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 93814784. Throughput: 0: 1782.9, 1: 1797.2. Samples: 23466472. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 10:07:46,078][22500] Avg episode reward: [(0, '8.450'), (1, '8.010')] -[2023-10-09 10:07:46,372][23469] Updated weights for policy 1, policy_version 45951 (0.0007) -[2023-10-09 10:07:48,469][23468] Updated weights for policy 0, policy_version 45703 (0.0008) -[2023-10-09 10:07:48,839][23468] Updated weights for policy 0, policy_version 45713 (0.0009) -[2023-10-09 10:07:49,218][23468] Updated weights for policy 0, policy_version 45723 (0.0010) -[2023-10-09 10:07:50,018][23469] Updated weights for policy 1, policy_version 45961 (0.0007) -[2023-10-09 10:07:50,375][23469] Updated weights for policy 1, policy_version 45971 (0.0009) -[2023-10-09 10:07:50,745][23469] Updated weights for policy 1, policy_version 45981 (0.0010) -[2023-10-09 10:07:51,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 93913088. Throughput: 0: 1808.4, 1: 1783.2. Samples: 23478344. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 10:07:51,078][22500] Avg episode reward: [(0, '8.330'), (1, '8.360')] -[2023-10-09 10:07:52,962][23468] Updated weights for policy 0, policy_version 45733 (0.0008) -[2023-10-09 10:07:53,335][23468] Updated weights for policy 0, policy_version 45743 (0.0007) -[2023-10-09 10:07:53,709][23468] Updated weights for policy 0, policy_version 45753 (0.0007) -[2023-10-09 10:07:54,561][23469] Updated weights for policy 1, policy_version 45991 (0.0010) -[2023-10-09 10:07:54,933][23469] Updated weights for policy 1, policy_version 46001 (0.0008) -[2023-10-09 10:07:55,300][23469] Updated weights for policy 1, policy_version 46011 (0.0008) -[2023-10-09 10:07:56,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 93978624. Throughput: 0: 1782.1, 1: 1805.6. Samples: 23498852. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 10:07:56,078][22500] Avg episode reward: [(0, '7.880'), (1, '8.080')] -[2023-10-09 10:07:57,420][23468] Updated weights for policy 0, policy_version 45763 (0.0009) -[2023-10-09 10:07:57,793][23468] Updated weights for policy 0, policy_version 45773 (0.0008) -[2023-10-09 10:07:58,171][23468] Updated weights for policy 0, policy_version 45783 (0.0008) -[2023-10-09 10:07:58,895][23469] Updated weights for policy 1, policy_version 46021 (0.0008) -[2023-10-09 10:07:59,279][23469] Updated weights for policy 1, policy_version 46031 (0.0010) -[2023-10-09 10:07:59,647][23469] Updated weights for policy 1, policy_version 46041 (0.0008) -[2023-10-09 10:08:01,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 94044160. Throughput: 0: 1782.2, 1: 1786.4. Samples: 23520440. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 10:08:01,078][22500] Avg episode reward: [(0, '8.020'), (1, '7.750')] -[2023-10-09 10:08:02,024][23468] Updated weights for policy 0, policy_version 45793 (0.0008) -[2023-10-09 10:08:02,397][23468] Updated weights for policy 0, policy_version 45803 (0.0008) -[2023-10-09 10:08:02,777][23468] Updated weights for policy 0, policy_version 45813 (0.0009) -[2023-10-09 10:08:03,146][23468] Updated weights for policy 0, policy_version 45823 (0.0009) -[2023-10-09 10:08:03,413][23469] Updated weights for policy 1, policy_version 46051 (0.0008) -[2023-10-09 10:08:03,778][23469] Updated weights for policy 1, policy_version 46061 (0.0009) -[2023-10-09 10:08:04,154][23469] Updated weights for policy 1, policy_version 46071 (0.0010) -[2023-10-09 10:08:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 94109696. Throughput: 0: 1782.2, 1: 1807.1. Samples: 23531110. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 10:08:06,078][22500] Avg episode reward: [(0, '8.240'), (1, '7.920')] -[2023-10-09 10:08:07,056][23468] Updated weights for policy 0, policy_version 45833 (0.0008) -[2023-10-09 10:08:07,433][23468] Updated weights for policy 0, policy_version 45843 (0.0007) -[2023-10-09 10:08:07,798][23468] Updated weights for policy 0, policy_version 45853 (0.0009) -[2023-10-09 10:08:07,876][23469] Updated weights for policy 1, policy_version 46081 (0.0008) -[2023-10-09 10:08:08,247][23469] Updated weights for policy 1, policy_version 46091 (0.0009) -[2023-10-09 10:08:08,618][23469] Updated weights for policy 1, policy_version 46101 (0.0010) -[2023-10-09 10:08:08,984][23469] Updated weights for policy 1, policy_version 46111 (0.0008) -[2023-10-09 10:08:11,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 94175232. Throughput: 0: 1782.1, 1: 1787.5. Samples: 23552636. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 10:08:11,078][22500] Avg episode reward: [(0, '8.600'), (1, '7.390')] -[2023-10-09 10:08:11,434][23468] Updated weights for policy 0, policy_version 45863 (0.0008) -[2023-10-09 10:08:11,809][23468] Updated weights for policy 0, policy_version 45873 (0.0007) -[2023-10-09 10:08:12,182][23468] Updated weights for policy 0, policy_version 45883 (0.0009) -[2023-10-09 10:08:12,735][23469] Updated weights for policy 1, policy_version 46121 (0.0009) -[2023-10-09 10:08:13,115][23469] Updated weights for policy 1, policy_version 46131 (0.0009) -[2023-10-09 10:08:13,474][23469] Updated weights for policy 1, policy_version 46141 (0.0008) -[2023-10-09 10:08:16,078][22500] Fps is (10 sec: 13106.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 94240768. Throughput: 0: 1795.7, 1: 1786.7. Samples: 23575138. Policy #0 lag: (min: 2.0, avg: 3.2, max: 25.0) -[2023-10-09 10:08:16,079][22500] Avg episode reward: [(0, '8.300'), (1, '7.380')] -[2023-10-09 10:08:16,081][23468] Updated weights for policy 0, policy_version 45893 (0.0008) -[2023-10-09 10:08:16,090][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000046144_47251456.pth... -[2023-10-09 10:08:16,124][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000044480_45547520.pth -[2023-10-09 10:08:16,475][23468] Updated weights for policy 0, policy_version 45903 (0.0007) -[2023-10-09 10:08:16,846][23468] Updated weights for policy 0, policy_version 45913 (0.0007) -[2023-10-09 10:08:17,095][23469] Updated weights for policy 1, policy_version 46151 (0.0008) -[2023-10-09 10:08:17,105][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000045920_47022080.pth... -[2023-10-09 10:08:17,140][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000044224_45285376.pth -[2023-10-09 10:08:17,472][23469] Updated weights for policy 1, policy_version 46161 (0.0010) -[2023-10-09 10:08:17,843][23469] Updated weights for policy 1, policy_version 46171 (0.0010) -[2023-10-09 10:08:20,519][23468] Updated weights for policy 0, policy_version 45923 (0.0007) -[2023-10-09 10:08:20,889][23468] Updated weights for policy 0, policy_version 45933 (0.0008) -[2023-10-09 10:08:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 94306304. Throughput: 0: 1783.8, 1: 1794.3. Samples: 23585038. Policy #0 lag: (min: 2.0, avg: 3.2, max: 25.0) -[2023-10-09 10:08:21,079][22500] Avg episode reward: [(0, '8.470'), (1, '7.130')] -[2023-10-09 10:08:21,267][23468] Updated weights for policy 0, policy_version 45943 (0.0011) -[2023-10-09 10:08:21,719][23469] Updated weights for policy 1, policy_version 46181 (0.0008) -[2023-10-09 10:08:22,084][23469] Updated weights for policy 1, policy_version 46191 (0.0008) -[2023-10-09 10:08:22,447][23469] Updated weights for policy 1, policy_version 46201 (0.0010) -[2023-10-09 10:08:24,962][23468] Updated weights for policy 0, policy_version 45953 (0.0010) -[2023-10-09 10:08:25,330][23468] Updated weights for policy 0, policy_version 45963 (0.0009) -[2023-10-09 10:08:25,705][23468] Updated weights for policy 0, policy_version 45973 (0.0009) -[2023-10-09 10:08:26,077][22500] Fps is (10 sec: 13107.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 94371840. Throughput: 0: 1789.2, 1: 1797.3. Samples: 23607250. Policy #0 lag: (min: 2.0, avg: 3.2, max: 25.0) -[2023-10-09 10:08:26,078][22500] Avg episode reward: [(0, '8.240'), (1, '7.270')] -[2023-10-09 10:08:26,082][23468] Updated weights for policy 0, policy_version 45983 (0.0008) -[2023-10-09 10:08:26,236][23469] Updated weights for policy 1, policy_version 46211 (0.0008) -[2023-10-09 10:08:26,648][23469] Updated weights for policy 1, policy_version 46221 (0.0008) -[2023-10-09 10:08:27,015][23469] Updated weights for policy 1, policy_version 46231 (0.0007) -[2023-10-09 10:08:29,841][23468] Updated weights for policy 0, policy_version 45993 (0.0008) -[2023-10-09 10:08:30,212][23468] Updated weights for policy 0, policy_version 46003 (0.0010) -[2023-10-09 10:08:30,583][23468] Updated weights for policy 0, policy_version 46013 (0.0009) -[2023-10-09 10:08:30,703][23469] Updated weights for policy 1, policy_version 46241 (0.0008) -[2023-10-09 10:08:31,067][23469] Updated weights for policy 1, policy_version 46251 (0.0009) -[2023-10-09 10:08:31,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 94470144. Throughput: 0: 1794.9, 1: 1808.0. Samples: 23628602. Policy #0 lag: (min: 2.0, avg: 3.2, max: 25.0) -[2023-10-09 10:08:31,078][22500] Avg episode reward: [(0, '8.390'), (1, '8.340')] -[2023-10-09 10:08:31,433][23469] Updated weights for policy 1, policy_version 46261 (0.0008) -[2023-10-09 10:08:31,808][23469] Updated weights for policy 1, policy_version 46271 (0.0007) -[2023-10-09 10:08:34,481][23468] Updated weights for policy 0, policy_version 46023 (0.0007) -[2023-10-09 10:08:34,861][23468] Updated weights for policy 0, policy_version 46033 (0.0008) -[2023-10-09 10:08:35,235][23468] Updated weights for policy 0, policy_version 46043 (0.0009) -[2023-10-09 10:08:35,584][23469] Updated weights for policy 1, policy_version 46281 (0.0008) -[2023-10-09 10:08:35,951][23469] Updated weights for policy 1, policy_version 46291 (0.0007) -[2023-10-09 10:08:36,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 94535680. Throughput: 0: 1781.6, 1: 1797.0. Samples: 23639378. Policy #0 lag: (min: 2.0, avg: 3.2, max: 25.0) -[2023-10-09 10:08:36,078][22500] Avg episode reward: [(0, '8.420'), (1, '8.010')] -[2023-10-09 10:08:36,312][23469] Updated weights for policy 1, policy_version 46301 (0.0007) -[2023-10-09 10:08:39,129][23468] Updated weights for policy 0, policy_version 46053 (0.0009) -[2023-10-09 10:08:39,499][23468] Updated weights for policy 0, policy_version 46063 (0.0009) -[2023-10-09 10:08:39,877][23468] Updated weights for policy 0, policy_version 46073 (0.0008) -[2023-10-09 10:08:39,923][23469] Updated weights for policy 1, policy_version 46311 (0.0008) -[2023-10-09 10:08:40,291][23469] Updated weights for policy 1, policy_version 46321 (0.0008) -[2023-10-09 10:08:40,669][23469] Updated weights for policy 1, policy_version 46331 (0.0009) -[2023-10-09 10:08:41,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 94633984. Throughput: 0: 1800.9, 1: 1813.4. Samples: 23661498. Policy #0 lag: (min: 2.0, avg: 3.2, max: 25.0) -[2023-10-09 10:08:41,078][22500] Avg episode reward: [(0, '8.010'), (1, '8.010')] -[2023-10-09 10:08:43,573][23468] Updated weights for policy 0, policy_version 46083 (0.0008) -[2023-10-09 10:08:43,950][23468] Updated weights for policy 0, policy_version 46093 (0.0008) -[2023-10-09 10:08:44,317][23468] Updated weights for policy 0, policy_version 46103 (0.0008) -[2023-10-09 10:08:44,433][23469] Updated weights for policy 1, policy_version 46341 (0.0010) -[2023-10-09 10:08:44,804][23469] Updated weights for policy 1, policy_version 46351 (0.0007) -[2023-10-09 10:08:45,180][23469] Updated weights for policy 1, policy_version 46361 (0.0007) -[2023-10-09 10:08:46,078][22500] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 94699520. Throughput: 0: 1773.7, 1: 1800.7. Samples: 23681288. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 10:08:46,079][22500] Avg episode reward: [(0, '8.340'), (1, '7.150')] -[2023-10-09 10:08:48,004][23468] Updated weights for policy 0, policy_version 46113 (0.0008) -[2023-10-09 10:08:48,380][23468] Updated weights for policy 0, policy_version 46123 (0.0009) -[2023-10-09 10:08:48,757][23468] Updated weights for policy 0, policy_version 46133 (0.0009) -[2023-10-09 10:08:49,002][23469] Updated weights for policy 1, policy_version 46371 (0.0008) -[2023-10-09 10:08:49,130][23468] Updated weights for policy 0, policy_version 46143 (0.0008) -[2023-10-09 10:08:49,365][23469] Updated weights for policy 1, policy_version 46381 (0.0007) -[2023-10-09 10:08:49,735][23469] Updated weights for policy 1, policy_version 46391 (0.0008) -[2023-10-09 10:08:51,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 94765056. Throughput: 0: 1802.9, 1: 1807.9. Samples: 23693596. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 10:08:51,078][22500] Avg episode reward: [(0, '8.710'), (1, '7.610')] -[2023-10-09 10:08:52,905][23468] Updated weights for policy 0, policy_version 46153 (0.0009) -[2023-10-09 10:08:53,272][23468] Updated weights for policy 0, policy_version 46163 (0.0007) -[2023-10-09 10:08:53,554][23469] Updated weights for policy 1, policy_version 46401 (0.0007) -[2023-10-09 10:08:53,656][23468] Updated weights for policy 0, policy_version 46173 (0.0008) -[2023-10-09 10:08:53,921][23469] Updated weights for policy 1, policy_version 46411 (0.0009) -[2023-10-09 10:08:54,297][23469] Updated weights for policy 1, policy_version 46421 (0.0007) -[2023-10-09 10:08:54,665][23469] Updated weights for policy 1, policy_version 46431 (0.0008) -[2023-10-09 10:08:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 94830592. Throughput: 0: 1779.7, 1: 1791.4. Samples: 23713338. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 10:08:56,078][22500] Avg episode reward: [(0, '8.870'), (1, '7.450')] -[2023-10-09 10:08:57,284][23468] Updated weights for policy 0, policy_version 46183 (0.0008) -[2023-10-09 10:08:57,662][23468] Updated weights for policy 0, policy_version 46193 (0.0007) -[2023-10-09 10:08:58,039][23468] Updated weights for policy 0, policy_version 46203 (0.0009) -[2023-10-09 10:08:58,324][23469] Updated weights for policy 1, policy_version 46441 (0.0007) -[2023-10-09 10:08:58,708][23469] Updated weights for policy 1, policy_version 46451 (0.0009) -[2023-10-09 10:08:59,070][23469] Updated weights for policy 1, policy_version 46461 (0.0009) -[2023-10-09 10:09:01,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 94896128. Throughput: 0: 1776.1, 1: 1793.4. Samples: 23735768. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 10:09:01,079][22500] Avg episode reward: [(0, '9.410'), (1, '7.540')] -[2023-10-09 10:09:01,090][23265] Saving new best policy, reward=9.410! -[2023-10-09 10:09:02,038][23468] Updated weights for policy 0, policy_version 46213 (0.0009) -[2023-10-09 10:09:02,415][23468] Updated weights for policy 0, policy_version 46223 (0.0007) -[2023-10-09 10:09:02,781][23468] Updated weights for policy 0, policy_version 46233 (0.0008) -[2023-10-09 10:09:02,855][23469] Updated weights for policy 1, policy_version 46471 (0.0010) -[2023-10-09 10:09:03,217][23469] Updated weights for policy 1, policy_version 46481 (0.0009) -[2023-10-09 10:09:03,580][23469] Updated weights for policy 1, policy_version 46491 (0.0010) -[2023-10-09 10:09:06,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 94961664. Throughput: 0: 1772.0, 1: 1787.3. Samples: 23745206. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 10:09:06,078][22500] Avg episode reward: [(0, '8.740'), (1, '7.670')] -[2023-10-09 10:09:06,606][23468] Updated weights for policy 0, policy_version 46243 (0.0009) -[2023-10-09 10:09:06,972][23468] Updated weights for policy 0, policy_version 46253 (0.0010) -[2023-10-09 10:09:07,345][23468] Updated weights for policy 0, policy_version 46263 (0.0010) -[2023-10-09 10:09:07,551][23469] Updated weights for policy 1, policy_version 46501 (0.0009) -[2023-10-09 10:09:07,908][23469] Updated weights for policy 1, policy_version 46511 (0.0009) -[2023-10-09 10:09:08,285][23469] Updated weights for policy 1, policy_version 46521 (0.0009) -[2023-10-09 10:09:11,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 95027200. Throughput: 0: 1768.9, 1: 1782.0. Samples: 23767044. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 10:09:11,079][22500] Avg episode reward: [(0, '8.500'), (1, '7.920')] -[2023-10-09 10:09:11,124][23468] Updated weights for policy 0, policy_version 46273 (0.0008) -[2023-10-09 10:09:11,509][23468] Updated weights for policy 0, policy_version 46283 (0.0008) -[2023-10-09 10:09:11,875][23468] Updated weights for policy 0, policy_version 46293 (0.0008) -[2023-10-09 10:09:12,145][23469] Updated weights for policy 1, policy_version 46531 (0.0008) -[2023-10-09 10:09:12,250][23468] Updated weights for policy 0, policy_version 46303 (0.0008) -[2023-10-09 10:09:12,547][23469] Updated weights for policy 1, policy_version 46541 (0.0011) -[2023-10-09 10:09:12,910][23469] Updated weights for policy 1, policy_version 46551 (0.0010) -[2023-10-09 10:09:16,004][23468] Updated weights for policy 0, policy_version 46313 (0.0010) -[2023-10-09 10:09:16,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.6, 300 sec: 14218.0). Total num frames: 95092736. Throughput: 0: 1789.9, 1: 1776.3. Samples: 23789082. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 10:09:16,078][22500] Avg episode reward: [(0, '8.210'), (1, '7.950')] -[2023-10-09 10:09:16,390][23468] Updated weights for policy 0, policy_version 46323 (0.0009) -[2023-10-09 10:09:16,762][23468] Updated weights for policy 0, policy_version 46333 (0.0009) -[2023-10-09 10:09:16,795][23469] Updated weights for policy 1, policy_version 46561 (0.0009) -[2023-10-09 10:09:17,165][23469] Updated weights for policy 1, policy_version 46571 (0.0008) -[2023-10-09 10:09:17,532][23469] Updated weights for policy 1, policy_version 46581 (0.0007) -[2023-10-09 10:09:17,900][23469] Updated weights for policy 1, policy_version 46591 (0.0007) -[2023-10-09 10:09:20,443][23468] Updated weights for policy 0, policy_version 46343 (0.0010) -[2023-10-09 10:09:20,817][23468] Updated weights for policy 0, policy_version 46353 (0.0009) -[2023-10-09 10:09:21,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 95158272. Throughput: 0: 1770.2, 1: 1775.0. Samples: 23798914. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:09:21,078][22500] Avg episode reward: [(0, '8.410'), (1, '7.210')] -[2023-10-09 10:09:21,188][23468] Updated weights for policy 0, policy_version 46363 (0.0009) -[2023-10-09 10:09:21,739][23469] Updated weights for policy 1, policy_version 46601 (0.0010) -[2023-10-09 10:09:22,108][23469] Updated weights for policy 1, policy_version 46611 (0.0011) -[2023-10-09 10:09:22,482][23469] Updated weights for policy 1, policy_version 46621 (0.0007) -[2023-10-09 10:09:24,956][23468] Updated weights for policy 0, policy_version 46373 (0.0007) -[2023-10-09 10:09:25,318][23468] Updated weights for policy 0, policy_version 46383 (0.0008) -[2023-10-09 10:09:25,689][23468] Updated weights for policy 0, policy_version 46393 (0.0011) -[2023-10-09 10:09:26,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 95256576. Throughput: 0: 1788.1, 1: 1769.0. Samples: 23821568. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:09:26,078][22500] Avg episode reward: [(0, '8.470'), (1, '7.700')] -[2023-10-09 10:09:26,190][23469] Updated weights for policy 1, policy_version 46631 (0.0009) -[2023-10-09 10:09:26,551][23469] Updated weights for policy 1, policy_version 46641 (0.0007) -[2023-10-09 10:09:26,933][23469] Updated weights for policy 1, policy_version 46651 (0.0009) -[2023-10-09 10:09:29,483][23468] Updated weights for policy 0, policy_version 46403 (0.0008) -[2023-10-09 10:09:29,853][23468] Updated weights for policy 0, policy_version 46413 (0.0007) -[2023-10-09 10:09:30,222][23468] Updated weights for policy 0, policy_version 46423 (0.0009) -[2023-10-09 10:09:30,579][23469] Updated weights for policy 1, policy_version 46661 (0.0010) -[2023-10-09 10:09:30,948][23469] Updated weights for policy 1, policy_version 46671 (0.0010) -[2023-10-09 10:09:31,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 95322112. Throughput: 0: 1787.7, 1: 1793.6. Samples: 23842446. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:09:31,078][22500] Avg episode reward: [(0, '9.050'), (1, '7.770')] -[2023-10-09 10:09:31,320][23469] Updated weights for policy 1, policy_version 46681 (0.0009) -[2023-10-09 10:09:34,004][23468] Updated weights for policy 0, policy_version 46433 (0.0007) -[2023-10-09 10:09:34,369][23468] Updated weights for policy 0, policy_version 46443 (0.0008) -[2023-10-09 10:09:34,749][23468] Updated weights for policy 0, policy_version 46453 (0.0008) -[2023-10-09 10:09:35,043][23469] Updated weights for policy 1, policy_version 46691 (0.0009) -[2023-10-09 10:09:35,116][23468] Updated weights for policy 0, policy_version 46463 (0.0008) -[2023-10-09 10:09:35,413][23469] Updated weights for policy 1, policy_version 46701 (0.0008) -[2023-10-09 10:09:35,784][23469] Updated weights for policy 1, policy_version 46711 (0.0010) -[2023-10-09 10:09:36,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 95387648. Throughput: 0: 1783.5, 1: 1771.9. Samples: 23853592. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:09:36,078][22500] Avg episode reward: [(0, '8.550'), (1, '7.600')] -[2023-10-09 10:09:38,828][23468] Updated weights for policy 0, policy_version 46473 (0.0007) -[2023-10-09 10:09:39,211][23468] Updated weights for policy 0, policy_version 46483 (0.0007) -[2023-10-09 10:09:39,424][23469] Updated weights for policy 1, policy_version 46721 (0.0008) -[2023-10-09 10:09:39,579][23468] Updated weights for policy 0, policy_version 46493 (0.0007) -[2023-10-09 10:09:39,794][23469] Updated weights for policy 1, policy_version 46731 (0.0008) -[2023-10-09 10:09:40,155][23469] Updated weights for policy 1, policy_version 46741 (0.0008) -[2023-10-09 10:09:40,526][23469] Updated weights for policy 1, policy_version 46751 (0.0009) -[2023-10-09 10:09:41,078][22500] Fps is (10 sec: 16383.4, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 95485952. Throughput: 0: 1784.4, 1: 1801.0. Samples: 23874680. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:09:41,079][22500] Avg episode reward: [(0, '8.410'), (1, '7.640')] -[2023-10-09 10:09:43,422][23468] Updated weights for policy 0, policy_version 46503 (0.0007) -[2023-10-09 10:09:43,795][23468] Updated weights for policy 0, policy_version 46513 (0.0008) -[2023-10-09 10:09:44,155][23469] Updated weights for policy 1, policy_version 46761 (0.0009) -[2023-10-09 10:09:44,169][23468] Updated weights for policy 0, policy_version 46523 (0.0007) -[2023-10-09 10:09:44,524][23469] Updated weights for policy 1, policy_version 46771 (0.0008) -[2023-10-09 10:09:44,898][23469] Updated weights for policy 1, policy_version 46781 (0.0007) -[2023-10-09 10:09:46,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 95551488. Throughput: 0: 1771.0, 1: 1779.7. Samples: 23895548. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:09:46,078][22500] Avg episode reward: [(0, '8.110'), (1, '8.050')] -[2023-10-09 10:09:47,906][23468] Updated weights for policy 0, policy_version 46533 (0.0008) -[2023-10-09 10:09:48,280][23468] Updated weights for policy 0, policy_version 46543 (0.0010) -[2023-10-09 10:09:48,646][23468] Updated weights for policy 0, policy_version 46553 (0.0007) -[2023-10-09 10:09:48,700][23469] Updated weights for policy 1, policy_version 46791 (0.0007) -[2023-10-09 10:09:49,068][23469] Updated weights for policy 1, policy_version 46801 (0.0008) -[2023-10-09 10:09:49,443][23469] Updated weights for policy 1, policy_version 46811 (0.0008) -[2023-10-09 10:09:51,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 95617024. Throughput: 0: 1794.8, 1: 1805.2. Samples: 23907202. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:09:51,078][22500] Avg episode reward: [(0, '8.460'), (1, '7.530')] -[2023-10-09 10:09:52,317][23468] Updated weights for policy 0, policy_version 46563 (0.0009) -[2023-10-09 10:09:52,694][23468] Updated weights for policy 0, policy_version 46573 (0.0009) -[2023-10-09 10:09:53,070][23468] Updated weights for policy 0, policy_version 46583 (0.0008) -[2023-10-09 10:09:53,251][23469] Updated weights for policy 1, policy_version 46821 (0.0008) -[2023-10-09 10:09:53,605][23469] Updated weights for policy 1, policy_version 46831 (0.0007) -[2023-10-09 10:09:53,983][23469] Updated weights for policy 1, policy_version 46841 (0.0008) -[2023-10-09 10:09:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 95682560. Throughput: 0: 1780.7, 1: 1788.4. Samples: 23927654. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:09:56,078][22500] Avg episode reward: [(0, '8.120'), (1, '7.410')] -[2023-10-09 10:09:56,910][23468] Updated weights for policy 0, policy_version 46593 (0.0008) -[2023-10-09 10:09:57,277][23468] Updated weights for policy 0, policy_version 46603 (0.0009) -[2023-10-09 10:09:57,655][23468] Updated weights for policy 0, policy_version 46613 (0.0007) -[2023-10-09 10:09:57,831][23469] Updated weights for policy 1, policy_version 46851 (0.0008) -[2023-10-09 10:09:58,043][23468] Updated weights for policy 0, policy_version 46623 (0.0008) -[2023-10-09 10:09:58,234][23469] Updated weights for policy 1, policy_version 46861 (0.0008) -[2023-10-09 10:09:58,601][23469] Updated weights for policy 1, policy_version 46871 (0.0008) -[2023-10-09 10:10:01,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 95748096. Throughput: 0: 1781.8, 1: 1792.6. Samples: 23949928. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:10:01,079][22500] Avg episode reward: [(0, '7.910'), (1, '7.430')] -[2023-10-09 10:10:01,738][23468] Updated weights for policy 0, policy_version 46633 (0.0007) -[2023-10-09 10:10:02,116][23468] Updated weights for policy 0, policy_version 46643 (0.0008) -[2023-10-09 10:10:02,353][23469] Updated weights for policy 1, policy_version 46881 (0.0009) -[2023-10-09 10:10:02,490][23468] Updated weights for policy 0, policy_version 46653 (0.0008) -[2023-10-09 10:10:02,728][23469] Updated weights for policy 1, policy_version 46891 (0.0008) -[2023-10-09 10:10:03,090][23469] Updated weights for policy 1, policy_version 46901 (0.0007) -[2023-10-09 10:10:03,462][23469] Updated weights for policy 1, policy_version 46911 (0.0007) -[2023-10-09 10:10:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 95813632. Throughput: 0: 1778.5, 1: 1788.7. Samples: 23959438. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:10:06,078][22500] Avg episode reward: [(0, '7.860'), (1, '7.770')] -[2023-10-09 10:10:06,281][23468] Updated weights for policy 0, policy_version 46663 (0.0009) -[2023-10-09 10:10:06,656][23468] Updated weights for policy 0, policy_version 46673 (0.0007) -[2023-10-09 10:10:07,029][23468] Updated weights for policy 0, policy_version 46683 (0.0009) -[2023-10-09 10:10:07,318][23469] Updated weights for policy 1, policy_version 46921 (0.0007) -[2023-10-09 10:10:07,693][23469] Updated weights for policy 1, policy_version 46931 (0.0008) -[2023-10-09 10:10:08,062][23469] Updated weights for policy 1, policy_version 46941 (0.0010) -[2023-10-09 10:10:10,815][23468] Updated weights for policy 0, policy_version 46693 (0.0009) -[2023-10-09 10:10:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 95879168. Throughput: 0: 1773.8, 1: 1782.4. Samples: 23981596. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:10:11,078][22500] Avg episode reward: [(0, '8.160'), (1, '8.110')] -[2023-10-09 10:10:11,188][23468] Updated weights for policy 0, policy_version 46703 (0.0010) -[2023-10-09 10:10:11,551][23468] Updated weights for policy 0, policy_version 46713 (0.0008) -[2023-10-09 10:10:11,961][23469] Updated weights for policy 1, policy_version 46951 (0.0011) -[2023-10-09 10:10:12,339][23469] Updated weights for policy 1, policy_version 46961 (0.0011) -[2023-10-09 10:10:12,707][23469] Updated weights for policy 1, policy_version 46971 (0.0007) -[2023-10-09 10:10:15,276][23468] Updated weights for policy 0, policy_version 46723 (0.0008) -[2023-10-09 10:10:15,647][23468] Updated weights for policy 0, policy_version 46733 (0.0010) -[2023-10-09 10:10:16,029][23468] Updated weights for policy 0, policy_version 46743 (0.0011) -[2023-10-09 10:10:16,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 95944704. Throughput: 0: 1799.1, 1: 1788.0. Samples: 24003870. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:10:16,078][22500] Avg episode reward: [(0, '8.390'), (1, '7.880')] -[2023-10-09 10:10:16,086][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000046976_48103424.pth... -[2023-10-09 10:10:16,122][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000045312_46399488.pth -[2023-10-09 10:10:16,359][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000046752_47874048.pth... -[2023-10-09 10:10:16,388][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000045056_46137344.pth -[2023-10-09 10:10:16,521][23469] Updated weights for policy 1, policy_version 46981 (0.0008) -[2023-10-09 10:10:16,897][23469] Updated weights for policy 1, policy_version 46991 (0.0008) -[2023-10-09 10:10:17,254][23469] Updated weights for policy 1, policy_version 47001 (0.0008) -[2023-10-09 10:10:19,767][23468] Updated weights for policy 0, policy_version 46753 (0.0010) -[2023-10-09 10:10:20,135][23468] Updated weights for policy 0, policy_version 46763 (0.0009) -[2023-10-09 10:10:20,506][23468] Updated weights for policy 0, policy_version 46773 (0.0008) -[2023-10-09 10:10:20,829][23469] Updated weights for policy 1, policy_version 47011 (0.0008) -[2023-10-09 10:10:20,878][23468] Updated weights for policy 0, policy_version 46783 (0.0007) -[2023-10-09 10:10:21,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 96043008. Throughput: 0: 1780.0, 1: 1774.7. Samples: 24013552. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 10:10:21,079][22500] Avg episode reward: [(0, '8.280'), (1, '7.220')] -[2023-10-09 10:10:21,207][23469] Updated weights for policy 1, policy_version 47021 (0.0010) -[2023-10-09 10:10:21,574][23469] Updated weights for policy 1, policy_version 47031 (0.0009) -[2023-10-09 10:10:24,796][23468] Updated weights for policy 0, policy_version 46793 (0.0008) -[2023-10-09 10:10:25,171][23468] Updated weights for policy 0, policy_version 46803 (0.0007) -[2023-10-09 10:10:25,329][23469] Updated weights for policy 1, policy_version 47041 (0.0008) -[2023-10-09 10:10:25,542][23468] Updated weights for policy 0, policy_version 46813 (0.0008) -[2023-10-09 10:10:25,699][23469] Updated weights for policy 1, policy_version 47051 (0.0008) -[2023-10-09 10:10:26,069][23469] Updated weights for policy 1, policy_version 47061 (0.0007) -[2023-10-09 10:10:26,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 96108544. Throughput: 0: 1801.5, 1: 1787.3. Samples: 24036174. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 10:10:26,078][22500] Avg episode reward: [(0, '8.550'), (1, '7.220')] -[2023-10-09 10:10:26,439][23469] Updated weights for policy 1, policy_version 47071 (0.0007) -[2023-10-09 10:10:29,243][23468] Updated weights for policy 0, policy_version 46823 (0.0009) -[2023-10-09 10:10:29,620][23468] Updated weights for policy 0, policy_version 46833 (0.0009) -[2023-10-09 10:10:29,936][23469] Updated weights for policy 1, policy_version 47081 (0.0008) -[2023-10-09 10:10:29,989][23468] Updated weights for policy 0, policy_version 46843 (0.0007) -[2023-10-09 10:10:30,304][23469] Updated weights for policy 1, policy_version 47091 (0.0009) -[2023-10-09 10:10:30,670][23469] Updated weights for policy 1, policy_version 47101 (0.0011) -[2023-10-09 10:10:31,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 96206848. Throughput: 0: 1781.6, 1: 1782.4. Samples: 24055928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 10:10:31,078][22500] Avg episode reward: [(0, '8.670'), (1, '7.620')] -[2023-10-09 10:10:33,858][23468] Updated weights for policy 0, policy_version 46853 (0.0009) -[2023-10-09 10:10:34,249][23468] Updated weights for policy 0, policy_version 46863 (0.0010) -[2023-10-09 10:10:34,506][23469] Updated weights for policy 1, policy_version 47111 (0.0009) -[2023-10-09 10:10:34,629][23468] Updated weights for policy 0, policy_version 46873 (0.0007) -[2023-10-09 10:10:34,866][23469] Updated weights for policy 1, policy_version 47121 (0.0008) -[2023-10-09 10:10:35,237][23469] Updated weights for policy 1, policy_version 47131 (0.0008) -[2023-10-09 10:10:36,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 96272384. Throughput: 0: 1797.6, 1: 1789.8. Samples: 24068636. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 10:10:36,078][22500] Avg episode reward: [(0, '8.670'), (1, '7.710')] -[2023-10-09 10:10:38,295][23468] Updated weights for policy 0, policy_version 46883 (0.0010) -[2023-10-09 10:10:38,665][23468] Updated weights for policy 0, policy_version 46893 (0.0008) -[2023-10-09 10:10:38,822][23469] Updated weights for policy 1, policy_version 47141 (0.0008) -[2023-10-09 10:10:39,032][23468] Updated weights for policy 0, policy_version 46903 (0.0007) -[2023-10-09 10:10:39,183][23469] Updated weights for policy 1, policy_version 47151 (0.0007) -[2023-10-09 10:10:39,547][23469] Updated weights for policy 1, policy_version 47161 (0.0009) -[2023-10-09 10:10:41,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 96337920. Throughput: 0: 1784.2, 1: 1790.7. Samples: 24088526. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 10:10:41,078][22500] Avg episode reward: [(0, '8.720'), (1, '7.500')] -[2023-10-09 10:10:42,773][23468] Updated weights for policy 0, policy_version 46913 (0.0007) -[2023-10-09 10:10:43,146][23468] Updated weights for policy 0, policy_version 46923 (0.0007) -[2023-10-09 10:10:43,518][23468] Updated weights for policy 0, policy_version 46933 (0.0008) -[2023-10-09 10:10:43,543][23469] Updated weights for policy 1, policy_version 47171 (0.0009) -[2023-10-09 10:10:43,890][23468] Updated weights for policy 0, policy_version 46943 (0.0008) -[2023-10-09 10:10:43,941][23469] Updated weights for policy 1, policy_version 47181 (0.0007) -[2023-10-09 10:10:44,301][23469] Updated weights for policy 1, policy_version 47191 (0.0008) -[2023-10-09 10:10:46,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 96403456. Throughput: 0: 1778.0, 1: 1786.3. Samples: 24110320. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 10:10:46,079][22500] Avg episode reward: [(0, '8.250'), (1, '7.480')] -[2023-10-09 10:10:47,732][23468] Updated weights for policy 0, policy_version 46953 (0.0008) -[2023-10-09 10:10:47,900][23469] Updated weights for policy 1, policy_version 47201 (0.0010) -[2023-10-09 10:10:48,106][23468] Updated weights for policy 0, policy_version 46963 (0.0008) -[2023-10-09 10:10:48,272][23469] Updated weights for policy 1, policy_version 47211 (0.0007) -[2023-10-09 10:10:48,468][23468] Updated weights for policy 0, policy_version 46973 (0.0007) -[2023-10-09 10:10:48,636][23469] Updated weights for policy 1, policy_version 47221 (0.0007) -[2023-10-09 10:10:49,006][23469] Updated weights for policy 1, policy_version 47231 (0.0008) -[2023-10-09 10:10:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 96468992. Throughput: 0: 1788.8, 1: 1800.1. Samples: 24120936. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 10:10:51,078][22500] Avg episode reward: [(0, '8.270'), (1, '7.580')] -[2023-10-09 10:10:52,460][23468] Updated weights for policy 0, policy_version 46983 (0.0008) -[2023-10-09 10:10:52,827][23468] Updated weights for policy 0, policy_version 46993 (0.0008) -[2023-10-09 10:10:52,888][23469] Updated weights for policy 1, policy_version 47241 (0.0007) -[2023-10-09 10:10:53,205][23468] Updated weights for policy 0, policy_version 47003 (0.0007) -[2023-10-09 10:10:53,253][23469] Updated weights for policy 1, policy_version 47251 (0.0007) -[2023-10-09 10:10:53,623][23469] Updated weights for policy 1, policy_version 47261 (0.0007) -[2023-10-09 10:10:56,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 96534528. Throughput: 0: 1775.1, 1: 1797.8. Samples: 24142376. Policy #0 lag: (min: 31.0, avg: 32.1, max: 49.0) -[2023-10-09 10:10:56,078][22500] Avg episode reward: [(0, '8.740'), (1, '8.120')] -[2023-10-09 10:10:56,902][23468] Updated weights for policy 0, policy_version 47013 (0.0008) -[2023-10-09 10:10:57,273][23468] Updated weights for policy 0, policy_version 47023 (0.0008) -[2023-10-09 10:10:57,319][23469] Updated weights for policy 1, policy_version 47271 (0.0009) -[2023-10-09 10:10:57,637][23468] Updated weights for policy 0, policy_version 47033 (0.0007) -[2023-10-09 10:10:57,683][23469] Updated weights for policy 1, policy_version 47281 (0.0007) -[2023-10-09 10:10:58,043][23469] Updated weights for policy 1, policy_version 47291 (0.0008) -[2023-10-09 10:11:01,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 96600064. Throughput: 0: 1771.8, 1: 1804.3. Samples: 24164794. Policy #0 lag: (min: 31.0, avg: 32.1, max: 49.0) -[2023-10-09 10:11:01,079][22500] Avg episode reward: [(0, '8.950'), (1, '8.000')] -[2023-10-09 10:11:01,547][23468] Updated weights for policy 0, policy_version 47043 (0.0007) -[2023-10-09 10:11:01,829][23469] Updated weights for policy 1, policy_version 47301 (0.0008) -[2023-10-09 10:11:01,914][23468] Updated weights for policy 0, policy_version 47053 (0.0007) -[2023-10-09 10:11:02,186][23469] Updated weights for policy 1, policy_version 47311 (0.0007) -[2023-10-09 10:11:02,293][23468] Updated weights for policy 0, policy_version 47063 (0.0008) -[2023-10-09 10:11:02,553][23469] Updated weights for policy 1, policy_version 47321 (0.0009) -[2023-10-09 10:11:06,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 96665600. Throughput: 0: 1766.0, 1: 1809.1. Samples: 24174432. Policy #0 lag: (min: 31.0, avg: 32.1, max: 49.0) -[2023-10-09 10:11:06,078][22500] Avg episode reward: [(0, '9.380'), (1, '7.770')] -[2023-10-09 10:11:06,097][23468] Updated weights for policy 0, policy_version 47073 (0.0008) -[2023-10-09 10:11:06,439][23469] Updated weights for policy 1, policy_version 47331 (0.0008) -[2023-10-09 10:11:06,461][23468] Updated weights for policy 0, policy_version 47083 (0.0009) -[2023-10-09 10:11:06,804][23469] Updated weights for policy 1, policy_version 47341 (0.0009) -[2023-10-09 10:11:06,833][23468] Updated weights for policy 0, policy_version 47093 (0.0008) -[2023-10-09 10:11:07,167][23469] Updated weights for policy 1, policy_version 47351 (0.0009) -[2023-10-09 10:11:07,211][23468] Updated weights for policy 0, policy_version 47103 (0.0007) -[2023-10-09 10:11:10,931][23468] Updated weights for policy 0, policy_version 47113 (0.0009) -[2023-10-09 10:11:11,036][23469] Updated weights for policy 1, policy_version 47361 (0.0007) -[2023-10-09 10:11:11,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 96731136. Throughput: 0: 1766.1, 1: 1794.5. Samples: 24196400. Policy #0 lag: (min: 31.0, avg: 32.1, max: 49.0) -[2023-10-09 10:11:11,078][22500] Avg episode reward: [(0, '8.490'), (1, '7.690')] -[2023-10-09 10:11:11,303][23468] Updated weights for policy 0, policy_version 47123 (0.0007) -[2023-10-09 10:11:11,397][23469] Updated weights for policy 1, policy_version 47371 (0.0007) -[2023-10-09 10:11:11,680][23468] Updated weights for policy 0, policy_version 47133 (0.0007) -[2023-10-09 10:11:11,770][23469] Updated weights for policy 1, policy_version 47381 (0.0008) -[2023-10-09 10:11:12,136][23469] Updated weights for policy 1, policy_version 47391 (0.0008) -[2023-10-09 10:11:15,265][23468] Updated weights for policy 0, policy_version 47143 (0.0009) -[2023-10-09 10:11:15,633][23468] Updated weights for policy 0, policy_version 47153 (0.0009) -[2023-10-09 10:11:15,931][23469] Updated weights for policy 1, policy_version 47401 (0.0008) -[2023-10-09 10:11:16,014][23468] Updated weights for policy 0, policy_version 47163 (0.0008) -[2023-10-09 10:11:16,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 96796672. Throughput: 0: 1793.7, 1: 1813.3. Samples: 24218246. Policy #0 lag: (min: 31.0, avg: 32.1, max: 49.0) -[2023-10-09 10:11:16,078][22500] Avg episode reward: [(0, '8.690'), (1, '7.660')] -[2023-10-09 10:11:16,306][23469] Updated weights for policy 1, policy_version 47411 (0.0007) -[2023-10-09 10:11:16,671][23469] Updated weights for policy 1, policy_version 47421 (0.0007) -[2023-10-09 10:11:19,770][23468] Updated weights for policy 0, policy_version 47173 (0.0008) -[2023-10-09 10:11:20,162][23468] Updated weights for policy 0, policy_version 47183 (0.0007) -[2023-10-09 10:11:20,413][23469] Updated weights for policy 1, policy_version 47431 (0.0009) -[2023-10-09 10:11:20,537][23468] Updated weights for policy 0, policy_version 47193 (0.0007) -[2023-10-09 10:11:20,792][23469] Updated weights for policy 1, policy_version 47441 (0.0008) -[2023-10-09 10:11:21,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 96894976. Throughput: 0: 1770.2, 1: 1784.8. Samples: 24228612. Policy #0 lag: (min: 31.0, avg: 32.1, max: 49.0) -[2023-10-09 10:11:21,079][22500] Avg episode reward: [(0, '8.170'), (1, '7.690')] -[2023-10-09 10:11:21,156][23469] Updated weights for policy 1, policy_version 47451 (0.0007) -[2023-10-09 10:11:24,392][23468] Updated weights for policy 0, policy_version 47203 (0.0010) -[2023-10-09 10:11:24,765][23468] Updated weights for policy 0, policy_version 47213 (0.0008) -[2023-10-09 10:11:24,813][23469] Updated weights for policy 1, policy_version 47461 (0.0008) -[2023-10-09 10:11:25,137][23468] Updated weights for policy 0, policy_version 47223 (0.0008) -[2023-10-09 10:11:25,179][23469] Updated weights for policy 1, policy_version 47471 (0.0008) -[2023-10-09 10:11:25,541][23469] Updated weights for policy 1, policy_version 47481 (0.0008) -[2023-10-09 10:11:26,077][22500] Fps is (10 sec: 19661.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 96993280. Throughput: 0: 1793.4, 1: 1808.8. Samples: 24250624. Policy #0 lag: (min: 9.0, avg: 22.2, max: 41.0) -[2023-10-09 10:11:26,078][22500] Avg episode reward: [(0, '8.130'), (1, '8.010')] -[2023-10-09 10:11:28,987][23468] Updated weights for policy 0, policy_version 47233 (0.0010) -[2023-10-09 10:11:29,355][23468] Updated weights for policy 0, policy_version 47243 (0.0008) -[2023-10-09 10:11:29,373][23469] Updated weights for policy 1, policy_version 47491 (0.0008) -[2023-10-09 10:11:29,725][23468] Updated weights for policy 0, policy_version 47253 (0.0008) -[2023-10-09 10:11:29,796][23469] Updated weights for policy 1, policy_version 47501 (0.0008) -[2023-10-09 10:11:30,103][23468] Updated weights for policy 0, policy_version 47263 (0.0010) -[2023-10-09 10:11:30,164][23469] Updated weights for policy 1, policy_version 47511 (0.0008) -[2023-10-09 10:11:31,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 97058816. Throughput: 0: 1764.0, 1: 1786.3. Samples: 24270082. Policy #0 lag: (min: 9.0, avg: 22.2, max: 41.0) -[2023-10-09 10:11:31,079][22500] Avg episode reward: [(0, '8.010'), (1, '7.660')] -[2023-10-09 10:11:33,774][23469] Updated weights for policy 1, policy_version 47521 (0.0009) -[2023-10-09 10:11:34,040][23468] Updated weights for policy 0, policy_version 47273 (0.0008) -[2023-10-09 10:11:34,144][23469] Updated weights for policy 1, policy_version 47531 (0.0010) -[2023-10-09 10:11:34,414][23468] Updated weights for policy 0, policy_version 47283 (0.0009) -[2023-10-09 10:11:34,510][23469] Updated weights for policy 1, policy_version 47541 (0.0007) -[2023-10-09 10:11:34,773][23468] Updated weights for policy 0, policy_version 47293 (0.0007) -[2023-10-09 10:11:34,876][23469] Updated weights for policy 1, policy_version 47551 (0.0007) -[2023-10-09 10:11:36,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 97124352. Throughput: 0: 1784.3, 1: 1808.4. Samples: 24282608. Policy #0 lag: (min: 9.0, avg: 22.2, max: 41.0) -[2023-10-09 10:11:36,078][22500] Avg episode reward: [(0, '8.170'), (1, '8.160')] -[2023-10-09 10:11:38,565][23468] Updated weights for policy 0, policy_version 47303 (0.0008) -[2023-10-09 10:11:38,760][23469] Updated weights for policy 1, policy_version 47561 (0.0009) -[2023-10-09 10:11:38,942][23468] Updated weights for policy 0, policy_version 47313 (0.0009) -[2023-10-09 10:11:39,123][23469] Updated weights for policy 1, policy_version 47571 (0.0008) -[2023-10-09 10:11:39,313][23468] Updated weights for policy 0, policy_version 47323 (0.0009) -[2023-10-09 10:11:39,487][23469] Updated weights for policy 1, policy_version 47581 (0.0010) -[2023-10-09 10:11:41,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 97189888. Throughput: 0: 1772.4, 1: 1780.0. Samples: 24302234. Policy #0 lag: (min: 9.0, avg: 22.2, max: 41.0) -[2023-10-09 10:11:41,078][22500] Avg episode reward: [(0, '8.410'), (1, '7.870')] -[2023-10-09 10:11:43,157][23469] Updated weights for policy 1, policy_version 47591 (0.0007) -[2023-10-09 10:11:43,171][23468] Updated weights for policy 0, policy_version 47333 (0.0008) -[2023-10-09 10:11:43,514][23469] Updated weights for policy 1, policy_version 47601 (0.0008) -[2023-10-09 10:11:43,546][23468] Updated weights for policy 0, policy_version 47343 (0.0008) -[2023-10-09 10:11:43,889][23469] Updated weights for policy 1, policy_version 47611 (0.0007) -[2023-10-09 10:11:43,914][23468] Updated weights for policy 0, policy_version 47353 (0.0009) -[2023-10-09 10:11:46,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 97255424. Throughput: 0: 1762.8, 1: 1774.1. Samples: 24323952. Policy #0 lag: (min: 9.0, avg: 22.2, max: 41.0) -[2023-10-09 10:11:46,078][22500] Avg episode reward: [(0, '8.460'), (1, '8.240')] -[2023-10-09 10:11:47,716][23469] Updated weights for policy 1, policy_version 47621 (0.0007) -[2023-10-09 10:11:47,719][23468] Updated weights for policy 0, policy_version 47363 (0.0008) -[2023-10-09 10:11:48,081][23469] Updated weights for policy 1, policy_version 47631 (0.0007) -[2023-10-09 10:11:48,099][23468] Updated weights for policy 0, policy_version 47373 (0.0008) -[2023-10-09 10:11:48,454][23469] Updated weights for policy 1, policy_version 47641 (0.0008) -[2023-10-09 10:11:48,470][23468] Updated weights for policy 0, policy_version 47383 (0.0008) -[2023-10-09 10:11:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 97320960. Throughput: 0: 1776.4, 1: 1774.2. Samples: 24334208. Policy #0 lag: (min: 9.0, avg: 22.2, max: 41.0) -[2023-10-09 10:11:51,078][22500] Avg episode reward: [(0, '8.300'), (1, '7.820')] -[2023-10-09 10:11:52,183][23469] Updated weights for policy 1, policy_version 47651 (0.0008) -[2023-10-09 10:11:52,256][23468] Updated weights for policy 0, policy_version 47393 (0.0007) -[2023-10-09 10:11:52,550][23469] Updated weights for policy 1, policy_version 47661 (0.0007) -[2023-10-09 10:11:52,627][23468] Updated weights for policy 0, policy_version 47403 (0.0008) -[2023-10-09 10:11:52,915][23469] Updated weights for policy 1, policy_version 47671 (0.0009) -[2023-10-09 10:11:52,998][23468] Updated weights for policy 0, policy_version 47413 (0.0008) -[2023-10-09 10:11:53,365][23468] Updated weights for policy 0, policy_version 47423 (0.0008) -[2023-10-09 10:11:56,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 97386496. Throughput: 0: 1756.7, 1: 1786.0. Samples: 24355820. Policy #0 lag: (min: 9.0, avg: 22.2, max: 41.0) -[2023-10-09 10:11:56,079][22500] Avg episode reward: [(0, '8.420'), (1, '8.030')] -[2023-10-09 10:11:56,631][23469] Updated weights for policy 1, policy_version 47681 (0.0010) -[2023-10-09 10:11:56,998][23468] Updated weights for policy 0, policy_version 47433 (0.0007) -[2023-10-09 10:11:56,999][23469] Updated weights for policy 1, policy_version 47691 (0.0007) -[2023-10-09 10:11:57,367][23468] Updated weights for policy 0, policy_version 47443 (0.0008) -[2023-10-09 10:11:57,373][23469] Updated weights for policy 1, policy_version 47701 (0.0007) -[2023-10-09 10:11:57,737][23468] Updated weights for policy 0, policy_version 47453 (0.0007) -[2023-10-09 10:11:57,741][23469] Updated weights for policy 1, policy_version 47711 (0.0007) -[2023-10-09 10:12:01,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 97452032. Throughput: 0: 1759.7, 1: 1793.8. Samples: 24378154. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:12:01,078][22500] Avg episode reward: [(0, '9.100'), (1, '7.610')] -[2023-10-09 10:12:01,551][23469] Updated weights for policy 1, policy_version 47721 (0.0008) -[2023-10-09 10:12:01,630][23468] Updated weights for policy 0, policy_version 47463 (0.0008) -[2023-10-09 10:12:01,919][23469] Updated weights for policy 1, policy_version 47731 (0.0008) -[2023-10-09 10:12:01,999][23468] Updated weights for policy 0, policy_version 47473 (0.0008) -[2023-10-09 10:12:02,286][23469] Updated weights for policy 1, policy_version 47741 (0.0009) -[2023-10-09 10:12:02,362][23468] Updated weights for policy 0, policy_version 47483 (0.0008) -[2023-10-09 10:12:06,014][23469] Updated weights for policy 1, policy_version 47751 (0.0008) -[2023-10-09 10:12:06,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 97517568. Throughput: 0: 1748.4, 1: 1789.3. Samples: 24387806. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:12:06,078][22500] Avg episode reward: [(0, '9.040'), (1, '7.680')] -[2023-10-09 10:12:06,269][23468] Updated weights for policy 0, policy_version 47493 (0.0009) -[2023-10-09 10:12:06,375][23469] Updated weights for policy 1, policy_version 47761 (0.0008) -[2023-10-09 10:12:06,656][23468] Updated weights for policy 0, policy_version 47503 (0.0009) -[2023-10-09 10:12:06,741][23469] Updated weights for policy 1, policy_version 47771 (0.0007) -[2023-10-09 10:12:07,038][23468] Updated weights for policy 0, policy_version 47513 (0.0008) -[2023-10-09 10:12:10,384][23469] Updated weights for policy 1, policy_version 47781 (0.0009) -[2023-10-09 10:12:10,762][23469] Updated weights for policy 1, policy_version 47791 (0.0008) -[2023-10-09 10:12:10,819][23468] Updated weights for policy 0, policy_version 47523 (0.0010) -[2023-10-09 10:12:11,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 97583104. Throughput: 0: 1748.4, 1: 1787.8. Samples: 24409754. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:12:11,078][22500] Avg episode reward: [(0, '8.740'), (1, '7.430')] -[2023-10-09 10:12:11,128][23469] Updated weights for policy 1, policy_version 47801 (0.0010) -[2023-10-09 10:12:11,194][23468] Updated weights for policy 0, policy_version 47533 (0.0007) -[2023-10-09 10:12:11,570][23468] Updated weights for policy 0, policy_version 47543 (0.0008) -[2023-10-09 10:12:14,948][23469] Updated weights for policy 1, policy_version 47811 (0.0007) -[2023-10-09 10:12:15,335][23468] Updated weights for policy 0, policy_version 47553 (0.0010) -[2023-10-09 10:12:15,351][23469] Updated weights for policy 1, policy_version 47821 (0.0008) -[2023-10-09 10:12:15,703][23468] Updated weights for policy 0, policy_version 47563 (0.0008) -[2023-10-09 10:12:15,713][23469] Updated weights for policy 1, policy_version 47831 (0.0008) -[2023-10-09 10:12:16,077][23468] Updated weights for policy 0, policy_version 47573 (0.0008) -[2023-10-09 10:12:16,078][22500] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 97681408. Throughput: 0: 1782.6, 1: 1795.5. Samples: 24431098. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:12:16,079][22500] Avg episode reward: [(0, '8.540'), (1, '7.660')] -[2023-10-09 10:12:16,089][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000047840_48988160.pth... -[2023-10-09 10:12:16,118][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000046144_47251456.pth -[2023-10-09 10:12:16,449][23468] Updated weights for policy 0, policy_version 47583 (0.0011) -[2023-10-09 10:12:16,479][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000047584_48726016.pth... -[2023-10-09 10:12:16,507][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000045920_47022080.pth -[2023-10-09 10:12:19,336][23469] Updated weights for policy 1, policy_version 47841 (0.0007) -[2023-10-09 10:12:19,698][23469] Updated weights for policy 1, policy_version 47851 (0.0008) -[2023-10-09 10:12:20,064][23469] Updated weights for policy 1, policy_version 47861 (0.0008) -[2023-10-09 10:12:20,397][23468] Updated weights for policy 0, policy_version 47593 (0.0010) -[2023-10-09 10:12:20,434][23469] Updated weights for policy 1, policy_version 47871 (0.0008) -[2023-10-09 10:12:20,775][23468] Updated weights for policy 0, policy_version 47603 (0.0007) -[2023-10-09 10:12:21,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 97746944. Throughput: 0: 1754.4, 1: 1785.5. Samples: 24441902. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:12:21,078][22500] Avg episode reward: [(0, '8.370'), (1, '7.490')] -[2023-10-09 10:12:21,143][23468] Updated weights for policy 0, policy_version 47613 (0.0007) -[2023-10-09 10:12:24,285][23469] Updated weights for policy 1, policy_version 47881 (0.0010) -[2023-10-09 10:12:24,665][23469] Updated weights for policy 1, policy_version 47891 (0.0010) -[2023-10-09 10:12:24,911][23468] Updated weights for policy 0, policy_version 47623 (0.0008) -[2023-10-09 10:12:25,024][23469] Updated weights for policy 1, policy_version 47901 (0.0007) -[2023-10-09 10:12:25,279][23468] Updated weights for policy 0, policy_version 47633 (0.0009) -[2023-10-09 10:12:25,653][23468] Updated weights for policy 0, policy_version 47643 (0.0011) -[2023-10-09 10:12:26,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 97845248. Throughput: 0: 1782.4, 1: 1801.6. Samples: 24463518. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:12:26,078][22500] Avg episode reward: [(0, '8.660'), (1, '7.230')] -[2023-10-09 10:12:28,881][23469] Updated weights for policy 1, policy_version 47911 (0.0009) -[2023-10-09 10:12:29,253][23469] Updated weights for policy 1, policy_version 47921 (0.0010) -[2023-10-09 10:12:29,435][23468] Updated weights for policy 0, policy_version 47653 (0.0009) -[2023-10-09 10:12:29,615][23469] Updated weights for policy 1, policy_version 47931 (0.0008) -[2023-10-09 10:12:29,811][23468] Updated weights for policy 0, policy_version 47663 (0.0008) -[2023-10-09 10:12:30,191][23468] Updated weights for policy 0, policy_version 47673 (0.0007) -[2023-10-09 10:12:31,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 97910784. Throughput: 0: 1769.0, 1: 1786.0. Samples: 24483928. Policy #0 lag: (min: 31.0, avg: 32.5, max: 57.0) -[2023-10-09 10:12:31,079][22500] Avg episode reward: [(0, '8.900'), (1, '7.330')] -[2023-10-09 10:12:33,170][23469] Updated weights for policy 1, policy_version 47941 (0.0008) -[2023-10-09 10:12:33,550][23469] Updated weights for policy 1, policy_version 47951 (0.0009) -[2023-10-09 10:12:33,921][23469] Updated weights for policy 1, policy_version 47961 (0.0008) -[2023-10-09 10:12:33,998][23468] Updated weights for policy 0, policy_version 47683 (0.0009) -[2023-10-09 10:12:34,363][23468] Updated weights for policy 0, policy_version 47693 (0.0007) -[2023-10-09 10:12:34,746][23468] Updated weights for policy 0, policy_version 47703 (0.0009) -[2023-10-09 10:12:36,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 97976320. Throughput: 0: 1783.1, 1: 1799.5. Samples: 24495422. Policy #0 lag: (min: 31.0, avg: 32.5, max: 57.0) -[2023-10-09 10:12:36,078][22500] Avg episode reward: [(0, '8.970'), (1, '7.490')] -[2023-10-09 10:12:37,789][23469] Updated weights for policy 1, policy_version 47971 (0.0009) -[2023-10-09 10:12:38,150][23469] Updated weights for policy 1, policy_version 47981 (0.0010) -[2023-10-09 10:12:38,457][23468] Updated weights for policy 0, policy_version 47713 (0.0009) -[2023-10-09 10:12:38,524][23469] Updated weights for policy 1, policy_version 47991 (0.0009) -[2023-10-09 10:12:38,831][23468] Updated weights for policy 0, policy_version 47723 (0.0009) -[2023-10-09 10:12:39,198][23468] Updated weights for policy 0, policy_version 47733 (0.0010) -[2023-10-09 10:12:39,578][23468] Updated weights for policy 0, policy_version 47743 (0.0007) -[2023-10-09 10:12:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 98041856. Throughput: 0: 1778.0, 1: 1784.4. Samples: 24516126. Policy #0 lag: (min: 31.0, avg: 32.5, max: 57.0) -[2023-10-09 10:12:41,078][22500] Avg episode reward: [(0, '8.290'), (1, '8.150')] -[2023-10-09 10:12:42,243][23469] Updated weights for policy 1, policy_version 48001 (0.0008) -[2023-10-09 10:12:42,614][23469] Updated weights for policy 1, policy_version 48011 (0.0007) -[2023-10-09 10:12:42,980][23469] Updated weights for policy 1, policy_version 48021 (0.0008) -[2023-10-09 10:12:43,318][23468] Updated weights for policy 0, policy_version 47753 (0.0008) -[2023-10-09 10:12:43,350][23469] Updated weights for policy 1, policy_version 48031 (0.0008) -[2023-10-09 10:12:43,693][23468] Updated weights for policy 0, policy_version 47763 (0.0010) -[2023-10-09 10:12:44,074][23468] Updated weights for policy 0, policy_version 47773 (0.0011) -[2023-10-09 10:12:46,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 98107392. Throughput: 0: 1774.6, 1: 1785.0. Samples: 24538336. Policy #0 lag: (min: 31.0, avg: 32.5, max: 57.0) -[2023-10-09 10:12:46,078][22500] Avg episode reward: [(0, '8.660'), (1, '8.080')] -[2023-10-09 10:12:47,152][23469] Updated weights for policy 1, policy_version 48041 (0.0009) -[2023-10-09 10:12:47,518][23469] Updated weights for policy 1, policy_version 48051 (0.0008) -[2023-10-09 10:12:47,639][23468] Updated weights for policy 0, policy_version 47783 (0.0008) -[2023-10-09 10:12:47,888][23469] Updated weights for policy 1, policy_version 48061 (0.0008) -[2023-10-09 10:12:48,017][23468] Updated weights for policy 0, policy_version 47793 (0.0008) -[2023-10-09 10:12:48,391][23468] Updated weights for policy 0, policy_version 47803 (0.0007) -[2023-10-09 10:12:51,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 98172928. Throughput: 0: 1788.1, 1: 1785.0. Samples: 24548596. Policy #0 lag: (min: 31.0, avg: 32.5, max: 57.0) -[2023-10-09 10:12:51,078][22500] Avg episode reward: [(0, '8.440'), (1, '7.610')] -[2023-10-09 10:12:51,534][23469] Updated weights for policy 1, policy_version 48071 (0.0011) -[2023-10-09 10:12:51,894][23469] Updated weights for policy 1, policy_version 48081 (0.0008) -[2023-10-09 10:12:52,117][23468] Updated weights for policy 0, policy_version 47813 (0.0008) -[2023-10-09 10:12:52,260][23469] Updated weights for policy 1, policy_version 48091 (0.0008) -[2023-10-09 10:12:52,496][23468] Updated weights for policy 0, policy_version 47823 (0.0008) -[2023-10-09 10:12:52,865][23468] Updated weights for policy 0, policy_version 47833 (0.0007) -[2023-10-09 10:12:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 98238464. Throughput: 0: 1785.9, 1: 1789.1. Samples: 24570630. Policy #0 lag: (min: 31.0, avg: 32.5, max: 57.0) -[2023-10-09 10:12:56,078][22500] Avg episode reward: [(0, '8.880'), (1, '7.470')] -[2023-10-09 10:12:56,078][23469] Updated weights for policy 1, policy_version 48101 (0.0010) -[2023-10-09 10:12:56,456][23469] Updated weights for policy 1, policy_version 48111 (0.0008) -[2023-10-09 10:12:56,784][23468] Updated weights for policy 0, policy_version 47843 (0.0008) -[2023-10-09 10:12:56,835][23469] Updated weights for policy 1, policy_version 48121 (0.0008) -[2023-10-09 10:12:57,172][23468] Updated weights for policy 0, policy_version 47853 (0.0008) -[2023-10-09 10:12:57,552][23468] Updated weights for policy 0, policy_version 47863 (0.0009) -[2023-10-09 10:13:00,707][23469] Updated weights for policy 1, policy_version 48131 (0.0008) -[2023-10-09 10:13:01,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 98304000. Throughput: 0: 1781.4, 1: 1804.5. Samples: 24592466. Policy #0 lag: (min: 31.0, avg: 32.5, max: 57.0) -[2023-10-09 10:13:01,078][22500] Avg episode reward: [(0, '8.590'), (1, '7.680')] -[2023-10-09 10:13:01,105][23469] Updated weights for policy 1, policy_version 48141 (0.0010) -[2023-10-09 10:13:01,222][23468] Updated weights for policy 0, policy_version 47873 (0.0007) -[2023-10-09 10:13:01,479][23469] Updated weights for policy 1, policy_version 48151 (0.0008) -[2023-10-09 10:13:01,588][23468] Updated weights for policy 0, policy_version 47883 (0.0009) -[2023-10-09 10:13:01,963][23468] Updated weights for policy 0, policy_version 47893 (0.0008) -[2023-10-09 10:13:02,328][23468] Updated weights for policy 0, policy_version 47903 (0.0009) -[2023-10-09 10:13:05,333][23469] Updated weights for policy 1, policy_version 48161 (0.0010) -[2023-10-09 10:13:05,698][23469] Updated weights for policy 1, policy_version 48171 (0.0009) -[2023-10-09 10:13:06,069][23469] Updated weights for policy 1, policy_version 48181 (0.0008) -[2023-10-09 10:13:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 98369536. Throughput: 0: 1779.1, 1: 1780.3. Samples: 24602074. Policy #0 lag: (min: 20.0, avg: 29.0, max: 52.0) -[2023-10-09 10:13:06,078][22500] Avg episode reward: [(0, '8.490'), (1, '8.050')] -[2023-10-09 10:13:06,248][23468] Updated weights for policy 0, policy_version 47913 (0.0009) -[2023-10-09 10:13:06,439][23469] Updated weights for policy 1, policy_version 48191 (0.0008) -[2023-10-09 10:13:06,622][23468] Updated weights for policy 0, policy_version 47923 (0.0008) -[2023-10-09 10:13:07,010][23468] Updated weights for policy 0, policy_version 47933 (0.0009) -[2023-10-09 10:13:10,311][23469] Updated weights for policy 1, policy_version 48201 (0.0008) -[2023-10-09 10:13:10,678][23469] Updated weights for policy 1, policy_version 48211 (0.0009) -[2023-10-09 10:13:10,750][23468] Updated weights for policy 0, policy_version 47943 (0.0010) -[2023-10-09 10:13:11,054][23469] Updated weights for policy 1, policy_version 48221 (0.0010) -[2023-10-09 10:13:11,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 98435072. Throughput: 0: 1768.9, 1: 1794.2. Samples: 24623858. Policy #0 lag: (min: 20.0, avg: 29.0, max: 52.0) -[2023-10-09 10:13:11,078][22500] Avg episode reward: [(0, '9.170'), (1, '8.200')] -[2023-10-09 10:13:11,120][23468] Updated weights for policy 0, policy_version 47953 (0.0009) -[2023-10-09 10:13:11,500][23468] Updated weights for policy 0, policy_version 47963 (0.0007) -[2023-10-09 10:13:14,890][23469] Updated weights for policy 1, policy_version 48231 (0.0008) -[2023-10-09 10:13:15,267][23469] Updated weights for policy 1, policy_version 48241 (0.0009) -[2023-10-09 10:13:15,285][23468] Updated weights for policy 0, policy_version 47973 (0.0008) -[2023-10-09 10:13:15,636][23469] Updated weights for policy 1, policy_version 48251 (0.0008) -[2023-10-09 10:13:15,649][23468] Updated weights for policy 0, policy_version 47983 (0.0009) -[2023-10-09 10:13:16,025][23468] Updated weights for policy 0, policy_version 47993 (0.0009) -[2023-10-09 10:13:16,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 98533376. Throughput: 0: 1791.5, 1: 1780.9. Samples: 24644684. Policy #0 lag: (min: 20.0, avg: 29.0, max: 52.0) -[2023-10-09 10:13:16,078][22500] Avg episode reward: [(0, '8.240'), (1, '8.030')] -[2023-10-09 10:13:19,403][23469] Updated weights for policy 1, policy_version 48261 (0.0008) -[2023-10-09 10:13:19,774][23469] Updated weights for policy 1, policy_version 48271 (0.0009) -[2023-10-09 10:13:19,892][23468] Updated weights for policy 0, policy_version 48003 (0.0010) -[2023-10-09 10:13:20,128][23469] Updated weights for policy 1, policy_version 48281 (0.0008) -[2023-10-09 10:13:20,258][23468] Updated weights for policy 0, policy_version 48013 (0.0008) -[2023-10-09 10:13:20,630][23468] Updated weights for policy 0, policy_version 48023 (0.0010) -[2023-10-09 10:13:21,078][22500] Fps is (10 sec: 19660.4, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 98631680. Throughput: 0: 1769.1, 1: 1800.5. Samples: 24656052. Policy #0 lag: (min: 20.0, avg: 29.0, max: 52.0) -[2023-10-09 10:13:21,079][22500] Avg episode reward: [(0, '8.480'), (1, '8.340')] -[2023-10-09 10:13:23,854][23469] Updated weights for policy 1, policy_version 48291 (0.0009) -[2023-10-09 10:13:24,222][23469] Updated weights for policy 1, policy_version 48301 (0.0008) -[2023-10-09 10:13:24,473][23468] Updated weights for policy 0, policy_version 48033 (0.0010) -[2023-10-09 10:13:24,595][23469] Updated weights for policy 1, policy_version 48311 (0.0008) -[2023-10-09 10:13:24,842][23468] Updated weights for policy 0, policy_version 48043 (0.0008) -[2023-10-09 10:13:25,211][23468] Updated weights for policy 0, policy_version 48053 (0.0009) -[2023-10-09 10:13:25,581][23468] Updated weights for policy 0, policy_version 48063 (0.0009) -[2023-10-09 10:13:26,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 98697216. Throughput: 0: 1796.7, 1: 1783.1. Samples: 24677216. Policy #0 lag: (min: 20.0, avg: 29.0, max: 52.0) -[2023-10-09 10:13:26,078][22500] Avg episode reward: [(0, '7.860'), (1, '8.200')] -[2023-10-09 10:13:28,319][23469] Updated weights for policy 1, policy_version 48321 (0.0008) -[2023-10-09 10:13:28,693][23469] Updated weights for policy 1, policy_version 48331 (0.0009) -[2023-10-09 10:13:29,065][23469] Updated weights for policy 1, policy_version 48341 (0.0009) -[2023-10-09 10:13:29,343][23468] Updated weights for policy 0, policy_version 48073 (0.0007) -[2023-10-09 10:13:29,436][23469] Updated weights for policy 1, policy_version 48351 (0.0007) -[2023-10-09 10:13:29,704][23468] Updated weights for policy 0, policy_version 48083 (0.0007) -[2023-10-09 10:13:30,082][23468] Updated weights for policy 0, policy_version 48093 (0.0010) -[2023-10-09 10:13:31,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 98762752. Throughput: 0: 1767.6, 1: 1780.1. Samples: 24697986. Policy #0 lag: (min: 20.0, avg: 29.0, max: 52.0) -[2023-10-09 10:13:31,079][22500] Avg episode reward: [(0, '7.790'), (1, '8.030')] -[2023-10-09 10:13:33,074][23469] Updated weights for policy 1, policy_version 48361 (0.0010) -[2023-10-09 10:13:33,440][23469] Updated weights for policy 1, policy_version 48371 (0.0011) -[2023-10-09 10:13:33,821][23469] Updated weights for policy 1, policy_version 48381 (0.0010) -[2023-10-09 10:13:34,025][23468] Updated weights for policy 0, policy_version 48103 (0.0009) -[2023-10-09 10:13:34,409][23468] Updated weights for policy 0, policy_version 48113 (0.0008) -[2023-10-09 10:13:34,776][23468] Updated weights for policy 0, policy_version 48123 (0.0009) -[2023-10-09 10:13:36,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 98828288. Throughput: 0: 1783.2, 1: 1785.6. Samples: 24709194. Policy #0 lag: (min: 15.0, avg: 15.2, max: 23.0) -[2023-10-09 10:13:36,079][22500] Avg episode reward: [(0, '7.590'), (1, '7.680')] -[2023-10-09 10:13:37,493][23469] Updated weights for policy 1, policy_version 48391 (0.0008) -[2023-10-09 10:13:37,874][23469] Updated weights for policy 1, policy_version 48401 (0.0007) -[2023-10-09 10:13:38,240][23469] Updated weights for policy 1, policy_version 48411 (0.0008) -[2023-10-09 10:13:38,313][23468] Updated weights for policy 0, policy_version 48133 (0.0009) -[2023-10-09 10:13:38,681][23468] Updated weights for policy 0, policy_version 48143 (0.0010) -[2023-10-09 10:13:39,058][23468] Updated weights for policy 0, policy_version 48153 (0.0009) -[2023-10-09 10:13:41,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 98893824. Throughput: 0: 1771.5, 1: 1779.1. Samples: 24730408. Policy #0 lag: (min: 15.0, avg: 15.2, max: 23.0) -[2023-10-09 10:13:41,079][22500] Avg episode reward: [(0, '7.290'), (1, '7.860')] -[2023-10-09 10:13:41,959][23469] Updated weights for policy 1, policy_version 48421 (0.0008) -[2023-10-09 10:13:42,328][23469] Updated weights for policy 1, policy_version 48431 (0.0007) -[2023-10-09 10:13:42,702][23469] Updated weights for policy 1, policy_version 48441 (0.0007) -[2023-10-09 10:13:43,010][23468] Updated weights for policy 0, policy_version 48163 (0.0008) -[2023-10-09 10:13:43,403][23468] Updated weights for policy 0, policy_version 48173 (0.0008) -[2023-10-09 10:13:43,772][23468] Updated weights for policy 0, policy_version 48183 (0.0010) -[2023-10-09 10:13:46,077][22500] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 98959360. Throughput: 0: 1772.2, 1: 1788.8. Samples: 24752710. Policy #0 lag: (min: 15.0, avg: 15.2, max: 23.0) -[2023-10-09 10:13:46,078][22500] Avg episode reward: [(0, '8.110'), (1, '8.030')] -[2023-10-09 10:13:46,550][23469] Updated weights for policy 1, policy_version 48451 (0.0008) -[2023-10-09 10:13:46,961][23469] Updated weights for policy 1, policy_version 48461 (0.0007) -[2023-10-09 10:13:47,334][23469] Updated weights for policy 1, policy_version 48471 (0.0007) -[2023-10-09 10:13:47,395][23468] Updated weights for policy 0, policy_version 48193 (0.0007) -[2023-10-09 10:13:47,761][23468] Updated weights for policy 0, policy_version 48203 (0.0008) -[2023-10-09 10:13:48,136][23468] Updated weights for policy 0, policy_version 48213 (0.0009) -[2023-10-09 10:13:48,511][23468] Updated weights for policy 0, policy_version 48223 (0.0008) -[2023-10-09 10:13:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 99024896. Throughput: 0: 1785.7, 1: 1783.9. Samples: 24762706. Policy #0 lag: (min: 15.0, avg: 15.2, max: 23.0) -[2023-10-09 10:13:51,079][22500] Avg episode reward: [(0, '8.340'), (1, '7.940')] -[2023-10-09 10:13:51,305][23469] Updated weights for policy 1, policy_version 48481 (0.0009) -[2023-10-09 10:13:51,677][23469] Updated weights for policy 1, policy_version 48491 (0.0009) -[2023-10-09 10:13:52,046][23469] Updated weights for policy 1, policy_version 48501 (0.0007) -[2023-10-09 10:13:52,334][23468] Updated weights for policy 0, policy_version 48233 (0.0008) -[2023-10-09 10:13:52,410][23469] Updated weights for policy 1, policy_version 48511 (0.0009) -[2023-10-09 10:13:52,720][23468] Updated weights for policy 0, policy_version 48243 (0.0010) -[2023-10-09 10:13:53,094][23468] Updated weights for policy 0, policy_version 48253 (0.0008) -[2023-10-09 10:13:56,078][22500] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 99090432. Throughput: 0: 1777.7, 1: 1783.6. Samples: 24784118. Policy #0 lag: (min: 15.0, avg: 15.2, max: 23.0) -[2023-10-09 10:13:56,079][22500] Avg episode reward: [(0, '8.960'), (1, '7.760')] -[2023-10-09 10:13:56,265][23469] Updated weights for policy 1, policy_version 48521 (0.0007) -[2023-10-09 10:13:56,639][23469] Updated weights for policy 1, policy_version 48531 (0.0010) -[2023-10-09 10:13:57,001][23468] Updated weights for policy 0, policy_version 48263 (0.0007) -[2023-10-09 10:13:57,011][23469] Updated weights for policy 1, policy_version 48541 (0.0009) -[2023-10-09 10:13:57,369][23468] Updated weights for policy 0, policy_version 48273 (0.0007) -[2023-10-09 10:13:57,746][23468] Updated weights for policy 0, policy_version 48283 (0.0009) -[2023-10-09 10:14:00,695][23469] Updated weights for policy 1, policy_version 48551 (0.0008) -[2023-10-09 10:14:01,063][23469] Updated weights for policy 1, policy_version 48561 (0.0008) -[2023-10-09 10:14:01,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 99155968. Throughput: 0: 1783.4, 1: 1802.9. Samples: 24806068. Policy #0 lag: (min: 15.0, avg: 15.2, max: 23.0) -[2023-10-09 10:14:01,078][22500] Avg episode reward: [(0, '8.660'), (1, '7.700')] -[2023-10-09 10:14:01,431][23468] Updated weights for policy 0, policy_version 48293 (0.0010) -[2023-10-09 10:14:01,436][23469] Updated weights for policy 1, policy_version 48571 (0.0008) -[2023-10-09 10:14:01,801][23468] Updated weights for policy 0, policy_version 48303 (0.0011) -[2023-10-09 10:14:02,186][23468] Updated weights for policy 0, policy_version 48313 (0.0009) -[2023-10-09 10:14:05,093][23469] Updated weights for policy 1, policy_version 48581 (0.0009) -[2023-10-09 10:14:05,458][23469] Updated weights for policy 1, policy_version 48591 (0.0009) -[2023-10-09 10:14:05,793][23468] Updated weights for policy 0, policy_version 48323 (0.0009) -[2023-10-09 10:14:05,827][23469] Updated weights for policy 1, policy_version 48601 (0.0008) -[2023-10-09 10:14:06,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 99254272. Throughput: 0: 1775.6, 1: 1781.3. Samples: 24816114. Policy #0 lag: (min: 15.0, avg: 15.2, max: 23.0) -[2023-10-09 10:14:06,078][22500] Avg episode reward: [(0, '8.480'), (1, '7.520')] -[2023-10-09 10:14:06,156][23468] Updated weights for policy 0, policy_version 48333 (0.0008) -[2023-10-09 10:14:06,537][23468] Updated weights for policy 0, policy_version 48343 (0.0008) -[2023-10-09 10:14:09,678][23469] Updated weights for policy 1, policy_version 48611 (0.0007) -[2023-10-09 10:14:10,051][23469] Updated weights for policy 1, policy_version 48621 (0.0008) -[2023-10-09 10:14:10,374][23468] Updated weights for policy 0, policy_version 48353 (0.0007) -[2023-10-09 10:14:10,417][23469] Updated weights for policy 1, policy_version 48631 (0.0009) -[2023-10-09 10:14:10,739][23468] Updated weights for policy 0, policy_version 48363 (0.0007) -[2023-10-09 10:14:11,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 99319808. Throughput: 0: 1773.9, 1: 1799.9. Samples: 24838038. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:14:11,078][22500] Avg episode reward: [(0, '8.470'), (1, '7.630')] -[2023-10-09 10:14:11,117][23468] Updated weights for policy 0, policy_version 48373 (0.0007) -[2023-10-09 10:14:11,490][23468] Updated weights for policy 0, policy_version 48383 (0.0007) -[2023-10-09 10:14:14,357][23469] Updated weights for policy 1, policy_version 48641 (0.0009) -[2023-10-09 10:14:14,729][23469] Updated weights for policy 1, policy_version 48651 (0.0008) -[2023-10-09 10:14:15,095][23469] Updated weights for policy 1, policy_version 48661 (0.0009) -[2023-10-09 10:14:15,346][23468] Updated weights for policy 0, policy_version 48393 (0.0008) -[2023-10-09 10:14:15,467][23469] Updated weights for policy 1, policy_version 48671 (0.0009) -[2023-10-09 10:14:15,725][23468] Updated weights for policy 0, policy_version 48403 (0.0008) -[2023-10-09 10:14:16,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 99385344. Throughput: 0: 1805.4, 1: 1768.6. Samples: 24858816. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:14:16,078][22500] Avg episode reward: [(0, '8.040'), (1, '7.160')] -[2023-10-09 10:14:16,090][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000048672_49840128.pth... -[2023-10-09 10:14:16,091][23468] Updated weights for policy 0, policy_version 48413 (0.0007) -[2023-10-09 10:14:16,118][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000046976_48103424.pth -[2023-10-09 10:14:16,200][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000048416_49577984.pth... -[2023-10-09 10:14:16,239][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000046752_47874048.pth -[2023-10-09 10:14:19,383][23469] Updated weights for policy 1, policy_version 48681 (0.0010) -[2023-10-09 10:14:19,752][23469] Updated weights for policy 1, policy_version 48691 (0.0008) -[2023-10-09 10:14:19,910][23468] Updated weights for policy 0, policy_version 48423 (0.0007) -[2023-10-09 10:14:20,129][23469] Updated weights for policy 1, policy_version 48701 (0.0008) -[2023-10-09 10:14:20,291][23468] Updated weights for policy 0, policy_version 48433 (0.0008) -[2023-10-09 10:14:20,656][23468] Updated weights for policy 0, policy_version 48443 (0.0008) -[2023-10-09 10:14:21,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 99483648. Throughput: 0: 1781.7, 1: 1793.0. Samples: 24870056. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:14:21,078][22500] Avg episode reward: [(0, '8.290'), (1, '7.270')] -[2023-10-09 10:14:23,803][23469] Updated weights for policy 1, policy_version 48711 (0.0008) -[2023-10-09 10:14:24,175][23469] Updated weights for policy 1, policy_version 48721 (0.0011) -[2023-10-09 10:14:24,387][23468] Updated weights for policy 0, policy_version 48453 (0.0010) -[2023-10-09 10:14:24,542][23469] Updated weights for policy 1, policy_version 48731 (0.0008) -[2023-10-09 10:14:24,750][23468] Updated weights for policy 0, policy_version 48463 (0.0008) -[2023-10-09 10:14:25,131][23468] Updated weights for policy 0, policy_version 48473 (0.0009) -[2023-10-09 10:14:26,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 99549184. Throughput: 0: 1800.2, 1: 1765.2. Samples: 24890852. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:14:26,078][22500] Avg episode reward: [(0, '8.340'), (1, '7.770')] -[2023-10-09 10:14:28,278][23469] Updated weights for policy 1, policy_version 48741 (0.0008) -[2023-10-09 10:14:28,656][23469] Updated weights for policy 1, policy_version 48751 (0.0010) -[2023-10-09 10:14:28,942][23468] Updated weights for policy 0, policy_version 48483 (0.0008) -[2023-10-09 10:14:29,030][23469] Updated weights for policy 1, policy_version 48761 (0.0009) -[2023-10-09 10:14:29,323][23468] Updated weights for policy 0, policy_version 48493 (0.0007) -[2023-10-09 10:14:29,700][23468] Updated weights for policy 0, policy_version 48503 (0.0007) -[2023-10-09 10:14:31,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 99614720. Throughput: 0: 1772.2, 1: 1762.9. Samples: 24911792. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:14:31,078][22500] Avg episode reward: [(0, '9.410'), (1, '7.980')] -[2023-10-09 10:14:32,749][23469] Updated weights for policy 1, policy_version 48771 (0.0008) -[2023-10-09 10:14:33,163][23469] Updated weights for policy 1, policy_version 48781 (0.0010) -[2023-10-09 10:14:33,522][23469] Updated weights for policy 1, policy_version 48791 (0.0010) -[2023-10-09 10:14:33,543][23468] Updated weights for policy 0, policy_version 48513 (0.0009) -[2023-10-09 10:14:33,911][23468] Updated weights for policy 0, policy_version 48523 (0.0007) -[2023-10-09 10:14:34,280][23468] Updated weights for policy 0, policy_version 48533 (0.0009) -[2023-10-09 10:14:34,660][23468] Updated weights for policy 0, policy_version 48543 (0.0011) -[2023-10-09 10:14:36,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 99680256. Throughput: 0: 1793.0, 1: 1766.2. Samples: 24922868. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:14:36,079][22500] Avg episode reward: [(0, '9.030'), (1, '8.140')] -[2023-10-09 10:14:37,318][23469] Updated weights for policy 1, policy_version 48801 (0.0008) -[2023-10-09 10:14:37,691][23469] Updated weights for policy 1, policy_version 48811 (0.0009) -[2023-10-09 10:14:38,066][23469] Updated weights for policy 1, policy_version 48821 (0.0008) -[2023-10-09 10:14:38,432][23469] Updated weights for policy 1, policy_version 48831 (0.0009) -[2023-10-09 10:14:38,462][23468] Updated weights for policy 0, policy_version 48553 (0.0009) -[2023-10-09 10:14:38,828][23468] Updated weights for policy 0, policy_version 48563 (0.0010) -[2023-10-09 10:14:39,206][23468] Updated weights for policy 0, policy_version 48573 (0.0008) -[2023-10-09 10:14:41,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 99745792. Throughput: 0: 1776.5, 1: 1764.2. Samples: 24943450. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:14:41,078][22500] Avg episode reward: [(0, '9.100'), (1, '8.040')] -[2023-10-09 10:14:42,200][23469] Updated weights for policy 1, policy_version 48841 (0.0009) -[2023-10-09 10:14:42,581][23469] Updated weights for policy 1, policy_version 48851 (0.0009) -[2023-10-09 10:14:42,838][23468] Updated weights for policy 0, policy_version 48583 (0.0007) -[2023-10-09 10:14:42,956][23469] Updated weights for policy 1, policy_version 48861 (0.0007) -[2023-10-09 10:14:43,207][23468] Updated weights for policy 0, policy_version 48593 (0.0007) -[2023-10-09 10:14:43,579][23468] Updated weights for policy 0, policy_version 48603 (0.0009) -[2023-10-09 10:14:46,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 99811328. Throughput: 0: 1770.7, 1: 1775.2. Samples: 24965634. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:14:46,078][22500] Avg episode reward: [(0, '8.480'), (1, '7.950')] -[2023-10-09 10:14:46,714][23469] Updated weights for policy 1, policy_version 48871 (0.0008) -[2023-10-09 10:14:47,069][23469] Updated weights for policy 1, policy_version 48881 (0.0007) -[2023-10-09 10:14:47,366][23468] Updated weights for policy 0, policy_version 48613 (0.0008) -[2023-10-09 10:14:47,431][23469] Updated weights for policy 1, policy_version 48891 (0.0007) -[2023-10-09 10:14:47,748][23468] Updated weights for policy 0, policy_version 48623 (0.0009) -[2023-10-09 10:14:48,111][23468] Updated weights for policy 0, policy_version 48633 (0.0010) -[2023-10-09 10:14:51,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 99876864. Throughput: 0: 1783.1, 1: 1763.8. Samples: 24975724. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:14:51,078][22500] Avg episode reward: [(0, '8.460'), (1, '8.170')] -[2023-10-09 10:14:51,175][23469] Updated weights for policy 1, policy_version 48901 (0.0007) -[2023-10-09 10:14:51,543][23469] Updated weights for policy 1, policy_version 48911 (0.0009) -[2023-10-09 10:14:51,742][23468] Updated weights for policy 0, policy_version 48643 (0.0009) -[2023-10-09 10:14:51,916][23469] Updated weights for policy 1, policy_version 48921 (0.0008) -[2023-10-09 10:14:52,110][23468] Updated weights for policy 0, policy_version 48653 (0.0007) -[2023-10-09 10:14:52,477][23468] Updated weights for policy 0, policy_version 48663 (0.0008) -[2023-10-09 10:14:55,695][23469] Updated weights for policy 1, policy_version 48931 (0.0010) -[2023-10-09 10:14:56,057][23469] Updated weights for policy 1, policy_version 48941 (0.0008) -[2023-10-09 10:14:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.6, 300 sec: 14218.0). Total num frames: 99942400. Throughput: 0: 1781.6, 1: 1774.6. Samples: 24998068. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:14:56,078][22500] Avg episode reward: [(0, '8.400'), (1, '8.020')] -[2023-10-09 10:14:56,137][23468] Updated weights for policy 0, policy_version 48673 (0.0007) -[2023-10-09 10:14:56,429][23469] Updated weights for policy 1, policy_version 48951 (0.0008) -[2023-10-09 10:14:56,514][23468] Updated weights for policy 0, policy_version 48683 (0.0008) -[2023-10-09 10:14:56,887][23468] Updated weights for policy 0, policy_version 48693 (0.0007) -[2023-10-09 10:14:57,260][23468] Updated weights for policy 0, policy_version 48703 (0.0007) -[2023-10-09 10:15:00,155][23469] Updated weights for policy 1, policy_version 48961 (0.0007) -[2023-10-09 10:15:00,524][23469] Updated weights for policy 1, policy_version 48971 (0.0008) -[2023-10-09 10:15:00,889][23469] Updated weights for policy 1, policy_version 48981 (0.0007) -[2023-10-09 10:15:01,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 100007936. Throughput: 0: 1785.9, 1: 1791.2. Samples: 25019786. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:15:01,078][22500] Avg episode reward: [(0, '8.690'), (1, '7.830')] -[2023-10-09 10:15:01,115][23468] Updated weights for policy 0, policy_version 48713 (0.0007) -[2023-10-09 10:15:01,255][23469] Updated weights for policy 1, policy_version 48991 (0.0009) -[2023-10-09 10:15:01,491][23468] Updated weights for policy 0, policy_version 48723 (0.0007) -[2023-10-09 10:15:01,871][23468] Updated weights for policy 0, policy_version 48733 (0.0007) -[2023-10-09 10:15:04,908][23469] Updated weights for policy 1, policy_version 49001 (0.0007) -[2023-10-09 10:15:05,279][23469] Updated weights for policy 1, policy_version 49011 (0.0010) -[2023-10-09 10:15:05,620][23468] Updated weights for policy 0, policy_version 48743 (0.0008) -[2023-10-09 10:15:05,639][23469] Updated weights for policy 1, policy_version 49021 (0.0008) -[2023-10-09 10:15:05,984][23468] Updated weights for policy 0, policy_version 48753 (0.0010) -[2023-10-09 10:15:06,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 100106240. Throughput: 0: 1784.1, 1: 1783.7. Samples: 25030608. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:15:06,078][22500] Avg episode reward: [(0, '9.620'), (1, '8.120')] -[2023-10-09 10:15:06,357][23468] Updated weights for policy 0, policy_version 48763 (0.0009) -[2023-10-09 10:15:06,545][23265] Saving new best policy, reward=9.620! -[2023-10-09 10:15:09,315][23469] Updated weights for policy 1, policy_version 49031 (0.0009) -[2023-10-09 10:15:09,690][23469] Updated weights for policy 1, policy_version 49041 (0.0012) -[2023-10-09 10:15:10,056][23469] Updated weights for policy 1, policy_version 49051 (0.0007) -[2023-10-09 10:15:10,080][23468] Updated weights for policy 0, policy_version 48773 (0.0009) -[2023-10-09 10:15:10,452][23468] Updated weights for policy 0, policy_version 48783 (0.0009) -[2023-10-09 10:15:10,827][23468] Updated weights for policy 0, policy_version 48793 (0.0010) -[2023-10-09 10:15:11,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 100171776. Throughput: 0: 1788.8, 1: 1800.1. Samples: 25052350. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:15:11,078][22500] Avg episode reward: [(0, '9.660'), (1, '8.020')] -[2023-10-09 10:15:11,078][23265] Saving new best policy, reward=9.660! -[2023-10-09 10:15:13,824][23469] Updated weights for policy 1, policy_version 49061 (0.0009) -[2023-10-09 10:15:14,195][23469] Updated weights for policy 1, policy_version 49071 (0.0008) -[2023-10-09 10:15:14,571][23469] Updated weights for policy 1, policy_version 49081 (0.0009) -[2023-10-09 10:15:14,610][23468] Updated weights for policy 0, policy_version 48803 (0.0010) -[2023-10-09 10:15:15,004][23468] Updated weights for policy 0, policy_version 48813 (0.0008) -[2023-10-09 10:15:15,376][23468] Updated weights for policy 0, policy_version 48823 (0.0009) -[2023-10-09 10:15:16,078][22500] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 100270080. Throughput: 0: 1800.0, 1: 1787.1. Samples: 25073212. Policy #0 lag: (min: 7.0, avg: 9.9, max: 39.0) -[2023-10-09 10:15:16,079][22500] Avg episode reward: [(0, '9.620'), (1, '8.220')] -[2023-10-09 10:15:18,490][23469] Updated weights for policy 1, policy_version 49091 (0.0007) -[2023-10-09 10:15:18,886][23469] Updated weights for policy 1, policy_version 49101 (0.0009) -[2023-10-09 10:15:19,076][23468] Updated weights for policy 0, policy_version 48833 (0.0009) -[2023-10-09 10:15:19,254][23469] Updated weights for policy 1, policy_version 49111 (0.0009) -[2023-10-09 10:15:19,444][23468] Updated weights for policy 0, policy_version 48843 (0.0007) -[2023-10-09 10:15:19,817][23468] Updated weights for policy 0, policy_version 48853 (0.0007) -[2023-10-09 10:15:20,188][23468] Updated weights for policy 0, policy_version 48863 (0.0007) -[2023-10-09 10:15:21,078][22500] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 100335616. Throughput: 0: 1787.1, 1: 1806.7. Samples: 25084590. Policy #0 lag: (min: 7.0, avg: 9.9, max: 39.0) -[2023-10-09 10:15:21,079][22500] Avg episode reward: [(0, '9.610'), (1, '7.450')] -[2023-10-09 10:15:23,086][23469] Updated weights for policy 1, policy_version 49121 (0.0008) -[2023-10-09 10:15:23,466][23469] Updated weights for policy 1, policy_version 49131 (0.0007) -[2023-10-09 10:15:23,835][23469] Updated weights for policy 1, policy_version 49141 (0.0009) -[2023-10-09 10:15:24,158][23468] Updated weights for policy 0, policy_version 48873 (0.0007) -[2023-10-09 10:15:24,202][23469] Updated weights for policy 1, policy_version 49151 (0.0008) -[2023-10-09 10:15:24,539][23468] Updated weights for policy 0, policy_version 48883 (0.0007) -[2023-10-09 10:15:24,910][23468] Updated weights for policy 0, policy_version 48893 (0.0008) -[2023-10-09 10:15:26,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 100401152. Throughput: 0: 1806.4, 1: 1790.9. Samples: 25105328. Policy #0 lag: (min: 7.0, avg: 9.9, max: 39.0) -[2023-10-09 10:15:26,078][22500] Avg episode reward: [(0, '9.340'), (1, '7.790')] -[2023-10-09 10:15:28,038][23469] Updated weights for policy 1, policy_version 49161 (0.0008) -[2023-10-09 10:15:28,407][23469] Updated weights for policy 1, policy_version 49171 (0.0010) -[2023-10-09 10:15:28,667][23468] Updated weights for policy 0, policy_version 48903 (0.0008) -[2023-10-09 10:15:28,783][23469] Updated weights for policy 1, policy_version 49181 (0.0007) -[2023-10-09 10:15:29,035][23468] Updated weights for policy 0, policy_version 48913 (0.0011) -[2023-10-09 10:15:29,405][23468] Updated weights for policy 0, policy_version 48923 (0.0009) -[2023-10-09 10:15:31,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 100466688. Throughput: 0: 1787.6, 1: 1789.7. Samples: 25126612. Policy #0 lag: (min: 7.0, avg: 9.9, max: 39.0) -[2023-10-09 10:15:31,078][22500] Avg episode reward: [(0, '9.280'), (1, '7.860')] -[2023-10-09 10:15:32,526][23469] Updated weights for policy 1, policy_version 49191 (0.0009) -[2023-10-09 10:15:32,895][23469] Updated weights for policy 1, policy_version 49201 (0.0009) -[2023-10-09 10:15:33,272][23469] Updated weights for policy 1, policy_version 49211 (0.0007) -[2023-10-09 10:15:33,353][23468] Updated weights for policy 0, policy_version 48933 (0.0009) -[2023-10-09 10:15:33,733][23468] Updated weights for policy 0, policy_version 48943 (0.0008) -[2023-10-09 10:15:34,104][23468] Updated weights for policy 0, policy_version 48953 (0.0012) -[2023-10-09 10:15:36,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 100532224. Throughput: 0: 1804.8, 1: 1788.5. Samples: 25137424. Policy #0 lag: (min: 7.0, avg: 9.9, max: 39.0) -[2023-10-09 10:15:36,079][22500] Avg episode reward: [(0, '9.400'), (1, '8.310')] -[2023-10-09 10:15:37,084][23469] Updated weights for policy 1, policy_version 49221 (0.0009) -[2023-10-09 10:15:37,459][23469] Updated weights for policy 1, policy_version 49231 (0.0008) -[2023-10-09 10:15:37,842][23469] Updated weights for policy 1, policy_version 49241 (0.0009) -[2023-10-09 10:15:37,905][23468] Updated weights for policy 0, policy_version 48963 (0.0009) -[2023-10-09 10:15:38,288][23468] Updated weights for policy 0, policy_version 48973 (0.0009) -[2023-10-09 10:15:38,663][23468] Updated weights for policy 0, policy_version 48983 (0.0008) -[2023-10-09 10:15:41,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 100597760. Throughput: 0: 1775.9, 1: 1786.4. Samples: 25158374. Policy #0 lag: (min: 7.0, avg: 9.9, max: 39.0) -[2023-10-09 10:15:41,078][22500] Avg episode reward: [(0, '8.940'), (1, '8.010')] -[2023-10-09 10:15:41,642][23469] Updated weights for policy 1, policy_version 49251 (0.0008) -[2023-10-09 10:15:42,023][23469] Updated weights for policy 1, policy_version 49261 (0.0008) -[2023-10-09 10:15:42,392][23469] Updated weights for policy 1, policy_version 49271 (0.0009) -[2023-10-09 10:15:42,427][23468] Updated weights for policy 0, policy_version 48993 (0.0010) -[2023-10-09 10:15:42,806][23468] Updated weights for policy 0, policy_version 49003 (0.0009) -[2023-10-09 10:15:43,180][23468] Updated weights for policy 0, policy_version 49013 (0.0009) -[2023-10-09 10:15:43,550][23468] Updated weights for policy 0, policy_version 49023 (0.0009) -[2023-10-09 10:15:45,950][23469] Updated weights for policy 1, policy_version 49281 (0.0008) -[2023-10-09 10:15:46,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 100663296. Throughput: 0: 1773.2, 1: 1804.1. Samples: 25180766. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 10:15:46,078][22500] Avg episode reward: [(0, '8.920'), (1, '7.850')] -[2023-10-09 10:15:46,311][23469] Updated weights for policy 1, policy_version 49291 (0.0010) -[2023-10-09 10:15:46,689][23469] Updated weights for policy 1, policy_version 49301 (0.0008) -[2023-10-09 10:15:47,071][23469] Updated weights for policy 1, policy_version 49311 (0.0009) -[2023-10-09 10:15:47,185][23468] Updated weights for policy 0, policy_version 49033 (0.0009) -[2023-10-09 10:15:47,569][23468] Updated weights for policy 0, policy_version 49043 (0.0008) -[2023-10-09 10:15:47,943][23468] Updated weights for policy 0, policy_version 49053 (0.0009) -[2023-10-09 10:15:50,926][23469] Updated weights for policy 1, policy_version 49321 (0.0009) -[2023-10-09 10:15:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 100728832. Throughput: 0: 1770.2, 1: 1778.4. Samples: 25190294. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 10:15:51,078][22500] Avg episode reward: [(0, '8.940'), (1, '7.760')] -[2023-10-09 10:15:51,296][23469] Updated weights for policy 1, policy_version 49331 (0.0007) -[2023-10-09 10:15:51,669][23469] Updated weights for policy 1, policy_version 49341 (0.0009) -[2023-10-09 10:15:51,685][23468] Updated weights for policy 0, policy_version 49063 (0.0008) -[2023-10-09 10:15:52,054][23468] Updated weights for policy 0, policy_version 49073 (0.0008) -[2023-10-09 10:15:52,428][23468] Updated weights for policy 0, policy_version 49083 (0.0010) -[2023-10-09 10:15:55,481][23469] Updated weights for policy 1, policy_version 49351 (0.0009) -[2023-10-09 10:15:55,854][23469] Updated weights for policy 1, policy_version 49361 (0.0008) -[2023-10-09 10:15:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 100794368. Throughput: 0: 1767.4, 1: 1793.5. Samples: 25212590. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 10:15:56,078][22500] Avg episode reward: [(0, '8.880'), (1, '8.020')] -[2023-10-09 10:15:56,197][23468] Updated weights for policy 0, policy_version 49093 (0.0009) -[2023-10-09 10:15:56,221][23469] Updated weights for policy 1, policy_version 49371 (0.0008) -[2023-10-09 10:15:56,559][23468] Updated weights for policy 0, policy_version 49103 (0.0009) -[2023-10-09 10:15:56,937][23468] Updated weights for policy 0, policy_version 49113 (0.0008) -[2023-10-09 10:15:59,934][23469] Updated weights for policy 1, policy_version 49381 (0.0008) -[2023-10-09 10:16:00,300][23469] Updated weights for policy 1, policy_version 49391 (0.0010) -[2023-10-09 10:16:00,676][23469] Updated weights for policy 1, policy_version 49401 (0.0010) -[2023-10-09 10:16:00,943][23468] Updated weights for policy 0, policy_version 49123 (0.0007) -[2023-10-09 10:16:01,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 100892672. Throughput: 0: 1788.0, 1: 1780.5. Samples: 25233794. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 10:16:01,078][22500] Avg episode reward: [(0, '9.250'), (1, '8.670')] -[2023-10-09 10:16:01,085][23343] Saving new best policy, reward=8.670! -[2023-10-09 10:16:01,334][23468] Updated weights for policy 0, policy_version 49133 (0.0010) -[2023-10-09 10:16:01,706][23468] Updated weights for policy 0, policy_version 49143 (0.0008) -[2023-10-09 10:16:04,566][23469] Updated weights for policy 1, policy_version 49411 (0.0007) -[2023-10-09 10:16:04,973][23469] Updated weights for policy 1, policy_version 49421 (0.0009) -[2023-10-09 10:16:05,336][23469] Updated weights for policy 1, policy_version 49431 (0.0009) -[2023-10-09 10:16:05,502][23468] Updated weights for policy 0, policy_version 49153 (0.0008) -[2023-10-09 10:16:05,879][23468] Updated weights for policy 0, policy_version 49163 (0.0009) -[2023-10-09 10:16:06,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 100958208. Throughput: 0: 1764.6, 1: 1791.8. Samples: 25244628. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 10:16:06,078][22500] Avg episode reward: [(0, '9.020'), (1, '8.470')] -[2023-10-09 10:16:06,244][23468] Updated weights for policy 0, policy_version 49173 (0.0009) -[2023-10-09 10:16:06,625][23468] Updated weights for policy 0, policy_version 49183 (0.0010) -[2023-10-09 10:16:09,101][23469] Updated weights for policy 1, policy_version 49441 (0.0008) -[2023-10-09 10:16:09,470][23469] Updated weights for policy 1, policy_version 49451 (0.0008) -[2023-10-09 10:16:09,844][23469] Updated weights for policy 1, policy_version 49461 (0.0008) -[2023-10-09 10:16:10,224][23469] Updated weights for policy 1, policy_version 49471 (0.0008) -[2023-10-09 10:16:10,397][23468] Updated weights for policy 0, policy_version 49193 (0.0009) -[2023-10-09 10:16:10,772][23468] Updated weights for policy 0, policy_version 49203 (0.0008) -[2023-10-09 10:16:11,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 101023744. Throughput: 0: 1774.6, 1: 1791.2. Samples: 25265792. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 10:16:11,078][22500] Avg episode reward: [(0, '8.760'), (1, '8.530')] -[2023-10-09 10:16:11,150][23468] Updated weights for policy 0, policy_version 49213 (0.0008) -[2023-10-09 10:16:14,020][23469] Updated weights for policy 1, policy_version 49481 (0.0010) -[2023-10-09 10:16:14,395][23469] Updated weights for policy 1, policy_version 49491 (0.0011) -[2023-10-09 10:16:14,759][23469] Updated weights for policy 1, policy_version 49501 (0.0007) -[2023-10-09 10:16:14,884][23468] Updated weights for policy 0, policy_version 49223 (0.0007) -[2023-10-09 10:16:15,261][23468] Updated weights for policy 0, policy_version 49233 (0.0008) -[2023-10-09 10:16:15,638][23468] Updated weights for policy 0, policy_version 49243 (0.0009) -[2023-10-09 10:16:16,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 101122048. Throughput: 0: 1778.3, 1: 1779.0. Samples: 25286690. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 10:16:16,078][22500] Avg episode reward: [(0, '8.340'), (1, '8.160')] -[2023-10-09 10:16:16,086][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000049504_50692096.pth... -[2023-10-09 10:16:16,086][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000049248_50429952.pth... -[2023-10-09 10:16:16,122][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000047584_48726016.pth -[2023-10-09 10:16:16,125][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000047840_48988160.pth -[2023-10-09 10:16:16,126][23265] Saving a milestone ./train_atari/atari_berzerk_APPO/checkpoint_p0/milestones/checkpoint_000049248_50429952.pth -[2023-10-09 10:16:16,131][23343] Saving a milestone ./train_atari/atari_berzerk_APPO/checkpoint_p1/milestones/checkpoint_000049504_50692096.pth -[2023-10-09 10:16:18,464][23469] Updated weights for policy 1, policy_version 49511 (0.0009) -[2023-10-09 10:16:18,830][23469] Updated weights for policy 1, policy_version 49521 (0.0008) -[2023-10-09 10:16:19,195][23469] Updated weights for policy 1, policy_version 49531 (0.0008) -[2023-10-09 10:16:19,445][23468] Updated weights for policy 0, policy_version 49253 (0.0009) -[2023-10-09 10:16:19,814][23468] Updated weights for policy 0, policy_version 49263 (0.0008) -[2023-10-09 10:16:20,185][23468] Updated weights for policy 0, policy_version 49273 (0.0009) -[2023-10-09 10:16:21,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 101187584. Throughput: 0: 1769.2, 1: 1795.6. Samples: 25297842. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 10:16:21,079][22500] Avg episode reward: [(0, '8.500'), (1, '7.990')] -[2023-10-09 10:16:22,885][23469] Updated weights for policy 1, policy_version 49541 (0.0009) -[2023-10-09 10:16:23,261][23469] Updated weights for policy 1, policy_version 49551 (0.0008) -[2023-10-09 10:16:23,631][23469] Updated weights for policy 1, policy_version 49561 (0.0007) -[2023-10-09 10:16:24,080][23468] Updated weights for policy 0, policy_version 49283 (0.0008) -[2023-10-09 10:16:24,440][23468] Updated weights for policy 0, policy_version 49293 (0.0008) -[2023-10-09 10:16:24,809][23468] Updated weights for policy 0, policy_version 49303 (0.0007) -[2023-10-09 10:16:26,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 101253120. Throughput: 0: 1788.5, 1: 1785.7. Samples: 25319216. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 10:16:26,078][22500] Avg episode reward: [(0, '8.120'), (1, '8.220')] -[2023-10-09 10:16:27,286][23469] Updated weights for policy 1, policy_version 49571 (0.0008) -[2023-10-09 10:16:27,664][23469] Updated weights for policy 1, policy_version 49581 (0.0007) -[2023-10-09 10:16:28,036][23469] Updated weights for policy 1, policy_version 49591 (0.0009) -[2023-10-09 10:16:28,498][23468] Updated weights for policy 0, policy_version 49313 (0.0007) -[2023-10-09 10:16:28,868][23468] Updated weights for policy 0, policy_version 49323 (0.0009) -[2023-10-09 10:16:29,243][23468] Updated weights for policy 0, policy_version 49333 (0.0007) -[2023-10-09 10:16:29,621][23468] Updated weights for policy 0, policy_version 49343 (0.0008) -[2023-10-09 10:16:31,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 101318656. Throughput: 0: 1765.9, 1: 1786.1. Samples: 25340606. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 10:16:31,078][22500] Avg episode reward: [(0, '8.050'), (1, '8.060')] -[2023-10-09 10:16:31,802][23469] Updated weights for policy 1, policy_version 49601 (0.0010) -[2023-10-09 10:16:32,164][23469] Updated weights for policy 1, policy_version 49611 (0.0007) -[2023-10-09 10:16:32,517][23469] Updated weights for policy 1, policy_version 49621 (0.0010) -[2023-10-09 10:16:32,890][23469] Updated weights for policy 1, policy_version 49631 (0.0009) -[2023-10-09 10:16:33,266][23468] Updated weights for policy 0, policy_version 49353 (0.0009) -[2023-10-09 10:16:33,633][23468] Updated weights for policy 0, policy_version 49363 (0.0009) -[2023-10-09 10:16:34,004][23468] Updated weights for policy 0, policy_version 49373 (0.0008) -[2023-10-09 10:16:36,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 101384192. Throughput: 0: 1791.2, 1: 1791.8. Samples: 25351526. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 10:16:36,078][22500] Avg episode reward: [(0, '7.950'), (1, '8.200')] -[2023-10-09 10:16:36,639][23469] Updated weights for policy 1, policy_version 49641 (0.0009) -[2023-10-09 10:16:37,010][23469] Updated weights for policy 1, policy_version 49651 (0.0008) -[2023-10-09 10:16:37,385][23469] Updated weights for policy 1, policy_version 49661 (0.0009) -[2023-10-09 10:16:37,718][23468] Updated weights for policy 0, policy_version 49383 (0.0008) -[2023-10-09 10:16:38,097][23468] Updated weights for policy 0, policy_version 49393 (0.0010) -[2023-10-09 10:16:38,462][23468] Updated weights for policy 0, policy_version 49403 (0.0010) -[2023-10-09 10:16:40,993][23469] Updated weights for policy 1, policy_version 49671 (0.0008) -[2023-10-09 10:16:41,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 101449728. Throughput: 0: 1772.6, 1: 1789.9. Samples: 25372904. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 10:16:41,078][22500] Avg episode reward: [(0, '8.490'), (1, '8.620')] -[2023-10-09 10:16:41,360][23469] Updated weights for policy 1, policy_version 49681 (0.0008) -[2023-10-09 10:16:41,719][23469] Updated weights for policy 1, policy_version 49691 (0.0007) -[2023-10-09 10:16:42,283][23468] Updated weights for policy 0, policy_version 49413 (0.0009) -[2023-10-09 10:16:42,651][23468] Updated weights for policy 0, policy_version 49423 (0.0008) -[2023-10-09 10:16:43,027][23468] Updated weights for policy 0, policy_version 49433 (0.0009) -[2023-10-09 10:16:45,302][23469] Updated weights for policy 1, policy_version 49701 (0.0008) -[2023-10-09 10:16:45,667][23469] Updated weights for policy 1, policy_version 49711 (0.0007) -[2023-10-09 10:16:46,042][23469] Updated weights for policy 1, policy_version 49721 (0.0007) -[2023-10-09 10:16:46,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 101515264. Throughput: 0: 1767.2, 1: 1805.1. Samples: 25394546. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 10:16:46,078][22500] Avg episode reward: [(0, '8.260'), (1, '8.580')] -[2023-10-09 10:16:46,874][23468] Updated weights for policy 0, policy_version 49443 (0.0008) -[2023-10-09 10:16:47,267][23468] Updated weights for policy 0, policy_version 49453 (0.0007) -[2023-10-09 10:16:47,635][23468] Updated weights for policy 0, policy_version 49463 (0.0009) -[2023-10-09 10:16:49,800][23469] Updated weights for policy 1, policy_version 49731 (0.0007) -[2023-10-09 10:16:50,212][23469] Updated weights for policy 1, policy_version 49741 (0.0008) -[2023-10-09 10:16:50,583][23469] Updated weights for policy 1, policy_version 49751 (0.0010) -[2023-10-09 10:16:51,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 101613568. Throughput: 0: 1771.0, 1: 1793.8. Samples: 25405044. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 10:16:51,078][22500] Avg episode reward: [(0, '8.140'), (1, '8.790')] -[2023-10-09 10:16:51,079][23343] Saving new best policy, reward=8.790! -[2023-10-09 10:16:51,594][23468] Updated weights for policy 0, policy_version 49473 (0.0008) -[2023-10-09 10:16:51,969][23468] Updated weights for policy 0, policy_version 49483 (0.0008) -[2023-10-09 10:16:52,341][23468] Updated weights for policy 0, policy_version 49493 (0.0007) -[2023-10-09 10:16:52,716][23468] Updated weights for policy 0, policy_version 49503 (0.0007) -[2023-10-09 10:16:54,417][23469] Updated weights for policy 1, policy_version 49761 (0.0009) -[2023-10-09 10:16:54,794][23469] Updated weights for policy 1, policy_version 49771 (0.0007) -[2023-10-09 10:16:55,169][23469] Updated weights for policy 1, policy_version 49781 (0.0007) -[2023-10-09 10:16:55,541][23469] Updated weights for policy 1, policy_version 49791 (0.0008) -[2023-10-09 10:16:56,078][22500] Fps is (10 sec: 16383.5, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 101679104. Throughput: 0: 1767.2, 1: 1804.3. Samples: 25426508. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 10:16:56,079][22500] Avg episode reward: [(0, '8.170'), (1, '8.740')] -[2023-10-09 10:16:56,598][23468] Updated weights for policy 0, policy_version 49513 (0.0009) -[2023-10-09 10:16:56,959][23468] Updated weights for policy 0, policy_version 49523 (0.0009) -[2023-10-09 10:16:57,332][23468] Updated weights for policy 0, policy_version 49533 (0.0009) -[2023-10-09 10:16:59,336][23469] Updated weights for policy 1, policy_version 49801 (0.0008) -[2023-10-09 10:16:59,708][23469] Updated weights for policy 1, policy_version 49811 (0.0009) -[2023-10-09 10:17:00,084][23469] Updated weights for policy 1, policy_version 49821 (0.0009) -[2023-10-09 10:17:00,974][23468] Updated weights for policy 0, policy_version 49543 (0.0011) -[2023-10-09 10:17:01,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 101744640. Throughput: 0: 1787.6, 1: 1794.3. Samples: 25447878. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 10:17:01,078][22500] Avg episode reward: [(0, '8.440'), (1, '8.170')] -[2023-10-09 10:17:01,345][23468] Updated weights for policy 0, policy_version 49553 (0.0008) -[2023-10-09 10:17:01,725][23468] Updated weights for policy 0, policy_version 49563 (0.0008) -[2023-10-09 10:17:03,961][23469] Updated weights for policy 1, policy_version 49831 (0.0010) -[2023-10-09 10:17:04,320][23469] Updated weights for policy 1, policy_version 49841 (0.0010) -[2023-10-09 10:17:04,690][23469] Updated weights for policy 1, policy_version 49851 (0.0009) -[2023-10-09 10:17:05,411][23468] Updated weights for policy 0, policy_version 49573 (0.0009) -[2023-10-09 10:17:05,779][23468] Updated weights for policy 0, policy_version 49583 (0.0010) -[2023-10-09 10:17:06,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 101810176. Throughput: 0: 1769.2, 1: 1806.0. Samples: 25458722. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 10:17:06,078][22500] Avg episode reward: [(0, '8.340'), (1, '8.120')] -[2023-10-09 10:17:06,164][23468] Updated weights for policy 0, policy_version 49593 (0.0010) -[2023-10-09 10:17:08,492][23469] Updated weights for policy 1, policy_version 49861 (0.0009) -[2023-10-09 10:17:08,859][23469] Updated weights for policy 1, policy_version 49871 (0.0007) -[2023-10-09 10:17:09,232][23469] Updated weights for policy 1, policy_version 49881 (0.0007) -[2023-10-09 10:17:09,932][23468] Updated weights for policy 0, policy_version 49603 (0.0010) -[2023-10-09 10:17:10,301][23468] Updated weights for policy 0, policy_version 49613 (0.0007) -[2023-10-09 10:17:10,675][23468] Updated weights for policy 0, policy_version 49623 (0.0007) -[2023-10-09 10:17:11,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 101908480. Throughput: 0: 1782.8, 1: 1785.7. Samples: 25479798. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 10:17:11,078][22500] Avg episode reward: [(0, '8.110'), (1, '8.500')] -[2023-10-09 10:17:12,928][23469] Updated weights for policy 1, policy_version 49891 (0.0008) -[2023-10-09 10:17:13,292][23469] Updated weights for policy 1, policy_version 49901 (0.0008) -[2023-10-09 10:17:13,662][23469] Updated weights for policy 1, policy_version 49911 (0.0008) -[2023-10-09 10:17:14,354][23468] Updated weights for policy 0, policy_version 49633 (0.0007) -[2023-10-09 10:17:14,736][23468] Updated weights for policy 0, policy_version 49643 (0.0008) -[2023-10-09 10:17:15,108][23468] Updated weights for policy 0, policy_version 49653 (0.0009) -[2023-10-09 10:17:15,487][23468] Updated weights for policy 0, policy_version 49663 (0.0007) -[2023-10-09 10:17:16,078][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 101974016. Throughput: 0: 1784.7, 1: 1790.5. Samples: 25501492. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 10:17:16,079][22500] Avg episode reward: [(0, '8.100'), (1, '7.900')] -[2023-10-09 10:17:17,249][23469] Updated weights for policy 1, policy_version 49921 (0.0008) -[2023-10-09 10:17:17,610][23469] Updated weights for policy 1, policy_version 49931 (0.0008) -[2023-10-09 10:17:17,987][23469] Updated weights for policy 1, policy_version 49941 (0.0009) -[2023-10-09 10:17:18,354][23469] Updated weights for policy 1, policy_version 49951 (0.0010) -[2023-10-09 10:17:19,216][23468] Updated weights for policy 0, policy_version 49673 (0.0010) -[2023-10-09 10:17:19,590][23468] Updated weights for policy 0, policy_version 49683 (0.0010) -[2023-10-09 10:17:19,960][23468] Updated weights for policy 0, policy_version 49693 (0.0010) -[2023-10-09 10:17:21,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 102039552. Throughput: 0: 1788.8, 1: 1787.3. Samples: 25512448. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-09 10:17:21,078][22500] Avg episode reward: [(0, '8.680'), (1, '7.820')] -[2023-10-09 10:17:22,246][23469] Updated weights for policy 1, policy_version 49961 (0.0007) -[2023-10-09 10:17:22,615][23469] Updated weights for policy 1, policy_version 49971 (0.0008) -[2023-10-09 10:17:22,984][23469] Updated weights for policy 1, policy_version 49981 (0.0008) -[2023-10-09 10:17:23,657][23468] Updated weights for policy 0, policy_version 49703 (0.0009) -[2023-10-09 10:17:24,023][23468] Updated weights for policy 0, policy_version 49713 (0.0008) -[2023-10-09 10:17:24,403][23468] Updated weights for policy 0, policy_version 49723 (0.0009) -[2023-10-09 10:17:26,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 102105088. Throughput: 0: 1787.3, 1: 1788.1. Samples: 25533798. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-09 10:17:26,078][22500] Avg episode reward: [(0, '8.490'), (1, '8.200')] -[2023-10-09 10:17:26,737][23469] Updated weights for policy 1, policy_version 49991 (0.0007) -[2023-10-09 10:17:27,113][23469] Updated weights for policy 1, policy_version 50001 (0.0009) -[2023-10-09 10:17:27,475][23469] Updated weights for policy 1, policy_version 50011 (0.0009) -[2023-10-09 10:17:28,259][23468] Updated weights for policy 0, policy_version 49733 (0.0009) -[2023-10-09 10:17:28,630][23468] Updated weights for policy 0, policy_version 49743 (0.0008) -[2023-10-09 10:17:29,004][23468] Updated weights for policy 0, policy_version 49753 (0.0010) -[2023-10-09 10:17:31,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 102170624. Throughput: 0: 1781.6, 1: 1796.8. Samples: 25555574. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-09 10:17:31,078][22500] Avg episode reward: [(0, '7.790'), (1, '8.170')] -[2023-10-09 10:17:31,239][23469] Updated weights for policy 1, policy_version 50021 (0.0007) -[2023-10-09 10:17:31,607][23469] Updated weights for policy 1, policy_version 50031 (0.0008) -[2023-10-09 10:17:31,983][23469] Updated weights for policy 1, policy_version 50041 (0.0008) -[2023-10-09 10:17:32,858][23468] Updated weights for policy 0, policy_version 49763 (0.0008) -[2023-10-09 10:17:33,254][23468] Updated weights for policy 0, policy_version 49773 (0.0009) -[2023-10-09 10:17:33,624][23468] Updated weights for policy 0, policy_version 49783 (0.0009) -[2023-10-09 10:17:35,897][23469] Updated weights for policy 1, policy_version 50051 (0.0010) -[2023-10-09 10:17:36,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 102236160. Throughput: 0: 1799.1, 1: 1778.4. Samples: 25566032. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-09 10:17:36,078][22500] Avg episode reward: [(0, '7.950'), (1, '8.190')] -[2023-10-09 10:17:36,266][23469] Updated weights for policy 1, policy_version 50061 (0.0009) -[2023-10-09 10:17:36,630][23469] Updated weights for policy 1, policy_version 50071 (0.0009) -[2023-10-09 10:17:37,390][23468] Updated weights for policy 0, policy_version 49793 (0.0007) -[2023-10-09 10:17:37,769][23468] Updated weights for policy 0, policy_version 49803 (0.0007) -[2023-10-09 10:17:38,140][23468] Updated weights for policy 0, policy_version 49813 (0.0010) -[2023-10-09 10:17:38,517][23468] Updated weights for policy 0, policy_version 49823 (0.0009) -[2023-10-09 10:17:40,262][23469] Updated weights for policy 1, policy_version 50081 (0.0009) -[2023-10-09 10:17:40,623][23469] Updated weights for policy 1, policy_version 50091 (0.0011) -[2023-10-09 10:17:40,985][23469] Updated weights for policy 1, policy_version 50101 (0.0010) -[2023-10-09 10:17:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 102301696. Throughput: 0: 1782.3, 1: 1788.1. Samples: 25587174. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-09 10:17:41,078][22500] Avg episode reward: [(0, '8.300'), (1, '8.670')] -[2023-10-09 10:17:41,356][23469] Updated weights for policy 1, policy_version 50111 (0.0009) -[2023-10-09 10:17:42,407][23468] Updated weights for policy 0, policy_version 49833 (0.0010) -[2023-10-09 10:17:42,785][23468] Updated weights for policy 0, policy_version 49843 (0.0009) -[2023-10-09 10:17:43,154][23468] Updated weights for policy 0, policy_version 49853 (0.0011) -[2023-10-09 10:17:45,273][23469] Updated weights for policy 1, policy_version 50121 (0.0010) -[2023-10-09 10:17:45,637][23469] Updated weights for policy 1, policy_version 50131 (0.0008) -[2023-10-09 10:17:46,012][23469] Updated weights for policy 1, policy_version 50141 (0.0007) -[2023-10-09 10:17:46,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 102367232. Throughput: 0: 1781.6, 1: 1785.3. Samples: 25608392. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-09 10:17:46,079][22500] Avg episode reward: [(0, '8.340'), (1, '8.550')] -[2023-10-09 10:17:46,754][23468] Updated weights for policy 0, policy_version 49863 (0.0008) -[2023-10-09 10:17:47,116][23468] Updated weights for policy 0, policy_version 49873 (0.0008) -[2023-10-09 10:17:47,495][23468] Updated weights for policy 0, policy_version 49883 (0.0007) -[2023-10-09 10:17:49,662][23469] Updated weights for policy 1, policy_version 50151 (0.0007) -[2023-10-09 10:17:50,033][23469] Updated weights for policy 1, policy_version 50161 (0.0008) -[2023-10-09 10:17:50,404][23469] Updated weights for policy 1, policy_version 50171 (0.0009) -[2023-10-09 10:17:51,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 102465536. Throughput: 0: 1782.2, 1: 1784.8. Samples: 25619238. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-09 10:17:51,078][22500] Avg episode reward: [(0, '8.580'), (1, '8.650')] -[2023-10-09 10:17:51,284][23468] Updated weights for policy 0, policy_version 49893 (0.0009) -[2023-10-09 10:17:51,649][23468] Updated weights for policy 0, policy_version 49903 (0.0010) -[2023-10-09 10:17:52,028][23468] Updated weights for policy 0, policy_version 49913 (0.0009) -[2023-10-09 10:17:54,180][23469] Updated weights for policy 1, policy_version 50181 (0.0008) -[2023-10-09 10:17:54,555][23469] Updated weights for policy 1, policy_version 50191 (0.0009) -[2023-10-09 10:17:54,929][23469] Updated weights for policy 1, policy_version 50201 (0.0008) -[2023-10-09 10:17:55,779][23468] Updated weights for policy 0, policy_version 49923 (0.0007) -[2023-10-09 10:17:56,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 102531072. Throughput: 0: 1780.4, 1: 1794.7. Samples: 25640678. Policy #0 lag: (min: 1.0, avg: 9.0, max: 33.0) -[2023-10-09 10:17:56,078][22500] Avg episode reward: [(0, '8.160'), (1, '8.470')] -[2023-10-09 10:17:56,160][23468] Updated weights for policy 0, policy_version 49933 (0.0007) -[2023-10-09 10:17:56,528][23468] Updated weights for policy 0, policy_version 49943 (0.0008) -[2023-10-09 10:17:58,702][23469] Updated weights for policy 1, policy_version 50211 (0.0008) -[2023-10-09 10:17:59,070][23469] Updated weights for policy 1, policy_version 50221 (0.0007) -[2023-10-09 10:17:59,453][23469] Updated weights for policy 1, policy_version 50231 (0.0007) -[2023-10-09 10:18:00,323][23468] Updated weights for policy 0, policy_version 49953 (0.0007) -[2023-10-09 10:18:00,704][23468] Updated weights for policy 0, policy_version 49963 (0.0008) -[2023-10-09 10:18:01,065][23468] Updated weights for policy 0, policy_version 49973 (0.0007) -[2023-10-09 10:18:01,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 102596608. Throughput: 0: 1802.6, 1: 1779.2. Samples: 25662674. Policy #0 lag: (min: 1.0, avg: 9.0, max: 33.0) -[2023-10-09 10:18:01,079][22500] Avg episode reward: [(0, '8.160'), (1, '8.590')] -[2023-10-09 10:18:01,437][23468] Updated weights for policy 0, policy_version 49983 (0.0009) -[2023-10-09 10:18:03,199][23469] Updated weights for policy 1, policy_version 50241 (0.0008) -[2023-10-09 10:18:03,558][23469] Updated weights for policy 1, policy_version 50251 (0.0008) -[2023-10-09 10:18:03,933][23469] Updated weights for policy 1, policy_version 50261 (0.0008) -[2023-10-09 10:18:04,306][23469] Updated weights for policy 1, policy_version 50271 (0.0008) -[2023-10-09 10:18:05,173][23468] Updated weights for policy 0, policy_version 49993 (0.0009) -[2023-10-09 10:18:05,544][23468] Updated weights for policy 0, policy_version 50003 (0.0008) -[2023-10-09 10:18:05,921][23468] Updated weights for policy 0, policy_version 50013 (0.0009) -[2023-10-09 10:18:06,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 102694912. Throughput: 0: 1774.8, 1: 1796.9. Samples: 25673178. Policy #0 lag: (min: 1.0, avg: 9.0, max: 33.0) -[2023-10-09 10:18:06,078][22500] Avg episode reward: [(0, '7.630'), (1, '8.530')] -[2023-10-09 10:18:08,020][23469] Updated weights for policy 1, policy_version 50281 (0.0008) -[2023-10-09 10:18:08,384][23469] Updated weights for policy 1, policy_version 50291 (0.0008) -[2023-10-09 10:18:08,758][23469] Updated weights for policy 1, policy_version 50301 (0.0009) -[2023-10-09 10:18:09,705][23468] Updated weights for policy 0, policy_version 50023 (0.0008) -[2023-10-09 10:18:10,083][23468] Updated weights for policy 0, policy_version 50033 (0.0009) -[2023-10-09 10:18:10,465][23468] Updated weights for policy 0, policy_version 50043 (0.0011) -[2023-10-09 10:18:11,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 102760448. Throughput: 0: 1796.3, 1: 1782.3. Samples: 25694838. Policy #0 lag: (min: 1.0, avg: 9.0, max: 33.0) -[2023-10-09 10:18:11,078][22500] Avg episode reward: [(0, '8.670'), (1, '9.200')] -[2023-10-09 10:18:11,080][23343] Saving new best policy, reward=9.200! -[2023-10-09 10:18:12,461][23469] Updated weights for policy 1, policy_version 50311 (0.0010) -[2023-10-09 10:18:12,830][23469] Updated weights for policy 1, policy_version 50321 (0.0010) -[2023-10-09 10:18:13,206][23469] Updated weights for policy 1, policy_version 50331 (0.0011) -[2023-10-09 10:18:14,126][23468] Updated weights for policy 0, policy_version 50053 (0.0010) -[2023-10-09 10:18:14,503][23468] Updated weights for policy 0, policy_version 50063 (0.0007) -[2023-10-09 10:18:14,883][23468] Updated weights for policy 0, policy_version 50073 (0.0009) -[2023-10-09 10:18:16,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 102825984. Throughput: 0: 1771.7, 1: 1782.4. Samples: 25715506. Policy #0 lag: (min: 1.0, avg: 9.0, max: 33.0) -[2023-10-09 10:18:16,078][22500] Avg episode reward: [(0, '9.030'), (1, '8.240')] -[2023-10-09 10:18:16,087][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000050336_51544064.pth... -[2023-10-09 10:18:16,088][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000050080_51281920.pth... -[2023-10-09 10:18:16,128][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000048416_49577984.pth -[2023-10-09 10:18:16,128][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000048672_49840128.pth -[2023-10-09 10:18:17,053][23469] Updated weights for policy 1, policy_version 50341 (0.0008) -[2023-10-09 10:18:17,425][23469] Updated weights for policy 1, policy_version 50351 (0.0007) -[2023-10-09 10:18:17,792][23469] Updated weights for policy 1, policy_version 50361 (0.0008) -[2023-10-09 10:18:18,746][23468] Updated weights for policy 0, policy_version 50083 (0.0009) -[2023-10-09 10:18:19,138][23468] Updated weights for policy 0, policy_version 50093 (0.0007) -[2023-10-09 10:18:19,518][23468] Updated weights for policy 0, policy_version 50103 (0.0008) -[2023-10-09 10:18:21,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 102891520. Throughput: 0: 1794.1, 1: 1782.4. Samples: 25726978. Policy #0 lag: (min: 1.0, avg: 9.0, max: 33.0) -[2023-10-09 10:18:21,079][22500] Avg episode reward: [(0, '9.460'), (1, '8.340')] -[2023-10-09 10:18:21,502][23469] Updated weights for policy 1, policy_version 50371 (0.0010) -[2023-10-09 10:18:21,874][23469] Updated weights for policy 1, policy_version 50381 (0.0010) -[2023-10-09 10:18:22,246][23469] Updated weights for policy 1, policy_version 50391 (0.0009) -[2023-10-09 10:18:23,209][23468] Updated weights for policy 0, policy_version 50113 (0.0008) -[2023-10-09 10:18:23,574][23468] Updated weights for policy 0, policy_version 50123 (0.0007) -[2023-10-09 10:18:23,951][23468] Updated weights for policy 0, policy_version 50133 (0.0008) -[2023-10-09 10:18:24,324][23468] Updated weights for policy 0, policy_version 50143 (0.0007) -[2023-10-09 10:18:26,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 102957056. Throughput: 0: 1784.8, 1: 1791.4. Samples: 25748104. Policy #0 lag: (min: 15.0, avg: 22.1, max: 47.0) -[2023-10-09 10:18:26,078][22500] Avg episode reward: [(0, '8.610'), (1, '8.140')] -[2023-10-09 10:18:26,087][23469] Updated weights for policy 1, policy_version 50401 (0.0009) -[2023-10-09 10:18:26,505][23469] Updated weights for policy 1, policy_version 50411 (0.0009) -[2023-10-09 10:18:26,867][23469] Updated weights for policy 1, policy_version 50421 (0.0009) -[2023-10-09 10:18:27,233][23469] Updated weights for policy 1, policy_version 50431 (0.0010) -[2023-10-09 10:18:28,080][23468] Updated weights for policy 0, policy_version 50153 (0.0007) -[2023-10-09 10:18:28,462][23468] Updated weights for policy 0, policy_version 50163 (0.0007) -[2023-10-09 10:18:28,827][23468] Updated weights for policy 0, policy_version 50173 (0.0008) -[2023-10-09 10:18:30,945][23469] Updated weights for policy 1, policy_version 50441 (0.0009) -[2023-10-09 10:18:31,078][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 103022592. Throughput: 0: 1776.3, 1: 1812.2. Samples: 25769876. Policy #0 lag: (min: 15.0, avg: 22.1, max: 47.0) -[2023-10-09 10:18:31,079][22500] Avg episode reward: [(0, '8.340'), (1, '7.200')] -[2023-10-09 10:18:31,317][23469] Updated weights for policy 1, policy_version 50451 (0.0008) -[2023-10-09 10:18:31,691][23469] Updated weights for policy 1, policy_version 50461 (0.0009) -[2023-10-09 10:18:32,812][23468] Updated weights for policy 0, policy_version 50183 (0.0009) -[2023-10-09 10:18:33,180][23468] Updated weights for policy 0, policy_version 50193 (0.0009) -[2023-10-09 10:18:33,549][23468] Updated weights for policy 0, policy_version 50203 (0.0008) -[2023-10-09 10:18:35,240][23469] Updated weights for policy 1, policy_version 50471 (0.0008) -[2023-10-09 10:18:35,603][23469] Updated weights for policy 1, policy_version 50481 (0.0007) -[2023-10-09 10:18:35,978][23469] Updated weights for policy 1, policy_version 50491 (0.0009) -[2023-10-09 10:18:36,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 103088128. Throughput: 0: 1789.0, 1: 1795.2. Samples: 25780524. Policy #0 lag: (min: 15.0, avg: 22.1, max: 47.0) -[2023-10-09 10:18:36,078][22500] Avg episode reward: [(0, '8.130'), (1, '7.530')] -[2023-10-09 10:18:37,382][23468] Updated weights for policy 0, policy_version 50213 (0.0010) -[2023-10-09 10:18:37,756][23468] Updated weights for policy 0, policy_version 50223 (0.0010) -[2023-10-09 10:18:38,134][23468] Updated weights for policy 0, policy_version 50233 (0.0009) -[2023-10-09 10:18:39,735][23469] Updated weights for policy 1, policy_version 50501 (0.0009) -[2023-10-09 10:18:40,117][23469] Updated weights for policy 1, policy_version 50511 (0.0009) -[2023-10-09 10:18:40,486][23469] Updated weights for policy 1, policy_version 50521 (0.0009) -[2023-10-09 10:18:41,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 103186432. Throughput: 0: 1769.4, 1: 1813.7. Samples: 25801918. Policy #0 lag: (min: 15.0, avg: 22.1, max: 47.0) -[2023-10-09 10:18:41,078][22500] Avg episode reward: [(0, '8.010'), (1, '7.260')] -[2023-10-09 10:18:41,755][23468] Updated weights for policy 0, policy_version 50243 (0.0010) -[2023-10-09 10:18:42,125][23468] Updated weights for policy 0, policy_version 50253 (0.0009) -[2023-10-09 10:18:42,506][23468] Updated weights for policy 0, policy_version 50263 (0.0010) -[2023-10-09 10:18:44,200][23469] Updated weights for policy 1, policy_version 50531 (0.0008) -[2023-10-09 10:18:44,572][23469] Updated weights for policy 1, policy_version 50541 (0.0009) -[2023-10-09 10:18:44,941][23469] Updated weights for policy 1, policy_version 50551 (0.0008) -[2023-10-09 10:18:46,078][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 103251968. Throughput: 0: 1774.0, 1: 1795.4. Samples: 25823298. Policy #0 lag: (min: 15.0, avg: 22.1, max: 47.0) -[2023-10-09 10:18:46,079][22500] Avg episode reward: [(0, '7.690'), (1, '7.710')] -[2023-10-09 10:18:46,439][23468] Updated weights for policy 0, policy_version 50273 (0.0007) -[2023-10-09 10:18:46,820][23468] Updated weights for policy 0, policy_version 50283 (0.0009) -[2023-10-09 10:18:47,197][23468] Updated weights for policy 0, policy_version 50293 (0.0007) -[2023-10-09 10:18:47,571][23468] Updated weights for policy 0, policy_version 50303 (0.0007) -[2023-10-09 10:18:48,759][23469] Updated weights for policy 1, policy_version 50561 (0.0008) -[2023-10-09 10:18:49,122][23469] Updated weights for policy 1, policy_version 50571 (0.0007) -[2023-10-09 10:18:49,494][23469] Updated weights for policy 1, policy_version 50581 (0.0008) -[2023-10-09 10:18:49,863][23469] Updated weights for policy 1, policy_version 50591 (0.0007) -[2023-10-09 10:18:51,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 103317504. Throughput: 0: 1769.3, 1: 1810.4. Samples: 25834266. Policy #0 lag: (min: 15.0, avg: 22.1, max: 47.0) -[2023-10-09 10:18:51,078][22500] Avg episode reward: [(0, '7.940'), (1, '8.250')] -[2023-10-09 10:18:51,319][23468] Updated weights for policy 0, policy_version 50313 (0.0009) -[2023-10-09 10:18:51,701][23468] Updated weights for policy 0, policy_version 50323 (0.0009) -[2023-10-09 10:18:52,066][23468] Updated weights for policy 0, policy_version 50333 (0.0007) -[2023-10-09 10:18:53,530][23469] Updated weights for policy 1, policy_version 50601 (0.0007) -[2023-10-09 10:18:53,911][23469] Updated weights for policy 1, policy_version 50611 (0.0009) -[2023-10-09 10:18:54,279][23469] Updated weights for policy 1, policy_version 50621 (0.0011) -[2023-10-09 10:18:55,724][23468] Updated weights for policy 0, policy_version 50343 (0.0009) -[2023-10-09 10:18:56,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 103383040. Throughput: 0: 1773.7, 1: 1794.2. Samples: 25855396. Policy #0 lag: (min: 15.0, avg: 22.1, max: 47.0) -[2023-10-09 10:18:56,078][22500] Avg episode reward: [(0, '7.950'), (1, '8.370')] -[2023-10-09 10:18:56,108][23468] Updated weights for policy 0, policy_version 50353 (0.0008) -[2023-10-09 10:18:56,485][23468] Updated weights for policy 0, policy_version 50363 (0.0008) -[2023-10-09 10:18:58,112][23469] Updated weights for policy 1, policy_version 50631 (0.0008) -[2023-10-09 10:18:58,479][23469] Updated weights for policy 1, policy_version 50641 (0.0008) -[2023-10-09 10:18:58,849][23469] Updated weights for policy 1, policy_version 50651 (0.0009) -[2023-10-09 10:19:00,084][23468] Updated weights for policy 0, policy_version 50373 (0.0009) -[2023-10-09 10:19:00,461][23468] Updated weights for policy 0, policy_version 50383 (0.0009) -[2023-10-09 10:19:00,828][23468] Updated weights for policy 0, policy_version 50393 (0.0009) -[2023-10-09 10:19:01,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 103448576. Throughput: 0: 1802.1, 1: 1796.5. Samples: 25877446. Policy #0 lag: (min: 14.0, avg: 14.1, max: 20.0) -[2023-10-09 10:19:01,078][22500] Avg episode reward: [(0, '8.510'), (1, '8.100')] -[2023-10-09 10:19:02,715][23469] Updated weights for policy 1, policy_version 50661 (0.0008) -[2023-10-09 10:19:03,083][23469] Updated weights for policy 1, policy_version 50671 (0.0007) -[2023-10-09 10:19:03,462][23469] Updated weights for policy 1, policy_version 50681 (0.0007) -[2023-10-09 10:19:04,774][23468] Updated weights for policy 0, policy_version 50403 (0.0008) -[2023-10-09 10:19:05,167][23468] Updated weights for policy 0, policy_version 50413 (0.0009) -[2023-10-09 10:19:05,537][23468] Updated weights for policy 0, policy_version 50423 (0.0012) -[2023-10-09 10:19:06,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 103546880. Throughput: 0: 1772.4, 1: 1796.8. Samples: 25887590. Policy #0 lag: (min: 14.0, avg: 14.1, max: 20.0) -[2023-10-09 10:19:06,078][22500] Avg episode reward: [(0, '8.690'), (1, '8.240')] -[2023-10-09 10:19:07,307][23469] Updated weights for policy 1, policy_version 50691 (0.0010) -[2023-10-09 10:19:07,678][23469] Updated weights for policy 1, policy_version 50701 (0.0008) -[2023-10-09 10:19:08,050][23469] Updated weights for policy 1, policy_version 50711 (0.0007) -[2023-10-09 10:19:09,296][23468] Updated weights for policy 0, policy_version 50433 (0.0007) -[2023-10-09 10:19:09,669][23468] Updated weights for policy 0, policy_version 50443 (0.0010) -[2023-10-09 10:19:10,049][23468] Updated weights for policy 0, policy_version 50453 (0.0011) -[2023-10-09 10:19:10,420][23468] Updated weights for policy 0, policy_version 50463 (0.0008) -[2023-10-09 10:19:11,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 103612416. Throughput: 0: 1798.4, 1: 1791.9. Samples: 25909664. Policy #0 lag: (min: 14.0, avg: 14.1, max: 20.0) -[2023-10-09 10:19:11,078][22500] Avg episode reward: [(0, '8.800'), (1, '7.550')] -[2023-10-09 10:19:11,871][23469] Updated weights for policy 1, policy_version 50721 (0.0009) -[2023-10-09 10:19:12,302][23469] Updated weights for policy 1, policy_version 50731 (0.0007) -[2023-10-09 10:19:12,677][23469] Updated weights for policy 1, policy_version 50741 (0.0009) -[2023-10-09 10:19:13,051][23469] Updated weights for policy 1, policy_version 50751 (0.0009) -[2023-10-09 10:19:14,183][23468] Updated weights for policy 0, policy_version 50473 (0.0008) -[2023-10-09 10:19:14,562][23468] Updated weights for policy 0, policy_version 50483 (0.0009) -[2023-10-09 10:19:14,938][23468] Updated weights for policy 0, policy_version 50493 (0.0007) -[2023-10-09 10:19:16,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 103677952. Throughput: 0: 1775.8, 1: 1791.6. Samples: 25930406. Policy #0 lag: (min: 14.0, avg: 14.1, max: 20.0) -[2023-10-09 10:19:16,079][22500] Avg episode reward: [(0, '8.730'), (1, '7.910')] -[2023-10-09 10:19:16,806][23469] Updated weights for policy 1, policy_version 50761 (0.0009) -[2023-10-09 10:19:17,176][23469] Updated weights for policy 1, policy_version 50771 (0.0007) -[2023-10-09 10:19:17,544][23469] Updated weights for policy 1, policy_version 50781 (0.0009) -[2023-10-09 10:19:18,613][23468] Updated weights for policy 0, policy_version 50503 (0.0009) -[2023-10-09 10:19:18,978][23468] Updated weights for policy 0, policy_version 50513 (0.0011) -[2023-10-09 10:19:19,351][23468] Updated weights for policy 0, policy_version 50523 (0.0011) -[2023-10-09 10:19:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 103743488. Throughput: 0: 1799.9, 1: 1778.5. Samples: 25941550. Policy #0 lag: (min: 14.0, avg: 14.1, max: 20.0) -[2023-10-09 10:19:21,078][22500] Avg episode reward: [(0, '8.970'), (1, '7.930')] -[2023-10-09 10:19:21,412][23469] Updated weights for policy 1, policy_version 50791 (0.0010) -[2023-10-09 10:19:21,779][23469] Updated weights for policy 1, policy_version 50801 (0.0011) -[2023-10-09 10:19:22,146][23469] Updated weights for policy 1, policy_version 50811 (0.0009) -[2023-10-09 10:19:23,240][23468] Updated weights for policy 0, policy_version 50533 (0.0009) -[2023-10-09 10:19:23,615][23468] Updated weights for policy 0, policy_version 50543 (0.0007) -[2023-10-09 10:19:24,001][23468] Updated weights for policy 0, policy_version 50553 (0.0008) -[2023-10-09 10:19:25,823][23469] Updated weights for policy 1, policy_version 50821 (0.0007) -[2023-10-09 10:19:26,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 103809024. Throughput: 0: 1780.2, 1: 1778.7. Samples: 25962066. Policy #0 lag: (min: 14.0, avg: 14.1, max: 20.0) -[2023-10-09 10:19:26,078][22500] Avg episode reward: [(0, '9.080'), (1, '7.790')] -[2023-10-09 10:19:26,198][23469] Updated weights for policy 1, policy_version 50831 (0.0008) -[2023-10-09 10:19:26,567][23469] Updated weights for policy 1, policy_version 50841 (0.0007) -[2023-10-09 10:19:27,687][23468] Updated weights for policy 0, policy_version 50563 (0.0008) -[2023-10-09 10:19:28,066][23468] Updated weights for policy 0, policy_version 50573 (0.0008) -[2023-10-09 10:19:28,438][23468] Updated weights for policy 0, policy_version 50583 (0.0008) -[2023-10-09 10:19:30,273][23469] Updated weights for policy 1, policy_version 50851 (0.0008) -[2023-10-09 10:19:30,636][23469] Updated weights for policy 1, policy_version 50861 (0.0009) -[2023-10-09 10:19:31,012][23469] Updated weights for policy 1, policy_version 50871 (0.0009) -[2023-10-09 10:19:31,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 103874560. Throughput: 0: 1776.5, 1: 1790.9. Samples: 25983832. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 10:19:31,079][22500] Avg episode reward: [(0, '8.320'), (1, '7.830')] -[2023-10-09 10:19:32,133][23468] Updated weights for policy 0, policy_version 50593 (0.0010) -[2023-10-09 10:19:32,506][23468] Updated weights for policy 0, policy_version 50603 (0.0007) -[2023-10-09 10:19:32,876][23468] Updated weights for policy 0, policy_version 50613 (0.0007) -[2023-10-09 10:19:33,255][23468] Updated weights for policy 0, policy_version 50623 (0.0008) -[2023-10-09 10:19:34,949][23469] Updated weights for policy 1, policy_version 50881 (0.0009) -[2023-10-09 10:19:35,319][23469] Updated weights for policy 1, policy_version 50891 (0.0009) -[2023-10-09 10:19:35,688][23469] Updated weights for policy 1, policy_version 50901 (0.0010) -[2023-10-09 10:19:36,048][23469] Updated weights for policy 1, policy_version 50911 (0.0008) -[2023-10-09 10:19:36,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 103940096. Throughput: 0: 1783.7, 1: 1771.4. Samples: 25994246. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 10:19:36,078][22500] Avg episode reward: [(0, '8.290'), (1, '8.190')] -[2023-10-09 10:19:37,001][23468] Updated weights for policy 0, policy_version 50633 (0.0007) -[2023-10-09 10:19:37,376][23468] Updated weights for policy 0, policy_version 50643 (0.0010) -[2023-10-09 10:19:37,746][23468] Updated weights for policy 0, policy_version 50653 (0.0008) -[2023-10-09 10:19:39,784][23469] Updated weights for policy 1, policy_version 50921 (0.0007) -[2023-10-09 10:19:40,157][23469] Updated weights for policy 1, policy_version 50931 (0.0007) -[2023-10-09 10:19:40,526][23469] Updated weights for policy 1, policy_version 50941 (0.0011) -[2023-10-09 10:19:41,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 104038400. Throughput: 0: 1783.2, 1: 1792.1. Samples: 26016282. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 10:19:41,078][22500] Avg episode reward: [(0, '8.510'), (1, '8.390')] -[2023-10-09 10:19:41,485][23468] Updated weights for policy 0, policy_version 50663 (0.0009) -[2023-10-09 10:19:41,865][23468] Updated weights for policy 0, policy_version 50673 (0.0011) -[2023-10-09 10:19:42,237][23468] Updated weights for policy 0, policy_version 50683 (0.0011) -[2023-10-09 10:19:44,252][23469] Updated weights for policy 1, policy_version 50951 (0.0009) -[2023-10-09 10:19:44,626][23469] Updated weights for policy 1, policy_version 50961 (0.0007) -[2023-10-09 10:19:44,989][23469] Updated weights for policy 1, policy_version 50971 (0.0007) -[2023-10-09 10:19:45,871][23468] Updated weights for policy 0, policy_version 50693 (0.0009) -[2023-10-09 10:19:46,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 104103936. Throughput: 0: 1793.1, 1: 1772.4. Samples: 26037894. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 10:19:46,079][22500] Avg episode reward: [(0, '8.590'), (1, '8.120')] -[2023-10-09 10:19:46,245][23468] Updated weights for policy 0, policy_version 50703 (0.0009) -[2023-10-09 10:19:46,622][23468] Updated weights for policy 0, policy_version 50713 (0.0009) -[2023-10-09 10:19:48,798][23469] Updated weights for policy 1, policy_version 50981 (0.0007) -[2023-10-09 10:19:49,177][23469] Updated weights for policy 1, policy_version 50991 (0.0007) -[2023-10-09 10:19:49,553][23469] Updated weights for policy 1, policy_version 51001 (0.0010) -[2023-10-09 10:19:50,486][23468] Updated weights for policy 0, policy_version 50723 (0.0007) -[2023-10-09 10:19:50,868][23468] Updated weights for policy 0, policy_version 50733 (0.0008) -[2023-10-09 10:19:51,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 104169472. Throughput: 0: 1780.3, 1: 1800.4. Samples: 26048720. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 10:19:51,079][22500] Avg episode reward: [(0, '8.660'), (1, '7.480')] -[2023-10-09 10:19:51,245][23468] Updated weights for policy 0, policy_version 50743 (0.0007) -[2023-10-09 10:19:53,139][23469] Updated weights for policy 1, policy_version 51011 (0.0008) -[2023-10-09 10:19:53,517][23469] Updated weights for policy 1, policy_version 51021 (0.0009) -[2023-10-09 10:19:53,889][23469] Updated weights for policy 1, policy_version 51031 (0.0010) -[2023-10-09 10:19:55,038][23468] Updated weights for policy 0, policy_version 50753 (0.0008) -[2023-10-09 10:19:55,406][23468] Updated weights for policy 0, policy_version 50763 (0.0008) -[2023-10-09 10:19:55,771][23468] Updated weights for policy 0, policy_version 50773 (0.0011) -[2023-10-09 10:19:56,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 104235008. Throughput: 0: 1781.4, 1: 1772.7. Samples: 26069598. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 10:19:56,078][22500] Avg episode reward: [(0, '9.150'), (1, '7.460')] -[2023-10-09 10:19:56,144][23468] Updated weights for policy 0, policy_version 50783 (0.0008) -[2023-10-09 10:19:57,652][23469] Updated weights for policy 1, policy_version 51041 (0.0010) -[2023-10-09 10:19:58,064][23469] Updated weights for policy 1, policy_version 51051 (0.0009) -[2023-10-09 10:19:58,436][23469] Updated weights for policy 1, policy_version 51061 (0.0009) -[2023-10-09 10:19:58,804][23469] Updated weights for policy 1, policy_version 51071 (0.0008) -[2023-10-09 10:19:59,962][23468] Updated weights for policy 0, policy_version 50793 (0.0008) -[2023-10-09 10:20:00,335][23468] Updated weights for policy 0, policy_version 50803 (0.0008) -[2023-10-09 10:20:00,703][23468] Updated weights for policy 0, policy_version 50813 (0.0009) -[2023-10-09 10:20:01,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 104333312. Throughput: 0: 1791.9, 1: 1780.0. Samples: 26091142. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 10:20:01,078][22500] Avg episode reward: [(0, '9.110'), (1, '8.190')] -[2023-10-09 10:20:02,530][23469] Updated weights for policy 1, policy_version 51081 (0.0010) -[2023-10-09 10:20:02,901][23469] Updated weights for policy 1, policy_version 51091 (0.0008) -[2023-10-09 10:20:03,276][23469] Updated weights for policy 1, policy_version 51101 (0.0010) -[2023-10-09 10:20:04,434][23468] Updated weights for policy 0, policy_version 50823 (0.0007) -[2023-10-09 10:20:04,815][23468] Updated weights for policy 0, policy_version 50833 (0.0007) -[2023-10-09 10:20:05,177][23468] Updated weights for policy 0, policy_version 50843 (0.0007) -[2023-10-09 10:20:06,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 104398848. Throughput: 0: 1775.7, 1: 1783.4. Samples: 26101710. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:20:06,078][22500] Avg episode reward: [(0, '8.630'), (1, '8.090')] -[2023-10-09 10:20:07,014][23469] Updated weights for policy 1, policy_version 51111 (0.0011) -[2023-10-09 10:20:07,384][23469] Updated weights for policy 1, policy_version 51121 (0.0011) -[2023-10-09 10:20:07,758][23469] Updated weights for policy 1, policy_version 51131 (0.0010) -[2023-10-09 10:20:09,077][23468] Updated weights for policy 0, policy_version 50853 (0.0010) -[2023-10-09 10:20:09,445][23468] Updated weights for policy 0, policy_version 50863 (0.0008) -[2023-10-09 10:20:09,819][23468] Updated weights for policy 0, policy_version 50873 (0.0008) -[2023-10-09 10:20:11,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 104464384. Throughput: 0: 1802.1, 1: 1786.6. Samples: 26123558. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:20:11,078][22500] Avg episode reward: [(0, '8.100'), (1, '8.550')] -[2023-10-09 10:20:11,515][23469] Updated weights for policy 1, policy_version 51141 (0.0009) -[2023-10-09 10:20:11,880][23469] Updated weights for policy 1, policy_version 51151 (0.0007) -[2023-10-09 10:20:12,249][23469] Updated weights for policy 1, policy_version 51161 (0.0009) -[2023-10-09 10:20:13,652][23468] Updated weights for policy 0, policy_version 50883 (0.0008) -[2023-10-09 10:20:14,024][23468] Updated weights for policy 0, policy_version 50893 (0.0009) -[2023-10-09 10:20:14,403][23468] Updated weights for policy 0, policy_version 50903 (0.0009) -[2023-10-09 10:20:15,975][23469] Updated weights for policy 1, policy_version 51171 (0.0009) -[2023-10-09 10:20:16,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 104529920. Throughput: 0: 1776.6, 1: 1803.9. Samples: 26144956. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:20:16,078][22500] Avg episode reward: [(0, '7.610'), (1, '8.050')] -[2023-10-09 10:20:16,085][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000050912_52133888.pth... -[2023-10-09 10:20:16,126][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000049248_50429952.pth -[2023-10-09 10:20:16,346][23469] Updated weights for policy 1, policy_version 51181 (0.0010) -[2023-10-09 10:20:16,717][23469] Updated weights for policy 1, policy_version 51191 (0.0008) -[2023-10-09 10:20:17,040][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000051200_52428800.pth... -[2023-10-09 10:20:17,080][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000049504_50692096.pth -[2023-10-09 10:20:18,147][23468] Updated weights for policy 0, policy_version 50913 (0.0007) -[2023-10-09 10:20:18,522][23468] Updated weights for policy 0, policy_version 50923 (0.0009) -[2023-10-09 10:20:18,895][23468] Updated weights for policy 0, policy_version 50933 (0.0009) -[2023-10-09 10:20:19,271][23468] Updated weights for policy 0, policy_version 50943 (0.0009) -[2023-10-09 10:20:20,451][23469] Updated weights for policy 1, policy_version 51201 (0.0009) -[2023-10-09 10:20:20,827][23469] Updated weights for policy 1, policy_version 51211 (0.0010) -[2023-10-09 10:20:21,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 104595456. Throughput: 0: 1802.2, 1: 1792.3. Samples: 26156000. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:20:21,078][22500] Avg episode reward: [(0, '8.160'), (1, '8.000')] -[2023-10-09 10:20:21,191][23469] Updated weights for policy 1, policy_version 51221 (0.0008) -[2023-10-09 10:20:21,559][23469] Updated weights for policy 1, policy_version 51231 (0.0009) -[2023-10-09 10:20:23,110][23468] Updated weights for policy 0, policy_version 50953 (0.0008) -[2023-10-09 10:20:23,487][23468] Updated weights for policy 0, policy_version 50963 (0.0007) -[2023-10-09 10:20:23,854][23468] Updated weights for policy 0, policy_version 50973 (0.0008) -[2023-10-09 10:20:25,191][23469] Updated weights for policy 1, policy_version 51241 (0.0007) -[2023-10-09 10:20:25,549][23469] Updated weights for policy 1, policy_version 51251 (0.0008) -[2023-10-09 10:20:25,923][23469] Updated weights for policy 1, policy_version 51261 (0.0007) -[2023-10-09 10:20:26,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 104693760. Throughput: 0: 1771.4, 1: 1806.6. Samples: 26177292. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:20:26,078][22500] Avg episode reward: [(0, '8.080'), (1, '7.800')] -[2023-10-09 10:20:27,594][23468] Updated weights for policy 0, policy_version 50983 (0.0009) -[2023-10-09 10:20:27,958][23468] Updated weights for policy 0, policy_version 50993 (0.0008) -[2023-10-09 10:20:28,337][23468] Updated weights for policy 0, policy_version 51003 (0.0008) -[2023-10-09 10:20:29,712][23469] Updated weights for policy 1, policy_version 51271 (0.0007) -[2023-10-09 10:20:30,091][23469] Updated weights for policy 1, policy_version 51281 (0.0010) -[2023-10-09 10:20:30,458][23469] Updated weights for policy 1, policy_version 51291 (0.0007) -[2023-10-09 10:20:31,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 104759296. Throughput: 0: 1770.5, 1: 1796.1. Samples: 26198390. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:20:31,078][22500] Avg episode reward: [(0, '9.190'), (1, '7.830')] -[2023-10-09 10:20:31,994][23468] Updated weights for policy 0, policy_version 51013 (0.0008) -[2023-10-09 10:20:32,371][23468] Updated weights for policy 0, policy_version 51023 (0.0008) -[2023-10-09 10:20:32,746][23468] Updated weights for policy 0, policy_version 51033 (0.0008) -[2023-10-09 10:20:34,205][23469] Updated weights for policy 1, policy_version 51301 (0.0009) -[2023-10-09 10:20:34,584][23469] Updated weights for policy 1, policy_version 51311 (0.0009) -[2023-10-09 10:20:34,959][23469] Updated weights for policy 1, policy_version 51321 (0.0009) -[2023-10-09 10:20:36,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 104824832. Throughput: 0: 1774.0, 1: 1801.8. Samples: 26209630. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:20:36,078][22500] Avg episode reward: [(0, '9.390'), (1, '8.170')] -[2023-10-09 10:20:36,546][23468] Updated weights for policy 0, policy_version 51043 (0.0008) -[2023-10-09 10:20:36,944][23468] Updated weights for policy 0, policy_version 51053 (0.0008) -[2023-10-09 10:20:37,312][23468] Updated weights for policy 0, policy_version 51063 (0.0009) -[2023-10-09 10:20:38,737][23469] Updated weights for policy 1, policy_version 51331 (0.0008) -[2023-10-09 10:20:39,103][23469] Updated weights for policy 1, policy_version 51341 (0.0008) -[2023-10-09 10:20:39,476][23469] Updated weights for policy 1, policy_version 51351 (0.0009) -[2023-10-09 10:20:41,046][23468] Updated weights for policy 0, policy_version 51073 (0.0009) -[2023-10-09 10:20:41,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 104890368. Throughput: 0: 1773.8, 1: 1795.6. Samples: 26230220. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:20:41,078][22500] Avg episode reward: [(0, '9.470'), (1, '7.630')] -[2023-10-09 10:20:41,416][23468] Updated weights for policy 0, policy_version 51083 (0.0007) -[2023-10-09 10:20:41,793][23468] Updated weights for policy 0, policy_version 51093 (0.0009) -[2023-10-09 10:20:42,171][23468] Updated weights for policy 0, policy_version 51103 (0.0009) -[2023-10-09 10:20:43,270][23469] Updated weights for policy 1, policy_version 51361 (0.0010) -[2023-10-09 10:20:43,696][23469] Updated weights for policy 1, policy_version 51371 (0.0009) -[2023-10-09 10:20:44,072][23469] Updated weights for policy 1, policy_version 51381 (0.0008) -[2023-10-09 10:20:44,440][23469] Updated weights for policy 1, policy_version 51391 (0.0008) -[2023-10-09 10:20:45,845][23468] Updated weights for policy 0, policy_version 51113 (0.0009) -[2023-10-09 10:20:46,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 104955904. Throughput: 0: 1798.8, 1: 1787.6. Samples: 26252532. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-09 10:20:46,079][22500] Avg episode reward: [(0, '8.790'), (1, '8.380')] -[2023-10-09 10:20:46,215][23468] Updated weights for policy 0, policy_version 51123 (0.0009) -[2023-10-09 10:20:46,591][23468] Updated weights for policy 0, policy_version 51133 (0.0008) -[2023-10-09 10:20:48,185][23469] Updated weights for policy 1, policy_version 51401 (0.0010) -[2023-10-09 10:20:48,548][23469] Updated weights for policy 1, policy_version 51411 (0.0010) -[2023-10-09 10:20:48,924][23469] Updated weights for policy 1, policy_version 51421 (0.0010) -[2023-10-09 10:20:50,324][23468] Updated weights for policy 0, policy_version 51143 (0.0010) -[2023-10-09 10:20:50,692][23468] Updated weights for policy 0, policy_version 51153 (0.0009) -[2023-10-09 10:20:51,066][23468] Updated weights for policy 0, policy_version 51163 (0.0007) -[2023-10-09 10:20:51,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 105021440. Throughput: 0: 1781.1, 1: 1795.8. Samples: 26262672. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-09 10:20:51,078][22500] Avg episode reward: [(0, '9.140'), (1, '7.640')] -[2023-10-09 10:20:52,769][23469] Updated weights for policy 1, policy_version 51431 (0.0008) -[2023-10-09 10:20:53,148][23469] Updated weights for policy 1, policy_version 51441 (0.0008) -[2023-10-09 10:20:53,519][23469] Updated weights for policy 1, policy_version 51451 (0.0008) -[2023-10-09 10:20:54,809][23468] Updated weights for policy 0, policy_version 51173 (0.0008) -[2023-10-09 10:20:55,184][23468] Updated weights for policy 0, policy_version 51183 (0.0009) -[2023-10-09 10:20:55,559][23468] Updated weights for policy 0, policy_version 51193 (0.0009) -[2023-10-09 10:20:56,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 105119744. Throughput: 0: 1792.7, 1: 1788.6. Samples: 26284714. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-09 10:20:56,079][22500] Avg episode reward: [(0, '8.610'), (1, '8.160')] -[2023-10-09 10:20:57,099][23469] Updated weights for policy 1, policy_version 51461 (0.0009) -[2023-10-09 10:20:57,469][23469] Updated weights for policy 1, policy_version 51471 (0.0010) -[2023-10-09 10:20:57,838][23469] Updated weights for policy 1, policy_version 51481 (0.0010) -[2023-10-09 10:20:59,175][23468] Updated weights for policy 0, policy_version 51203 (0.0008) -[2023-10-09 10:20:59,543][23468] Updated weights for policy 0, policy_version 51213 (0.0008) -[2023-10-09 10:20:59,915][23468] Updated weights for policy 0, policy_version 51223 (0.0007) -[2023-10-09 10:21:01,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 105185280. Throughput: 0: 1788.5, 1: 1786.8. Samples: 26305844. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-09 10:21:01,078][22500] Avg episode reward: [(0, '8.660'), (1, '8.030')] -[2023-10-09 10:21:01,761][23469] Updated weights for policy 1, policy_version 51491 (0.0011) -[2023-10-09 10:21:02,131][23469] Updated weights for policy 1, policy_version 51501 (0.0010) -[2023-10-09 10:21:02,493][23469] Updated weights for policy 1, policy_version 51511 (0.0008) -[2023-10-09 10:21:03,849][23468] Updated weights for policy 0, policy_version 51233 (0.0008) -[2023-10-09 10:21:04,224][23468] Updated weights for policy 0, policy_version 51243 (0.0009) -[2023-10-09 10:21:04,604][23468] Updated weights for policy 0, policy_version 51253 (0.0009) -[2023-10-09 10:21:04,981][23468] Updated weights for policy 0, policy_version 51263 (0.0007) -[2023-10-09 10:21:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 105250816. Throughput: 0: 1792.0, 1: 1784.1. Samples: 26316926. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-09 10:21:06,079][22500] Avg episode reward: [(0, '9.600'), (1, '8.290')] -[2023-10-09 10:21:06,320][23469] Updated weights for policy 1, policy_version 51521 (0.0008) -[2023-10-09 10:21:06,687][23469] Updated weights for policy 1, policy_version 51531 (0.0008) -[2023-10-09 10:21:07,068][23469] Updated weights for policy 1, policy_version 51541 (0.0009) -[2023-10-09 10:21:07,437][23469] Updated weights for policy 1, policy_version 51551 (0.0009) -[2023-10-09 10:21:08,723][23468] Updated weights for policy 0, policy_version 51273 (0.0009) -[2023-10-09 10:21:09,096][23468] Updated weights for policy 0, policy_version 51283 (0.0010) -[2023-10-09 10:21:09,469][23468] Updated weights for policy 0, policy_version 51293 (0.0009) -[2023-10-09 10:21:11,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 105316352. Throughput: 0: 1794.4, 1: 1782.2. Samples: 26338238. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-09 10:21:11,078][22500] Avg episode reward: [(0, '8.950'), (1, '8.410')] -[2023-10-09 10:21:11,315][23469] Updated weights for policy 1, policy_version 51561 (0.0009) -[2023-10-09 10:21:11,687][23469] Updated weights for policy 1, policy_version 51571 (0.0008) -[2023-10-09 10:21:12,065][23469] Updated weights for policy 1, policy_version 51581 (0.0009) -[2023-10-09 10:21:13,233][23468] Updated weights for policy 0, policy_version 51303 (0.0009) -[2023-10-09 10:21:13,609][23468] Updated weights for policy 0, policy_version 51313 (0.0007) -[2023-10-09 10:21:13,979][23468] Updated weights for policy 0, policy_version 51323 (0.0009) -[2023-10-09 10:21:15,751][23469] Updated weights for policy 1, policy_version 51591 (0.0009) -[2023-10-09 10:21:16,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 105381888. Throughput: 0: 1784.4, 1: 1804.5. Samples: 26359894. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-09 10:21:16,078][22500] Avg episode reward: [(0, '8.550'), (1, '8.110')] -[2023-10-09 10:21:16,125][23469] Updated weights for policy 1, policy_version 51601 (0.0007) -[2023-10-09 10:21:16,492][23469] Updated weights for policy 1, policy_version 51611 (0.0007) -[2023-10-09 10:21:17,873][23468] Updated weights for policy 0, policy_version 51333 (0.0009) -[2023-10-09 10:21:18,242][23468] Updated weights for policy 0, policy_version 51343 (0.0009) -[2023-10-09 10:21:18,623][23468] Updated weights for policy 0, policy_version 51353 (0.0009) -[2023-10-09 10:21:20,147][23469] Updated weights for policy 1, policy_version 51621 (0.0010) -[2023-10-09 10:21:20,514][23469] Updated weights for policy 1, policy_version 51631 (0.0010) -[2023-10-09 10:21:20,890][23469] Updated weights for policy 1, policy_version 51641 (0.0009) -[2023-10-09 10:21:21,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 105447424. Throughput: 0: 1798.6, 1: 1784.0. Samples: 26370846. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 10:21:21,079][22500] Avg episode reward: [(0, '7.920'), (1, '8.500')] -[2023-10-09 10:21:22,452][23468] Updated weights for policy 0, policy_version 51363 (0.0010) -[2023-10-09 10:21:22,825][23468] Updated weights for policy 0, policy_version 51373 (0.0009) -[2023-10-09 10:21:23,200][23468] Updated weights for policy 0, policy_version 51383 (0.0010) -[2023-10-09 10:21:24,637][23469] Updated weights for policy 1, policy_version 51651 (0.0008) -[2023-10-09 10:21:25,013][23469] Updated weights for policy 1, policy_version 51661 (0.0010) -[2023-10-09 10:21:25,391][23469] Updated weights for policy 1, policy_version 51671 (0.0009) -[2023-10-09 10:21:26,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 105545728. Throughput: 0: 1783.5, 1: 1812.6. Samples: 26392044. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 10:21:26,078][22500] Avg episode reward: [(0, '8.710'), (1, '8.370')] -[2023-10-09 10:21:26,938][23468] Updated weights for policy 0, policy_version 51393 (0.0010) -[2023-10-09 10:21:27,354][23468] Updated weights for policy 0, policy_version 51403 (0.0007) -[2023-10-09 10:21:27,722][23468] Updated weights for policy 0, policy_version 51413 (0.0008) -[2023-10-09 10:21:28,091][23468] Updated weights for policy 0, policy_version 51423 (0.0007) -[2023-10-09 10:21:28,972][23469] Updated weights for policy 1, policy_version 51681 (0.0009) -[2023-10-09 10:21:29,418][23469] Updated weights for policy 1, policy_version 51691 (0.0008) -[2023-10-09 10:21:29,791][23469] Updated weights for policy 1, policy_version 51701 (0.0009) -[2023-10-09 10:21:30,150][23469] Updated weights for policy 1, policy_version 51711 (0.0009) -[2023-10-09 10:21:31,078][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 105611264. Throughput: 0: 1780.6, 1: 1792.0. Samples: 26413296. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 10:21:31,079][22500] Avg episode reward: [(0, '8.760'), (1, '8.370')] -[2023-10-09 10:21:31,791][23468] Updated weights for policy 0, policy_version 51433 (0.0008) -[2023-10-09 10:21:32,171][23468] Updated weights for policy 0, policy_version 51443 (0.0008) -[2023-10-09 10:21:32,548][23468] Updated weights for policy 0, policy_version 51453 (0.0009) -[2023-10-09 10:21:33,769][23469] Updated weights for policy 1, policy_version 51721 (0.0009) -[2023-10-09 10:21:34,141][23469] Updated weights for policy 1, policy_version 51731 (0.0008) -[2023-10-09 10:21:34,499][23469] Updated weights for policy 1, policy_version 51741 (0.0008) -[2023-10-09 10:21:36,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 105676800. Throughput: 0: 1779.8, 1: 1808.1. Samples: 26424126. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 10:21:36,078][22500] Avg episode reward: [(0, '9.320'), (1, '7.950')] -[2023-10-09 10:21:36,103][23468] Updated weights for policy 0, policy_version 51463 (0.0008) -[2023-10-09 10:21:36,474][23468] Updated weights for policy 0, policy_version 51473 (0.0009) -[2023-10-09 10:21:36,852][23468] Updated weights for policy 0, policy_version 51483 (0.0008) -[2023-10-09 10:21:38,238][23469] Updated weights for policy 1, policy_version 51751 (0.0009) -[2023-10-09 10:21:38,606][23469] Updated weights for policy 1, policy_version 51761 (0.0011) -[2023-10-09 10:21:38,981][23469] Updated weights for policy 1, policy_version 51771 (0.0010) -[2023-10-09 10:21:40,662][23468] Updated weights for policy 0, policy_version 51493 (0.0008) -[2023-10-09 10:21:41,033][23468] Updated weights for policy 0, policy_version 51503 (0.0009) -[2023-10-09 10:21:41,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 105742336. Throughput: 0: 1780.1, 1: 1791.0. Samples: 26445414. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 10:21:41,078][22500] Avg episode reward: [(0, '9.210'), (1, '8.230')] -[2023-10-09 10:21:41,421][23468] Updated weights for policy 0, policy_version 51513 (0.0011) -[2023-10-09 10:21:42,795][23469] Updated weights for policy 1, policy_version 51781 (0.0010) -[2023-10-09 10:21:43,178][23469] Updated weights for policy 1, policy_version 51791 (0.0010) -[2023-10-09 10:21:43,546][23469] Updated weights for policy 1, policy_version 51801 (0.0010) -[2023-10-09 10:21:45,331][23468] Updated weights for policy 0, policy_version 51523 (0.0010) -[2023-10-09 10:21:45,703][23468] Updated weights for policy 0, policy_version 51533 (0.0010) -[2023-10-09 10:21:46,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 105807872. Throughput: 0: 1807.6, 1: 1787.8. Samples: 26467640. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 10:21:46,078][22500] Avg episode reward: [(0, '8.620'), (1, '8.520')] -[2023-10-09 10:21:46,083][23468] Updated weights for policy 0, policy_version 51543 (0.0008) -[2023-10-09 10:21:47,312][23469] Updated weights for policy 1, policy_version 51811 (0.0009) -[2023-10-09 10:21:47,683][23469] Updated weights for policy 1, policy_version 51821 (0.0007) -[2023-10-09 10:21:48,059][23469] Updated weights for policy 1, policy_version 51831 (0.0009) -[2023-10-09 10:21:49,890][23468] Updated weights for policy 0, policy_version 51553 (0.0009) -[2023-10-09 10:21:50,263][23468] Updated weights for policy 0, policy_version 51563 (0.0008) -[2023-10-09 10:21:50,643][23468] Updated weights for policy 0, policy_version 51573 (0.0008) -[2023-10-09 10:21:51,013][23468] Updated weights for policy 0, policy_version 51583 (0.0007) -[2023-10-09 10:21:51,078][22500] Fps is (10 sec: 16383.5, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 105906176. Throughput: 0: 1776.9, 1: 1790.6. Samples: 26477462. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 10:21:51,079][22500] Avg episode reward: [(0, '8.210'), (1, '8.460')] -[2023-10-09 10:21:51,795][23469] Updated weights for policy 1, policy_version 51841 (0.0008) -[2023-10-09 10:21:52,169][23469] Updated weights for policy 1, policy_version 51851 (0.0008) -[2023-10-09 10:21:52,556][23469] Updated weights for policy 1, policy_version 51861 (0.0007) -[2023-10-09 10:21:52,919][23469] Updated weights for policy 1, policy_version 51871 (0.0009) -[2023-10-09 10:21:54,880][23468] Updated weights for policy 0, policy_version 51593 (0.0008) -[2023-10-09 10:21:55,253][23468] Updated weights for policy 0, policy_version 51603 (0.0008) -[2023-10-09 10:21:55,620][23468] Updated weights for policy 0, policy_version 51613 (0.0009) -[2023-10-09 10:21:56,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 105971712. Throughput: 0: 1800.0, 1: 1788.3. Samples: 26499714. Policy #0 lag: (min: 2.0, avg: 10.2, max: 34.0) -[2023-10-09 10:21:56,078][22500] Avg episode reward: [(0, '8.020'), (1, '8.340')] -[2023-10-09 10:21:56,633][23469] Updated weights for policy 1, policy_version 51881 (0.0007) -[2023-10-09 10:21:56,995][23469] Updated weights for policy 1, policy_version 51891 (0.0008) -[2023-10-09 10:21:57,376][23469] Updated weights for policy 1, policy_version 51901 (0.0009) -[2023-10-09 10:21:59,269][23468] Updated weights for policy 0, policy_version 51623 (0.0011) -[2023-10-09 10:21:59,648][23468] Updated weights for policy 0, policy_version 51633 (0.0007) -[2023-10-09 10:22:00,024][23468] Updated weights for policy 0, policy_version 51643 (0.0007) -[2023-10-09 10:22:01,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 106037248. Throughput: 0: 1773.8, 1: 1797.1. Samples: 26520584. Policy #0 lag: (min: 2.0, avg: 10.2, max: 34.0) -[2023-10-09 10:22:01,078][22500] Avg episode reward: [(0, '8.220'), (1, '7.770')] -[2023-10-09 10:22:01,190][23469] Updated weights for policy 1, policy_version 51911 (0.0008) -[2023-10-09 10:22:01,557][23469] Updated weights for policy 1, policy_version 51921 (0.0008) -[2023-10-09 10:22:01,930][23469] Updated weights for policy 1, policy_version 51931 (0.0007) -[2023-10-09 10:22:03,765][23468] Updated weights for policy 0, policy_version 51653 (0.0008) -[2023-10-09 10:22:04,149][23468] Updated weights for policy 0, policy_version 51663 (0.0009) -[2023-10-09 10:22:04,521][23468] Updated weights for policy 0, policy_version 51673 (0.0009) -[2023-10-09 10:22:05,667][23469] Updated weights for policy 1, policy_version 51941 (0.0009) -[2023-10-09 10:22:06,048][23469] Updated weights for policy 1, policy_version 51951 (0.0007) -[2023-10-09 10:22:06,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 106102784. Throughput: 0: 1794.3, 1: 1786.0. Samples: 26531960. Policy #0 lag: (min: 2.0, avg: 10.2, max: 34.0) -[2023-10-09 10:22:06,079][22500] Avg episode reward: [(0, '8.430'), (1, '8.160')] -[2023-10-09 10:22:06,418][23469] Updated weights for policy 1, policy_version 51961 (0.0009) -[2023-10-09 10:22:08,289][23468] Updated weights for policy 0, policy_version 51683 (0.0007) -[2023-10-09 10:22:08,661][23468] Updated weights for policy 0, policy_version 51693 (0.0007) -[2023-10-09 10:22:09,028][23468] Updated weights for policy 0, policy_version 51703 (0.0009) -[2023-10-09 10:22:10,188][23469] Updated weights for policy 1, policy_version 51971 (0.0010) -[2023-10-09 10:22:10,567][23469] Updated weights for policy 1, policy_version 51981 (0.0010) -[2023-10-09 10:22:10,925][23469] Updated weights for policy 1, policy_version 51991 (0.0011) -[2023-10-09 10:22:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 106168320. Throughput: 0: 1789.9, 1: 1788.1. Samples: 26553054. Policy #0 lag: (min: 2.0, avg: 10.2, max: 34.0) -[2023-10-09 10:22:11,078][22500] Avg episode reward: [(0, '8.270'), (1, '8.430')] -[2023-10-09 10:22:12,800][23468] Updated weights for policy 0, policy_version 51713 (0.0008) -[2023-10-09 10:22:13,214][23468] Updated weights for policy 0, policy_version 51723 (0.0007) -[2023-10-09 10:22:13,601][23468] Updated weights for policy 0, policy_version 51733 (0.0008) -[2023-10-09 10:22:13,973][23468] Updated weights for policy 0, policy_version 51743 (0.0007) -[2023-10-09 10:22:14,598][23469] Updated weights for policy 1, policy_version 52001 (0.0009) -[2023-10-09 10:22:15,013][23469] Updated weights for policy 1, policy_version 52011 (0.0009) -[2023-10-09 10:22:15,386][23469] Updated weights for policy 1, policy_version 52021 (0.0011) -[2023-10-09 10:22:15,766][23469] Updated weights for policy 1, policy_version 52031 (0.0011) -[2023-10-09 10:22:16,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 106266624. Throughput: 0: 1780.3, 1: 1789.7. Samples: 26573946. Policy #0 lag: (min: 2.0, avg: 10.2, max: 34.0) -[2023-10-09 10:22:16,078][22500] Avg episode reward: [(0, '7.820'), (1, '8.320')] -[2023-10-09 10:22:16,089][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000052032_53280768.pth... -[2023-10-09 10:22:16,089][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000051744_52985856.pth... -[2023-10-09 10:22:16,126][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000050336_51544064.pth -[2023-10-09 10:22:16,127][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000050080_51281920.pth -[2023-10-09 10:22:17,669][23468] Updated weights for policy 0, policy_version 51753 (0.0010) -[2023-10-09 10:22:18,040][23468] Updated weights for policy 0, policy_version 51763 (0.0010) -[2023-10-09 10:22:18,416][23468] Updated weights for policy 0, policy_version 51773 (0.0010) -[2023-10-09 10:22:19,523][23469] Updated weights for policy 1, policy_version 52041 (0.0009) -[2023-10-09 10:22:19,890][23469] Updated weights for policy 1, policy_version 52051 (0.0010) -[2023-10-09 10:22:20,257][23469] Updated weights for policy 1, policy_version 52061 (0.0009) -[2023-10-09 10:22:21,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 106332160. Throughput: 0: 1789.5, 1: 1800.1. Samples: 26585656. Policy #0 lag: (min: 2.0, avg: 10.2, max: 34.0) -[2023-10-09 10:22:21,079][22500] Avg episode reward: [(0, '7.680'), (1, '8.360')] -[2023-10-09 10:22:22,251][23468] Updated weights for policy 0, policy_version 51783 (0.0010) -[2023-10-09 10:22:22,629][23468] Updated weights for policy 0, policy_version 51793 (0.0008) -[2023-10-09 10:22:23,001][23468] Updated weights for policy 0, policy_version 51803 (0.0008) -[2023-10-09 10:22:23,991][23469] Updated weights for policy 1, policy_version 52071 (0.0010) -[2023-10-09 10:22:24,360][23469] Updated weights for policy 1, policy_version 52081 (0.0008) -[2023-10-09 10:22:24,735][23469] Updated weights for policy 1, policy_version 52091 (0.0007) -[2023-10-09 10:22:26,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 106397696. Throughput: 0: 1776.2, 1: 1798.6. Samples: 26606278. Policy #0 lag: (min: 2.0, avg: 10.2, max: 34.0) -[2023-10-09 10:22:26,078][22500] Avg episode reward: [(0, '7.820'), (1, '8.680')] -[2023-10-09 10:22:26,759][23468] Updated weights for policy 0, policy_version 51813 (0.0008) -[2023-10-09 10:22:27,134][23468] Updated weights for policy 0, policy_version 51823 (0.0009) -[2023-10-09 10:22:27,516][23468] Updated weights for policy 0, policy_version 51833 (0.0007) -[2023-10-09 10:22:28,337][23469] Updated weights for policy 1, policy_version 52101 (0.0008) -[2023-10-09 10:22:28,706][23469] Updated weights for policy 1, policy_version 52111 (0.0008) -[2023-10-09 10:22:29,076][23469] Updated weights for policy 1, policy_version 52121 (0.0007) -[2023-10-09 10:22:31,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 106463232. Throughput: 0: 1780.4, 1: 1799.0. Samples: 26628716. Policy #0 lag: (min: 2.0, avg: 10.2, max: 34.0) -[2023-10-09 10:22:31,078][22500] Avg episode reward: [(0, '8.470'), (1, '8.390')] -[2023-10-09 10:22:31,191][23468] Updated weights for policy 0, policy_version 51843 (0.0008) -[2023-10-09 10:22:31,561][23468] Updated weights for policy 0, policy_version 51853 (0.0008) -[2023-10-09 10:22:31,930][23468] Updated weights for policy 0, policy_version 51863 (0.0009) -[2023-10-09 10:22:32,748][23469] Updated weights for policy 1, policy_version 52131 (0.0009) -[2023-10-09 10:22:33,120][23469] Updated weights for policy 1, policy_version 52141 (0.0008) -[2023-10-09 10:22:33,490][23469] Updated weights for policy 1, policy_version 52151 (0.0007) -[2023-10-09 10:22:35,667][23468] Updated weights for policy 0, policy_version 51873 (0.0008) -[2023-10-09 10:22:36,036][23468] Updated weights for policy 0, policy_version 51883 (0.0008) -[2023-10-09 10:22:36,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 106528768. Throughput: 0: 1776.5, 1: 1805.1. Samples: 26638632. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:22:36,079][22500] Avg episode reward: [(0, '8.430'), (1, '8.660')] -[2023-10-09 10:22:36,404][23468] Updated weights for policy 0, policy_version 51893 (0.0008) -[2023-10-09 10:22:36,776][23468] Updated weights for policy 0, policy_version 51903 (0.0008) -[2023-10-09 10:22:37,335][23469] Updated weights for policy 1, policy_version 52161 (0.0007) -[2023-10-09 10:22:37,698][23469] Updated weights for policy 1, policy_version 52171 (0.0009) -[2023-10-09 10:22:38,063][23469] Updated weights for policy 1, policy_version 52181 (0.0009) -[2023-10-09 10:22:38,432][23469] Updated weights for policy 1, policy_version 52191 (0.0008) -[2023-10-09 10:22:40,402][23468] Updated weights for policy 0, policy_version 51913 (0.0008) -[2023-10-09 10:22:40,780][23468] Updated weights for policy 0, policy_version 51923 (0.0010) -[2023-10-09 10:22:41,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 106594304. Throughput: 0: 1785.1, 1: 1800.7. Samples: 26661074. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:22:41,078][22500] Avg episode reward: [(0, '8.870'), (1, '8.340')] -[2023-10-09 10:22:41,154][23468] Updated weights for policy 0, policy_version 51933 (0.0008) -[2023-10-09 10:22:42,205][23469] Updated weights for policy 1, policy_version 52201 (0.0007) -[2023-10-09 10:22:42,572][23469] Updated weights for policy 1, policy_version 52211 (0.0007) -[2023-10-09 10:22:42,944][23469] Updated weights for policy 1, policy_version 52221 (0.0011) -[2023-10-09 10:22:44,981][23468] Updated weights for policy 0, policy_version 51943 (0.0008) -[2023-10-09 10:22:45,344][23468] Updated weights for policy 0, policy_version 51953 (0.0008) -[2023-10-09 10:22:45,715][23468] Updated weights for policy 0, policy_version 51963 (0.0008) -[2023-10-09 10:22:46,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 106692608. Throughput: 0: 1805.5, 1: 1798.6. Samples: 26682766. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:22:46,078][22500] Avg episode reward: [(0, '8.960'), (1, '8.390')] -[2023-10-09 10:22:46,657][23469] Updated weights for policy 1, policy_version 52231 (0.0008) -[2023-10-09 10:22:47,014][23469] Updated weights for policy 1, policy_version 52241 (0.0008) -[2023-10-09 10:22:47,384][23469] Updated weights for policy 1, policy_version 52251 (0.0011) -[2023-10-09 10:22:49,411][23468] Updated weights for policy 0, policy_version 51973 (0.0009) -[2023-10-09 10:22:49,782][23468] Updated weights for policy 0, policy_version 51983 (0.0010) -[2023-10-09 10:22:50,155][23468] Updated weights for policy 0, policy_version 51993 (0.0008) -[2023-10-09 10:22:51,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 106758144. Throughput: 0: 1788.1, 1: 1793.5. Samples: 26693134. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:22:51,078][22500] Avg episode reward: [(0, '8.860'), (1, '8.100')] -[2023-10-09 10:22:51,283][23469] Updated weights for policy 1, policy_version 52261 (0.0011) -[2023-10-09 10:22:51,653][23469] Updated weights for policy 1, policy_version 52271 (0.0009) -[2023-10-09 10:22:52,022][23469] Updated weights for policy 1, policy_version 52281 (0.0011) -[2023-10-09 10:22:53,987][23468] Updated weights for policy 0, policy_version 52003 (0.0007) -[2023-10-09 10:22:54,355][23468] Updated weights for policy 0, policy_version 52013 (0.0007) -[2023-10-09 10:22:54,735][23468] Updated weights for policy 0, policy_version 52023 (0.0010) -[2023-10-09 10:22:55,730][23469] Updated weights for policy 1, policy_version 52291 (0.0010) -[2023-10-09 10:22:56,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 106823680. Throughput: 0: 1799.0, 1: 1795.3. Samples: 26714796. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:22:56,078][22500] Avg episode reward: [(0, '8.020'), (1, '8.040')] -[2023-10-09 10:22:56,098][23469] Updated weights for policy 1, policy_version 52301 (0.0008) -[2023-10-09 10:22:56,470][23469] Updated weights for policy 1, policy_version 52311 (0.0008) -[2023-10-09 10:22:58,574][23468] Updated weights for policy 0, policy_version 52033 (0.0009) -[2023-10-09 10:22:58,978][23468] Updated weights for policy 0, policy_version 52043 (0.0010) -[2023-10-09 10:22:59,350][23468] Updated weights for policy 0, policy_version 52053 (0.0011) -[2023-10-09 10:22:59,714][23468] Updated weights for policy 0, policy_version 52063 (0.0010) -[2023-10-09 10:23:00,100][23469] Updated weights for policy 1, policy_version 52321 (0.0008) -[2023-10-09 10:23:00,518][23469] Updated weights for policy 1, policy_version 52331 (0.0008) -[2023-10-09 10:23:00,894][23469] Updated weights for policy 1, policy_version 52341 (0.0008) -[2023-10-09 10:23:01,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 106889216. Throughput: 0: 1777.9, 1: 1808.7. Samples: 26735340. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:23:01,078][22500] Avg episode reward: [(0, '8.500'), (1, '8.530')] -[2023-10-09 10:23:01,262][23469] Updated weights for policy 1, policy_version 52351 (0.0008) -[2023-10-09 10:23:03,517][23468] Updated weights for policy 0, policy_version 52073 (0.0010) -[2023-10-09 10:23:03,888][23468] Updated weights for policy 0, policy_version 52083 (0.0008) -[2023-10-09 10:23:04,262][23468] Updated weights for policy 0, policy_version 52093 (0.0008) -[2023-10-09 10:23:05,087][23469] Updated weights for policy 1, policy_version 52361 (0.0008) -[2023-10-09 10:23:05,458][23469] Updated weights for policy 1, policy_version 52371 (0.0008) -[2023-10-09 10:23:05,828][23469] Updated weights for policy 1, policy_version 52381 (0.0008) -[2023-10-09 10:23:06,077][22500] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 106987520. Throughput: 0: 1797.7, 1: 1788.8. Samples: 26747048. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:23:06,078][22500] Avg episode reward: [(0, '8.260'), (1, '8.450')] -[2023-10-09 10:23:07,938][23468] Updated weights for policy 0, policy_version 52103 (0.0010) -[2023-10-09 10:23:08,306][23468] Updated weights for policy 0, policy_version 52113 (0.0008) -[2023-10-09 10:23:08,676][23468] Updated weights for policy 0, policy_version 52123 (0.0008) -[2023-10-09 10:23:09,610][23469] Updated weights for policy 1, policy_version 52391 (0.0008) -[2023-10-09 10:23:09,989][23469] Updated weights for policy 1, policy_version 52401 (0.0010) -[2023-10-09 10:23:10,356][23469] Updated weights for policy 1, policy_version 52411 (0.0010) -[2023-10-09 10:23:11,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 107053056. Throughput: 0: 1780.2, 1: 1807.4. Samples: 26767720. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-09 10:23:11,078][22500] Avg episode reward: [(0, '9.200'), (1, '8.690')] -[2023-10-09 10:23:12,364][23468] Updated weights for policy 0, policy_version 52133 (0.0008) -[2023-10-09 10:23:12,735][23468] Updated weights for policy 0, policy_version 52143 (0.0007) -[2023-10-09 10:23:13,112][23468] Updated weights for policy 0, policy_version 52153 (0.0009) -[2023-10-09 10:23:13,963][23469] Updated weights for policy 1, policy_version 52421 (0.0009) -[2023-10-09 10:23:14,333][23469] Updated weights for policy 1, policy_version 52431 (0.0010) -[2023-10-09 10:23:14,709][23469] Updated weights for policy 1, policy_version 52441 (0.0010) -[2023-10-09 10:23:16,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 107118592. Throughput: 0: 1782.1, 1: 1790.2. Samples: 26789470. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-09 10:23:16,079][22500] Avg episode reward: [(0, '8.940'), (1, '8.970')] -[2023-10-09 10:23:16,827][23468] Updated weights for policy 0, policy_version 52163 (0.0009) -[2023-10-09 10:23:17,204][23468] Updated weights for policy 0, policy_version 52173 (0.0010) -[2023-10-09 10:23:17,582][23468] Updated weights for policy 0, policy_version 52183 (0.0009) -[2023-10-09 10:23:18,469][23469] Updated weights for policy 1, policy_version 52451 (0.0010) -[2023-10-09 10:23:18,837][23469] Updated weights for policy 1, policy_version 52461 (0.0008) -[2023-10-09 10:23:19,203][23469] Updated weights for policy 1, policy_version 52471 (0.0011) -[2023-10-09 10:23:21,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 107184128. Throughput: 0: 1780.4, 1: 1808.5. Samples: 26800136. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-09 10:23:21,079][22500] Avg episode reward: [(0, '8.940'), (1, '8.340')] -[2023-10-09 10:23:21,487][23468] Updated weights for policy 0, policy_version 52193 (0.0010) -[2023-10-09 10:23:21,861][23468] Updated weights for policy 0, policy_version 52203 (0.0008) -[2023-10-09 10:23:22,241][23468] Updated weights for policy 0, policy_version 52213 (0.0008) -[2023-10-09 10:23:22,608][23468] Updated weights for policy 0, policy_version 52223 (0.0007) -[2023-10-09 10:23:22,850][23469] Updated weights for policy 1, policy_version 52481 (0.0008) -[2023-10-09 10:23:23,212][23469] Updated weights for policy 1, policy_version 52491 (0.0007) -[2023-10-09 10:23:23,583][23469] Updated weights for policy 1, policy_version 52501 (0.0008) -[2023-10-09 10:23:23,953][23469] Updated weights for policy 1, policy_version 52511 (0.0009) -[2023-10-09 10:23:26,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 107249664. Throughput: 0: 1772.1, 1: 1791.2. Samples: 26821422. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-09 10:23:26,078][22500] Avg episode reward: [(0, '9.670'), (1, '8.440')] -[2023-10-09 10:23:26,079][23265] Saving new best policy, reward=9.670! -[2023-10-09 10:23:26,642][23468] Updated weights for policy 0, policy_version 52233 (0.0011) -[2023-10-09 10:23:27,006][23468] Updated weights for policy 0, policy_version 52243 (0.0007) -[2023-10-09 10:23:27,378][23468] Updated weights for policy 0, policy_version 52253 (0.0007) -[2023-10-09 10:23:27,637][23469] Updated weights for policy 1, policy_version 52521 (0.0009) -[2023-10-09 10:23:28,012][23469] Updated weights for policy 1, policy_version 52531 (0.0008) -[2023-10-09 10:23:28,379][23469] Updated weights for policy 1, policy_version 52541 (0.0011) -[2023-10-09 10:23:31,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 107315200. Throughput: 0: 1781.7, 1: 1796.4. Samples: 26843780. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-09 10:23:31,078][22500] Avg episode reward: [(0, '8.840'), (1, '8.620')] -[2023-10-09 10:23:31,162][23468] Updated weights for policy 0, policy_version 52263 (0.0009) -[2023-10-09 10:23:31,528][23468] Updated weights for policy 0, policy_version 52273 (0.0010) -[2023-10-09 10:23:31,910][23468] Updated weights for policy 0, policy_version 52283 (0.0009) -[2023-10-09 10:23:31,992][23469] Updated weights for policy 1, policy_version 52551 (0.0008) -[2023-10-09 10:23:32,363][23469] Updated weights for policy 1, policy_version 52561 (0.0008) -[2023-10-09 10:23:32,725][23469] Updated weights for policy 1, policy_version 52571 (0.0007) -[2023-10-09 10:23:35,658][23468] Updated weights for policy 0, policy_version 52293 (0.0009) -[2023-10-09 10:23:36,025][23468] Updated weights for policy 0, policy_version 52303 (0.0011) -[2023-10-09 10:23:36,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 107380736. Throughput: 0: 1767.1, 1: 1801.2. Samples: 26853708. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-09 10:23:36,078][22500] Avg episode reward: [(0, '9.000'), (1, '8.260')] -[2023-10-09 10:23:36,399][23468] Updated weights for policy 0, policy_version 52313 (0.0008) -[2023-10-09 10:23:36,498][23469] Updated weights for policy 1, policy_version 52581 (0.0007) -[2023-10-09 10:23:36,874][23469] Updated weights for policy 1, policy_version 52591 (0.0009) -[2023-10-09 10:23:37,239][23469] Updated weights for policy 1, policy_version 52601 (0.0011) -[2023-10-09 10:23:40,166][23468] Updated weights for policy 0, policy_version 52323 (0.0008) -[2023-10-09 10:23:40,535][23468] Updated weights for policy 0, policy_version 52333 (0.0008) -[2023-10-09 10:23:40,902][23468] Updated weights for policy 0, policy_version 52343 (0.0010) -[2023-10-09 10:23:40,914][23469] Updated weights for policy 1, policy_version 52611 (0.0010) -[2023-10-09 10:23:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 107446272. Throughput: 0: 1781.7, 1: 1800.2. Samples: 26875982. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-09 10:23:41,078][22500] Avg episode reward: [(0, '8.720'), (1, '8.200')] -[2023-10-09 10:23:41,279][23469] Updated weights for policy 1, policy_version 52621 (0.0009) -[2023-10-09 10:23:41,643][23469] Updated weights for policy 1, policy_version 52631 (0.0011) -[2023-10-09 10:23:44,726][23468] Updated weights for policy 0, policy_version 52353 (0.0008) -[2023-10-09 10:23:45,151][23468] Updated weights for policy 0, policy_version 52363 (0.0008) -[2023-10-09 10:23:45,449][23469] Updated weights for policy 1, policy_version 52641 (0.0009) -[2023-10-09 10:23:45,515][23468] Updated weights for policy 0, policy_version 52373 (0.0008) -[2023-10-09 10:23:45,868][23469] Updated weights for policy 1, policy_version 52651 (0.0007) -[2023-10-09 10:23:45,887][23468] Updated weights for policy 0, policy_version 52383 (0.0009) -[2023-10-09 10:23:46,078][22500] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 107544576. Throughput: 0: 1788.6, 1: 1807.2. Samples: 26897150. Policy #0 lag: (min: 17.0, avg: 27.9, max: 49.0) -[2023-10-09 10:23:46,078][22500] Avg episode reward: [(0, '9.030'), (1, '7.960')] -[2023-10-09 10:23:46,245][23469] Updated weights for policy 1, policy_version 52661 (0.0009) -[2023-10-09 10:23:46,612][23469] Updated weights for policy 1, policy_version 52671 (0.0011) -[2023-10-09 10:23:49,520][23468] Updated weights for policy 0, policy_version 52393 (0.0008) -[2023-10-09 10:23:49,891][23468] Updated weights for policy 0, policy_version 52403 (0.0009) -[2023-10-09 10:23:50,265][23468] Updated weights for policy 0, policy_version 52413 (0.0009) -[2023-10-09 10:23:50,480][23469] Updated weights for policy 1, policy_version 52681 (0.0009) -[2023-10-09 10:23:50,852][23469] Updated weights for policy 1, policy_version 52691 (0.0009) -[2023-10-09 10:23:51,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 107610112. Throughput: 0: 1774.6, 1: 1797.5. Samples: 26907792. Policy #0 lag: (min: 17.0, avg: 27.9, max: 49.0) -[2023-10-09 10:23:51,078][22500] Avg episode reward: [(0, '8.690'), (1, '7.850')] -[2023-10-09 10:23:51,220][23469] Updated weights for policy 1, policy_version 52701 (0.0009) -[2023-10-09 10:23:53,957][23468] Updated weights for policy 0, policy_version 52423 (0.0007) -[2023-10-09 10:23:54,331][23468] Updated weights for policy 0, policy_version 52433 (0.0007) -[2023-10-09 10:23:54,695][23468] Updated weights for policy 0, policy_version 52443 (0.0007) -[2023-10-09 10:23:55,040][23469] Updated weights for policy 1, policy_version 52711 (0.0009) -[2023-10-09 10:23:55,411][23469] Updated weights for policy 1, policy_version 52721 (0.0010) -[2023-10-09 10:23:55,783][23469] Updated weights for policy 1, policy_version 52731 (0.0011) -[2023-10-09 10:23:56,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 107708416. Throughput: 0: 1790.3, 1: 1807.4. Samples: 26929616. Policy #0 lag: (min: 17.0, avg: 27.9, max: 49.0) -[2023-10-09 10:23:56,078][22500] Avg episode reward: [(0, '9.910'), (1, '7.760')] -[2023-10-09 10:23:56,080][23265] Saving new best policy, reward=9.910! -[2023-10-09 10:23:58,463][23468] Updated weights for policy 0, policy_version 52453 (0.0007) -[2023-10-09 10:23:58,838][23468] Updated weights for policy 0, policy_version 52463 (0.0008) -[2023-10-09 10:23:59,203][23468] Updated weights for policy 0, policy_version 52473 (0.0012) -[2023-10-09 10:23:59,499][23469] Updated weights for policy 1, policy_version 52741 (0.0008) -[2023-10-09 10:23:59,863][23469] Updated weights for policy 1, policy_version 52751 (0.0007) -[2023-10-09 10:24:00,232][23469] Updated weights for policy 1, policy_version 52761 (0.0007) -[2023-10-09 10:24:01,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 107773952. Throughput: 0: 1773.7, 1: 1794.3. Samples: 26950032. Policy #0 lag: (min: 17.0, avg: 27.9, max: 49.0) -[2023-10-09 10:24:01,078][22500] Avg episode reward: [(0, '9.560'), (1, '7.750')] -[2023-10-09 10:24:03,009][23468] Updated weights for policy 0, policy_version 52483 (0.0008) -[2023-10-09 10:24:03,374][23468] Updated weights for policy 0, policy_version 52493 (0.0007) -[2023-10-09 10:24:03,764][23468] Updated weights for policy 0, policy_version 52503 (0.0009) -[2023-10-09 10:24:04,085][23469] Updated weights for policy 1, policy_version 52771 (0.0008) -[2023-10-09 10:24:04,454][23469] Updated weights for policy 1, policy_version 52781 (0.0010) -[2023-10-09 10:24:04,822][23469] Updated weights for policy 1, policy_version 52791 (0.0009) -[2023-10-09 10:24:06,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 107839488. Throughput: 0: 1798.4, 1: 1802.8. Samples: 26962188. Policy #0 lag: (min: 17.0, avg: 27.9, max: 49.0) -[2023-10-09 10:24:06,078][22500] Avg episode reward: [(0, '9.350'), (1, '7.900')] -[2023-10-09 10:24:07,516][23468] Updated weights for policy 0, policy_version 52513 (0.0008) -[2023-10-09 10:24:07,891][23468] Updated weights for policy 0, policy_version 52523 (0.0008) -[2023-10-09 10:24:08,269][23468] Updated weights for policy 0, policy_version 52533 (0.0010) -[2023-10-09 10:24:08,628][23468] Updated weights for policy 0, policy_version 52543 (0.0009) -[2023-10-09 10:24:08,653][23469] Updated weights for policy 1, policy_version 52801 (0.0009) -[2023-10-09 10:24:09,029][23469] Updated weights for policy 1, policy_version 52811 (0.0007) -[2023-10-09 10:24:09,399][23469] Updated weights for policy 1, policy_version 52821 (0.0008) -[2023-10-09 10:24:09,769][23469] Updated weights for policy 1, policy_version 52831 (0.0008) -[2023-10-09 10:24:11,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 107905024. Throughput: 0: 1778.5, 1: 1792.7. Samples: 26982126. Policy #0 lag: (min: 17.0, avg: 27.9, max: 49.0) -[2023-10-09 10:24:11,078][22500] Avg episode reward: [(0, '8.910'), (1, '8.030')] -[2023-10-09 10:24:12,409][23468] Updated weights for policy 0, policy_version 52553 (0.0008) -[2023-10-09 10:24:12,785][23468] Updated weights for policy 0, policy_version 52563 (0.0008) -[2023-10-09 10:24:13,162][23468] Updated weights for policy 0, policy_version 52573 (0.0008) -[2023-10-09 10:24:13,412][23469] Updated weights for policy 1, policy_version 52841 (0.0008) -[2023-10-09 10:24:13,771][23469] Updated weights for policy 1, policy_version 52851 (0.0008) -[2023-10-09 10:24:14,144][23469] Updated weights for policy 1, policy_version 52861 (0.0010) -[2023-10-09 10:24:16,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 107970560. Throughput: 0: 1783.6, 1: 1787.5. Samples: 27004478. Policy #0 lag: (min: 17.0, avg: 27.9, max: 49.0) -[2023-10-09 10:24:16,078][22500] Avg episode reward: [(0, '8.930'), (1, '8.030')] -[2023-10-09 10:24:16,086][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000052864_54132736.pth... -[2023-10-09 10:24:16,086][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000052576_53837824.pth... -[2023-10-09 10:24:16,115][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000051200_52428800.pth -[2023-10-09 10:24:16,122][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000050912_52133888.pth -[2023-10-09 10:24:16,938][23468] Updated weights for policy 0, policy_version 52583 (0.0009) -[2023-10-09 10:24:17,318][23468] Updated weights for policy 0, policy_version 52593 (0.0009) -[2023-10-09 10:24:17,698][23468] Updated weights for policy 0, policy_version 52603 (0.0007) -[2023-10-09 10:24:17,854][23469] Updated weights for policy 1, policy_version 52871 (0.0008) -[2023-10-09 10:24:18,220][23469] Updated weights for policy 1, policy_version 52881 (0.0010) -[2023-10-09 10:24:18,586][23469] Updated weights for policy 1, policy_version 52891 (0.0010) -[2023-10-09 10:24:21,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 108036096. Throughput: 0: 1777.8, 1: 1790.0. Samples: 27014260. Policy #0 lag: (min: 17.0, avg: 27.9, max: 49.0) -[2023-10-09 10:24:21,078][22500] Avg episode reward: [(0, '8.650'), (1, '8.520')] -[2023-10-09 10:24:21,451][23468] Updated weights for policy 0, policy_version 52613 (0.0009) -[2023-10-09 10:24:21,833][23468] Updated weights for policy 0, policy_version 52623 (0.0010) -[2023-10-09 10:24:22,209][23468] Updated weights for policy 0, policy_version 52633 (0.0007) -[2023-10-09 10:24:22,298][23469] Updated weights for policy 1, policy_version 52901 (0.0010) -[2023-10-09 10:24:22,677][23469] Updated weights for policy 1, policy_version 52911 (0.0009) -[2023-10-09 10:24:23,049][23469] Updated weights for policy 1, policy_version 52921 (0.0007) -[2023-10-09 10:24:26,006][23468] Updated weights for policy 0, policy_version 52643 (0.0007) -[2023-10-09 10:24:26,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 108101632. Throughput: 0: 1779.5, 1: 1788.1. Samples: 27036526. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-09 10:24:26,078][22500] Avg episode reward: [(0, '8.560'), (1, '8.570')] -[2023-10-09 10:24:26,387][23468] Updated weights for policy 0, policy_version 52653 (0.0008) -[2023-10-09 10:24:26,723][23469] Updated weights for policy 1, policy_version 52931 (0.0007) -[2023-10-09 10:24:26,758][23468] Updated weights for policy 0, policy_version 52663 (0.0007) -[2023-10-09 10:24:27,092][23469] Updated weights for policy 1, policy_version 52941 (0.0008) -[2023-10-09 10:24:27,463][23469] Updated weights for policy 1, policy_version 52951 (0.0010) -[2023-10-09 10:24:30,640][23468] Updated weights for policy 0, policy_version 52673 (0.0007) -[2023-10-09 10:24:31,041][23468] Updated weights for policy 0, policy_version 52683 (0.0009) -[2023-10-09 10:24:31,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 108167168. Throughput: 0: 1798.3, 1: 1797.3. Samples: 27058954. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-09 10:24:31,078][22500] Avg episode reward: [(0, '8.750'), (1, '8.630')] -[2023-10-09 10:24:31,234][23469] Updated weights for policy 1, policy_version 52961 (0.0010) -[2023-10-09 10:24:31,411][23468] Updated weights for policy 0, policy_version 52693 (0.0008) -[2023-10-09 10:24:31,655][23469] Updated weights for policy 1, policy_version 52971 (0.0007) -[2023-10-09 10:24:31,775][23468] Updated weights for policy 0, policy_version 52703 (0.0008) -[2023-10-09 10:24:32,030][23469] Updated weights for policy 1, policy_version 52981 (0.0009) -[2023-10-09 10:24:32,389][23469] Updated weights for policy 1, policy_version 52991 (0.0009) -[2023-10-09 10:24:35,569][23468] Updated weights for policy 0, policy_version 52713 (0.0009) -[2023-10-09 10:24:35,934][23468] Updated weights for policy 0, policy_version 52723 (0.0008) -[2023-10-09 10:24:36,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 108232704. Throughput: 0: 1779.3, 1: 1791.0. Samples: 27068458. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-09 10:24:36,078][22500] Avg episode reward: [(0, '8.650'), (1, '8.920')] -[2023-10-09 10:24:36,206][23469] Updated weights for policy 1, policy_version 53001 (0.0008) -[2023-10-09 10:24:36,302][23468] Updated weights for policy 0, policy_version 52733 (0.0008) -[2023-10-09 10:24:36,578][23469] Updated weights for policy 1, policy_version 53011 (0.0008) -[2023-10-09 10:24:36,956][23469] Updated weights for policy 1, policy_version 53021 (0.0008) -[2023-10-09 10:24:39,905][23468] Updated weights for policy 0, policy_version 52743 (0.0008) -[2023-10-09 10:24:40,273][23468] Updated weights for policy 0, policy_version 52753 (0.0009) -[2023-10-09 10:24:40,644][23469] Updated weights for policy 1, policy_version 53031 (0.0009) -[2023-10-09 10:24:40,651][23468] Updated weights for policy 0, policy_version 52763 (0.0008) -[2023-10-09 10:24:41,010][23469] Updated weights for policy 1, policy_version 53041 (0.0009) -[2023-10-09 10:24:41,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 108331008. Throughput: 0: 1794.1, 1: 1786.3. Samples: 27090736. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-09 10:24:41,078][22500] Avg episode reward: [(0, '8.490'), (1, '8.600')] -[2023-10-09 10:24:41,380][23469] Updated weights for policy 1, policy_version 53051 (0.0007) -[2023-10-09 10:24:44,365][23468] Updated weights for policy 0, policy_version 52773 (0.0008) -[2023-10-09 10:24:44,741][23468] Updated weights for policy 0, policy_version 52783 (0.0007) -[2023-10-09 10:24:45,114][23468] Updated weights for policy 0, policy_version 52793 (0.0007) -[2023-10-09 10:24:45,129][23469] Updated weights for policy 1, policy_version 53061 (0.0007) -[2023-10-09 10:24:45,497][23469] Updated weights for policy 1, policy_version 53071 (0.0010) -[2023-10-09 10:24:45,873][23469] Updated weights for policy 1, policy_version 53081 (0.0008) -[2023-10-09 10:24:46,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 108396544. Throughput: 0: 1776.5, 1: 1795.3. Samples: 27110762. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-09 10:24:46,078][22500] Avg episode reward: [(0, '8.030'), (1, '8.320')] -[2023-10-09 10:24:48,941][23468] Updated weights for policy 0, policy_version 52803 (0.0008) -[2023-10-09 10:24:49,302][23468] Updated weights for policy 0, policy_version 52813 (0.0009) -[2023-10-09 10:24:49,676][23468] Updated weights for policy 0, policy_version 52823 (0.0009) -[2023-10-09 10:24:49,772][23469] Updated weights for policy 1, policy_version 53091 (0.0007) -[2023-10-09 10:24:50,139][23469] Updated weights for policy 1, policy_version 53101 (0.0007) -[2023-10-09 10:24:50,513][23469] Updated weights for policy 1, policy_version 53111 (0.0010) -[2023-10-09 10:24:51,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 108494848. Throughput: 0: 1784.1, 1: 1782.4. Samples: 27122682. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-09 10:24:51,078][22500] Avg episode reward: [(0, '8.160'), (1, '8.400')] -[2023-10-09 10:24:53,355][23468] Updated weights for policy 0, policy_version 52833 (0.0008) -[2023-10-09 10:24:53,734][23468] Updated weights for policy 0, policy_version 52843 (0.0009) -[2023-10-09 10:24:54,098][23468] Updated weights for policy 0, policy_version 52853 (0.0009) -[2023-10-09 10:24:54,345][23469] Updated weights for policy 1, policy_version 53121 (0.0009) -[2023-10-09 10:24:54,471][23468] Updated weights for policy 0, policy_version 52863 (0.0010) -[2023-10-09 10:24:54,712][23469] Updated weights for policy 1, policy_version 53131 (0.0009) -[2023-10-09 10:24:55,082][23469] Updated weights for policy 1, policy_version 53141 (0.0011) -[2023-10-09 10:24:55,438][23469] Updated weights for policy 1, policy_version 53151 (0.0008) -[2023-10-09 10:24:56,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 108560384. Throughput: 0: 1783.7, 1: 1802.5. Samples: 27143506. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-09 10:24:56,078][22500] Avg episode reward: [(0, '8.320'), (1, '7.500')] -[2023-10-09 10:24:58,281][23468] Updated weights for policy 0, policy_version 52873 (0.0007) -[2023-10-09 10:24:58,656][23468] Updated weights for policy 0, policy_version 52883 (0.0007) -[2023-10-09 10:24:59,026][23468] Updated weights for policy 0, policy_version 52893 (0.0008) -[2023-10-09 10:24:59,284][23469] Updated weights for policy 1, policy_version 53161 (0.0010) -[2023-10-09 10:24:59,653][23469] Updated weights for policy 1, policy_version 53171 (0.0009) -[2023-10-09 10:25:00,013][23469] Updated weights for policy 1, policy_version 53181 (0.0009) -[2023-10-09 10:25:01,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 108625920. Throughput: 0: 1780.2, 1: 1779.9. Samples: 27164682. Policy #0 lag: (min: 22.0, avg: 29.3, max: 54.0) -[2023-10-09 10:25:01,079][22500] Avg episode reward: [(0, '8.480'), (1, '7.380')] -[2023-10-09 10:25:02,580][23468] Updated weights for policy 0, policy_version 52903 (0.0008) -[2023-10-09 10:25:02,956][23468] Updated weights for policy 0, policy_version 52913 (0.0008) -[2023-10-09 10:25:03,323][23468] Updated weights for policy 0, policy_version 52923 (0.0008) -[2023-10-09 10:25:03,633][23469] Updated weights for policy 1, policy_version 53191 (0.0008) -[2023-10-09 10:25:03,997][23469] Updated weights for policy 1, policy_version 53201 (0.0008) -[2023-10-09 10:25:04,368][23469] Updated weights for policy 1, policy_version 53211 (0.0007) -[2023-10-09 10:25:06,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 108691456. Throughput: 0: 1790.9, 1: 1805.1. Samples: 27176078. Policy #0 lag: (min: 22.0, avg: 29.3, max: 54.0) -[2023-10-09 10:25:06,078][22500] Avg episode reward: [(0, '9.100'), (1, '7.620')] -[2023-10-09 10:25:07,199][23468] Updated weights for policy 0, policy_version 52933 (0.0008) -[2023-10-09 10:25:07,572][23468] Updated weights for policy 0, policy_version 52943 (0.0009) -[2023-10-09 10:25:07,952][23468] Updated weights for policy 0, policy_version 52953 (0.0008) -[2023-10-09 10:25:08,079][23469] Updated weights for policy 1, policy_version 53221 (0.0009) -[2023-10-09 10:25:08,452][23469] Updated weights for policy 1, policy_version 53231 (0.0007) -[2023-10-09 10:25:08,823][23469] Updated weights for policy 1, policy_version 53241 (0.0008) -[2023-10-09 10:25:11,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 108756992. Throughput: 0: 1774.5, 1: 1790.1. Samples: 27196934. Policy #0 lag: (min: 22.0, avg: 29.3, max: 54.0) -[2023-10-09 10:25:11,078][22500] Avg episode reward: [(0, '9.160'), (1, '8.600')] -[2023-10-09 10:25:11,847][23468] Updated weights for policy 0, policy_version 52963 (0.0009) -[2023-10-09 10:25:12,220][23468] Updated weights for policy 0, policy_version 52973 (0.0009) -[2023-10-09 10:25:12,417][23469] Updated weights for policy 1, policy_version 53251 (0.0008) -[2023-10-09 10:25:12,588][23468] Updated weights for policy 0, policy_version 52983 (0.0007) -[2023-10-09 10:25:12,785][23469] Updated weights for policy 1, policy_version 53261 (0.0007) -[2023-10-09 10:25:13,155][23469] Updated weights for policy 1, policy_version 53271 (0.0009) -[2023-10-09 10:25:16,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 108822528. Throughput: 0: 1771.8, 1: 1791.5. Samples: 27219302. Policy #0 lag: (min: 22.0, avg: 29.3, max: 54.0) -[2023-10-09 10:25:16,079][22500] Avg episode reward: [(0, '8.690'), (1, '8.860')] -[2023-10-09 10:25:16,428][23468] Updated weights for policy 0, policy_version 52993 (0.0008) -[2023-10-09 10:25:16,827][23468] Updated weights for policy 0, policy_version 53003 (0.0009) -[2023-10-09 10:25:16,906][23469] Updated weights for policy 1, policy_version 53281 (0.0007) -[2023-10-09 10:25:17,195][23468] Updated weights for policy 0, policy_version 53013 (0.0008) -[2023-10-09 10:25:17,317][23469] Updated weights for policy 1, policy_version 53291 (0.0007) -[2023-10-09 10:25:17,564][23468] Updated weights for policy 0, policy_version 53023 (0.0009) -[2023-10-09 10:25:17,682][23469] Updated weights for policy 1, policy_version 53301 (0.0007) -[2023-10-09 10:25:18,044][23469] Updated weights for policy 1, policy_version 53311 (0.0008) -[2023-10-09 10:25:21,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 108888064. Throughput: 0: 1773.4, 1: 1790.8. Samples: 27228846. Policy #0 lag: (min: 22.0, avg: 29.3, max: 54.0) -[2023-10-09 10:25:21,078][22500] Avg episode reward: [(0, '8.830'), (1, '9.620')] -[2023-10-09 10:25:21,079][23343] Saving new best policy, reward=9.620! -[2023-10-09 10:25:21,392][23468] Updated weights for policy 0, policy_version 53033 (0.0007) -[2023-10-09 10:25:21,750][23469] Updated weights for policy 1, policy_version 53321 (0.0008) -[2023-10-09 10:25:21,772][23468] Updated weights for policy 0, policy_version 53043 (0.0008) -[2023-10-09 10:25:22,114][23469] Updated weights for policy 1, policy_version 53331 (0.0008) -[2023-10-09 10:25:22,142][23468] Updated weights for policy 0, policy_version 53053 (0.0007) -[2023-10-09 10:25:22,484][23469] Updated weights for policy 1, policy_version 53341 (0.0008) -[2023-10-09 10:25:25,733][23468] Updated weights for policy 0, policy_version 53063 (0.0010) -[2023-10-09 10:25:26,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 108953600. Throughput: 0: 1773.5, 1: 1792.7. Samples: 27251212. Policy #0 lag: (min: 22.0, avg: 29.3, max: 54.0) -[2023-10-09 10:25:26,079][22500] Avg episode reward: [(0, '9.470'), (1, '9.970')] -[2023-10-09 10:25:26,109][23468] Updated weights for policy 0, policy_version 53073 (0.0009) -[2023-10-09 10:25:26,161][23469] Updated weights for policy 1, policy_version 53351 (0.0008) -[2023-10-09 10:25:26,487][23468] Updated weights for policy 0, policy_version 53083 (0.0008) -[2023-10-09 10:25:26,533][23469] Updated weights for policy 1, policy_version 53361 (0.0009) -[2023-10-09 10:25:26,906][23469] Updated weights for policy 1, policy_version 53371 (0.0009) -[2023-10-09 10:25:27,086][23343] Saving new best policy, reward=9.970! -[2023-10-09 10:25:30,239][23468] Updated weights for policy 0, policy_version 53093 (0.0008) -[2023-10-09 10:25:30,611][23468] Updated weights for policy 0, policy_version 53103 (0.0009) -[2023-10-09 10:25:30,657][23469] Updated weights for policy 1, policy_version 53381 (0.0008) -[2023-10-09 10:25:30,980][23468] Updated weights for policy 0, policy_version 53113 (0.0008) -[2023-10-09 10:25:31,025][23469] Updated weights for policy 1, policy_version 53391 (0.0010) -[2023-10-09 10:25:31,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 109019136. Throughput: 0: 1796.2, 1: 1812.0. Samples: 27273132. Policy #0 lag: (min: 22.0, avg: 29.3, max: 54.0) -[2023-10-09 10:25:31,079][22500] Avg episode reward: [(0, '9.400'), (1, '9.670')] -[2023-10-09 10:25:31,392][23469] Updated weights for policy 1, policy_version 53401 (0.0008) -[2023-10-09 10:25:34,670][23468] Updated weights for policy 0, policy_version 53123 (0.0008) -[2023-10-09 10:25:35,051][23468] Updated weights for policy 0, policy_version 53133 (0.0008) -[2023-10-09 10:25:35,088][23469] Updated weights for policy 1, policy_version 53411 (0.0007) -[2023-10-09 10:25:35,423][23468] Updated weights for policy 0, policy_version 53143 (0.0008) -[2023-10-09 10:25:35,456][23469] Updated weights for policy 1, policy_version 53421 (0.0008) -[2023-10-09 10:25:35,832][23469] Updated weights for policy 1, policy_version 53431 (0.0009) -[2023-10-09 10:25:36,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 109117440. Throughput: 0: 1776.6, 1: 1802.6. Samples: 27283748. Policy #0 lag: (min: 10.0, avg: 12.9, max: 42.0) -[2023-10-09 10:25:36,078][22500] Avg episode reward: [(0, '10.060'), (1, '9.070')] -[2023-10-09 10:25:36,080][23265] Saving new best policy, reward=10.060! -[2023-10-09 10:25:39,260][23468] Updated weights for policy 0, policy_version 53153 (0.0008) -[2023-10-09 10:25:39,635][23468] Updated weights for policy 0, policy_version 53163 (0.0008) -[2023-10-09 10:25:39,702][23469] Updated weights for policy 1, policy_version 53441 (0.0007) -[2023-10-09 10:25:40,001][23468] Updated weights for policy 0, policy_version 53173 (0.0008) -[2023-10-09 10:25:40,059][23469] Updated weights for policy 1, policy_version 53451 (0.0008) -[2023-10-09 10:25:40,375][23468] Updated weights for policy 0, policy_version 53183 (0.0009) -[2023-10-09 10:25:40,430][23469] Updated weights for policy 1, policy_version 53461 (0.0008) -[2023-10-09 10:25:40,799][23469] Updated weights for policy 1, policy_version 53471 (0.0010) -[2023-10-09 10:25:41,077][22500] Fps is (10 sec: 19661.4, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 109215744. Throughput: 0: 1798.3, 1: 1813.0. Samples: 27306016. Policy #0 lag: (min: 10.0, avg: 12.9, max: 42.0) -[2023-10-09 10:25:41,078][22500] Avg episode reward: [(0, '9.110'), (1, '8.440')] -[2023-10-09 10:25:44,292][23468] Updated weights for policy 0, policy_version 53193 (0.0008) -[2023-10-09 10:25:44,363][23469] Updated weights for policy 1, policy_version 53481 (0.0008) -[2023-10-09 10:25:44,667][23468] Updated weights for policy 0, policy_version 53203 (0.0009) -[2023-10-09 10:25:44,732][23469] Updated weights for policy 1, policy_version 53491 (0.0007) -[2023-10-09 10:25:45,039][23468] Updated weights for policy 0, policy_version 53213 (0.0007) -[2023-10-09 10:25:45,106][23469] Updated weights for policy 1, policy_version 53501 (0.0007) -[2023-10-09 10:25:46,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 109281280. Throughput: 0: 1762.2, 1: 1808.6. Samples: 27325368. Policy #0 lag: (min: 10.0, avg: 12.9, max: 42.0) -[2023-10-09 10:25:46,078][22500] Avg episode reward: [(0, '9.170'), (1, '8.560')] -[2023-10-09 10:25:48,809][23468] Updated weights for policy 0, policy_version 53223 (0.0009) -[2023-10-09 10:25:48,939][23469] Updated weights for policy 1, policy_version 53511 (0.0009) -[2023-10-09 10:25:49,181][23468] Updated weights for policy 0, policy_version 53233 (0.0009) -[2023-10-09 10:25:49,313][23469] Updated weights for policy 1, policy_version 53521 (0.0009) -[2023-10-09 10:25:49,547][23468] Updated weights for policy 0, policy_version 53243 (0.0008) -[2023-10-09 10:25:49,674][23469] Updated weights for policy 1, policy_version 53531 (0.0007) -[2023-10-09 10:25:51,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 109346816. Throughput: 0: 1786.0, 1: 1808.0. Samples: 27337810. Policy #0 lag: (min: 10.0, avg: 12.9, max: 42.0) -[2023-10-09 10:25:51,079][22500] Avg episode reward: [(0, '8.670'), (1, '7.880')] -[2023-10-09 10:25:53,449][23469] Updated weights for policy 1, policy_version 53541 (0.0007) -[2023-10-09 10:25:53,476][23468] Updated weights for policy 0, policy_version 53253 (0.0009) -[2023-10-09 10:25:53,818][23469] Updated weights for policy 1, policy_version 53551 (0.0008) -[2023-10-09 10:25:53,849][23468] Updated weights for policy 0, policy_version 53263 (0.0008) -[2023-10-09 10:25:54,189][23469] Updated weights for policy 1, policy_version 53561 (0.0008) -[2023-10-09 10:25:54,225][23468] Updated weights for policy 0, policy_version 53273 (0.0009) -[2023-10-09 10:25:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 109412352. Throughput: 0: 1770.1, 1: 1793.8. Samples: 27357312. Policy #0 lag: (min: 10.0, avg: 12.9, max: 42.0) -[2023-10-09 10:25:56,078][22500] Avg episode reward: [(0, '8.420'), (1, '8.340')] -[2023-10-09 10:25:57,932][23469] Updated weights for policy 1, policy_version 53571 (0.0008) -[2023-10-09 10:25:57,994][23468] Updated weights for policy 0, policy_version 53283 (0.0008) -[2023-10-09 10:25:58,301][23469] Updated weights for policy 1, policy_version 53581 (0.0008) -[2023-10-09 10:25:58,357][23468] Updated weights for policy 0, policy_version 53293 (0.0008) -[2023-10-09 10:25:58,670][23469] Updated weights for policy 1, policy_version 53591 (0.0009) -[2023-10-09 10:25:58,729][23468] Updated weights for policy 0, policy_version 53303 (0.0008) -[2023-10-09 10:26:01,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 109477888. Throughput: 0: 1764.0, 1: 1791.1. Samples: 27379280. Policy #0 lag: (min: 10.0, avg: 12.9, max: 42.0) -[2023-10-09 10:26:01,078][22500] Avg episode reward: [(0, '8.620'), (1, '8.280')] -[2023-10-09 10:26:02,533][23469] Updated weights for policy 1, policy_version 53601 (0.0008) -[2023-10-09 10:26:02,643][23468] Updated weights for policy 0, policy_version 53313 (0.0012) -[2023-10-09 10:26:02,913][23469] Updated weights for policy 1, policy_version 53611 (0.0007) -[2023-10-09 10:26:03,038][23468] Updated weights for policy 0, policy_version 53323 (0.0007) -[2023-10-09 10:26:03,285][23469] Updated weights for policy 1, policy_version 53621 (0.0008) -[2023-10-09 10:26:03,417][23468] Updated weights for policy 0, policy_version 53333 (0.0009) -[2023-10-09 10:26:03,654][23469] Updated weights for policy 1, policy_version 53631 (0.0007) -[2023-10-09 10:26:03,790][23468] Updated weights for policy 0, policy_version 53343 (0.0007) -[2023-10-09 10:26:06,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 109543424. Throughput: 0: 1783.1, 1: 1790.3. Samples: 27389646. Policy #0 lag: (min: 10.0, avg: 12.9, max: 42.0) -[2023-10-09 10:26:06,078][22500] Avg episode reward: [(0, '8.830'), (1, '8.250')] -[2023-10-09 10:26:07,351][23468] Updated weights for policy 0, policy_version 53353 (0.0007) -[2023-10-09 10:26:07,530][23469] Updated weights for policy 1, policy_version 53641 (0.0008) -[2023-10-09 10:26:07,718][23468] Updated weights for policy 0, policy_version 53363 (0.0010) -[2023-10-09 10:26:07,892][23469] Updated weights for policy 1, policy_version 53651 (0.0009) -[2023-10-09 10:26:08,093][23468] Updated weights for policy 0, policy_version 53373 (0.0009) -[2023-10-09 10:26:08,268][23469] Updated weights for policy 1, policy_version 53661 (0.0008) -[2023-10-09 10:26:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 109608960. Throughput: 0: 1771.4, 1: 1783.1. Samples: 27411166. Policy #0 lag: (min: 10.0, avg: 12.9, max: 42.0) -[2023-10-09 10:26:11,078][22500] Avg episode reward: [(0, '8.850'), (1, '8.510')] -[2023-10-09 10:26:11,906][23468] Updated weights for policy 0, policy_version 53383 (0.0008) -[2023-10-09 10:26:12,159][23469] Updated weights for policy 1, policy_version 53671 (0.0007) -[2023-10-09 10:26:12,278][23468] Updated weights for policy 0, policy_version 53393 (0.0008) -[2023-10-09 10:26:12,530][23469] Updated weights for policy 1, policy_version 53681 (0.0007) -[2023-10-09 10:26:12,657][23468] Updated weights for policy 0, policy_version 53403 (0.0007) -[2023-10-09 10:26:12,902][23469] Updated weights for policy 1, policy_version 53691 (0.0007) -[2023-10-09 10:26:16,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 109674496. Throughput: 0: 1778.9, 1: 1786.6. Samples: 27433580. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) -[2023-10-09 10:26:16,078][22500] Avg episode reward: [(0, '9.490'), (1, '8.060')] -[2023-10-09 10:26:16,088][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000053408_54689792.pth... -[2023-10-09 10:26:16,088][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000053696_54984704.pth... -[2023-10-09 10:26:16,126][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000051744_52985856.pth -[2023-10-09 10:26:16,127][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000052032_53280768.pth -[2023-10-09 10:26:16,417][23468] Updated weights for policy 0, policy_version 53413 (0.0008) -[2023-10-09 10:26:16,706][23469] Updated weights for policy 1, policy_version 53701 (0.0008) -[2023-10-09 10:26:16,787][23468] Updated weights for policy 0, policy_version 53423 (0.0007) -[2023-10-09 10:26:17,076][23469] Updated weights for policy 1, policy_version 53711 (0.0007) -[2023-10-09 10:26:17,157][23468] Updated weights for policy 0, policy_version 53433 (0.0007) -[2023-10-09 10:26:17,450][23469] Updated weights for policy 1, policy_version 53721 (0.0009) -[2023-10-09 10:26:21,003][23468] Updated weights for policy 0, policy_version 53443 (0.0008) -[2023-10-09 10:26:21,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 109740032. Throughput: 0: 1768.2, 1: 1772.7. Samples: 27443090. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) -[2023-10-09 10:26:21,078][22500] Avg episode reward: [(0, '9.000'), (1, '8.270')] -[2023-10-09 10:26:21,292][23469] Updated weights for policy 1, policy_version 53731 (0.0010) -[2023-10-09 10:26:21,378][23468] Updated weights for policy 0, policy_version 53453 (0.0007) -[2023-10-09 10:26:21,666][23469] Updated weights for policy 1, policy_version 53741 (0.0008) -[2023-10-09 10:26:21,753][23468] Updated weights for policy 0, policy_version 53463 (0.0009) -[2023-10-09 10:26:22,038][23469] Updated weights for policy 1, policy_version 53751 (0.0009) -[2023-10-09 10:26:25,569][23468] Updated weights for policy 0, policy_version 53473 (0.0008) -[2023-10-09 10:26:25,704][23469] Updated weights for policy 1, policy_version 53761 (0.0007) -[2023-10-09 10:26:25,933][23468] Updated weights for policy 0, policy_version 53483 (0.0009) -[2023-10-09 10:26:26,075][23469] Updated weights for policy 1, policy_version 53771 (0.0008) -[2023-10-09 10:26:26,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.6, 300 sec: 14218.0). Total num frames: 109805568. Throughput: 0: 1766.1, 1: 1773.5. Samples: 27465300. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) -[2023-10-09 10:26:26,078][22500] Avg episode reward: [(0, '9.050'), (1, '7.940')] -[2023-10-09 10:26:26,311][23468] Updated weights for policy 0, policy_version 53493 (0.0008) -[2023-10-09 10:26:26,443][23469] Updated weights for policy 1, policy_version 53781 (0.0007) -[2023-10-09 10:26:26,688][23468] Updated weights for policy 0, policy_version 53503 (0.0008) -[2023-10-09 10:26:26,810][23469] Updated weights for policy 1, policy_version 53791 (0.0008) -[2023-10-09 10:26:30,370][23468] Updated weights for policy 0, policy_version 53513 (0.0008) -[2023-10-09 10:26:30,476][23469] Updated weights for policy 1, policy_version 53801 (0.0009) -[2023-10-09 10:26:30,746][23468] Updated weights for policy 0, policy_version 53523 (0.0009) -[2023-10-09 10:26:30,844][23469] Updated weights for policy 1, policy_version 53811 (0.0011) -[2023-10-09 10:26:31,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 109871104. Throughput: 0: 1799.3, 1: 1788.5. Samples: 27486818. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) -[2023-10-09 10:26:31,079][22500] Avg episode reward: [(0, '8.590'), (1, '8.730')] -[2023-10-09 10:26:31,122][23468] Updated weights for policy 0, policy_version 53533 (0.0009) -[2023-10-09 10:26:31,220][23469] Updated weights for policy 1, policy_version 53821 (0.0008) -[2023-10-09 10:26:34,895][23468] Updated weights for policy 0, policy_version 53543 (0.0007) -[2023-10-09 10:26:35,060][23469] Updated weights for policy 1, policy_version 53831 (0.0009) -[2023-10-09 10:26:35,279][23468] Updated weights for policy 0, policy_version 53553 (0.0009) -[2023-10-09 10:26:35,420][23469] Updated weights for policy 1, policy_version 53841 (0.0010) -[2023-10-09 10:26:35,644][23468] Updated weights for policy 0, policy_version 53563 (0.0008) -[2023-10-09 10:26:35,795][23469] Updated weights for policy 1, policy_version 53851 (0.0007) -[2023-10-09 10:26:36,077][22500] Fps is (10 sec: 19660.5, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 110002176. Throughput: 0: 1776.0, 1: 1773.6. Samples: 27497540. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) -[2023-10-09 10:26:36,078][22500] Avg episode reward: [(0, '8.890'), (1, '8.230')] -[2023-10-09 10:26:39,442][23468] Updated weights for policy 0, policy_version 53573 (0.0008) -[2023-10-09 10:26:39,605][23469] Updated weights for policy 1, policy_version 53861 (0.0010) -[2023-10-09 10:26:39,813][23468] Updated weights for policy 0, policy_version 53583 (0.0008) -[2023-10-09 10:26:39,977][23469] Updated weights for policy 1, policy_version 53871 (0.0009) -[2023-10-09 10:26:40,174][23468] Updated weights for policy 0, policy_version 53593 (0.0007) -[2023-10-09 10:26:40,345][23469] Updated weights for policy 1, policy_version 53881 (0.0007) -[2023-10-09 10:26:41,077][22500] Fps is (10 sec: 19661.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 110067712. Throughput: 0: 1807.2, 1: 1793.3. Samples: 27519338. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) -[2023-10-09 10:26:41,078][22500] Avg episode reward: [(0, '8.630'), (1, '8.090')] -[2023-10-09 10:26:43,904][23468] Updated weights for policy 0, policy_version 53603 (0.0008) -[2023-10-09 10:26:44,124][23469] Updated weights for policy 1, policy_version 53891 (0.0009) -[2023-10-09 10:26:44,273][23468] Updated weights for policy 0, policy_version 53613 (0.0007) -[2023-10-09 10:26:44,483][23469] Updated weights for policy 1, policy_version 53901 (0.0008) -[2023-10-09 10:26:44,655][23468] Updated weights for policy 0, policy_version 53623 (0.0008) -[2023-10-09 10:26:44,860][23469] Updated weights for policy 1, policy_version 53911 (0.0008) -[2023-10-09 10:26:46,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 110133248. Throughput: 0: 1787.8, 1: 1766.7. Samples: 27539232. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) -[2023-10-09 10:26:46,078][22500] Avg episode reward: [(0, '8.770'), (1, '8.020')] -[2023-10-09 10:26:48,390][23468] Updated weights for policy 0, policy_version 53633 (0.0009) -[2023-10-09 10:26:48,601][23469] Updated weights for policy 1, policy_version 53921 (0.0007) -[2023-10-09 10:26:48,807][23468] Updated weights for policy 0, policy_version 53643 (0.0008) -[2023-10-09 10:26:49,016][23469] Updated weights for policy 1, policy_version 53931 (0.0008) -[2023-10-09 10:26:49,169][23468] Updated weights for policy 0, policy_version 53653 (0.0008) -[2023-10-09 10:26:49,383][23469] Updated weights for policy 1, policy_version 53941 (0.0008) -[2023-10-09 10:26:49,545][23468] Updated weights for policy 0, policy_version 53663 (0.0008) -[2023-10-09 10:26:49,748][23469] Updated weights for policy 1, policy_version 53951 (0.0009) -[2023-10-09 10:26:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 110198784. Throughput: 0: 1804.7, 1: 1799.3. Samples: 27551826. Policy #0 lag: (min: 28.0, avg: 31.6, max: 60.0) -[2023-10-09 10:26:51,078][22500] Avg episode reward: [(0, '8.580'), (1, '8.410')] -[2023-10-09 10:26:53,413][23468] Updated weights for policy 0, policy_version 53673 (0.0007) -[2023-10-09 10:26:53,556][23469] Updated weights for policy 1, policy_version 53961 (0.0008) -[2023-10-09 10:26:53,781][23468] Updated weights for policy 0, policy_version 53683 (0.0008) -[2023-10-09 10:26:53,925][23469] Updated weights for policy 1, policy_version 53971 (0.0009) -[2023-10-09 10:26:54,149][23468] Updated weights for policy 0, policy_version 53693 (0.0008) -[2023-10-09 10:26:54,299][23469] Updated weights for policy 1, policy_version 53981 (0.0009) -[2023-10-09 10:26:56,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 110264320. Throughput: 0: 1778.3, 1: 1775.4. Samples: 27571084. Policy #0 lag: (min: 28.0, avg: 31.6, max: 60.0) -[2023-10-09 10:26:56,079][22500] Avg episode reward: [(0, '8.470'), (1, '8.590')] -[2023-10-09 10:26:57,993][23468] Updated weights for policy 0, policy_version 53703 (0.0009) -[2023-10-09 10:26:58,037][23469] Updated weights for policy 1, policy_version 53991 (0.0008) -[2023-10-09 10:26:58,370][23468] Updated weights for policy 0, policy_version 53713 (0.0009) -[2023-10-09 10:26:58,408][23469] Updated weights for policy 1, policy_version 54001 (0.0008) -[2023-10-09 10:26:58,749][23468] Updated weights for policy 0, policy_version 53723 (0.0007) -[2023-10-09 10:26:58,773][23469] Updated weights for policy 1, policy_version 54011 (0.0009) -[2023-10-09 10:27:01,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 110329856. Throughput: 0: 1776.1, 1: 1777.0. Samples: 27593470. Policy #0 lag: (min: 28.0, avg: 31.6, max: 60.0) -[2023-10-09 10:27:01,078][22500] Avg episode reward: [(0, '8.360'), (1, '8.530')] -[2023-10-09 10:27:02,364][23468] Updated weights for policy 0, policy_version 53733 (0.0009) -[2023-10-09 10:27:02,455][23469] Updated weights for policy 1, policy_version 54021 (0.0007) -[2023-10-09 10:27:02,740][23468] Updated weights for policy 0, policy_version 53743 (0.0008) -[2023-10-09 10:27:02,826][23469] Updated weights for policy 1, policy_version 54031 (0.0007) -[2023-10-09 10:27:03,110][23468] Updated weights for policy 0, policy_version 53753 (0.0007) -[2023-10-09 10:27:03,195][23469] Updated weights for policy 1, policy_version 54041 (0.0009) -[2023-10-09 10:27:06,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 110395392. Throughput: 0: 1782.9, 1: 1780.7. Samples: 27603454. Policy #0 lag: (min: 28.0, avg: 31.6, max: 60.0) -[2023-10-09 10:27:06,078][22500] Avg episode reward: [(0, '8.430'), (1, '8.610')] -[2023-10-09 10:27:06,846][23469] Updated weights for policy 1, policy_version 54051 (0.0008) -[2023-10-09 10:27:06,991][23468] Updated weights for policy 0, policy_version 53763 (0.0008) -[2023-10-09 10:27:07,220][23469] Updated weights for policy 1, policy_version 54061 (0.0008) -[2023-10-09 10:27:07,358][23468] Updated weights for policy 0, policy_version 53773 (0.0009) -[2023-10-09 10:27:07,580][23469] Updated weights for policy 1, policy_version 54071 (0.0007) -[2023-10-09 10:27:07,727][23468] Updated weights for policy 0, policy_version 53783 (0.0009) -[2023-10-09 10:27:11,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 110460928. Throughput: 0: 1778.6, 1: 1789.6. Samples: 27625872. Policy #0 lag: (min: 28.0, avg: 31.6, max: 60.0) -[2023-10-09 10:27:11,078][22500] Avg episode reward: [(0, '8.460'), (1, '8.270')] -[2023-10-09 10:27:11,379][23469] Updated weights for policy 1, policy_version 54081 (0.0007) -[2023-10-09 10:27:11,455][23468] Updated weights for policy 0, policy_version 53793 (0.0009) -[2023-10-09 10:27:11,745][23469] Updated weights for policy 1, policy_version 54091 (0.0008) -[2023-10-09 10:27:11,834][23468] Updated weights for policy 0, policy_version 53803 (0.0007) -[2023-10-09 10:27:12,117][23469] Updated weights for policy 1, policy_version 54101 (0.0007) -[2023-10-09 10:27:12,203][23468] Updated weights for policy 0, policy_version 53813 (0.0007) -[2023-10-09 10:27:12,491][23469] Updated weights for policy 1, policy_version 54111 (0.0009) -[2023-10-09 10:27:12,571][23468] Updated weights for policy 0, policy_version 53823 (0.0010) -[2023-10-09 10:27:16,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 110526464. Throughput: 0: 1783.4, 1: 1804.1. Samples: 27648256. Policy #0 lag: (min: 28.0, avg: 31.6, max: 60.0) -[2023-10-09 10:27:16,079][22500] Avg episode reward: [(0, '9.200'), (1, '8.320')] -[2023-10-09 10:27:16,230][23469] Updated weights for policy 1, policy_version 54121 (0.0007) -[2023-10-09 10:27:16,319][23468] Updated weights for policy 0, policy_version 53833 (0.0008) -[2023-10-09 10:27:16,604][23469] Updated weights for policy 1, policy_version 54131 (0.0007) -[2023-10-09 10:27:16,690][23468] Updated weights for policy 0, policy_version 53843 (0.0007) -[2023-10-09 10:27:16,973][23469] Updated weights for policy 1, policy_version 54141 (0.0007) -[2023-10-09 10:27:17,057][23468] Updated weights for policy 0, policy_version 53853 (0.0009) -[2023-10-09 10:27:20,712][23469] Updated weights for policy 1, policy_version 54151 (0.0009) -[2023-10-09 10:27:20,841][23468] Updated weights for policy 0, policy_version 53863 (0.0008) -[2023-10-09 10:27:21,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 110592000. Throughput: 0: 1776.1, 1: 1789.2. Samples: 27657976. Policy #0 lag: (min: 28.0, avg: 31.6, max: 60.0) -[2023-10-09 10:27:21,078][22500] Avg episode reward: [(0, '8.860'), (1, '8.150')] -[2023-10-09 10:27:21,079][23469] Updated weights for policy 1, policy_version 54161 (0.0008) -[2023-10-09 10:27:21,213][23468] Updated weights for policy 0, policy_version 53873 (0.0007) -[2023-10-09 10:27:21,443][23469] Updated weights for policy 1, policy_version 54171 (0.0007) -[2023-10-09 10:27:21,581][23468] Updated weights for policy 0, policy_version 53883 (0.0007) -[2023-10-09 10:27:25,334][23469] Updated weights for policy 1, policy_version 54181 (0.0009) -[2023-10-09 10:27:25,377][23468] Updated weights for policy 0, policy_version 53893 (0.0010) -[2023-10-09 10:27:25,699][23469] Updated weights for policy 1, policy_version 54191 (0.0009) -[2023-10-09 10:27:25,739][23468] Updated weights for policy 0, policy_version 53903 (0.0010) -[2023-10-09 10:27:26,068][23469] Updated weights for policy 1, policy_version 54201 (0.0007) -[2023-10-09 10:27:26,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 110657536. Throughput: 0: 1775.2, 1: 1799.5. Samples: 27680196. Policy #0 lag: (min: 28.0, avg: 31.6, max: 60.0) -[2023-10-09 10:27:26,078][22500] Avg episode reward: [(0, '9.220'), (1, '8.060')] -[2023-10-09 10:27:26,119][23468] Updated weights for policy 0, policy_version 53913 (0.0009) -[2023-10-09 10:27:29,854][23468] Updated weights for policy 0, policy_version 53923 (0.0009) -[2023-10-09 10:27:29,943][23469] Updated weights for policy 1, policy_version 54211 (0.0009) -[2023-10-09 10:27:30,232][23468] Updated weights for policy 0, policy_version 53933 (0.0007) -[2023-10-09 10:27:30,322][23469] Updated weights for policy 1, policy_version 54221 (0.0007) -[2023-10-09 10:27:30,601][23468] Updated weights for policy 0, policy_version 53943 (0.0008) -[2023-10-09 10:27:30,683][23469] Updated weights for policy 1, policy_version 54231 (0.0007) -[2023-10-09 10:27:31,077][22500] Fps is (10 sec: 19660.6, 60 sec: 15291.8, 300 sec: 14440.1). Total num frames: 110788608. Throughput: 0: 1793.4, 1: 1797.4. Samples: 27700820. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:27:31,078][22500] Avg episode reward: [(0, '9.690'), (1, '8.230')] -[2023-10-09 10:27:34,232][23468] Updated weights for policy 0, policy_version 53953 (0.0009) -[2023-10-09 10:27:34,537][23469] Updated weights for policy 1, policy_version 54241 (0.0008) -[2023-10-09 10:27:34,653][23468] Updated weights for policy 0, policy_version 53963 (0.0008) -[2023-10-09 10:27:34,950][23469] Updated weights for policy 1, policy_version 54251 (0.0007) -[2023-10-09 10:27:35,033][23468] Updated weights for policy 0, policy_version 53973 (0.0009) -[2023-10-09 10:27:35,328][23469] Updated weights for policy 1, policy_version 54261 (0.0007) -[2023-10-09 10:27:35,419][23468] Updated weights for policy 0, policy_version 53983 (0.0009) -[2023-10-09 10:27:35,695][23469] Updated weights for policy 1, policy_version 54271 (0.0010) -[2023-10-09 10:27:36,078][22500] Fps is (10 sec: 19660.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 110854144. Throughput: 0: 1777.6, 1: 1788.9. Samples: 27712320. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:27:36,079][22500] Avg episode reward: [(0, '8.850'), (1, '8.060')] -[2023-10-09 10:27:39,127][23468] Updated weights for policy 0, policy_version 53993 (0.0010) -[2023-10-09 10:27:39,441][23469] Updated weights for policy 1, policy_version 54281 (0.0009) -[2023-10-09 10:27:39,502][23468] Updated weights for policy 0, policy_version 54003 (0.0008) -[2023-10-09 10:27:39,807][23469] Updated weights for policy 1, policy_version 54291 (0.0009) -[2023-10-09 10:27:39,864][23468] Updated weights for policy 0, policy_version 54013 (0.0007) -[2023-10-09 10:27:40,180][23469] Updated weights for policy 1, policy_version 54301 (0.0009) -[2023-10-09 10:27:41,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 110919680. Throughput: 0: 1800.0, 1: 1798.7. Samples: 27733024. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:27:41,078][22500] Avg episode reward: [(0, '9.360'), (1, '8.620')] -[2023-10-09 10:27:43,751][23468] Updated weights for policy 0, policy_version 54023 (0.0008) -[2023-10-09 10:27:43,860][23469] Updated weights for policy 1, policy_version 54311 (0.0008) -[2023-10-09 10:27:44,118][23468] Updated weights for policy 0, policy_version 54033 (0.0007) -[2023-10-09 10:27:44,236][23469] Updated weights for policy 1, policy_version 54321 (0.0009) -[2023-10-09 10:27:44,487][23468] Updated weights for policy 0, policy_version 54043 (0.0009) -[2023-10-09 10:27:44,604][23469] Updated weights for policy 1, policy_version 54331 (0.0009) -[2023-10-09 10:27:46,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 110985216. Throughput: 0: 1780.5, 1: 1780.8. Samples: 27753732. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:27:46,078][22500] Avg episode reward: [(0, '9.290'), (1, '8.660')] -[2023-10-09 10:27:48,226][23468] Updated weights for policy 0, policy_version 54053 (0.0010) -[2023-10-09 10:27:48,428][23469] Updated weights for policy 1, policy_version 54341 (0.0008) -[2023-10-09 10:27:48,595][23468] Updated weights for policy 0, policy_version 54063 (0.0008) -[2023-10-09 10:27:48,798][23469] Updated weights for policy 1, policy_version 54351 (0.0009) -[2023-10-09 10:27:48,977][23468] Updated weights for policy 0, policy_version 54073 (0.0008) -[2023-10-09 10:27:49,170][23469] Updated weights for policy 1, policy_version 54361 (0.0009) -[2023-10-09 10:27:51,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 111050752. Throughput: 0: 1803.3, 1: 1794.9. Samples: 27765374. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:27:51,078][22500] Avg episode reward: [(0, '9.750'), (1, '8.670')] -[2023-10-09 10:27:52,903][23468] Updated weights for policy 0, policy_version 54083 (0.0008) -[2023-10-09 10:27:53,157][23469] Updated weights for policy 1, policy_version 54371 (0.0009) -[2023-10-09 10:27:53,269][23468] Updated weights for policy 0, policy_version 54093 (0.0007) -[2023-10-09 10:27:53,526][23469] Updated weights for policy 1, policy_version 54381 (0.0008) -[2023-10-09 10:27:53,639][23468] Updated weights for policy 0, policy_version 54103 (0.0009) -[2023-10-09 10:27:53,892][23469] Updated weights for policy 1, policy_version 54391 (0.0008) -[2023-10-09 10:27:56,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 111116288. Throughput: 0: 1781.3, 1: 1763.0. Samples: 27785366. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:27:56,078][22500] Avg episode reward: [(0, '8.880'), (1, '8.530')] -[2023-10-09 10:27:57,393][23468] Updated weights for policy 0, policy_version 54113 (0.0009) -[2023-10-09 10:27:57,589][23469] Updated weights for policy 1, policy_version 54401 (0.0010) -[2023-10-09 10:27:57,771][23468] Updated weights for policy 0, policy_version 54123 (0.0010) -[2023-10-09 10:27:57,962][23469] Updated weights for policy 1, policy_version 54411 (0.0009) -[2023-10-09 10:27:58,140][23468] Updated weights for policy 0, policy_version 54133 (0.0009) -[2023-10-09 10:27:58,331][23469] Updated weights for policy 1, policy_version 54421 (0.0008) -[2023-10-09 10:27:58,512][23468] Updated weights for policy 0, policy_version 54143 (0.0008) -[2023-10-09 10:27:58,692][23469] Updated weights for policy 1, policy_version 54431 (0.0008) -[2023-10-09 10:28:01,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 111181824. Throughput: 0: 1781.4, 1: 1757.2. Samples: 27807494. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:28:01,078][22500] Avg episode reward: [(0, '9.060'), (1, '8.380')] -[2023-10-09 10:28:02,312][23468] Updated weights for policy 0, policy_version 54153 (0.0008) -[2023-10-09 10:28:02,576][23469] Updated weights for policy 1, policy_version 54441 (0.0009) -[2023-10-09 10:28:02,685][23468] Updated weights for policy 0, policy_version 54163 (0.0010) -[2023-10-09 10:28:02,950][23469] Updated weights for policy 1, policy_version 54451 (0.0009) -[2023-10-09 10:28:03,066][23468] Updated weights for policy 0, policy_version 54173 (0.0008) -[2023-10-09 10:28:03,322][23469] Updated weights for policy 1, policy_version 54461 (0.0010) -[2023-10-09 10:28:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 111247360. Throughput: 0: 1776.8, 1: 1757.5. Samples: 27817022. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:28:06,078][22500] Avg episode reward: [(0, '7.930'), (1, '8.150')] -[2023-10-09 10:28:06,701][23468] Updated weights for policy 0, policy_version 54183 (0.0008) -[2023-10-09 10:28:06,997][23469] Updated weights for policy 1, policy_version 54471 (0.0009) -[2023-10-09 10:28:07,073][23468] Updated weights for policy 0, policy_version 54193 (0.0008) -[2023-10-09 10:28:07,363][23469] Updated weights for policy 1, policy_version 54481 (0.0008) -[2023-10-09 10:28:07,442][23468] Updated weights for policy 0, policy_version 54203 (0.0008) -[2023-10-09 10:28:07,732][23469] Updated weights for policy 1, policy_version 54491 (0.0008) -[2023-10-09 10:28:11,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 111312896. Throughput: 0: 1778.8, 1: 1766.1. Samples: 27839718. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:28:11,078][22500] Avg episode reward: [(0, '8.130'), (1, '8.320')] -[2023-10-09 10:28:11,344][23468] Updated weights for policy 0, policy_version 54213 (0.0008) -[2023-10-09 10:28:11,509][23469] Updated weights for policy 1, policy_version 54501 (0.0008) -[2023-10-09 10:28:11,722][23468] Updated weights for policy 0, policy_version 54223 (0.0008) -[2023-10-09 10:28:11,869][23469] Updated weights for policy 1, policy_version 54511 (0.0009) -[2023-10-09 10:28:12,092][23468] Updated weights for policy 0, policy_version 54233 (0.0007) -[2023-10-09 10:28:12,232][23469] Updated weights for policy 1, policy_version 54521 (0.0010) -[2023-10-09 10:28:15,797][23468] Updated weights for policy 0, policy_version 54243 (0.0008) -[2023-10-09 10:28:16,019][23469] Updated weights for policy 1, policy_version 54531 (0.0008) -[2023-10-09 10:28:16,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 111378432. Throughput: 0: 1789.1, 1: 1787.5. Samples: 27861766. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:28:16,078][22500] Avg episode reward: [(0, '8.650'), (1, '8.630')] -[2023-10-09 10:28:16,168][23468] Updated weights for policy 0, policy_version 54253 (0.0008) -[2023-10-09 10:28:16,396][23469] Updated weights for policy 1, policy_version 54541 (0.0008) -[2023-10-09 10:28:16,541][23468] Updated weights for policy 0, policy_version 54263 (0.0008) -[2023-10-09 10:28:16,766][23469] Updated weights for policy 1, policy_version 54551 (0.0008) -[2023-10-09 10:28:16,874][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000054272_55574528.pth... -[2023-10-09 10:28:16,904][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000052576_53837824.pth -[2023-10-09 10:28:17,090][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000054560_55869440.pth... -[2023-10-09 10:28:17,118][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000052864_54132736.pth -[2023-10-09 10:28:20,397][23468] Updated weights for policy 0, policy_version 54273 (0.0009) -[2023-10-09 10:28:20,544][23469] Updated weights for policy 1, policy_version 54561 (0.0008) -[2023-10-09 10:28:20,802][23468] Updated weights for policy 0, policy_version 54283 (0.0008) -[2023-10-09 10:28:20,931][23469] Updated weights for policy 1, policy_version 54571 (0.0007) -[2023-10-09 10:28:21,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 111443968. Throughput: 0: 1771.3, 1: 1764.0. Samples: 27871406. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:28:21,078][22500] Avg episode reward: [(0, '8.880'), (1, '8.910')] -[2023-10-09 10:28:21,172][23468] Updated weights for policy 0, policy_version 54293 (0.0009) -[2023-10-09 10:28:21,301][23469] Updated weights for policy 1, policy_version 54581 (0.0007) -[2023-10-09 10:28:21,539][23468] Updated weights for policy 0, policy_version 54303 (0.0007) -[2023-10-09 10:28:21,670][23469] Updated weights for policy 1, policy_version 54591 (0.0008) -[2023-10-09 10:28:25,310][23468] Updated weights for policy 0, policy_version 54313 (0.0008) -[2023-10-09 10:28:25,383][23469] Updated weights for policy 1, policy_version 54601 (0.0010) -[2023-10-09 10:28:25,682][23468] Updated weights for policy 0, policy_version 54323 (0.0007) -[2023-10-09 10:28:25,760][23469] Updated weights for policy 1, policy_version 54611 (0.0009) -[2023-10-09 10:28:26,053][23468] Updated weights for policy 0, policy_version 54333 (0.0007) -[2023-10-09 10:28:26,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 111509504. Throughput: 0: 1789.5, 1: 1785.1. Samples: 27893884. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:28:26,079][22500] Avg episode reward: [(0, '8.670'), (1, '8.530')] -[2023-10-09 10:28:26,120][23469] Updated weights for policy 1, policy_version 54621 (0.0009) -[2023-10-09 10:28:29,879][23469] Updated weights for policy 1, policy_version 54631 (0.0008) -[2023-10-09 10:28:30,026][23468] Updated weights for policy 0, policy_version 54343 (0.0009) -[2023-10-09 10:28:30,236][23469] Updated weights for policy 1, policy_version 54641 (0.0008) -[2023-10-09 10:28:30,398][23468] Updated weights for policy 0, policy_version 54353 (0.0009) -[2023-10-09 10:28:30,606][23469] Updated weights for policy 1, policy_version 54651 (0.0009) -[2023-10-09 10:28:30,768][23468] Updated weights for policy 0, policy_version 54363 (0.0008) -[2023-10-09 10:28:31,077][22500] Fps is (10 sec: 19660.7, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 111640576. Throughput: 0: 1789.6, 1: 1773.9. Samples: 27914090. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:28:31,078][22500] Avg episode reward: [(0, '8.310'), (1, '8.390')] -[2023-10-09 10:28:34,363][23469] Updated weights for policy 1, policy_version 54661 (0.0009) -[2023-10-09 10:28:34,474][23468] Updated weights for policy 0, policy_version 54373 (0.0008) -[2023-10-09 10:28:34,741][23469] Updated weights for policy 1, policy_version 54671 (0.0007) -[2023-10-09 10:28:34,835][23468] Updated weights for policy 0, policy_version 54383 (0.0007) -[2023-10-09 10:28:35,107][23469] Updated weights for policy 1, policy_version 54681 (0.0008) -[2023-10-09 10:28:35,207][23468] Updated weights for policy 0, policy_version 54393 (0.0009) -[2023-10-09 10:28:36,077][22500] Fps is (10 sec: 19661.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 111706112. Throughput: 0: 1776.0, 1: 1789.1. Samples: 27925804. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:28:36,078][22500] Avg episode reward: [(0, '8.700'), (1, '8.040')] -[2023-10-09 10:28:38,864][23469] Updated weights for policy 1, policy_version 54691 (0.0008) -[2023-10-09 10:28:39,047][23468] Updated weights for policy 0, policy_version 54403 (0.0007) -[2023-10-09 10:28:39,240][23469] Updated weights for policy 1, policy_version 54701 (0.0009) -[2023-10-09 10:28:39,408][23468] Updated weights for policy 0, policy_version 54413 (0.0008) -[2023-10-09 10:28:39,595][23469] Updated weights for policy 1, policy_version 54711 (0.0009) -[2023-10-09 10:28:39,787][23468] Updated weights for policy 0, policy_version 54423 (0.0008) -[2023-10-09 10:28:41,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 111771648. Throughput: 0: 1793.0, 1: 1786.4. Samples: 27946440. Policy #0 lag: (min: 25.0, avg: 34.9, max: 57.0) -[2023-10-09 10:28:41,078][22500] Avg episode reward: [(0, '8.600'), (1, '7.870')] -[2023-10-09 10:28:43,391][23469] Updated weights for policy 1, policy_version 54721 (0.0009) -[2023-10-09 10:28:43,545][23468] Updated weights for policy 0, policy_version 54433 (0.0007) -[2023-10-09 10:28:43,760][23469] Updated weights for policy 1, policy_version 54731 (0.0008) -[2023-10-09 10:28:43,918][23468] Updated weights for policy 0, policy_version 54443 (0.0007) -[2023-10-09 10:28:44,122][23469] Updated weights for policy 1, policy_version 54741 (0.0007) -[2023-10-09 10:28:44,294][23468] Updated weights for policy 0, policy_version 54453 (0.0008) -[2023-10-09 10:28:44,494][23469] Updated weights for policy 1, policy_version 54751 (0.0008) -[2023-10-09 10:28:44,671][23468] Updated weights for policy 0, policy_version 54463 (0.0009) -[2023-10-09 10:28:46,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 111837184. Throughput: 0: 1767.5, 1: 1780.0. Samples: 27967132. Policy #0 lag: (min: 25.0, avg: 34.9, max: 57.0) -[2023-10-09 10:28:46,078][22500] Avg episode reward: [(0, '9.620'), (1, '7.770')] -[2023-10-09 10:28:48,275][23469] Updated weights for policy 1, policy_version 54761 (0.0009) -[2023-10-09 10:28:48,490][23468] Updated weights for policy 0, policy_version 54473 (0.0009) -[2023-10-09 10:28:48,645][23469] Updated weights for policy 1, policy_version 54771 (0.0009) -[2023-10-09 10:28:48,866][23468] Updated weights for policy 0, policy_version 54483 (0.0009) -[2023-10-09 10:28:49,014][23469] Updated weights for policy 1, policy_version 54781 (0.0009) -[2023-10-09 10:28:49,238][23468] Updated weights for policy 0, policy_version 54493 (0.0008) -[2023-10-09 10:28:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 111902720. Throughput: 0: 1800.0, 1: 1788.8. Samples: 27978520. Policy #0 lag: (min: 25.0, avg: 34.9, max: 57.0) -[2023-10-09 10:28:51,078][22500] Avg episode reward: [(0, '9.650'), (1, '8.810')] -[2023-10-09 10:28:52,914][23469] Updated weights for policy 1, policy_version 54791 (0.0008) -[2023-10-09 10:28:53,078][23468] Updated weights for policy 0, policy_version 54503 (0.0007) -[2023-10-09 10:28:53,284][23469] Updated weights for policy 1, policy_version 54801 (0.0007) -[2023-10-09 10:28:53,448][23468] Updated weights for policy 0, policy_version 54513 (0.0010) -[2023-10-09 10:28:53,661][23469] Updated weights for policy 1, policy_version 54811 (0.0007) -[2023-10-09 10:28:53,819][23468] Updated weights for policy 0, policy_version 54523 (0.0007) -[2023-10-09 10:28:56,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 111968256. Throughput: 0: 1765.0, 1: 1772.8. Samples: 27998920. Policy #0 lag: (min: 25.0, avg: 34.9, max: 57.0) -[2023-10-09 10:28:56,078][22500] Avg episode reward: [(0, '8.840'), (1, '8.490')] -[2023-10-09 10:28:57,388][23469] Updated weights for policy 1, policy_version 54821 (0.0008) -[2023-10-09 10:28:57,632][23468] Updated weights for policy 0, policy_version 54533 (0.0008) -[2023-10-09 10:28:57,761][23469] Updated weights for policy 1, policy_version 54831 (0.0009) -[2023-10-09 10:28:58,007][23468] Updated weights for policy 0, policy_version 54543 (0.0009) -[2023-10-09 10:28:58,119][23469] Updated weights for policy 1, policy_version 54841 (0.0007) -[2023-10-09 10:28:58,381][23468] Updated weights for policy 0, policy_version 54553 (0.0008) -[2023-10-09 10:29:01,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 112033792. Throughput: 0: 1769.3, 1: 1778.5. Samples: 28021416. Policy #0 lag: (min: 25.0, avg: 34.9, max: 57.0) -[2023-10-09 10:29:01,079][22500] Avg episode reward: [(0, '8.630'), (1, '8.710')] -[2023-10-09 10:29:01,990][23469] Updated weights for policy 1, policy_version 54851 (0.0007) -[2023-10-09 10:29:02,135][23468] Updated weights for policy 0, policy_version 54563 (0.0009) -[2023-10-09 10:29:02,365][23469] Updated weights for policy 1, policy_version 54861 (0.0007) -[2023-10-09 10:29:02,509][23468] Updated weights for policy 0, policy_version 54573 (0.0009) -[2023-10-09 10:29:02,742][23469] Updated weights for policy 1, policy_version 54871 (0.0008) -[2023-10-09 10:29:02,871][23468] Updated weights for policy 0, policy_version 54583 (0.0008) -[2023-10-09 10:29:06,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 112099328. Throughput: 0: 1769.2, 1: 1776.8. Samples: 28030974. Policy #0 lag: (min: 25.0, avg: 34.9, max: 57.0) -[2023-10-09 10:29:06,078][22500] Avg episode reward: [(0, '9.020'), (1, '8.840')] -[2023-10-09 10:29:06,535][23469] Updated weights for policy 1, policy_version 54881 (0.0008) -[2023-10-09 10:29:06,699][23468] Updated weights for policy 0, policy_version 54593 (0.0007) -[2023-10-09 10:29:06,959][23469] Updated weights for policy 1, policy_version 54891 (0.0009) -[2023-10-09 10:29:07,112][23468] Updated weights for policy 0, policy_version 54603 (0.0007) -[2023-10-09 10:29:07,323][23469] Updated weights for policy 1, policy_version 54901 (0.0007) -[2023-10-09 10:29:07,486][23468] Updated weights for policy 0, policy_version 54613 (0.0007) -[2023-10-09 10:29:07,694][23469] Updated weights for policy 1, policy_version 54911 (0.0007) -[2023-10-09 10:29:07,865][23468] Updated weights for policy 0, policy_version 54623 (0.0008) -[2023-10-09 10:29:11,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 112164864. Throughput: 0: 1759.0, 1: 1769.1. Samples: 28052646. Policy #0 lag: (min: 25.0, avg: 34.9, max: 57.0) -[2023-10-09 10:29:11,078][22500] Avg episode reward: [(0, '9.320'), (1, '8.650')] -[2023-10-09 10:29:11,626][23469] Updated weights for policy 1, policy_version 54921 (0.0007) -[2023-10-09 10:29:11,724][23468] Updated weights for policy 0, policy_version 54633 (0.0009) -[2023-10-09 10:29:12,003][23469] Updated weights for policy 1, policy_version 54931 (0.0009) -[2023-10-09 10:29:12,094][23468] Updated weights for policy 0, policy_version 54643 (0.0008) -[2023-10-09 10:29:12,366][23469] Updated weights for policy 1, policy_version 54941 (0.0008) -[2023-10-09 10:29:12,472][23468] Updated weights for policy 0, policy_version 54653 (0.0007) -[2023-10-09 10:29:16,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 112230400. Throughput: 0: 1776.5, 1: 1795.3. Samples: 28074824. Policy #0 lag: (min: 25.0, avg: 34.9, max: 57.0) -[2023-10-09 10:29:16,078][22500] Avg episode reward: [(0, '9.240'), (1, '8.450')] -[2023-10-09 10:29:16,152][23469] Updated weights for policy 1, policy_version 54951 (0.0009) -[2023-10-09 10:29:16,329][23468] Updated weights for policy 0, policy_version 54663 (0.0009) -[2023-10-09 10:29:16,522][23469] Updated weights for policy 1, policy_version 54961 (0.0007) -[2023-10-09 10:29:16,699][23468] Updated weights for policy 0, policy_version 54673 (0.0008) -[2023-10-09 10:29:16,893][23469] Updated weights for policy 1, policy_version 54971 (0.0008) -[2023-10-09 10:29:17,073][23468] Updated weights for policy 0, policy_version 54683 (0.0009) -[2023-10-09 10:29:20,616][23469] Updated weights for policy 1, policy_version 54981 (0.0008) -[2023-10-09 10:29:20,767][23468] Updated weights for policy 0, policy_version 54693 (0.0009) -[2023-10-09 10:29:20,975][23469] Updated weights for policy 1, policy_version 54991 (0.0008) -[2023-10-09 10:29:21,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 112295936. Throughput: 0: 1759.6, 1: 1768.3. Samples: 28084558. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:29:21,078][22500] Avg episode reward: [(0, '8.780'), (1, '8.810')] -[2023-10-09 10:29:21,137][23468] Updated weights for policy 0, policy_version 54703 (0.0009) -[2023-10-09 10:29:21,346][23469] Updated weights for policy 1, policy_version 55001 (0.0008) -[2023-10-09 10:29:21,507][23468] Updated weights for policy 0, policy_version 54713 (0.0009) -[2023-10-09 10:29:25,191][23468] Updated weights for policy 0, policy_version 54723 (0.0008) -[2023-10-09 10:29:25,213][23469] Updated weights for policy 1, policy_version 55011 (0.0008) -[2023-10-09 10:29:25,568][23468] Updated weights for policy 0, policy_version 54733 (0.0009) -[2023-10-09 10:29:25,581][23469] Updated weights for policy 1, policy_version 55021 (0.0008) -[2023-10-09 10:29:25,944][23468] Updated weights for policy 0, policy_version 54743 (0.0008) -[2023-10-09 10:29:25,958][23469] Updated weights for policy 1, policy_version 55031 (0.0008) -[2023-10-09 10:29:26,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 112361472. Throughput: 0: 1773.3, 1: 1792.3. Samples: 28106894. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:29:26,078][22500] Avg episode reward: [(0, '8.680'), (1, '7.790')] -[2023-10-09 10:29:29,653][23469] Updated weights for policy 1, policy_version 55041 (0.0008) -[2023-10-09 10:29:29,708][23468] Updated weights for policy 0, policy_version 54753 (0.0008) -[2023-10-09 10:29:30,022][23469] Updated weights for policy 1, policy_version 55051 (0.0008) -[2023-10-09 10:29:30,081][23468] Updated weights for policy 0, policy_version 54763 (0.0008) -[2023-10-09 10:29:30,393][23469] Updated weights for policy 1, policy_version 55061 (0.0009) -[2023-10-09 10:29:30,453][23468] Updated weights for policy 0, policy_version 54773 (0.0007) -[2023-10-09 10:29:30,750][23469] Updated weights for policy 1, policy_version 55071 (0.0008) -[2023-10-09 10:29:30,825][23468] Updated weights for policy 0, policy_version 54783 (0.0007) -[2023-10-09 10:29:31,077][22500] Fps is (10 sec: 19660.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 112492544. Throughput: 0: 1779.8, 1: 1774.3. Samples: 28127066. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:29:31,078][22500] Avg episode reward: [(0, '9.170'), (1, '8.390')] -[2023-10-09 10:29:34,480][23469] Updated weights for policy 1, policy_version 55081 (0.0007) -[2023-10-09 10:29:34,645][23468] Updated weights for policy 0, policy_version 54793 (0.0008) -[2023-10-09 10:29:34,841][23469] Updated weights for policy 1, policy_version 55091 (0.0007) -[2023-10-09 10:29:35,011][23468] Updated weights for policy 0, policy_version 54803 (0.0008) -[2023-10-09 10:29:35,220][23469] Updated weights for policy 1, policy_version 55101 (0.0007) -[2023-10-09 10:29:35,384][23468] Updated weights for policy 0, policy_version 54813 (0.0007) -[2023-10-09 10:29:36,077][22500] Fps is (10 sec: 19660.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 112558080. Throughput: 0: 1768.4, 1: 1798.8. Samples: 28139044. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:29:36,078][22500] Avg episode reward: [(0, '9.010'), (1, '8.830')] -[2023-10-09 10:29:38,858][23469] Updated weights for policy 1, policy_version 55111 (0.0007) -[2023-10-09 10:29:39,162][23468] Updated weights for policy 0, policy_version 54823 (0.0008) -[2023-10-09 10:29:39,222][23469] Updated weights for policy 1, policy_version 55121 (0.0007) -[2023-10-09 10:29:39,537][23468] Updated weights for policy 0, policy_version 54833 (0.0007) -[2023-10-09 10:29:39,588][23469] Updated weights for policy 1, policy_version 55131 (0.0008) -[2023-10-09 10:29:39,905][23468] Updated weights for policy 0, policy_version 54843 (0.0010) -[2023-10-09 10:29:41,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 112623616. Throughput: 0: 1789.0, 1: 1779.7. Samples: 28159510. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:29:41,078][22500] Avg episode reward: [(0, '9.210'), (1, '8.620')] -[2023-10-09 10:29:43,373][23469] Updated weights for policy 1, policy_version 55141 (0.0008) -[2023-10-09 10:29:43,658][23468] Updated weights for policy 0, policy_version 54853 (0.0008) -[2023-10-09 10:29:43,732][23469] Updated weights for policy 1, policy_version 55151 (0.0007) -[2023-10-09 10:29:44,023][23468] Updated weights for policy 0, policy_version 54863 (0.0010) -[2023-10-09 10:29:44,099][23469] Updated weights for policy 1, policy_version 55161 (0.0009) -[2023-10-09 10:29:44,394][23468] Updated weights for policy 0, policy_version 54873 (0.0008) -[2023-10-09 10:29:46,078][22500] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 112689152. Throughput: 0: 1765.9, 1: 1777.3. Samples: 28180860. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:29:46,079][22500] Avg episode reward: [(0, '8.600'), (1, '8.500')] -[2023-10-09 10:29:47,822][23469] Updated weights for policy 1, policy_version 55171 (0.0009) -[2023-10-09 10:29:48,193][23469] Updated weights for policy 1, policy_version 55181 (0.0010) -[2023-10-09 10:29:48,260][23468] Updated weights for policy 0, policy_version 54883 (0.0007) -[2023-10-09 10:29:48,557][23469] Updated weights for policy 1, policy_version 55191 (0.0009) -[2023-10-09 10:29:48,644][23468] Updated weights for policy 0, policy_version 54893 (0.0007) -[2023-10-09 10:29:49,023][23468] Updated weights for policy 0, policy_version 54903 (0.0007) -[2023-10-09 10:29:51,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 112754688. Throughput: 0: 1791.4, 1: 1786.4. Samples: 28191976. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:29:51,078][22500] Avg episode reward: [(0, '8.850'), (1, '8.340')] -[2023-10-09 10:29:52,486][23469] Updated weights for policy 1, policy_version 55201 (0.0007) -[2023-10-09 10:29:52,755][23468] Updated weights for policy 0, policy_version 54913 (0.0007) -[2023-10-09 10:29:52,866][23469] Updated weights for policy 1, policy_version 55211 (0.0007) -[2023-10-09 10:29:53,124][23468] Updated weights for policy 0, policy_version 54923 (0.0008) -[2023-10-09 10:29:53,234][23469] Updated weights for policy 1, policy_version 55221 (0.0008) -[2023-10-09 10:29:53,502][23468] Updated weights for policy 0, policy_version 54933 (0.0009) -[2023-10-09 10:29:53,601][23469] Updated weights for policy 1, policy_version 55231 (0.0009) -[2023-10-09 10:29:53,879][23468] Updated weights for policy 0, policy_version 54943 (0.0011) -[2023-10-09 10:29:56,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 112820224. Throughput: 0: 1767.4, 1: 1785.5. Samples: 28212524. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 10:29:56,078][22500] Avg episode reward: [(0, '8.480'), (1, '8.530')] -[2023-10-09 10:29:57,462][23469] Updated weights for policy 1, policy_version 55241 (0.0008) -[2023-10-09 10:29:57,728][23468] Updated weights for policy 0, policy_version 54953 (0.0008) -[2023-10-09 10:29:57,828][23469] Updated weights for policy 1, policy_version 55251 (0.0007) -[2023-10-09 10:29:58,099][23468] Updated weights for policy 0, policy_version 54963 (0.0008) -[2023-10-09 10:29:58,197][23469] Updated weights for policy 1, policy_version 55261 (0.0007) -[2023-10-09 10:29:58,462][23468] Updated weights for policy 0, policy_version 54973 (0.0008) -[2023-10-09 10:30:01,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 112885760. Throughput: 0: 1763.2, 1: 1793.1. Samples: 28234854. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 10:30:01,079][22500] Avg episode reward: [(0, '8.270'), (1, '8.540')] -[2023-10-09 10:30:01,831][23469] Updated weights for policy 1, policy_version 55271 (0.0008) -[2023-10-09 10:30:02,199][23469] Updated weights for policy 1, policy_version 55281 (0.0009) -[2023-10-09 10:30:02,338][23468] Updated weights for policy 0, policy_version 54983 (0.0008) -[2023-10-09 10:30:02,567][23469] Updated weights for policy 1, policy_version 55291 (0.0008) -[2023-10-09 10:30:02,722][23468] Updated weights for policy 0, policy_version 54993 (0.0008) -[2023-10-09 10:30:03,098][23468] Updated weights for policy 0, policy_version 55003 (0.0010) -[2023-10-09 10:30:06,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 112951296. Throughput: 0: 1763.2, 1: 1789.4. Samples: 28244424. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 10:30:06,078][22500] Avg episode reward: [(0, '8.340'), (1, '8.630')] -[2023-10-09 10:30:06,167][23469] Updated weights for policy 1, policy_version 55301 (0.0010) -[2023-10-09 10:30:06,541][23469] Updated weights for policy 1, policy_version 55311 (0.0010) -[2023-10-09 10:30:06,907][23468] Updated weights for policy 0, policy_version 55013 (0.0008) -[2023-10-09 10:30:06,910][23469] Updated weights for policy 1, policy_version 55321 (0.0009) -[2023-10-09 10:30:07,279][23468] Updated weights for policy 0, policy_version 55023 (0.0008) -[2023-10-09 10:30:07,644][23468] Updated weights for policy 0, policy_version 55033 (0.0009) -[2023-10-09 10:30:10,834][23469] Updated weights for policy 1, policy_version 55331 (0.0008) -[2023-10-09 10:30:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 113016832. Throughput: 0: 1753.0, 1: 1795.1. Samples: 28266556. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 10:30:11,078][22500] Avg episode reward: [(0, '8.560'), (1, '8.280')] -[2023-10-09 10:30:11,196][23469] Updated weights for policy 1, policy_version 55341 (0.0008) -[2023-10-09 10:30:11,511][23468] Updated weights for policy 0, policy_version 55043 (0.0008) -[2023-10-09 10:30:11,566][23469] Updated weights for policy 1, policy_version 55351 (0.0009) -[2023-10-09 10:30:11,883][23468] Updated weights for policy 0, policy_version 55053 (0.0008) -[2023-10-09 10:30:12,256][23468] Updated weights for policy 0, policy_version 55063 (0.0009) -[2023-10-09 10:30:15,349][23469] Updated weights for policy 1, policy_version 55361 (0.0009) -[2023-10-09 10:30:15,722][23469] Updated weights for policy 1, policy_version 55371 (0.0007) -[2023-10-09 10:30:16,076][23468] Updated weights for policy 0, policy_version 55073 (0.0007) -[2023-10-09 10:30:16,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 113082368. Throughput: 0: 1770.7, 1: 1811.4. Samples: 28288260. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 10:30:16,078][22500] Avg episode reward: [(0, '8.900'), (1, '8.650')] -[2023-10-09 10:30:16,094][23469] Updated weights for policy 1, policy_version 55381 (0.0010) -[2023-10-09 10:30:16,443][23468] Updated weights for policy 0, policy_version 55083 (0.0008) -[2023-10-09 10:30:16,455][23469] Updated weights for policy 1, policy_version 55391 (0.0007) -[2023-10-09 10:30:16,491][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000055392_56721408.pth... -[2023-10-09 10:30:16,520][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000053696_54984704.pth -[2023-10-09 10:30:16,815][23468] Updated weights for policy 0, policy_version 55093 (0.0009) -[2023-10-09 10:30:17,190][23468] Updated weights for policy 0, policy_version 55103 (0.0007) -[2023-10-09 10:30:17,223][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000055104_56426496.pth... -[2023-10-09 10:30:17,263][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000053408_54689792.pth -[2023-10-09 10:30:20,168][23469] Updated weights for policy 1, policy_version 55401 (0.0009) -[2023-10-09 10:30:20,542][23469] Updated weights for policy 1, policy_version 55411 (0.0009) -[2023-10-09 10:30:20,902][23469] Updated weights for policy 1, policy_version 55421 (0.0008) -[2023-10-09 10:30:20,934][23468] Updated weights for policy 0, policy_version 55113 (0.0009) -[2023-10-09 10:30:21,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 113180672. Throughput: 0: 1753.8, 1: 1791.1. Samples: 28298566. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 10:30:21,078][22500] Avg episode reward: [(0, '9.110'), (1, '8.100')] -[2023-10-09 10:30:21,308][23468] Updated weights for policy 0, policy_version 55123 (0.0010) -[2023-10-09 10:30:21,683][23468] Updated weights for policy 0, policy_version 55133 (0.0008) -[2023-10-09 10:30:24,753][23469] Updated weights for policy 1, policy_version 55431 (0.0008) -[2023-10-09 10:30:25,121][23469] Updated weights for policy 1, policy_version 55441 (0.0009) -[2023-10-09 10:30:25,493][23469] Updated weights for policy 1, policy_version 55451 (0.0010) -[2023-10-09 10:30:25,532][23468] Updated weights for policy 0, policy_version 55143 (0.0007) -[2023-10-09 10:30:25,896][23468] Updated weights for policy 0, policy_version 55153 (0.0008) -[2023-10-09 10:30:26,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 113246208. Throughput: 0: 1762.8, 1: 1808.8. Samples: 28320232. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 10:30:26,078][22500] Avg episode reward: [(0, '9.580'), (1, '8.380')] -[2023-10-09 10:30:26,265][23468] Updated weights for policy 0, policy_version 55163 (0.0010) -[2023-10-09 10:30:29,284][23469] Updated weights for policy 1, policy_version 55461 (0.0010) -[2023-10-09 10:30:29,655][23469] Updated weights for policy 1, policy_version 55471 (0.0007) -[2023-10-09 10:30:30,018][23469] Updated weights for policy 1, policy_version 55481 (0.0007) -[2023-10-09 10:30:30,089][23468] Updated weights for policy 0, policy_version 55173 (0.0008) -[2023-10-09 10:30:30,460][23468] Updated weights for policy 0, policy_version 55183 (0.0007) -[2023-10-09 10:30:30,837][23468] Updated weights for policy 0, policy_version 55193 (0.0009) -[2023-10-09 10:30:31,077][22500] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 14218.0). Total num frames: 113311744. Throughput: 0: 1774.6, 1: 1780.0. Samples: 28340816. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 10:30:31,078][22500] Avg episode reward: [(0, '8.580'), (1, '8.530')] -[2023-10-09 10:30:33,719][23469] Updated weights for policy 1, policy_version 55491 (0.0009) -[2023-10-09 10:30:34,085][23469] Updated weights for policy 1, policy_version 55501 (0.0008) -[2023-10-09 10:30:34,449][23469] Updated weights for policy 1, policy_version 55511 (0.0008) -[2023-10-09 10:30:34,690][23468] Updated weights for policy 0, policy_version 55203 (0.0009) -[2023-10-09 10:30:35,063][23468] Updated weights for policy 0, policy_version 55213 (0.0008) -[2023-10-09 10:30:35,435][23468] Updated weights for policy 0, policy_version 55223 (0.0008) -[2023-10-09 10:30:36,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 113410048. Throughput: 0: 1757.2, 1: 1803.1. Samples: 28352190. Policy #0 lag: (min: 31.0, avg: 32.1, max: 54.0) -[2023-10-09 10:30:36,078][22500] Avg episode reward: [(0, '8.440'), (1, '8.500')] -[2023-10-09 10:30:38,324][23469] Updated weights for policy 1, policy_version 55521 (0.0009) -[2023-10-09 10:30:38,730][23469] Updated weights for policy 1, policy_version 55531 (0.0009) -[2023-10-09 10:30:39,090][23468] Updated weights for policy 0, policy_version 55233 (0.0008) -[2023-10-09 10:30:39,102][23469] Updated weights for policy 1, policy_version 55541 (0.0009) -[2023-10-09 10:30:39,469][23468] Updated weights for policy 0, policy_version 55243 (0.0008) -[2023-10-09 10:30:39,473][23469] Updated weights for policy 1, policy_version 55551 (0.0007) -[2023-10-09 10:30:39,842][23468] Updated weights for policy 0, policy_version 55253 (0.0009) -[2023-10-09 10:30:40,218][23468] Updated weights for policy 0, policy_version 55263 (0.0007) -[2023-10-09 10:30:41,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 113475584. Throughput: 0: 1786.3, 1: 1782.3. Samples: 28373110. Policy #0 lag: (min: 31.0, avg: 32.1, max: 54.0) -[2023-10-09 10:30:41,078][22500] Avg episode reward: [(0, '8.390'), (1, '8.940')] -[2023-10-09 10:30:43,175][23469] Updated weights for policy 1, policy_version 55561 (0.0007) -[2023-10-09 10:30:43,551][23469] Updated weights for policy 1, policy_version 55571 (0.0008) -[2023-10-09 10:30:43,919][23469] Updated weights for policy 1, policy_version 55581 (0.0007) -[2023-10-09 10:30:44,010][23468] Updated weights for policy 0, policy_version 55273 (0.0009) -[2023-10-09 10:30:44,383][23468] Updated weights for policy 0, policy_version 55283 (0.0007) -[2023-10-09 10:30:44,776][23468] Updated weights for policy 0, policy_version 55293 (0.0010) -[2023-10-09 10:30:46,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 113541120. Throughput: 0: 1760.9, 1: 1782.1. Samples: 28394290. Policy #0 lag: (min: 31.0, avg: 32.1, max: 54.0) -[2023-10-09 10:30:46,079][22500] Avg episode reward: [(0, '8.580'), (1, '8.740')] -[2023-10-09 10:30:47,453][23469] Updated weights for policy 1, policy_version 55591 (0.0008) -[2023-10-09 10:30:47,819][23469] Updated weights for policy 1, policy_version 55601 (0.0009) -[2023-10-09 10:30:48,195][23469] Updated weights for policy 1, policy_version 55611 (0.0010) -[2023-10-09 10:30:48,477][23468] Updated weights for policy 0, policy_version 55303 (0.0008) -[2023-10-09 10:30:48,851][23468] Updated weights for policy 0, policy_version 55313 (0.0008) -[2023-10-09 10:30:49,226][23468] Updated weights for policy 0, policy_version 55323 (0.0008) -[2023-10-09 10:30:51,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 113606656. Throughput: 0: 1796.3, 1: 1786.3. Samples: 28405642. Policy #0 lag: (min: 31.0, avg: 32.1, max: 54.0) -[2023-10-09 10:30:51,078][22500] Avg episode reward: [(0, '9.110'), (1, '8.940')] -[2023-10-09 10:30:51,946][23469] Updated weights for policy 1, policy_version 55621 (0.0009) -[2023-10-09 10:30:52,316][23469] Updated weights for policy 1, policy_version 55631 (0.0007) -[2023-10-09 10:30:52,687][23469] Updated weights for policy 1, policy_version 55641 (0.0010) -[2023-10-09 10:30:52,879][23468] Updated weights for policy 0, policy_version 55333 (0.0007) -[2023-10-09 10:30:53,255][23468] Updated weights for policy 0, policy_version 55343 (0.0007) -[2023-10-09 10:30:53,635][23468] Updated weights for policy 0, policy_version 55353 (0.0008) -[2023-10-09 10:30:56,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 113672192. Throughput: 0: 1774.8, 1: 1781.4. Samples: 28426586. Policy #0 lag: (min: 31.0, avg: 32.1, max: 54.0) -[2023-10-09 10:30:56,078][22500] Avg episode reward: [(0, '8.710'), (1, '9.020')] -[2023-10-09 10:30:56,526][23469] Updated weights for policy 1, policy_version 55651 (0.0008) -[2023-10-09 10:30:56,890][23469] Updated weights for policy 1, policy_version 55661 (0.0009) -[2023-10-09 10:30:57,253][23469] Updated weights for policy 1, policy_version 55671 (0.0007) -[2023-10-09 10:30:57,451][23468] Updated weights for policy 0, policy_version 55363 (0.0008) -[2023-10-09 10:30:57,824][23468] Updated weights for policy 0, policy_version 55373 (0.0007) -[2023-10-09 10:30:58,191][23468] Updated weights for policy 0, policy_version 55383 (0.0008) -[2023-10-09 10:31:00,893][23469] Updated weights for policy 1, policy_version 55681 (0.0007) -[2023-10-09 10:31:01,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 113737728. Throughput: 0: 1778.4, 1: 1793.3. Samples: 28448990. Policy #0 lag: (min: 31.0, avg: 32.1, max: 54.0) -[2023-10-09 10:31:01,079][22500] Avg episode reward: [(0, '9.070'), (1, '8.660')] -[2023-10-09 10:31:01,255][23469] Updated weights for policy 1, policy_version 55691 (0.0007) -[2023-10-09 10:31:01,614][23469] Updated weights for policy 1, policy_version 55701 (0.0007) -[2023-10-09 10:31:01,950][23468] Updated weights for policy 0, policy_version 55393 (0.0009) -[2023-10-09 10:31:01,983][23469] Updated weights for policy 1, policy_version 55711 (0.0008) -[2023-10-09 10:31:02,326][23468] Updated weights for policy 0, policy_version 55403 (0.0008) -[2023-10-09 10:31:02,710][23468] Updated weights for policy 0, policy_version 55413 (0.0008) -[2023-10-09 10:31:03,085][23468] Updated weights for policy 0, policy_version 55423 (0.0008) -[2023-10-09 10:31:05,854][23469] Updated weights for policy 1, policy_version 55721 (0.0010) -[2023-10-09 10:31:06,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 113803264. Throughput: 0: 1774.6, 1: 1780.6. Samples: 28458550. Policy #0 lag: (min: 31.0, avg: 32.1, max: 54.0) -[2023-10-09 10:31:06,078][22500] Avg episode reward: [(0, '8.950'), (1, '9.070')] -[2023-10-09 10:31:06,219][23469] Updated weights for policy 1, policy_version 55731 (0.0011) -[2023-10-09 10:31:06,586][23469] Updated weights for policy 1, policy_version 55741 (0.0010) -[2023-10-09 10:31:06,873][23468] Updated weights for policy 0, policy_version 55433 (0.0009) -[2023-10-09 10:31:07,244][23468] Updated weights for policy 0, policy_version 55443 (0.0008) -[2023-10-09 10:31:07,617][23468] Updated weights for policy 0, policy_version 55453 (0.0007) -[2023-10-09 10:31:10,155][23469] Updated weights for policy 1, policy_version 55751 (0.0007) -[2023-10-09 10:31:10,529][23469] Updated weights for policy 1, policy_version 55761 (0.0009) -[2023-10-09 10:31:10,895][23469] Updated weights for policy 1, policy_version 55771 (0.0008) -[2023-10-09 10:31:11,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 113868800. Throughput: 0: 1781.2, 1: 1794.2. Samples: 28481124. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:31:11,078][22500] Avg episode reward: [(0, '8.610'), (1, '8.910')] -[2023-10-09 10:31:11,396][23468] Updated weights for policy 0, policy_version 55463 (0.0009) -[2023-10-09 10:31:11,766][23468] Updated weights for policy 0, policy_version 55473 (0.0010) -[2023-10-09 10:31:12,145][23468] Updated weights for policy 0, policy_version 55483 (0.0007) -[2023-10-09 10:31:14,713][23469] Updated weights for policy 1, policy_version 55781 (0.0007) -[2023-10-09 10:31:15,075][23469] Updated weights for policy 1, policy_version 55791 (0.0008) -[2023-10-09 10:31:15,449][23469] Updated weights for policy 1, policy_version 55801 (0.0010) -[2023-10-09 10:31:15,969][23468] Updated weights for policy 0, policy_version 55493 (0.0009) -[2023-10-09 10:31:16,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 113967104. Throughput: 0: 1793.0, 1: 1794.2. Samples: 28502238. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:31:16,078][22500] Avg episode reward: [(0, '8.730'), (1, '8.880')] -[2023-10-09 10:31:16,345][23468] Updated weights for policy 0, policy_version 55503 (0.0008) -[2023-10-09 10:31:16,716][23468] Updated weights for policy 0, policy_version 55513 (0.0009) -[2023-10-09 10:31:19,180][23469] Updated weights for policy 1, policy_version 55811 (0.0010) -[2023-10-09 10:31:19,547][23469] Updated weights for policy 1, policy_version 55821 (0.0009) -[2023-10-09 10:31:19,918][23469] Updated weights for policy 1, policy_version 55831 (0.0009) -[2023-10-09 10:31:20,335][23468] Updated weights for policy 0, policy_version 55523 (0.0009) -[2023-10-09 10:31:20,706][23468] Updated weights for policy 0, policy_version 55533 (0.0007) -[2023-10-09 10:31:21,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 114032640. Throughput: 0: 1783.9, 1: 1799.7. Samples: 28513450. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:31:21,079][22500] Avg episode reward: [(0, '9.220'), (1, '8.920')] -[2023-10-09 10:31:21,081][23468] Updated weights for policy 0, policy_version 55543 (0.0010) -[2023-10-09 10:31:23,918][23469] Updated weights for policy 1, policy_version 55841 (0.0009) -[2023-10-09 10:31:24,355][23469] Updated weights for policy 1, policy_version 55851 (0.0007) -[2023-10-09 10:31:24,738][23469] Updated weights for policy 1, policy_version 55861 (0.0007) -[2023-10-09 10:31:24,780][23468] Updated weights for policy 0, policy_version 55553 (0.0008) -[2023-10-09 10:31:25,106][23469] Updated weights for policy 1, policy_version 55871 (0.0008) -[2023-10-09 10:31:25,153][23468] Updated weights for policy 0, policy_version 55563 (0.0009) -[2023-10-09 10:31:25,523][23468] Updated weights for policy 0, policy_version 55573 (0.0008) -[2023-10-09 10:31:25,893][23468] Updated weights for policy 0, policy_version 55583 (0.0009) -[2023-10-09 10:31:26,078][22500] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 114130944. Throughput: 0: 1789.7, 1: 1801.1. Samples: 28534694. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:31:26,079][22500] Avg episode reward: [(0, '9.560'), (1, '8.670')] -[2023-10-09 10:31:28,767][23469] Updated weights for policy 1, policy_version 55881 (0.0009) -[2023-10-09 10:31:29,135][23469] Updated weights for policy 1, policy_version 55891 (0.0007) -[2023-10-09 10:31:29,502][23469] Updated weights for policy 1, policy_version 55901 (0.0007) -[2023-10-09 10:31:29,672][23468] Updated weights for policy 0, policy_version 55593 (0.0008) -[2023-10-09 10:31:30,050][23468] Updated weights for policy 0, policy_version 55603 (0.0010) -[2023-10-09 10:31:30,430][23468] Updated weights for policy 0, policy_version 55613 (0.0010) -[2023-10-09 10:31:31,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 114196480. Throughput: 0: 1793.5, 1: 1783.0. Samples: 28555232. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:31:31,078][22500] Avg episode reward: [(0, '9.220'), (1, '8.590')] -[2023-10-09 10:31:33,387][23469] Updated weights for policy 1, policy_version 55911 (0.0008) -[2023-10-09 10:31:33,770][23469] Updated weights for policy 1, policy_version 55921 (0.0008) -[2023-10-09 10:31:34,134][23469] Updated weights for policy 1, policy_version 55931 (0.0008) -[2023-10-09 10:31:34,274][23468] Updated weights for policy 0, policy_version 55623 (0.0008) -[2023-10-09 10:31:34,658][23468] Updated weights for policy 0, policy_version 55633 (0.0008) -[2023-10-09 10:31:35,023][23468] Updated weights for policy 0, policy_version 55643 (0.0009) -[2023-10-09 10:31:36,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 114262016. Throughput: 0: 1781.7, 1: 1791.8. Samples: 28566450. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:31:36,078][22500] Avg episode reward: [(0, '8.920'), (1, '8.920')] -[2023-10-09 10:31:37,910][23469] Updated weights for policy 1, policy_version 55941 (0.0007) -[2023-10-09 10:31:38,277][23469] Updated weights for policy 1, policy_version 55951 (0.0008) -[2023-10-09 10:31:38,642][23469] Updated weights for policy 1, policy_version 55961 (0.0008) -[2023-10-09 10:31:38,784][23468] Updated weights for policy 0, policy_version 55653 (0.0008) -[2023-10-09 10:31:39,161][23468] Updated weights for policy 0, policy_version 55663 (0.0007) -[2023-10-09 10:31:39,540][23468] Updated weights for policy 0, policy_version 55673 (0.0009) -[2023-10-09 10:31:41,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 114327552. Throughput: 0: 1796.1, 1: 1776.6. Samples: 28587360. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:31:41,078][22500] Avg episode reward: [(0, '9.020'), (1, '8.720')] -[2023-10-09 10:31:42,409][23469] Updated weights for policy 1, policy_version 55971 (0.0008) -[2023-10-09 10:31:42,778][23469] Updated weights for policy 1, policy_version 55981 (0.0008) -[2023-10-09 10:31:43,147][23469] Updated weights for policy 1, policy_version 55991 (0.0007) -[2023-10-09 10:31:43,383][23468] Updated weights for policy 0, policy_version 55683 (0.0009) -[2023-10-09 10:31:43,755][23468] Updated weights for policy 0, policy_version 55693 (0.0009) -[2023-10-09 10:31:44,129][23468] Updated weights for policy 0, policy_version 55703 (0.0010) -[2023-10-09 10:31:46,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 114393088. Throughput: 0: 1775.3, 1: 1775.2. Samples: 28608764. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:31:46,078][22500] Avg episode reward: [(0, '8.690'), (1, '8.980')] -[2023-10-09 10:31:46,987][23469] Updated weights for policy 1, policy_version 56001 (0.0007) -[2023-10-09 10:31:47,360][23469] Updated weights for policy 1, policy_version 56011 (0.0007) -[2023-10-09 10:31:47,720][23469] Updated weights for policy 1, policy_version 56021 (0.0008) -[2023-10-09 10:31:47,782][23468] Updated weights for policy 0, policy_version 55713 (0.0008) -[2023-10-09 10:31:48,092][23469] Updated weights for policy 1, policy_version 56031 (0.0009) -[2023-10-09 10:31:48,157][23468] Updated weights for policy 0, policy_version 55723 (0.0010) -[2023-10-09 10:31:48,534][23468] Updated weights for policy 0, policy_version 55733 (0.0008) -[2023-10-09 10:31:48,910][23468] Updated weights for policy 0, policy_version 55743 (0.0008) -[2023-10-09 10:31:51,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 114458624. Throughput: 0: 1800.4, 1: 1772.3. Samples: 28619320. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:31:51,078][22500] Avg episode reward: [(0, '9.800'), (1, '8.910')] -[2023-10-09 10:31:51,881][23469] Updated weights for policy 1, policy_version 56041 (0.0010) -[2023-10-09 10:31:52,256][23469] Updated weights for policy 1, policy_version 56051 (0.0009) -[2023-10-09 10:31:52,628][23469] Updated weights for policy 1, policy_version 56061 (0.0010) -[2023-10-09 10:31:52,628][23468] Updated weights for policy 0, policy_version 55753 (0.0008) -[2023-10-09 10:31:52,996][23468] Updated weights for policy 0, policy_version 55763 (0.0008) -[2023-10-09 10:31:53,372][23468] Updated weights for policy 0, policy_version 55773 (0.0008) -[2023-10-09 10:31:56,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 114524160. Throughput: 0: 1781.8, 1: 1768.4. Samples: 28640880. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:31:56,078][22500] Avg episode reward: [(0, '9.510'), (1, '8.640')] -[2023-10-09 10:31:56,462][23469] Updated weights for policy 1, policy_version 56071 (0.0008) -[2023-10-09 10:31:56,830][23469] Updated weights for policy 1, policy_version 56081 (0.0007) -[2023-10-09 10:31:57,072][23468] Updated weights for policy 0, policy_version 55783 (0.0008) -[2023-10-09 10:31:57,198][23469] Updated weights for policy 1, policy_version 56091 (0.0007) -[2023-10-09 10:31:57,434][23468] Updated weights for policy 0, policy_version 55793 (0.0007) -[2023-10-09 10:31:57,810][23468] Updated weights for policy 0, policy_version 55803 (0.0010) -[2023-10-09 10:32:01,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.6, 300 sec: 14218.0). Total num frames: 114589696. Throughput: 0: 1782.8, 1: 1796.0. Samples: 28663284. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:32:01,078][22500] Avg episode reward: [(0, '9.690'), (1, '8.890')] -[2023-10-09 10:32:01,160][23469] Updated weights for policy 1, policy_version 56101 (0.0010) -[2023-10-09 10:32:01,531][23469] Updated weights for policy 1, policy_version 56111 (0.0009) -[2023-10-09 10:32:01,647][23468] Updated weights for policy 0, policy_version 55813 (0.0010) -[2023-10-09 10:32:01,901][23469] Updated weights for policy 1, policy_version 56121 (0.0007) -[2023-10-09 10:32:02,013][23468] Updated weights for policy 0, policy_version 55823 (0.0008) -[2023-10-09 10:32:02,389][23468] Updated weights for policy 0, policy_version 55833 (0.0009) -[2023-10-09 10:32:05,569][23469] Updated weights for policy 1, policy_version 56131 (0.0009) -[2023-10-09 10:32:05,945][23469] Updated weights for policy 1, policy_version 56141 (0.0009) -[2023-10-09 10:32:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 114655232. Throughput: 0: 1779.7, 1: 1761.9. Samples: 28672820. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:32:06,081][22500] Avg episode reward: [(0, '9.360'), (1, '8.590')] -[2023-10-09 10:32:06,275][23468] Updated weights for policy 0, policy_version 55843 (0.0010) -[2023-10-09 10:32:06,323][23469] Updated weights for policy 1, policy_version 56151 (0.0009) -[2023-10-09 10:32:06,651][23468] Updated weights for policy 0, policy_version 55853 (0.0008) -[2023-10-09 10:32:07,021][23468] Updated weights for policy 0, policy_version 55863 (0.0009) -[2023-10-09 10:32:10,085][23469] Updated weights for policy 1, policy_version 56161 (0.0008) -[2023-10-09 10:32:10,477][23469] Updated weights for policy 1, policy_version 56171 (0.0008) -[2023-10-09 10:32:10,837][23469] Updated weights for policy 1, policy_version 56181 (0.0011) -[2023-10-09 10:32:10,868][23468] Updated weights for policy 0, policy_version 55873 (0.0008) -[2023-10-09 10:32:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 114720768. Throughput: 0: 1771.9, 1: 1793.6. Samples: 28695138. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:32:11,078][22500] Avg episode reward: [(0, '9.210'), (1, '8.370')] -[2023-10-09 10:32:11,202][23469] Updated weights for policy 1, policy_version 56191 (0.0008) -[2023-10-09 10:32:11,244][23468] Updated weights for policy 0, policy_version 55883 (0.0009) -[2023-10-09 10:32:11,611][23468] Updated weights for policy 0, policy_version 55893 (0.0009) -[2023-10-09 10:32:11,980][23468] Updated weights for policy 0, policy_version 55903 (0.0009) -[2023-10-09 10:32:14,985][23469] Updated weights for policy 1, policy_version 56201 (0.0007) -[2023-10-09 10:32:15,354][23469] Updated weights for policy 1, policy_version 56211 (0.0008) -[2023-10-09 10:32:15,726][23469] Updated weights for policy 1, policy_version 56221 (0.0008) -[2023-10-09 10:32:15,738][23468] Updated weights for policy 0, policy_version 55913 (0.0008) -[2023-10-09 10:32:16,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 114819072. Throughput: 0: 1801.7, 1: 1776.0. Samples: 28716228. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:32:16,078][22500] Avg episode reward: [(0, '8.270'), (1, '8.730')] -[2023-10-09 10:32:16,089][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000056224_57573376.pth... -[2023-10-09 10:32:16,108][23468] Updated weights for policy 0, policy_version 55923 (0.0009) -[2023-10-09 10:32:16,124][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000054560_55869440.pth -[2023-10-09 10:32:16,472][23468] Updated weights for policy 0, policy_version 55933 (0.0009) -[2023-10-09 10:32:16,585][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000055936_57278464.pth... -[2023-10-09 10:32:16,622][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000054272_55574528.pth -[2023-10-09 10:32:19,335][23469] Updated weights for policy 1, policy_version 56231 (0.0009) -[2023-10-09 10:32:19,709][23469] Updated weights for policy 1, policy_version 56241 (0.0007) -[2023-10-09 10:32:20,082][23469] Updated weights for policy 1, policy_version 56251 (0.0008) -[2023-10-09 10:32:20,289][23468] Updated weights for policy 0, policy_version 55943 (0.0010) -[2023-10-09 10:32:20,664][23468] Updated weights for policy 0, policy_version 55953 (0.0009) -[2023-10-09 10:32:21,043][23468] Updated weights for policy 0, policy_version 55963 (0.0009) -[2023-10-09 10:32:21,077][22500] Fps is (10 sec: 16383.5, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 114884608. Throughput: 0: 1775.3, 1: 1801.3. Samples: 28727398. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:32:21,078][22500] Avg episode reward: [(0, '8.060'), (1, '8.700')] -[2023-10-09 10:32:23,515][23469] Updated weights for policy 1, policy_version 56261 (0.0008) -[2023-10-09 10:32:23,884][23469] Updated weights for policy 1, policy_version 56271 (0.0008) -[2023-10-09 10:32:24,262][23469] Updated weights for policy 1, policy_version 56281 (0.0008) -[2023-10-09 10:32:24,857][23468] Updated weights for policy 0, policy_version 55973 (0.0008) -[2023-10-09 10:32:25,232][23468] Updated weights for policy 0, policy_version 55983 (0.0007) -[2023-10-09 10:32:25,605][23468] Updated weights for policy 0, policy_version 55993 (0.0008) -[2023-10-09 10:32:26,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 114982912. Throughput: 0: 1790.5, 1: 1791.0. Samples: 28748526. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 10:32:26,078][22500] Avg episode reward: [(0, '7.960'), (1, '8.600')] -[2023-10-09 10:32:27,882][23469] Updated weights for policy 1, policy_version 56291 (0.0010) -[2023-10-09 10:32:28,253][23469] Updated weights for policy 1, policy_version 56301 (0.0008) -[2023-10-09 10:32:28,614][23469] Updated weights for policy 1, policy_version 56311 (0.0008) -[2023-10-09 10:32:29,304][23468] Updated weights for policy 0, policy_version 56003 (0.0009) -[2023-10-09 10:32:29,681][23468] Updated weights for policy 0, policy_version 56013 (0.0007) -[2023-10-09 10:32:30,060][23468] Updated weights for policy 0, policy_version 56023 (0.0007) -[2023-10-09 10:32:31,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 115048448. Throughput: 0: 1782.4, 1: 1799.7. Samples: 28769954. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 10:32:31,078][22500] Avg episode reward: [(0, '8.530'), (1, '8.260')] -[2023-10-09 10:32:32,389][23469] Updated weights for policy 1, policy_version 56321 (0.0008) -[2023-10-09 10:32:32,761][23469] Updated weights for policy 1, policy_version 56331 (0.0007) -[2023-10-09 10:32:33,126][23469] Updated weights for policy 1, policy_version 56341 (0.0009) -[2023-10-09 10:32:33,494][23469] Updated weights for policy 1, policy_version 56351 (0.0007) -[2023-10-09 10:32:33,696][23468] Updated weights for policy 0, policy_version 56033 (0.0008) -[2023-10-09 10:32:34,070][23468] Updated weights for policy 0, policy_version 56043 (0.0009) -[2023-10-09 10:32:34,446][23468] Updated weights for policy 0, policy_version 56053 (0.0007) -[2023-10-09 10:32:34,810][23468] Updated weights for policy 0, policy_version 56063 (0.0007) -[2023-10-09 10:32:36,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 115113984. Throughput: 0: 1793.8, 1: 1800.7. Samples: 28781076. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 10:32:36,078][22500] Avg episode reward: [(0, '8.960'), (1, '8.830')] -[2023-10-09 10:32:37,216][23469] Updated weights for policy 1, policy_version 56361 (0.0009) -[2023-10-09 10:32:37,574][23469] Updated weights for policy 1, policy_version 56371 (0.0009) -[2023-10-09 10:32:37,945][23469] Updated weights for policy 1, policy_version 56381 (0.0008) -[2023-10-09 10:32:38,668][23468] Updated weights for policy 0, policy_version 56073 (0.0007) -[2023-10-09 10:32:39,051][23468] Updated weights for policy 0, policy_version 56083 (0.0010) -[2023-10-09 10:32:39,424][23468] Updated weights for policy 0, policy_version 56093 (0.0010) -[2023-10-09 10:32:41,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 115179520. Throughput: 0: 1783.5, 1: 1805.9. Samples: 28802402. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 10:32:41,078][22500] Avg episode reward: [(0, '9.400'), (1, '8.760')] -[2023-10-09 10:32:41,601][23469] Updated weights for policy 1, policy_version 56391 (0.0009) -[2023-10-09 10:32:41,982][23469] Updated weights for policy 1, policy_version 56401 (0.0010) -[2023-10-09 10:32:42,348][23469] Updated weights for policy 1, policy_version 56411 (0.0007) -[2023-10-09 10:32:43,148][23468] Updated weights for policy 0, policy_version 56103 (0.0010) -[2023-10-09 10:32:43,513][23468] Updated weights for policy 0, policy_version 56113 (0.0008) -[2023-10-09 10:32:43,891][23468] Updated weights for policy 0, policy_version 56123 (0.0010) -[2023-10-09 10:32:46,057][23469] Updated weights for policy 1, policy_version 56421 (0.0007) -[2023-10-09 10:32:46,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 115245056. Throughput: 0: 1774.4, 1: 1807.5. Samples: 28824466. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 10:32:46,078][22500] Avg episode reward: [(0, '8.880'), (1, '8.700')] -[2023-10-09 10:32:46,423][23469] Updated weights for policy 1, policy_version 56431 (0.0007) -[2023-10-09 10:32:46,794][23469] Updated weights for policy 1, policy_version 56441 (0.0007) -[2023-10-09 10:32:47,521][23468] Updated weights for policy 0, policy_version 56133 (0.0007) -[2023-10-09 10:32:47,892][23468] Updated weights for policy 0, policy_version 56143 (0.0009) -[2023-10-09 10:32:48,260][23468] Updated weights for policy 0, policy_version 56153 (0.0010) -[2023-10-09 10:32:50,576][23469] Updated weights for policy 1, policy_version 56451 (0.0009) -[2023-10-09 10:32:50,952][23469] Updated weights for policy 1, policy_version 56461 (0.0010) -[2023-10-09 10:32:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 115310592. Throughput: 0: 1790.4, 1: 1805.2. Samples: 28834622. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 10:32:51,078][22500] Avg episode reward: [(0, '8.330'), (1, '8.050')] -[2023-10-09 10:32:51,324][23469] Updated weights for policy 1, policy_version 56471 (0.0010) -[2023-10-09 10:32:52,148][23468] Updated weights for policy 0, policy_version 56163 (0.0010) -[2023-10-09 10:32:52,526][23468] Updated weights for policy 0, policy_version 56173 (0.0008) -[2023-10-09 10:32:52,890][23468] Updated weights for policy 0, policy_version 56183 (0.0007) -[2023-10-09 10:32:55,089][23469] Updated weights for policy 1, policy_version 56481 (0.0010) -[2023-10-09 10:32:55,502][23469] Updated weights for policy 1, policy_version 56491 (0.0009) -[2023-10-09 10:32:55,867][23469] Updated weights for policy 1, policy_version 56501 (0.0008) -[2023-10-09 10:32:56,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 115376128. Throughput: 0: 1788.1, 1: 1804.0. Samples: 28856786. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 10:32:56,078][22500] Avg episode reward: [(0, '8.170'), (1, '8.020')] -[2023-10-09 10:32:56,240][23469] Updated weights for policy 1, policy_version 56511 (0.0007) -[2023-10-09 10:32:56,671][23468] Updated weights for policy 0, policy_version 56193 (0.0008) -[2023-10-09 10:32:57,053][23468] Updated weights for policy 0, policy_version 56203 (0.0007) -[2023-10-09 10:32:57,430][23468] Updated weights for policy 0, policy_version 56213 (0.0007) -[2023-10-09 10:32:57,808][23468] Updated weights for policy 0, policy_version 56223 (0.0008) -[2023-10-09 10:32:59,987][23469] Updated weights for policy 1, policy_version 56521 (0.0010) -[2023-10-09 10:33:00,351][23469] Updated weights for policy 1, policy_version 56531 (0.0010) -[2023-10-09 10:33:00,713][23469] Updated weights for policy 1, policy_version 56541 (0.0008) -[2023-10-09 10:33:01,078][22500] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 115474432. Throughput: 0: 1788.5, 1: 1806.8. Samples: 28878016. Policy #0 lag: (min: 31.0, avg: 43.1, max: 63.0) -[2023-10-09 10:33:01,079][22500] Avg episode reward: [(0, '8.830'), (1, '8.500')] -[2023-10-09 10:33:01,444][23468] Updated weights for policy 0, policy_version 56233 (0.0008) -[2023-10-09 10:33:01,819][23468] Updated weights for policy 0, policy_version 56243 (0.0008) -[2023-10-09 10:33:02,200][23468] Updated weights for policy 0, policy_version 56253 (0.0007) -[2023-10-09 10:33:04,464][23469] Updated weights for policy 1, policy_version 56551 (0.0008) -[2023-10-09 10:33:04,834][23469] Updated weights for policy 1, policy_version 56561 (0.0008) -[2023-10-09 10:33:05,202][23469] Updated weights for policy 1, policy_version 56571 (0.0008) -[2023-10-09 10:33:05,911][23468] Updated weights for policy 0, policy_version 56263 (0.0008) -[2023-10-09 10:33:06,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 115539968. Throughput: 0: 1793.7, 1: 1800.9. Samples: 28889154. Policy #0 lag: (min: 31.0, avg: 43.1, max: 63.0) -[2023-10-09 10:33:06,078][22500] Avg episode reward: [(0, '9.320'), (1, '8.270')] -[2023-10-09 10:33:06,290][23468] Updated weights for policy 0, policy_version 56273 (0.0007) -[2023-10-09 10:33:06,649][23468] Updated weights for policy 0, policy_version 56283 (0.0008) -[2023-10-09 10:33:08,897][23469] Updated weights for policy 1, policy_version 56581 (0.0010) -[2023-10-09 10:33:09,262][23469] Updated weights for policy 1, policy_version 56591 (0.0010) -[2023-10-09 10:33:09,636][23469] Updated weights for policy 1, policy_version 56601 (0.0010) -[2023-10-09 10:33:10,158][23468] Updated weights for policy 0, policy_version 56293 (0.0008) -[2023-10-09 10:33:10,526][23468] Updated weights for policy 0, policy_version 56303 (0.0009) -[2023-10-09 10:33:10,899][23468] Updated weights for policy 0, policy_version 56313 (0.0010) -[2023-10-09 10:33:11,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 115605504. Throughput: 0: 1799.5, 1: 1801.5. Samples: 28910570. Policy #0 lag: (min: 31.0, avg: 43.1, max: 63.0) -[2023-10-09 10:33:11,078][22500] Avg episode reward: [(0, '9.260'), (1, '8.660')] -[2023-10-09 10:33:13,485][23469] Updated weights for policy 1, policy_version 56611 (0.0009) -[2023-10-09 10:33:13,850][23469] Updated weights for policy 1, policy_version 56621 (0.0009) -[2023-10-09 10:33:14,229][23469] Updated weights for policy 1, policy_version 56631 (0.0009) -[2023-10-09 10:33:14,734][23468] Updated weights for policy 0, policy_version 56323 (0.0009) -[2023-10-09 10:33:15,108][23468] Updated weights for policy 0, policy_version 56333 (0.0007) -[2023-10-09 10:33:15,476][23468] Updated weights for policy 0, policy_version 56343 (0.0010) -[2023-10-09 10:33:16,078][22500] Fps is (10 sec: 16383.5, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 115703808. Throughput: 0: 1809.5, 1: 1791.3. Samples: 28931990. Policy #0 lag: (min: 31.0, avg: 43.1, max: 63.0) -[2023-10-09 10:33:16,079][22500] Avg episode reward: [(0, '8.910'), (1, '8.550')] -[2023-10-09 10:33:17,775][23469] Updated weights for policy 1, policy_version 56641 (0.0007) -[2023-10-09 10:33:18,138][23469] Updated weights for policy 1, policy_version 56651 (0.0008) -[2023-10-09 10:33:18,514][23469] Updated weights for policy 1, policy_version 56661 (0.0007) -[2023-10-09 10:33:18,886][23469] Updated weights for policy 1, policy_version 56671 (0.0008) -[2023-10-09 10:33:19,191][23468] Updated weights for policy 0, policy_version 56353 (0.0009) -[2023-10-09 10:33:19,572][23468] Updated weights for policy 0, policy_version 56363 (0.0007) -[2023-10-09 10:33:19,950][23468] Updated weights for policy 0, policy_version 56373 (0.0008) -[2023-10-09 10:33:20,327][23468] Updated weights for policy 0, policy_version 56383 (0.0010) -[2023-10-09 10:33:21,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14745.7, 300 sec: 14440.2). Total num frames: 115769344. Throughput: 0: 1796.7, 1: 1801.3. Samples: 28942984. Policy #0 lag: (min: 31.0, avg: 43.1, max: 63.0) -[2023-10-09 10:33:21,078][22500] Avg episode reward: [(0, '9.630'), (1, '8.740')] -[2023-10-09 10:33:22,650][23469] Updated weights for policy 1, policy_version 56681 (0.0007) -[2023-10-09 10:33:23,017][23469] Updated weights for policy 1, policy_version 56691 (0.0008) -[2023-10-09 10:33:23,401][23469] Updated weights for policy 1, policy_version 56701 (0.0008) -[2023-10-09 10:33:24,077][23468] Updated weights for policy 0, policy_version 56393 (0.0010) -[2023-10-09 10:33:24,458][23468] Updated weights for policy 0, policy_version 56403 (0.0010) -[2023-10-09 10:33:24,838][23468] Updated weights for policy 0, policy_version 56413 (0.0008) -[2023-10-09 10:33:26,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 115834880. Throughput: 0: 1810.0, 1: 1791.9. Samples: 28964488. Policy #0 lag: (min: 31.0, avg: 43.1, max: 63.0) -[2023-10-09 10:33:26,078][22500] Avg episode reward: [(0, '9.560'), (1, '8.480')] -[2023-10-09 10:33:27,178][23469] Updated weights for policy 1, policy_version 56711 (0.0008) -[2023-10-09 10:33:27,555][23469] Updated weights for policy 1, policy_version 56721 (0.0008) -[2023-10-09 10:33:27,915][23469] Updated weights for policy 1, policy_version 56731 (0.0008) -[2023-10-09 10:33:28,524][23468] Updated weights for policy 0, policy_version 56423 (0.0008) -[2023-10-09 10:33:28,897][23468] Updated weights for policy 0, policy_version 56433 (0.0007) -[2023-10-09 10:33:29,270][23468] Updated weights for policy 0, policy_version 56443 (0.0007) -[2023-10-09 10:33:31,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 115900416. Throughput: 0: 1801.2, 1: 1795.5. Samples: 28986320. Policy #0 lag: (min: 31.0, avg: 43.1, max: 63.0) -[2023-10-09 10:33:31,078][22500] Avg episode reward: [(0, '9.780'), (1, '8.160')] -[2023-10-09 10:33:31,614][23469] Updated weights for policy 1, policy_version 56741 (0.0008) -[2023-10-09 10:33:32,001][23469] Updated weights for policy 1, policy_version 56751 (0.0009) -[2023-10-09 10:33:32,371][23469] Updated weights for policy 1, policy_version 56761 (0.0009) -[2023-10-09 10:33:33,061][23468] Updated weights for policy 0, policy_version 56453 (0.0007) -[2023-10-09 10:33:33,425][23468] Updated weights for policy 0, policy_version 56463 (0.0007) -[2023-10-09 10:33:33,795][23468] Updated weights for policy 0, policy_version 56473 (0.0010) -[2023-10-09 10:33:36,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 115965952. Throughput: 0: 1811.6, 1: 1798.8. Samples: 28997092. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:33:36,078][22500] Avg episode reward: [(0, '9.740'), (1, '8.070')] -[2023-10-09 10:33:36,190][23469] Updated weights for policy 1, policy_version 56771 (0.0009) -[2023-10-09 10:33:36,560][23469] Updated weights for policy 1, policy_version 56781 (0.0007) -[2023-10-09 10:33:36,929][23469] Updated weights for policy 1, policy_version 56791 (0.0007) -[2023-10-09 10:33:37,600][23468] Updated weights for policy 0, policy_version 56483 (0.0009) -[2023-10-09 10:33:37,977][23468] Updated weights for policy 0, policy_version 56493 (0.0009) -[2023-10-09 10:33:38,339][23468] Updated weights for policy 0, policy_version 56503 (0.0008) -[2023-10-09 10:33:40,776][23469] Updated weights for policy 1, policy_version 56801 (0.0007) -[2023-10-09 10:33:41,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 116031488. Throughput: 0: 1795.6, 1: 1796.2. Samples: 29018416. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:33:41,079][22500] Avg episode reward: [(0, '9.300'), (1, '8.160')] -[2023-10-09 10:33:41,197][23469] Updated weights for policy 1, policy_version 56811 (0.0008) -[2023-10-09 10:33:41,574][23469] Updated weights for policy 1, policy_version 56821 (0.0008) -[2023-10-09 10:33:41,945][23469] Updated weights for policy 1, policy_version 56831 (0.0010) -[2023-10-09 10:33:42,032][23468] Updated weights for policy 0, policy_version 56513 (0.0007) -[2023-10-09 10:33:42,408][23468] Updated weights for policy 0, policy_version 56523 (0.0010) -[2023-10-09 10:33:42,785][23468] Updated weights for policy 0, policy_version 56533 (0.0008) -[2023-10-09 10:33:43,152][23468] Updated weights for policy 0, policy_version 56543 (0.0007) -[2023-10-09 10:33:45,443][23469] Updated weights for policy 1, policy_version 56841 (0.0009) -[2023-10-09 10:33:45,811][23469] Updated weights for policy 1, policy_version 56851 (0.0010) -[2023-10-09 10:33:46,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 116097024. Throughput: 0: 1793.1, 1: 1806.9. Samples: 29040016. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:33:46,078][22500] Avg episode reward: [(0, '9.020'), (1, '8.210')] -[2023-10-09 10:33:46,176][23469] Updated weights for policy 1, policy_version 56861 (0.0007) -[2023-10-09 10:33:46,985][23468] Updated weights for policy 0, policy_version 56553 (0.0010) -[2023-10-09 10:33:47,370][23468] Updated weights for policy 0, policy_version 56563 (0.0009) -[2023-10-09 10:33:47,746][23468] Updated weights for policy 0, policy_version 56573 (0.0009) -[2023-10-09 10:33:49,994][23469] Updated weights for policy 1, policy_version 56871 (0.0010) -[2023-10-09 10:33:50,356][23469] Updated weights for policy 1, policy_version 56881 (0.0008) -[2023-10-09 10:33:50,717][23469] Updated weights for policy 1, policy_version 56891 (0.0009) -[2023-10-09 10:33:51,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 116195328. Throughput: 0: 1794.1, 1: 1794.3. Samples: 29050632. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:33:51,078][22500] Avg episode reward: [(0, '9.840'), (1, '8.000')] -[2023-10-09 10:33:51,510][23468] Updated weights for policy 0, policy_version 56583 (0.0009) -[2023-10-09 10:33:51,885][23468] Updated weights for policy 0, policy_version 56593 (0.0009) -[2023-10-09 10:33:52,258][23468] Updated weights for policy 0, policy_version 56603 (0.0008) -[2023-10-09 10:33:54,484][23469] Updated weights for policy 1, policy_version 56901 (0.0009) -[2023-10-09 10:33:54,855][23469] Updated weights for policy 1, policy_version 56911 (0.0008) -[2023-10-09 10:33:55,223][23469] Updated weights for policy 1, policy_version 56921 (0.0008) -[2023-10-09 10:33:55,963][23468] Updated weights for policy 0, policy_version 56613 (0.0008) -[2023-10-09 10:33:56,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 116260864. Throughput: 0: 1793.4, 1: 1808.4. Samples: 29072652. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:33:56,078][22500] Avg episode reward: [(0, '9.440'), (1, '7.780')] -[2023-10-09 10:33:56,330][23468] Updated weights for policy 0, policy_version 56623 (0.0008) -[2023-10-09 10:33:56,703][23468] Updated weights for policy 0, policy_version 56633 (0.0007) -[2023-10-09 10:33:59,010][23469] Updated weights for policy 1, policy_version 56931 (0.0009) -[2023-10-09 10:33:59,377][23469] Updated weights for policy 1, policy_version 56941 (0.0012) -[2023-10-09 10:33:59,742][23469] Updated weights for policy 1, policy_version 56951 (0.0007) -[2023-10-09 10:34:00,397][23468] Updated weights for policy 0, policy_version 56643 (0.0008) -[2023-10-09 10:34:00,769][23468] Updated weights for policy 0, policy_version 56653 (0.0007) -[2023-10-09 10:34:01,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 116326400. Throughput: 0: 1811.6, 1: 1787.8. Samples: 29093964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:34:01,078][22500] Avg episode reward: [(0, '8.940'), (1, '7.800')] -[2023-10-09 10:34:01,136][23468] Updated weights for policy 0, policy_version 56663 (0.0009) -[2023-10-09 10:34:03,603][23469] Updated weights for policy 1, policy_version 56961 (0.0008) -[2023-10-09 10:34:03,974][23469] Updated weights for policy 1, policy_version 56971 (0.0008) -[2023-10-09 10:34:04,335][23469] Updated weights for policy 1, policy_version 56981 (0.0007) -[2023-10-09 10:34:04,714][23469] Updated weights for policy 1, policy_version 56991 (0.0008) -[2023-10-09 10:34:04,730][23468] Updated weights for policy 0, policy_version 56673 (0.0010) -[2023-10-09 10:34:05,108][23468] Updated weights for policy 0, policy_version 56683 (0.0008) -[2023-10-09 10:34:05,473][23468] Updated weights for policy 0, policy_version 56693 (0.0009) -[2023-10-09 10:34:05,851][23468] Updated weights for policy 0, policy_version 56703 (0.0009) -[2023-10-09 10:34:06,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 116424704. Throughput: 0: 1795.4, 1: 1805.5. Samples: 29105026. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:34:06,079][22500] Avg episode reward: [(0, '9.360'), (1, '8.260')] -[2023-10-09 10:34:08,297][23469] Updated weights for policy 1, policy_version 57001 (0.0007) -[2023-10-09 10:34:08,670][23469] Updated weights for policy 1, policy_version 57011 (0.0008) -[2023-10-09 10:34:09,034][23469] Updated weights for policy 1, policy_version 57021 (0.0009) -[2023-10-09 10:34:09,655][23468] Updated weights for policy 0, policy_version 56713 (0.0008) -[2023-10-09 10:34:10,041][23468] Updated weights for policy 0, policy_version 56723 (0.0007) -[2023-10-09 10:34:10,421][23468] Updated weights for policy 0, policy_version 56733 (0.0009) -[2023-10-09 10:34:11,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 116490240. Throughput: 0: 1811.4, 1: 1791.4. Samples: 29126616. Policy #0 lag: (min: 15.0, avg: 24.2, max: 47.0) -[2023-10-09 10:34:11,078][22500] Avg episode reward: [(0, '8.400'), (1, '8.670')] -[2023-10-09 10:34:12,834][23469] Updated weights for policy 1, policy_version 57031 (0.0008) -[2023-10-09 10:34:13,212][23469] Updated weights for policy 1, policy_version 57041 (0.0008) -[2023-10-09 10:34:13,574][23469] Updated weights for policy 1, policy_version 57051 (0.0009) -[2023-10-09 10:34:14,066][23468] Updated weights for policy 0, policy_version 56743 (0.0010) -[2023-10-09 10:34:14,432][23468] Updated weights for policy 0, policy_version 56753 (0.0011) -[2023-10-09 10:34:14,801][23468] Updated weights for policy 0, policy_version 56763 (0.0010) -[2023-10-09 10:34:16,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 116555776. Throughput: 0: 1793.0, 1: 1791.2. Samples: 29147608. Policy #0 lag: (min: 15.0, avg: 24.2, max: 47.0) -[2023-10-09 10:34:16,078][22500] Avg episode reward: [(0, '9.260'), (1, '8.410')] -[2023-10-09 10:34:16,089][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000057056_58425344.pth... -[2023-10-09 10:34:16,089][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000056768_58130432.pth... -[2023-10-09 10:34:16,124][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000055392_56721408.pth -[2023-10-09 10:34:16,126][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000055104_56426496.pth -[2023-10-09 10:34:17,406][23469] Updated weights for policy 1, policy_version 57061 (0.0008) -[2023-10-09 10:34:17,769][23469] Updated weights for policy 1, policy_version 57071 (0.0009) -[2023-10-09 10:34:18,143][23469] Updated weights for policy 1, policy_version 57081 (0.0008) -[2023-10-09 10:34:18,619][23468] Updated weights for policy 0, policy_version 56773 (0.0009) -[2023-10-09 10:34:18,983][23468] Updated weights for policy 0, policy_version 56783 (0.0011) -[2023-10-09 10:34:19,361][23468] Updated weights for policy 0, policy_version 56793 (0.0010) -[2023-10-09 10:34:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 116621312. Throughput: 0: 1802.9, 1: 1789.3. Samples: 29158740. Policy #0 lag: (min: 15.0, avg: 24.2, max: 47.0) -[2023-10-09 10:34:21,078][22500] Avg episode reward: [(0, '8.690'), (1, '8.510')] -[2023-10-09 10:34:21,964][23469] Updated weights for policy 1, policy_version 57091 (0.0009) -[2023-10-09 10:34:22,339][23469] Updated weights for policy 1, policy_version 57101 (0.0010) -[2023-10-09 10:34:22,709][23469] Updated weights for policy 1, policy_version 57111 (0.0010) -[2023-10-09 10:34:23,040][23468] Updated weights for policy 0, policy_version 56803 (0.0010) -[2023-10-09 10:34:23,411][23468] Updated weights for policy 0, policy_version 56813 (0.0009) -[2023-10-09 10:34:23,780][23468] Updated weights for policy 0, policy_version 56823 (0.0007) -[2023-10-09 10:34:26,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 116686848. Throughput: 0: 1795.4, 1: 1786.7. Samples: 29179610. Policy #0 lag: (min: 15.0, avg: 24.2, max: 47.0) -[2023-10-09 10:34:26,078][22500] Avg episode reward: [(0, '9.270'), (1, '8.150')] -[2023-10-09 10:34:26,487][23469] Updated weights for policy 1, policy_version 57121 (0.0009) -[2023-10-09 10:34:26,912][23469] Updated weights for policy 1, policy_version 57131 (0.0009) -[2023-10-09 10:34:27,286][23469] Updated weights for policy 1, policy_version 57141 (0.0009) -[2023-10-09 10:34:27,493][23468] Updated weights for policy 0, policy_version 56833 (0.0008) -[2023-10-09 10:34:27,649][23469] Updated weights for policy 1, policy_version 57151 (0.0008) -[2023-10-09 10:34:27,862][23468] Updated weights for policy 0, policy_version 56843 (0.0007) -[2023-10-09 10:34:28,235][23468] Updated weights for policy 0, policy_version 56853 (0.0008) -[2023-10-09 10:34:28,609][23468] Updated weights for policy 0, policy_version 56863 (0.0007) -[2023-10-09 10:34:31,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 116752384. Throughput: 0: 1799.2, 1: 1803.6. Samples: 29202142. Policy #0 lag: (min: 15.0, avg: 24.2, max: 47.0) -[2023-10-09 10:34:31,078][22500] Avg episode reward: [(0, '9.250'), (1, '7.770')] -[2023-10-09 10:34:31,313][23469] Updated weights for policy 1, policy_version 57161 (0.0010) -[2023-10-09 10:34:31,692][23469] Updated weights for policy 1, policy_version 57171 (0.0011) -[2023-10-09 10:34:32,062][23469] Updated weights for policy 1, policy_version 57181 (0.0009) -[2023-10-09 10:34:32,357][23468] Updated weights for policy 0, policy_version 56873 (0.0009) -[2023-10-09 10:34:32,728][23468] Updated weights for policy 0, policy_version 56883 (0.0011) -[2023-10-09 10:34:33,111][23468] Updated weights for policy 0, policy_version 56893 (0.0010) -[2023-10-09 10:34:35,691][23469] Updated weights for policy 1, policy_version 57191 (0.0009) -[2023-10-09 10:34:36,076][23469] Updated weights for policy 1, policy_version 57201 (0.0009) -[2023-10-09 10:34:36,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 116817920. Throughput: 0: 1799.8, 1: 1785.1. Samples: 29211952. Policy #0 lag: (min: 15.0, avg: 24.2, max: 47.0) -[2023-10-09 10:34:36,078][22500] Avg episode reward: [(0, '9.810'), (1, '7.560')] -[2023-10-09 10:34:36,440][23469] Updated weights for policy 1, policy_version 57211 (0.0010) -[2023-10-09 10:34:36,838][23468] Updated weights for policy 0, policy_version 56903 (0.0009) -[2023-10-09 10:34:37,212][23468] Updated weights for policy 0, policy_version 56913 (0.0008) -[2023-10-09 10:34:37,579][23468] Updated weights for policy 0, policy_version 56923 (0.0007) -[2023-10-09 10:34:40,154][23469] Updated weights for policy 1, policy_version 57221 (0.0008) -[2023-10-09 10:34:40,517][23469] Updated weights for policy 1, policy_version 57231 (0.0009) -[2023-10-09 10:34:40,892][23469] Updated weights for policy 1, policy_version 57241 (0.0010) -[2023-10-09 10:34:41,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 116883456. Throughput: 0: 1795.2, 1: 1805.1. Samples: 29234664. Policy #0 lag: (min: 15.0, avg: 24.2, max: 47.0) -[2023-10-09 10:34:41,078][22500] Avg episode reward: [(0, '9.060'), (1, '8.250')] -[2023-10-09 10:34:41,281][23468] Updated weights for policy 0, policy_version 56933 (0.0008) -[2023-10-09 10:34:41,649][23468] Updated weights for policy 0, policy_version 56943 (0.0008) -[2023-10-09 10:34:42,029][23468] Updated weights for policy 0, policy_version 56953 (0.0009) -[2023-10-09 10:34:44,606][23469] Updated weights for policy 1, policy_version 57251 (0.0009) -[2023-10-09 10:34:44,966][23469] Updated weights for policy 1, policy_version 57261 (0.0008) -[2023-10-09 10:34:45,336][23469] Updated weights for policy 1, policy_version 57271 (0.0010) -[2023-10-09 10:34:45,798][23468] Updated weights for policy 0, policy_version 56963 (0.0008) -[2023-10-09 10:34:46,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 116981760. Throughput: 0: 1794.7, 1: 1799.1. Samples: 29255684. Policy #0 lag: (min: 15.0, avg: 24.2, max: 47.0) -[2023-10-09 10:34:46,078][22500] Avg episode reward: [(0, '8.570'), (1, '8.300')] -[2023-10-09 10:34:46,179][23468] Updated weights for policy 0, policy_version 56973 (0.0008) -[2023-10-09 10:34:46,548][23468] Updated weights for policy 0, policy_version 56983 (0.0007) -[2023-10-09 10:34:49,142][23469] Updated weights for policy 1, policy_version 57281 (0.0008) -[2023-10-09 10:34:49,511][23469] Updated weights for policy 1, policy_version 57291 (0.0011) -[2023-10-09 10:34:49,872][23469] Updated weights for policy 1, policy_version 57301 (0.0007) -[2023-10-09 10:34:50,223][23468] Updated weights for policy 0, policy_version 56993 (0.0009) -[2023-10-09 10:34:50,247][23469] Updated weights for policy 1, policy_version 57311 (0.0008) -[2023-10-09 10:34:50,583][23468] Updated weights for policy 0, policy_version 57003 (0.0008) -[2023-10-09 10:34:50,953][23468] Updated weights for policy 0, policy_version 57013 (0.0008) -[2023-10-09 10:34:51,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 117047296. Throughput: 0: 1789.1, 1: 1805.6. Samples: 29266786. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 10:34:51,079][22500] Avg episode reward: [(0, '8.120'), (1, '8.540')] -[2023-10-09 10:34:51,339][23468] Updated weights for policy 0, policy_version 57023 (0.0008) -[2023-10-09 10:34:54,006][23469] Updated weights for policy 1, policy_version 57321 (0.0007) -[2023-10-09 10:34:54,384][23469] Updated weights for policy 1, policy_version 57331 (0.0009) -[2023-10-09 10:34:54,756][23469] Updated weights for policy 1, policy_version 57341 (0.0007) -[2023-10-09 10:34:55,139][23468] Updated weights for policy 0, policy_version 57033 (0.0007) -[2023-10-09 10:34:55,507][23468] Updated weights for policy 0, policy_version 57043 (0.0007) -[2023-10-09 10:34:55,880][23468] Updated weights for policy 0, policy_version 57053 (0.0007) -[2023-10-09 10:34:56,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 117145600. Throughput: 0: 1786.0, 1: 1797.2. Samples: 29287860. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 10:34:56,078][22500] Avg episode reward: [(0, '8.270'), (1, '8.260')] -[2023-10-09 10:34:58,532][23469] Updated weights for policy 1, policy_version 57351 (0.0008) -[2023-10-09 10:34:58,899][23469] Updated weights for policy 1, policy_version 57361 (0.0007) -[2023-10-09 10:34:59,268][23469] Updated weights for policy 1, policy_version 57371 (0.0009) -[2023-10-09 10:34:59,745][23468] Updated weights for policy 0, policy_version 57063 (0.0007) -[2023-10-09 10:35:00,122][23468] Updated weights for policy 0, policy_version 57073 (0.0008) -[2023-10-09 10:35:00,495][23468] Updated weights for policy 0, policy_version 57083 (0.0009) -[2023-10-09 10:35:01,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 117211136. Throughput: 0: 1801.4, 1: 1789.6. Samples: 29309204. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 10:35:01,078][22500] Avg episode reward: [(0, '8.630'), (1, '7.920')] -[2023-10-09 10:35:03,089][23469] Updated weights for policy 1, policy_version 57381 (0.0008) -[2023-10-09 10:35:03,462][23469] Updated weights for policy 1, policy_version 57391 (0.0008) -[2023-10-09 10:35:03,833][23469] Updated weights for policy 1, policy_version 57401 (0.0009) -[2023-10-09 10:35:04,317][23468] Updated weights for policy 0, policy_version 57093 (0.0010) -[2023-10-09 10:35:04,691][23468] Updated weights for policy 0, policy_version 57103 (0.0010) -[2023-10-09 10:35:05,067][23468] Updated weights for policy 0, policy_version 57113 (0.0010) -[2023-10-09 10:35:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 117276672. Throughput: 0: 1791.9, 1: 1796.8. Samples: 29320232. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 10:35:06,078][22500] Avg episode reward: [(0, '8.790'), (1, '8.570')] -[2023-10-09 10:35:07,582][23469] Updated weights for policy 1, policy_version 57411 (0.0007) -[2023-10-09 10:35:07,956][23469] Updated weights for policy 1, policy_version 57421 (0.0008) -[2023-10-09 10:35:08,327][23469] Updated weights for policy 1, policy_version 57431 (0.0009) -[2023-10-09 10:35:08,632][23468] Updated weights for policy 0, policy_version 57123 (0.0010) -[2023-10-09 10:35:09,006][23468] Updated weights for policy 0, policy_version 57133 (0.0008) -[2023-10-09 10:35:09,375][23468] Updated weights for policy 0, policy_version 57143 (0.0007) -[2023-10-09 10:35:11,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 117342208. Throughput: 0: 1805.4, 1: 1793.1. Samples: 29341544. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 10:35:11,078][22500] Avg episode reward: [(0, '9.180'), (1, '8.480')] -[2023-10-09 10:35:12,035][23469] Updated weights for policy 1, policy_version 57441 (0.0008) -[2023-10-09 10:35:12,449][23469] Updated weights for policy 1, policy_version 57451 (0.0007) -[2023-10-09 10:35:12,824][23469] Updated weights for policy 1, policy_version 57461 (0.0010) -[2023-10-09 10:35:13,197][23469] Updated weights for policy 1, policy_version 57471 (0.0009) -[2023-10-09 10:35:13,200][23468] Updated weights for policy 0, policy_version 57153 (0.0009) -[2023-10-09 10:35:13,562][23468] Updated weights for policy 0, policy_version 57163 (0.0007) -[2023-10-09 10:35:13,948][23468] Updated weights for policy 0, policy_version 57173 (0.0008) -[2023-10-09 10:35:14,321][23468] Updated weights for policy 0, policy_version 57183 (0.0009) -[2023-10-09 10:35:16,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 117407744. Throughput: 0: 1784.3, 1: 1793.7. Samples: 29363152. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 10:35:16,078][22500] Avg episode reward: [(0, '9.450'), (1, '8.440')] -[2023-10-09 10:35:17,016][23469] Updated weights for policy 1, policy_version 57481 (0.0008) -[2023-10-09 10:35:17,381][23469] Updated weights for policy 1, policy_version 57491 (0.0009) -[2023-10-09 10:35:17,750][23469] Updated weights for policy 1, policy_version 57501 (0.0009) -[2023-10-09 10:35:18,170][23468] Updated weights for policy 0, policy_version 57193 (0.0009) -[2023-10-09 10:35:18,548][23468] Updated weights for policy 0, policy_version 57203 (0.0010) -[2023-10-09 10:35:18,925][23468] Updated weights for policy 0, policy_version 57213 (0.0007) -[2023-10-09 10:35:21,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 117473280. Throughput: 0: 1804.8, 1: 1795.5. Samples: 29373964. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 10:35:21,079][22500] Avg episode reward: [(0, '9.200'), (1, '9.370')] -[2023-10-09 10:35:21,476][23469] Updated weights for policy 1, policy_version 57511 (0.0010) -[2023-10-09 10:35:21,841][23469] Updated weights for policy 1, policy_version 57521 (0.0011) -[2023-10-09 10:35:22,209][23469] Updated weights for policy 1, policy_version 57531 (0.0009) -[2023-10-09 10:35:22,546][23468] Updated weights for policy 0, policy_version 57223 (0.0007) -[2023-10-09 10:35:22,923][23468] Updated weights for policy 0, policy_version 57233 (0.0007) -[2023-10-09 10:35:23,291][23468] Updated weights for policy 0, policy_version 57243 (0.0007) -[2023-10-09 10:35:25,772][23469] Updated weights for policy 1, policy_version 57541 (0.0008) -[2023-10-09 10:35:26,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 117538816. Throughput: 0: 1784.7, 1: 1796.7. Samples: 29395828. Policy #0 lag: (min: 13.0, avg: 18.3, max: 45.0) -[2023-10-09 10:35:26,078][22500] Avg episode reward: [(0, '9.410'), (1, '8.570')] -[2023-10-09 10:35:26,151][23469] Updated weights for policy 1, policy_version 57551 (0.0008) -[2023-10-09 10:35:26,517][23469] Updated weights for policy 1, policy_version 57561 (0.0009) -[2023-10-09 10:35:26,962][23468] Updated weights for policy 0, policy_version 57253 (0.0007) -[2023-10-09 10:35:27,335][23468] Updated weights for policy 0, policy_version 57263 (0.0007) -[2023-10-09 10:35:27,715][23468] Updated weights for policy 0, policy_version 57273 (0.0007) -[2023-10-09 10:35:30,192][23469] Updated weights for policy 1, policy_version 57571 (0.0008) -[2023-10-09 10:35:30,560][23469] Updated weights for policy 1, policy_version 57581 (0.0009) -[2023-10-09 10:35:30,929][23469] Updated weights for policy 1, policy_version 57591 (0.0010) -[2023-10-09 10:35:31,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 117604352. Throughput: 0: 1785.2, 1: 1815.8. Samples: 29417730. Policy #0 lag: (min: 13.0, avg: 18.3, max: 45.0) -[2023-10-09 10:35:31,078][22500] Avg episode reward: [(0, '9.310'), (1, '8.420')] -[2023-10-09 10:35:31,516][23468] Updated weights for policy 0, policy_version 57283 (0.0010) -[2023-10-09 10:35:31,887][23468] Updated weights for policy 0, policy_version 57293 (0.0008) -[2023-10-09 10:35:32,263][23468] Updated weights for policy 0, policy_version 57303 (0.0008) -[2023-10-09 10:35:34,495][23469] Updated weights for policy 1, policy_version 57601 (0.0007) -[2023-10-09 10:35:34,867][23469] Updated weights for policy 1, policy_version 57611 (0.0007) -[2023-10-09 10:35:35,245][23469] Updated weights for policy 1, policy_version 57621 (0.0009) -[2023-10-09 10:35:35,605][23469] Updated weights for policy 1, policy_version 57631 (0.0009) -[2023-10-09 10:35:36,034][23468] Updated weights for policy 0, policy_version 57313 (0.0008) -[2023-10-09 10:35:36,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 117702656. Throughput: 0: 1789.9, 1: 1802.6. Samples: 29428448. Policy #0 lag: (min: 13.0, avg: 18.3, max: 45.0) -[2023-10-09 10:35:36,078][22500] Avg episode reward: [(0, '9.610'), (1, '8.110')] -[2023-10-09 10:35:36,407][23468] Updated weights for policy 0, policy_version 57323 (0.0009) -[2023-10-09 10:35:36,785][23468] Updated weights for policy 0, policy_version 57333 (0.0008) -[2023-10-09 10:35:37,164][23468] Updated weights for policy 0, policy_version 57343 (0.0009) -[2023-10-09 10:35:39,401][23469] Updated weights for policy 1, policy_version 57641 (0.0009) -[2023-10-09 10:35:39,775][23469] Updated weights for policy 1, policy_version 57651 (0.0011) -[2023-10-09 10:35:40,143][23469] Updated weights for policy 1, policy_version 57661 (0.0008) -[2023-10-09 10:35:40,978][23468] Updated weights for policy 0, policy_version 57353 (0.0010) -[2023-10-09 10:35:41,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 117768192. Throughput: 0: 1793.5, 1: 1815.3. Samples: 29450256. Policy #0 lag: (min: 13.0, avg: 18.3, max: 45.0) -[2023-10-09 10:35:41,078][22500] Avg episode reward: [(0, '9.240'), (1, '8.130')] -[2023-10-09 10:35:41,349][23468] Updated weights for policy 0, policy_version 57363 (0.0009) -[2023-10-09 10:35:41,711][23468] Updated weights for policy 0, policy_version 57373 (0.0009) -[2023-10-09 10:35:44,102][23469] Updated weights for policy 1, policy_version 57671 (0.0008) -[2023-10-09 10:35:44,465][23469] Updated weights for policy 1, policy_version 57681 (0.0008) -[2023-10-09 10:35:44,838][23469] Updated weights for policy 1, policy_version 57691 (0.0009) -[2023-10-09 10:35:45,478][23468] Updated weights for policy 0, policy_version 57383 (0.0009) -[2023-10-09 10:35:45,852][23468] Updated weights for policy 0, policy_version 57393 (0.0007) -[2023-10-09 10:35:46,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 117833728. Throughput: 0: 1808.9, 1: 1799.6. Samples: 29471588. Policy #0 lag: (min: 13.0, avg: 18.3, max: 45.0) -[2023-10-09 10:35:46,078][22500] Avg episode reward: [(0, '9.100'), (1, '8.300')] -[2023-10-09 10:35:46,228][23468] Updated weights for policy 0, policy_version 57403 (0.0009) -[2023-10-09 10:35:48,525][23469] Updated weights for policy 1, policy_version 57701 (0.0008) -[2023-10-09 10:35:48,888][23469] Updated weights for policy 1, policy_version 57711 (0.0009) -[2023-10-09 10:35:49,263][23469] Updated weights for policy 1, policy_version 57721 (0.0008) -[2023-10-09 10:35:49,925][23468] Updated weights for policy 0, policy_version 57413 (0.0008) -[2023-10-09 10:35:50,308][23468] Updated weights for policy 0, policy_version 57423 (0.0008) -[2023-10-09 10:35:50,672][23468] Updated weights for policy 0, policy_version 57433 (0.0008) -[2023-10-09 10:35:51,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 117932032. Throughput: 0: 1788.0, 1: 1815.9. Samples: 29482406. Policy #0 lag: (min: 13.0, avg: 18.3, max: 45.0) -[2023-10-09 10:35:51,078][22500] Avg episode reward: [(0, '9.130'), (1, '8.410')] -[2023-10-09 10:35:53,177][23469] Updated weights for policy 1, policy_version 57731 (0.0010) -[2023-10-09 10:35:53,547][23469] Updated weights for policy 1, policy_version 57741 (0.0008) -[2023-10-09 10:35:53,922][23469] Updated weights for policy 1, policy_version 57751 (0.0008) -[2023-10-09 10:35:54,353][23468] Updated weights for policy 0, policy_version 57443 (0.0008) -[2023-10-09 10:35:54,720][23468] Updated weights for policy 0, policy_version 57453 (0.0007) -[2023-10-09 10:35:55,098][23468] Updated weights for policy 0, policy_version 57463 (0.0008) -[2023-10-09 10:35:56,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 117997568. Throughput: 0: 1803.8, 1: 1800.7. Samples: 29503746. Policy #0 lag: (min: 13.0, avg: 18.3, max: 45.0) -[2023-10-09 10:35:56,079][22500] Avg episode reward: [(0, '8.940'), (1, '8.360')] -[2023-10-09 10:35:57,578][23469] Updated weights for policy 1, policy_version 57761 (0.0007) -[2023-10-09 10:35:57,988][23469] Updated weights for policy 1, policy_version 57771 (0.0008) -[2023-10-09 10:35:58,353][23469] Updated weights for policy 1, policy_version 57781 (0.0008) -[2023-10-09 10:35:58,724][23469] Updated weights for policy 1, policy_version 57791 (0.0007) -[2023-10-09 10:35:58,907][23468] Updated weights for policy 0, policy_version 57473 (0.0009) -[2023-10-09 10:35:59,271][23468] Updated weights for policy 0, policy_version 57483 (0.0010) -[2023-10-09 10:35:59,644][23468] Updated weights for policy 0, policy_version 57493 (0.0008) -[2023-10-09 10:36:00,017][23468] Updated weights for policy 0, policy_version 57503 (0.0008) -[2023-10-09 10:36:01,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 118063104. Throughput: 0: 1789.6, 1: 1806.0. Samples: 29524952. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:36:01,078][22500] Avg episode reward: [(0, '9.370'), (1, '8.790')] -[2023-10-09 10:36:02,292][23469] Updated weights for policy 1, policy_version 57801 (0.0008) -[2023-10-09 10:36:02,658][23469] Updated weights for policy 1, policy_version 57811 (0.0008) -[2023-10-09 10:36:03,031][23469] Updated weights for policy 1, policy_version 57821 (0.0008) -[2023-10-09 10:36:03,985][23468] Updated weights for policy 0, policy_version 57513 (0.0009) -[2023-10-09 10:36:04,352][23468] Updated weights for policy 0, policy_version 57523 (0.0009) -[2023-10-09 10:36:04,727][23468] Updated weights for policy 0, policy_version 57533 (0.0009) -[2023-10-09 10:36:06,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 118128640. Throughput: 0: 1799.8, 1: 1799.6. Samples: 29535936. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:36:06,078][22500] Avg episode reward: [(0, '9.350'), (1, '8.500')] -[2023-10-09 10:36:06,872][23469] Updated weights for policy 1, policy_version 57831 (0.0007) -[2023-10-09 10:36:07,239][23469] Updated weights for policy 1, policy_version 57841 (0.0007) -[2023-10-09 10:36:07,600][23469] Updated weights for policy 1, policy_version 57851 (0.0007) -[2023-10-09 10:36:08,510][23468] Updated weights for policy 0, policy_version 57543 (0.0007) -[2023-10-09 10:36:08,884][23468] Updated weights for policy 0, policy_version 57553 (0.0007) -[2023-10-09 10:36:09,256][23468] Updated weights for policy 0, policy_version 57563 (0.0008) -[2023-10-09 10:36:11,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 118194176. Throughput: 0: 1790.4, 1: 1794.2. Samples: 29557136. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:36:11,078][22500] Avg episode reward: [(0, '9.700'), (1, '8.410')] -[2023-10-09 10:36:11,313][23469] Updated weights for policy 1, policy_version 57861 (0.0007) -[2023-10-09 10:36:11,695][23469] Updated weights for policy 1, policy_version 57871 (0.0008) -[2023-10-09 10:36:12,053][23469] Updated weights for policy 1, policy_version 57881 (0.0008) -[2023-10-09 10:36:13,047][23468] Updated weights for policy 0, policy_version 57573 (0.0008) -[2023-10-09 10:36:13,418][23468] Updated weights for policy 0, policy_version 57583 (0.0010) -[2023-10-09 10:36:13,796][23468] Updated weights for policy 0, policy_version 57593 (0.0010) -[2023-10-09 10:36:15,664][23469] Updated weights for policy 1, policy_version 57891 (0.0008) -[2023-10-09 10:36:16,038][23469] Updated weights for policy 1, policy_version 57901 (0.0009) -[2023-10-09 10:36:16,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 118259712. Throughput: 0: 1787.1, 1: 1799.1. Samples: 29579110. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:36:16,078][22500] Avg episode reward: [(0, '9.760'), (1, '8.410')] -[2023-10-09 10:36:16,086][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000057600_58982400.pth... -[2023-10-09 10:36:16,124][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000055936_57278464.pth -[2023-10-09 10:36:16,128][23265] Saving a milestone ./train_atari/atari_berzerk_APPO/checkpoint_p0/milestones/checkpoint_000057600_58982400.pth -[2023-10-09 10:36:16,413][23469] Updated weights for policy 1, policy_version 57911 (0.0011) -[2023-10-09 10:36:16,747][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000057920_59310080.pth... -[2023-10-09 10:36:16,786][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000056224_57573376.pth -[2023-10-09 10:36:16,791][23343] Saving a milestone ./train_atari/atari_berzerk_APPO/checkpoint_p1/milestones/checkpoint_000057920_59310080.pth -[2023-10-09 10:36:17,613][23468] Updated weights for policy 0, policy_version 57603 (0.0010) -[2023-10-09 10:36:17,977][23468] Updated weights for policy 0, policy_version 57613 (0.0007) -[2023-10-09 10:36:18,355][23468] Updated weights for policy 0, policy_version 57623 (0.0008) -[2023-10-09 10:36:20,220][23469] Updated weights for policy 1, policy_version 57921 (0.0011) -[2023-10-09 10:36:20,606][23469] Updated weights for policy 1, policy_version 57931 (0.0009) -[2023-10-09 10:36:20,967][23469] Updated weights for policy 1, policy_version 57941 (0.0010) -[2023-10-09 10:36:21,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 118325248. Throughput: 0: 1798.2, 1: 1787.5. Samples: 29589802. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:36:21,078][22500] Avg episode reward: [(0, '9.970'), (1, '9.160')] -[2023-10-09 10:36:21,336][23469] Updated weights for policy 1, policy_version 57951 (0.0011) -[2023-10-09 10:36:22,134][23468] Updated weights for policy 0, policy_version 57633 (0.0008) -[2023-10-09 10:36:22,515][23468] Updated weights for policy 0, policy_version 57643 (0.0010) -[2023-10-09 10:36:22,892][23468] Updated weights for policy 0, policy_version 57653 (0.0010) -[2023-10-09 10:36:23,267][23468] Updated weights for policy 0, policy_version 57663 (0.0010) -[2023-10-09 10:36:25,236][23469] Updated weights for policy 1, policy_version 57961 (0.0009) -[2023-10-09 10:36:25,606][23469] Updated weights for policy 1, policy_version 57971 (0.0009) -[2023-10-09 10:36:25,978][23469] Updated weights for policy 1, policy_version 57981 (0.0008) -[2023-10-09 10:36:26,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 118390784. Throughput: 0: 1781.3, 1: 1804.0. Samples: 29611594. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:36:26,078][22500] Avg episode reward: [(0, '10.260'), (1, '8.560')] -[2023-10-09 10:36:26,079][23265] Saving new best policy, reward=10.260! -[2023-10-09 10:36:26,937][23468] Updated weights for policy 0, policy_version 57673 (0.0009) -[2023-10-09 10:36:27,321][23468] Updated weights for policy 0, policy_version 57683 (0.0010) -[2023-10-09 10:36:27,699][23468] Updated weights for policy 0, policy_version 57693 (0.0008) -[2023-10-09 10:36:29,841][23469] Updated weights for policy 1, policy_version 57991 (0.0009) -[2023-10-09 10:36:30,212][23469] Updated weights for policy 1, policy_version 58001 (0.0008) -[2023-10-09 10:36:30,581][23469] Updated weights for policy 1, policy_version 58011 (0.0010) -[2023-10-09 10:36:31,078][22500] Fps is (10 sec: 16383.3, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 118489088. Throughput: 0: 1782.8, 1: 1791.6. Samples: 29632436. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:36:31,079][22500] Avg episode reward: [(0, '10.240'), (1, '8.960')] -[2023-10-09 10:36:31,413][23468] Updated weights for policy 0, policy_version 57703 (0.0007) -[2023-10-09 10:36:31,789][23468] Updated weights for policy 0, policy_version 57713 (0.0009) -[2023-10-09 10:36:32,161][23468] Updated weights for policy 0, policy_version 57723 (0.0009) -[2023-10-09 10:36:34,296][23469] Updated weights for policy 1, policy_version 58021 (0.0009) -[2023-10-09 10:36:34,659][23469] Updated weights for policy 1, policy_version 58031 (0.0009) -[2023-10-09 10:36:35,029][23469] Updated weights for policy 1, policy_version 58041 (0.0009) -[2023-10-09 10:36:36,035][23468] Updated weights for policy 0, policy_version 57733 (0.0010) -[2023-10-09 10:36:36,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 118554624. Throughput: 0: 1778.3, 1: 1801.3. Samples: 29643490. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:36:36,078][22500] Avg episode reward: [(0, '9.670'), (1, '8.860')] -[2023-10-09 10:36:36,398][23468] Updated weights for policy 0, policy_version 57743 (0.0010) -[2023-10-09 10:36:36,777][23468] Updated weights for policy 0, policy_version 57753 (0.0009) -[2023-10-09 10:36:38,672][23469] Updated weights for policy 1, policy_version 58051 (0.0008) -[2023-10-09 10:36:39,038][23469] Updated weights for policy 1, policy_version 58061 (0.0009) -[2023-10-09 10:36:39,411][23469] Updated weights for policy 1, policy_version 58071 (0.0007) -[2023-10-09 10:36:40,511][23468] Updated weights for policy 0, policy_version 57763 (0.0008) -[2023-10-09 10:36:40,887][23468] Updated weights for policy 0, policy_version 57773 (0.0008) -[2023-10-09 10:36:41,077][22500] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 118620160. Throughput: 0: 1776.0, 1: 1796.3. Samples: 29664500. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-09 10:36:41,078][22500] Avg episode reward: [(0, '9.570'), (1, '8.550')] -[2023-10-09 10:36:41,264][23468] Updated weights for policy 0, policy_version 57783 (0.0007) -[2023-10-09 10:36:43,258][23469] Updated weights for policy 1, policy_version 58081 (0.0007) -[2023-10-09 10:36:43,676][23469] Updated weights for policy 1, policy_version 58091 (0.0007) -[2023-10-09 10:36:44,059][23469] Updated weights for policy 1, policy_version 58101 (0.0009) -[2023-10-09 10:36:44,431][23469] Updated weights for policy 1, policy_version 58111 (0.0007) -[2023-10-09 10:36:44,999][23468] Updated weights for policy 0, policy_version 57793 (0.0007) -[2023-10-09 10:36:45,368][23468] Updated weights for policy 0, policy_version 57803 (0.0008) -[2023-10-09 10:36:45,743][23468] Updated weights for policy 0, policy_version 57813 (0.0010) -[2023-10-09 10:36:46,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 118685696. Throughput: 0: 1797.0, 1: 1782.0. Samples: 29686008. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-09 10:36:46,078][22500] Avg episode reward: [(0, '9.760'), (1, '7.960')] -[2023-10-09 10:36:46,108][23468] Updated weights for policy 0, policy_version 57823 (0.0008) -[2023-10-09 10:36:48,265][23469] Updated weights for policy 1, policy_version 58121 (0.0008) -[2023-10-09 10:36:48,644][23469] Updated weights for policy 1, policy_version 58131 (0.0009) -[2023-10-09 10:36:49,010][23469] Updated weights for policy 1, policy_version 58141 (0.0009) -[2023-10-09 10:36:49,960][23468] Updated weights for policy 0, policy_version 57833 (0.0010) -[2023-10-09 10:36:50,328][23468] Updated weights for policy 0, policy_version 57843 (0.0009) -[2023-10-09 10:36:50,713][23468] Updated weights for policy 0, policy_version 57853 (0.0009) -[2023-10-09 10:36:51,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 118784000. Throughput: 0: 1778.4, 1: 1794.3. Samples: 29696706. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-09 10:36:51,078][22500] Avg episode reward: [(0, '9.510'), (1, '7.460')] -[2023-10-09 10:36:52,698][23469] Updated weights for policy 1, policy_version 58151 (0.0010) -[2023-10-09 10:36:53,065][23469] Updated weights for policy 1, policy_version 58161 (0.0009) -[2023-10-09 10:36:53,452][23469] Updated weights for policy 1, policy_version 58171 (0.0010) -[2023-10-09 10:36:54,485][23468] Updated weights for policy 0, policy_version 57863 (0.0008) -[2023-10-09 10:36:54,859][23468] Updated weights for policy 0, policy_version 57873 (0.0008) -[2023-10-09 10:36:55,234][23468] Updated weights for policy 0, policy_version 57883 (0.0007) -[2023-10-09 10:36:56,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 118849536. Throughput: 0: 1805.5, 1: 1782.4. Samples: 29718590. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-09 10:36:56,078][22500] Avg episode reward: [(0, '9.800'), (1, '7.250')] -[2023-10-09 10:36:57,220][23469] Updated weights for policy 1, policy_version 58181 (0.0010) -[2023-10-09 10:36:57,589][23469] Updated weights for policy 1, policy_version 58191 (0.0010) -[2023-10-09 10:36:57,962][23469] Updated weights for policy 1, policy_version 58201 (0.0009) -[2023-10-09 10:36:58,989][23468] Updated weights for policy 0, policy_version 57893 (0.0011) -[2023-10-09 10:36:59,361][23468] Updated weights for policy 0, policy_version 57903 (0.0008) -[2023-10-09 10:36:59,730][23468] Updated weights for policy 0, policy_version 57913 (0.0007) -[2023-10-09 10:37:01,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 118915072. Throughput: 0: 1770.1, 1: 1792.2. Samples: 29739412. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-09 10:37:01,078][22500] Avg episode reward: [(0, '9.250'), (1, '7.520')] -[2023-10-09 10:37:01,647][23469] Updated weights for policy 1, policy_version 58211 (0.0009) -[2023-10-09 10:37:02,005][23469] Updated weights for policy 1, policy_version 58221 (0.0007) -[2023-10-09 10:37:02,370][23469] Updated weights for policy 1, policy_version 58231 (0.0007) -[2023-10-09 10:37:03,445][23468] Updated weights for policy 0, policy_version 57923 (0.0008) -[2023-10-09 10:37:03,815][23468] Updated weights for policy 0, policy_version 57933 (0.0010) -[2023-10-09 10:37:04,194][23468] Updated weights for policy 0, policy_version 57943 (0.0010) -[2023-10-09 10:37:05,974][23469] Updated weights for policy 1, policy_version 58241 (0.0009) -[2023-10-09 10:37:06,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 118980608. Throughput: 0: 1792.2, 1: 1786.7. Samples: 29750854. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-09 10:37:06,078][22500] Avg episode reward: [(0, '9.120'), (1, '8.090')] -[2023-10-09 10:37:06,334][23469] Updated weights for policy 1, policy_version 58251 (0.0007) -[2023-10-09 10:37:06,711][23469] Updated weights for policy 1, policy_version 58261 (0.0007) -[2023-10-09 10:37:07,077][23469] Updated weights for policy 1, policy_version 58271 (0.0007) -[2023-10-09 10:37:07,934][23468] Updated weights for policy 0, policy_version 57953 (0.0009) -[2023-10-09 10:37:08,311][23468] Updated weights for policy 0, policy_version 57963 (0.0011) -[2023-10-09 10:37:08,688][23468] Updated weights for policy 0, policy_version 57973 (0.0008) -[2023-10-09 10:37:09,060][23468] Updated weights for policy 0, policy_version 57983 (0.0010) -[2023-10-09 10:37:10,831][23469] Updated weights for policy 1, policy_version 58281 (0.0008) -[2023-10-09 10:37:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 119046144. Throughput: 0: 1771.0, 1: 1793.3. Samples: 29771986. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-09 10:37:11,078][22500] Avg episode reward: [(0, '8.760'), (1, '8.600')] -[2023-10-09 10:37:11,193][23469] Updated weights for policy 1, policy_version 58291 (0.0008) -[2023-10-09 10:37:11,562][23469] Updated weights for policy 1, policy_version 58301 (0.0010) -[2023-10-09 10:37:12,930][23468] Updated weights for policy 0, policy_version 57993 (0.0007) -[2023-10-09 10:37:13,303][23468] Updated weights for policy 0, policy_version 58003 (0.0011) -[2023-10-09 10:37:13,668][23468] Updated weights for policy 0, policy_version 58013 (0.0011) -[2023-10-09 10:37:15,094][23469] Updated weights for policy 1, policy_version 58311 (0.0010) -[2023-10-09 10:37:15,455][23469] Updated weights for policy 1, policy_version 58321 (0.0009) -[2023-10-09 10:37:15,830][23469] Updated weights for policy 1, policy_version 58331 (0.0008) -[2023-10-09 10:37:16,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 119144448. Throughput: 0: 1772.9, 1: 1804.3. Samples: 29793410. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-09 10:37:16,078][22500] Avg episode reward: [(0, '8.510'), (1, '8.760')] -[2023-10-09 10:37:17,416][23468] Updated weights for policy 0, policy_version 58023 (0.0009) -[2023-10-09 10:37:17,792][23468] Updated weights for policy 0, policy_version 58033 (0.0007) -[2023-10-09 10:37:18,159][23468] Updated weights for policy 0, policy_version 58043 (0.0007) -[2023-10-09 10:37:19,572][23469] Updated weights for policy 1, policy_version 58341 (0.0008) -[2023-10-09 10:37:19,938][23469] Updated weights for policy 1, policy_version 58351 (0.0007) -[2023-10-09 10:37:20,311][23469] Updated weights for policy 1, policy_version 58361 (0.0007) -[2023-10-09 10:37:21,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 119209984. Throughput: 0: 1778.4, 1: 1798.5. Samples: 29804450. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-09 10:37:21,078][22500] Avg episode reward: [(0, '8.950'), (1, '8.700')] -[2023-10-09 10:37:22,018][23468] Updated weights for policy 0, policy_version 58053 (0.0009) -[2023-10-09 10:37:22,386][23468] Updated weights for policy 0, policy_version 58063 (0.0010) -[2023-10-09 10:37:22,753][23468] Updated weights for policy 0, policy_version 58073 (0.0007) -[2023-10-09 10:37:23,982][23469] Updated weights for policy 1, policy_version 58371 (0.0009) -[2023-10-09 10:37:24,353][23469] Updated weights for policy 1, policy_version 58381 (0.0008) -[2023-10-09 10:37:24,729][23469] Updated weights for policy 1, policy_version 58391 (0.0008) -[2023-10-09 10:37:26,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 119275520. Throughput: 0: 1771.7, 1: 1801.8. Samples: 29825308. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-09 10:37:26,078][22500] Avg episode reward: [(0, '9.410'), (1, '8.310')] -[2023-10-09 10:37:26,596][23468] Updated weights for policy 0, policy_version 58083 (0.0007) -[2023-10-09 10:37:26,985][23468] Updated weights for policy 0, policy_version 58093 (0.0010) -[2023-10-09 10:37:27,343][23468] Updated weights for policy 0, policy_version 58103 (0.0010) -[2023-10-09 10:37:28,561][23469] Updated weights for policy 1, policy_version 58401 (0.0008) -[2023-10-09 10:37:28,986][23469] Updated weights for policy 1, policy_version 58411 (0.0010) -[2023-10-09 10:37:29,354][23469] Updated weights for policy 1, policy_version 58421 (0.0010) -[2023-10-09 10:37:29,729][23469] Updated weights for policy 1, policy_version 58431 (0.0010) -[2023-10-09 10:37:31,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 119341056. Throughput: 0: 1775.7, 1: 1791.9. Samples: 29846548. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-09 10:37:31,078][22500] Avg episode reward: [(0, '9.320'), (1, '8.170')] -[2023-10-09 10:37:31,140][23468] Updated weights for policy 0, policy_version 58113 (0.0011) -[2023-10-09 10:37:31,511][23468] Updated weights for policy 0, policy_version 58123 (0.0007) -[2023-10-09 10:37:31,873][23468] Updated weights for policy 0, policy_version 58133 (0.0008) -[2023-10-09 10:37:32,254][23468] Updated weights for policy 0, policy_version 58143 (0.0008) -[2023-10-09 10:37:33,472][23469] Updated weights for policy 1, policy_version 58441 (0.0008) -[2023-10-09 10:37:33,834][23469] Updated weights for policy 1, policy_version 58451 (0.0009) -[2023-10-09 10:37:34,213][23469] Updated weights for policy 1, policy_version 58461 (0.0010) -[2023-10-09 10:37:35,861][23468] Updated weights for policy 0, policy_version 58153 (0.0007) -[2023-10-09 10:37:36,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 119406592. Throughput: 0: 1763.7, 1: 1800.3. Samples: 29857086. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-09 10:37:36,078][22500] Avg episode reward: [(0, '9.030'), (1, '8.220')] -[2023-10-09 10:37:36,238][23468] Updated weights for policy 0, policy_version 58163 (0.0009) -[2023-10-09 10:37:36,606][23468] Updated weights for policy 0, policy_version 58173 (0.0007) -[2023-10-09 10:37:38,008][23469] Updated weights for policy 1, policy_version 58471 (0.0009) -[2023-10-09 10:37:38,375][23469] Updated weights for policy 1, policy_version 58481 (0.0008) -[2023-10-09 10:37:38,750][23469] Updated weights for policy 1, policy_version 58491 (0.0009) -[2023-10-09 10:37:40,366][23468] Updated weights for policy 0, policy_version 58183 (0.0007) -[2023-10-09 10:37:40,743][23468] Updated weights for policy 0, policy_version 58193 (0.0009) -[2023-10-09 10:37:41,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 119472128. Throughput: 0: 1766.0, 1: 1792.9. Samples: 29878742. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-09 10:37:41,078][22500] Avg episode reward: [(0, '9.170'), (1, '8.710')] -[2023-10-09 10:37:41,113][23468] Updated weights for policy 0, policy_version 58203 (0.0008) -[2023-10-09 10:37:42,521][23469] Updated weights for policy 1, policy_version 58501 (0.0009) -[2023-10-09 10:37:42,888][23469] Updated weights for policy 1, policy_version 58511 (0.0008) -[2023-10-09 10:37:43,260][23469] Updated weights for policy 1, policy_version 58521 (0.0009) -[2023-10-09 10:37:44,846][23468] Updated weights for policy 0, policy_version 58213 (0.0007) -[2023-10-09 10:37:45,210][23468] Updated weights for policy 0, policy_version 58223 (0.0008) -[2023-10-09 10:37:45,580][23468] Updated weights for policy 0, policy_version 58233 (0.0010) -[2023-10-09 10:37:46,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 119570432. Throughput: 0: 1789.1, 1: 1793.7. Samples: 29900638. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-09 10:37:46,078][22500] Avg episode reward: [(0, '9.840'), (1, '8.980')] -[2023-10-09 10:37:47,041][23469] Updated weights for policy 1, policy_version 58531 (0.0009) -[2023-10-09 10:37:47,421][23469] Updated weights for policy 1, policy_version 58541 (0.0008) -[2023-10-09 10:37:47,779][23469] Updated weights for policy 1, policy_version 58551 (0.0008) -[2023-10-09 10:37:49,377][23468] Updated weights for policy 0, policy_version 58243 (0.0010) -[2023-10-09 10:37:49,749][23468] Updated weights for policy 0, policy_version 58253 (0.0008) -[2023-10-09 10:37:50,132][23468] Updated weights for policy 0, policy_version 58263 (0.0009) -[2023-10-09 10:37:51,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 119635968. Throughput: 0: 1770.8, 1: 1790.0. Samples: 29911088. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-09 10:37:51,078][22500] Avg episode reward: [(0, '9.750'), (1, '8.610')] -[2023-10-09 10:37:51,643][23469] Updated weights for policy 1, policy_version 58561 (0.0009) -[2023-10-09 10:37:52,015][23469] Updated weights for policy 1, policy_version 58571 (0.0008) -[2023-10-09 10:37:52,385][23469] Updated weights for policy 1, policy_version 58581 (0.0009) -[2023-10-09 10:37:52,757][23469] Updated weights for policy 1, policy_version 58591 (0.0009) -[2023-10-09 10:37:53,883][23468] Updated weights for policy 0, policy_version 58273 (0.0009) -[2023-10-09 10:37:54,241][23468] Updated weights for policy 0, policy_version 58283 (0.0010) -[2023-10-09 10:37:54,620][23468] Updated weights for policy 0, policy_version 58293 (0.0008) -[2023-10-09 10:37:54,988][23468] Updated weights for policy 0, policy_version 58303 (0.0007) -[2023-10-09 10:37:56,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 119701504. Throughput: 0: 1791.9, 1: 1776.2. Samples: 29932552. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-09 10:37:56,078][22500] Avg episode reward: [(0, '10.350'), (1, '8.230')] -[2023-10-09 10:37:56,079][23265] Saving new best policy, reward=10.350! -[2023-10-09 10:37:56,556][23469] Updated weights for policy 1, policy_version 58601 (0.0009) -[2023-10-09 10:37:56,932][23469] Updated weights for policy 1, policy_version 58611 (0.0008) -[2023-10-09 10:37:57,295][23469] Updated weights for policy 1, policy_version 58621 (0.0007) -[2023-10-09 10:37:58,810][23468] Updated weights for policy 0, policy_version 58313 (0.0010) -[2023-10-09 10:37:59,176][23468] Updated weights for policy 0, policy_version 58323 (0.0010) -[2023-10-09 10:37:59,550][23468] Updated weights for policy 0, policy_version 58333 (0.0009) -[2023-10-09 10:38:01,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 119767040. Throughput: 0: 1768.9, 1: 1800.5. Samples: 29954034. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 10:38:01,078][22500] Avg episode reward: [(0, '9.820'), (1, '7.710')] -[2023-10-09 10:38:01,097][23469] Updated weights for policy 1, policy_version 58631 (0.0009) -[2023-10-09 10:38:01,473][23469] Updated weights for policy 1, policy_version 58641 (0.0008) -[2023-10-09 10:38:01,841][23469] Updated weights for policy 1, policy_version 58651 (0.0010) -[2023-10-09 10:38:03,385][23468] Updated weights for policy 0, policy_version 58343 (0.0009) -[2023-10-09 10:38:03,775][23468] Updated weights for policy 0, policy_version 58353 (0.0007) -[2023-10-09 10:38:04,146][23468] Updated weights for policy 0, policy_version 58363 (0.0010) -[2023-10-09 10:38:05,481][23469] Updated weights for policy 1, policy_version 58661 (0.0009) -[2023-10-09 10:38:05,851][23469] Updated weights for policy 1, policy_version 58671 (0.0008) -[2023-10-09 10:38:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 119832576. Throughput: 0: 1797.9, 1: 1777.3. Samples: 29965336. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 10:38:06,078][22500] Avg episode reward: [(0, '9.880'), (1, '8.410')] -[2023-10-09 10:38:06,224][23469] Updated weights for policy 1, policy_version 58681 (0.0008) -[2023-10-09 10:38:07,741][23468] Updated weights for policy 0, policy_version 58373 (0.0009) -[2023-10-09 10:38:08,111][23468] Updated weights for policy 0, policy_version 58383 (0.0010) -[2023-10-09 10:38:08,490][23468] Updated weights for policy 0, policy_version 58393 (0.0011) -[2023-10-09 10:38:10,094][23469] Updated weights for policy 1, policy_version 58691 (0.0008) -[2023-10-09 10:38:10,456][23469] Updated weights for policy 1, policy_version 58701 (0.0008) -[2023-10-09 10:38:10,825][23469] Updated weights for policy 1, policy_version 58711 (0.0008) -[2023-10-09 10:38:11,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 119898112. Throughput: 0: 1781.1, 1: 1803.8. Samples: 29986628. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 10:38:11,078][22500] Avg episode reward: [(0, '10.180'), (1, '7.800')] -[2023-10-09 10:38:12,594][23468] Updated weights for policy 0, policy_version 58403 (0.0008) -[2023-10-09 10:38:12,973][23468] Updated weights for policy 0, policy_version 58413 (0.0008) -[2023-10-09 10:38:13,347][23468] Updated weights for policy 0, policy_version 58423 (0.0008) -[2023-10-09 10:38:14,672][23469] Updated weights for policy 1, policy_version 58721 (0.0008) -[2023-10-09 10:38:15,078][23469] Updated weights for policy 1, policy_version 58731 (0.0010) -[2023-10-09 10:38:15,450][23469] Updated weights for policy 1, policy_version 58741 (0.0010) -[2023-10-09 10:38:15,811][23469] Updated weights for policy 1, policy_version 58751 (0.0010) -[2023-10-09 10:38:16,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 119996416. Throughput: 0: 1782.2, 1: 1788.4. Samples: 30007226. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 10:38:16,078][22500] Avg episode reward: [(0, '9.350'), (1, '8.220')] -[2023-10-09 10:38:16,085][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000058752_60162048.pth... -[2023-10-09 10:38:16,086][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000058432_59834368.pth... -[2023-10-09 10:38:16,115][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000057056_58425344.pth -[2023-10-09 10:38:16,131][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000056768_58130432.pth -[2023-10-09 10:38:17,021][23468] Updated weights for policy 0, policy_version 58433 (0.0008) -[2023-10-09 10:38:17,394][23468] Updated weights for policy 0, policy_version 58443 (0.0007) -[2023-10-09 10:38:17,767][23468] Updated weights for policy 0, policy_version 58453 (0.0007) -[2023-10-09 10:38:18,145][23468] Updated weights for policy 0, policy_version 58463 (0.0007) -[2023-10-09 10:38:19,656][23469] Updated weights for policy 1, policy_version 58761 (0.0007) -[2023-10-09 10:38:20,031][23469] Updated weights for policy 1, policy_version 58771 (0.0007) -[2023-10-09 10:38:20,397][23469] Updated weights for policy 1, policy_version 58781 (0.0007) -[2023-10-09 10:38:21,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 120061952. Throughput: 0: 1782.7, 1: 1802.4. Samples: 30018418. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 10:38:21,078][22500] Avg episode reward: [(0, '9.090'), (1, '7.940')] -[2023-10-09 10:38:21,895][23468] Updated weights for policy 0, policy_version 58473 (0.0008) -[2023-10-09 10:38:22,269][23468] Updated weights for policy 0, policy_version 58483 (0.0009) -[2023-10-09 10:38:22,651][23468] Updated weights for policy 0, policy_version 58493 (0.0009) -[2023-10-09 10:38:23,869][23469] Updated weights for policy 1, policy_version 58791 (0.0008) -[2023-10-09 10:38:24,246][23469] Updated weights for policy 1, policy_version 58801 (0.0009) -[2023-10-09 10:38:24,616][23469] Updated weights for policy 1, policy_version 58811 (0.0009) -[2023-10-09 10:38:26,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 120127488. Throughput: 0: 1783.3, 1: 1789.7. Samples: 30039526. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 10:38:26,078][22500] Avg episode reward: [(0, '9.610'), (1, '8.080')] -[2023-10-09 10:38:26,366][23468] Updated weights for policy 0, policy_version 58503 (0.0008) -[2023-10-09 10:38:26,740][23468] Updated weights for policy 0, policy_version 58513 (0.0007) -[2023-10-09 10:38:27,111][23468] Updated weights for policy 0, policy_version 58523 (0.0007) -[2023-10-09 10:38:28,394][23469] Updated weights for policy 1, policy_version 58821 (0.0010) -[2023-10-09 10:38:28,762][23469] Updated weights for policy 1, policy_version 58831 (0.0011) -[2023-10-09 10:38:29,136][23469] Updated weights for policy 1, policy_version 58841 (0.0010) -[2023-10-09 10:38:30,750][23468] Updated weights for policy 0, policy_version 58533 (0.0009) -[2023-10-09 10:38:31,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 120193024. Throughput: 0: 1801.5, 1: 1779.9. Samples: 30061804. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 10:38:31,079][22500] Avg episode reward: [(0, '9.300'), (1, '8.220')] -[2023-10-09 10:38:31,126][23468] Updated weights for policy 0, policy_version 58543 (0.0011) -[2023-10-09 10:38:31,508][23468] Updated weights for policy 0, policy_version 58553 (0.0008) -[2023-10-09 10:38:32,993][23469] Updated weights for policy 1, policy_version 58851 (0.0010) -[2023-10-09 10:38:33,361][23469] Updated weights for policy 1, policy_version 58861 (0.0009) -[2023-10-09 10:38:33,733][23469] Updated weights for policy 1, policy_version 58871 (0.0008) -[2023-10-09 10:38:35,218][23468] Updated weights for policy 0, policy_version 58563 (0.0008) -[2023-10-09 10:38:35,589][23468] Updated weights for policy 0, policy_version 58573 (0.0010) -[2023-10-09 10:38:35,960][23468] Updated weights for policy 0, policy_version 58583 (0.0008) -[2023-10-09 10:38:36,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 120258560. Throughput: 0: 1781.0, 1: 1790.0. Samples: 30071780. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 10:38:36,079][22500] Avg episode reward: [(0, '9.860'), (1, '8.300')] -[2023-10-09 10:38:37,467][23469] Updated weights for policy 1, policy_version 58881 (0.0009) -[2023-10-09 10:38:37,830][23469] Updated weights for policy 1, policy_version 58891 (0.0009) -[2023-10-09 10:38:38,198][23469] Updated weights for policy 1, policy_version 58901 (0.0009) -[2023-10-09 10:38:38,575][23469] Updated weights for policy 1, policy_version 58911 (0.0008) -[2023-10-09 10:38:39,753][23468] Updated weights for policy 0, policy_version 58593 (0.0007) -[2023-10-09 10:38:40,123][23468] Updated weights for policy 0, policy_version 58603 (0.0010) -[2023-10-09 10:38:40,489][23468] Updated weights for policy 0, policy_version 58613 (0.0010) -[2023-10-09 10:38:40,866][23468] Updated weights for policy 0, policy_version 58623 (0.0010) -[2023-10-09 10:38:41,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 120356864. Throughput: 0: 1794.0, 1: 1791.4. Samples: 30093892. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:38:41,078][22500] Avg episode reward: [(0, '9.280'), (1, '8.120')] -[2023-10-09 10:38:42,230][23469] Updated weights for policy 1, policy_version 58921 (0.0008) -[2023-10-09 10:38:42,596][23469] Updated weights for policy 1, policy_version 58931 (0.0007) -[2023-10-09 10:38:42,962][23469] Updated weights for policy 1, policy_version 58941 (0.0007) -[2023-10-09 10:38:44,704][23468] Updated weights for policy 0, policy_version 58633 (0.0011) -[2023-10-09 10:38:45,086][23468] Updated weights for policy 0, policy_version 58643 (0.0010) -[2023-10-09 10:38:45,453][23468] Updated weights for policy 0, policy_version 58653 (0.0009) -[2023-10-09 10:38:46,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 120422400. Throughput: 0: 1788.2, 1: 1788.6. Samples: 30114990. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:38:46,079][22500] Avg episode reward: [(0, '9.650'), (1, '8.400')] -[2023-10-09 10:38:46,772][23469] Updated weights for policy 1, policy_version 58951 (0.0007) -[2023-10-09 10:38:47,150][23469] Updated weights for policy 1, policy_version 58961 (0.0007) -[2023-10-09 10:38:47,523][23469] Updated weights for policy 1, policy_version 58971 (0.0007) -[2023-10-09 10:38:49,259][23468] Updated weights for policy 0, policy_version 58663 (0.0011) -[2023-10-09 10:38:49,638][23468] Updated weights for policy 0, policy_version 58673 (0.0007) -[2023-10-09 10:38:49,995][23468] Updated weights for policy 0, policy_version 58683 (0.0008) -[2023-10-09 10:38:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 120487936. Throughput: 0: 1780.4, 1: 1785.3. Samples: 30125794. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:38:51,078][22500] Avg episode reward: [(0, '9.630'), (1, '8.030')] -[2023-10-09 10:38:51,388][23469] Updated weights for policy 1, policy_version 58981 (0.0008) -[2023-10-09 10:38:51,765][23469] Updated weights for policy 1, policy_version 58991 (0.0008) -[2023-10-09 10:38:52,125][23469] Updated weights for policy 1, policy_version 59001 (0.0010) -[2023-10-09 10:38:53,697][23468] Updated weights for policy 0, policy_version 58693 (0.0008) -[2023-10-09 10:38:54,074][23468] Updated weights for policy 0, policy_version 58703 (0.0009) -[2023-10-09 10:38:54,455][23468] Updated weights for policy 0, policy_version 58713 (0.0008) -[2023-10-09 10:38:55,883][23469] Updated weights for policy 1, policy_version 59011 (0.0007) -[2023-10-09 10:38:56,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 120553472. Throughput: 0: 1790.6, 1: 1780.8. Samples: 30147342. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:38:56,078][22500] Avg episode reward: [(0, '9.330'), (1, '8.370')] -[2023-10-09 10:38:56,258][23469] Updated weights for policy 1, policy_version 59021 (0.0008) -[2023-10-09 10:38:56,628][23469] Updated weights for policy 1, policy_version 59031 (0.0008) -[2023-10-09 10:38:58,084][23468] Updated weights for policy 0, policy_version 58723 (0.0007) -[2023-10-09 10:38:58,450][23468] Updated weights for policy 0, policy_version 58733 (0.0007) -[2023-10-09 10:38:58,827][23468] Updated weights for policy 0, policy_version 58743 (0.0007) -[2023-10-09 10:39:00,399][23469] Updated weights for policy 1, policy_version 59041 (0.0009) -[2023-10-09 10:39:00,806][23469] Updated weights for policy 1, policy_version 59051 (0.0008) -[2023-10-09 10:39:01,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 120619008. Throughput: 0: 1787.3, 1: 1805.1. Samples: 30168884. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:39:01,079][22500] Avg episode reward: [(0, '10.090'), (1, '8.460')] -[2023-10-09 10:39:01,178][23469] Updated weights for policy 1, policy_version 59061 (0.0007) -[2023-10-09 10:39:01,538][23469] Updated weights for policy 1, policy_version 59071 (0.0008) -[2023-10-09 10:39:02,520][23468] Updated weights for policy 0, policy_version 58753 (0.0007) -[2023-10-09 10:39:02,890][23468] Updated weights for policy 0, policy_version 58763 (0.0008) -[2023-10-09 10:39:03,273][23468] Updated weights for policy 0, policy_version 58773 (0.0009) -[2023-10-09 10:39:03,646][23468] Updated weights for policy 0, policy_version 58783 (0.0007) -[2023-10-09 10:39:05,131][23469] Updated weights for policy 1, policy_version 59081 (0.0007) -[2023-10-09 10:39:05,496][23469] Updated weights for policy 1, policy_version 59091 (0.0009) -[2023-10-09 10:39:05,864][23469] Updated weights for policy 1, policy_version 59101 (0.0010) -[2023-10-09 10:39:06,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 120717312. Throughput: 0: 1799.3, 1: 1787.7. Samples: 30179832. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:39:06,078][22500] Avg episode reward: [(0, '9.590'), (1, '8.580')] -[2023-10-09 10:39:07,408][23468] Updated weights for policy 0, policy_version 58793 (0.0007) -[2023-10-09 10:39:07,789][23468] Updated weights for policy 0, policy_version 58803 (0.0007) -[2023-10-09 10:39:08,154][23468] Updated weights for policy 0, policy_version 58813 (0.0009) -[2023-10-09 10:39:09,587][23469] Updated weights for policy 1, policy_version 59111 (0.0009) -[2023-10-09 10:39:09,967][23469] Updated weights for policy 1, policy_version 59121 (0.0010) -[2023-10-09 10:39:10,343][23469] Updated weights for policy 1, policy_version 59131 (0.0011) -[2023-10-09 10:39:11,078][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 120782848. Throughput: 0: 1786.8, 1: 1807.5. Samples: 30201270. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:39:11,079][22500] Avg episode reward: [(0, '9.210'), (1, '9.400')] -[2023-10-09 10:39:11,939][23468] Updated weights for policy 0, policy_version 58823 (0.0010) -[2023-10-09 10:39:12,318][23468] Updated weights for policy 0, policy_version 58833 (0.0007) -[2023-10-09 10:39:12,691][23468] Updated weights for policy 0, policy_version 58843 (0.0008) -[2023-10-09 10:39:14,114][23469] Updated weights for policy 1, policy_version 59141 (0.0009) -[2023-10-09 10:39:14,478][23469] Updated weights for policy 1, policy_version 59151 (0.0008) -[2023-10-09 10:39:14,852][23469] Updated weights for policy 1, policy_version 59161 (0.0008) -[2023-10-09 10:39:16,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 120848384. Throughput: 0: 1782.5, 1: 1790.4. Samples: 30222586. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:39:16,078][22500] Avg episode reward: [(0, '9.430'), (1, '9.120')] -[2023-10-09 10:39:16,457][23468] Updated weights for policy 0, policy_version 58853 (0.0009) -[2023-10-09 10:39:16,846][23468] Updated weights for policy 0, policy_version 58863 (0.0010) -[2023-10-09 10:39:17,217][23468] Updated weights for policy 0, policy_version 58873 (0.0008) -[2023-10-09 10:39:18,637][23469] Updated weights for policy 1, policy_version 59171 (0.0009) -[2023-10-09 10:39:18,997][23469] Updated weights for policy 1, policy_version 59181 (0.0009) -[2023-10-09 10:39:19,367][23469] Updated weights for policy 1, policy_version 59191 (0.0008) -[2023-10-09 10:39:21,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 120913920. Throughput: 0: 1783.2, 1: 1809.0. Samples: 30233432. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:39:21,078][22500] Avg episode reward: [(0, '8.710'), (1, '9.320')] -[2023-10-09 10:39:21,116][23468] Updated weights for policy 0, policy_version 58883 (0.0010) -[2023-10-09 10:39:21,482][23468] Updated weights for policy 0, policy_version 58893 (0.0010) -[2023-10-09 10:39:21,855][23468] Updated weights for policy 0, policy_version 58903 (0.0011) -[2023-10-09 10:39:23,189][23469] Updated weights for policy 1, policy_version 59201 (0.0009) -[2023-10-09 10:39:23,554][23469] Updated weights for policy 1, policy_version 59211 (0.0008) -[2023-10-09 10:39:23,927][23469] Updated weights for policy 1, policy_version 59221 (0.0010) -[2023-10-09 10:39:24,292][23469] Updated weights for policy 1, policy_version 59231 (0.0007) -[2023-10-09 10:39:25,544][23468] Updated weights for policy 0, policy_version 58913 (0.0010) -[2023-10-09 10:39:25,912][23468] Updated weights for policy 0, policy_version 58923 (0.0008) -[2023-10-09 10:39:26,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 120979456. Throughput: 0: 1781.6, 1: 1788.9. Samples: 30254562. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:39:26,078][22500] Avg episode reward: [(0, '8.590'), (1, '8.810')] -[2023-10-09 10:39:26,293][23468] Updated weights for policy 0, policy_version 58933 (0.0009) -[2023-10-09 10:39:26,677][23468] Updated weights for policy 0, policy_version 58943 (0.0008) -[2023-10-09 10:39:27,972][23469] Updated weights for policy 1, policy_version 59241 (0.0007) -[2023-10-09 10:39:28,339][23469] Updated weights for policy 1, policy_version 59251 (0.0010) -[2023-10-09 10:39:28,711][23469] Updated weights for policy 1, policy_version 59261 (0.0009) -[2023-10-09 10:39:30,442][23468] Updated weights for policy 0, policy_version 58953 (0.0009) -[2023-10-09 10:39:30,819][23468] Updated weights for policy 0, policy_version 58963 (0.0008) -[2023-10-09 10:39:31,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 121044992. Throughput: 0: 1807.2, 1: 1792.0. Samples: 30276956. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:39:31,078][22500] Avg episode reward: [(0, '8.910'), (1, '8.790')] -[2023-10-09 10:39:31,184][23468] Updated weights for policy 0, policy_version 58973 (0.0007) -[2023-10-09 10:39:32,361][23469] Updated weights for policy 1, policy_version 59271 (0.0010) -[2023-10-09 10:39:32,739][23469] Updated weights for policy 1, policy_version 59281 (0.0011) -[2023-10-09 10:39:33,106][23469] Updated weights for policy 1, policy_version 59291 (0.0009) -[2023-10-09 10:39:34,942][23468] Updated weights for policy 0, policy_version 58983 (0.0008) -[2023-10-09 10:39:35,307][23468] Updated weights for policy 0, policy_version 58993 (0.0009) -[2023-10-09 10:39:35,691][23468] Updated weights for policy 0, policy_version 59003 (0.0010) -[2023-10-09 10:39:36,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 121143296. Throughput: 0: 1793.2, 1: 1793.0. Samples: 30287174. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:39:36,078][22500] Avg episode reward: [(0, '8.810'), (1, '8.490')] -[2023-10-09 10:39:36,819][23469] Updated weights for policy 1, policy_version 59301 (0.0009) -[2023-10-09 10:39:37,191][23469] Updated weights for policy 1, policy_version 59311 (0.0010) -[2023-10-09 10:39:37,567][23469] Updated weights for policy 1, policy_version 59321 (0.0010) -[2023-10-09 10:39:39,608][23468] Updated weights for policy 0, policy_version 59013 (0.0009) -[2023-10-09 10:39:39,984][23468] Updated weights for policy 0, policy_version 59023 (0.0008) -[2023-10-09 10:39:40,369][23468] Updated weights for policy 0, policy_version 59033 (0.0009) -[2023-10-09 10:39:41,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 121208832. Throughput: 0: 1803.7, 1: 1792.0. Samples: 30309146. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:39:41,078][22500] Avg episode reward: [(0, '9.670'), (1, '8.470')] -[2023-10-09 10:39:41,471][23469] Updated weights for policy 1, policy_version 59331 (0.0009) -[2023-10-09 10:39:41,834][23469] Updated weights for policy 1, policy_version 59341 (0.0008) -[2023-10-09 10:39:42,203][23469] Updated weights for policy 1, policy_version 59351 (0.0011) -[2023-10-09 10:39:44,251][23468] Updated weights for policy 0, policy_version 59043 (0.0009) -[2023-10-09 10:39:44,623][23468] Updated weights for policy 0, policy_version 59053 (0.0011) -[2023-10-09 10:39:44,985][23468] Updated weights for policy 0, policy_version 59063 (0.0010) -[2023-10-09 10:39:45,915][23469] Updated weights for policy 1, policy_version 59361 (0.0009) -[2023-10-09 10:39:46,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 121274368. Throughput: 0: 1775.1, 1: 1800.5. Samples: 30329786. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:39:46,078][22500] Avg episode reward: [(0, '9.220'), (1, '8.390')] -[2023-10-09 10:39:46,296][23469] Updated weights for policy 1, policy_version 59371 (0.0008) -[2023-10-09 10:39:46,666][23469] Updated weights for policy 1, policy_version 59381 (0.0010) -[2023-10-09 10:39:47,037][23469] Updated weights for policy 1, policy_version 59391 (0.0009) -[2023-10-09 10:39:48,713][23468] Updated weights for policy 0, policy_version 59073 (0.0009) -[2023-10-09 10:39:49,087][23468] Updated weights for policy 0, policy_version 59083 (0.0010) -[2023-10-09 10:39:49,449][23468] Updated weights for policy 0, policy_version 59093 (0.0008) -[2023-10-09 10:39:49,826][23468] Updated weights for policy 0, policy_version 59103 (0.0009) -[2023-10-09 10:39:50,731][23469] Updated weights for policy 1, policy_version 59401 (0.0008) -[2023-10-09 10:39:51,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 121339904. Throughput: 0: 1792.6, 1: 1782.0. Samples: 30340688. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:39:51,078][22500] Avg episode reward: [(0, '9.320'), (1, '8.160')] -[2023-10-09 10:39:51,100][23469] Updated weights for policy 1, policy_version 59411 (0.0009) -[2023-10-09 10:39:51,473][23469] Updated weights for policy 1, policy_version 59421 (0.0008) -[2023-10-09 10:39:53,631][23468] Updated weights for policy 0, policy_version 59113 (0.0009) -[2023-10-09 10:39:54,008][23468] Updated weights for policy 0, policy_version 59123 (0.0007) -[2023-10-09 10:39:54,375][23468] Updated weights for policy 0, policy_version 59133 (0.0007) -[2023-10-09 10:39:55,304][23469] Updated weights for policy 1, policy_version 59431 (0.0010) -[2023-10-09 10:39:55,680][23469] Updated weights for policy 1, policy_version 59441 (0.0009) -[2023-10-09 10:39:56,044][23469] Updated weights for policy 1, policy_version 59451 (0.0008) -[2023-10-09 10:39:56,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 121405440. Throughput: 0: 1777.6, 1: 1794.3. Samples: 30362002. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:39:56,078][22500] Avg episode reward: [(0, '9.440'), (1, '8.590')] -[2023-10-09 10:39:58,116][23468] Updated weights for policy 0, policy_version 59143 (0.0008) -[2023-10-09 10:39:58,500][23468] Updated weights for policy 0, policy_version 59153 (0.0008) -[2023-10-09 10:39:58,869][23468] Updated weights for policy 0, policy_version 59163 (0.0009) -[2023-10-09 10:39:59,818][23469] Updated weights for policy 1, policy_version 59461 (0.0007) -[2023-10-09 10:40:00,189][23469] Updated weights for policy 1, policy_version 59471 (0.0007) -[2023-10-09 10:40:00,570][23469] Updated weights for policy 1, policy_version 59481 (0.0007) -[2023-10-09 10:40:01,077][22500] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 121503744. Throughput: 0: 1768.4, 1: 1793.5. Samples: 30382872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:40:01,078][22500] Avg episode reward: [(0, '9.450'), (1, '8.310')] -[2023-10-09 10:40:02,742][23468] Updated weights for policy 0, policy_version 59173 (0.0008) -[2023-10-09 10:40:03,106][23468] Updated weights for policy 0, policy_version 59183 (0.0010) -[2023-10-09 10:40:03,478][23468] Updated weights for policy 0, policy_version 59193 (0.0011) -[2023-10-09 10:40:04,175][23469] Updated weights for policy 1, policy_version 59491 (0.0009) -[2023-10-09 10:40:04,550][23469] Updated weights for policy 1, policy_version 59501 (0.0010) -[2023-10-09 10:40:04,916][23469] Updated weights for policy 1, policy_version 59511 (0.0011) -[2023-10-09 10:40:06,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 121569280. Throughput: 0: 1781.8, 1: 1798.2. Samples: 30394534. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:40:06,078][22500] Avg episode reward: [(0, '9.290'), (1, '7.880')] -[2023-10-09 10:40:07,223][23468] Updated weights for policy 0, policy_version 59203 (0.0008) -[2023-10-09 10:40:07,596][23468] Updated weights for policy 0, policy_version 59213 (0.0007) -[2023-10-09 10:40:07,960][23468] Updated weights for policy 0, policy_version 59223 (0.0007) -[2023-10-09 10:40:08,727][23469] Updated weights for policy 1, policy_version 59521 (0.0009) -[2023-10-09 10:40:09,101][23469] Updated weights for policy 1, policy_version 59531 (0.0008) -[2023-10-09 10:40:09,463][23469] Updated weights for policy 1, policy_version 59541 (0.0009) -[2023-10-09 10:40:09,840][23469] Updated weights for policy 1, policy_version 59551 (0.0011) -[2023-10-09 10:40:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 121634816. Throughput: 0: 1769.8, 1: 1796.0. Samples: 30415024. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:40:11,078][22500] Avg episode reward: [(0, '8.870'), (1, '7.910')] -[2023-10-09 10:40:11,613][23468] Updated weights for policy 0, policy_version 59233 (0.0009) -[2023-10-09 10:40:11,988][23468] Updated weights for policy 0, policy_version 59243 (0.0007) -[2023-10-09 10:40:12,356][23468] Updated weights for policy 0, policy_version 59253 (0.0008) -[2023-10-09 10:40:12,732][23468] Updated weights for policy 0, policy_version 59263 (0.0007) -[2023-10-09 10:40:13,630][23469] Updated weights for policy 1, policy_version 59561 (0.0008) -[2023-10-09 10:40:13,996][23469] Updated weights for policy 1, policy_version 59571 (0.0010) -[2023-10-09 10:40:14,362][23469] Updated weights for policy 1, policy_version 59581 (0.0010) -[2023-10-09 10:40:16,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 121700352. Throughput: 0: 1778.3, 1: 1788.3. Samples: 30437454. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:40:16,079][22500] Avg episode reward: [(0, '8.920'), (1, '8.980')] -[2023-10-09 10:40:16,091][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000059584_61014016.pth... -[2023-10-09 10:40:16,125][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000057920_59310080.pth -[2023-10-09 10:40:16,469][23468] Updated weights for policy 0, policy_version 59273 (0.0009) -[2023-10-09 10:40:16,847][23468] Updated weights for policy 0, policy_version 59283 (0.0007) -[2023-10-09 10:40:17,216][23468] Updated weights for policy 0, policy_version 59293 (0.0007) -[2023-10-09 10:40:17,329][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000059296_60719104.pth... -[2023-10-09 10:40:17,358][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000057600_58982400.pth -[2023-10-09 10:40:18,048][23469] Updated weights for policy 1, policy_version 59591 (0.0008) -[2023-10-09 10:40:18,412][23469] Updated weights for policy 1, policy_version 59601 (0.0009) -[2023-10-09 10:40:18,773][23469] Updated weights for policy 1, policy_version 59611 (0.0011) -[2023-10-09 10:40:21,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 121765888. Throughput: 0: 1762.4, 1: 1794.9. Samples: 30447254. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:40:21,078][22500] Avg episode reward: [(0, '8.630'), (1, '8.990')] -[2023-10-09 10:40:21,185][23468] Updated weights for policy 0, policy_version 59303 (0.0007) -[2023-10-09 10:40:21,563][23468] Updated weights for policy 0, policy_version 59313 (0.0007) -[2023-10-09 10:40:21,923][23468] Updated weights for policy 0, policy_version 59323 (0.0009) -[2023-10-09 10:40:22,529][23469] Updated weights for policy 1, policy_version 59621 (0.0008) -[2023-10-09 10:40:22,888][23469] Updated weights for policy 1, policy_version 59631 (0.0007) -[2023-10-09 10:40:23,254][23469] Updated weights for policy 1, policy_version 59641 (0.0007) -[2023-10-09 10:40:25,677][23468] Updated weights for policy 0, policy_version 59333 (0.0008) -[2023-10-09 10:40:26,054][23468] Updated weights for policy 0, policy_version 59343 (0.0012) -[2023-10-09 10:40:26,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 121831424. Throughput: 0: 1766.2, 1: 1794.6. Samples: 30469384. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:40:26,078][22500] Avg episode reward: [(0, '9.400'), (1, '9.220')] -[2023-10-09 10:40:26,435][23468] Updated weights for policy 0, policy_version 59353 (0.0007) -[2023-10-09 10:40:26,922][23469] Updated weights for policy 1, policy_version 59651 (0.0008) -[2023-10-09 10:40:27,294][23469] Updated weights for policy 1, policy_version 59661 (0.0009) -[2023-10-09 10:40:27,673][23469] Updated weights for policy 1, policy_version 59671 (0.0008) -[2023-10-09 10:40:30,343][23468] Updated weights for policy 0, policy_version 59363 (0.0008) -[2023-10-09 10:40:30,725][23468] Updated weights for policy 0, policy_version 59373 (0.0011) -[2023-10-09 10:40:31,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 121896960. Throughput: 0: 1801.8, 1: 1798.1. Samples: 30491784. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:40:31,078][22500] Avg episode reward: [(0, '9.860'), (1, '8.900')] -[2023-10-09 10:40:31,092][23468] Updated weights for policy 0, policy_version 59383 (0.0009) -[2023-10-09 10:40:31,448][23469] Updated weights for policy 1, policy_version 59681 (0.0009) -[2023-10-09 10:40:31,864][23469] Updated weights for policy 1, policy_version 59691 (0.0008) -[2023-10-09 10:40:32,230][23469] Updated weights for policy 1, policy_version 59701 (0.0010) -[2023-10-09 10:40:32,603][23469] Updated weights for policy 1, policy_version 59711 (0.0008) -[2023-10-09 10:40:34,913][23468] Updated weights for policy 0, policy_version 59393 (0.0008) -[2023-10-09 10:40:35,289][23468] Updated weights for policy 0, policy_version 59403 (0.0010) -[2023-10-09 10:40:35,660][23468] Updated weights for policy 0, policy_version 59413 (0.0007) -[2023-10-09 10:40:36,028][23468] Updated weights for policy 0, policy_version 59423 (0.0007) -[2023-10-09 10:40:36,077][22500] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 121995264. Throughput: 0: 1772.0, 1: 1799.7. Samples: 30501418. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:40:36,078][22500] Avg episode reward: [(0, '9.460'), (1, '8.960')] -[2023-10-09 10:40:36,216][23469] Updated weights for policy 1, policy_version 59721 (0.0007) -[2023-10-09 10:40:36,582][23469] Updated weights for policy 1, policy_version 59731 (0.0008) -[2023-10-09 10:40:36,950][23469] Updated weights for policy 1, policy_version 59741 (0.0009) -[2023-10-09 10:40:39,834][23468] Updated weights for policy 0, policy_version 59433 (0.0007) -[2023-10-09 10:40:40,203][23468] Updated weights for policy 0, policy_version 59443 (0.0009) -[2023-10-09 10:40:40,570][23468] Updated weights for policy 0, policy_version 59453 (0.0007) -[2023-10-09 10:40:40,677][23469] Updated weights for policy 1, policy_version 59751 (0.0008) -[2023-10-09 10:40:41,040][23469] Updated weights for policy 1, policy_version 59761 (0.0008) -[2023-10-09 10:40:41,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 122060800. Throughput: 0: 1797.7, 1: 1803.3. Samples: 30524048. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:40:41,078][22500] Avg episode reward: [(0, '8.870'), (1, '8.510')] -[2023-10-09 10:40:41,411][23469] Updated weights for policy 1, policy_version 59771 (0.0009) -[2023-10-09 10:40:44,372][23468] Updated weights for policy 0, policy_version 59463 (0.0009) -[2023-10-09 10:40:44,744][23468] Updated weights for policy 0, policy_version 59473 (0.0007) -[2023-10-09 10:40:45,116][23468] Updated weights for policy 0, policy_version 59483 (0.0008) -[2023-10-09 10:40:45,245][23469] Updated weights for policy 1, policy_version 59781 (0.0008) -[2023-10-09 10:40:45,615][23469] Updated weights for policy 1, policy_version 59791 (0.0010) -[2023-10-09 10:40:45,985][23469] Updated weights for policy 1, policy_version 59801 (0.0010) -[2023-10-09 10:40:46,078][22500] Fps is (10 sec: 13106.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 122126336. Throughput: 0: 1772.6, 1: 1808.8. Samples: 30544032. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:40:46,079][22500] Avg episode reward: [(0, '8.470'), (1, '9.010')] -[2023-10-09 10:40:48,946][23468] Updated weights for policy 0, policy_version 59493 (0.0010) -[2023-10-09 10:40:49,325][23468] Updated weights for policy 0, policy_version 59503 (0.0009) -[2023-10-09 10:40:49,702][23468] Updated weights for policy 0, policy_version 59513 (0.0009) -[2023-10-09 10:40:49,782][23469] Updated weights for policy 1, policy_version 59811 (0.0011) -[2023-10-09 10:40:50,141][23469] Updated weights for policy 1, policy_version 59821 (0.0009) -[2023-10-09 10:40:50,506][23469] Updated weights for policy 1, policy_version 59831 (0.0011) -[2023-10-09 10:40:51,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 122224640. Throughput: 0: 1790.9, 1: 1791.2. Samples: 30555726. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:40:51,078][22500] Avg episode reward: [(0, '8.760'), (1, '8.740')] -[2023-10-09 10:40:53,405][23468] Updated weights for policy 0, policy_version 59523 (0.0007) -[2023-10-09 10:40:53,789][23468] Updated weights for policy 0, policy_version 59533 (0.0009) -[2023-10-09 10:40:54,160][23468] Updated weights for policy 0, policy_version 59543 (0.0011) -[2023-10-09 10:40:54,347][23469] Updated weights for policy 1, policy_version 59841 (0.0009) -[2023-10-09 10:40:54,718][23469] Updated weights for policy 1, policy_version 59851 (0.0008) -[2023-10-09 10:40:55,092][23469] Updated weights for policy 1, policy_version 59861 (0.0008) -[2023-10-09 10:40:55,469][23469] Updated weights for policy 1, policy_version 59871 (0.0008) -[2023-10-09 10:40:56,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 122290176. Throughput: 0: 1775.0, 1: 1811.1. Samples: 30576398. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:40:56,078][22500] Avg episode reward: [(0, '8.800'), (1, '8.800')] -[2023-10-09 10:40:57,907][23468] Updated weights for policy 0, policy_version 59553 (0.0008) -[2023-10-09 10:40:58,278][23468] Updated weights for policy 0, policy_version 59563 (0.0009) -[2023-10-09 10:40:58,647][23468] Updated weights for policy 0, policy_version 59573 (0.0008) -[2023-10-09 10:40:59,021][23468] Updated weights for policy 0, policy_version 59583 (0.0010) -[2023-10-09 10:40:59,075][23469] Updated weights for policy 1, policy_version 59881 (0.0007) -[2023-10-09 10:40:59,436][23469] Updated weights for policy 1, policy_version 59891 (0.0008) -[2023-10-09 10:40:59,811][23469] Updated weights for policy 1, policy_version 59901 (0.0008) -[2023-10-09 10:41:01,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 122355712. Throughput: 0: 1765.7, 1: 1800.2. Samples: 30597920. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:41:01,078][22500] Avg episode reward: [(0, '9.520'), (1, '8.450')] -[2023-10-09 10:41:02,770][23468] Updated weights for policy 0, policy_version 59593 (0.0008) -[2023-10-09 10:41:03,147][23468] Updated weights for policy 0, policy_version 59603 (0.0009) -[2023-10-09 10:41:03,515][23468] Updated weights for policy 0, policy_version 59613 (0.0009) -[2023-10-09 10:41:03,546][23469] Updated weights for policy 1, policy_version 59911 (0.0009) -[2023-10-09 10:41:03,910][23469] Updated weights for policy 1, policy_version 59921 (0.0007) -[2023-10-09 10:41:04,277][23469] Updated weights for policy 1, policy_version 59931 (0.0007) -[2023-10-09 10:41:06,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 122421248. Throughput: 0: 1780.8, 1: 1815.9. Samples: 30609106. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:41:06,079][22500] Avg episode reward: [(0, '9.140'), (1, '8.220')] -[2023-10-09 10:41:07,146][23468] Updated weights for policy 0, policy_version 59623 (0.0009) -[2023-10-09 10:41:07,506][23468] Updated weights for policy 0, policy_version 59633 (0.0007) -[2023-10-09 10:41:07,857][23469] Updated weights for policy 1, policy_version 59941 (0.0010) -[2023-10-09 10:41:07,885][23468] Updated weights for policy 0, policy_version 59643 (0.0007) -[2023-10-09 10:41:08,214][23469] Updated weights for policy 1, policy_version 59951 (0.0009) -[2023-10-09 10:41:08,588][23469] Updated weights for policy 1, policy_version 59961 (0.0010) -[2023-10-09 10:41:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 122486784. Throughput: 0: 1776.5, 1: 1804.7. Samples: 30630538. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:41:11,078][22500] Avg episode reward: [(0, '9.230'), (1, '8.510')] -[2023-10-09 10:41:11,627][23468] Updated weights for policy 0, policy_version 59653 (0.0008) -[2023-10-09 10:41:12,001][23468] Updated weights for policy 0, policy_version 59663 (0.0008) -[2023-10-09 10:41:12,343][23469] Updated weights for policy 1, policy_version 59971 (0.0010) -[2023-10-09 10:41:12,370][23468] Updated weights for policy 0, policy_version 59673 (0.0007) -[2023-10-09 10:41:12,716][23469] Updated weights for policy 1, policy_version 59981 (0.0010) -[2023-10-09 10:41:13,083][23469] Updated weights for policy 1, policy_version 59991 (0.0008) -[2023-10-09 10:41:16,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 122552320. Throughput: 0: 1777.7, 1: 1802.4. Samples: 30652890. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:41:16,078][22500] Avg episode reward: [(0, '9.370'), (1, '8.450')] -[2023-10-09 10:41:16,139][23468] Updated weights for policy 0, policy_version 59683 (0.0007) -[2023-10-09 10:41:16,514][23468] Updated weights for policy 0, policy_version 59693 (0.0009) -[2023-10-09 10:41:16,880][23468] Updated weights for policy 0, policy_version 59703 (0.0008) -[2023-10-09 10:41:16,993][23469] Updated weights for policy 1, policy_version 60001 (0.0010) -[2023-10-09 10:41:17,405][23469] Updated weights for policy 1, policy_version 60011 (0.0009) -[2023-10-09 10:41:17,781][23469] Updated weights for policy 1, policy_version 60021 (0.0009) -[2023-10-09 10:41:18,150][23469] Updated weights for policy 1, policy_version 60031 (0.0008) -[2023-10-09 10:41:20,622][23468] Updated weights for policy 0, policy_version 59713 (0.0008) -[2023-10-09 10:41:20,998][23468] Updated weights for policy 0, policy_version 59723 (0.0007) -[2023-10-09 10:41:21,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 122617856. Throughput: 0: 1775.9, 1: 1802.3. Samples: 30662438. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:41:21,078][22500] Avg episode reward: [(0, '9.540'), (1, '8.980')] -[2023-10-09 10:41:21,368][23468] Updated weights for policy 0, policy_version 59733 (0.0008) -[2023-10-09 10:41:21,737][23468] Updated weights for policy 0, policy_version 59743 (0.0008) -[2023-10-09 10:41:21,774][23469] Updated weights for policy 1, policy_version 60041 (0.0008) -[2023-10-09 10:41:22,144][23469] Updated weights for policy 1, policy_version 60051 (0.0009) -[2023-10-09 10:41:22,517][23469] Updated weights for policy 1, policy_version 60061 (0.0010) -[2023-10-09 10:41:25,514][23468] Updated weights for policy 0, policy_version 59753 (0.0009) -[2023-10-09 10:41:25,884][23468] Updated weights for policy 0, policy_version 59763 (0.0010) -[2023-10-09 10:41:26,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 122683392. Throughput: 0: 1774.7, 1: 1796.3. Samples: 30684748. Policy #0 lag: (min: 31.0, avg: 31.4, max: 46.0) -[2023-10-09 10:41:26,079][22500] Avg episode reward: [(0, '9.690'), (1, '8.140')] -[2023-10-09 10:41:26,188][23469] Updated weights for policy 1, policy_version 60071 (0.0008) -[2023-10-09 10:41:26,268][23468] Updated weights for policy 0, policy_version 59773 (0.0009) -[2023-10-09 10:41:26,557][23469] Updated weights for policy 1, policy_version 60081 (0.0009) -[2023-10-09 10:41:26,922][23469] Updated weights for policy 1, policy_version 60091 (0.0008) -[2023-10-09 10:41:30,050][23468] Updated weights for policy 0, policy_version 59783 (0.0008) -[2023-10-09 10:41:30,427][23468] Updated weights for policy 0, policy_version 59793 (0.0011) -[2023-10-09 10:41:30,705][23469] Updated weights for policy 1, policy_version 60101 (0.0010) -[2023-10-09 10:41:30,797][23468] Updated weights for policy 0, policy_version 59803 (0.0010) -[2023-10-09 10:41:31,066][23469] Updated weights for policy 1, policy_version 60111 (0.0008) -[2023-10-09 10:41:31,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 122781696. Throughput: 0: 1795.0, 1: 1806.6. Samples: 30706106. Policy #0 lag: (min: 31.0, avg: 31.4, max: 46.0) -[2023-10-09 10:41:31,078][22500] Avg episode reward: [(0, '10.220'), (1, '8.930')] -[2023-10-09 10:41:31,435][23469] Updated weights for policy 1, policy_version 60121 (0.0007) -[2023-10-09 10:41:34,618][23468] Updated weights for policy 0, policy_version 59813 (0.0008) -[2023-10-09 10:41:34,994][23468] Updated weights for policy 0, policy_version 59823 (0.0009) -[2023-10-09 10:41:35,132][23469] Updated weights for policy 1, policy_version 60131 (0.0008) -[2023-10-09 10:41:35,364][23468] Updated weights for policy 0, policy_version 59833 (0.0007) -[2023-10-09 10:41:35,500][23469] Updated weights for policy 1, policy_version 60141 (0.0008) -[2023-10-09 10:41:35,873][23469] Updated weights for policy 1, policy_version 60151 (0.0008) -[2023-10-09 10:41:36,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 122847232. Throughput: 0: 1776.5, 1: 1800.0. Samples: 30716666. Policy #0 lag: (min: 31.0, avg: 31.4, max: 46.0) -[2023-10-09 10:41:36,078][22500] Avg episode reward: [(0, '9.500'), (1, '8.570')] -[2023-10-09 10:41:39,171][23468] Updated weights for policy 0, policy_version 59843 (0.0010) -[2023-10-09 10:41:39,542][23468] Updated weights for policy 0, policy_version 59853 (0.0008) -[2023-10-09 10:41:39,584][23469] Updated weights for policy 1, policy_version 60161 (0.0008) -[2023-10-09 10:41:39,922][23468] Updated weights for policy 0, policy_version 59863 (0.0008) -[2023-10-09 10:41:39,955][23469] Updated weights for policy 1, policy_version 60171 (0.0007) -[2023-10-09 10:41:40,318][23469] Updated weights for policy 1, policy_version 60181 (0.0007) -[2023-10-09 10:41:40,690][23469] Updated weights for policy 1, policy_version 60191 (0.0007) -[2023-10-09 10:41:41,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 122945536. Throughput: 0: 1803.9, 1: 1804.9. Samples: 30738792. Policy #0 lag: (min: 31.0, avg: 31.4, max: 46.0) -[2023-10-09 10:41:41,078][22500] Avg episode reward: [(0, '9.830'), (1, '8.670')] -[2023-10-09 10:41:43,703][23468] Updated weights for policy 0, policy_version 59873 (0.0008) -[2023-10-09 10:41:44,074][23468] Updated weights for policy 0, policy_version 59883 (0.0009) -[2023-10-09 10:41:44,450][23468] Updated weights for policy 0, policy_version 59893 (0.0009) -[2023-10-09 10:41:44,565][23469] Updated weights for policy 1, policy_version 60201 (0.0007) -[2023-10-09 10:41:44,825][23468] Updated weights for policy 0, policy_version 59903 (0.0008) -[2023-10-09 10:41:44,936][23469] Updated weights for policy 1, policy_version 60211 (0.0007) -[2023-10-09 10:41:45,309][23469] Updated weights for policy 1, policy_version 60221 (0.0007) -[2023-10-09 10:41:46,078][22500] Fps is (10 sec: 16383.4, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 123011072. Throughput: 0: 1774.8, 1: 1789.5. Samples: 30758314. Policy #0 lag: (min: 31.0, avg: 31.4, max: 46.0) -[2023-10-09 10:41:46,079][22500] Avg episode reward: [(0, '9.200'), (1, '8.130')] -[2023-10-09 10:41:48,591][23468] Updated weights for policy 0, policy_version 59913 (0.0007) -[2023-10-09 10:41:48,959][23468] Updated weights for policy 0, policy_version 59923 (0.0009) -[2023-10-09 10:41:49,116][23469] Updated weights for policy 1, policy_version 60231 (0.0009) -[2023-10-09 10:41:49,335][23468] Updated weights for policy 0, policy_version 59933 (0.0007) -[2023-10-09 10:41:49,482][23469] Updated weights for policy 1, policy_version 60241 (0.0008) -[2023-10-09 10:41:49,853][23469] Updated weights for policy 1, policy_version 60251 (0.0011) -[2023-10-09 10:41:51,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 123076608. Throughput: 0: 1799.8, 1: 1796.5. Samples: 30770940. Policy #0 lag: (min: 31.0, avg: 31.4, max: 46.0) -[2023-10-09 10:41:51,079][22500] Avg episode reward: [(0, '9.000'), (1, '7.650')] -[2023-10-09 10:41:53,063][23468] Updated weights for policy 0, policy_version 59943 (0.0008) -[2023-10-09 10:41:53,429][23468] Updated weights for policy 0, policy_version 59953 (0.0009) -[2023-10-09 10:41:53,676][23469] Updated weights for policy 1, policy_version 60261 (0.0010) -[2023-10-09 10:41:53,807][23468] Updated weights for policy 0, policy_version 59963 (0.0008) -[2023-10-09 10:41:54,046][23469] Updated weights for policy 1, policy_version 60271 (0.0007) -[2023-10-09 10:41:54,415][23469] Updated weights for policy 1, policy_version 60281 (0.0008) -[2023-10-09 10:41:56,077][22500] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 123142144. Throughput: 0: 1775.0, 1: 1778.4. Samples: 30790444. Policy #0 lag: (min: 31.0, avg: 31.4, max: 46.0) -[2023-10-09 10:41:56,078][22500] Avg episode reward: [(0, '8.760'), (1, '7.820')] -[2023-10-09 10:41:57,642][23468] Updated weights for policy 0, policy_version 59973 (0.0009) -[2023-10-09 10:41:57,991][23469] Updated weights for policy 1, policy_version 60291 (0.0007) -[2023-10-09 10:41:58,015][23468] Updated weights for policy 0, policy_version 59983 (0.0009) -[2023-10-09 10:41:58,362][23469] Updated weights for policy 1, policy_version 60301 (0.0008) -[2023-10-09 10:41:58,390][23468] Updated weights for policy 0, policy_version 59993 (0.0008) -[2023-10-09 10:41:58,731][23469] Updated weights for policy 1, policy_version 60311 (0.0007) -[2023-10-09 10:42:01,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 123207680. Throughput: 0: 1772.2, 1: 1778.7. Samples: 30812680. Policy #0 lag: (min: 31.0, avg: 31.4, max: 46.0) -[2023-10-09 10:42:01,078][22500] Avg episode reward: [(0, '8.630'), (1, '8.630')] -[2023-10-09 10:42:02,043][23468] Updated weights for policy 0, policy_version 60003 (0.0008) -[2023-10-09 10:42:02,409][23468] Updated weights for policy 0, policy_version 60013 (0.0008) -[2023-10-09 10:42:02,620][23469] Updated weights for policy 1, policy_version 60321 (0.0008) -[2023-10-09 10:42:02,785][23468] Updated weights for policy 0, policy_version 60023 (0.0009) -[2023-10-09 10:42:03,033][23469] Updated weights for policy 1, policy_version 60331 (0.0007) -[2023-10-09 10:42:03,408][23469] Updated weights for policy 1, policy_version 60341 (0.0007) -[2023-10-09 10:42:03,784][23469] Updated weights for policy 1, policy_version 60351 (0.0008) -[2023-10-09 10:42:06,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 123273216. Throughput: 0: 1770.0, 1: 1783.6. Samples: 30822350. Policy #0 lag: (min: 3.0, avg: 10.3, max: 35.0) -[2023-10-09 10:42:06,079][22500] Avg episode reward: [(0, '9.020'), (1, '8.750')] -[2023-10-09 10:42:06,461][23468] Updated weights for policy 0, policy_version 60033 (0.0009) -[2023-10-09 10:42:06,835][23468] Updated weights for policy 0, policy_version 60043 (0.0009) -[2023-10-09 10:42:07,200][23468] Updated weights for policy 0, policy_version 60053 (0.0007) -[2023-10-09 10:42:07,564][23468] Updated weights for policy 0, policy_version 60063 (0.0008) -[2023-10-09 10:42:07,622][23469] Updated weights for policy 1, policy_version 60361 (0.0009) -[2023-10-09 10:42:07,998][23469] Updated weights for policy 1, policy_version 60371 (0.0009) -[2023-10-09 10:42:08,359][23469] Updated weights for policy 1, policy_version 60381 (0.0008) -[2023-10-09 10:42:11,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 123338752. Throughput: 0: 1779.1, 1: 1775.3. Samples: 30844694. Policy #0 lag: (min: 3.0, avg: 10.3, max: 35.0) -[2023-10-09 10:42:11,079][22500] Avg episode reward: [(0, '9.710'), (1, '9.100')] -[2023-10-09 10:42:11,326][23468] Updated weights for policy 0, policy_version 60073 (0.0008) -[2023-10-09 10:42:11,695][23468] Updated weights for policy 0, policy_version 60083 (0.0008) -[2023-10-09 10:42:12,065][23468] Updated weights for policy 0, policy_version 60093 (0.0009) -[2023-10-09 10:42:12,177][23469] Updated weights for policy 1, policy_version 60391 (0.0008) -[2023-10-09 10:42:12,548][23469] Updated weights for policy 1, policy_version 60401 (0.0007) -[2023-10-09 10:42:12,917][23469] Updated weights for policy 1, policy_version 60411 (0.0008) -[2023-10-09 10:42:15,862][23468] Updated weights for policy 0, policy_version 60103 (0.0009) -[2023-10-09 10:42:16,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 123404288. Throughput: 0: 1795.7, 1: 1784.0. Samples: 30867194. Policy #0 lag: (min: 3.0, avg: 10.3, max: 35.0) -[2023-10-09 10:42:16,078][22500] Avg episode reward: [(0, '9.840'), (1, '9.040')] -[2023-10-09 10:42:16,087][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000060416_61865984.pth... -[2023-10-09 10:42:16,122][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000058752_60162048.pth -[2023-10-09 10:42:16,250][23468] Updated weights for policy 0, policy_version 60113 (0.0010) -[2023-10-09 10:42:16,605][23469] Updated weights for policy 1, policy_version 60421 (0.0010) -[2023-10-09 10:42:16,618][23468] Updated weights for policy 0, policy_version 60123 (0.0009) -[2023-10-09 10:42:16,807][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000060128_61571072.pth... -[2023-10-09 10:42:16,839][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000058432_59834368.pth -[2023-10-09 10:42:16,974][23469] Updated weights for policy 1, policy_version 60431 (0.0007) -[2023-10-09 10:42:17,338][23469] Updated weights for policy 1, policy_version 60441 (0.0009) -[2023-10-09 10:42:20,622][23468] Updated weights for policy 0, policy_version 60133 (0.0009) -[2023-10-09 10:42:20,994][23468] Updated weights for policy 0, policy_version 60143 (0.0011) -[2023-10-09 10:42:21,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 123469824. Throughput: 0: 1783.2, 1: 1775.9. Samples: 30876824. Policy #0 lag: (min: 3.0, avg: 10.3, max: 35.0) -[2023-10-09 10:42:21,078][22500] Avg episode reward: [(0, '9.980'), (1, '8.940')] -[2023-10-09 10:42:21,269][23469] Updated weights for policy 1, policy_version 60451 (0.0009) -[2023-10-09 10:42:21,373][23468] Updated weights for policy 0, policy_version 60153 (0.0008) -[2023-10-09 10:42:21,632][23469] Updated weights for policy 1, policy_version 60461 (0.0009) -[2023-10-09 10:42:22,000][23469] Updated weights for policy 1, policy_version 60471 (0.0010) -[2023-10-09 10:42:25,138][23468] Updated weights for policy 0, policy_version 60163 (0.0008) -[2023-10-09 10:42:25,508][23468] Updated weights for policy 0, policy_version 60173 (0.0010) -[2023-10-09 10:42:25,804][23469] Updated weights for policy 1, policy_version 60481 (0.0009) -[2023-10-09 10:42:25,874][23468] Updated weights for policy 0, policy_version 60183 (0.0009) -[2023-10-09 10:42:26,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 123535360. Throughput: 0: 1780.1, 1: 1779.2. Samples: 30898962. Policy #0 lag: (min: 3.0, avg: 10.3, max: 35.0) -[2023-10-09 10:42:26,079][22500] Avg episode reward: [(0, '10.160'), (1, '8.790')] -[2023-10-09 10:42:26,180][23469] Updated weights for policy 1, policy_version 60491 (0.0008) -[2023-10-09 10:42:26,553][23469] Updated weights for policy 1, policy_version 60501 (0.0008) -[2023-10-09 10:42:26,921][23469] Updated weights for policy 1, policy_version 60511 (0.0008) -[2023-10-09 10:42:29,719][23468] Updated weights for policy 0, policy_version 60193 (0.0008) -[2023-10-09 10:42:30,081][23468] Updated weights for policy 0, policy_version 60203 (0.0009) -[2023-10-09 10:42:30,463][23468] Updated weights for policy 0, policy_version 60213 (0.0008) -[2023-10-09 10:42:30,490][23469] Updated weights for policy 1, policy_version 60521 (0.0007) -[2023-10-09 10:42:30,837][23468] Updated weights for policy 0, policy_version 60223 (0.0008) -[2023-10-09 10:42:30,858][23469] Updated weights for policy 1, policy_version 60531 (0.0009) -[2023-10-09 10:42:31,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 123633664. Throughput: 0: 1797.3, 1: 1795.6. Samples: 30919994. Policy #0 lag: (min: 3.0, avg: 10.3, max: 35.0) -[2023-10-09 10:42:31,078][22500] Avg episode reward: [(0, '10.140'), (1, '8.770')] -[2023-10-09 10:42:31,240][23469] Updated weights for policy 1, policy_version 60541 (0.0009) -[2023-10-09 10:42:34,693][23468] Updated weights for policy 0, policy_version 60233 (0.0008) -[2023-10-09 10:42:34,984][23469] Updated weights for policy 1, policy_version 60551 (0.0008) -[2023-10-09 10:42:35,061][23468] Updated weights for policy 0, policy_version 60243 (0.0008) -[2023-10-09 10:42:35,350][23469] Updated weights for policy 1, policy_version 60561 (0.0009) -[2023-10-09 10:42:35,443][23468] Updated weights for policy 0, policy_version 60253 (0.0008) -[2023-10-09 10:42:35,728][23469] Updated weights for policy 1, policy_version 60571 (0.0007) -[2023-10-09 10:42:36,077][22500] Fps is (10 sec: 19661.3, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 123731968. Throughput: 0: 1780.3, 1: 1783.0. Samples: 30931288. Policy #0 lag: (min: 3.0, avg: 10.3, max: 35.0) -[2023-10-09 10:42:36,078][22500] Avg episode reward: [(0, '9.230'), (1, '8.880')] -[2023-10-09 10:42:39,100][23468] Updated weights for policy 0, policy_version 60263 (0.0009) -[2023-10-09 10:42:39,421][23469] Updated weights for policy 1, policy_version 60581 (0.0007) -[2023-10-09 10:42:39,466][23468] Updated weights for policy 0, policy_version 60273 (0.0009) -[2023-10-09 10:42:39,785][23469] Updated weights for policy 1, policy_version 60591 (0.0008) -[2023-10-09 10:42:39,843][23468] Updated weights for policy 0, policy_version 60283 (0.0008) -[2023-10-09 10:42:40,161][23469] Updated weights for policy 1, policy_version 60601 (0.0008) -[2023-10-09 10:42:41,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 123797504. Throughput: 0: 1801.8, 1: 1804.9. Samples: 30952746. Policy #0 lag: (min: 3.0, avg: 10.3, max: 35.0) -[2023-10-09 10:42:41,078][22500] Avg episode reward: [(0, '9.280'), (1, '8.770')] -[2023-10-09 10:42:43,572][23468] Updated weights for policy 0, policy_version 60293 (0.0010) -[2023-10-09 10:42:43,805][23469] Updated weights for policy 1, policy_version 60611 (0.0009) -[2023-10-09 10:42:43,935][23468] Updated weights for policy 0, policy_version 60303 (0.0008) -[2023-10-09 10:42:44,174][23469] Updated weights for policy 1, policy_version 60621 (0.0007) -[2023-10-09 10:42:44,308][23468] Updated weights for policy 0, policy_version 60313 (0.0007) -[2023-10-09 10:42:44,544][23469] Updated weights for policy 1, policy_version 60631 (0.0009) -[2023-10-09 10:42:46,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 123863040. Throughput: 0: 1784.3, 1: 1788.4. Samples: 30973452. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:42:46,079][22500] Avg episode reward: [(0, '8.970'), (1, '9.090')] -[2023-10-09 10:42:48,024][23468] Updated weights for policy 0, policy_version 60323 (0.0009) -[2023-10-09 10:42:48,318][23469] Updated weights for policy 1, policy_version 60641 (0.0010) -[2023-10-09 10:42:48,399][23468] Updated weights for policy 0, policy_version 60333 (0.0010) -[2023-10-09 10:42:48,705][23469] Updated weights for policy 1, policy_version 60651 (0.0007) -[2023-10-09 10:42:48,766][23468] Updated weights for policy 0, policy_version 60343 (0.0009) -[2023-10-09 10:42:49,068][23469] Updated weights for policy 1, policy_version 60661 (0.0008) -[2023-10-09 10:42:49,439][23469] Updated weights for policy 1, policy_version 60671 (0.0009) -[2023-10-09 10:42:51,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 123928576. Throughput: 0: 1807.1, 1: 1806.5. Samples: 30984958. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:42:51,078][22500] Avg episode reward: [(0, '9.910'), (1, '9.350')] -[2023-10-09 10:42:52,407][23468] Updated weights for policy 0, policy_version 60353 (0.0009) -[2023-10-09 10:42:52,786][23468] Updated weights for policy 0, policy_version 60363 (0.0009) -[2023-10-09 10:42:53,158][23468] Updated weights for policy 0, policy_version 60373 (0.0007) -[2023-10-09 10:42:53,214][23469] Updated weights for policy 1, policy_version 60681 (0.0008) -[2023-10-09 10:42:53,543][23468] Updated weights for policy 0, policy_version 60383 (0.0008) -[2023-10-09 10:42:53,582][23469] Updated weights for policy 1, policy_version 60691 (0.0009) -[2023-10-09 10:42:53,959][23469] Updated weights for policy 1, policy_version 60701 (0.0008) -[2023-10-09 10:42:56,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 123994112. Throughput: 0: 1781.0, 1: 1792.3. Samples: 31005492. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:42:56,078][22500] Avg episode reward: [(0, '10.090'), (1, '9.230')] -[2023-10-09 10:42:57,339][23468] Updated weights for policy 0, policy_version 60393 (0.0009) -[2023-10-09 10:42:57,687][23469] Updated weights for policy 1, policy_version 60711 (0.0009) -[2023-10-09 10:42:57,718][23468] Updated weights for policy 0, policy_version 60403 (0.0008) -[2023-10-09 10:42:58,057][23469] Updated weights for policy 1, policy_version 60721 (0.0007) -[2023-10-09 10:42:58,093][23468] Updated weights for policy 0, policy_version 60413 (0.0010) -[2023-10-09 10:42:58,431][23469] Updated weights for policy 1, policy_version 60731 (0.0007) -[2023-10-09 10:43:01,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 124059648. Throughput: 0: 1772.0, 1: 1792.5. Samples: 31027598. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:43:01,079][22500] Avg episode reward: [(0, '10.030'), (1, '9.300')] -[2023-10-09 10:43:02,156][23468] Updated weights for policy 0, policy_version 60423 (0.0009) -[2023-10-09 10:43:02,374][23469] Updated weights for policy 1, policy_version 60741 (0.0008) -[2023-10-09 10:43:02,533][23468] Updated weights for policy 0, policy_version 60433 (0.0008) -[2023-10-09 10:43:02,733][23469] Updated weights for policy 1, policy_version 60751 (0.0007) -[2023-10-09 10:43:02,903][23468] Updated weights for policy 0, policy_version 60443 (0.0008) -[2023-10-09 10:43:03,104][23469] Updated weights for policy 1, policy_version 60761 (0.0007) -[2023-10-09 10:43:06,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 124125184. Throughput: 0: 1769.0, 1: 1789.9. Samples: 31036974. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:43:06,078][22500] Avg episode reward: [(0, '9.380'), (1, '8.750')] -[2023-10-09 10:43:06,654][23468] Updated weights for policy 0, policy_version 60453 (0.0010) -[2023-10-09 10:43:06,880][23469] Updated weights for policy 1, policy_version 60771 (0.0008) -[2023-10-09 10:43:07,029][23468] Updated weights for policy 0, policy_version 60463 (0.0008) -[2023-10-09 10:43:07,246][23469] Updated weights for policy 1, policy_version 60781 (0.0010) -[2023-10-09 10:43:07,407][23468] Updated weights for policy 0, policy_version 60473 (0.0008) -[2023-10-09 10:43:07,615][23469] Updated weights for policy 1, policy_version 60791 (0.0008) -[2023-10-09 10:43:11,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 124190720. Throughput: 0: 1768.5, 1: 1789.2. Samples: 31059060. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:43:11,078][22500] Avg episode reward: [(0, '9.200'), (1, '8.280')] -[2023-10-09 10:43:11,176][23468] Updated weights for policy 0, policy_version 60483 (0.0008) -[2023-10-09 10:43:11,324][23469] Updated weights for policy 1, policy_version 60801 (0.0011) -[2023-10-09 10:43:11,551][23468] Updated weights for policy 0, policy_version 60493 (0.0007) -[2023-10-09 10:43:11,684][23469] Updated weights for policy 1, policy_version 60811 (0.0009) -[2023-10-09 10:43:11,921][23468] Updated weights for policy 0, policy_version 60503 (0.0008) -[2023-10-09 10:43:12,051][23469] Updated weights for policy 1, policy_version 60821 (0.0007) -[2023-10-09 10:43:12,431][23469] Updated weights for policy 1, policy_version 60831 (0.0008) -[2023-10-09 10:43:15,818][23468] Updated weights for policy 0, policy_version 60513 (0.0007) -[2023-10-09 10:43:16,078][22500] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 124256256. Throughput: 0: 1782.7, 1: 1810.3. Samples: 31081678. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:43:16,079][22500] Avg episode reward: [(0, '9.240'), (1, '8.960')] -[2023-10-09 10:43:16,121][23469] Updated weights for policy 1, policy_version 60841 (0.0009) -[2023-10-09 10:43:16,194][23468] Updated weights for policy 0, policy_version 60523 (0.0007) -[2023-10-09 10:43:16,497][23469] Updated weights for policy 1, policy_version 60851 (0.0008) -[2023-10-09 10:43:16,563][23468] Updated weights for policy 0, policy_version 60533 (0.0008) -[2023-10-09 10:43:16,859][23469] Updated weights for policy 1, policy_version 60861 (0.0008) -[2023-10-09 10:43:16,929][23468] Updated weights for policy 0, policy_version 60543 (0.0008) -[2023-10-09 10:43:20,411][23468] Updated weights for policy 0, policy_version 60553 (0.0008) -[2023-10-09 10:43:20,523][23469] Updated weights for policy 1, policy_version 60871 (0.0008) -[2023-10-09 10:43:20,785][23468] Updated weights for policy 0, policy_version 60563 (0.0008) -[2023-10-09 10:43:20,894][23469] Updated weights for policy 1, policy_version 60881 (0.0009) -[2023-10-09 10:43:21,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 124321792. Throughput: 0: 1769.2, 1: 1793.0. Samples: 31091584. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:43:21,078][22500] Avg episode reward: [(0, '9.640'), (1, '8.580')] -[2023-10-09 10:43:21,146][23468] Updated weights for policy 0, policy_version 60573 (0.0008) -[2023-10-09 10:43:21,262][23469] Updated weights for policy 1, policy_version 60891 (0.0008) -[2023-10-09 10:43:25,003][23468] Updated weights for policy 0, policy_version 60583 (0.0009) -[2023-10-09 10:43:25,061][23469] Updated weights for policy 1, policy_version 60901 (0.0009) -[2023-10-09 10:43:25,379][23468] Updated weights for policy 0, policy_version 60593 (0.0007) -[2023-10-09 10:43:25,419][23469] Updated weights for policy 1, policy_version 60911 (0.0010) -[2023-10-09 10:43:25,747][23468] Updated weights for policy 0, policy_version 60603 (0.0009) -[2023-10-09 10:43:25,796][23469] Updated weights for policy 1, policy_version 60921 (0.0009) -[2023-10-09 10:43:26,077][22500] Fps is (10 sec: 19661.2, 60 sec: 15291.7, 300 sec: 14440.1). Total num frames: 124452864. Throughput: 0: 1777.8, 1: 1807.4. Samples: 31114078. Policy #0 lag: (min: 9.0, avg: 14.7, max: 41.0) -[2023-10-09 10:43:26,079][22500] Avg episode reward: [(0, '9.380'), (1, '8.720')] -[2023-10-09 10:43:29,612][23468] Updated weights for policy 0, policy_version 60613 (0.0008) -[2023-10-09 10:43:29,678][23469] Updated weights for policy 1, policy_version 60931 (0.0008) -[2023-10-09 10:43:29,979][23468] Updated weights for policy 0, policy_version 60623 (0.0009) -[2023-10-09 10:43:30,043][23469] Updated weights for policy 1, policy_version 60941 (0.0008) -[2023-10-09 10:43:30,352][23468] Updated weights for policy 0, policy_version 60633 (0.0009) -[2023-10-09 10:43:30,416][23469] Updated weights for policy 1, policy_version 60951 (0.0007) -[2023-10-09 10:43:31,077][22500] Fps is (10 sec: 19660.5, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 124518400. Throughput: 0: 1770.5, 1: 1789.8. Samples: 31133668. Policy #0 lag: (min: 9.0, avg: 14.7, max: 41.0) -[2023-10-09 10:43:31,078][22500] Avg episode reward: [(0, '9.650'), (1, '8.490')] -[2023-10-09 10:43:34,129][23469] Updated weights for policy 1, policy_version 60961 (0.0009) -[2023-10-09 10:43:34,272][23468] Updated weights for policy 0, policy_version 60643 (0.0008) -[2023-10-09 10:43:34,496][23469] Updated weights for policy 1, policy_version 60971 (0.0009) -[2023-10-09 10:43:34,638][23468] Updated weights for policy 0, policy_version 60653 (0.0007) -[2023-10-09 10:43:34,875][23469] Updated weights for policy 1, policy_version 60981 (0.0008) -[2023-10-09 10:43:35,004][23468] Updated weights for policy 0, policy_version 60663 (0.0008) -[2023-10-09 10:43:35,238][23469] Updated weights for policy 1, policy_version 60991 (0.0007) -[2023-10-09 10:43:36,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 124583936. Throughput: 0: 1771.9, 1: 1803.0. Samples: 31145826. Policy #0 lag: (min: 9.0, avg: 14.7, max: 41.0) -[2023-10-09 10:43:36,078][22500] Avg episode reward: [(0, '9.330'), (1, '8.660')] -[2023-10-09 10:43:38,736][23468] Updated weights for policy 0, policy_version 60673 (0.0007) -[2023-10-09 10:43:39,045][23469] Updated weights for policy 1, policy_version 61001 (0.0008) -[2023-10-09 10:43:39,104][23468] Updated weights for policy 0, policy_version 60683 (0.0009) -[2023-10-09 10:43:39,413][23469] Updated weights for policy 1, policy_version 61011 (0.0007) -[2023-10-09 10:43:39,465][23468] Updated weights for policy 0, policy_version 60693 (0.0009) -[2023-10-09 10:43:39,779][23469] Updated weights for policy 1, policy_version 61021 (0.0007) -[2023-10-09 10:43:39,846][23468] Updated weights for policy 0, policy_version 60703 (0.0007) -[2023-10-09 10:43:41,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 124649472. Throughput: 0: 1774.4, 1: 1790.2. Samples: 31165896. Policy #0 lag: (min: 9.0, avg: 14.7, max: 41.0) -[2023-10-09 10:43:41,078][22500] Avg episode reward: [(0, '9.110'), (1, '8.260')] -[2023-10-09 10:43:43,557][23469] Updated weights for policy 1, policy_version 61031 (0.0008) -[2023-10-09 10:43:43,651][23468] Updated weights for policy 0, policy_version 60713 (0.0008) -[2023-10-09 10:43:43,929][23469] Updated weights for policy 1, policy_version 61041 (0.0009) -[2023-10-09 10:43:44,022][23468] Updated weights for policy 0, policy_version 60723 (0.0007) -[2023-10-09 10:43:44,299][23469] Updated weights for policy 1, policy_version 61051 (0.0008) -[2023-10-09 10:43:44,397][23468] Updated weights for policy 0, policy_version 60733 (0.0007) -[2023-10-09 10:43:46,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 124715008. Throughput: 0: 1766.6, 1: 1781.4. Samples: 31187260. Policy #0 lag: (min: 9.0, avg: 14.7, max: 41.0) -[2023-10-09 10:43:46,079][22500] Avg episode reward: [(0, '8.700'), (1, '8.890')] -[2023-10-09 10:43:48,063][23469] Updated weights for policy 1, policy_version 61061 (0.0008) -[2023-10-09 10:43:48,377][23468] Updated weights for policy 0, policy_version 60743 (0.0008) -[2023-10-09 10:43:48,425][23469] Updated weights for policy 1, policy_version 61071 (0.0007) -[2023-10-09 10:43:48,760][23468] Updated weights for policy 0, policy_version 60753 (0.0007) -[2023-10-09 10:43:48,799][23469] Updated weights for policy 1, policy_version 61081 (0.0007) -[2023-10-09 10:43:49,129][23468] Updated weights for policy 0, policy_version 60763 (0.0008) -[2023-10-09 10:43:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 124780544. Throughput: 0: 1794.6, 1: 1793.7. Samples: 31198448. Policy #0 lag: (min: 9.0, avg: 14.7, max: 41.0) -[2023-10-09 10:43:51,078][22500] Avg episode reward: [(0, '8.520'), (1, '8.730')] -[2023-10-09 10:43:52,655][23469] Updated weights for policy 1, policy_version 61091 (0.0008) -[2023-10-09 10:43:52,750][23468] Updated weights for policy 0, policy_version 60773 (0.0007) -[2023-10-09 10:43:53,026][23469] Updated weights for policy 1, policy_version 61101 (0.0007) -[2023-10-09 10:43:53,109][23468] Updated weights for policy 0, policy_version 60783 (0.0007) -[2023-10-09 10:43:53,398][23469] Updated weights for policy 1, policy_version 61111 (0.0008) -[2023-10-09 10:43:53,489][23468] Updated weights for policy 0, policy_version 60793 (0.0008) -[2023-10-09 10:43:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 124846080. Throughput: 0: 1769.9, 1: 1788.5. Samples: 31219186. Policy #0 lag: (min: 9.0, avg: 14.7, max: 41.0) -[2023-10-09 10:43:56,078][22500] Avg episode reward: [(0, '8.590'), (1, '9.350')] -[2023-10-09 10:43:57,108][23469] Updated weights for policy 1, policy_version 61121 (0.0009) -[2023-10-09 10:43:57,346][23468] Updated weights for policy 0, policy_version 60803 (0.0008) -[2023-10-09 10:43:57,473][23469] Updated weights for policy 1, policy_version 61131 (0.0008) -[2023-10-09 10:43:57,733][23468] Updated weights for policy 0, policy_version 60813 (0.0008) -[2023-10-09 10:43:57,853][23469] Updated weights for policy 1, policy_version 61141 (0.0009) -[2023-10-09 10:43:58,099][23468] Updated weights for policy 0, policy_version 60823 (0.0008) -[2023-10-09 10:43:58,215][23469] Updated weights for policy 1, policy_version 61151 (0.0010) -[2023-10-09 10:44:01,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 124911616. Throughput: 0: 1767.6, 1: 1782.5. Samples: 31241434. Policy #0 lag: (min: 9.0, avg: 14.7, max: 41.0) -[2023-10-09 10:44:01,078][22500] Avg episode reward: [(0, '9.630'), (1, '9.000')] -[2023-10-09 10:44:01,861][23468] Updated weights for policy 0, policy_version 60833 (0.0009) -[2023-10-09 10:44:01,985][23469] Updated weights for policy 1, policy_version 61161 (0.0008) -[2023-10-09 10:44:02,231][23468] Updated weights for policy 0, policy_version 60843 (0.0008) -[2023-10-09 10:44:02,347][23469] Updated weights for policy 1, policy_version 61171 (0.0007) -[2023-10-09 10:44:02,602][23468] Updated weights for policy 0, policy_version 60853 (0.0008) -[2023-10-09 10:44:02,726][23469] Updated weights for policy 1, policy_version 61181 (0.0009) -[2023-10-09 10:44:02,975][23468] Updated weights for policy 0, policy_version 60863 (0.0008) -[2023-10-09 10:44:06,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 124977152. Throughput: 0: 1762.4, 1: 1784.5. Samples: 31251194. Policy #0 lag: (min: 9.0, avg: 14.7, max: 41.0) -[2023-10-09 10:44:06,078][22500] Avg episode reward: [(0, '9.320'), (1, '9.220')] -[2023-10-09 10:44:06,488][23469] Updated weights for policy 1, policy_version 61191 (0.0009) -[2023-10-09 10:44:06,795][23468] Updated weights for policy 0, policy_version 60873 (0.0009) -[2023-10-09 10:44:06,855][23469] Updated weights for policy 1, policy_version 61201 (0.0008) -[2023-10-09 10:44:07,165][23468] Updated weights for policy 0, policy_version 60883 (0.0009) -[2023-10-09 10:44:07,220][23469] Updated weights for policy 1, policy_version 61211 (0.0008) -[2023-10-09 10:44:07,536][23468] Updated weights for policy 0, policy_version 60893 (0.0008) -[2023-10-09 10:44:11,057][23469] Updated weights for policy 1, policy_version 61221 (0.0008) -[2023-10-09 10:44:11,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 125042688. Throughput: 0: 1758.3, 1: 1781.0. Samples: 31273348. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-09 10:44:11,078][22500] Avg episode reward: [(0, '9.050'), (1, '8.580')] -[2023-10-09 10:44:11,144][23468] Updated weights for policy 0, policy_version 60903 (0.0008) -[2023-10-09 10:44:11,428][23469] Updated weights for policy 1, policy_version 61231 (0.0007) -[2023-10-09 10:44:11,517][23468] Updated weights for policy 0, policy_version 60913 (0.0007) -[2023-10-09 10:44:11,793][23469] Updated weights for policy 1, policy_version 61241 (0.0009) -[2023-10-09 10:44:11,887][23468] Updated weights for policy 0, policy_version 60923 (0.0008) -[2023-10-09 10:44:15,210][23469] Updated weights for policy 1, policy_version 61251 (0.0009) -[2023-10-09 10:44:15,581][23469] Updated weights for policy 1, policy_version 61261 (0.0009) -[2023-10-09 10:44:15,883][23468] Updated weights for policy 0, policy_version 60933 (0.0008) -[2023-10-09 10:44:15,962][23469] Updated weights for policy 1, policy_version 61271 (0.0007) -[2023-10-09 10:44:16,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 125108224. Throughput: 0: 1786.4, 1: 1804.4. Samples: 31295254. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-09 10:44:16,078][22500] Avg episode reward: [(0, '9.510'), (1, '8.850')] -[2023-10-09 10:44:16,254][23468] Updated weights for policy 0, policy_version 60943 (0.0008) -[2023-10-09 10:44:16,291][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000061280_62750720.pth... -[2023-10-09 10:44:16,320][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000059584_61014016.pth -[2023-10-09 10:44:16,632][23468] Updated weights for policy 0, policy_version 60953 (0.0009) -[2023-10-09 10:44:16,891][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000060960_62423040.pth... -[2023-10-09 10:44:16,920][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000059296_60719104.pth -[2023-10-09 10:44:19,805][23469] Updated weights for policy 1, policy_version 61281 (0.0008) -[2023-10-09 10:44:20,215][23469] Updated weights for policy 1, policy_version 61291 (0.0008) -[2023-10-09 10:44:20,356][23468] Updated weights for policy 0, policy_version 60963 (0.0008) -[2023-10-09 10:44:20,586][23469] Updated weights for policy 1, policy_version 61301 (0.0008) -[2023-10-09 10:44:20,730][23468] Updated weights for policy 0, policy_version 60973 (0.0008) -[2023-10-09 10:44:20,949][23469] Updated weights for policy 1, policy_version 61311 (0.0008) -[2023-10-09 10:44:21,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 125206528. Throughput: 0: 1762.6, 1: 1790.8. Samples: 31305728. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-09 10:44:21,079][22500] Avg episode reward: [(0, '8.510'), (1, '9.010')] -[2023-10-09 10:44:21,107][23468] Updated weights for policy 0, policy_version 60983 (0.0009) -[2023-10-09 10:44:24,781][23469] Updated weights for policy 1, policy_version 61321 (0.0009) -[2023-10-09 10:44:24,935][23468] Updated weights for policy 0, policy_version 60993 (0.0007) -[2023-10-09 10:44:25,160][23469] Updated weights for policy 1, policy_version 61331 (0.0008) -[2023-10-09 10:44:25,302][23468] Updated weights for policy 0, policy_version 61003 (0.0008) -[2023-10-09 10:44:25,530][23469] Updated weights for policy 1, policy_version 61341 (0.0008) -[2023-10-09 10:44:25,673][23468] Updated weights for policy 0, policy_version 61013 (0.0009) -[2023-10-09 10:44:26,051][23468] Updated weights for policy 0, policy_version 61023 (0.0008) -[2023-10-09 10:44:26,077][22500] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 14329.1). Total num frames: 125272064. Throughput: 0: 1779.6, 1: 1808.1. Samples: 31327344. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-09 10:44:26,079][22500] Avg episode reward: [(0, '8.700'), (1, '8.640')] -[2023-10-09 10:44:29,287][23469] Updated weights for policy 1, policy_version 61351 (0.0010) -[2023-10-09 10:44:29,668][23469] Updated weights for policy 1, policy_version 61361 (0.0008) -[2023-10-09 10:44:29,831][23468] Updated weights for policy 0, policy_version 61033 (0.0009) -[2023-10-09 10:44:30,041][23469] Updated weights for policy 1, policy_version 61371 (0.0009) -[2023-10-09 10:44:30,203][23468] Updated weights for policy 0, policy_version 61043 (0.0007) -[2023-10-09 10:44:30,574][23468] Updated weights for policy 0, policy_version 61053 (0.0007) -[2023-10-09 10:44:31,078][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 125370368. Throughput: 0: 1773.6, 1: 1793.1. Samples: 31347762. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-09 10:44:31,079][22500] Avg episode reward: [(0, '8.730'), (1, '9.210')] -[2023-10-09 10:44:33,615][23469] Updated weights for policy 1, policy_version 61381 (0.0008) -[2023-10-09 10:44:33,983][23469] Updated weights for policy 1, policy_version 61391 (0.0010) -[2023-10-09 10:44:34,356][23469] Updated weights for policy 1, policy_version 61401 (0.0010) -[2023-10-09 10:44:34,360][23468] Updated weights for policy 0, policy_version 61063 (0.0009) -[2023-10-09 10:44:34,748][23468] Updated weights for policy 0, policy_version 61073 (0.0009) -[2023-10-09 10:44:35,120][23468] Updated weights for policy 0, policy_version 61083 (0.0010) -[2023-10-09 10:44:36,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 125435904. Throughput: 0: 1772.1, 1: 1809.2. Samples: 31359610. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-09 10:44:36,079][22500] Avg episode reward: [(0, '9.410'), (1, '9.030')] -[2023-10-09 10:44:38,018][23469] Updated weights for policy 1, policy_version 61411 (0.0007) -[2023-10-09 10:44:38,391][23469] Updated weights for policy 1, policy_version 61421 (0.0009) -[2023-10-09 10:44:38,699][23468] Updated weights for policy 0, policy_version 61093 (0.0009) -[2023-10-09 10:44:38,758][23469] Updated weights for policy 1, policy_version 61431 (0.0007) -[2023-10-09 10:44:39,066][23468] Updated weights for policy 0, policy_version 61103 (0.0009) -[2023-10-09 10:44:39,430][23468] Updated weights for policy 0, policy_version 61113 (0.0007) -[2023-10-09 10:44:41,077][22500] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 125501440. Throughput: 0: 1786.5, 1: 1795.4. Samples: 31380372. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-09 10:44:41,078][22500] Avg episode reward: [(0, '9.610'), (1, '9.340')] -[2023-10-09 10:44:42,521][23469] Updated weights for policy 1, policy_version 61441 (0.0007) -[2023-10-09 10:44:42,892][23469] Updated weights for policy 1, policy_version 61451 (0.0010) -[2023-10-09 10:44:43,243][23468] Updated weights for policy 0, policy_version 61123 (0.0007) -[2023-10-09 10:44:43,265][23469] Updated weights for policy 1, policy_version 61461 (0.0009) -[2023-10-09 10:44:43,619][23468] Updated weights for policy 0, policy_version 61133 (0.0007) -[2023-10-09 10:44:43,642][23469] Updated weights for policy 1, policy_version 61471 (0.0008) -[2023-10-09 10:44:43,991][23468] Updated weights for policy 0, policy_version 61143 (0.0008) -[2023-10-09 10:44:46,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 125566976. Throughput: 0: 1779.4, 1: 1792.2. Samples: 31402158. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-09 10:44:46,079][22500] Avg episode reward: [(0, '9.270'), (1, '8.840')] -[2023-10-09 10:44:47,399][23469] Updated weights for policy 1, policy_version 61481 (0.0007) -[2023-10-09 10:44:47,639][23468] Updated weights for policy 0, policy_version 61153 (0.0009) -[2023-10-09 10:44:47,761][23469] Updated weights for policy 1, policy_version 61491 (0.0009) -[2023-10-09 10:44:48,013][23468] Updated weights for policy 0, policy_version 61163 (0.0008) -[2023-10-09 10:44:48,135][23469] Updated weights for policy 1, policy_version 61501 (0.0007) -[2023-10-09 10:44:48,391][23468] Updated weights for policy 0, policy_version 61173 (0.0009) -[2023-10-09 10:44:48,766][23468] Updated weights for policy 0, policy_version 61183 (0.0007) -[2023-10-09 10:44:51,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 125632512. Throughput: 0: 1796.2, 1: 1792.5. Samples: 31412684. Policy #0 lag: (min: 3.0, avg: 18.3, max: 35.0) -[2023-10-09 10:44:51,078][22500] Avg episode reward: [(0, '9.380'), (1, '9.070')] -[2023-10-09 10:44:51,945][23469] Updated weights for policy 1, policy_version 61511 (0.0010) -[2023-10-09 10:44:52,313][23469] Updated weights for policy 1, policy_version 61521 (0.0008) -[2023-10-09 10:44:52,583][23468] Updated weights for policy 0, policy_version 61193 (0.0008) -[2023-10-09 10:44:52,689][23469] Updated weights for policy 1, policy_version 61531 (0.0008) -[2023-10-09 10:44:52,956][23468] Updated weights for policy 0, policy_version 61203 (0.0008) -[2023-10-09 10:44:53,333][23468] Updated weights for policy 0, policy_version 61213 (0.0009) -[2023-10-09 10:44:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 125698048. Throughput: 0: 1782.2, 1: 1796.9. Samples: 31434410. Policy #0 lag: (min: 3.0, avg: 18.3, max: 35.0) -[2023-10-09 10:44:56,078][22500] Avg episode reward: [(0, '9.570'), (1, '8.260')] -[2023-10-09 10:44:56,518][23469] Updated weights for policy 1, policy_version 61541 (0.0007) -[2023-10-09 10:44:56,895][23469] Updated weights for policy 1, policy_version 61551 (0.0008) -[2023-10-09 10:44:57,097][23468] Updated weights for policy 0, policy_version 61223 (0.0008) -[2023-10-09 10:44:57,272][23469] Updated weights for policy 1, policy_version 61561 (0.0007) -[2023-10-09 10:44:57,479][23468] Updated weights for policy 0, policy_version 61233 (0.0008) -[2023-10-09 10:44:57,849][23468] Updated weights for policy 0, policy_version 61243 (0.0008) -[2023-10-09 10:45:00,953][23469] Updated weights for policy 1, policy_version 61571 (0.0008) -[2023-10-09 10:45:01,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 125763584. Throughput: 0: 1786.8, 1: 1810.2. Samples: 31457118. Policy #0 lag: (min: 3.0, avg: 18.3, max: 35.0) -[2023-10-09 10:45:01,079][22500] Avg episode reward: [(0, '9.640'), (1, '8.300')] -[2023-10-09 10:45:01,329][23469] Updated weights for policy 1, policy_version 61581 (0.0009) -[2023-10-09 10:45:01,587][23468] Updated weights for policy 0, policy_version 61253 (0.0007) -[2023-10-09 10:45:01,700][23469] Updated weights for policy 1, policy_version 61591 (0.0007) -[2023-10-09 10:45:01,955][23468] Updated weights for policy 0, policy_version 61263 (0.0008) -[2023-10-09 10:45:02,338][23468] Updated weights for policy 0, policy_version 61273 (0.0010) -[2023-10-09 10:45:05,509][23469] Updated weights for policy 1, policy_version 61601 (0.0009) -[2023-10-09 10:45:05,926][23469] Updated weights for policy 1, policy_version 61611 (0.0010) -[2023-10-09 10:45:06,074][23468] Updated weights for policy 0, policy_version 61283 (0.0010) -[2023-10-09 10:45:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 125829120. Throughput: 0: 1786.8, 1: 1790.8. Samples: 31466720. Policy #0 lag: (min: 3.0, avg: 18.3, max: 35.0) -[2023-10-09 10:45:06,078][22500] Avg episode reward: [(0, '9.530'), (1, '8.370')] -[2023-10-09 10:45:06,299][23469] Updated weights for policy 1, policy_version 61621 (0.0009) -[2023-10-09 10:45:06,453][23468] Updated weights for policy 0, policy_version 61293 (0.0008) -[2023-10-09 10:45:06,664][23469] Updated weights for policy 1, policy_version 61631 (0.0007) -[2023-10-09 10:45:06,828][23468] Updated weights for policy 0, policy_version 61303 (0.0007) -[2023-10-09 10:45:10,317][23469] Updated weights for policy 1, policy_version 61641 (0.0009) -[2023-10-09 10:45:10,611][23468] Updated weights for policy 0, policy_version 61313 (0.0008) -[2023-10-09 10:45:10,676][23469] Updated weights for policy 1, policy_version 61651 (0.0008) -[2023-10-09 10:45:10,981][23468] Updated weights for policy 0, policy_version 61323 (0.0009) -[2023-10-09 10:45:11,047][23469] Updated weights for policy 1, policy_version 61661 (0.0009) -[2023-10-09 10:45:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 125894656. Throughput: 0: 1787.2, 1: 1804.9. Samples: 31488986. Policy #0 lag: (min: 3.0, avg: 18.3, max: 35.0) -[2023-10-09 10:45:11,078][22500] Avg episode reward: [(0, '9.280'), (1, '8.810')] -[2023-10-09 10:45:11,350][23468] Updated weights for policy 0, policy_version 61333 (0.0007) -[2023-10-09 10:45:11,730][23468] Updated weights for policy 0, policy_version 61343 (0.0010) -[2023-10-09 10:45:14,760][23469] Updated weights for policy 1, policy_version 61671 (0.0010) -[2023-10-09 10:45:15,133][23469] Updated weights for policy 1, policy_version 61681 (0.0010) -[2023-10-09 10:45:15,501][23469] Updated weights for policy 1, policy_version 61691 (0.0010) -[2023-10-09 10:45:15,542][23468] Updated weights for policy 0, policy_version 61353 (0.0010) -[2023-10-09 10:45:15,912][23468] Updated weights for policy 0, policy_version 61363 (0.0009) -[2023-10-09 10:45:16,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 125992960. Throughput: 0: 1804.1, 1: 1794.6. Samples: 31509706. Policy #0 lag: (min: 3.0, avg: 18.3, max: 35.0) -[2023-10-09 10:45:16,078][22500] Avg episode reward: [(0, '9.190'), (1, '8.930')] -[2023-10-09 10:45:16,284][23468] Updated weights for policy 0, policy_version 61373 (0.0008) -[2023-10-09 10:45:19,205][23469] Updated weights for policy 1, policy_version 61701 (0.0009) -[2023-10-09 10:45:19,579][23469] Updated weights for policy 1, policy_version 61711 (0.0009) -[2023-10-09 10:45:19,947][23469] Updated weights for policy 1, policy_version 61721 (0.0008) -[2023-10-09 10:45:20,018][23468] Updated weights for policy 0, policy_version 61383 (0.0007) -[2023-10-09 10:45:20,404][23468] Updated weights for policy 0, policy_version 61393 (0.0008) -[2023-10-09 10:45:20,779][23468] Updated weights for policy 0, policy_version 61403 (0.0008) -[2023-10-09 10:45:21,077][22500] Fps is (10 sec: 19660.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 126091264. Throughput: 0: 1790.1, 1: 1802.5. Samples: 31521278. Policy #0 lag: (min: 3.0, avg: 18.3, max: 35.0) -[2023-10-09 10:45:21,078][22500] Avg episode reward: [(0, '8.980'), (1, '9.400')] -[2023-10-09 10:45:23,659][23469] Updated weights for policy 1, policy_version 61731 (0.0008) -[2023-10-09 10:45:24,033][23469] Updated weights for policy 1, policy_version 61741 (0.0008) -[2023-10-09 10:45:24,404][23469] Updated weights for policy 1, policy_version 61751 (0.0007) -[2023-10-09 10:45:24,550][23468] Updated weights for policy 0, policy_version 61413 (0.0008) -[2023-10-09 10:45:24,937][23468] Updated weights for policy 0, policy_version 61423 (0.0007) -[2023-10-09 10:45:25,312][23468] Updated weights for policy 0, policy_version 61433 (0.0008) -[2023-10-09 10:45:26,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 126156800. Throughput: 0: 1805.2, 1: 1793.9. Samples: 31542334. Policy #0 lag: (min: 3.0, avg: 18.3, max: 35.0) -[2023-10-09 10:45:26,078][22500] Avg episode reward: [(0, '8.720'), (1, '8.530')] -[2023-10-09 10:45:28,123][23469] Updated weights for policy 1, policy_version 61761 (0.0009) -[2023-10-09 10:45:28,490][23469] Updated weights for policy 1, policy_version 61771 (0.0007) -[2023-10-09 10:45:28,863][23469] Updated weights for policy 1, policy_version 61781 (0.0009) -[2023-10-09 10:45:29,073][23468] Updated weights for policy 0, policy_version 61443 (0.0010) -[2023-10-09 10:45:29,235][23469] Updated weights for policy 1, policy_version 61791 (0.0008) -[2023-10-09 10:45:29,445][23468] Updated weights for policy 0, policy_version 61453 (0.0008) -[2023-10-09 10:45:29,818][23468] Updated weights for policy 0, policy_version 61463 (0.0008) -[2023-10-09 10:45:31,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 126222336. Throughput: 0: 1780.9, 1: 1800.7. Samples: 31563326. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:45:31,078][22500] Avg episode reward: [(0, '8.770'), (1, '9.170')] -[2023-10-09 10:45:32,974][23469] Updated weights for policy 1, policy_version 61801 (0.0011) -[2023-10-09 10:45:33,342][23469] Updated weights for policy 1, policy_version 61811 (0.0010) -[2023-10-09 10:45:33,517][23468] Updated weights for policy 0, policy_version 61473 (0.0009) -[2023-10-09 10:45:33,717][23469] Updated weights for policy 1, policy_version 61821 (0.0008) -[2023-10-09 10:45:33,900][23468] Updated weights for policy 0, policy_version 61483 (0.0008) -[2023-10-09 10:45:34,271][23468] Updated weights for policy 0, policy_version 61493 (0.0007) -[2023-10-09 10:45:34,647][23468] Updated weights for policy 0, policy_version 61503 (0.0007) -[2023-10-09 10:45:36,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 126287872. Throughput: 0: 1796.7, 1: 1801.0. Samples: 31574580. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:45:36,078][22500] Avg episode reward: [(0, '9.150'), (1, '9.090')] -[2023-10-09 10:45:37,374][23469] Updated weights for policy 1, policy_version 61831 (0.0009) -[2023-10-09 10:45:37,741][23469] Updated weights for policy 1, policy_version 61841 (0.0008) -[2023-10-09 10:45:38,103][23469] Updated weights for policy 1, policy_version 61851 (0.0008) -[2023-10-09 10:45:38,354][23468] Updated weights for policy 0, policy_version 61513 (0.0009) -[2023-10-09 10:45:38,727][23468] Updated weights for policy 0, policy_version 61523 (0.0009) -[2023-10-09 10:45:39,104][23468] Updated weights for policy 0, policy_version 61533 (0.0008) -[2023-10-09 10:45:41,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 126353408. Throughput: 0: 1781.4, 1: 1796.4. Samples: 31595408. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:45:41,078][22500] Avg episode reward: [(0, '9.360'), (1, '9.070')] -[2023-10-09 10:45:41,850][23469] Updated weights for policy 1, policy_version 61861 (0.0009) -[2023-10-09 10:45:42,226][23469] Updated weights for policy 1, policy_version 61871 (0.0009) -[2023-10-09 10:45:42,588][23469] Updated weights for policy 1, policy_version 61881 (0.0007) -[2023-10-09 10:45:42,890][23468] Updated weights for policy 0, policy_version 61543 (0.0008) -[2023-10-09 10:45:43,273][23468] Updated weights for policy 0, policy_version 61553 (0.0010) -[2023-10-09 10:45:43,647][23468] Updated weights for policy 0, policy_version 61563 (0.0011) -[2023-10-09 10:45:46,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 126418944. Throughput: 0: 1775.6, 1: 1791.6. Samples: 31617640. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:45:46,078][22500] Avg episode reward: [(0, '9.540'), (1, '8.610')] -[2023-10-09 10:45:46,502][23469] Updated weights for policy 1, policy_version 61891 (0.0007) -[2023-10-09 10:45:46,869][23469] Updated weights for policy 1, policy_version 61901 (0.0008) -[2023-10-09 10:45:47,234][23469] Updated weights for policy 1, policy_version 61911 (0.0008) -[2023-10-09 10:45:47,498][23468] Updated weights for policy 0, policy_version 61573 (0.0010) -[2023-10-09 10:45:47,871][23468] Updated weights for policy 0, policy_version 61583 (0.0008) -[2023-10-09 10:45:48,240][23468] Updated weights for policy 0, policy_version 61593 (0.0009) -[2023-10-09 10:45:51,042][23469] Updated weights for policy 1, policy_version 61921 (0.0009) -[2023-10-09 10:45:51,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 126484480. Throughput: 0: 1785.6, 1: 1791.3. Samples: 31627682. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:45:51,078][22500] Avg episode reward: [(0, '9.270'), (1, '8.340')] -[2023-10-09 10:45:51,429][23469] Updated weights for policy 1, policy_version 61931 (0.0007) -[2023-10-09 10:45:51,807][23469] Updated weights for policy 1, policy_version 61941 (0.0009) -[2023-10-09 10:45:52,088][23468] Updated weights for policy 0, policy_version 61603 (0.0009) -[2023-10-09 10:45:52,172][23469] Updated weights for policy 1, policy_version 61951 (0.0008) -[2023-10-09 10:45:52,460][23468] Updated weights for policy 0, policy_version 61613 (0.0008) -[2023-10-09 10:45:52,833][23468] Updated weights for policy 0, policy_version 61623 (0.0007) -[2023-10-09 10:45:55,944][23469] Updated weights for policy 1, policy_version 61961 (0.0010) -[2023-10-09 10:45:56,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 126550016. Throughput: 0: 1776.8, 1: 1793.2. Samples: 31649638. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:45:56,078][22500] Avg episode reward: [(0, '9.410'), (1, '8.560')] -[2023-10-09 10:45:56,321][23469] Updated weights for policy 1, policy_version 61971 (0.0008) -[2023-10-09 10:45:56,609][23468] Updated weights for policy 0, policy_version 61633 (0.0008) -[2023-10-09 10:45:56,687][23469] Updated weights for policy 1, policy_version 61981 (0.0008) -[2023-10-09 10:45:56,991][23468] Updated weights for policy 0, policy_version 61643 (0.0009) -[2023-10-09 10:45:57,362][23468] Updated weights for policy 0, policy_version 61653 (0.0008) -[2023-10-09 10:45:57,745][23468] Updated weights for policy 0, policy_version 61663 (0.0011) -[2023-10-09 10:46:00,540][23469] Updated weights for policy 1, policy_version 61991 (0.0008) -[2023-10-09 10:46:00,920][23469] Updated weights for policy 1, policy_version 62001 (0.0009) -[2023-10-09 10:46:01,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 126615552. Throughput: 0: 1781.1, 1: 1810.3. Samples: 31671320. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:46:01,078][22500] Avg episode reward: [(0, '9.630'), (1, '8.640')] -[2023-10-09 10:46:01,288][23469] Updated weights for policy 1, policy_version 62011 (0.0009) -[2023-10-09 10:46:01,478][23468] Updated weights for policy 0, policy_version 61673 (0.0007) -[2023-10-09 10:46:01,845][23468] Updated weights for policy 0, policy_version 61683 (0.0009) -[2023-10-09 10:46:02,229][23468] Updated weights for policy 0, policy_version 61693 (0.0008) -[2023-10-09 10:46:04,896][23469] Updated weights for policy 1, policy_version 62021 (0.0008) -[2023-10-09 10:46:05,260][23469] Updated weights for policy 1, policy_version 62031 (0.0007) -[2023-10-09 10:46:05,627][23469] Updated weights for policy 1, policy_version 62041 (0.0009) -[2023-10-09 10:46:06,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 126713856. Throughput: 0: 1772.5, 1: 1791.7. Samples: 31681668. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:46:06,079][22500] Avg episode reward: [(0, '9.610'), (1, '9.180')] -[2023-10-09 10:46:06,156][23468] Updated weights for policy 0, policy_version 61703 (0.0009) -[2023-10-09 10:46:06,543][23468] Updated weights for policy 0, policy_version 61713 (0.0009) -[2023-10-09 10:46:06,921][23468] Updated weights for policy 0, policy_version 61723 (0.0009) -[2023-10-09 10:46:09,472][23469] Updated weights for policy 1, policy_version 62051 (0.0009) -[2023-10-09 10:46:09,842][23469] Updated weights for policy 1, policy_version 62061 (0.0008) -[2023-10-09 10:46:10,218][23469] Updated weights for policy 1, policy_version 62071 (0.0009) -[2023-10-09 10:46:10,821][23468] Updated weights for policy 0, policy_version 61733 (0.0009) -[2023-10-09 10:46:11,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 126779392. Throughput: 0: 1763.7, 1: 1811.9. Samples: 31703234. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:46:11,078][22500] Avg episode reward: [(0, '9.820'), (1, '8.930')] -[2023-10-09 10:46:11,179][23468] Updated weights for policy 0, policy_version 61743 (0.0010) -[2023-10-09 10:46:11,552][23468] Updated weights for policy 0, policy_version 61753 (0.0008) -[2023-10-09 10:46:13,946][23469] Updated weights for policy 1, policy_version 62081 (0.0009) -[2023-10-09 10:46:14,312][23469] Updated weights for policy 1, policy_version 62091 (0.0007) -[2023-10-09 10:46:14,687][23469] Updated weights for policy 1, policy_version 62101 (0.0007) -[2023-10-09 10:46:15,052][23469] Updated weights for policy 1, policy_version 62111 (0.0007) -[2023-10-09 10:46:15,271][23468] Updated weights for policy 0, policy_version 61763 (0.0010) -[2023-10-09 10:46:15,643][23468] Updated weights for policy 0, policy_version 61773 (0.0007) -[2023-10-09 10:46:16,011][23468] Updated weights for policy 0, policy_version 61783 (0.0009) -[2023-10-09 10:46:16,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 126844928. Throughput: 0: 1798.0, 1: 1786.5. Samples: 31724630. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-09 10:46:16,079][22500] Avg episode reward: [(0, '9.660'), (1, '9.210')] -[2023-10-09 10:46:16,091][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000062112_63602688.pth... -[2023-10-09 10:46:16,124][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000060416_61865984.pth -[2023-10-09 10:46:16,342][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000061792_63275008.pth... -[2023-10-09 10:46:16,371][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000060128_61571072.pth -[2023-10-09 10:46:18,691][23469] Updated weights for policy 1, policy_version 62121 (0.0010) -[2023-10-09 10:46:19,062][23469] Updated weights for policy 1, policy_version 62131 (0.0011) -[2023-10-09 10:46:19,430][23469] Updated weights for policy 1, policy_version 62141 (0.0008) -[2023-10-09 10:46:19,778][23468] Updated weights for policy 0, policy_version 61793 (0.0008) -[2023-10-09 10:46:20,149][23468] Updated weights for policy 0, policy_version 61803 (0.0008) -[2023-10-09 10:46:20,519][23468] Updated weights for policy 0, policy_version 61813 (0.0008) -[2023-10-09 10:46:20,892][23468] Updated weights for policy 0, policy_version 61823 (0.0010) -[2023-10-09 10:46:21,077][22500] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 126943232. Throughput: 0: 1768.4, 1: 1807.4. Samples: 31735490. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-09 10:46:21,078][22500] Avg episode reward: [(0, '9.060'), (1, '9.550')] -[2023-10-09 10:46:23,393][23469] Updated weights for policy 1, policy_version 62151 (0.0009) -[2023-10-09 10:46:23,763][23469] Updated weights for policy 1, policy_version 62161 (0.0008) -[2023-10-09 10:46:24,127][23469] Updated weights for policy 1, policy_version 62171 (0.0009) -[2023-10-09 10:46:24,632][23468] Updated weights for policy 0, policy_version 61833 (0.0009) -[2023-10-09 10:46:25,007][23468] Updated weights for policy 0, policy_version 61843 (0.0008) -[2023-10-09 10:46:25,371][23468] Updated weights for policy 0, policy_version 61853 (0.0008) -[2023-10-09 10:46:26,077][22500] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 127008768. Throughput: 0: 1806.8, 1: 1783.8. Samples: 31756986. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-09 10:46:26,078][22500] Avg episode reward: [(0, '8.970'), (1, '9.100')] -[2023-10-09 10:46:27,625][23469] Updated weights for policy 1, policy_version 62181 (0.0008) -[2023-10-09 10:46:28,000][23469] Updated weights for policy 1, policy_version 62191 (0.0007) -[2023-10-09 10:46:28,370][23469] Updated weights for policy 1, policy_version 62201 (0.0009) -[2023-10-09 10:46:29,027][23468] Updated weights for policy 0, policy_version 61863 (0.0009) -[2023-10-09 10:46:29,410][23468] Updated weights for policy 0, policy_version 61873 (0.0008) -[2023-10-09 10:46:29,794][23468] Updated weights for policy 0, policy_version 61883 (0.0008) -[2023-10-09 10:46:31,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 127074304. Throughput: 0: 1777.5, 1: 1794.9. Samples: 31778400. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-09 10:46:31,078][22500] Avg episode reward: [(0, '9.190'), (1, '8.650')] -[2023-10-09 10:46:32,100][23469] Updated weights for policy 1, policy_version 62211 (0.0009) -[2023-10-09 10:46:32,473][23469] Updated weights for policy 1, policy_version 62221 (0.0010) -[2023-10-09 10:46:32,837][23469] Updated weights for policy 1, policy_version 62231 (0.0010) -[2023-10-09 10:46:33,565][23468] Updated weights for policy 0, policy_version 61893 (0.0008) -[2023-10-09 10:46:33,945][23468] Updated weights for policy 0, policy_version 61903 (0.0009) -[2023-10-09 10:46:34,318][23468] Updated weights for policy 0, policy_version 61913 (0.0007) -[2023-10-09 10:46:36,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 127139840. Throughput: 0: 1805.0, 1: 1792.2. Samples: 31789554. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-09 10:46:36,079][22500] Avg episode reward: [(0, '9.770'), (1, '8.850')] -[2023-10-09 10:46:36,499][23469] Updated weights for policy 1, policy_version 62241 (0.0010) -[2023-10-09 10:46:36,884][23469] Updated weights for policy 1, policy_version 62251 (0.0009) -[2023-10-09 10:46:37,263][23469] Updated weights for policy 1, policy_version 62261 (0.0009) -[2023-10-09 10:46:37,631][23469] Updated weights for policy 1, policy_version 62271 (0.0009) -[2023-10-09 10:46:37,898][23468] Updated weights for policy 0, policy_version 61923 (0.0008) -[2023-10-09 10:46:38,266][23468] Updated weights for policy 0, policy_version 61933 (0.0010) -[2023-10-09 10:46:38,643][23468] Updated weights for policy 0, policy_version 61943 (0.0011) -[2023-10-09 10:46:41,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 127205376. Throughput: 0: 1783.4, 1: 1798.3. Samples: 31810816. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-09 10:46:41,079][22500] Avg episode reward: [(0, '10.190'), (1, '9.290')] -[2023-10-09 10:46:41,338][23469] Updated weights for policy 1, policy_version 62281 (0.0008) -[2023-10-09 10:46:41,709][23469] Updated weights for policy 1, policy_version 62291 (0.0009) -[2023-10-09 10:46:42,080][23469] Updated weights for policy 1, policy_version 62301 (0.0009) -[2023-10-09 10:46:42,541][23468] Updated weights for policy 0, policy_version 61953 (0.0010) -[2023-10-09 10:46:42,909][23468] Updated weights for policy 0, policy_version 61963 (0.0007) -[2023-10-09 10:46:43,287][23468] Updated weights for policy 0, policy_version 61973 (0.0007) -[2023-10-09 10:46:43,654][23468] Updated weights for policy 0, policy_version 61983 (0.0007) -[2023-10-09 10:46:45,988][23469] Updated weights for policy 1, policy_version 62311 (0.0009) -[2023-10-09 10:46:46,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 127270912. Throughput: 0: 1783.7, 1: 1809.3. Samples: 31833008. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-09 10:46:46,079][22500] Avg episode reward: [(0, '10.250'), (1, '8.670')] -[2023-10-09 10:46:46,361][23469] Updated weights for policy 1, policy_version 62321 (0.0007) -[2023-10-09 10:46:46,732][23469] Updated weights for policy 1, policy_version 62331 (0.0008) -[2023-10-09 10:46:47,425][23468] Updated weights for policy 0, policy_version 61993 (0.0007) -[2023-10-09 10:46:47,795][23468] Updated weights for policy 0, policy_version 62003 (0.0009) -[2023-10-09 10:46:48,164][23468] Updated weights for policy 0, policy_version 62013 (0.0008) -[2023-10-09 10:46:50,439][23469] Updated weights for policy 1, policy_version 62341 (0.0008) -[2023-10-09 10:46:50,816][23469] Updated weights for policy 1, policy_version 62351 (0.0008) -[2023-10-09 10:46:51,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 127336448. Throughput: 0: 1783.7, 1: 1794.3. Samples: 31842680. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-09 10:46:51,078][22500] Avg episode reward: [(0, '9.960'), (1, '8.420')] -[2023-10-09 10:46:51,185][23469] Updated weights for policy 1, policy_version 62361 (0.0009) -[2023-10-09 10:46:51,854][23468] Updated weights for policy 0, policy_version 62023 (0.0009) -[2023-10-09 10:46:52,236][23468] Updated weights for policy 0, policy_version 62033 (0.0008) -[2023-10-09 10:46:52,606][23468] Updated weights for policy 0, policy_version 62043 (0.0007) -[2023-10-09 10:46:54,768][23469] Updated weights for policy 1, policy_version 62371 (0.0010) -[2023-10-09 10:46:55,128][23469] Updated weights for policy 1, policy_version 62381 (0.0007) -[2023-10-09 10:46:55,497][23469] Updated weights for policy 1, policy_version 62391 (0.0008) -[2023-10-09 10:46:56,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 127434752. Throughput: 0: 1789.5, 1: 1809.1. Samples: 31865168. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-09 10:46:56,079][22500] Avg episode reward: [(0, '10.010'), (1, '7.990')] -[2023-10-09 10:46:56,429][23468] Updated weights for policy 0, policy_version 62053 (0.0010) -[2023-10-09 10:46:56,794][23468] Updated weights for policy 0, policy_version 62063 (0.0009) -[2023-10-09 10:46:57,159][23468] Updated weights for policy 0, policy_version 62073 (0.0010) -[2023-10-09 10:46:59,354][23469] Updated weights for policy 1, policy_version 62401 (0.0008) -[2023-10-09 10:46:59,725][23469] Updated weights for policy 1, policy_version 62411 (0.0007) -[2023-10-09 10:47:00,100][23469] Updated weights for policy 1, policy_version 62421 (0.0007) -[2023-10-09 10:47:00,474][23469] Updated weights for policy 1, policy_version 62431 (0.0007) -[2023-10-09 10:47:00,829][23468] Updated weights for policy 0, policy_version 62083 (0.0007) -[2023-10-09 10:47:01,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 127500288. Throughput: 0: 1793.6, 1: 1801.7. Samples: 31886418. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-09 10:47:01,078][22500] Avg episode reward: [(0, '9.560'), (1, '8.260')] -[2023-10-09 10:47:01,207][23468] Updated weights for policy 0, policy_version 62093 (0.0008) -[2023-10-09 10:47:01,573][23468] Updated weights for policy 0, policy_version 62103 (0.0009) -[2023-10-09 10:47:04,044][23469] Updated weights for policy 1, policy_version 62441 (0.0010) -[2023-10-09 10:47:04,403][23469] Updated weights for policy 1, policy_version 62451 (0.0008) -[2023-10-09 10:47:04,769][23469] Updated weights for policy 1, policy_version 62461 (0.0007) -[2023-10-09 10:47:05,213][23468] Updated weights for policy 0, policy_version 62113 (0.0009) -[2023-10-09 10:47:05,585][23468] Updated weights for policy 0, policy_version 62123 (0.0008) -[2023-10-09 10:47:05,965][23468] Updated weights for policy 0, policy_version 62133 (0.0009) -[2023-10-09 10:47:06,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 127565824. Throughput: 0: 1793.8, 1: 1814.2. Samples: 31897850. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-09 10:47:06,079][22500] Avg episode reward: [(0, '9.690'), (1, '8.120')] -[2023-10-09 10:47:06,345][23468] Updated weights for policy 0, policy_version 62143 (0.0011) -[2023-10-09 10:47:08,314][23469] Updated weights for policy 1, policy_version 62471 (0.0009) -[2023-10-09 10:47:08,685][23469] Updated weights for policy 1, policy_version 62481 (0.0008) -[2023-10-09 10:47:09,069][23469] Updated weights for policy 1, policy_version 62491 (0.0009) -[2023-10-09 10:47:10,123][23468] Updated weights for policy 0, policy_version 62153 (0.0009) -[2023-10-09 10:47:10,492][23468] Updated weights for policy 0, policy_version 62163 (0.0009) -[2023-10-09 10:47:10,866][23468] Updated weights for policy 0, policy_version 62173 (0.0008) -[2023-10-09 10:47:11,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 127664128. Throughput: 0: 1791.5, 1: 1812.0. Samples: 31919142. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-09 10:47:11,078][22500] Avg episode reward: [(0, '9.800'), (1, '8.350')] -[2023-10-09 10:47:12,797][23469] Updated weights for policy 1, policy_version 62501 (0.0007) -[2023-10-09 10:47:13,179][23469] Updated weights for policy 1, policy_version 62511 (0.0009) -[2023-10-09 10:47:13,555][23469] Updated weights for policy 1, policy_version 62521 (0.0007) -[2023-10-09 10:47:14,541][23468] Updated weights for policy 0, policy_version 62183 (0.0008) -[2023-10-09 10:47:14,922][23468] Updated weights for policy 0, policy_version 62193 (0.0008) -[2023-10-09 10:47:15,294][23468] Updated weights for policy 0, policy_version 62203 (0.0009) -[2023-10-09 10:47:16,078][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 127729664. Throughput: 0: 1801.6, 1: 1801.6. Samples: 31940546. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-09 10:47:16,079][22500] Avg episode reward: [(0, '9.620'), (1, '7.930')] -[2023-10-09 10:47:17,359][23469] Updated weights for policy 1, policy_version 62531 (0.0009) -[2023-10-09 10:47:17,725][23469] Updated weights for policy 1, policy_version 62541 (0.0008) -[2023-10-09 10:47:18,096][23469] Updated weights for policy 1, policy_version 62551 (0.0008) -[2023-10-09 10:47:18,961][23468] Updated weights for policy 0, policy_version 62213 (0.0009) -[2023-10-09 10:47:19,335][23468] Updated weights for policy 0, policy_version 62223 (0.0007) -[2023-10-09 10:47:19,708][23468] Updated weights for policy 0, policy_version 62233 (0.0007) -[2023-10-09 10:47:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 127795200. Throughput: 0: 1795.6, 1: 1805.2. Samples: 31951590. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-09 10:47:21,078][22500] Avg episode reward: [(0, '9.770'), (1, '8.450')] -[2023-10-09 10:47:21,913][23469] Updated weights for policy 1, policy_version 62561 (0.0008) -[2023-10-09 10:47:22,288][23469] Updated weights for policy 1, policy_version 62571 (0.0010) -[2023-10-09 10:47:22,660][23469] Updated weights for policy 1, policy_version 62581 (0.0009) -[2023-10-09 10:47:23,036][23469] Updated weights for policy 1, policy_version 62591 (0.0008) -[2023-10-09 10:47:23,497][23468] Updated weights for policy 0, policy_version 62243 (0.0008) -[2023-10-09 10:47:23,861][23468] Updated weights for policy 0, policy_version 62253 (0.0010) -[2023-10-09 10:47:24,239][23468] Updated weights for policy 0, policy_version 62263 (0.0008) -[2023-10-09 10:47:26,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 127860736. Throughput: 0: 1802.6, 1: 1800.1. Samples: 31972938. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-09 10:47:26,079][22500] Avg episode reward: [(0, '8.780'), (1, '8.440')] -[2023-10-09 10:47:26,868][23469] Updated weights for policy 1, policy_version 62601 (0.0007) -[2023-10-09 10:47:27,244][23469] Updated weights for policy 1, policy_version 62611 (0.0007) -[2023-10-09 10:47:27,616][23469] Updated weights for policy 1, policy_version 62621 (0.0008) -[2023-10-09 10:47:28,007][23468] Updated weights for policy 0, policy_version 62273 (0.0007) -[2023-10-09 10:47:28,377][23468] Updated weights for policy 0, policy_version 62283 (0.0009) -[2023-10-09 10:47:28,753][23468] Updated weights for policy 0, policy_version 62293 (0.0008) -[2023-10-09 10:47:29,132][23468] Updated weights for policy 0, policy_version 62303 (0.0008) -[2023-10-09 10:47:31,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 127926272. Throughput: 0: 1789.2, 1: 1805.4. Samples: 31994762. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-09 10:47:31,079][22500] Avg episode reward: [(0, '8.530'), (1, '8.700')] -[2023-10-09 10:47:31,159][23469] Updated weights for policy 1, policy_version 62631 (0.0008) -[2023-10-09 10:47:31,525][23469] Updated weights for policy 1, policy_version 62641 (0.0007) -[2023-10-09 10:47:31,894][23469] Updated weights for policy 1, policy_version 62651 (0.0010) -[2023-10-09 10:47:32,901][23468] Updated weights for policy 0, policy_version 62313 (0.0007) -[2023-10-09 10:47:33,269][23468] Updated weights for policy 0, policy_version 62323 (0.0009) -[2023-10-09 10:47:33,650][23468] Updated weights for policy 0, policy_version 62333 (0.0008) -[2023-10-09 10:47:35,576][23469] Updated weights for policy 1, policy_version 62661 (0.0008) -[2023-10-09 10:47:35,940][23469] Updated weights for policy 1, policy_version 62671 (0.0008) -[2023-10-09 10:47:36,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 127991808. Throughput: 0: 1804.6, 1: 1810.5. Samples: 32005360. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:47:36,078][22500] Avg episode reward: [(0, '8.930'), (1, '9.730')] -[2023-10-09 10:47:36,312][23469] Updated weights for policy 1, policy_version 62681 (0.0010) -[2023-10-09 10:47:37,352][23468] Updated weights for policy 0, policy_version 62343 (0.0009) -[2023-10-09 10:47:37,726][23468] Updated weights for policy 0, policy_version 62353 (0.0008) -[2023-10-09 10:47:38,102][23468] Updated weights for policy 0, policy_version 62363 (0.0007) -[2023-10-09 10:47:40,021][23469] Updated weights for policy 1, policy_version 62691 (0.0009) -[2023-10-09 10:47:40,388][23469] Updated weights for policy 1, policy_version 62701 (0.0008) -[2023-10-09 10:47:40,761][23469] Updated weights for policy 1, policy_version 62711 (0.0007) -[2023-10-09 10:47:41,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 128057344. Throughput: 0: 1794.2, 1: 1808.0. Samples: 32027266. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:47:41,078][22500] Avg episode reward: [(0, '9.170'), (1, '8.950')] -[2023-10-09 10:47:41,821][23468] Updated weights for policy 0, policy_version 62373 (0.0007) -[2023-10-09 10:47:42,206][23468] Updated weights for policy 0, policy_version 62383 (0.0010) -[2023-10-09 10:47:42,582][23468] Updated weights for policy 0, policy_version 62393 (0.0008) -[2023-10-09 10:47:44,377][23469] Updated weights for policy 1, policy_version 62721 (0.0008) -[2023-10-09 10:47:44,739][23469] Updated weights for policy 1, policy_version 62731 (0.0008) -[2023-10-09 10:47:45,112][23469] Updated weights for policy 1, policy_version 62741 (0.0008) -[2023-10-09 10:47:45,476][23469] Updated weights for policy 1, policy_version 62751 (0.0009) -[2023-10-09 10:47:46,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 128155648. Throughput: 0: 1795.2, 1: 1807.8. Samples: 32048550. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:47:46,078][22500] Avg episode reward: [(0, '9.410'), (1, '9.120')] -[2023-10-09 10:47:46,370][23468] Updated weights for policy 0, policy_version 62403 (0.0007) -[2023-10-09 10:47:46,733][23468] Updated weights for policy 0, policy_version 62413 (0.0007) -[2023-10-09 10:47:47,114][23468] Updated weights for policy 0, policy_version 62423 (0.0007) -[2023-10-09 10:47:49,230][23469] Updated weights for policy 1, policy_version 62761 (0.0009) -[2023-10-09 10:47:49,606][23469] Updated weights for policy 1, policy_version 62771 (0.0008) -[2023-10-09 10:47:49,983][23469] Updated weights for policy 1, policy_version 62781 (0.0010) -[2023-10-09 10:47:50,864][23468] Updated weights for policy 0, policy_version 62433 (0.0007) -[2023-10-09 10:47:51,077][22500] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 128221184. Throughput: 0: 1791.7, 1: 1806.1. Samples: 32059750. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:47:51,079][22500] Avg episode reward: [(0, '9.680'), (1, '9.180')] -[2023-10-09 10:47:51,245][23468] Updated weights for policy 0, policy_version 62443 (0.0009) -[2023-10-09 10:47:51,626][23468] Updated weights for policy 0, policy_version 62453 (0.0010) -[2023-10-09 10:47:52,004][23468] Updated weights for policy 0, policy_version 62463 (0.0008) -[2023-10-09 10:47:53,824][23469] Updated weights for policy 1, policy_version 62791 (0.0010) -[2023-10-09 10:47:54,198][23469] Updated weights for policy 1, policy_version 62801 (0.0010) -[2023-10-09 10:47:54,562][23469] Updated weights for policy 1, policy_version 62811 (0.0008) -[2023-10-09 10:47:55,733][23468] Updated weights for policy 0, policy_version 62473 (0.0010) -[2023-10-09 10:47:56,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 128286720. Throughput: 0: 1790.3, 1: 1800.0. Samples: 32080708. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:47:56,078][22500] Avg episode reward: [(0, '9.570'), (1, '8.980')] -[2023-10-09 10:47:56,101][23468] Updated weights for policy 0, policy_version 62483 (0.0008) -[2023-10-09 10:47:56,470][23468] Updated weights for policy 0, policy_version 62493 (0.0007) -[2023-10-09 10:47:58,300][23469] Updated weights for policy 1, policy_version 62821 (0.0007) -[2023-10-09 10:47:58,667][23469] Updated weights for policy 1, policy_version 62831 (0.0008) -[2023-10-09 10:47:59,034][23469] Updated weights for policy 1, policy_version 62841 (0.0009) -[2023-10-09 10:48:00,222][23468] Updated weights for policy 0, policy_version 62503 (0.0008) -[2023-10-09 10:48:00,601][23468] Updated weights for policy 0, policy_version 62513 (0.0008) -[2023-10-09 10:48:00,980][23468] Updated weights for policy 0, policy_version 62523 (0.0009) -[2023-10-09 10:48:01,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 128352256. Throughput: 0: 1804.6, 1: 1802.6. Samples: 32102870. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:48:01,079][22500] Avg episode reward: [(0, '9.640'), (1, '9.480')] -[2023-10-09 10:48:02,685][23469] Updated weights for policy 1, policy_version 62851 (0.0007) -[2023-10-09 10:48:03,054][23469] Updated weights for policy 1, policy_version 62861 (0.0007) -[2023-10-09 10:48:03,426][23469] Updated weights for policy 1, policy_version 62871 (0.0010) -[2023-10-09 10:48:04,810][23468] Updated weights for policy 0, policy_version 62533 (0.0009) -[2023-10-09 10:48:05,182][23468] Updated weights for policy 0, policy_version 62543 (0.0008) -[2023-10-09 10:48:05,561][23468] Updated weights for policy 0, policy_version 62553 (0.0008) -[2023-10-09 10:48:06,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 128450560. Throughput: 0: 1782.9, 1: 1804.6. Samples: 32113030. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:48:06,078][22500] Avg episode reward: [(0, '9.260'), (1, '9.450')] -[2023-10-09 10:48:07,175][23469] Updated weights for policy 1, policy_version 62881 (0.0010) -[2023-10-09 10:48:07,543][23469] Updated weights for policy 1, policy_version 62891 (0.0008) -[2023-10-09 10:48:07,923][23469] Updated weights for policy 1, policy_version 62901 (0.0010) -[2023-10-09 10:48:08,283][23469] Updated weights for policy 1, policy_version 62911 (0.0012) -[2023-10-09 10:48:09,297][23468] Updated weights for policy 0, policy_version 62563 (0.0007) -[2023-10-09 10:48:09,671][23468] Updated weights for policy 0, policy_version 62573 (0.0007) -[2023-10-09 10:48:10,047][23468] Updated weights for policy 0, policy_version 62583 (0.0007) -[2023-10-09 10:48:11,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 128516096. Throughput: 0: 1803.7, 1: 1809.0. Samples: 32135512. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:48:11,078][22500] Avg episode reward: [(0, '9.480'), (1, '9.800')] -[2023-10-09 10:48:12,063][23469] Updated weights for policy 1, policy_version 62921 (0.0010) -[2023-10-09 10:48:12,421][23469] Updated weights for policy 1, policy_version 62931 (0.0010) -[2023-10-09 10:48:12,787][23469] Updated weights for policy 1, policy_version 62941 (0.0011) -[2023-10-09 10:48:13,811][23468] Updated weights for policy 0, policy_version 62593 (0.0008) -[2023-10-09 10:48:14,180][23468] Updated weights for policy 0, policy_version 62603 (0.0008) -[2023-10-09 10:48:14,558][23468] Updated weights for policy 0, policy_version 62613 (0.0007) -[2023-10-09 10:48:14,939][23468] Updated weights for policy 0, policy_version 62623 (0.0007) -[2023-10-09 10:48:16,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 128581632. Throughput: 0: 1786.3, 1: 1810.0. Samples: 32156594. Policy #0 lag: (min: 30.0, avg: 33.3, max: 62.0) -[2023-10-09 10:48:16,079][22500] Avg episode reward: [(0, '9.390'), (1, '9.700')] -[2023-10-09 10:48:16,091][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000062944_64454656.pth... -[2023-10-09 10:48:16,091][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000062624_64126976.pth... -[2023-10-09 10:48:16,122][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000060960_62423040.pth -[2023-10-09 10:48:16,122][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000061280_62750720.pth -[2023-10-09 10:48:16,521][23469] Updated weights for policy 1, policy_version 62951 (0.0008) -[2023-10-09 10:48:16,884][23469] Updated weights for policy 1, policy_version 62961 (0.0008) -[2023-10-09 10:48:17,256][23469] Updated weights for policy 1, policy_version 62971 (0.0007) -[2023-10-09 10:48:18,775][23468] Updated weights for policy 0, policy_version 62633 (0.0008) -[2023-10-09 10:48:19,148][23468] Updated weights for policy 0, policy_version 62643 (0.0007) -[2023-10-09 10:48:19,527][23468] Updated weights for policy 0, policy_version 62653 (0.0007) -[2023-10-09 10:48:21,021][23469] Updated weights for policy 1, policy_version 62981 (0.0010) -[2023-10-09 10:48:21,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 128647168. Throughput: 0: 1804.8, 1: 1803.3. Samples: 32167726. Policy #0 lag: (min: 30.0, avg: 33.3, max: 62.0) -[2023-10-09 10:48:21,078][22500] Avg episode reward: [(0, '9.960'), (1, '9.150')] -[2023-10-09 10:48:21,384][23469] Updated weights for policy 1, policy_version 62991 (0.0008) -[2023-10-09 10:48:21,761][23469] Updated weights for policy 1, policy_version 63001 (0.0010) -[2023-10-09 10:48:23,280][23468] Updated weights for policy 0, policy_version 62663 (0.0009) -[2023-10-09 10:48:23,648][23468] Updated weights for policy 0, policy_version 62673 (0.0009) -[2023-10-09 10:48:24,022][23468] Updated weights for policy 0, policy_version 62683 (0.0009) -[2023-10-09 10:48:25,416][23469] Updated weights for policy 1, policy_version 63011 (0.0011) -[2023-10-09 10:48:25,779][23469] Updated weights for policy 1, policy_version 63021 (0.0009) -[2023-10-09 10:48:26,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 128712704. Throughput: 0: 1785.5, 1: 1807.3. Samples: 32188942. Policy #0 lag: (min: 30.0, avg: 33.3, max: 62.0) -[2023-10-09 10:48:26,078][22500] Avg episode reward: [(0, '9.840'), (1, '8.920')] -[2023-10-09 10:48:26,158][23469] Updated weights for policy 1, policy_version 63031 (0.0007) -[2023-10-09 10:48:27,795][23468] Updated weights for policy 0, policy_version 62693 (0.0009) -[2023-10-09 10:48:28,182][23468] Updated weights for policy 0, policy_version 62703 (0.0008) -[2023-10-09 10:48:28,560][23468] Updated weights for policy 0, policy_version 62713 (0.0008) -[2023-10-09 10:48:29,786][23469] Updated weights for policy 1, policy_version 63041 (0.0010) -[2023-10-09 10:48:30,160][23469] Updated weights for policy 1, policy_version 63051 (0.0008) -[2023-10-09 10:48:30,528][23469] Updated weights for policy 1, policy_version 63061 (0.0008) -[2023-10-09 10:48:30,890][23469] Updated weights for policy 1, policy_version 63071 (0.0009) -[2023-10-09 10:48:31,078][22500] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 128811008. Throughput: 0: 1782.8, 1: 1815.5. Samples: 32210472. Policy #0 lag: (min: 30.0, avg: 33.3, max: 62.0) -[2023-10-09 10:48:31,079][22500] Avg episode reward: [(0, '9.130'), (1, '8.890')] -[2023-10-09 10:48:32,232][23468] Updated weights for policy 0, policy_version 62723 (0.0010) -[2023-10-09 10:48:32,591][23468] Updated weights for policy 0, policy_version 62733 (0.0010) -[2023-10-09 10:48:32,958][23468] Updated weights for policy 0, policy_version 62743 (0.0009) -[2023-10-09 10:48:34,671][23469] Updated weights for policy 1, policy_version 63081 (0.0009) -[2023-10-09 10:48:35,042][23469] Updated weights for policy 1, policy_version 63091 (0.0010) -[2023-10-09 10:48:35,411][23469] Updated weights for policy 1, policy_version 63101 (0.0008) -[2023-10-09 10:48:36,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 128876544. Throughput: 0: 1781.6, 1: 1806.9. Samples: 32221234. Policy #0 lag: (min: 30.0, avg: 33.3, max: 62.0) -[2023-10-09 10:48:36,078][22500] Avg episode reward: [(0, '8.520'), (1, '8.920')] -[2023-10-09 10:48:36,700][23468] Updated weights for policy 0, policy_version 62753 (0.0009) -[2023-10-09 10:48:37,077][23468] Updated weights for policy 0, policy_version 62763 (0.0007) -[2023-10-09 10:48:37,449][23468] Updated weights for policy 0, policy_version 62773 (0.0008) -[2023-10-09 10:48:37,822][23468] Updated weights for policy 0, policy_version 62783 (0.0008) -[2023-10-09 10:48:39,122][23469] Updated weights for policy 1, policy_version 63111 (0.0009) -[2023-10-09 10:48:39,498][23469] Updated weights for policy 1, policy_version 63121 (0.0007) -[2023-10-09 10:48:39,862][23469] Updated weights for policy 1, policy_version 63131 (0.0007) -[2023-10-09 10:48:41,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 128942080. Throughput: 0: 1779.3, 1: 1814.5. Samples: 32242430. Policy #0 lag: (min: 30.0, avg: 33.3, max: 62.0) -[2023-10-09 10:48:41,078][22500] Avg episode reward: [(0, '8.780'), (1, '9.120')] -[2023-10-09 10:48:41,627][23468] Updated weights for policy 0, policy_version 62793 (0.0008) -[2023-10-09 10:48:41,997][23468] Updated weights for policy 0, policy_version 62803 (0.0007) -[2023-10-09 10:48:42,372][23468] Updated weights for policy 0, policy_version 62813 (0.0007) -[2023-10-09 10:48:43,749][23469] Updated weights for policy 1, policy_version 63141 (0.0009) -[2023-10-09 10:48:44,117][23469] Updated weights for policy 1, policy_version 63151 (0.0010) -[2023-10-09 10:48:44,486][23469] Updated weights for policy 1, policy_version 63161 (0.0007) -[2023-10-09 10:48:46,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 129007616. Throughput: 0: 1789.2, 1: 1800.6. Samples: 32264408. Policy #0 lag: (min: 30.0, avg: 33.3, max: 62.0) -[2023-10-09 10:48:46,078][22500] Avg episode reward: [(0, '8.960'), (1, '8.590')] -[2023-10-09 10:48:46,169][23468] Updated weights for policy 0, policy_version 62823 (0.0008) -[2023-10-09 10:48:46,540][23468] Updated weights for policy 0, policy_version 62833 (0.0007) -[2023-10-09 10:48:46,916][23468] Updated weights for policy 0, policy_version 62843 (0.0007) -[2023-10-09 10:48:48,207][23469] Updated weights for policy 1, policy_version 63171 (0.0009) -[2023-10-09 10:48:48,576][23469] Updated weights for policy 1, policy_version 63181 (0.0007) -[2023-10-09 10:48:48,944][23469] Updated weights for policy 1, policy_version 63191 (0.0008) -[2023-10-09 10:48:50,624][23468] Updated weights for policy 0, policy_version 62853 (0.0007) -[2023-10-09 10:48:51,000][23468] Updated weights for policy 0, policy_version 62863 (0.0007) -[2023-10-09 10:48:51,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 129073152. Throughput: 0: 1780.3, 1: 1817.4. Samples: 32274926. Policy #0 lag: (min: 30.0, avg: 33.3, max: 62.0) -[2023-10-09 10:48:51,078][22500] Avg episode reward: [(0, '8.920'), (1, '8.690')] -[2023-10-09 10:48:51,371][23468] Updated weights for policy 0, policy_version 62873 (0.0007) -[2023-10-09 10:48:52,764][23469] Updated weights for policy 1, policy_version 63201 (0.0011) -[2023-10-09 10:48:53,131][23469] Updated weights for policy 1, policy_version 63211 (0.0008) -[2023-10-09 10:48:53,501][23469] Updated weights for policy 1, policy_version 63221 (0.0009) -[2023-10-09 10:48:53,879][23469] Updated weights for policy 1, policy_version 63231 (0.0009) -[2023-10-09 10:48:54,991][23468] Updated weights for policy 0, policy_version 62883 (0.0007) -[2023-10-09 10:48:55,359][23468] Updated weights for policy 0, policy_version 62893 (0.0008) -[2023-10-09 10:48:55,741][23468] Updated weights for policy 0, policy_version 62903 (0.0011) -[2023-10-09 10:48:56,078][22500] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 129171456. Throughput: 0: 1788.5, 1: 1799.0. Samples: 32296950. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:48:56,079][22500] Avg episode reward: [(0, '9.970'), (1, '8.530')] -[2023-10-09 10:48:57,620][23469] Updated weights for policy 1, policy_version 63241 (0.0009) -[2023-10-09 10:48:58,001][23469] Updated weights for policy 1, policy_version 63251 (0.0008) -[2023-10-09 10:48:58,364][23469] Updated weights for policy 1, policy_version 63261 (0.0008) -[2023-10-09 10:48:59,301][23468] Updated weights for policy 0, policy_version 62913 (0.0010) -[2023-10-09 10:48:59,672][23468] Updated weights for policy 0, policy_version 62923 (0.0009) -[2023-10-09 10:49:00,045][23468] Updated weights for policy 0, policy_version 62933 (0.0009) -[2023-10-09 10:49:00,417][23468] Updated weights for policy 0, policy_version 62943 (0.0009) -[2023-10-09 10:49:01,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 129236992. Throughput: 0: 1800.6, 1: 1798.0. Samples: 32318528. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:49:01,078][22500] Avg episode reward: [(0, '9.680'), (1, '8.550')] -[2023-10-09 10:49:02,118][23469] Updated weights for policy 1, policy_version 63271 (0.0007) -[2023-10-09 10:49:02,482][23469] Updated weights for policy 1, policy_version 63281 (0.0007) -[2023-10-09 10:49:02,854][23469] Updated weights for policy 1, policy_version 63291 (0.0007) -[2023-10-09 10:49:04,115][23468] Updated weights for policy 0, policy_version 62953 (0.0007) -[2023-10-09 10:49:04,493][23468] Updated weights for policy 0, policy_version 62963 (0.0007) -[2023-10-09 10:49:04,870][23468] Updated weights for policy 0, policy_version 62973 (0.0009) -[2023-10-09 10:49:06,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 129302528. Throughput: 0: 1797.4, 1: 1798.3. Samples: 32329532. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:49:06,078][22500] Avg episode reward: [(0, '10.480'), (1, '8.400')] -[2023-10-09 10:49:06,078][23265] Saving new best policy, reward=10.480! -[2023-10-09 10:49:06,583][23469] Updated weights for policy 1, policy_version 63301 (0.0010) -[2023-10-09 10:49:06,944][23469] Updated weights for policy 1, policy_version 63311 (0.0008) -[2023-10-09 10:49:07,316][23469] Updated weights for policy 1, policy_version 63321 (0.0008) -[2023-10-09 10:49:08,665][23468] Updated weights for policy 0, policy_version 62983 (0.0007) -[2023-10-09 10:49:09,039][23468] Updated weights for policy 0, policy_version 62993 (0.0009) -[2023-10-09 10:49:09,409][23468] Updated weights for policy 0, policy_version 63003 (0.0010) -[2023-10-09 10:49:10,920][23469] Updated weights for policy 1, policy_version 63331 (0.0008) -[2023-10-09 10:49:11,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 129368064. Throughput: 0: 1806.9, 1: 1792.3. Samples: 32350906. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:49:11,078][22500] Avg episode reward: [(0, '9.450'), (1, '8.490')] -[2023-10-09 10:49:11,286][23469] Updated weights for policy 1, policy_version 63341 (0.0008) -[2023-10-09 10:49:11,659][23469] Updated weights for policy 1, policy_version 63351 (0.0010) -[2023-10-09 10:49:13,256][23468] Updated weights for policy 0, policy_version 63013 (0.0008) -[2023-10-09 10:49:13,629][23468] Updated weights for policy 0, policy_version 63023 (0.0007) -[2023-10-09 10:49:14,000][23468] Updated weights for policy 0, policy_version 63033 (0.0009) -[2023-10-09 10:49:15,373][23469] Updated weights for policy 1, policy_version 63361 (0.0007) -[2023-10-09 10:49:15,745][23469] Updated weights for policy 1, policy_version 63371 (0.0008) -[2023-10-09 10:49:16,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 129433600. Throughput: 0: 1788.1, 1: 1809.3. Samples: 32372356. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:49:16,078][22500] Avg episode reward: [(0, '10.440'), (1, '8.720')] -[2023-10-09 10:49:16,119][23469] Updated weights for policy 1, policy_version 63381 (0.0007) -[2023-10-09 10:49:16,487][23469] Updated weights for policy 1, policy_version 63391 (0.0008) -[2023-10-09 10:49:17,805][23468] Updated weights for policy 0, policy_version 63043 (0.0009) -[2023-10-09 10:49:18,174][23468] Updated weights for policy 0, policy_version 63053 (0.0010) -[2023-10-09 10:49:18,550][23468] Updated weights for policy 0, policy_version 63063 (0.0010) -[2023-10-09 10:49:20,283][23469] Updated weights for policy 1, policy_version 63401 (0.0010) -[2023-10-09 10:49:20,650][23469] Updated weights for policy 1, policy_version 63411 (0.0010) -[2023-10-09 10:49:21,017][23469] Updated weights for policy 1, policy_version 63421 (0.0009) -[2023-10-09 10:49:21,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 129499136. Throughput: 0: 1811.0, 1: 1794.5. Samples: 32383484. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:49:21,078][22500] Avg episode reward: [(0, '10.370'), (1, '9.390')] -[2023-10-09 10:49:22,408][23468] Updated weights for policy 0, policy_version 63073 (0.0010) -[2023-10-09 10:49:22,789][23468] Updated weights for policy 0, policy_version 63083 (0.0009) -[2023-10-09 10:49:23,158][23468] Updated weights for policy 0, policy_version 63093 (0.0008) -[2023-10-09 10:49:23,533][23468] Updated weights for policy 0, policy_version 63103 (0.0007) -[2023-10-09 10:49:24,741][23469] Updated weights for policy 1, policy_version 63431 (0.0009) -[2023-10-09 10:49:25,114][23469] Updated weights for policy 1, policy_version 63441 (0.0007) -[2023-10-09 10:49:25,489][23469] Updated weights for policy 1, policy_version 63451 (0.0010) -[2023-10-09 10:49:26,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 129597440. Throughput: 0: 1796.6, 1: 1810.8. Samples: 32404760. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:49:26,078][22500] Avg episode reward: [(0, '9.740'), (1, '9.520')] -[2023-10-09 10:49:27,295][23468] Updated weights for policy 0, policy_version 63113 (0.0008) -[2023-10-09 10:49:27,666][23468] Updated weights for policy 0, policy_version 63123 (0.0010) -[2023-10-09 10:49:28,046][23468] Updated weights for policy 0, policy_version 63133 (0.0008) -[2023-10-09 10:49:29,054][23469] Updated weights for policy 1, policy_version 63461 (0.0008) -[2023-10-09 10:49:29,429][23469] Updated weights for policy 1, policy_version 63471 (0.0008) -[2023-10-09 10:49:29,813][23469] Updated weights for policy 1, policy_version 63481 (0.0009) -[2023-10-09 10:49:31,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 129662976. Throughput: 0: 1793.5, 1: 1803.7. Samples: 32426282. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:49:31,078][22500] Avg episode reward: [(0, '10.040'), (1, '9.120')] -[2023-10-09 10:49:31,795][23468] Updated weights for policy 0, policy_version 63143 (0.0008) -[2023-10-09 10:49:32,157][23468] Updated weights for policy 0, policy_version 63153 (0.0008) -[2023-10-09 10:49:32,542][23468] Updated weights for policy 0, policy_version 63163 (0.0009) -[2023-10-09 10:49:33,277][23469] Updated weights for policy 1, policy_version 63491 (0.0009) -[2023-10-09 10:49:33,647][23469] Updated weights for policy 1, policy_version 63501 (0.0008) -[2023-10-09 10:49:34,024][23469] Updated weights for policy 1, policy_version 63511 (0.0008) -[2023-10-09 10:49:36,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 129728512. Throughput: 0: 1792.0, 1: 1806.6. Samples: 32436864. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:49:36,078][22500] Avg episode reward: [(0, '9.500'), (1, '8.690')] -[2023-10-09 10:49:36,272][23468] Updated weights for policy 0, policy_version 63173 (0.0009) -[2023-10-09 10:49:36,641][23468] Updated weights for policy 0, policy_version 63183 (0.0007) -[2023-10-09 10:49:37,017][23468] Updated weights for policy 0, policy_version 63193 (0.0007) -[2023-10-09 10:49:37,950][23469] Updated weights for policy 1, policy_version 63521 (0.0007) -[2023-10-09 10:49:38,324][23469] Updated weights for policy 1, policy_version 63531 (0.0009) -[2023-10-09 10:49:38,684][23469] Updated weights for policy 1, policy_version 63541 (0.0009) -[2023-10-09 10:49:39,046][23469] Updated weights for policy 1, policy_version 63551 (0.0009) -[2023-10-09 10:49:40,793][23468] Updated weights for policy 0, policy_version 63203 (0.0008) -[2023-10-09 10:49:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 129794048. Throughput: 0: 1789.5, 1: 1805.3. Samples: 32458712. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 10:49:41,078][22500] Avg episode reward: [(0, '9.490'), (1, '8.590')] -[2023-10-09 10:49:41,164][23468] Updated weights for policy 0, policy_version 63213 (0.0010) -[2023-10-09 10:49:41,539][23468] Updated weights for policy 0, policy_version 63223 (0.0007) -[2023-10-09 10:49:42,962][23469] Updated weights for policy 1, policy_version 63561 (0.0008) -[2023-10-09 10:49:43,340][23469] Updated weights for policy 1, policy_version 63571 (0.0008) -[2023-10-09 10:49:43,710][23469] Updated weights for policy 1, policy_version 63581 (0.0008) -[2023-10-09 10:49:45,290][23468] Updated weights for policy 0, policy_version 63233 (0.0008) -[2023-10-09 10:49:45,661][23468] Updated weights for policy 0, policy_version 63243 (0.0010) -[2023-10-09 10:49:46,032][23468] Updated weights for policy 0, policy_version 63253 (0.0009) -[2023-10-09 10:49:46,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 129859584. Throughput: 0: 1802.1, 1: 1797.6. Samples: 32480518. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 10:49:46,079][22500] Avg episode reward: [(0, '9.600'), (1, '8.980')] -[2023-10-09 10:49:46,411][23468] Updated weights for policy 0, policy_version 63263 (0.0007) -[2023-10-09 10:49:47,320][23469] Updated weights for policy 1, policy_version 63591 (0.0008) -[2023-10-09 10:49:47,684][23469] Updated weights for policy 1, policy_version 63601 (0.0007) -[2023-10-09 10:49:48,057][23469] Updated weights for policy 1, policy_version 63611 (0.0009) -[2023-10-09 10:49:50,153][23468] Updated weights for policy 0, policy_version 63273 (0.0009) -[2023-10-09 10:49:50,523][23468] Updated weights for policy 0, policy_version 63283 (0.0008) -[2023-10-09 10:49:50,890][23468] Updated weights for policy 0, policy_version 63293 (0.0009) -[2023-10-09 10:49:51,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 129957888. Throughput: 0: 1773.0, 1: 1802.0. Samples: 32490404. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 10:49:51,078][22500] Avg episode reward: [(0, '9.420'), (1, '8.830')] -[2023-10-09 10:49:51,802][23469] Updated weights for policy 1, policy_version 63621 (0.0009) -[2023-10-09 10:49:52,172][23469] Updated weights for policy 1, policy_version 63631 (0.0007) -[2023-10-09 10:49:52,545][23469] Updated weights for policy 1, policy_version 63641 (0.0007) -[2023-10-09 10:49:54,597][23468] Updated weights for policy 0, policy_version 63303 (0.0009) -[2023-10-09 10:49:54,978][23468] Updated weights for policy 0, policy_version 63313 (0.0008) -[2023-10-09 10:49:55,348][23468] Updated weights for policy 0, policy_version 63323 (0.0008) -[2023-10-09 10:49:56,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 130023424. Throughput: 0: 1798.1, 1: 1797.4. Samples: 32512704. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 10:49:56,078][22500] Avg episode reward: [(0, '10.020'), (1, '9.540')] -[2023-10-09 10:49:56,454][23469] Updated weights for policy 1, policy_version 63651 (0.0008) -[2023-10-09 10:49:56,830][23469] Updated weights for policy 1, policy_version 63661 (0.0009) -[2023-10-09 10:49:57,205][23469] Updated weights for policy 1, policy_version 63671 (0.0008) -[2023-10-09 10:49:59,198][23468] Updated weights for policy 0, policy_version 63333 (0.0009) -[2023-10-09 10:49:59,592][23468] Updated weights for policy 0, policy_version 63343 (0.0010) -[2023-10-09 10:49:59,973][23468] Updated weights for policy 0, policy_version 63353 (0.0009) -[2023-10-09 10:50:01,028][23469] Updated weights for policy 1, policy_version 63681 (0.0010) -[2023-10-09 10:50:01,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 130088960. Throughput: 0: 1777.8, 1: 1803.6. Samples: 32533522. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 10:50:01,078][22500] Avg episode reward: [(0, '9.630'), (1, '8.900')] -[2023-10-09 10:50:01,395][23469] Updated weights for policy 1, policy_version 63691 (0.0011) -[2023-10-09 10:50:01,777][23469] Updated weights for policy 1, policy_version 63701 (0.0010) -[2023-10-09 10:50:02,144][23469] Updated weights for policy 1, policy_version 63711 (0.0008) -[2023-10-09 10:50:03,959][23468] Updated weights for policy 0, policy_version 63363 (0.0010) -[2023-10-09 10:50:04,328][23468] Updated weights for policy 0, policy_version 63373 (0.0009) -[2023-10-09 10:50:04,700][23468] Updated weights for policy 0, policy_version 63383 (0.0009) -[2023-10-09 10:50:06,057][23469] Updated weights for policy 1, policy_version 63721 (0.0008) -[2023-10-09 10:50:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 130154496. Throughput: 0: 1786.1, 1: 1788.0. Samples: 32544318. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 10:50:06,078][22500] Avg episode reward: [(0, '9.960'), (1, '8.740')] -[2023-10-09 10:50:06,422][23469] Updated weights for policy 1, policy_version 63731 (0.0009) -[2023-10-09 10:50:06,796][23469] Updated weights for policy 1, policy_version 63741 (0.0011) -[2023-10-09 10:50:08,351][23468] Updated weights for policy 0, policy_version 63393 (0.0011) -[2023-10-09 10:50:08,733][23468] Updated weights for policy 0, policy_version 63403 (0.0009) -[2023-10-09 10:50:09,102][23468] Updated weights for policy 0, policy_version 63413 (0.0008) -[2023-10-09 10:50:09,486][23468] Updated weights for policy 0, policy_version 63423 (0.0007) -[2023-10-09 10:50:10,517][23469] Updated weights for policy 1, policy_version 63751 (0.0009) -[2023-10-09 10:50:10,884][23469] Updated weights for policy 1, policy_version 63761 (0.0007) -[2023-10-09 10:50:11,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 130220032. Throughput: 0: 1778.1, 1: 1795.6. Samples: 32565574. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 10:50:11,078][22500] Avg episode reward: [(0, '9.800'), (1, '8.860')] -[2023-10-09 10:50:11,257][23469] Updated weights for policy 1, policy_version 63771 (0.0007) -[2023-10-09 10:50:13,250][23468] Updated weights for policy 0, policy_version 63433 (0.0008) -[2023-10-09 10:50:13,613][23468] Updated weights for policy 0, policy_version 63443 (0.0010) -[2023-10-09 10:50:13,991][23468] Updated weights for policy 0, policy_version 63453 (0.0009) -[2023-10-09 10:50:14,862][23469] Updated weights for policy 1, policy_version 63781 (0.0007) -[2023-10-09 10:50:15,234][23469] Updated weights for policy 1, policy_version 63791 (0.0009) -[2023-10-09 10:50:15,608][23469] Updated weights for policy 1, policy_version 63801 (0.0009) -[2023-10-09 10:50:16,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 130318336. Throughput: 0: 1772.4, 1: 1790.6. Samples: 32586614. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 10:50:16,078][22500] Avg episode reward: [(0, '9.650'), (1, '8.510')] -[2023-10-09 10:50:16,086][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000063456_64978944.pth... -[2023-10-09 10:50:16,086][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000063808_65339392.pth... -[2023-10-09 10:50:16,122][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000062112_63602688.pth -[2023-10-09 10:50:16,124][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000061792_63275008.pth -[2023-10-09 10:50:17,593][23468] Updated weights for policy 0, policy_version 63463 (0.0009) -[2023-10-09 10:50:17,953][23468] Updated weights for policy 0, policy_version 63473 (0.0007) -[2023-10-09 10:50:18,316][23468] Updated weights for policy 0, policy_version 63483 (0.0007) -[2023-10-09 10:50:19,332][23469] Updated weights for policy 1, policy_version 63811 (0.0010) -[2023-10-09 10:50:19,703][23469] Updated weights for policy 1, policy_version 63821 (0.0009) -[2023-10-09 10:50:20,073][23469] Updated weights for policy 1, policy_version 63831 (0.0008) -[2023-10-09 10:50:21,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 130383872. Throughput: 0: 1785.5, 1: 1800.3. Samples: 32598226. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:50:21,078][22500] Avg episode reward: [(0, '9.780'), (1, '8.670')] -[2023-10-09 10:50:22,160][23468] Updated weights for policy 0, policy_version 63493 (0.0009) -[2023-10-09 10:50:22,536][23468] Updated weights for policy 0, policy_version 63503 (0.0007) -[2023-10-09 10:50:22,912][23468] Updated weights for policy 0, policy_version 63513 (0.0007) -[2023-10-09 10:50:23,905][23469] Updated weights for policy 1, policy_version 63841 (0.0008) -[2023-10-09 10:50:24,280][23469] Updated weights for policy 1, policy_version 63851 (0.0007) -[2023-10-09 10:50:24,641][23469] Updated weights for policy 1, policy_version 63861 (0.0007) -[2023-10-09 10:50:25,022][23469] Updated weights for policy 1, policy_version 63871 (0.0007) -[2023-10-09 10:50:26,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 130449408. Throughput: 0: 1771.7, 1: 1788.2. Samples: 32618910. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:50:26,078][22500] Avg episode reward: [(0, '10.120'), (1, '8.940')] -[2023-10-09 10:50:26,698][23468] Updated weights for policy 0, policy_version 63523 (0.0010) -[2023-10-09 10:50:27,082][23468] Updated weights for policy 0, policy_version 63533 (0.0009) -[2023-10-09 10:50:27,460][23468] Updated weights for policy 0, policy_version 63543 (0.0009) -[2023-10-09 10:50:28,637][23469] Updated weights for policy 1, policy_version 63881 (0.0010) -[2023-10-09 10:50:29,018][23469] Updated weights for policy 1, policy_version 63891 (0.0010) -[2023-10-09 10:50:29,392][23469] Updated weights for policy 1, policy_version 63901 (0.0011) -[2023-10-09 10:50:31,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 130514944. Throughput: 0: 1781.3, 1: 1787.9. Samples: 32641130. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:50:31,078][22500] Avg episode reward: [(0, '9.860'), (1, '8.600')] -[2023-10-09 10:50:31,245][23468] Updated weights for policy 0, policy_version 63553 (0.0008) -[2023-10-09 10:50:31,620][23468] Updated weights for policy 0, policy_version 63563 (0.0009) -[2023-10-09 10:50:31,989][23468] Updated weights for policy 0, policy_version 63573 (0.0009) -[2023-10-09 10:50:32,367][23468] Updated weights for policy 0, policy_version 63583 (0.0008) -[2023-10-09 10:50:33,103][23469] Updated weights for policy 1, policy_version 63911 (0.0008) -[2023-10-09 10:50:33,475][23469] Updated weights for policy 1, policy_version 63921 (0.0009) -[2023-10-09 10:50:33,855][23469] Updated weights for policy 1, policy_version 63931 (0.0009) -[2023-10-09 10:50:36,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 130580480. Throughput: 0: 1778.7, 1: 1797.4. Samples: 32651332. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:50:36,078][22500] Avg episode reward: [(0, '9.810'), (1, '9.350')] -[2023-10-09 10:50:36,165][23468] Updated weights for policy 0, policy_version 63593 (0.0008) -[2023-10-09 10:50:36,544][23468] Updated weights for policy 0, policy_version 63603 (0.0007) -[2023-10-09 10:50:36,914][23468] Updated weights for policy 0, policy_version 63613 (0.0008) -[2023-10-09 10:50:37,527][23469] Updated weights for policy 1, policy_version 63941 (0.0009) -[2023-10-09 10:50:37,889][23469] Updated weights for policy 1, policy_version 63951 (0.0007) -[2023-10-09 10:50:38,253][23469] Updated weights for policy 1, policy_version 63961 (0.0008) -[2023-10-09 10:50:40,504][23468] Updated weights for policy 0, policy_version 63623 (0.0009) -[2023-10-09 10:50:40,874][23468] Updated weights for policy 0, policy_version 63633 (0.0008) -[2023-10-09 10:50:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 130646016. Throughput: 0: 1777.7, 1: 1794.0. Samples: 32673428. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:50:41,078][22500] Avg episode reward: [(0, '9.850'), (1, '9.660')] -[2023-10-09 10:50:41,252][23468] Updated weights for policy 0, policy_version 63643 (0.0009) -[2023-10-09 10:50:41,913][23469] Updated weights for policy 1, policy_version 63971 (0.0008) -[2023-10-09 10:50:42,287][23469] Updated weights for policy 1, policy_version 63981 (0.0008) -[2023-10-09 10:50:42,661][23469] Updated weights for policy 1, policy_version 63991 (0.0008) -[2023-10-09 10:50:45,111][23468] Updated weights for policy 0, policy_version 63653 (0.0008) -[2023-10-09 10:50:45,489][23468] Updated weights for policy 0, policy_version 63663 (0.0009) -[2023-10-09 10:50:45,862][23468] Updated weights for policy 0, policy_version 63673 (0.0009) -[2023-10-09 10:50:46,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 130711552. Throughput: 0: 1805.6, 1: 1791.1. Samples: 32695376. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:50:46,078][22500] Avg episode reward: [(0, '9.790'), (1, '9.230')] -[2023-10-09 10:50:46,409][23469] Updated weights for policy 1, policy_version 64001 (0.0009) -[2023-10-09 10:50:46,784][23469] Updated weights for policy 1, policy_version 64011 (0.0007) -[2023-10-09 10:50:47,152][23469] Updated weights for policy 1, policy_version 64021 (0.0007) -[2023-10-09 10:50:47,522][23469] Updated weights for policy 1, policy_version 64031 (0.0008) -[2023-10-09 10:50:49,482][23468] Updated weights for policy 0, policy_version 63683 (0.0009) -[2023-10-09 10:50:49,851][23468] Updated weights for policy 0, policy_version 63693 (0.0009) -[2023-10-09 10:50:50,231][23468] Updated weights for policy 0, policy_version 63703 (0.0007) -[2023-10-09 10:50:51,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 130809856. Throughput: 0: 1789.8, 1: 1798.3. Samples: 32705784. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:50:51,078][22500] Avg episode reward: [(0, '10.040'), (1, '8.760')] -[2023-10-09 10:50:51,199][23469] Updated weights for policy 1, policy_version 64041 (0.0009) -[2023-10-09 10:50:51,579][23469] Updated weights for policy 1, policy_version 64051 (0.0008) -[2023-10-09 10:50:51,956][23469] Updated weights for policy 1, policy_version 64061 (0.0008) -[2023-10-09 10:50:53,965][23468] Updated weights for policy 0, policy_version 63713 (0.0007) -[2023-10-09 10:50:54,339][23468] Updated weights for policy 0, policy_version 63723 (0.0008) -[2023-10-09 10:50:54,719][23468] Updated weights for policy 0, policy_version 63733 (0.0008) -[2023-10-09 10:50:55,095][23468] Updated weights for policy 0, policy_version 63743 (0.0009) -[2023-10-09 10:50:55,680][23469] Updated weights for policy 1, policy_version 64071 (0.0010) -[2023-10-09 10:50:56,048][23469] Updated weights for policy 1, policy_version 64081 (0.0011) -[2023-10-09 10:50:56,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 130875392. Throughput: 0: 1801.0, 1: 1806.0. Samples: 32727890. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:50:56,079][22500] Avg episode reward: [(0, '9.770'), (1, '8.970')] -[2023-10-09 10:50:56,414][23469] Updated weights for policy 1, policy_version 64091 (0.0007) -[2023-10-09 10:50:58,784][23468] Updated weights for policy 0, policy_version 63753 (0.0008) -[2023-10-09 10:50:59,162][23468] Updated weights for policy 0, policy_version 63763 (0.0009) -[2023-10-09 10:50:59,536][23468] Updated weights for policy 0, policy_version 63773 (0.0008) -[2023-10-09 10:51:00,094][23469] Updated weights for policy 1, policy_version 64101 (0.0010) -[2023-10-09 10:51:00,470][23469] Updated weights for policy 1, policy_version 64111 (0.0010) -[2023-10-09 10:51:00,844][23469] Updated weights for policy 1, policy_version 64121 (0.0010) -[2023-10-09 10:51:01,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 130940928. Throughput: 0: 1785.2, 1: 1811.6. Samples: 32748470. Policy #0 lag: (min: 31.0, avg: 42.2, max: 63.0) -[2023-10-09 10:51:01,078][22500] Avg episode reward: [(0, '10.020'), (1, '8.730')] -[2023-10-09 10:51:03,219][23468] Updated weights for policy 0, policy_version 63783 (0.0008) -[2023-10-09 10:51:03,596][23468] Updated weights for policy 0, policy_version 63793 (0.0007) -[2023-10-09 10:51:03,964][23468] Updated weights for policy 0, policy_version 63803 (0.0008) -[2023-10-09 10:51:04,589][23469] Updated weights for policy 1, policy_version 64131 (0.0011) -[2023-10-09 10:51:04,959][23469] Updated weights for policy 1, policy_version 64141 (0.0009) -[2023-10-09 10:51:05,330][23469] Updated weights for policy 1, policy_version 64151 (0.0007) -[2023-10-09 10:51:06,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 131039232. Throughput: 0: 1805.8, 1: 1799.7. Samples: 32760472. Policy #0 lag: (min: 31.0, avg: 42.2, max: 63.0) -[2023-10-09 10:51:06,078][22500] Avg episode reward: [(0, '9.310'), (1, '9.130')] -[2023-10-09 10:51:07,830][23468] Updated weights for policy 0, policy_version 63813 (0.0008) -[2023-10-09 10:51:08,206][23468] Updated weights for policy 0, policy_version 63823 (0.0008) -[2023-10-09 10:51:08,585][23468] Updated weights for policy 0, policy_version 63833 (0.0009) -[2023-10-09 10:51:09,235][23469] Updated weights for policy 1, policy_version 64161 (0.0009) -[2023-10-09 10:51:09,602][23469] Updated weights for policy 1, policy_version 64171 (0.0007) -[2023-10-09 10:51:09,980][23469] Updated weights for policy 1, policy_version 64181 (0.0007) -[2023-10-09 10:51:10,341][23469] Updated weights for policy 1, policy_version 64191 (0.0010) -[2023-10-09 10:51:11,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 131104768. Throughput: 0: 1794.7, 1: 1811.5. Samples: 32781190. Policy #0 lag: (min: 31.0, avg: 42.2, max: 63.0) -[2023-10-09 10:51:11,078][22500] Avg episode reward: [(0, '9.660'), (1, '8.280')] -[2023-10-09 10:51:12,260][23468] Updated weights for policy 0, policy_version 63843 (0.0010) -[2023-10-09 10:51:12,630][23468] Updated weights for policy 0, policy_version 63853 (0.0007) -[2023-10-09 10:51:13,002][23468] Updated weights for policy 0, policy_version 63863 (0.0007) -[2023-10-09 10:51:14,124][23469] Updated weights for policy 1, policy_version 64201 (0.0009) -[2023-10-09 10:51:14,497][23469] Updated weights for policy 1, policy_version 64211 (0.0009) -[2023-10-09 10:51:14,874][23469] Updated weights for policy 1, policy_version 64221 (0.0007) -[2023-10-09 10:51:16,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 131170304. Throughput: 0: 1794.2, 1: 1800.1. Samples: 32802874. Policy #0 lag: (min: 31.0, avg: 42.2, max: 63.0) -[2023-10-09 10:51:16,079][22500] Avg episode reward: [(0, '10.540'), (1, '8.800')] -[2023-10-09 10:51:16,091][23265] Saving new best policy, reward=10.540! -[2023-10-09 10:51:16,662][23468] Updated weights for policy 0, policy_version 63873 (0.0007) -[2023-10-09 10:51:17,042][23468] Updated weights for policy 0, policy_version 63883 (0.0007) -[2023-10-09 10:51:17,413][23468] Updated weights for policy 0, policy_version 63893 (0.0007) -[2023-10-09 10:51:17,784][23468] Updated weights for policy 0, policy_version 63903 (0.0007) -[2023-10-09 10:51:18,394][23469] Updated weights for policy 1, policy_version 64231 (0.0008) -[2023-10-09 10:51:18,774][23469] Updated weights for policy 1, policy_version 64241 (0.0008) -[2023-10-09 10:51:19,139][23469] Updated weights for policy 1, policy_version 64251 (0.0009) -[2023-10-09 10:51:21,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 131235840. Throughput: 0: 1793.7, 1: 1807.2. Samples: 32813374. Policy #0 lag: (min: 31.0, avg: 42.2, max: 63.0) -[2023-10-09 10:51:21,078][22500] Avg episode reward: [(0, '10.200'), (1, '8.190')] -[2023-10-09 10:51:21,683][23468] Updated weights for policy 0, policy_version 63913 (0.0009) -[2023-10-09 10:51:22,057][23468] Updated weights for policy 0, policy_version 63923 (0.0008) -[2023-10-09 10:51:22,426][23468] Updated weights for policy 0, policy_version 63933 (0.0007) -[2023-10-09 10:51:22,892][23469] Updated weights for policy 1, policy_version 64261 (0.0008) -[2023-10-09 10:51:23,264][23469] Updated weights for policy 1, policy_version 64271 (0.0011) -[2023-10-09 10:51:23,632][23469] Updated weights for policy 1, policy_version 64281 (0.0008) -[2023-10-09 10:51:26,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 131301376. Throughput: 0: 1794.5, 1: 1798.0. Samples: 32835092. Policy #0 lag: (min: 31.0, avg: 42.2, max: 63.0) -[2023-10-09 10:51:26,078][22500] Avg episode reward: [(0, '10.110'), (1, '9.170')] -[2023-10-09 10:51:26,141][23468] Updated weights for policy 0, policy_version 63943 (0.0008) -[2023-10-09 10:51:26,516][23468] Updated weights for policy 0, policy_version 63953 (0.0007) -[2023-10-09 10:51:26,902][23468] Updated weights for policy 0, policy_version 63963 (0.0010) -[2023-10-09 10:51:27,314][23469] Updated weights for policy 1, policy_version 64291 (0.0010) -[2023-10-09 10:51:27,695][23469] Updated weights for policy 1, policy_version 64301 (0.0009) -[2023-10-09 10:51:28,072][23469] Updated weights for policy 1, policy_version 64311 (0.0008) -[2023-10-09 10:51:30,656][23468] Updated weights for policy 0, policy_version 63973 (0.0010) -[2023-10-09 10:51:31,031][23468] Updated weights for policy 0, policy_version 63983 (0.0009) -[2023-10-09 10:51:31,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 131366912. Throughput: 0: 1805.7, 1: 1797.5. Samples: 32857522. Policy #0 lag: (min: 31.0, avg: 42.2, max: 63.0) -[2023-10-09 10:51:31,078][22500] Avg episode reward: [(0, '10.690'), (1, '8.980')] -[2023-10-09 10:51:31,395][23468] Updated weights for policy 0, policy_version 63993 (0.0007) -[2023-10-09 10:51:31,651][23265] Saving new best policy, reward=10.690! -[2023-10-09 10:51:31,795][23469] Updated weights for policy 1, policy_version 64321 (0.0010) -[2023-10-09 10:51:32,177][23469] Updated weights for policy 1, policy_version 64331 (0.0007) -[2023-10-09 10:51:32,547][23469] Updated weights for policy 1, policy_version 64341 (0.0007) -[2023-10-09 10:51:32,914][23469] Updated weights for policy 1, policy_version 64351 (0.0007) -[2023-10-09 10:51:35,285][23468] Updated weights for policy 0, policy_version 64003 (0.0007) -[2023-10-09 10:51:35,652][23468] Updated weights for policy 0, policy_version 64013 (0.0007) -[2023-10-09 10:51:36,017][23468] Updated weights for policy 0, policy_version 64023 (0.0008) -[2023-10-09 10:51:36,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 131432448. Throughput: 0: 1793.8, 1: 1800.4. Samples: 32867522. Policy #0 lag: (min: 31.0, avg: 42.2, max: 63.0) -[2023-10-09 10:51:36,078][22500] Avg episode reward: [(0, '10.040'), (1, '8.860')] -[2023-10-09 10:51:36,687][23469] Updated weights for policy 1, policy_version 64361 (0.0007) -[2023-10-09 10:51:37,062][23469] Updated weights for policy 1, policy_version 64371 (0.0010) -[2023-10-09 10:51:37,434][23469] Updated weights for policy 1, policy_version 64381 (0.0009) -[2023-10-09 10:51:39,781][23468] Updated weights for policy 0, policy_version 64033 (0.0008) -[2023-10-09 10:51:40,148][23468] Updated weights for policy 0, policy_version 64043 (0.0007) -[2023-10-09 10:51:40,522][23468] Updated weights for policy 0, policy_version 64053 (0.0011) -[2023-10-09 10:51:40,897][23468] Updated weights for policy 0, policy_version 64063 (0.0009) -[2023-10-09 10:51:41,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 131530752. Throughput: 0: 1804.4, 1: 1788.8. Samples: 32889586. Policy #0 lag: (min: 24.0, avg: 45.8, max: 48.0) -[2023-10-09 10:51:41,079][22500] Avg episode reward: [(0, '10.220'), (1, '8.450')] -[2023-10-09 10:51:41,251][23469] Updated weights for policy 1, policy_version 64391 (0.0007) -[2023-10-09 10:51:41,624][23469] Updated weights for policy 1, policy_version 64401 (0.0011) -[2023-10-09 10:51:41,996][23469] Updated weights for policy 1, policy_version 64411 (0.0010) -[2023-10-09 10:51:44,610][23468] Updated weights for policy 0, policy_version 64073 (0.0007) -[2023-10-09 10:51:44,979][23468] Updated weights for policy 0, policy_version 64083 (0.0007) -[2023-10-09 10:51:45,359][23468] Updated weights for policy 0, policy_version 64093 (0.0007) -[2023-10-09 10:51:45,879][23469] Updated weights for policy 1, policy_version 64421 (0.0008) -[2023-10-09 10:51:46,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 131596288. Throughput: 0: 1802.3, 1: 1801.2. Samples: 32910628. Policy #0 lag: (min: 24.0, avg: 45.8, max: 48.0) -[2023-10-09 10:51:46,078][22500] Avg episode reward: [(0, '10.380'), (1, '8.300')] -[2023-10-09 10:51:46,246][23469] Updated weights for policy 1, policy_version 64431 (0.0008) -[2023-10-09 10:51:46,625][23469] Updated weights for policy 1, policy_version 64441 (0.0009) -[2023-10-09 10:51:48,975][23468] Updated weights for policy 0, policy_version 64103 (0.0011) -[2023-10-09 10:51:49,349][23468] Updated weights for policy 0, policy_version 64113 (0.0009) -[2023-10-09 10:51:49,731][23468] Updated weights for policy 0, policy_version 64123 (0.0008) -[2023-10-09 10:51:50,283][23469] Updated weights for policy 1, policy_version 64451 (0.0009) -[2023-10-09 10:51:50,649][23469] Updated weights for policy 1, policy_version 64461 (0.0010) -[2023-10-09 10:51:51,018][23469] Updated weights for policy 1, policy_version 64471 (0.0011) -[2023-10-09 10:51:51,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 131661824. Throughput: 0: 1801.6, 1: 1783.0. Samples: 32921782. Policy #0 lag: (min: 24.0, avg: 45.8, max: 48.0) -[2023-10-09 10:51:51,078][22500] Avg episode reward: [(0, '9.280'), (1, '8.280')] -[2023-10-09 10:51:53,469][23468] Updated weights for policy 0, policy_version 64133 (0.0008) -[2023-10-09 10:51:53,836][23468] Updated weights for policy 0, policy_version 64143 (0.0010) -[2023-10-09 10:51:54,218][23468] Updated weights for policy 0, policy_version 64153 (0.0011) -[2023-10-09 10:51:54,800][23469] Updated weights for policy 1, policy_version 64481 (0.0008) -[2023-10-09 10:51:55,176][23469] Updated weights for policy 1, policy_version 64491 (0.0007) -[2023-10-09 10:51:55,540][23469] Updated weights for policy 1, policy_version 64501 (0.0009) -[2023-10-09 10:51:55,920][23469] Updated weights for policy 1, policy_version 64511 (0.0007) -[2023-10-09 10:51:56,078][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 131760128. Throughput: 0: 1798.4, 1: 1801.2. Samples: 32943174. Policy #0 lag: (min: 24.0, avg: 45.8, max: 48.0) -[2023-10-09 10:51:56,079][22500] Avg episode reward: [(0, '9.830'), (1, '8.480')] -[2023-10-09 10:51:58,021][23468] Updated weights for policy 0, policy_version 64163 (0.0010) -[2023-10-09 10:51:58,390][23468] Updated weights for policy 0, policy_version 64173 (0.0010) -[2023-10-09 10:51:58,768][23468] Updated weights for policy 0, policy_version 64183 (0.0010) -[2023-10-09 10:51:59,730][23469] Updated weights for policy 1, policy_version 64521 (0.0008) -[2023-10-09 10:52:00,107][23469] Updated weights for policy 1, policy_version 64531 (0.0010) -[2023-10-09 10:52:00,478][23469] Updated weights for policy 1, policy_version 64541 (0.0010) -[2023-10-09 10:52:01,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.2). Total num frames: 131825664. Throughput: 0: 1785.9, 1: 1787.1. Samples: 32963658. Policy #0 lag: (min: 24.0, avg: 45.8, max: 48.0) -[2023-10-09 10:52:01,078][22500] Avg episode reward: [(0, '9.860'), (1, '8.010')] -[2023-10-09 10:52:02,437][23468] Updated weights for policy 0, policy_version 64193 (0.0008) -[2023-10-09 10:52:02,800][23468] Updated weights for policy 0, policy_version 64203 (0.0007) -[2023-10-09 10:52:03,184][23468] Updated weights for policy 0, policy_version 64213 (0.0007) -[2023-10-09 10:52:03,556][23468] Updated weights for policy 0, policy_version 64223 (0.0008) -[2023-10-09 10:52:04,092][23469] Updated weights for policy 1, policy_version 64551 (0.0008) -[2023-10-09 10:52:04,463][23469] Updated weights for policy 1, policy_version 64561 (0.0008) -[2023-10-09 10:52:04,824][23469] Updated weights for policy 1, policy_version 64571 (0.0007) -[2023-10-09 10:52:06,078][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 131891200. Throughput: 0: 1797.4, 1: 1804.9. Samples: 32975476. Policy #0 lag: (min: 24.0, avg: 45.8, max: 48.0) -[2023-10-09 10:52:06,079][22500] Avg episode reward: [(0, '10.000'), (1, '8.380')] -[2023-10-09 10:52:07,362][23468] Updated weights for policy 0, policy_version 64233 (0.0010) -[2023-10-09 10:52:07,736][23468] Updated weights for policy 0, policy_version 64243 (0.0008) -[2023-10-09 10:52:08,113][23468] Updated weights for policy 0, policy_version 64253 (0.0007) -[2023-10-09 10:52:08,466][23469] Updated weights for policy 1, policy_version 64581 (0.0007) -[2023-10-09 10:52:08,840][23469] Updated weights for policy 1, policy_version 64591 (0.0010) -[2023-10-09 10:52:09,206][23469] Updated weights for policy 1, policy_version 64601 (0.0011) -[2023-10-09 10:52:11,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 131956736. Throughput: 0: 1789.9, 1: 1788.1. Samples: 32996102. Policy #0 lag: (min: 24.0, avg: 45.8, max: 48.0) -[2023-10-09 10:52:11,078][22500] Avg episode reward: [(0, '10.130'), (1, '8.440')] -[2023-10-09 10:52:11,783][23468] Updated weights for policy 0, policy_version 64263 (0.0010) -[2023-10-09 10:52:12,162][23468] Updated weights for policy 0, policy_version 64273 (0.0009) -[2023-10-09 10:52:12,529][23468] Updated weights for policy 0, policy_version 64283 (0.0009) -[2023-10-09 10:52:13,094][23469] Updated weights for policy 1, policy_version 64611 (0.0011) -[2023-10-09 10:52:13,464][23469] Updated weights for policy 1, policy_version 64621 (0.0009) -[2023-10-09 10:52:13,835][23469] Updated weights for policy 1, policy_version 64631 (0.0008) -[2023-10-09 10:52:16,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 132022272. Throughput: 0: 1786.9, 1: 1786.5. Samples: 33018324. Policy #0 lag: (min: 24.0, avg: 45.8, max: 48.0) -[2023-10-09 10:52:16,078][22500] Avg episode reward: [(0, '10.150'), (1, '8.350')] -[2023-10-09 10:52:16,089][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000064288_65830912.pth... -[2023-10-09 10:52:16,089][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000064640_66191360.pth... -[2023-10-09 10:52:16,125][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000062944_64454656.pth -[2023-10-09 10:52:16,133][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000062624_64126976.pth -[2023-10-09 10:52:16,632][23468] Updated weights for policy 0, policy_version 64293 (0.0008) -[2023-10-09 10:52:17,019][23468] Updated weights for policy 0, policy_version 64303 (0.0007) -[2023-10-09 10:52:17,395][23468] Updated weights for policy 0, policy_version 64313 (0.0007) -[2023-10-09 10:52:17,607][23469] Updated weights for policy 1, policy_version 64641 (0.0009) -[2023-10-09 10:52:17,970][23469] Updated weights for policy 1, policy_version 64651 (0.0008) -[2023-10-09 10:52:18,337][23469] Updated weights for policy 1, policy_version 64661 (0.0008) -[2023-10-09 10:52:18,702][23469] Updated weights for policy 1, policy_version 64671 (0.0007) -[2023-10-09 10:52:21,069][23468] Updated weights for policy 0, policy_version 64323 (0.0007) -[2023-10-09 10:52:21,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 132087808. Throughput: 0: 1782.5, 1: 1781.7. Samples: 33027914. Policy #0 lag: (min: 24.0, avg: 45.8, max: 48.0) -[2023-10-09 10:52:21,079][22500] Avg episode reward: [(0, '10.220'), (1, '8.460')] -[2023-10-09 10:52:21,442][23468] Updated weights for policy 0, policy_version 64333 (0.0007) -[2023-10-09 10:52:21,824][23468] Updated weights for policy 0, policy_version 64343 (0.0008) -[2023-10-09 10:52:22,537][23469] Updated weights for policy 1, policy_version 64681 (0.0009) -[2023-10-09 10:52:22,900][23469] Updated weights for policy 1, policy_version 64691 (0.0009) -[2023-10-09 10:52:23,279][23469] Updated weights for policy 1, policy_version 64701 (0.0007) -[2023-10-09 10:52:25,543][23468] Updated weights for policy 0, policy_version 64353 (0.0008) -[2023-10-09 10:52:25,915][23468] Updated weights for policy 0, policy_version 64363 (0.0009) -[2023-10-09 10:52:26,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 132153344. Throughput: 0: 1782.6, 1: 1783.6. Samples: 33050064. Policy #0 lag: (min: 17.0, avg: 25.0, max: 49.0) -[2023-10-09 10:52:26,078][22500] Avg episode reward: [(0, '9.730'), (1, '8.450')] -[2023-10-09 10:52:26,288][23468] Updated weights for policy 0, policy_version 64373 (0.0009) -[2023-10-09 10:52:26,652][23468] Updated weights for policy 0, policy_version 64383 (0.0007) -[2023-10-09 10:52:27,014][23469] Updated weights for policy 1, policy_version 64711 (0.0008) -[2023-10-09 10:52:27,390][23469] Updated weights for policy 1, policy_version 64721 (0.0011) -[2023-10-09 10:52:27,756][23469] Updated weights for policy 1, policy_version 64731 (0.0009) -[2023-10-09 10:52:30,400][23468] Updated weights for policy 0, policy_version 64393 (0.0008) -[2023-10-09 10:52:30,767][23468] Updated weights for policy 0, policy_version 64403 (0.0010) -[2023-10-09 10:52:31,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 132218880. Throughput: 0: 1799.2, 1: 1790.4. Samples: 33072164. Policy #0 lag: (min: 17.0, avg: 25.0, max: 49.0) -[2023-10-09 10:52:31,079][22500] Avg episode reward: [(0, '9.300'), (1, '8.880')] -[2023-10-09 10:52:31,135][23468] Updated weights for policy 0, policy_version 64413 (0.0009) -[2023-10-09 10:52:31,626][23469] Updated weights for policy 1, policy_version 64741 (0.0009) -[2023-10-09 10:52:31,994][23469] Updated weights for policy 1, policy_version 64751 (0.0010) -[2023-10-09 10:52:32,362][23469] Updated weights for policy 1, policy_version 64761 (0.0010) -[2023-10-09 10:52:34,780][23468] Updated weights for policy 0, policy_version 64423 (0.0007) -[2023-10-09 10:52:35,154][23468] Updated weights for policy 0, policy_version 64433 (0.0008) -[2023-10-09 10:52:35,524][23468] Updated weights for policy 0, policy_version 64443 (0.0008) -[2023-10-09 10:52:36,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 132317184. Throughput: 0: 1779.3, 1: 1789.0. Samples: 33082358. Policy #0 lag: (min: 17.0, avg: 25.0, max: 49.0) -[2023-10-09 10:52:36,078][22500] Avg episode reward: [(0, '9.300'), (1, '9.210')] -[2023-10-09 10:52:36,118][23469] Updated weights for policy 1, policy_version 64771 (0.0011) -[2023-10-09 10:52:36,487][23469] Updated weights for policy 1, policy_version 64781 (0.0010) -[2023-10-09 10:52:36,854][23469] Updated weights for policy 1, policy_version 64791 (0.0009) -[2023-10-09 10:52:39,221][23468] Updated weights for policy 0, policy_version 64453 (0.0010) -[2023-10-09 10:52:39,598][23468] Updated weights for policy 0, policy_version 64463 (0.0009) -[2023-10-09 10:52:39,967][23468] Updated weights for policy 0, policy_version 64473 (0.0008) -[2023-10-09 10:52:40,472][23469] Updated weights for policy 1, policy_version 64801 (0.0009) -[2023-10-09 10:52:40,839][23469] Updated weights for policy 1, policy_version 64811 (0.0008) -[2023-10-09 10:52:41,077][22500] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 132382720. Throughput: 0: 1796.6, 1: 1791.2. Samples: 33104626. Policy #0 lag: (min: 17.0, avg: 25.0, max: 49.0) -[2023-10-09 10:52:41,078][22500] Avg episode reward: [(0, '8.850'), (1, '9.260')] -[2023-10-09 10:52:41,218][23469] Updated weights for policy 1, policy_version 64821 (0.0009) -[2023-10-09 10:52:41,596][23469] Updated weights for policy 1, policy_version 64831 (0.0009) -[2023-10-09 10:52:43,720][23468] Updated weights for policy 0, policy_version 64483 (0.0008) -[2023-10-09 10:52:44,093][23468] Updated weights for policy 0, policy_version 64493 (0.0008) -[2023-10-09 10:52:44,463][23468] Updated weights for policy 0, policy_version 64503 (0.0007) -[2023-10-09 10:52:45,328][23469] Updated weights for policy 1, policy_version 64841 (0.0008) -[2023-10-09 10:52:45,687][23469] Updated weights for policy 1, policy_version 64851 (0.0009) -[2023-10-09 10:52:46,053][23469] Updated weights for policy 1, policy_version 64861 (0.0010) -[2023-10-09 10:52:46,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 132448256. Throughput: 0: 1780.8, 1: 1804.7. Samples: 33125004. Policy #0 lag: (min: 17.0, avg: 25.0, max: 49.0) -[2023-10-09 10:52:46,078][22500] Avg episode reward: [(0, '9.660'), (1, '9.320')] -[2023-10-09 10:52:48,317][23468] Updated weights for policy 0, policy_version 64513 (0.0008) -[2023-10-09 10:52:48,685][23468] Updated weights for policy 0, policy_version 64523 (0.0007) -[2023-10-09 10:52:49,056][23468] Updated weights for policy 0, policy_version 64533 (0.0010) -[2023-10-09 10:52:49,425][23468] Updated weights for policy 0, policy_version 64543 (0.0010) -[2023-10-09 10:52:49,770][23469] Updated weights for policy 1, policy_version 64871 (0.0008) -[2023-10-09 10:52:50,132][23469] Updated weights for policy 1, policy_version 64881 (0.0008) -[2023-10-09 10:52:50,513][23469] Updated weights for policy 1, policy_version 64891 (0.0007) -[2023-10-09 10:52:51,078][22500] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 132546560. Throughput: 0: 1803.2, 1: 1787.2. Samples: 33137044. Policy #0 lag: (min: 17.0, avg: 25.0, max: 49.0) -[2023-10-09 10:52:51,078][22500] Avg episode reward: [(0, '9.830'), (1, '8.840')] -[2023-10-09 10:52:53,207][23468] Updated weights for policy 0, policy_version 64553 (0.0008) -[2023-10-09 10:52:53,583][23468] Updated weights for policy 0, policy_version 64563 (0.0008) -[2023-10-09 10:52:53,953][23468] Updated weights for policy 0, policy_version 64573 (0.0008) -[2023-10-09 10:52:54,217][23469] Updated weights for policy 1, policy_version 64901 (0.0009) -[2023-10-09 10:52:54,592][23469] Updated weights for policy 1, policy_version 64911 (0.0009) -[2023-10-09 10:52:54,958][23469] Updated weights for policy 1, policy_version 64921 (0.0009) -[2023-10-09 10:52:56,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 132612096. Throughput: 0: 1775.3, 1: 1800.4. Samples: 33157006. Policy #0 lag: (min: 17.0, avg: 25.0, max: 49.0) -[2023-10-09 10:52:56,078][22500] Avg episode reward: [(0, '9.620'), (1, '8.750')] -[2023-10-09 10:52:57,698][23468] Updated weights for policy 0, policy_version 64583 (0.0008) -[2023-10-09 10:52:58,066][23468] Updated weights for policy 0, policy_version 64593 (0.0012) -[2023-10-09 10:52:58,446][23468] Updated weights for policy 0, policy_version 64603 (0.0009) -[2023-10-09 10:52:58,545][23469] Updated weights for policy 1, policy_version 64931 (0.0009) -[2023-10-09 10:52:58,910][23469] Updated weights for policy 1, policy_version 64941 (0.0009) -[2023-10-09 10:52:59,289][23469] Updated weights for policy 1, policy_version 64951 (0.0010) -[2023-10-09 10:53:01,078][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 132677632. Throughput: 0: 1776.1, 1: 1798.0. Samples: 33179162. Policy #0 lag: (min: 17.0, avg: 25.0, max: 49.0) -[2023-10-09 10:53:01,079][22500] Avg episode reward: [(0, '9.670'), (1, '8.990')] -[2023-10-09 10:53:02,332][23468] Updated weights for policy 0, policy_version 64613 (0.0009) -[2023-10-09 10:53:02,720][23468] Updated weights for policy 0, policy_version 64623 (0.0008) -[2023-10-09 10:53:02,960][23469] Updated weights for policy 1, policy_version 64961 (0.0008) -[2023-10-09 10:53:03,104][23468] Updated weights for policy 0, policy_version 64633 (0.0008) -[2023-10-09 10:53:03,336][23469] Updated weights for policy 1, policy_version 64971 (0.0008) -[2023-10-09 10:53:03,707][23469] Updated weights for policy 1, policy_version 64981 (0.0009) -[2023-10-09 10:53:04,074][23469] Updated weights for policy 1, policy_version 64991 (0.0011) -[2023-10-09 10:53:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 132743168. Throughput: 0: 1779.6, 1: 1811.1. Samples: 33189494. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 10:53:06,078][22500] Avg episode reward: [(0, '9.470'), (1, '8.300')] -[2023-10-09 10:53:06,753][23468] Updated weights for policy 0, policy_version 64643 (0.0009) -[2023-10-09 10:53:07,123][23468] Updated weights for policy 0, policy_version 64653 (0.0009) -[2023-10-09 10:53:07,494][23468] Updated weights for policy 0, policy_version 64663 (0.0010) -[2023-10-09 10:53:07,904][23469] Updated weights for policy 1, policy_version 65001 (0.0007) -[2023-10-09 10:53:08,269][23469] Updated weights for policy 1, policy_version 65011 (0.0011) -[2023-10-09 10:53:08,649][23469] Updated weights for policy 1, policy_version 65021 (0.0008) -[2023-10-09 10:53:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 132808704. Throughput: 0: 1783.7, 1: 1800.1. Samples: 33211334. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 10:53:11,078][22500] Avg episode reward: [(0, '10.470'), (1, '8.110')] -[2023-10-09 10:53:11,187][23468] Updated weights for policy 0, policy_version 64673 (0.0009) -[2023-10-09 10:53:11,558][23468] Updated weights for policy 0, policy_version 64683 (0.0009) -[2023-10-09 10:53:11,927][23468] Updated weights for policy 0, policy_version 64693 (0.0008) -[2023-10-09 10:53:12,304][23468] Updated weights for policy 0, policy_version 64703 (0.0008) -[2023-10-09 10:53:12,323][23469] Updated weights for policy 1, policy_version 65031 (0.0008) -[2023-10-09 10:53:12,691][23469] Updated weights for policy 1, policy_version 65041 (0.0009) -[2023-10-09 10:53:13,068][23469] Updated weights for policy 1, policy_version 65051 (0.0007) -[2023-10-09 10:53:16,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 132874240. Throughput: 0: 1792.0, 1: 1802.0. Samples: 33233894. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 10:53:16,078][22500] Avg episode reward: [(0, '10.780'), (1, '8.570')] -[2023-10-09 10:53:16,150][23468] Updated weights for policy 0, policy_version 64713 (0.0009) -[2023-10-09 10:53:16,519][23468] Updated weights for policy 0, policy_version 64723 (0.0008) -[2023-10-09 10:53:16,876][23469] Updated weights for policy 1, policy_version 65061 (0.0008) -[2023-10-09 10:53:16,881][23468] Updated weights for policy 0, policy_version 64733 (0.0008) -[2023-10-09 10:53:16,990][23265] Saving new best policy, reward=10.780! -[2023-10-09 10:53:17,252][23469] Updated weights for policy 1, policy_version 65071 (0.0011) -[2023-10-09 10:53:17,622][23469] Updated weights for policy 1, policy_version 65081 (0.0007) -[2023-10-09 10:53:20,661][23468] Updated weights for policy 0, policy_version 64743 (0.0009) -[2023-10-09 10:53:21,034][23468] Updated weights for policy 0, policy_version 64753 (0.0008) -[2023-10-09 10:53:21,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 132939776. Throughput: 0: 1780.4, 1: 1799.7. Samples: 33243464. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 10:53:21,078][22500] Avg episode reward: [(0, '10.540'), (1, '8.450')] -[2023-10-09 10:53:21,394][23468] Updated weights for policy 0, policy_version 64763 (0.0008) -[2023-10-09 10:53:21,481][23469] Updated weights for policy 1, policy_version 65091 (0.0008) -[2023-10-09 10:53:21,855][23469] Updated weights for policy 1, policy_version 65101 (0.0008) -[2023-10-09 10:53:22,219][23469] Updated weights for policy 1, policy_version 65111 (0.0010) -[2023-10-09 10:53:25,242][23468] Updated weights for policy 0, policy_version 64773 (0.0008) -[2023-10-09 10:53:25,608][23468] Updated weights for policy 0, policy_version 64783 (0.0009) -[2023-10-09 10:53:25,992][23468] Updated weights for policy 0, policy_version 64793 (0.0010) -[2023-10-09 10:53:26,039][23469] Updated weights for policy 1, policy_version 65121 (0.0009) -[2023-10-09 10:53:26,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 133005312. Throughput: 0: 1787.2, 1: 1791.6. Samples: 33265676. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 10:53:26,078][22500] Avg episode reward: [(0, '10.370'), (1, '8.740')] -[2023-10-09 10:53:26,411][23469] Updated weights for policy 1, policy_version 65131 (0.0009) -[2023-10-09 10:53:26,781][23469] Updated weights for policy 1, policy_version 65141 (0.0007) -[2023-10-09 10:53:27,154][23469] Updated weights for policy 1, policy_version 65151 (0.0008) -[2023-10-09 10:53:29,742][23468] Updated weights for policy 0, policy_version 64803 (0.0007) -[2023-10-09 10:53:30,114][23468] Updated weights for policy 0, policy_version 64813 (0.0008) -[2023-10-09 10:53:30,494][23468] Updated weights for policy 0, policy_version 64823 (0.0010) -[2023-10-09 10:53:31,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 133103616. Throughput: 0: 1792.7, 1: 1808.3. Samples: 33287048. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 10:53:31,078][22500] Avg episode reward: [(0, '10.060'), (1, '8.890')] -[2023-10-09 10:53:31,148][23469] Updated weights for policy 1, policy_version 65161 (0.0010) -[2023-10-09 10:53:31,524][23469] Updated weights for policy 1, policy_version 65171 (0.0008) -[2023-10-09 10:53:31,889][23469] Updated weights for policy 1, policy_version 65181 (0.0008) -[2023-10-09 10:53:34,210][23468] Updated weights for policy 0, policy_version 64833 (0.0010) -[2023-10-09 10:53:34,593][23468] Updated weights for policy 0, policy_version 64843 (0.0011) -[2023-10-09 10:53:34,975][23468] Updated weights for policy 0, policy_version 64853 (0.0008) -[2023-10-09 10:53:35,353][23468] Updated weights for policy 0, policy_version 64863 (0.0009) -[2023-10-09 10:53:35,448][23469] Updated weights for policy 1, policy_version 65191 (0.0008) -[2023-10-09 10:53:35,805][23469] Updated weights for policy 1, policy_version 65201 (0.0009) -[2023-10-09 10:53:36,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 133169152. Throughput: 0: 1781.1, 1: 1791.7. Samples: 33297818. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 10:53:36,078][22500] Avg episode reward: [(0, '10.060'), (1, '9.390')] -[2023-10-09 10:53:36,178][23469] Updated weights for policy 1, policy_version 65211 (0.0009) -[2023-10-09 10:53:39,178][23468] Updated weights for policy 0, policy_version 64873 (0.0008) -[2023-10-09 10:53:39,548][23468] Updated weights for policy 0, policy_version 64883 (0.0007) -[2023-10-09 10:53:39,843][23469] Updated weights for policy 1, policy_version 65221 (0.0009) -[2023-10-09 10:53:39,911][23468] Updated weights for policy 0, policy_version 64893 (0.0008) -[2023-10-09 10:53:40,208][23469] Updated weights for policy 1, policy_version 65231 (0.0007) -[2023-10-09 10:53:40,577][23469] Updated weights for policy 1, policy_version 65241 (0.0008) -[2023-10-09 10:53:41,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 133267456. Throughput: 0: 1804.0, 1: 1810.3. Samples: 33319650. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 10:53:41,079][22500] Avg episode reward: [(0, '10.170'), (1, '9.160')] -[2023-10-09 10:53:43,596][23468] Updated weights for policy 0, policy_version 64903 (0.0009) -[2023-10-09 10:53:43,968][23468] Updated weights for policy 0, policy_version 64913 (0.0011) -[2023-10-09 10:53:44,343][23468] Updated weights for policy 0, policy_version 64923 (0.0010) -[2023-10-09 10:53:44,376][23469] Updated weights for policy 1, policy_version 65251 (0.0007) -[2023-10-09 10:53:44,750][23469] Updated weights for policy 1, policy_version 65261 (0.0007) -[2023-10-09 10:53:45,122][23469] Updated weights for policy 1, policy_version 65271 (0.0007) -[2023-10-09 10:53:46,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 133332992. Throughput: 0: 1787.0, 1: 1784.8. Samples: 33339892. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:53:46,078][22500] Avg episode reward: [(0, '9.770'), (1, '9.290')] -[2023-10-09 10:53:48,264][23468] Updated weights for policy 0, policy_version 64933 (0.0008) -[2023-10-09 10:53:48,657][23468] Updated weights for policy 0, policy_version 64943 (0.0008) -[2023-10-09 10:53:49,033][23468] Updated weights for policy 0, policy_version 64953 (0.0007) -[2023-10-09 10:53:49,066][23469] Updated weights for policy 1, policy_version 65281 (0.0010) -[2023-10-09 10:53:49,438][23469] Updated weights for policy 1, policy_version 65291 (0.0007) -[2023-10-09 10:53:49,802][23469] Updated weights for policy 1, policy_version 65301 (0.0008) -[2023-10-09 10:53:50,176][23469] Updated weights for policy 1, policy_version 65311 (0.0008) -[2023-10-09 10:53:51,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 133398528. Throughput: 0: 1810.7, 1: 1800.7. Samples: 33352006. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:53:51,078][22500] Avg episode reward: [(0, '10.440'), (1, '9.190')] -[2023-10-09 10:53:52,762][23468] Updated weights for policy 0, policy_version 64963 (0.0008) -[2023-10-09 10:53:53,137][23468] Updated weights for policy 0, policy_version 64973 (0.0010) -[2023-10-09 10:53:53,516][23468] Updated weights for policy 0, policy_version 64983 (0.0010) -[2023-10-09 10:53:53,880][23469] Updated weights for policy 1, policy_version 65321 (0.0007) -[2023-10-09 10:53:54,257][23469] Updated weights for policy 1, policy_version 65331 (0.0009) -[2023-10-09 10:53:54,626][23469] Updated weights for policy 1, policy_version 65341 (0.0009) -[2023-10-09 10:53:56,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 133464064. Throughput: 0: 1779.8, 1: 1784.4. Samples: 33371724. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:53:56,078][22500] Avg episode reward: [(0, '10.770'), (1, '9.470')] -[2023-10-09 10:53:57,247][23468] Updated weights for policy 0, policy_version 64993 (0.0008) -[2023-10-09 10:53:57,624][23468] Updated weights for policy 0, policy_version 65003 (0.0007) -[2023-10-09 10:53:57,992][23468] Updated weights for policy 0, policy_version 65013 (0.0008) -[2023-10-09 10:53:58,369][23468] Updated weights for policy 0, policy_version 65023 (0.0007) -[2023-10-09 10:53:58,444][23469] Updated weights for policy 1, policy_version 65351 (0.0008) -[2023-10-09 10:53:58,815][23469] Updated weights for policy 1, policy_version 65361 (0.0009) -[2023-10-09 10:53:59,186][23469] Updated weights for policy 1, policy_version 65371 (0.0009) -[2023-10-09 10:54:01,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 133529600. Throughput: 0: 1778.8, 1: 1781.4. Samples: 33394106. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:54:01,078][22500] Avg episode reward: [(0, '9.780'), (1, '9.310')] -[2023-10-09 10:54:02,085][23468] Updated weights for policy 0, policy_version 65033 (0.0007) -[2023-10-09 10:54:02,468][23468] Updated weights for policy 0, policy_version 65043 (0.0008) -[2023-10-09 10:54:02,849][23468] Updated weights for policy 0, policy_version 65053 (0.0007) -[2023-10-09 10:54:03,012][23469] Updated weights for policy 1, policy_version 65381 (0.0010) -[2023-10-09 10:54:03,375][23469] Updated weights for policy 1, policy_version 65391 (0.0010) -[2023-10-09 10:54:03,754][23469] Updated weights for policy 1, policy_version 65401 (0.0010) -[2023-10-09 10:54:06,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 133595136. Throughput: 0: 1781.6, 1: 1790.5. Samples: 33404210. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:54:06,078][22500] Avg episode reward: [(0, '10.540'), (1, '9.100')] -[2023-10-09 10:54:06,499][23468] Updated weights for policy 0, policy_version 65063 (0.0009) -[2023-10-09 10:54:06,872][23468] Updated weights for policy 0, policy_version 65073 (0.0007) -[2023-10-09 10:54:07,256][23468] Updated weights for policy 0, policy_version 65083 (0.0009) -[2023-10-09 10:54:07,502][23469] Updated weights for policy 1, policy_version 65411 (0.0009) -[2023-10-09 10:54:07,877][23469] Updated weights for policy 1, policy_version 65421 (0.0008) -[2023-10-09 10:54:08,251][23469] Updated weights for policy 1, policy_version 65431 (0.0008) -[2023-10-09 10:54:11,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 133660672. Throughput: 0: 1780.3, 1: 1786.3. Samples: 33426170. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:54:11,078][22500] Avg episode reward: [(0, '10.320'), (1, '8.830')] -[2023-10-09 10:54:11,119][23468] Updated weights for policy 0, policy_version 65093 (0.0007) -[2023-10-09 10:54:11,488][23468] Updated weights for policy 0, policy_version 65103 (0.0007) -[2023-10-09 10:54:11,868][23468] Updated weights for policy 0, policy_version 65113 (0.0009) -[2023-10-09 10:54:11,900][23469] Updated weights for policy 1, policy_version 65441 (0.0008) -[2023-10-09 10:54:12,267][23469] Updated weights for policy 1, policy_version 65451 (0.0008) -[2023-10-09 10:54:12,633][23469] Updated weights for policy 1, policy_version 65461 (0.0007) -[2023-10-09 10:54:13,005][23469] Updated weights for policy 1, policy_version 65471 (0.0007) -[2023-10-09 10:54:15,576][23468] Updated weights for policy 0, policy_version 65123 (0.0010) -[2023-10-09 10:54:15,949][23468] Updated weights for policy 0, policy_version 65133 (0.0010) -[2023-10-09 10:54:16,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 133726208. Throughput: 0: 1800.4, 1: 1791.7. Samples: 33448692. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:54:16,078][22500] Avg episode reward: [(0, '9.900'), (1, '8.740')] -[2023-10-09 10:54:16,086][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000065472_67043328.pth... -[2023-10-09 10:54:16,118][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000063808_65339392.pth -[2023-10-09 10:54:16,320][23468] Updated weights for policy 0, policy_version 65143 (0.0009) -[2023-10-09 10:54:16,650][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000065152_66715648.pth... -[2023-10-09 10:54:16,681][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000063456_64978944.pth -[2023-10-09 10:54:16,695][23469] Updated weights for policy 1, policy_version 65481 (0.0007) -[2023-10-09 10:54:17,075][23469] Updated weights for policy 1, policy_version 65491 (0.0009) -[2023-10-09 10:54:17,446][23469] Updated weights for policy 1, policy_version 65501 (0.0010) -[2023-10-09 10:54:19,890][23468] Updated weights for policy 0, policy_version 65153 (0.0008) -[2023-10-09 10:54:20,261][23468] Updated weights for policy 0, policy_version 65163 (0.0008) -[2023-10-09 10:54:20,643][23468] Updated weights for policy 0, policy_version 65173 (0.0008) -[2023-10-09 10:54:21,005][23468] Updated weights for policy 0, policy_version 65183 (0.0010) -[2023-10-09 10:54:21,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 133824512. Throughput: 0: 1778.8, 1: 1784.8. Samples: 33458182. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:54:21,078][22500] Avg episode reward: [(0, '10.210'), (1, '8.530')] -[2023-10-09 10:54:21,244][23469] Updated weights for policy 1, policy_version 65511 (0.0008) -[2023-10-09 10:54:21,602][23469] Updated weights for policy 1, policy_version 65521 (0.0009) -[2023-10-09 10:54:21,977][23469] Updated weights for policy 1, policy_version 65531 (0.0010) -[2023-10-09 10:54:24,773][23468] Updated weights for policy 0, policy_version 65193 (0.0007) -[2023-10-09 10:54:25,157][23468] Updated weights for policy 0, policy_version 65203 (0.0007) -[2023-10-09 10:54:25,525][23468] Updated weights for policy 0, policy_version 65213 (0.0009) -[2023-10-09 10:54:25,767][23469] Updated weights for policy 1, policy_version 65541 (0.0010) -[2023-10-09 10:54:26,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 133890048. Throughput: 0: 1794.0, 1: 1786.1. Samples: 33480756. Policy #0 lag: (min: 31.0, avg: 31.9, max: 51.0) -[2023-10-09 10:54:26,078][22500] Avg episode reward: [(0, '10.780'), (1, '8.860')] -[2023-10-09 10:54:26,133][23469] Updated weights for policy 1, policy_version 65551 (0.0008) -[2023-10-09 10:54:26,497][23469] Updated weights for policy 1, policy_version 65561 (0.0008) -[2023-10-09 10:54:29,284][23468] Updated weights for policy 0, policy_version 65223 (0.0009) -[2023-10-09 10:54:29,651][23468] Updated weights for policy 0, policy_version 65233 (0.0009) -[2023-10-09 10:54:30,026][23468] Updated weights for policy 0, policy_version 65243 (0.0011) -[2023-10-09 10:54:30,126][23469] Updated weights for policy 1, policy_version 65571 (0.0007) -[2023-10-09 10:54:30,495][23469] Updated weights for policy 1, policy_version 65581 (0.0010) -[2023-10-09 10:54:30,867][23469] Updated weights for policy 1, policy_version 65591 (0.0009) -[2023-10-09 10:54:31,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 133955584. Throughput: 0: 1778.6, 1: 1799.5. Samples: 33500906. Policy #0 lag: (min: 31.0, avg: 31.9, max: 51.0) -[2023-10-09 10:54:31,078][22500] Avg episode reward: [(0, '10.010'), (1, '8.930')] -[2023-10-09 10:54:33,824][23468] Updated weights for policy 0, policy_version 65253 (0.0009) -[2023-10-09 10:54:34,209][23468] Updated weights for policy 0, policy_version 65263 (0.0008) -[2023-10-09 10:54:34,589][23468] Updated weights for policy 0, policy_version 65273 (0.0008) -[2023-10-09 10:54:34,703][23469] Updated weights for policy 1, policy_version 65601 (0.0009) -[2023-10-09 10:54:35,065][23469] Updated weights for policy 1, policy_version 65611 (0.0008) -[2023-10-09 10:54:35,440][23469] Updated weights for policy 1, policy_version 65621 (0.0008) -[2023-10-09 10:54:35,803][23469] Updated weights for policy 1, policy_version 65631 (0.0008) -[2023-10-09 10:54:36,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 134053888. Throughput: 0: 1790.5, 1: 1792.0. Samples: 33513218. Policy #0 lag: (min: 31.0, avg: 31.9, max: 51.0) -[2023-10-09 10:54:36,078][22500] Avg episode reward: [(0, '9.830'), (1, '9.160')] -[2023-10-09 10:54:38,403][23468] Updated weights for policy 0, policy_version 65283 (0.0007) -[2023-10-09 10:54:38,779][23468] Updated weights for policy 0, policy_version 65293 (0.0007) -[2023-10-09 10:54:39,144][23468] Updated weights for policy 0, policy_version 65303 (0.0009) -[2023-10-09 10:54:39,569][23469] Updated weights for policy 1, policy_version 65641 (0.0008) -[2023-10-09 10:54:39,937][23469] Updated weights for policy 1, policy_version 65651 (0.0007) -[2023-10-09 10:54:40,307][23469] Updated weights for policy 1, policy_version 65661 (0.0008) -[2023-10-09 10:54:41,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 134119424. Throughput: 0: 1789.4, 1: 1809.7. Samples: 33533684. Policy #0 lag: (min: 31.0, avg: 31.9, max: 51.0) -[2023-10-09 10:54:41,079][22500] Avg episode reward: [(0, '8.750'), (1, '9.340')] -[2023-10-09 10:54:42,922][23468] Updated weights for policy 0, policy_version 65313 (0.0008) -[2023-10-09 10:54:43,290][23468] Updated weights for policy 0, policy_version 65323 (0.0008) -[2023-10-09 10:54:43,675][23468] Updated weights for policy 0, policy_version 65333 (0.0009) -[2023-10-09 10:54:43,897][23469] Updated weights for policy 1, policy_version 65671 (0.0009) -[2023-10-09 10:54:44,045][23468] Updated weights for policy 0, policy_version 65343 (0.0008) -[2023-10-09 10:54:44,271][23469] Updated weights for policy 1, policy_version 65681 (0.0007) -[2023-10-09 10:54:44,636][23469] Updated weights for policy 1, policy_version 65691 (0.0007) -[2023-10-09 10:54:46,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 134184960. Throughput: 0: 1780.4, 1: 1792.7. Samples: 33554896. Policy #0 lag: (min: 31.0, avg: 31.9, max: 51.0) -[2023-10-09 10:54:46,078][22500] Avg episode reward: [(0, '9.100'), (1, '8.960')] -[2023-10-09 10:54:47,851][23468] Updated weights for policy 0, policy_version 65353 (0.0008) -[2023-10-09 10:54:48,208][23468] Updated weights for policy 0, policy_version 65363 (0.0009) -[2023-10-09 10:54:48,384][23469] Updated weights for policy 1, policy_version 65701 (0.0009) -[2023-10-09 10:54:48,585][23468] Updated weights for policy 0, policy_version 65373 (0.0009) -[2023-10-09 10:54:48,744][23469] Updated weights for policy 1, policy_version 65711 (0.0007) -[2023-10-09 10:54:49,113][23469] Updated weights for policy 1, policy_version 65721 (0.0008) -[2023-10-09 10:54:51,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 134250496. Throughput: 0: 1790.3, 1: 1806.2. Samples: 33566050. Policy #0 lag: (min: 31.0, avg: 31.9, max: 51.0) -[2023-10-09 10:54:51,078][22500] Avg episode reward: [(0, '10.310'), (1, '9.370')] -[2023-10-09 10:54:52,429][23468] Updated weights for policy 0, policy_version 65383 (0.0008) -[2023-10-09 10:54:52,811][23468] Updated weights for policy 0, policy_version 65393 (0.0009) -[2023-10-09 10:54:52,876][23469] Updated weights for policy 1, policy_version 65731 (0.0008) -[2023-10-09 10:54:53,174][23468] Updated weights for policy 0, policy_version 65403 (0.0009) -[2023-10-09 10:54:53,251][23469] Updated weights for policy 1, policy_version 65741 (0.0007) -[2023-10-09 10:54:53,619][23469] Updated weights for policy 1, policy_version 65751 (0.0007) -[2023-10-09 10:54:56,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 134316032. Throughput: 0: 1780.6, 1: 1798.8. Samples: 33587242. Policy #0 lag: (min: 31.0, avg: 31.9, max: 51.0) -[2023-10-09 10:54:56,079][22500] Avg episode reward: [(0, '10.370'), (1, '8.760')] -[2023-10-09 10:54:56,981][23468] Updated weights for policy 0, policy_version 65413 (0.0007) -[2023-10-09 10:54:57,339][23469] Updated weights for policy 1, policy_version 65761 (0.0009) -[2023-10-09 10:54:57,354][23468] Updated weights for policy 0, policy_version 65423 (0.0010) -[2023-10-09 10:54:57,704][23469] Updated weights for policy 1, policy_version 65771 (0.0007) -[2023-10-09 10:54:57,735][23468] Updated weights for policy 0, policy_version 65433 (0.0007) -[2023-10-09 10:54:58,086][23469] Updated weights for policy 1, policy_version 65781 (0.0009) -[2023-10-09 10:54:58,449][23469] Updated weights for policy 1, policy_version 65791 (0.0010) -[2023-10-09 10:55:01,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 134381568. Throughput: 0: 1777.2, 1: 1797.9. Samples: 33609572. Policy #0 lag: (min: 31.0, avg: 31.9, max: 51.0) -[2023-10-09 10:55:01,078][22500] Avg episode reward: [(0, '10.180'), (1, '8.700')] -[2023-10-09 10:55:01,556][23468] Updated weights for policy 0, policy_version 65443 (0.0009) -[2023-10-09 10:55:01,927][23468] Updated weights for policy 0, policy_version 65453 (0.0008) -[2023-10-09 10:55:02,233][23469] Updated weights for policy 1, policy_version 65801 (0.0009) -[2023-10-09 10:55:02,292][23468] Updated weights for policy 0, policy_version 65463 (0.0007) -[2023-10-09 10:55:02,595][23469] Updated weights for policy 1, policy_version 65811 (0.0008) -[2023-10-09 10:55:02,976][23469] Updated weights for policy 1, policy_version 65821 (0.0007) -[2023-10-09 10:55:05,977][23468] Updated weights for policy 0, policy_version 65473 (0.0007) -[2023-10-09 10:55:06,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 134447104. Throughput: 0: 1777.9, 1: 1800.5. Samples: 33619210. Policy #0 lag: (min: 31.0, avg: 31.9, max: 51.0) -[2023-10-09 10:55:06,078][22500] Avg episode reward: [(0, '9.650'), (1, '9.130')] -[2023-10-09 10:55:06,357][23468] Updated weights for policy 0, policy_version 65483 (0.0007) -[2023-10-09 10:55:06,646][23469] Updated weights for policy 1, policy_version 65831 (0.0008) -[2023-10-09 10:55:06,729][23468] Updated weights for policy 0, policy_version 65493 (0.0007) -[2023-10-09 10:55:07,015][23469] Updated weights for policy 1, policy_version 65841 (0.0007) -[2023-10-09 10:55:07,103][23468] Updated weights for policy 0, policy_version 65503 (0.0007) -[2023-10-09 10:55:07,390][23469] Updated weights for policy 1, policy_version 65851 (0.0008) -[2023-10-09 10:55:10,869][23468] Updated weights for policy 0, policy_version 65513 (0.0008) -[2023-10-09 10:55:11,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 134512640. Throughput: 0: 1772.0, 1: 1799.4. Samples: 33641468. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:55:11,078][22500] Avg episode reward: [(0, '9.260'), (1, '8.910')] -[2023-10-09 10:55:11,250][23468] Updated weights for policy 0, policy_version 65523 (0.0008) -[2023-10-09 10:55:11,287][23469] Updated weights for policy 1, policy_version 65861 (0.0007) -[2023-10-09 10:55:11,625][23468] Updated weights for policy 0, policy_version 65533 (0.0007) -[2023-10-09 10:55:11,655][23469] Updated weights for policy 1, policy_version 65871 (0.0009) -[2023-10-09 10:55:12,033][23469] Updated weights for policy 1, policy_version 65881 (0.0011) -[2023-10-09 10:55:15,333][23468] Updated weights for policy 0, policy_version 65543 (0.0008) -[2023-10-09 10:55:15,699][23468] Updated weights for policy 0, policy_version 65553 (0.0010) -[2023-10-09 10:55:15,779][23469] Updated weights for policy 1, policy_version 65891 (0.0007) -[2023-10-09 10:55:16,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 134578176. Throughput: 0: 1801.3, 1: 1811.9. Samples: 33663502. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:55:16,078][22500] Avg episode reward: [(0, '8.820'), (1, '8.980')] -[2023-10-09 10:55:16,083][23468] Updated weights for policy 0, policy_version 65563 (0.0008) -[2023-10-09 10:55:16,153][23469] Updated weights for policy 1, policy_version 65901 (0.0007) -[2023-10-09 10:55:16,527][23469] Updated weights for policy 1, policy_version 65911 (0.0008) -[2023-10-09 10:55:19,872][23468] Updated weights for policy 0, policy_version 65573 (0.0008) -[2023-10-09 10:55:20,218][23469] Updated weights for policy 1, policy_version 65921 (0.0008) -[2023-10-09 10:55:20,261][23468] Updated weights for policy 0, policy_version 65583 (0.0007) -[2023-10-09 10:55:20,584][23469] Updated weights for policy 1, policy_version 65931 (0.0007) -[2023-10-09 10:55:20,630][23468] Updated weights for policy 0, policy_version 65593 (0.0009) -[2023-10-09 10:55:20,950][23469] Updated weights for policy 1, policy_version 65941 (0.0007) -[2023-10-09 10:55:21,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 134676480. Throughput: 0: 1774.3, 1: 1791.6. Samples: 33673682. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:55:21,078][22500] Avg episode reward: [(0, '10.020'), (1, '9.070')] -[2023-10-09 10:55:21,318][23469] Updated weights for policy 1, policy_version 65951 (0.0007) -[2023-10-09 10:55:24,449][23468] Updated weights for policy 0, policy_version 65603 (0.0007) -[2023-10-09 10:55:24,826][23468] Updated weights for policy 0, policy_version 65613 (0.0007) -[2023-10-09 10:55:25,110][23469] Updated weights for policy 1, policy_version 65961 (0.0008) -[2023-10-09 10:55:25,199][23468] Updated weights for policy 0, policy_version 65623 (0.0007) -[2023-10-09 10:55:25,475][23469] Updated weights for policy 1, policy_version 65971 (0.0008) -[2023-10-09 10:55:25,845][23469] Updated weights for policy 1, policy_version 65981 (0.0007) -[2023-10-09 10:55:26,077][22500] Fps is (10 sec: 19660.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 134774784. Throughput: 0: 1797.7, 1: 1803.1. Samples: 33695722. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:55:26,078][22500] Avg episode reward: [(0, '9.500'), (1, '8.810')] -[2023-10-09 10:55:29,027][23468] Updated weights for policy 0, policy_version 65633 (0.0008) -[2023-10-09 10:55:29,399][23468] Updated weights for policy 0, policy_version 65643 (0.0010) -[2023-10-09 10:55:29,612][23469] Updated weights for policy 1, policy_version 65991 (0.0008) -[2023-10-09 10:55:29,773][23468] Updated weights for policy 0, policy_version 65653 (0.0007) -[2023-10-09 10:55:29,975][23469] Updated weights for policy 1, policy_version 66001 (0.0007) -[2023-10-09 10:55:30,147][23468] Updated weights for policy 0, policy_version 65663 (0.0007) -[2023-10-09 10:55:30,350][23469] Updated weights for policy 1, policy_version 66011 (0.0008) -[2023-10-09 10:55:31,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 134840320. Throughput: 0: 1769.4, 1: 1786.1. Samples: 33714894. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:55:31,078][22500] Avg episode reward: [(0, '10.040'), (1, '9.210')] -[2023-10-09 10:55:33,877][23468] Updated weights for policy 0, policy_version 65673 (0.0012) -[2023-10-09 10:55:34,180][23469] Updated weights for policy 1, policy_version 66021 (0.0008) -[2023-10-09 10:55:34,241][23468] Updated weights for policy 0, policy_version 65683 (0.0009) -[2023-10-09 10:55:34,546][23469] Updated weights for policy 1, policy_version 66031 (0.0007) -[2023-10-09 10:55:34,612][23468] Updated weights for policy 0, policy_version 65693 (0.0007) -[2023-10-09 10:55:34,921][23469] Updated weights for policy 1, policy_version 66041 (0.0007) -[2023-10-09 10:55:36,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 134905856. Throughput: 0: 1793.1, 1: 1796.3. Samples: 33727574. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:55:36,078][22500] Avg episode reward: [(0, '10.360'), (1, '8.530')] -[2023-10-09 10:55:38,394][23468] Updated weights for policy 0, policy_version 65703 (0.0007) -[2023-10-09 10:55:38,572][23469] Updated weights for policy 1, policy_version 66051 (0.0007) -[2023-10-09 10:55:38,770][23468] Updated weights for policy 0, policy_version 65713 (0.0007) -[2023-10-09 10:55:38,938][23469] Updated weights for policy 1, policy_version 66061 (0.0007) -[2023-10-09 10:55:39,147][23468] Updated weights for policy 0, policy_version 65723 (0.0008) -[2023-10-09 10:55:39,303][23469] Updated weights for policy 1, policy_version 66071 (0.0008) -[2023-10-09 10:55:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 134971392. Throughput: 0: 1775.4, 1: 1778.1. Samples: 33747146. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:55:41,078][22500] Avg episode reward: [(0, '9.370'), (1, '8.510')] -[2023-10-09 10:55:42,840][23468] Updated weights for policy 0, policy_version 65733 (0.0009) -[2023-10-09 10:55:43,124][23469] Updated weights for policy 1, policy_version 66081 (0.0008) -[2023-10-09 10:55:43,202][23468] Updated weights for policy 0, policy_version 65743 (0.0007) -[2023-10-09 10:55:43,487][23469] Updated weights for policy 1, policy_version 66091 (0.0007) -[2023-10-09 10:55:43,584][23468] Updated weights for policy 0, policy_version 65753 (0.0007) -[2023-10-09 10:55:43,853][23469] Updated weights for policy 1, policy_version 66101 (0.0010) -[2023-10-09 10:55:44,227][23469] Updated weights for policy 1, policy_version 66111 (0.0008) -[2023-10-09 10:55:46,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 135036928. Throughput: 0: 1775.2, 1: 1776.4. Samples: 33769394. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:55:46,079][22500] Avg episode reward: [(0, '9.070'), (1, '8.410')] -[2023-10-09 10:55:47,267][23468] Updated weights for policy 0, policy_version 65763 (0.0008) -[2023-10-09 10:55:47,635][23468] Updated weights for policy 0, policy_version 65773 (0.0010) -[2023-10-09 10:55:48,007][23468] Updated weights for policy 0, policy_version 65783 (0.0009) -[2023-10-09 10:55:48,105][23469] Updated weights for policy 1, policy_version 66121 (0.0007) -[2023-10-09 10:55:48,482][23469] Updated weights for policy 1, policy_version 66131 (0.0007) -[2023-10-09 10:55:48,848][23469] Updated weights for policy 1, policy_version 66141 (0.0009) -[2023-10-09 10:55:51,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 135102464. Throughput: 0: 1781.2, 1: 1780.9. Samples: 33779504. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:55:51,078][22500] Avg episode reward: [(0, '9.650'), (1, '9.160')] -[2023-10-09 10:55:51,962][23468] Updated weights for policy 0, policy_version 65793 (0.0009) -[2023-10-09 10:55:52,338][23468] Updated weights for policy 0, policy_version 65803 (0.0008) -[2023-10-09 10:55:52,710][23468] Updated weights for policy 0, policy_version 65813 (0.0007) -[2023-10-09 10:55:52,713][23469] Updated weights for policy 1, policy_version 66151 (0.0008) -[2023-10-09 10:55:53,081][23469] Updated weights for policy 1, policy_version 66161 (0.0007) -[2023-10-09 10:55:53,084][23468] Updated weights for policy 0, policy_version 65823 (0.0008) -[2023-10-09 10:55:53,449][23469] Updated weights for policy 1, policy_version 66171 (0.0007) -[2023-10-09 10:55:56,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 135168000. Throughput: 0: 1782.7, 1: 1774.8. Samples: 33801556. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-09 10:55:56,078][22500] Avg episode reward: [(0, '9.560'), (1, '8.790')] -[2023-10-09 10:55:56,962][23468] Updated weights for policy 0, policy_version 65833 (0.0009) -[2023-10-09 10:55:57,246][23469] Updated weights for policy 1, policy_version 66181 (0.0009) -[2023-10-09 10:55:57,340][23468] Updated weights for policy 0, policy_version 65843 (0.0007) -[2023-10-09 10:55:57,613][23469] Updated weights for policy 1, policy_version 66191 (0.0007) -[2023-10-09 10:55:57,709][23468] Updated weights for policy 0, policy_version 65853 (0.0007) -[2023-10-09 10:55:57,985][23469] Updated weights for policy 1, policy_version 66201 (0.0009) -[2023-10-09 10:56:01,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 135233536. Throughput: 0: 1779.3, 1: 1779.7. Samples: 33823660. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-09 10:56:01,079][22500] Avg episode reward: [(0, '9.830'), (1, '8.740')] -[2023-10-09 10:56:01,529][23468] Updated weights for policy 0, policy_version 65863 (0.0007) -[2023-10-09 10:56:01,798][23469] Updated weights for policy 1, policy_version 66211 (0.0009) -[2023-10-09 10:56:01,898][23468] Updated weights for policy 0, policy_version 65873 (0.0009) -[2023-10-09 10:56:02,168][23469] Updated weights for policy 1, policy_version 66221 (0.0010) -[2023-10-09 10:56:02,284][23468] Updated weights for policy 0, policy_version 65883 (0.0009) -[2023-10-09 10:56:02,529][23469] Updated weights for policy 1, policy_version 66231 (0.0007) -[2023-10-09 10:56:06,048][23468] Updated weights for policy 0, policy_version 65893 (0.0010) -[2023-10-09 10:56:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 135299072. Throughput: 0: 1772.3, 1: 1779.2. Samples: 33833500. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-09 10:56:06,078][22500] Avg episode reward: [(0, '9.720'), (1, '8.590')] -[2023-10-09 10:56:06,228][23469] Updated weights for policy 1, policy_version 66241 (0.0011) -[2023-10-09 10:56:06,438][23468] Updated weights for policy 0, policy_version 65903 (0.0007) -[2023-10-09 10:56:06,594][23469] Updated weights for policy 1, policy_version 66251 (0.0008) -[2023-10-09 10:56:06,810][23468] Updated weights for policy 0, policy_version 65913 (0.0009) -[2023-10-09 10:56:06,968][23469] Updated weights for policy 1, policy_version 66261 (0.0009) -[2023-10-09 10:56:07,338][23469] Updated weights for policy 1, policy_version 66271 (0.0008) -[2023-10-09 10:56:10,708][23468] Updated weights for policy 0, policy_version 65923 (0.0008) -[2023-10-09 10:56:11,006][23469] Updated weights for policy 1, policy_version 66281 (0.0008) -[2023-10-09 10:56:11,077][22500] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 135364608. Throughput: 0: 1769.8, 1: 1780.1. Samples: 33855468. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-09 10:56:11,078][22500] Avg episode reward: [(0, '9.970'), (1, '8.660')] -[2023-10-09 10:56:11,079][23468] Updated weights for policy 0, policy_version 65933 (0.0008) -[2023-10-09 10:56:11,381][23469] Updated weights for policy 1, policy_version 66291 (0.0007) -[2023-10-09 10:56:11,448][23468] Updated weights for policy 0, policy_version 65943 (0.0008) -[2023-10-09 10:56:11,754][23469] Updated weights for policy 1, policy_version 66301 (0.0011) -[2023-10-09 10:56:15,008][23468] Updated weights for policy 0, policy_version 65953 (0.0008) -[2023-10-09 10:56:15,378][23468] Updated weights for policy 0, policy_version 65963 (0.0008) -[2023-10-09 10:56:15,542][23469] Updated weights for policy 1, policy_version 66311 (0.0010) -[2023-10-09 10:56:15,748][23468] Updated weights for policy 0, policy_version 65973 (0.0008) -[2023-10-09 10:56:15,899][23469] Updated weights for policy 1, policy_version 66321 (0.0009) -[2023-10-09 10:56:16,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 135430144. Throughput: 0: 1803.0, 1: 1802.4. Samples: 33877140. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-09 10:56:16,078][22500] Avg episode reward: [(0, '9.720'), (1, '8.930')] -[2023-10-09 10:56:16,128][23468] Updated weights for policy 0, policy_version 65983 (0.0007) -[2023-10-09 10:56:16,160][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000065984_67567616.pth... -[2023-10-09 10:56:16,193][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000064288_65830912.pth -[2023-10-09 10:56:16,196][23265] Saving a milestone ./train_atari/atari_berzerk_APPO/checkpoint_p0/milestones/checkpoint_000065984_67567616.pth -[2023-10-09 10:56:16,269][23469] Updated weights for policy 1, policy_version 66331 (0.0008) -[2023-10-09 10:56:16,454][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000066336_67928064.pth... -[2023-10-09 10:56:16,487][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000064640_66191360.pth -[2023-10-09 10:56:16,491][23343] Saving a milestone ./train_atari/atari_berzerk_APPO/checkpoint_p1/milestones/checkpoint_000066336_67928064.pth -[2023-10-09 10:56:19,965][23469] Updated weights for policy 1, policy_version 66341 (0.0007) -[2023-10-09 10:56:20,050][23468] Updated weights for policy 0, policy_version 65993 (0.0007) -[2023-10-09 10:56:20,325][23469] Updated weights for policy 1, policy_version 66351 (0.0007) -[2023-10-09 10:56:20,411][23468] Updated weights for policy 0, policy_version 66003 (0.0008) -[2023-10-09 10:56:20,699][23469] Updated weights for policy 1, policy_version 66361 (0.0007) -[2023-10-09 10:56:20,781][23468] Updated weights for policy 0, policy_version 66013 (0.0009) -[2023-10-09 10:56:21,077][22500] Fps is (10 sec: 19660.4, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 135561216. Throughput: 0: 1774.7, 1: 1785.9. Samples: 33887802. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-09 10:56:21,078][22500] Avg episode reward: [(0, '10.170'), (1, '9.020')] -[2023-10-09 10:56:24,558][23468] Updated weights for policy 0, policy_version 66023 (0.0007) -[2023-10-09 10:56:24,597][23469] Updated weights for policy 1, policy_version 66371 (0.0009) -[2023-10-09 10:56:24,927][23468] Updated weights for policy 0, policy_version 66033 (0.0007) -[2023-10-09 10:56:24,958][23469] Updated weights for policy 1, policy_version 66381 (0.0007) -[2023-10-09 10:56:25,295][23468] Updated weights for policy 0, policy_version 66043 (0.0008) -[2023-10-09 10:56:25,322][23469] Updated weights for policy 1, policy_version 66391 (0.0008) -[2023-10-09 10:56:26,077][22500] Fps is (10 sec: 19660.7, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 135626752. Throughput: 0: 1802.1, 1: 1807.9. Samples: 33909596. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-09 10:56:26,079][22500] Avg episode reward: [(0, '9.490'), (1, '8.690')] -[2023-10-09 10:56:29,049][23469] Updated weights for policy 1, policy_version 66401 (0.0008) -[2023-10-09 10:56:29,125][23468] Updated weights for policy 0, policy_version 66053 (0.0009) -[2023-10-09 10:56:29,417][23469] Updated weights for policy 1, policy_version 66411 (0.0007) -[2023-10-09 10:56:29,492][23468] Updated weights for policy 0, policy_version 66063 (0.0010) -[2023-10-09 10:56:29,778][23469] Updated weights for policy 1, policy_version 66421 (0.0007) -[2023-10-09 10:56:29,880][23468] Updated weights for policy 0, policy_version 66073 (0.0009) -[2023-10-09 10:56:30,150][23469] Updated weights for policy 1, policy_version 66431 (0.0008) -[2023-10-09 10:56:31,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 135692288. Throughput: 0: 1772.1, 1: 1784.5. Samples: 33929440. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-09 10:56:31,078][22500] Avg episode reward: [(0, '9.400'), (1, '8.370')] -[2023-10-09 10:56:33,660][23468] Updated weights for policy 0, policy_version 66083 (0.0008) -[2023-10-09 10:56:33,762][23469] Updated weights for policy 1, policy_version 66441 (0.0010) -[2023-10-09 10:56:34,042][23468] Updated weights for policy 0, policy_version 66093 (0.0010) -[2023-10-09 10:56:34,135][23469] Updated weights for policy 1, policy_version 66451 (0.0008) -[2023-10-09 10:56:34,413][23468] Updated weights for policy 0, policy_version 66103 (0.0007) -[2023-10-09 10:56:34,510][23469] Updated weights for policy 1, policy_version 66461 (0.0007) -[2023-10-09 10:56:36,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 135757824. Throughput: 0: 1799.7, 1: 1809.4. Samples: 33941916. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:56:36,078][22500] Avg episode reward: [(0, '9.310'), (1, '8.320')] -[2023-10-09 10:56:38,129][23468] Updated weights for policy 0, policy_version 66113 (0.0008) -[2023-10-09 10:56:38,299][23469] Updated weights for policy 1, policy_version 66471 (0.0008) -[2023-10-09 10:56:38,495][23468] Updated weights for policy 0, policy_version 66123 (0.0007) -[2023-10-09 10:56:38,683][23469] Updated weights for policy 1, policy_version 66481 (0.0008) -[2023-10-09 10:56:38,867][23468] Updated weights for policy 0, policy_version 66133 (0.0008) -[2023-10-09 10:56:39,046][23469] Updated weights for policy 1, policy_version 66491 (0.0008) -[2023-10-09 10:56:39,240][23468] Updated weights for policy 0, policy_version 66143 (0.0009) -[2023-10-09 10:56:41,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 135823360. Throughput: 0: 1768.1, 1: 1789.5. Samples: 33961650. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:56:41,078][22500] Avg episode reward: [(0, '9.410'), (1, '8.370')] -[2023-10-09 10:56:42,766][23469] Updated weights for policy 1, policy_version 66501 (0.0009) -[2023-10-09 10:56:43,096][23468] Updated weights for policy 0, policy_version 66153 (0.0008) -[2023-10-09 10:56:43,132][23469] Updated weights for policy 1, policy_version 66511 (0.0009) -[2023-10-09 10:56:43,465][23468] Updated weights for policy 0, policy_version 66163 (0.0007) -[2023-10-09 10:56:43,510][23469] Updated weights for policy 1, policy_version 66521 (0.0008) -[2023-10-09 10:56:43,837][23468] Updated weights for policy 0, policy_version 66173 (0.0008) -[2023-10-09 10:56:46,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 135888896. Throughput: 0: 1766.5, 1: 1788.9. Samples: 33983652. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:56:46,079][22500] Avg episode reward: [(0, '9.890'), (1, '8.900')] -[2023-10-09 10:56:47,321][23469] Updated weights for policy 1, policy_version 66531 (0.0007) -[2023-10-09 10:56:47,575][23468] Updated weights for policy 0, policy_version 66183 (0.0009) -[2023-10-09 10:56:47,692][23469] Updated weights for policy 1, policy_version 66541 (0.0008) -[2023-10-09 10:56:47,957][23468] Updated weights for policy 0, policy_version 66193 (0.0008) -[2023-10-09 10:56:48,065][23469] Updated weights for policy 1, policy_version 66551 (0.0010) -[2023-10-09 10:56:48,325][23468] Updated weights for policy 0, policy_version 66203 (0.0009) -[2023-10-09 10:56:51,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 135954432. Throughput: 0: 1772.8, 1: 1784.9. Samples: 33993598. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:56:51,078][22500] Avg episode reward: [(0, '9.970'), (1, '8.950')] -[2023-10-09 10:56:51,825][23469] Updated weights for policy 1, policy_version 66561 (0.0008) -[2023-10-09 10:56:52,192][23469] Updated weights for policy 1, policy_version 66571 (0.0008) -[2023-10-09 10:56:52,232][23468] Updated weights for policy 0, policy_version 66213 (0.0008) -[2023-10-09 10:56:52,569][23469] Updated weights for policy 1, policy_version 66581 (0.0007) -[2023-10-09 10:56:52,596][23468] Updated weights for policy 0, policy_version 66223 (0.0008) -[2023-10-09 10:56:52,934][23469] Updated weights for policy 1, policy_version 66591 (0.0008) -[2023-10-09 10:56:52,971][23468] Updated weights for policy 0, policy_version 66233 (0.0009) -[2023-10-09 10:56:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 136019968. Throughput: 0: 1768.9, 1: 1790.5. Samples: 34015642. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:56:56,079][22500] Avg episode reward: [(0, '10.000'), (1, '9.190')] -[2023-10-09 10:56:56,569][23469] Updated weights for policy 1, policy_version 66601 (0.0008) -[2023-10-09 10:56:56,724][23468] Updated weights for policy 0, policy_version 66243 (0.0009) -[2023-10-09 10:56:56,944][23469] Updated weights for policy 1, policy_version 66611 (0.0009) -[2023-10-09 10:56:57,108][23468] Updated weights for policy 0, policy_version 66253 (0.0007) -[2023-10-09 10:56:57,311][23469] Updated weights for policy 1, policy_version 66621 (0.0008) -[2023-10-09 10:56:57,489][23468] Updated weights for policy 0, policy_version 66263 (0.0007) -[2023-10-09 10:57:01,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 136085504. Throughput: 0: 1770.0, 1: 1801.4. Samples: 34037854. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:57:01,078][22500] Avg episode reward: [(0, '9.280'), (1, '8.860')] -[2023-10-09 10:57:01,095][23469] Updated weights for policy 1, policy_version 66631 (0.0010) -[2023-10-09 10:57:01,235][23468] Updated weights for policy 0, policy_version 66273 (0.0007) -[2023-10-09 10:57:01,462][23469] Updated weights for policy 1, policy_version 66641 (0.0007) -[2023-10-09 10:57:01,614][23468] Updated weights for policy 0, policy_version 66283 (0.0008) -[2023-10-09 10:57:01,836][23469] Updated weights for policy 1, policy_version 66651 (0.0008) -[2023-10-09 10:57:01,976][23468] Updated weights for policy 0, policy_version 66293 (0.0008) -[2023-10-09 10:57:02,361][23468] Updated weights for policy 0, policy_version 66303 (0.0010) -[2023-10-09 10:57:05,498][23469] Updated weights for policy 1, policy_version 66661 (0.0008) -[2023-10-09 10:57:05,866][23469] Updated weights for policy 1, policy_version 66671 (0.0008) -[2023-10-09 10:57:06,016][23468] Updated weights for policy 0, policy_version 66313 (0.0008) -[2023-10-09 10:57:06,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 136151040. Throughput: 0: 1763.6, 1: 1789.4. Samples: 34047684. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:57:06,078][22500] Avg episode reward: [(0, '10.050'), (1, '8.660')] -[2023-10-09 10:57:06,249][23469] Updated weights for policy 1, policy_version 66681 (0.0010) -[2023-10-09 10:57:06,392][23468] Updated weights for policy 0, policy_version 66323 (0.0007) -[2023-10-09 10:57:06,767][23468] Updated weights for policy 0, policy_version 66333 (0.0007) -[2023-10-09 10:57:10,037][23469] Updated weights for policy 1, policy_version 66691 (0.0009) -[2023-10-09 10:57:10,401][23469] Updated weights for policy 1, policy_version 66701 (0.0010) -[2023-10-09 10:57:10,556][23468] Updated weights for policy 0, policy_version 66343 (0.0009) -[2023-10-09 10:57:10,771][23469] Updated weights for policy 1, policy_version 66711 (0.0009) -[2023-10-09 10:57:10,928][23468] Updated weights for policy 0, policy_version 66353 (0.0009) -[2023-10-09 10:57:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 136216576. Throughput: 0: 1767.0, 1: 1801.0. Samples: 34070154. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:57:11,078][22500] Avg episode reward: [(0, '9.700'), (1, '8.800')] -[2023-10-09 10:57:11,296][23468] Updated weights for policy 0, policy_version 66363 (0.0008) -[2023-10-09 10:57:14,579][23469] Updated weights for policy 1, policy_version 66721 (0.0008) -[2023-10-09 10:57:14,955][23469] Updated weights for policy 1, policy_version 66731 (0.0007) -[2023-10-09 10:57:15,011][23468] Updated weights for policy 0, policy_version 66373 (0.0008) -[2023-10-09 10:57:15,333][23469] Updated weights for policy 1, policy_version 66741 (0.0007) -[2023-10-09 10:57:15,380][23468] Updated weights for policy 0, policy_version 66383 (0.0008) -[2023-10-09 10:57:15,703][23469] Updated weights for policy 1, policy_version 66751 (0.0008) -[2023-10-09 10:57:15,752][23468] Updated weights for policy 0, policy_version 66393 (0.0008) -[2023-10-09 10:57:16,078][22500] Fps is (10 sec: 19660.1, 60 sec: 15291.7, 300 sec: 14440.1). Total num frames: 136347648. Throughput: 0: 1787.4, 1: 1791.9. Samples: 34090508. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:57:16,079][22500] Avg episode reward: [(0, '10.220'), (1, '8.810')] -[2023-10-09 10:57:19,501][23469] Updated weights for policy 1, policy_version 66761 (0.0009) -[2023-10-09 10:57:19,550][23468] Updated weights for policy 0, policy_version 66403 (0.0010) -[2023-10-09 10:57:19,868][23469] Updated weights for policy 1, policy_version 66771 (0.0008) -[2023-10-09 10:57:19,935][23468] Updated weights for policy 0, policy_version 66413 (0.0008) -[2023-10-09 10:57:20,235][23469] Updated weights for policy 1, policy_version 66781 (0.0008) -[2023-10-09 10:57:20,298][23468] Updated weights for policy 0, policy_version 66423 (0.0007) -[2023-10-09 10:57:21,077][22500] Fps is (10 sec: 19660.8, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 136413184. Throughput: 0: 1765.9, 1: 1793.7. Samples: 34102100. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-09 10:57:21,078][22500] Avg episode reward: [(0, '10.280'), (1, '8.770')] -[2023-10-09 10:57:24,114][23468] Updated weights for policy 0, policy_version 66433 (0.0010) -[2023-10-09 10:57:24,147][23469] Updated weights for policy 1, policy_version 66791 (0.0009) -[2023-10-09 10:57:24,486][23468] Updated weights for policy 0, policy_version 66443 (0.0008) -[2023-10-09 10:57:24,526][23469] Updated weights for policy 1, policy_version 66801 (0.0007) -[2023-10-09 10:57:24,862][23468] Updated weights for policy 0, policy_version 66453 (0.0008) -[2023-10-09 10:57:24,899][23469] Updated weights for policy 1, policy_version 66811 (0.0007) -[2023-10-09 10:57:25,223][23468] Updated weights for policy 0, policy_version 66463 (0.0007) -[2023-10-09 10:57:26,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 136478720. Throughput: 0: 1793.7, 1: 1788.2. Samples: 34122836. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-09 10:57:26,078][22500] Avg episode reward: [(0, '10.450'), (1, '8.790')] -[2023-10-09 10:57:28,611][23469] Updated weights for policy 1, policy_version 66821 (0.0009) -[2023-10-09 10:57:28,991][23469] Updated weights for policy 1, policy_version 66831 (0.0009) -[2023-10-09 10:57:29,036][23468] Updated weights for policy 0, policy_version 66473 (0.0009) -[2023-10-09 10:57:29,363][23469] Updated weights for policy 1, policy_version 66841 (0.0008) -[2023-10-09 10:57:29,407][23468] Updated weights for policy 0, policy_version 66483 (0.0008) -[2023-10-09 10:57:29,776][23468] Updated weights for policy 0, policy_version 66493 (0.0009) -[2023-10-09 10:57:31,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 136544256. Throughput: 0: 1771.0, 1: 1776.1. Samples: 34143268. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-09 10:57:31,078][22500] Avg episode reward: [(0, '10.670'), (1, '8.790')] -[2023-10-09 10:57:33,070][23469] Updated weights for policy 1, policy_version 66851 (0.0009) -[2023-10-09 10:57:33,444][23469] Updated weights for policy 1, policy_version 66861 (0.0007) -[2023-10-09 10:57:33,680][23468] Updated weights for policy 0, policy_version 66503 (0.0008) -[2023-10-09 10:57:33,817][23469] Updated weights for policy 1, policy_version 66871 (0.0009) -[2023-10-09 10:57:34,058][23468] Updated weights for policy 0, policy_version 66513 (0.0009) -[2023-10-09 10:57:34,421][23468] Updated weights for policy 0, policy_version 66523 (0.0008) -[2023-10-09 10:57:36,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 136609792. Throughput: 0: 1795.3, 1: 1792.5. Samples: 34155048. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-09 10:57:36,078][22500] Avg episode reward: [(0, '10.530'), (1, '8.940')] -[2023-10-09 10:57:37,706][23469] Updated weights for policy 1, policy_version 66881 (0.0008) -[2023-10-09 10:57:38,076][23469] Updated weights for policy 1, policy_version 66891 (0.0009) -[2023-10-09 10:57:38,189][23468] Updated weights for policy 0, policy_version 66533 (0.0009) -[2023-10-09 10:57:38,446][23469] Updated weights for policy 1, policy_version 66901 (0.0007) -[2023-10-09 10:57:38,559][23468] Updated weights for policy 0, policy_version 66543 (0.0009) -[2023-10-09 10:57:38,818][23469] Updated weights for policy 1, policy_version 66911 (0.0008) -[2023-10-09 10:57:38,932][23468] Updated weights for policy 0, policy_version 66553 (0.0009) -[2023-10-09 10:57:41,078][22500] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 136675328. Throughput: 0: 1772.4, 1: 1774.8. Samples: 34175266. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-09 10:57:41,079][22500] Avg episode reward: [(0, '10.550'), (1, '9.050')] -[2023-10-09 10:57:42,523][23469] Updated weights for policy 1, policy_version 66921 (0.0010) -[2023-10-09 10:57:42,788][23468] Updated weights for policy 0, policy_version 66563 (0.0008) -[2023-10-09 10:57:42,889][23469] Updated weights for policy 1, policy_version 66931 (0.0007) -[2023-10-09 10:57:43,169][23468] Updated weights for policy 0, policy_version 66573 (0.0008) -[2023-10-09 10:57:43,256][23469] Updated weights for policy 1, policy_version 66941 (0.0007) -[2023-10-09 10:57:43,543][23468] Updated weights for policy 0, policy_version 66583 (0.0007) -[2023-10-09 10:57:46,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 136740864. Throughput: 0: 1767.8, 1: 1775.4. Samples: 34197296. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-09 10:57:46,078][22500] Avg episode reward: [(0, '10.480'), (1, '8.680')] -[2023-10-09 10:57:47,031][23469] Updated weights for policy 1, policy_version 66951 (0.0008) -[2023-10-09 10:57:47,345][23468] Updated weights for policy 0, policy_version 66593 (0.0010) -[2023-10-09 10:57:47,392][23469] Updated weights for policy 1, policy_version 66961 (0.0009) -[2023-10-09 10:57:47,710][23468] Updated weights for policy 0, policy_version 66603 (0.0009) -[2023-10-09 10:57:47,756][23469] Updated weights for policy 1, policy_version 66971 (0.0010) -[2023-10-09 10:57:48,088][23468] Updated weights for policy 0, policy_version 66613 (0.0009) -[2023-10-09 10:57:48,465][23468] Updated weights for policy 0, policy_version 66623 (0.0009) -[2023-10-09 10:57:51,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 136806400. Throughput: 0: 1774.7, 1: 1775.2. Samples: 34207432. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-09 10:57:51,078][22500] Avg episode reward: [(0, '10.800'), (1, '9.170')] -[2023-10-09 10:57:51,079][23265] Saving new best policy, reward=10.800! -[2023-10-09 10:57:51,652][23469] Updated weights for policy 1, policy_version 66981 (0.0009) -[2023-10-09 10:57:52,024][23469] Updated weights for policy 1, policy_version 66991 (0.0008) -[2023-10-09 10:57:52,330][23468] Updated weights for policy 0, policy_version 66633 (0.0007) -[2023-10-09 10:57:52,389][23469] Updated weights for policy 1, policy_version 67001 (0.0009) -[2023-10-09 10:57:52,702][23468] Updated weights for policy 0, policy_version 66643 (0.0007) -[2023-10-09 10:57:53,072][23468] Updated weights for policy 0, policy_version 66653 (0.0008) -[2023-10-09 10:57:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 136871936. Throughput: 0: 1764.4, 1: 1772.6. Samples: 34229322. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-09 10:57:56,078][22500] Avg episode reward: [(0, '10.850'), (1, '8.750')] -[2023-10-09 10:57:56,080][23265] Saving new best policy, reward=10.850! -[2023-10-09 10:57:56,138][23469] Updated weights for policy 1, policy_version 67011 (0.0007) -[2023-10-09 10:57:56,506][23469] Updated weights for policy 1, policy_version 67021 (0.0009) -[2023-10-09 10:57:56,768][23468] Updated weights for policy 0, policy_version 66663 (0.0007) -[2023-10-09 10:57:56,874][23469] Updated weights for policy 1, policy_version 67031 (0.0007) -[2023-10-09 10:57:57,148][23468] Updated weights for policy 0, policy_version 66673 (0.0007) -[2023-10-09 10:57:57,525][23468] Updated weights for policy 0, policy_version 66683 (0.0009) -[2023-10-09 10:58:00,576][23469] Updated weights for policy 1, policy_version 67041 (0.0008) -[2023-10-09 10:58:00,944][23469] Updated weights for policy 1, policy_version 67051 (0.0008) -[2023-10-09 10:58:01,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 136937472. Throughput: 0: 1780.7, 1: 1801.6. Samples: 34251708. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-09 10:58:01,078][22500] Avg episode reward: [(0, '10.660'), (1, '9.160')] -[2023-10-09 10:58:01,313][23469] Updated weights for policy 1, policy_version 67061 (0.0007) -[2023-10-09 10:58:01,374][23468] Updated weights for policy 0, policy_version 66693 (0.0009) -[2023-10-09 10:58:01,687][23469] Updated weights for policy 1, policy_version 67071 (0.0008) -[2023-10-09 10:58:01,747][23468] Updated weights for policy 0, policy_version 66703 (0.0009) -[2023-10-09 10:58:02,115][23468] Updated weights for policy 0, policy_version 66713 (0.0008) -[2023-10-09 10:58:05,468][23469] Updated weights for policy 1, policy_version 67081 (0.0010) -[2023-10-09 10:58:05,807][23468] Updated weights for policy 0, policy_version 66723 (0.0007) -[2023-10-09 10:58:05,847][23469] Updated weights for policy 1, policy_version 67091 (0.0009) -[2023-10-09 10:58:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 137003008. Throughput: 0: 1768.2, 1: 1781.0. Samples: 34261816. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:58:06,078][22500] Avg episode reward: [(0, '10.230'), (1, '8.880')] -[2023-10-09 10:58:06,183][23468] Updated weights for policy 0, policy_version 66733 (0.0007) -[2023-10-09 10:58:06,218][23469] Updated weights for policy 1, policy_version 67101 (0.0009) -[2023-10-09 10:58:06,556][23468] Updated weights for policy 0, policy_version 66743 (0.0010) -[2023-10-09 10:58:09,967][23469] Updated weights for policy 1, policy_version 67111 (0.0008) -[2023-10-09 10:58:10,316][23468] Updated weights for policy 0, policy_version 66753 (0.0007) -[2023-10-09 10:58:10,341][23469] Updated weights for policy 1, policy_version 67121 (0.0009) -[2023-10-09 10:58:10,692][23468] Updated weights for policy 0, policy_version 66763 (0.0008) -[2023-10-09 10:58:10,702][23469] Updated weights for policy 1, policy_version 67131 (0.0007) -[2023-10-09 10:58:11,059][23468] Updated weights for policy 0, policy_version 66773 (0.0007) -[2023-10-09 10:58:11,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 137101312. Throughput: 0: 1769.7, 1: 1807.9. Samples: 34283830. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:58:11,078][22500] Avg episode reward: [(0, '9.380'), (1, '9.170')] -[2023-10-09 10:58:11,437][23468] Updated weights for policy 0, policy_version 66783 (0.0007) -[2023-10-09 10:58:14,392][23469] Updated weights for policy 1, policy_version 67141 (0.0010) -[2023-10-09 10:58:14,759][23469] Updated weights for policy 1, policy_version 67151 (0.0011) -[2023-10-09 10:58:15,124][23469] Updated weights for policy 1, policy_version 67161 (0.0008) -[2023-10-09 10:58:15,212][23468] Updated weights for policy 0, policy_version 66793 (0.0007) -[2023-10-09 10:58:15,588][23468] Updated weights for policy 0, policy_version 66803 (0.0008) -[2023-10-09 10:58:15,961][23468] Updated weights for policy 0, policy_version 66813 (0.0008) -[2023-10-09 10:58:16,078][22500] Fps is (10 sec: 19660.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 137199616. Throughput: 0: 1785.9, 1: 1792.1. Samples: 34304280. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:58:16,079][22500] Avg episode reward: [(0, '9.360'), (1, '8.990')] -[2023-10-09 10:58:16,089][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000067168_68780032.pth... -[2023-10-09 10:58:16,089][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000066816_68419584.pth... -[2023-10-09 10:58:16,127][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000065472_67043328.pth -[2023-10-09 10:58:16,128][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000065152_66715648.pth -[2023-10-09 10:58:18,878][23469] Updated weights for policy 1, policy_version 67171 (0.0009) -[2023-10-09 10:58:19,236][23469] Updated weights for policy 1, policy_version 67181 (0.0007) -[2023-10-09 10:58:19,614][23469] Updated weights for policy 1, policy_version 67191 (0.0007) -[2023-10-09 10:58:19,676][23468] Updated weights for policy 0, policy_version 66823 (0.0008) -[2023-10-09 10:58:20,051][23468] Updated weights for policy 0, policy_version 66833 (0.0009) -[2023-10-09 10:58:20,419][23468] Updated weights for policy 0, policy_version 66843 (0.0007) -[2023-10-09 10:58:21,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 137265152. Throughput: 0: 1766.9, 1: 1810.3. Samples: 34316022. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:58:21,078][22500] Avg episode reward: [(0, '9.150'), (1, '9.000')] -[2023-10-09 10:58:23,447][23469] Updated weights for policy 1, policy_version 67201 (0.0008) -[2023-10-09 10:58:23,818][23469] Updated weights for policy 1, policy_version 67211 (0.0009) -[2023-10-09 10:58:24,191][23468] Updated weights for policy 0, policy_version 66853 (0.0008) -[2023-10-09 10:58:24,192][23469] Updated weights for policy 1, policy_version 67221 (0.0008) -[2023-10-09 10:58:24,553][23469] Updated weights for policy 1, policy_version 67231 (0.0008) -[2023-10-09 10:58:24,572][23468] Updated weights for policy 0, policy_version 66863 (0.0009) -[2023-10-09 10:58:24,943][23468] Updated weights for policy 0, policy_version 66873 (0.0008) -[2023-10-09 10:58:26,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 137330688. Throughput: 0: 1794.5, 1: 1790.9. Samples: 34336606. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:58:26,078][22500] Avg episode reward: [(0, '9.760'), (1, '8.840')] -[2023-10-09 10:58:28,274][23469] Updated weights for policy 1, policy_version 67241 (0.0009) -[2023-10-09 10:58:28,644][23469] Updated weights for policy 1, policy_version 67251 (0.0007) -[2023-10-09 10:58:28,813][23468] Updated weights for policy 0, policy_version 66883 (0.0007) -[2023-10-09 10:58:29,022][23469] Updated weights for policy 1, policy_version 67261 (0.0009) -[2023-10-09 10:58:29,203][23468] Updated weights for policy 0, policy_version 66893 (0.0010) -[2023-10-09 10:58:29,583][23468] Updated weights for policy 0, policy_version 66903 (0.0007) -[2023-10-09 10:58:31,078][22500] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 137396224. Throughput: 0: 1771.7, 1: 1794.5. Samples: 34357776. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:58:31,079][22500] Avg episode reward: [(0, '9.840'), (1, '8.490')] -[2023-10-09 10:58:32,716][23469] Updated weights for policy 1, policy_version 67271 (0.0010) -[2023-10-09 10:58:33,078][23469] Updated weights for policy 1, policy_version 67281 (0.0010) -[2023-10-09 10:58:33,259][23468] Updated weights for policy 0, policy_version 66913 (0.0007) -[2023-10-09 10:58:33,449][23469] Updated weights for policy 1, policy_version 67291 (0.0007) -[2023-10-09 10:58:33,630][23468] Updated weights for policy 0, policy_version 66923 (0.0007) -[2023-10-09 10:58:34,000][23468] Updated weights for policy 0, policy_version 66933 (0.0009) -[2023-10-09 10:58:34,373][23468] Updated weights for policy 0, policy_version 66943 (0.0011) -[2023-10-09 10:58:36,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 137461760. Throughput: 0: 1797.8, 1: 1789.2. Samples: 34368848. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:58:36,079][22500] Avg episode reward: [(0, '9.660'), (1, '9.110')] -[2023-10-09 10:58:37,165][23469] Updated weights for policy 1, policy_version 67301 (0.0008) -[2023-10-09 10:58:37,529][23469] Updated weights for policy 1, policy_version 67311 (0.0008) -[2023-10-09 10:58:37,893][23469] Updated weights for policy 1, policy_version 67321 (0.0007) -[2023-10-09 10:58:38,006][23468] Updated weights for policy 0, policy_version 66953 (0.0007) -[2023-10-09 10:58:38,370][23468] Updated weights for policy 0, policy_version 66963 (0.0008) -[2023-10-09 10:58:38,743][23468] Updated weights for policy 0, policy_version 66973 (0.0008) -[2023-10-09 10:58:41,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 137527296. Throughput: 0: 1781.5, 1: 1791.3. Samples: 34390100. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:58:41,078][22500] Avg episode reward: [(0, '9.910'), (1, '8.610')] -[2023-10-09 10:58:41,677][23469] Updated weights for policy 1, policy_version 67331 (0.0009) -[2023-10-09 10:58:42,039][23469] Updated weights for policy 1, policy_version 67341 (0.0009) -[2023-10-09 10:58:42,416][23469] Updated weights for policy 1, policy_version 67351 (0.0008) -[2023-10-09 10:58:42,524][23468] Updated weights for policy 0, policy_version 66983 (0.0008) -[2023-10-09 10:58:42,894][23468] Updated weights for policy 0, policy_version 66993 (0.0008) -[2023-10-09 10:58:43,279][23468] Updated weights for policy 0, policy_version 67003 (0.0009) -[2023-10-09 10:58:46,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 137592832. Throughput: 0: 1780.0, 1: 1795.9. Samples: 34412622. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 10:58:46,078][22500] Avg episode reward: [(0, '10.310'), (1, '8.390')] -[2023-10-09 10:58:46,182][23469] Updated weights for policy 1, policy_version 67361 (0.0007) -[2023-10-09 10:58:46,554][23469] Updated weights for policy 1, policy_version 67371 (0.0008) -[2023-10-09 10:58:46,930][23469] Updated weights for policy 1, policy_version 67381 (0.0010) -[2023-10-09 10:58:47,043][23468] Updated weights for policy 0, policy_version 67013 (0.0008) -[2023-10-09 10:58:47,297][23469] Updated weights for policy 1, policy_version 67391 (0.0008) -[2023-10-09 10:58:47,412][23468] Updated weights for policy 0, policy_version 67023 (0.0008) -[2023-10-09 10:58:47,791][23468] Updated weights for policy 0, policy_version 67033 (0.0009) -[2023-10-09 10:58:51,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 137658368. Throughput: 0: 1783.2, 1: 1786.4. Samples: 34422448. Policy #0 lag: (min: 10.0, avg: 24.5, max: 42.0) -[2023-10-09 10:58:51,078][22500] Avg episode reward: [(0, '10.210'), (1, '8.760')] -[2023-10-09 10:58:51,259][23469] Updated weights for policy 1, policy_version 67401 (0.0007) -[2023-10-09 10:58:51,628][23469] Updated weights for policy 1, policy_version 67411 (0.0008) -[2023-10-09 10:58:51,676][23468] Updated weights for policy 0, policy_version 67043 (0.0010) -[2023-10-09 10:58:51,989][23469] Updated weights for policy 1, policy_version 67421 (0.0008) -[2023-10-09 10:58:52,043][23468] Updated weights for policy 0, policy_version 67053 (0.0008) -[2023-10-09 10:58:52,419][23468] Updated weights for policy 0, policy_version 67063 (0.0007) -[2023-10-09 10:58:55,731][23469] Updated weights for policy 1, policy_version 67431 (0.0007) -[2023-10-09 10:58:56,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 137723904. Throughput: 0: 1785.2, 1: 1786.9. Samples: 34444570. Policy #0 lag: (min: 10.0, avg: 24.5, max: 42.0) -[2023-10-09 10:58:56,078][22500] Avg episode reward: [(0, '10.570'), (1, '8.590')] -[2023-10-09 10:58:56,101][23469] Updated weights for policy 1, policy_version 67441 (0.0008) -[2023-10-09 10:58:56,157][23468] Updated weights for policy 0, policy_version 67073 (0.0007) -[2023-10-09 10:58:56,470][23469] Updated weights for policy 1, policy_version 67451 (0.0007) -[2023-10-09 10:58:56,530][23468] Updated weights for policy 0, policy_version 67083 (0.0007) -[2023-10-09 10:58:56,909][23468] Updated weights for policy 0, policy_version 67093 (0.0008) -[2023-10-09 10:58:57,286][23468] Updated weights for policy 0, policy_version 67103 (0.0009) -[2023-10-09 10:59:00,174][23469] Updated weights for policy 1, policy_version 67461 (0.0008) -[2023-10-09 10:59:00,537][23469] Updated weights for policy 1, policy_version 67471 (0.0010) -[2023-10-09 10:59:00,908][23469] Updated weights for policy 1, policy_version 67481 (0.0008) -[2023-10-09 10:59:01,077][23468] Updated weights for policy 0, policy_version 67113 (0.0008) -[2023-10-09 10:59:01,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 137789440. Throughput: 0: 1795.2, 1: 1797.8. Samples: 34465966. Policy #0 lag: (min: 10.0, avg: 24.5, max: 42.0) -[2023-10-09 10:59:01,078][22500] Avg episode reward: [(0, '10.690'), (1, '8.540')] -[2023-10-09 10:59:01,448][23468] Updated weights for policy 0, policy_version 67123 (0.0007) -[2023-10-09 10:59:01,823][23468] Updated weights for policy 0, policy_version 67133 (0.0009) -[2023-10-09 10:59:04,762][23469] Updated weights for policy 1, policy_version 67491 (0.0007) -[2023-10-09 10:59:05,122][23469] Updated weights for policy 1, policy_version 67501 (0.0007) -[2023-10-09 10:59:05,491][23469] Updated weights for policy 1, policy_version 67511 (0.0007) -[2023-10-09 10:59:05,502][23468] Updated weights for policy 0, policy_version 67143 (0.0008) -[2023-10-09 10:59:05,881][23468] Updated weights for policy 0, policy_version 67153 (0.0008) -[2023-10-09 10:59:06,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 137887744. Throughput: 0: 1783.4, 1: 1786.8. Samples: 34476680. Policy #0 lag: (min: 10.0, avg: 24.5, max: 42.0) -[2023-10-09 10:59:06,080][22500] Avg episode reward: [(0, '9.380'), (1, '8.310')] -[2023-10-09 10:59:06,248][23468] Updated weights for policy 0, policy_version 67163 (0.0007) -[2023-10-09 10:59:09,223][23469] Updated weights for policy 1, policy_version 67521 (0.0009) -[2023-10-09 10:59:09,591][23469] Updated weights for policy 1, policy_version 67531 (0.0009) -[2023-10-09 10:59:09,859][23468] Updated weights for policy 0, policy_version 67173 (0.0008) -[2023-10-09 10:59:09,966][23469] Updated weights for policy 1, policy_version 67541 (0.0008) -[2023-10-09 10:59:10,230][23468] Updated weights for policy 0, policy_version 67183 (0.0009) -[2023-10-09 10:59:10,323][23469] Updated weights for policy 1, policy_version 67551 (0.0009) -[2023-10-09 10:59:10,605][23468] Updated weights for policy 0, policy_version 67193 (0.0010) -[2023-10-09 10:59:11,077][22500] Fps is (10 sec: 19660.6, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 137986048. Throughput: 0: 1797.2, 1: 1799.8. Samples: 34498470. Policy #0 lag: (min: 10.0, avg: 24.5, max: 42.0) -[2023-10-09 10:59:11,078][22500] Avg episode reward: [(0, '9.680'), (1, '8.430')] -[2023-10-09 10:59:13,977][23469] Updated weights for policy 1, policy_version 67561 (0.0010) -[2023-10-09 10:59:14,340][23469] Updated weights for policy 1, policy_version 67571 (0.0010) -[2023-10-09 10:59:14,398][23468] Updated weights for policy 0, policy_version 67203 (0.0010) -[2023-10-09 10:59:14,712][23469] Updated weights for policy 1, policy_version 67581 (0.0008) -[2023-10-09 10:59:14,776][23468] Updated weights for policy 0, policy_version 67213 (0.0008) -[2023-10-09 10:59:15,154][23468] Updated weights for policy 0, policy_version 67223 (0.0011) -[2023-10-09 10:59:16,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 138051584. Throughput: 0: 1802.1, 1: 1782.7. Samples: 34519092. Policy #0 lag: (min: 10.0, avg: 24.5, max: 42.0) -[2023-10-09 10:59:16,078][22500] Avg episode reward: [(0, '9.680'), (1, '8.270')] -[2023-10-09 10:59:18,428][23469] Updated weights for policy 1, policy_version 67591 (0.0010) -[2023-10-09 10:59:18,800][23469] Updated weights for policy 1, policy_version 67601 (0.0009) -[2023-10-09 10:59:18,899][23468] Updated weights for policy 0, policy_version 67233 (0.0008) -[2023-10-09 10:59:19,169][23469] Updated weights for policy 1, policy_version 67611 (0.0008) -[2023-10-09 10:59:19,270][23468] Updated weights for policy 0, policy_version 67243 (0.0008) -[2023-10-09 10:59:19,637][23468] Updated weights for policy 0, policy_version 67253 (0.0007) -[2023-10-09 10:59:20,021][23468] Updated weights for policy 0, policy_version 67263 (0.0008) -[2023-10-09 10:59:21,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 138117120. Throughput: 0: 1792.6, 1: 1802.4. Samples: 34530622. Policy #0 lag: (min: 10.0, avg: 24.5, max: 42.0) -[2023-10-09 10:59:21,078][22500] Avg episode reward: [(0, '9.710'), (1, '8.560')] -[2023-10-09 10:59:22,850][23469] Updated weights for policy 1, policy_version 67621 (0.0008) -[2023-10-09 10:59:23,213][23469] Updated weights for policy 1, policy_version 67631 (0.0007) -[2023-10-09 10:59:23,586][23469] Updated weights for policy 1, policy_version 67641 (0.0009) -[2023-10-09 10:59:23,799][23468] Updated weights for policy 0, policy_version 67273 (0.0008) -[2023-10-09 10:59:24,176][23468] Updated weights for policy 0, policy_version 67283 (0.0008) -[2023-10-09 10:59:24,538][23468] Updated weights for policy 0, policy_version 67293 (0.0010) -[2023-10-09 10:59:26,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 138182656. Throughput: 0: 1795.6, 1: 1789.3. Samples: 34551420. Policy #0 lag: (min: 10.0, avg: 24.5, max: 42.0) -[2023-10-09 10:59:26,078][22500] Avg episode reward: [(0, '10.040'), (1, '8.900')] -[2023-10-09 10:59:27,343][23469] Updated weights for policy 1, policy_version 67651 (0.0007) -[2023-10-09 10:59:27,703][23469] Updated weights for policy 1, policy_version 67661 (0.0010) -[2023-10-09 10:59:28,067][23469] Updated weights for policy 1, policy_version 67671 (0.0009) -[2023-10-09 10:59:28,248][23468] Updated weights for policy 0, policy_version 67303 (0.0009) -[2023-10-09 10:59:28,615][23468] Updated weights for policy 0, policy_version 67313 (0.0009) -[2023-10-09 10:59:28,997][23468] Updated weights for policy 0, policy_version 67323 (0.0008) -[2023-10-09 10:59:31,077][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 138248192. Throughput: 0: 1783.6, 1: 1787.1. Samples: 34573306. Policy #0 lag: (min: 10.0, avg: 24.5, max: 42.0) -[2023-10-09 10:59:31,079][22500] Avg episode reward: [(0, '9.720'), (1, '8.900')] -[2023-10-09 10:59:31,946][23469] Updated weights for policy 1, policy_version 67681 (0.0007) -[2023-10-09 10:59:32,306][23469] Updated weights for policy 1, policy_version 67691 (0.0007) -[2023-10-09 10:59:32,684][23469] Updated weights for policy 1, policy_version 67701 (0.0007) -[2023-10-09 10:59:32,802][23468] Updated weights for policy 0, policy_version 67333 (0.0009) -[2023-10-09 10:59:33,051][23469] Updated weights for policy 1, policy_version 67711 (0.0007) -[2023-10-09 10:59:33,175][23468] Updated weights for policy 0, policy_version 67343 (0.0008) -[2023-10-09 10:59:33,550][23468] Updated weights for policy 0, policy_version 67353 (0.0008) -[2023-10-09 10:59:36,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 138313728. Throughput: 0: 1796.8, 1: 1787.4. Samples: 34583734. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-09 10:59:36,078][22500] Avg episode reward: [(0, '9.320'), (1, '8.860')] -[2023-10-09 10:59:36,785][23469] Updated weights for policy 1, policy_version 67721 (0.0010) -[2023-10-09 10:59:37,145][23469] Updated weights for policy 1, policy_version 67731 (0.0009) -[2023-10-09 10:59:37,286][23468] Updated weights for policy 0, policy_version 67363 (0.0008) -[2023-10-09 10:59:37,512][23469] Updated weights for policy 1, policy_version 67741 (0.0009) -[2023-10-09 10:59:37,662][23468] Updated weights for policy 0, policy_version 67373 (0.0008) -[2023-10-09 10:59:38,032][23468] Updated weights for policy 0, policy_version 67383 (0.0008) -[2023-10-09 10:59:41,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 138379264. Throughput: 0: 1782.8, 1: 1793.6. Samples: 34605510. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-09 10:59:41,078][22500] Avg episode reward: [(0, '9.360'), (1, '8.350')] -[2023-10-09 10:59:41,137][23469] Updated weights for policy 1, policy_version 67751 (0.0009) -[2023-10-09 10:59:41,509][23469] Updated weights for policy 1, policy_version 67761 (0.0007) -[2023-10-09 10:59:41,816][23468] Updated weights for policy 0, policy_version 67393 (0.0010) -[2023-10-09 10:59:41,875][23469] Updated weights for policy 1, policy_version 67771 (0.0007) -[2023-10-09 10:59:42,193][23468] Updated weights for policy 0, policy_version 67403 (0.0008) -[2023-10-09 10:59:42,565][23468] Updated weights for policy 0, policy_version 67413 (0.0008) -[2023-10-09 10:59:42,931][23468] Updated weights for policy 0, policy_version 67423 (0.0007) -[2023-10-09 10:59:45,666][23469] Updated weights for policy 1, policy_version 67781 (0.0008) -[2023-10-09 10:59:46,039][23469] Updated weights for policy 1, policy_version 67791 (0.0007) -[2023-10-09 10:59:46,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 138444800. Throughput: 0: 1792.1, 1: 1807.9. Samples: 34627966. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-09 10:59:46,079][22500] Avg episode reward: [(0, '9.840'), (1, '8.220')] -[2023-10-09 10:59:46,398][23469] Updated weights for policy 1, policy_version 67801 (0.0007) -[2023-10-09 10:59:46,736][23468] Updated weights for policy 0, policy_version 67433 (0.0009) -[2023-10-09 10:59:47,104][23468] Updated weights for policy 0, policy_version 67443 (0.0009) -[2023-10-09 10:59:47,472][23468] Updated weights for policy 0, policy_version 67453 (0.0009) -[2023-10-09 10:59:50,254][23469] Updated weights for policy 1, policy_version 67811 (0.0007) -[2023-10-09 10:59:50,629][23469] Updated weights for policy 1, policy_version 67821 (0.0008) -[2023-10-09 10:59:51,002][23469] Updated weights for policy 1, policy_version 67831 (0.0009) -[2023-10-09 10:59:51,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 138510336. Throughput: 0: 1792.4, 1: 1792.1. Samples: 34637984. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-09 10:59:51,078][22500] Avg episode reward: [(0, '9.400'), (1, '8.520')] -[2023-10-09 10:59:51,116][23468] Updated weights for policy 0, policy_version 67463 (0.0010) -[2023-10-09 10:59:51,495][23468] Updated weights for policy 0, policy_version 67473 (0.0009) -[2023-10-09 10:59:51,871][23468] Updated weights for policy 0, policy_version 67483 (0.0008) -[2023-10-09 10:59:54,740][23469] Updated weights for policy 1, policy_version 67841 (0.0008) -[2023-10-09 10:59:55,117][23469] Updated weights for policy 1, policy_version 67851 (0.0010) -[2023-10-09 10:59:55,473][23468] Updated weights for policy 0, policy_version 67493 (0.0009) -[2023-10-09 10:59:55,473][23469] Updated weights for policy 1, policy_version 67861 (0.0007) -[2023-10-09 10:59:55,840][23468] Updated weights for policy 0, policy_version 67503 (0.0009) -[2023-10-09 10:59:55,843][23469] Updated weights for policy 1, policy_version 67871 (0.0008) -[2023-10-09 10:59:56,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 138608640. Throughput: 0: 1789.0, 1: 1807.7. Samples: 34660324. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-09 10:59:56,078][22500] Avg episode reward: [(0, '9.350'), (1, '8.180')] -[2023-10-09 10:59:56,215][23468] Updated weights for policy 0, policy_version 67513 (0.0010) -[2023-10-09 10:59:59,629][23469] Updated weights for policy 1, policy_version 67881 (0.0010) -[2023-10-09 10:59:59,993][23469] Updated weights for policy 1, policy_version 67891 (0.0009) -[2023-10-09 11:00:00,061][23468] Updated weights for policy 0, policy_version 67523 (0.0008) -[2023-10-09 11:00:00,358][23469] Updated weights for policy 1, policy_version 67901 (0.0010) -[2023-10-09 11:00:00,462][23468] Updated weights for policy 0, policy_version 67533 (0.0008) -[2023-10-09 11:00:00,836][23468] Updated weights for policy 0, policy_version 67543 (0.0010) -[2023-10-09 11:00:01,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 138674176. Throughput: 0: 1806.8, 1: 1787.7. Samples: 34680846. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-09 11:00:01,078][22500] Avg episode reward: [(0, '10.500'), (1, '8.320')] -[2023-10-09 11:00:03,970][23469] Updated weights for policy 1, policy_version 67911 (0.0011) -[2023-10-09 11:00:04,347][23469] Updated weights for policy 1, policy_version 67921 (0.0007) -[2023-10-09 11:00:04,488][23468] Updated weights for policy 0, policy_version 67553 (0.0009) -[2023-10-09 11:00:04,713][23469] Updated weights for policy 1, policy_version 67931 (0.0008) -[2023-10-09 11:00:04,858][23468] Updated weights for policy 0, policy_version 67563 (0.0009) -[2023-10-09 11:00:05,232][23468] Updated weights for policy 0, policy_version 67573 (0.0009) -[2023-10-09 11:00:05,602][23468] Updated weights for policy 0, policy_version 67583 (0.0008) -[2023-10-09 11:00:06,078][22500] Fps is (10 sec: 16383.5, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 138772480. Throughput: 0: 1791.0, 1: 1805.9. Samples: 34692486. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-09 11:00:06,079][22500] Avg episode reward: [(0, '10.040'), (1, '8.310')] -[2023-10-09 11:00:08,422][23469] Updated weights for policy 1, policy_version 67941 (0.0010) -[2023-10-09 11:00:08,788][23469] Updated weights for policy 1, policy_version 67951 (0.0011) -[2023-10-09 11:00:09,153][23469] Updated weights for policy 1, policy_version 67961 (0.0009) -[2023-10-09 11:00:09,404][23468] Updated weights for policy 0, policy_version 67593 (0.0008) -[2023-10-09 11:00:09,771][23468] Updated weights for policy 0, policy_version 67603 (0.0007) -[2023-10-09 11:00:10,145][23468] Updated weights for policy 0, policy_version 67613 (0.0008) -[2023-10-09 11:00:11,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 138838016. Throughput: 0: 1803.6, 1: 1789.1. Samples: 34713090. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-09 11:00:11,078][22500] Avg episode reward: [(0, '10.050'), (1, '8.700')] -[2023-10-09 11:00:12,958][23469] Updated weights for policy 1, policy_version 67971 (0.0009) -[2023-10-09 11:00:13,326][23469] Updated weights for policy 1, policy_version 67981 (0.0007) -[2023-10-09 11:00:13,701][23469] Updated weights for policy 1, policy_version 67991 (0.0008) -[2023-10-09 11:00:13,987][23468] Updated weights for policy 0, policy_version 67623 (0.0009) -[2023-10-09 11:00:14,365][23468] Updated weights for policy 0, policy_version 67633 (0.0009) -[2023-10-09 11:00:14,743][23468] Updated weights for policy 0, policy_version 67643 (0.0007) -[2023-10-09 11:00:16,078][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 138903552. Throughput: 0: 1786.0, 1: 1789.5. Samples: 34734204. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-09 11:00:16,078][22500] Avg episode reward: [(0, '10.150'), (1, '9.020')] -[2023-10-09 11:00:16,089][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000068000_69632000.pth... -[2023-10-09 11:00:16,089][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000067648_69271552.pth... -[2023-10-09 11:00:16,124][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000066336_67928064.pth -[2023-10-09 11:00:16,125][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000065984_67567616.pth -[2023-10-09 11:00:17,476][23469] Updated weights for policy 1, policy_version 68001 (0.0009) -[2023-10-09 11:00:17,848][23469] Updated weights for policy 1, policy_version 68011 (0.0007) -[2023-10-09 11:00:18,224][23469] Updated weights for policy 1, policy_version 68021 (0.0009) -[2023-10-09 11:00:18,508][23468] Updated weights for policy 0, policy_version 67653 (0.0010) -[2023-10-09 11:00:18,589][23469] Updated weights for policy 1, policy_version 68031 (0.0008) -[2023-10-09 11:00:18,877][23468] Updated weights for policy 0, policy_version 67663 (0.0009) -[2023-10-09 11:00:19,246][23468] Updated weights for policy 0, policy_version 67673 (0.0009) -[2023-10-09 11:00:21,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 138969088. Throughput: 0: 1807.5, 1: 1788.6. Samples: 34745560. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:00:21,078][22500] Avg episode reward: [(0, '10.280'), (1, '9.300')] -[2023-10-09 11:00:22,422][23469] Updated weights for policy 1, policy_version 68041 (0.0007) -[2023-10-09 11:00:22,799][23469] Updated weights for policy 1, policy_version 68051 (0.0007) -[2023-10-09 11:00:23,043][23468] Updated weights for policy 0, policy_version 67683 (0.0008) -[2023-10-09 11:00:23,162][23469] Updated weights for policy 1, policy_version 68061 (0.0008) -[2023-10-09 11:00:23,426][23468] Updated weights for policy 0, policy_version 67693 (0.0009) -[2023-10-09 11:00:23,797][23468] Updated weights for policy 0, policy_version 67703 (0.0009) -[2023-10-09 11:00:26,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 139034624. Throughput: 0: 1788.9, 1: 1786.7. Samples: 34766410. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:00:26,078][22500] Avg episode reward: [(0, '9.920'), (1, '9.640')] -[2023-10-09 11:00:27,071][23469] Updated weights for policy 1, policy_version 68071 (0.0010) -[2023-10-09 11:00:27,437][23469] Updated weights for policy 1, policy_version 68081 (0.0010) -[2023-10-09 11:00:27,570][23468] Updated weights for policy 0, policy_version 67713 (0.0010) -[2023-10-09 11:00:27,814][23469] Updated weights for policy 1, policy_version 68091 (0.0008) -[2023-10-09 11:00:27,935][23468] Updated weights for policy 0, policy_version 67723 (0.0008) -[2023-10-09 11:00:28,306][23468] Updated weights for policy 0, policy_version 67733 (0.0009) -[2023-10-09 11:00:28,678][23468] Updated weights for policy 0, policy_version 67743 (0.0007) -[2023-10-09 11:00:31,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 139100160. Throughput: 0: 1787.7, 1: 1786.9. Samples: 34788822. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:00:31,079][22500] Avg episode reward: [(0, '10.160'), (1, '9.280')] -[2023-10-09 11:00:31,517][23469] Updated weights for policy 1, policy_version 68101 (0.0008) -[2023-10-09 11:00:31,887][23469] Updated weights for policy 1, policy_version 68111 (0.0008) -[2023-10-09 11:00:32,262][23469] Updated weights for policy 1, policy_version 68121 (0.0009) -[2023-10-09 11:00:32,485][23468] Updated weights for policy 0, policy_version 67753 (0.0008) -[2023-10-09 11:00:32,861][23468] Updated weights for policy 0, policy_version 67763 (0.0008) -[2023-10-09 11:00:33,230][23468] Updated weights for policy 0, policy_version 67773 (0.0009) -[2023-10-09 11:00:35,947][23469] Updated weights for policy 1, policy_version 68131 (0.0009) -[2023-10-09 11:00:36,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 139165696. Throughput: 0: 1788.5, 1: 1783.2. Samples: 34798714. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:00:36,078][22500] Avg episode reward: [(0, '10.610'), (1, '8.840')] -[2023-10-09 11:00:36,310][23469] Updated weights for policy 1, policy_version 68141 (0.0007) -[2023-10-09 11:00:36,685][23469] Updated weights for policy 1, policy_version 68151 (0.0009) -[2023-10-09 11:00:36,962][23468] Updated weights for policy 0, policy_version 67783 (0.0007) -[2023-10-09 11:00:37,340][23468] Updated weights for policy 0, policy_version 67793 (0.0007) -[2023-10-09 11:00:37,705][23468] Updated weights for policy 0, policy_version 67803 (0.0007) -[2023-10-09 11:00:40,489][23469] Updated weights for policy 1, policy_version 68161 (0.0007) -[2023-10-09 11:00:40,849][23469] Updated weights for policy 1, policy_version 68171 (0.0008) -[2023-10-09 11:00:41,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 139231232. Throughput: 0: 1782.3, 1: 1786.6. Samples: 34820926. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:00:41,078][22500] Avg episode reward: [(0, '10.070'), (1, '8.260')] -[2023-10-09 11:00:41,221][23469] Updated weights for policy 1, policy_version 68181 (0.0010) -[2023-10-09 11:00:41,450][23468] Updated weights for policy 0, policy_version 67813 (0.0008) -[2023-10-09 11:00:41,594][23469] Updated weights for policy 1, policy_version 68191 (0.0008) -[2023-10-09 11:00:41,816][23468] Updated weights for policy 0, policy_version 67823 (0.0011) -[2023-10-09 11:00:42,201][23468] Updated weights for policy 0, policy_version 67833 (0.0008) -[2023-10-09 11:00:45,257][23469] Updated weights for policy 1, policy_version 68201 (0.0007) -[2023-10-09 11:00:45,634][23469] Updated weights for policy 1, policy_version 68211 (0.0008) -[2023-10-09 11:00:45,912][23468] Updated weights for policy 0, policy_version 67843 (0.0007) -[2023-10-09 11:00:46,017][23469] Updated weights for policy 1, policy_version 68221 (0.0007) -[2023-10-09 11:00:46,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 139296768. Throughput: 0: 1792.2, 1: 1802.5. Samples: 34842606. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:00:46,078][22500] Avg episode reward: [(0, '10.650'), (1, '8.540')] -[2023-10-09 11:00:46,310][23468] Updated weights for policy 0, policy_version 67853 (0.0007) -[2023-10-09 11:00:46,677][23468] Updated weights for policy 0, policy_version 67863 (0.0008) -[2023-10-09 11:00:49,718][23469] Updated weights for policy 1, policy_version 68231 (0.0008) -[2023-10-09 11:00:50,091][23469] Updated weights for policy 1, policy_version 68241 (0.0007) -[2023-10-09 11:00:50,459][23469] Updated weights for policy 1, policy_version 68251 (0.0009) -[2023-10-09 11:00:50,526][23468] Updated weights for policy 0, policy_version 67873 (0.0011) -[2023-10-09 11:00:50,898][23468] Updated weights for policy 0, policy_version 67883 (0.0010) -[2023-10-09 11:00:51,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 139395072. Throughput: 0: 1778.9, 1: 1792.5. Samples: 34853200. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:00:51,078][22500] Avg episode reward: [(0, '8.960'), (1, '8.500')] -[2023-10-09 11:00:51,277][23468] Updated weights for policy 0, policy_version 67893 (0.0010) -[2023-10-09 11:00:51,641][23468] Updated weights for policy 0, policy_version 67903 (0.0010) -[2023-10-09 11:00:54,320][23469] Updated weights for policy 1, policy_version 68261 (0.0008) -[2023-10-09 11:00:54,681][23469] Updated weights for policy 1, policy_version 68271 (0.0007) -[2023-10-09 11:00:55,053][23469] Updated weights for policy 1, policy_version 68281 (0.0008) -[2023-10-09 11:00:55,372][23468] Updated weights for policy 0, policy_version 67913 (0.0007) -[2023-10-09 11:00:55,743][23468] Updated weights for policy 0, policy_version 67923 (0.0008) -[2023-10-09 11:00:56,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 139460608. Throughput: 0: 1788.7, 1: 1805.2. Samples: 34874818. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:00:56,078][22500] Avg episode reward: [(0, '9.040'), (1, '8.880')] -[2023-10-09 11:00:56,106][23468] Updated weights for policy 0, policy_version 67933 (0.0008) -[2023-10-09 11:00:58,736][23469] Updated weights for policy 1, policy_version 68291 (0.0010) -[2023-10-09 11:00:59,100][23469] Updated weights for policy 1, policy_version 68301 (0.0010) -[2023-10-09 11:00:59,472][23469] Updated weights for policy 1, policy_version 68311 (0.0009) -[2023-10-09 11:00:59,778][23468] Updated weights for policy 0, policy_version 67943 (0.0008) -[2023-10-09 11:01:00,162][23468] Updated weights for policy 0, policy_version 67953 (0.0008) -[2023-10-09 11:01:00,538][23468] Updated weights for policy 0, policy_version 67963 (0.0008) -[2023-10-09 11:01:01,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 139558912. Throughput: 0: 1801.3, 1: 1793.5. Samples: 34895972. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:01:01,078][22500] Avg episode reward: [(0, '8.950'), (1, '8.560')] -[2023-10-09 11:01:03,209][23469] Updated weights for policy 1, policy_version 68321 (0.0009) -[2023-10-09 11:01:03,574][23469] Updated weights for policy 1, policy_version 68331 (0.0008) -[2023-10-09 11:01:03,944][23469] Updated weights for policy 1, policy_version 68341 (0.0007) -[2023-10-09 11:01:04,315][23469] Updated weights for policy 1, policy_version 68351 (0.0007) -[2023-10-09 11:01:04,353][23468] Updated weights for policy 0, policy_version 67973 (0.0008) -[2023-10-09 11:01:04,724][23468] Updated weights for policy 0, policy_version 67983 (0.0008) -[2023-10-09 11:01:05,106][23468] Updated weights for policy 0, policy_version 67993 (0.0009) -[2023-10-09 11:01:06,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 139624448. Throughput: 0: 1779.6, 1: 1809.8. Samples: 34907080. Policy #0 lag: (min: 31.0, avg: 31.7, max: 48.0) -[2023-10-09 11:01:06,078][22500] Avg episode reward: [(0, '9.270'), (1, '8.810')] -[2023-10-09 11:01:08,002][23469] Updated weights for policy 1, policy_version 68361 (0.0008) -[2023-10-09 11:01:08,380][23469] Updated weights for policy 1, policy_version 68371 (0.0008) -[2023-10-09 11:01:08,747][23469] Updated weights for policy 1, policy_version 68381 (0.0008) -[2023-10-09 11:01:08,863][23468] Updated weights for policy 0, policy_version 68003 (0.0008) -[2023-10-09 11:01:09,236][23468] Updated weights for policy 0, policy_version 68013 (0.0009) -[2023-10-09 11:01:09,612][23468] Updated weights for policy 0, policy_version 68023 (0.0008) -[2023-10-09 11:01:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 139689984. Throughput: 0: 1801.2, 1: 1801.2. Samples: 34928518. Policy #0 lag: (min: 31.0, avg: 31.7, max: 48.0) -[2023-10-09 11:01:11,078][22500] Avg episode reward: [(0, '9.390'), (1, '9.230')] -[2023-10-09 11:01:12,385][23469] Updated weights for policy 1, policy_version 68391 (0.0009) -[2023-10-09 11:01:12,769][23469] Updated weights for policy 1, policy_version 68401 (0.0008) -[2023-10-09 11:01:13,144][23469] Updated weights for policy 1, policy_version 68411 (0.0007) -[2023-10-09 11:01:13,462][23468] Updated weights for policy 0, policy_version 68033 (0.0008) -[2023-10-09 11:01:13,822][23468] Updated weights for policy 0, policy_version 68043 (0.0008) -[2023-10-09 11:01:14,198][23468] Updated weights for policy 0, policy_version 68053 (0.0009) -[2023-10-09 11:01:14,571][23468] Updated weights for policy 0, policy_version 68063 (0.0010) -[2023-10-09 11:01:16,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 139755520. Throughput: 0: 1773.6, 1: 1802.9. Samples: 34949766. Policy #0 lag: (min: 31.0, avg: 31.7, max: 48.0) -[2023-10-09 11:01:16,078][22500] Avg episode reward: [(0, '9.470'), (1, '9.090')] -[2023-10-09 11:01:16,751][23469] Updated weights for policy 1, policy_version 68421 (0.0008) -[2023-10-09 11:01:17,126][23469] Updated weights for policy 1, policy_version 68431 (0.0008) -[2023-10-09 11:01:17,498][23469] Updated weights for policy 1, policy_version 68441 (0.0007) -[2023-10-09 11:01:18,291][23468] Updated weights for policy 0, policy_version 68073 (0.0008) -[2023-10-09 11:01:18,667][23468] Updated weights for policy 0, policy_version 68083 (0.0007) -[2023-10-09 11:01:19,040][23468] Updated weights for policy 0, policy_version 68093 (0.0009) -[2023-10-09 11:01:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 139821056. Throughput: 0: 1795.8, 1: 1802.0. Samples: 34960616. Policy #0 lag: (min: 31.0, avg: 31.7, max: 48.0) -[2023-10-09 11:01:21,078][22500] Avg episode reward: [(0, '9.120'), (1, '8.850')] -[2023-10-09 11:01:21,295][23469] Updated weights for policy 1, policy_version 68451 (0.0008) -[2023-10-09 11:01:21,658][23469] Updated weights for policy 1, policy_version 68461 (0.0009) -[2023-10-09 11:01:22,028][23469] Updated weights for policy 1, policy_version 68471 (0.0010) -[2023-10-09 11:01:22,863][23468] Updated weights for policy 0, policy_version 68103 (0.0008) -[2023-10-09 11:01:23,234][23468] Updated weights for policy 0, policy_version 68113 (0.0009) -[2023-10-09 11:01:23,610][23468] Updated weights for policy 0, policy_version 68123 (0.0009) -[2023-10-09 11:01:25,763][23469] Updated weights for policy 1, policy_version 68481 (0.0007) -[2023-10-09 11:01:26,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 139886592. Throughput: 0: 1772.4, 1: 1801.0. Samples: 34981728. Policy #0 lag: (min: 31.0, avg: 31.7, max: 48.0) -[2023-10-09 11:01:26,078][22500] Avg episode reward: [(0, '9.080'), (1, '8.760')] -[2023-10-09 11:01:26,124][23469] Updated weights for policy 1, policy_version 68491 (0.0010) -[2023-10-09 11:01:26,492][23469] Updated weights for policy 1, policy_version 68501 (0.0009) -[2023-10-09 11:01:26,865][23469] Updated weights for policy 1, policy_version 68511 (0.0008) -[2023-10-09 11:01:27,350][23468] Updated weights for policy 0, policy_version 68133 (0.0007) -[2023-10-09 11:01:27,719][23468] Updated weights for policy 0, policy_version 68143 (0.0007) -[2023-10-09 11:01:28,083][23468] Updated weights for policy 0, policy_version 68153 (0.0008) -[2023-10-09 11:01:30,624][23469] Updated weights for policy 1, policy_version 68521 (0.0008) -[2023-10-09 11:01:31,002][23469] Updated weights for policy 1, policy_version 68531 (0.0011) -[2023-10-09 11:01:31,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 139952128. Throughput: 0: 1765.2, 1: 1802.6. Samples: 35003156. Policy #0 lag: (min: 31.0, avg: 31.7, max: 48.0) -[2023-10-09 11:01:31,078][22500] Avg episode reward: [(0, '10.180'), (1, '8.820')] -[2023-10-09 11:01:31,375][23469] Updated weights for policy 1, policy_version 68541 (0.0008) -[2023-10-09 11:01:31,948][23468] Updated weights for policy 0, policy_version 68163 (0.0009) -[2023-10-09 11:01:32,331][23468] Updated weights for policy 0, policy_version 68173 (0.0009) -[2023-10-09 11:01:32,697][23468] Updated weights for policy 0, policy_version 68183 (0.0008) -[2023-10-09 11:01:35,113][23469] Updated weights for policy 1, policy_version 68551 (0.0008) -[2023-10-09 11:01:35,476][23469] Updated weights for policy 1, policy_version 68561 (0.0009) -[2023-10-09 11:01:35,846][23469] Updated weights for policy 1, policy_version 68571 (0.0011) -[2023-10-09 11:01:36,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 140050432. Throughput: 0: 1771.0, 1: 1793.5. Samples: 35013600. Policy #0 lag: (min: 31.0, avg: 31.7, max: 48.0) -[2023-10-09 11:01:36,078][22500] Avg episode reward: [(0, '9.610'), (1, '8.990')] -[2023-10-09 11:01:36,379][23468] Updated weights for policy 0, policy_version 68193 (0.0010) -[2023-10-09 11:01:36,753][23468] Updated weights for policy 0, policy_version 68203 (0.0007) -[2023-10-09 11:01:37,130][23468] Updated weights for policy 0, policy_version 68213 (0.0007) -[2023-10-09 11:01:37,514][23468] Updated weights for policy 0, policy_version 68223 (0.0007) -[2023-10-09 11:01:39,712][23469] Updated weights for policy 1, policy_version 68581 (0.0010) -[2023-10-09 11:01:40,086][23469] Updated weights for policy 1, policy_version 68591 (0.0008) -[2023-10-09 11:01:40,451][23469] Updated weights for policy 1, policy_version 68601 (0.0008) -[2023-10-09 11:01:41,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 140115968. Throughput: 0: 1773.2, 1: 1805.2. Samples: 35035846. Policy #0 lag: (min: 31.0, avg: 31.7, max: 48.0) -[2023-10-09 11:01:41,079][22500] Avg episode reward: [(0, '10.050'), (1, '8.560')] -[2023-10-09 11:01:41,288][23468] Updated weights for policy 0, policy_version 68233 (0.0009) -[2023-10-09 11:01:41,658][23468] Updated weights for policy 0, policy_version 68243 (0.0008) -[2023-10-09 11:01:42,043][23468] Updated weights for policy 0, policy_version 68253 (0.0008) -[2023-10-09 11:01:44,299][23469] Updated weights for policy 1, policy_version 68611 (0.0008) -[2023-10-09 11:01:44,662][23469] Updated weights for policy 1, policy_version 68621 (0.0011) -[2023-10-09 11:01:45,031][23469] Updated weights for policy 1, policy_version 68631 (0.0011) -[2023-10-09 11:01:45,788][23468] Updated weights for policy 0, policy_version 68263 (0.0008) -[2023-10-09 11:01:46,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 140181504. Throughput: 0: 1790.3, 1: 1787.7. Samples: 35056982. Policy #0 lag: (min: 31.0, avg: 31.7, max: 48.0) -[2023-10-09 11:01:46,078][22500] Avg episode reward: [(0, '9.980'), (1, '8.530')] -[2023-10-09 11:01:46,164][23468] Updated weights for policy 0, policy_version 68273 (0.0010) -[2023-10-09 11:01:46,534][23468] Updated weights for policy 0, policy_version 68283 (0.0010) -[2023-10-09 11:01:48,686][23469] Updated weights for policy 1, policy_version 68641 (0.0011) -[2023-10-09 11:01:49,056][23469] Updated weights for policy 1, policy_version 68651 (0.0009) -[2023-10-09 11:01:49,424][23469] Updated weights for policy 1, policy_version 68661 (0.0008) -[2023-10-09 11:01:49,803][23469] Updated weights for policy 1, policy_version 68671 (0.0009) -[2023-10-09 11:01:50,450][23468] Updated weights for policy 0, policy_version 68293 (0.0011) -[2023-10-09 11:01:50,829][23468] Updated weights for policy 0, policy_version 68303 (0.0009) -[2023-10-09 11:01:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 140247040. Throughput: 0: 1772.0, 1: 1806.1. Samples: 35068096. Policy #0 lag: (min: 31.0, avg: 31.7, max: 48.0) -[2023-10-09 11:01:51,078][22500] Avg episode reward: [(0, '9.820'), (1, '8.370')] -[2023-10-09 11:01:51,200][23468] Updated weights for policy 0, policy_version 68313 (0.0009) -[2023-10-09 11:01:53,446][23469] Updated weights for policy 1, policy_version 68681 (0.0011) -[2023-10-09 11:01:53,814][23469] Updated weights for policy 1, policy_version 68691 (0.0010) -[2023-10-09 11:01:54,186][23469] Updated weights for policy 1, policy_version 68701 (0.0009) -[2023-10-09 11:01:54,974][23468] Updated weights for policy 0, policy_version 68323 (0.0008) -[2023-10-09 11:01:55,351][23468] Updated weights for policy 0, policy_version 68333 (0.0009) -[2023-10-09 11:01:55,714][23468] Updated weights for policy 0, policy_version 68343 (0.0008) -[2023-10-09 11:01:56,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 140345344. Throughput: 0: 1784.8, 1: 1786.7. Samples: 35089238. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) -[2023-10-09 11:01:56,079][22500] Avg episode reward: [(0, '10.040'), (1, '8.580')] -[2023-10-09 11:01:58,057][23469] Updated weights for policy 1, policy_version 68711 (0.0012) -[2023-10-09 11:01:58,445][23469] Updated weights for policy 1, policy_version 68721 (0.0009) -[2023-10-09 11:01:58,818][23469] Updated weights for policy 1, policy_version 68731 (0.0007) -[2023-10-09 11:01:59,512][23468] Updated weights for policy 0, policy_version 68353 (0.0007) -[2023-10-09 11:01:59,878][23468] Updated weights for policy 0, policy_version 68363 (0.0008) -[2023-10-09 11:02:00,246][23468] Updated weights for policy 0, policy_version 68373 (0.0008) -[2023-10-09 11:02:00,623][23468] Updated weights for policy 0, policy_version 68383 (0.0009) -[2023-10-09 11:02:01,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 140410880. Throughput: 0: 1786.3, 1: 1791.3. Samples: 35110758. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) -[2023-10-09 11:02:01,078][22500] Avg episode reward: [(0, '9.980'), (1, '8.600')] -[2023-10-09 11:02:02,532][23469] Updated weights for policy 1, policy_version 68741 (0.0008) -[2023-10-09 11:02:02,915][23469] Updated weights for policy 1, policy_version 68751 (0.0008) -[2023-10-09 11:02:03,278][23469] Updated weights for policy 1, policy_version 68761 (0.0008) -[2023-10-09 11:02:04,219][23468] Updated weights for policy 0, policy_version 68393 (0.0009) -[2023-10-09 11:02:04,591][23468] Updated weights for policy 0, policy_version 68403 (0.0008) -[2023-10-09 11:02:04,973][23468] Updated weights for policy 0, policy_version 68413 (0.0008) -[2023-10-09 11:02:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 140476416. Throughput: 0: 1786.0, 1: 1786.5. Samples: 35121378. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) -[2023-10-09 11:02:06,078][22500] Avg episode reward: [(0, '9.540'), (1, '9.120')] -[2023-10-09 11:02:07,113][23469] Updated weights for policy 1, policy_version 68771 (0.0010) -[2023-10-09 11:02:07,480][23469] Updated weights for policy 1, policy_version 68781 (0.0011) -[2023-10-09 11:02:07,854][23469] Updated weights for policy 1, policy_version 68791 (0.0010) -[2023-10-09 11:02:08,707][23468] Updated weights for policy 0, policy_version 68423 (0.0007) -[2023-10-09 11:02:09,076][23468] Updated weights for policy 0, policy_version 68433 (0.0007) -[2023-10-09 11:02:09,454][23468] Updated weights for policy 0, policy_version 68443 (0.0007) -[2023-10-09 11:02:11,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 140541952. Throughput: 0: 1789.6, 1: 1793.4. Samples: 35142964. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) -[2023-10-09 11:02:11,078][22500] Avg episode reward: [(0, '8.780'), (1, '9.060')] -[2023-10-09 11:02:11,419][23469] Updated weights for policy 1, policy_version 68801 (0.0009) -[2023-10-09 11:02:11,789][23469] Updated weights for policy 1, policy_version 68811 (0.0008) -[2023-10-09 11:02:12,151][23469] Updated weights for policy 1, policy_version 68821 (0.0007) -[2023-10-09 11:02:12,521][23469] Updated weights for policy 1, policy_version 68831 (0.0007) -[2023-10-09 11:02:13,137][23468] Updated weights for policy 0, policy_version 68453 (0.0007) -[2023-10-09 11:02:13,499][23468] Updated weights for policy 0, policy_version 68463 (0.0007) -[2023-10-09 11:02:13,886][23468] Updated weights for policy 0, policy_version 68473 (0.0009) -[2023-10-09 11:02:16,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 140607488. Throughput: 0: 1792.4, 1: 1816.3. Samples: 35165548. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) -[2023-10-09 11:02:16,078][22500] Avg episode reward: [(0, '9.540'), (1, '9.440')] -[2023-10-09 11:02:16,085][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000068480_70123520.pth... -[2023-10-09 11:02:16,125][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000066816_68419584.pth -[2023-10-09 11:02:16,319][23469] Updated weights for policy 1, policy_version 68841 (0.0008) -[2023-10-09 11:02:16,693][23469] Updated weights for policy 1, policy_version 68851 (0.0009) -[2023-10-09 11:02:17,057][23469] Updated weights for policy 1, policy_version 68861 (0.0007) -[2023-10-09 11:02:17,157][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000068864_70516736.pth... -[2023-10-09 11:02:17,186][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000067168_68780032.pth -[2023-10-09 11:02:17,511][23468] Updated weights for policy 0, policy_version 68483 (0.0009) -[2023-10-09 11:02:17,901][23468] Updated weights for policy 0, policy_version 68493 (0.0007) -[2023-10-09 11:02:18,269][23468] Updated weights for policy 0, policy_version 68503 (0.0010) -[2023-10-09 11:02:20,594][23469] Updated weights for policy 1, policy_version 68871 (0.0008) -[2023-10-09 11:02:20,961][23469] Updated weights for policy 1, policy_version 68881 (0.0007) -[2023-10-09 11:02:21,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 140673024. Throughput: 0: 1802.1, 1: 1806.9. Samples: 35176006. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) -[2023-10-09 11:02:21,078][22500] Avg episode reward: [(0, '10.330'), (1, '9.010')] -[2023-10-09 11:02:21,328][23469] Updated weights for policy 1, policy_version 68891 (0.0007) -[2023-10-09 11:02:22,020][23468] Updated weights for policy 0, policy_version 68513 (0.0011) -[2023-10-09 11:02:22,385][23468] Updated weights for policy 0, policy_version 68523 (0.0009) -[2023-10-09 11:02:22,751][23468] Updated weights for policy 0, policy_version 68533 (0.0009) -[2023-10-09 11:02:23,127][23468] Updated weights for policy 0, policy_version 68543 (0.0010) -[2023-10-09 11:02:25,117][23469] Updated weights for policy 1, policy_version 68901 (0.0007) -[2023-10-09 11:02:25,489][23469] Updated weights for policy 1, policy_version 68911 (0.0009) -[2023-10-09 11:02:25,845][23469] Updated weights for policy 1, policy_version 68921 (0.0010) -[2023-10-09 11:02:26,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 140738560. Throughput: 0: 1786.4, 1: 1815.2. Samples: 35197918. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) -[2023-10-09 11:02:26,078][22500] Avg episode reward: [(0, '10.450'), (1, '9.860')] -[2023-10-09 11:02:26,829][23468] Updated weights for policy 0, policy_version 68553 (0.0009) -[2023-10-09 11:02:27,207][23468] Updated weights for policy 0, policy_version 68563 (0.0009) -[2023-10-09 11:02:27,571][23468] Updated weights for policy 0, policy_version 68573 (0.0007) -[2023-10-09 11:02:29,519][23469] Updated weights for policy 1, policy_version 68931 (0.0011) -[2023-10-09 11:02:29,893][23469] Updated weights for policy 1, policy_version 68941 (0.0010) -[2023-10-09 11:02:30,268][23469] Updated weights for policy 1, policy_version 68951 (0.0010) -[2023-10-09 11:02:31,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 140836864. Throughput: 0: 1789.1, 1: 1809.9. Samples: 35218938. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) -[2023-10-09 11:02:31,078][22500] Avg episode reward: [(0, '10.630'), (1, '9.750')] -[2023-10-09 11:02:31,452][23468] Updated weights for policy 0, policy_version 68583 (0.0008) -[2023-10-09 11:02:31,817][23468] Updated weights for policy 0, policy_version 68593 (0.0009) -[2023-10-09 11:02:32,193][23468] Updated weights for policy 0, policy_version 68603 (0.0012) -[2023-10-09 11:02:33,984][23469] Updated weights for policy 1, policy_version 68961 (0.0010) -[2023-10-09 11:02:34,361][23469] Updated weights for policy 1, policy_version 68971 (0.0011) -[2023-10-09 11:02:34,726][23469] Updated weights for policy 1, policy_version 68981 (0.0010) -[2023-10-09 11:02:35,101][23469] Updated weights for policy 1, policy_version 68991 (0.0008) -[2023-10-09 11:02:36,060][23468] Updated weights for policy 0, policy_version 68613 (0.0009) -[2023-10-09 11:02:36,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 140902400. Throughput: 0: 1789.0, 1: 1812.0. Samples: 35230140. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) -[2023-10-09 11:02:36,078][22500] Avg episode reward: [(0, '10.620'), (1, '10.210')] -[2023-10-09 11:02:36,078][23343] Saving new best policy, reward=10.210! -[2023-10-09 11:02:36,425][23468] Updated weights for policy 0, policy_version 68623 (0.0009) -[2023-10-09 11:02:36,797][23468] Updated weights for policy 0, policy_version 68633 (0.0010) -[2023-10-09 11:02:38,905][23469] Updated weights for policy 1, policy_version 69001 (0.0008) -[2023-10-09 11:02:39,272][23469] Updated weights for policy 1, policy_version 69011 (0.0011) -[2023-10-09 11:02:39,646][23469] Updated weights for policy 1, policy_version 69021 (0.0008) -[2023-10-09 11:02:40,590][23468] Updated weights for policy 0, policy_version 68643 (0.0010) -[2023-10-09 11:02:40,965][23468] Updated weights for policy 0, policy_version 68653 (0.0007) -[2023-10-09 11:02:41,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 140967936. Throughput: 0: 1791.0, 1: 1809.5. Samples: 35251260. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:02:41,078][22500] Avg episode reward: [(0, '10.290'), (1, '9.440')] -[2023-10-09 11:02:41,344][23468] Updated weights for policy 0, policy_version 68663 (0.0008) -[2023-10-09 11:02:43,380][23469] Updated weights for policy 1, policy_version 69031 (0.0007) -[2023-10-09 11:02:43,760][23469] Updated weights for policy 1, policy_version 69041 (0.0009) -[2023-10-09 11:02:44,128][23469] Updated weights for policy 1, policy_version 69051 (0.0009) -[2023-10-09 11:02:45,080][23468] Updated weights for policy 0, policy_version 68673 (0.0007) -[2023-10-09 11:02:45,460][23468] Updated weights for policy 0, policy_version 68683 (0.0008) -[2023-10-09 11:02:45,822][23468] Updated weights for policy 0, policy_version 68693 (0.0007) -[2023-10-09 11:02:46,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 141033472. Throughput: 0: 1808.8, 1: 1806.0. Samples: 35273426. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:02:46,078][22500] Avg episode reward: [(0, '9.920'), (1, '8.640')] -[2023-10-09 11:02:46,199][23468] Updated weights for policy 0, policy_version 68703 (0.0007) -[2023-10-09 11:02:47,725][23469] Updated weights for policy 1, policy_version 69061 (0.0007) -[2023-10-09 11:02:48,102][23469] Updated weights for policy 1, policy_version 69071 (0.0011) -[2023-10-09 11:02:48,470][23469] Updated weights for policy 1, policy_version 69081 (0.0010) -[2023-10-09 11:02:49,990][23468] Updated weights for policy 0, policy_version 68713 (0.0011) -[2023-10-09 11:02:50,369][23468] Updated weights for policy 0, policy_version 68723 (0.0009) -[2023-10-09 11:02:50,734][23468] Updated weights for policy 0, policy_version 68733 (0.0008) -[2023-10-09 11:02:51,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 141131776. Throughput: 0: 1790.3, 1: 1815.4. Samples: 35283634. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:02:51,078][22500] Avg episode reward: [(0, '10.330'), (1, '9.080')] -[2023-10-09 11:02:52,110][23469] Updated weights for policy 1, policy_version 69091 (0.0009) -[2023-10-09 11:02:52,479][23469] Updated weights for policy 1, policy_version 69101 (0.0010) -[2023-10-09 11:02:52,847][23469] Updated weights for policy 1, policy_version 69111 (0.0010) -[2023-10-09 11:02:54,406][23468] Updated weights for policy 0, policy_version 68743 (0.0008) -[2023-10-09 11:02:54,785][23468] Updated weights for policy 0, policy_version 68753 (0.0007) -[2023-10-09 11:02:55,151][23468] Updated weights for policy 0, policy_version 68763 (0.0008) -[2023-10-09 11:02:56,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 141197312. Throughput: 0: 1810.8, 1: 1812.5. Samples: 35306014. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:02:56,078][22500] Avg episode reward: [(0, '10.340'), (1, '9.100')] -[2023-10-09 11:02:56,618][23469] Updated weights for policy 1, policy_version 69121 (0.0009) -[2023-10-09 11:02:56,989][23469] Updated weights for policy 1, policy_version 69131 (0.0011) -[2023-10-09 11:02:57,359][23469] Updated weights for policy 1, policy_version 69141 (0.0007) -[2023-10-09 11:02:57,720][23469] Updated weights for policy 1, policy_version 69151 (0.0009) -[2023-10-09 11:02:58,879][23468] Updated weights for policy 0, policy_version 68773 (0.0008) -[2023-10-09 11:02:59,251][23468] Updated weights for policy 0, policy_version 68783 (0.0008) -[2023-10-09 11:02:59,632][23468] Updated weights for policy 0, policy_version 68793 (0.0007) -[2023-10-09 11:03:01,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 141262848. Throughput: 0: 1785.9, 1: 1809.5. Samples: 35327338. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:03:01,079][22500] Avg episode reward: [(0, '9.950'), (1, '9.080')] -[2023-10-09 11:03:01,383][23469] Updated weights for policy 1, policy_version 69161 (0.0011) -[2023-10-09 11:03:01,755][23469] Updated weights for policy 1, policy_version 69171 (0.0007) -[2023-10-09 11:03:02,126][23469] Updated weights for policy 1, policy_version 69181 (0.0009) -[2023-10-09 11:03:03,491][23468] Updated weights for policy 0, policy_version 68803 (0.0009) -[2023-10-09 11:03:03,898][23468] Updated weights for policy 0, policy_version 68813 (0.0008) -[2023-10-09 11:03:04,266][23468] Updated weights for policy 0, policy_version 68823 (0.0011) -[2023-10-09 11:03:05,974][23469] Updated weights for policy 1, policy_version 69191 (0.0007) -[2023-10-09 11:03:06,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 141328384. Throughput: 0: 1807.6, 1: 1803.8. Samples: 35338518. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:03:06,078][22500] Avg episode reward: [(0, '9.890'), (1, '8.520')] -[2023-10-09 11:03:06,349][23469] Updated weights for policy 1, policy_version 69201 (0.0007) -[2023-10-09 11:03:06,724][23469] Updated weights for policy 1, policy_version 69211 (0.0008) -[2023-10-09 11:03:07,963][23468] Updated weights for policy 0, policy_version 68833 (0.0008) -[2023-10-09 11:03:08,347][23468] Updated weights for policy 0, policy_version 68843 (0.0011) -[2023-10-09 11:03:08,729][23468] Updated weights for policy 0, policy_version 68853 (0.0010) -[2023-10-09 11:03:09,099][23468] Updated weights for policy 0, policy_version 68863 (0.0010) -[2023-10-09 11:03:10,452][23469] Updated weights for policy 1, policy_version 69221 (0.0007) -[2023-10-09 11:03:10,813][23469] Updated weights for policy 1, policy_version 69231 (0.0007) -[2023-10-09 11:03:11,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 141393920. Throughput: 0: 1783.9, 1: 1802.0. Samples: 35359282. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:03:11,078][22500] Avg episode reward: [(0, '9.540'), (1, '8.760')] -[2023-10-09 11:03:11,183][23469] Updated weights for policy 1, policy_version 69241 (0.0011) -[2023-10-09 11:03:12,753][23468] Updated weights for policy 0, policy_version 68873 (0.0009) -[2023-10-09 11:03:13,132][23468] Updated weights for policy 0, policy_version 68883 (0.0008) -[2023-10-09 11:03:13,504][23468] Updated weights for policy 0, policy_version 68893 (0.0007) -[2023-10-09 11:03:14,922][23469] Updated weights for policy 1, policy_version 69251 (0.0009) -[2023-10-09 11:03:15,282][23469] Updated weights for policy 1, policy_version 69261 (0.0007) -[2023-10-09 11:03:15,658][23469] Updated weights for policy 1, policy_version 69271 (0.0009) -[2023-10-09 11:03:16,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 141492224. Throughput: 0: 1780.8, 1: 1811.2. Samples: 35380574. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:03:16,078][22500] Avg episode reward: [(0, '10.000'), (1, '8.360')] -[2023-10-09 11:03:17,288][23468] Updated weights for policy 0, policy_version 68903 (0.0007) -[2023-10-09 11:03:17,668][23468] Updated weights for policy 0, policy_version 68913 (0.0007) -[2023-10-09 11:03:18,039][23468] Updated weights for policy 0, policy_version 68923 (0.0009) -[2023-10-09 11:03:19,320][23469] Updated weights for policy 1, policy_version 69281 (0.0008) -[2023-10-09 11:03:19,682][23469] Updated weights for policy 1, policy_version 69291 (0.0007) -[2023-10-09 11:03:20,046][23469] Updated weights for policy 1, policy_version 69301 (0.0007) -[2023-10-09 11:03:20,426][23469] Updated weights for policy 1, policy_version 69311 (0.0010) -[2023-10-09 11:03:21,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 141557760. Throughput: 0: 1782.4, 1: 1803.8. Samples: 35391520. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:03:21,078][22500] Avg episode reward: [(0, '9.970'), (1, '8.360')] -[2023-10-09 11:03:21,746][23468] Updated weights for policy 0, policy_version 68933 (0.0008) -[2023-10-09 11:03:22,129][23468] Updated weights for policy 0, policy_version 68943 (0.0008) -[2023-10-09 11:03:22,499][23468] Updated weights for policy 0, policy_version 68953 (0.0007) -[2023-10-09 11:03:24,209][23469] Updated weights for policy 1, policy_version 69321 (0.0011) -[2023-10-09 11:03:24,575][23469] Updated weights for policy 1, policy_version 69331 (0.0008) -[2023-10-09 11:03:24,953][23469] Updated weights for policy 1, policy_version 69341 (0.0010) -[2023-10-09 11:03:26,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 141623296. Throughput: 0: 1780.4, 1: 1808.0. Samples: 35412734. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:03:26,078][22500] Avg episode reward: [(0, '9.980'), (1, '7.810')] -[2023-10-09 11:03:26,211][23468] Updated weights for policy 0, policy_version 68963 (0.0008) -[2023-10-09 11:03:26,585][23468] Updated weights for policy 0, policy_version 68973 (0.0007) -[2023-10-09 11:03:26,956][23468] Updated weights for policy 0, policy_version 68983 (0.0008) -[2023-10-09 11:03:28,748][23469] Updated weights for policy 1, policy_version 69351 (0.0008) -[2023-10-09 11:03:29,118][23469] Updated weights for policy 1, policy_version 69361 (0.0009) -[2023-10-09 11:03:29,480][23469] Updated weights for policy 1, policy_version 69371 (0.0007) -[2023-10-09 11:03:30,677][23468] Updated weights for policy 0, policy_version 68993 (0.0008) -[2023-10-09 11:03:31,052][23468] Updated weights for policy 0, policy_version 69003 (0.0010) -[2023-10-09 11:03:31,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 141688832. Throughput: 0: 1789.3, 1: 1799.1. Samples: 35434904. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:03:31,078][22500] Avg episode reward: [(0, '10.340'), (1, '8.330')] -[2023-10-09 11:03:31,435][23468] Updated weights for policy 0, policy_version 69013 (0.0009) -[2023-10-09 11:03:31,812][23468] Updated weights for policy 0, policy_version 69023 (0.0008) -[2023-10-09 11:03:33,234][23469] Updated weights for policy 1, policy_version 69381 (0.0007) -[2023-10-09 11:03:33,602][23469] Updated weights for policy 1, policy_version 69391 (0.0008) -[2023-10-09 11:03:33,969][23469] Updated weights for policy 1, policy_version 69401 (0.0008) -[2023-10-09 11:03:35,534][23468] Updated weights for policy 0, policy_version 69033 (0.0009) -[2023-10-09 11:03:35,902][23468] Updated weights for policy 0, policy_version 69043 (0.0011) -[2023-10-09 11:03:36,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 141754368. Throughput: 0: 1785.1, 1: 1808.3. Samples: 35445336. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:03:36,078][22500] Avg episode reward: [(0, '9.790'), (1, '9.280')] -[2023-10-09 11:03:36,273][23468] Updated weights for policy 0, policy_version 69053 (0.0011) -[2023-10-09 11:03:37,746][23469] Updated weights for policy 1, policy_version 69411 (0.0008) -[2023-10-09 11:03:38,121][23469] Updated weights for policy 1, policy_version 69421 (0.0009) -[2023-10-09 11:03:38,491][23469] Updated weights for policy 1, policy_version 69431 (0.0007) -[2023-10-09 11:03:40,129][23468] Updated weights for policy 0, policy_version 69063 (0.0008) -[2023-10-09 11:03:40,492][23468] Updated weights for policy 0, policy_version 69073 (0.0008) -[2023-10-09 11:03:40,870][23468] Updated weights for policy 0, policy_version 69083 (0.0009) -[2023-10-09 11:03:41,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 141852672. Throughput: 0: 1788.0, 1: 1792.4. Samples: 35467130. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:03:41,078][22500] Avg episode reward: [(0, '10.090'), (1, '9.220')] -[2023-10-09 11:03:42,257][23469] Updated weights for policy 1, policy_version 69441 (0.0009) -[2023-10-09 11:03:42,640][23469] Updated weights for policy 1, policy_version 69451 (0.0010) -[2023-10-09 11:03:43,010][23469] Updated weights for policy 1, policy_version 69461 (0.0010) -[2023-10-09 11:03:43,385][23469] Updated weights for policy 1, policy_version 69471 (0.0011) -[2023-10-09 11:03:44,562][23468] Updated weights for policy 0, policy_version 69093 (0.0008) -[2023-10-09 11:03:44,938][23468] Updated weights for policy 0, policy_version 69103 (0.0007) -[2023-10-09 11:03:45,307][23468] Updated weights for policy 0, policy_version 69113 (0.0009) -[2023-10-09 11:03:46,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 141918208. Throughput: 0: 1792.2, 1: 1789.3. Samples: 35488508. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:03:46,078][22500] Avg episode reward: [(0, '10.670'), (1, '9.290')] -[2023-10-09 11:03:47,203][23469] Updated weights for policy 1, policy_version 69481 (0.0008) -[2023-10-09 11:03:47,571][23469] Updated weights for policy 1, policy_version 69491 (0.0010) -[2023-10-09 11:03:47,944][23469] Updated weights for policy 1, policy_version 69501 (0.0010) -[2023-10-09 11:03:49,209][23468] Updated weights for policy 0, policy_version 69123 (0.0009) -[2023-10-09 11:03:49,616][23468] Updated weights for policy 0, policy_version 69133 (0.0010) -[2023-10-09 11:03:49,990][23468] Updated weights for policy 0, policy_version 69143 (0.0008) -[2023-10-09 11:03:51,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 141983744. Throughput: 0: 1783.6, 1: 1784.8. Samples: 35499092. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:03:51,078][22500] Avg episode reward: [(0, '10.580'), (1, '8.190')] -[2023-10-09 11:03:51,719][23469] Updated weights for policy 1, policy_version 69511 (0.0010) -[2023-10-09 11:03:52,089][23469] Updated weights for policy 1, policy_version 69521 (0.0009) -[2023-10-09 11:03:52,457][23469] Updated weights for policy 1, policy_version 69531 (0.0011) -[2023-10-09 11:03:53,783][23468] Updated weights for policy 0, policy_version 69153 (0.0009) -[2023-10-09 11:03:54,162][23468] Updated weights for policy 0, policy_version 69163 (0.0009) -[2023-10-09 11:03:54,531][23468] Updated weights for policy 0, policy_version 69173 (0.0008) -[2023-10-09 11:03:54,913][23468] Updated weights for policy 0, policy_version 69183 (0.0008) -[2023-10-09 11:03:56,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 142049280. Throughput: 0: 1799.3, 1: 1781.0. Samples: 35520396. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:03:56,078][22500] Avg episode reward: [(0, '11.330'), (1, '8.260')] -[2023-10-09 11:03:56,078][23265] Saving new best policy, reward=11.330! -[2023-10-09 11:03:56,260][23469] Updated weights for policy 1, policy_version 69541 (0.0009) -[2023-10-09 11:03:56,641][23469] Updated weights for policy 1, policy_version 69551 (0.0007) -[2023-10-09 11:03:57,018][23469] Updated weights for policy 1, policy_version 69561 (0.0008) -[2023-10-09 11:03:58,755][23468] Updated weights for policy 0, policy_version 69193 (0.0008) -[2023-10-09 11:03:59,122][23468] Updated weights for policy 0, policy_version 69203 (0.0007) -[2023-10-09 11:03:59,497][23468] Updated weights for policy 0, policy_version 69213 (0.0007) -[2023-10-09 11:04:00,679][23469] Updated weights for policy 1, policy_version 69571 (0.0008) -[2023-10-09 11:04:01,049][23469] Updated weights for policy 1, policy_version 69581 (0.0007) -[2023-10-09 11:04:01,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 142114816. Throughput: 0: 1775.7, 1: 1801.8. Samples: 35541562. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:04:01,078][22500] Avg episode reward: [(0, '9.580'), (1, '8.990')] -[2023-10-09 11:04:01,416][23469] Updated weights for policy 1, policy_version 69591 (0.0009) -[2023-10-09 11:04:03,394][23468] Updated weights for policy 0, policy_version 69223 (0.0007) -[2023-10-09 11:04:03,770][23468] Updated weights for policy 0, policy_version 69233 (0.0008) -[2023-10-09 11:04:04,140][23468] Updated weights for policy 0, policy_version 69243 (0.0011) -[2023-10-09 11:04:05,126][23469] Updated weights for policy 1, policy_version 69601 (0.0009) -[2023-10-09 11:04:05,493][23469] Updated weights for policy 1, policy_version 69611 (0.0008) -[2023-10-09 11:04:05,869][23469] Updated weights for policy 1, policy_version 69621 (0.0008) -[2023-10-09 11:04:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 142180352. Throughput: 0: 1800.0, 1: 1781.0. Samples: 35552668. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:04:06,078][22500] Avg episode reward: [(0, '9.610'), (1, '9.100')] -[2023-10-09 11:04:06,235][23469] Updated weights for policy 1, policy_version 69631 (0.0007) -[2023-10-09 11:04:07,842][23468] Updated weights for policy 0, policy_version 69253 (0.0010) -[2023-10-09 11:04:08,206][23468] Updated weights for policy 0, policy_version 69263 (0.0007) -[2023-10-09 11:04:08,583][23468] Updated weights for policy 0, policy_version 69273 (0.0007) -[2023-10-09 11:04:09,870][23469] Updated weights for policy 1, policy_version 69641 (0.0007) -[2023-10-09 11:04:10,241][23469] Updated weights for policy 1, policy_version 69651 (0.0008) -[2023-10-09 11:04:10,612][23469] Updated weights for policy 1, policy_version 69661 (0.0010) -[2023-10-09 11:04:11,078][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 142278656. Throughput: 0: 1773.1, 1: 1809.2. Samples: 35573940. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:04:11,079][22500] Avg episode reward: [(0, '8.680'), (1, '9.870')] -[2023-10-09 11:04:12,396][23468] Updated weights for policy 0, policy_version 69283 (0.0009) -[2023-10-09 11:04:12,757][23468] Updated weights for policy 0, policy_version 69293 (0.0008) -[2023-10-09 11:04:13,130][23468] Updated weights for policy 0, policy_version 69303 (0.0008) -[2023-10-09 11:04:14,531][23469] Updated weights for policy 1, policy_version 69671 (0.0009) -[2023-10-09 11:04:14,911][23469] Updated weights for policy 1, policy_version 69681 (0.0007) -[2023-10-09 11:04:15,278][23469] Updated weights for policy 1, policy_version 69691 (0.0007) -[2023-10-09 11:04:16,078][22500] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 142344192. Throughput: 0: 1768.7, 1: 1787.9. Samples: 35594952. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:04:16,078][22500] Avg episode reward: [(0, '9.490'), (1, '9.610')] -[2023-10-09 11:04:16,087][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000069696_71368704.pth... -[2023-10-09 11:04:16,088][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000069312_70975488.pth... -[2023-10-09 11:04:16,123][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000067648_69271552.pth -[2023-10-09 11:04:16,129][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000068000_69632000.pth -[2023-10-09 11:04:16,964][23468] Updated weights for policy 0, policy_version 69313 (0.0008) -[2023-10-09 11:04:17,340][23468] Updated weights for policy 0, policy_version 69323 (0.0008) -[2023-10-09 11:04:17,713][23468] Updated weights for policy 0, policy_version 69333 (0.0007) -[2023-10-09 11:04:18,074][23468] Updated weights for policy 0, policy_version 69343 (0.0009) -[2023-10-09 11:04:18,807][23469] Updated weights for policy 1, policy_version 69701 (0.0009) -[2023-10-09 11:04:19,172][23469] Updated weights for policy 1, policy_version 69711 (0.0009) -[2023-10-09 11:04:19,541][23469] Updated weights for policy 1, policy_version 69721 (0.0010) -[2023-10-09 11:04:21,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 142409728. Throughput: 0: 1765.7, 1: 1811.0. Samples: 35606290. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:04:21,078][22500] Avg episode reward: [(0, '10.330'), (1, '9.850')] -[2023-10-09 11:04:21,848][23468] Updated weights for policy 0, policy_version 69353 (0.0008) -[2023-10-09 11:04:22,226][23468] Updated weights for policy 0, policy_version 69363 (0.0007) -[2023-10-09 11:04:22,592][23468] Updated weights for policy 0, policy_version 69373 (0.0008) -[2023-10-09 11:04:23,314][23469] Updated weights for policy 1, policy_version 69731 (0.0009) -[2023-10-09 11:04:23,690][23469] Updated weights for policy 1, policy_version 69741 (0.0007) -[2023-10-09 11:04:24,055][23469] Updated weights for policy 1, policy_version 69751 (0.0008) -[2023-10-09 11:04:26,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 142475264. Throughput: 0: 1762.6, 1: 1794.0. Samples: 35627180. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:04:26,078][22500] Avg episode reward: [(0, '10.330'), (1, '9.370')] -[2023-10-09 11:04:26,362][23468] Updated weights for policy 0, policy_version 69383 (0.0009) -[2023-10-09 11:04:26,734][23468] Updated weights for policy 0, policy_version 69393 (0.0009) -[2023-10-09 11:04:27,108][23468] Updated weights for policy 0, policy_version 69403 (0.0007) -[2023-10-09 11:04:27,714][23469] Updated weights for policy 1, policy_version 69761 (0.0007) -[2023-10-09 11:04:28,079][23469] Updated weights for policy 1, policy_version 69771 (0.0008) -[2023-10-09 11:04:28,453][23469] Updated weights for policy 1, policy_version 69781 (0.0008) -[2023-10-09 11:04:28,830][23469] Updated weights for policy 1, policy_version 69791 (0.0008) -[2023-10-09 11:04:30,950][23468] Updated weights for policy 0, policy_version 69413 (0.0008) -[2023-10-09 11:04:31,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 142540800. Throughput: 0: 1786.6, 1: 1798.0. Samples: 35649818. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:04:31,078][22500] Avg episode reward: [(0, '10.070'), (1, '9.500')] -[2023-10-09 11:04:31,322][23468] Updated weights for policy 0, policy_version 69423 (0.0007) -[2023-10-09 11:04:31,691][23468] Updated weights for policy 0, policy_version 69433 (0.0008) -[2023-10-09 11:04:32,606][23469] Updated weights for policy 1, policy_version 69801 (0.0008) -[2023-10-09 11:04:32,974][23469] Updated weights for policy 1, policy_version 69811 (0.0008) -[2023-10-09 11:04:33,346][23469] Updated weights for policy 1, policy_version 69821 (0.0008) -[2023-10-09 11:04:35,299][23468] Updated weights for policy 0, policy_version 69443 (0.0007) -[2023-10-09 11:04:35,691][23468] Updated weights for policy 0, policy_version 69453 (0.0009) -[2023-10-09 11:04:36,069][23468] Updated weights for policy 0, policy_version 69463 (0.0010) -[2023-10-09 11:04:36,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 142606336. Throughput: 0: 1766.3, 1: 1802.7. Samples: 35659696. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:04:36,078][22500] Avg episode reward: [(0, '10.070'), (1, '8.890')] -[2023-10-09 11:04:37,041][23469] Updated weights for policy 1, policy_version 69831 (0.0010) -[2023-10-09 11:04:37,409][23469] Updated weights for policy 1, policy_version 69841 (0.0010) -[2023-10-09 11:04:37,774][23469] Updated weights for policy 1, policy_version 69851 (0.0008) -[2023-10-09 11:04:39,880][23468] Updated weights for policy 0, policy_version 69473 (0.0008) -[2023-10-09 11:04:40,255][23468] Updated weights for policy 0, policy_version 69483 (0.0008) -[2023-10-09 11:04:40,634][23468] Updated weights for policy 0, policy_version 69493 (0.0009) -[2023-10-09 11:04:41,005][23468] Updated weights for policy 0, policy_version 69503 (0.0007) -[2023-10-09 11:04:41,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 142704640. Throughput: 0: 1786.7, 1: 1806.7. Samples: 35682100. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:04:41,079][22500] Avg episode reward: [(0, '9.990'), (1, '9.310')] -[2023-10-09 11:04:41,556][23469] Updated weights for policy 1, policy_version 69861 (0.0007) -[2023-10-09 11:04:41,925][23469] Updated weights for policy 1, policy_version 69871 (0.0010) -[2023-10-09 11:04:42,295][23469] Updated weights for policy 1, policy_version 69881 (0.0010) -[2023-10-09 11:04:44,661][23468] Updated weights for policy 0, policy_version 69513 (0.0008) -[2023-10-09 11:04:45,034][23468] Updated weights for policy 0, policy_version 69523 (0.0008) -[2023-10-09 11:04:45,403][23468] Updated weights for policy 0, policy_version 69533 (0.0008) -[2023-10-09 11:04:46,077][23469] Updated weights for policy 1, policy_version 69891 (0.0010) -[2023-10-09 11:04:46,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 142770176. Throughput: 0: 1782.9, 1: 1813.0. Samples: 35703378. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:04:46,078][22500] Avg episode reward: [(0, '9.750'), (1, '8.830')] -[2023-10-09 11:04:46,446][23469] Updated weights for policy 1, policy_version 69901 (0.0009) -[2023-10-09 11:04:46,819][23469] Updated weights for policy 1, policy_version 69911 (0.0009) -[2023-10-09 11:04:48,991][23468] Updated weights for policy 0, policy_version 69543 (0.0009) -[2023-10-09 11:04:49,359][23468] Updated weights for policy 0, policy_version 69553 (0.0008) -[2023-10-09 11:04:49,740][23468] Updated weights for policy 0, policy_version 69563 (0.0008) -[2023-10-09 11:04:50,498][23469] Updated weights for policy 1, policy_version 69921 (0.0009) -[2023-10-09 11:04:50,867][23469] Updated weights for policy 1, policy_version 69931 (0.0010) -[2023-10-09 11:04:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 142835712. Throughput: 0: 1792.9, 1: 1807.3. Samples: 35714680. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:04:51,079][22500] Avg episode reward: [(0, '10.540'), (1, '8.990')] -[2023-10-09 11:04:51,238][23469] Updated weights for policy 1, policy_version 69941 (0.0010) -[2023-10-09 11:04:51,601][23469] Updated weights for policy 1, policy_version 69951 (0.0008) -[2023-10-09 11:04:53,417][23468] Updated weights for policy 0, policy_version 69573 (0.0009) -[2023-10-09 11:04:53,786][23468] Updated weights for policy 0, policy_version 69583 (0.0010) -[2023-10-09 11:04:54,159][23468] Updated weights for policy 0, policy_version 69593 (0.0010) -[2023-10-09 11:04:55,308][23469] Updated weights for policy 1, policy_version 69961 (0.0009) -[2023-10-09 11:04:55,675][23469] Updated weights for policy 1, policy_version 69971 (0.0009) -[2023-10-09 11:04:56,039][23469] Updated weights for policy 1, policy_version 69981 (0.0008) -[2023-10-09 11:04:56,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 142901248. Throughput: 0: 1793.4, 1: 1807.6. Samples: 35735984. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:04:56,078][22500] Avg episode reward: [(0, '10.100'), (1, '9.250')] -[2023-10-09 11:04:57,874][23468] Updated weights for policy 0, policy_version 69603 (0.0010) -[2023-10-09 11:04:58,244][23468] Updated weights for policy 0, policy_version 69613 (0.0010) -[2023-10-09 11:04:58,626][23468] Updated weights for policy 0, policy_version 69623 (0.0007) -[2023-10-09 11:04:59,763][23469] Updated weights for policy 1, policy_version 69991 (0.0009) -[2023-10-09 11:05:00,142][23469] Updated weights for policy 1, policy_version 70001 (0.0010) -[2023-10-09 11:05:00,509][23469] Updated weights for policy 1, policy_version 70011 (0.0007) -[2023-10-09 11:05:01,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 142999552. Throughput: 0: 1784.9, 1: 1806.7. Samples: 35756576. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:05:01,078][22500] Avg episode reward: [(0, '10.170'), (1, '9.570')] -[2023-10-09 11:05:02,457][23468] Updated weights for policy 0, policy_version 69633 (0.0008) -[2023-10-09 11:05:02,834][23468] Updated weights for policy 0, policy_version 69643 (0.0008) -[2023-10-09 11:05:03,200][23468] Updated weights for policy 0, policy_version 69653 (0.0011) -[2023-10-09 11:05:03,575][23468] Updated weights for policy 0, policy_version 69663 (0.0008) -[2023-10-09 11:05:04,276][23469] Updated weights for policy 1, policy_version 70021 (0.0008) -[2023-10-09 11:05:04,651][23469] Updated weights for policy 1, policy_version 70031 (0.0007) -[2023-10-09 11:05:05,031][23469] Updated weights for policy 1, policy_version 70041 (0.0008) -[2023-10-09 11:05:06,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 143065088. Throughput: 0: 1794.5, 1: 1802.0. Samples: 35768134. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:05:06,078][22500] Avg episode reward: [(0, '10.140'), (1, '9.600')] -[2023-10-09 11:05:07,511][23468] Updated weights for policy 0, policy_version 69673 (0.0007) -[2023-10-09 11:05:07,881][23468] Updated weights for policy 0, policy_version 69683 (0.0008) -[2023-10-09 11:05:08,251][23468] Updated weights for policy 0, policy_version 69693 (0.0008) -[2023-10-09 11:05:08,689][23469] Updated weights for policy 1, policy_version 70051 (0.0010) -[2023-10-09 11:05:09,065][23469] Updated weights for policy 1, policy_version 70061 (0.0009) -[2023-10-09 11:05:09,435][23469] Updated weights for policy 1, policy_version 70071 (0.0010) -[2023-10-09 11:05:11,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 143130624. Throughput: 0: 1786.9, 1: 1804.4. Samples: 35788788. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:05:11,078][22500] Avg episode reward: [(0, '9.460'), (1, '9.800')] -[2023-10-09 11:05:12,043][23468] Updated weights for policy 0, policy_version 69703 (0.0009) -[2023-10-09 11:05:12,419][23468] Updated weights for policy 0, policy_version 69713 (0.0007) -[2023-10-09 11:05:12,790][23468] Updated weights for policy 0, policy_version 69723 (0.0009) -[2023-10-09 11:05:13,196][23469] Updated weights for policy 1, policy_version 70081 (0.0010) -[2023-10-09 11:05:13,558][23469] Updated weights for policy 1, policy_version 70091 (0.0009) -[2023-10-09 11:05:13,933][23469] Updated weights for policy 1, policy_version 70101 (0.0011) -[2023-10-09 11:05:14,305][23469] Updated weights for policy 1, policy_version 70111 (0.0007) -[2023-10-09 11:05:16,078][22500] Fps is (10 sec: 13106.7, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 143196160. Throughput: 0: 1785.7, 1: 1788.9. Samples: 35810676. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:05:16,078][22500] Avg episode reward: [(0, '9.330'), (1, '9.740')] -[2023-10-09 11:05:16,465][23468] Updated weights for policy 0, policy_version 69733 (0.0009) -[2023-10-09 11:05:16,847][23468] Updated weights for policy 0, policy_version 69743 (0.0009) -[2023-10-09 11:05:17,211][23468] Updated weights for policy 0, policy_version 69753 (0.0008) -[2023-10-09 11:05:18,194][23469] Updated weights for policy 1, policy_version 70121 (0.0009) -[2023-10-09 11:05:18,569][23469] Updated weights for policy 1, policy_version 70131 (0.0009) -[2023-10-09 11:05:18,929][23469] Updated weights for policy 1, policy_version 70141 (0.0008) -[2023-10-09 11:05:21,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 143261696. Throughput: 0: 1783.5, 1: 1799.8. Samples: 35820944. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:05:21,078][22500] Avg episode reward: [(0, '9.040'), (1, '9.280')] -[2023-10-09 11:05:21,172][23468] Updated weights for policy 0, policy_version 69763 (0.0007) -[2023-10-09 11:05:21,547][23468] Updated weights for policy 0, policy_version 69773 (0.0009) -[2023-10-09 11:05:21,924][23468] Updated weights for policy 0, policy_version 69783 (0.0011) -[2023-10-09 11:05:22,593][23469] Updated weights for policy 1, policy_version 70151 (0.0008) -[2023-10-09 11:05:22,962][23469] Updated weights for policy 1, policy_version 70161 (0.0008) -[2023-10-09 11:05:23,319][23469] Updated weights for policy 1, policy_version 70171 (0.0007) -[2023-10-09 11:05:25,511][23468] Updated weights for policy 0, policy_version 69793 (0.0008) -[2023-10-09 11:05:25,877][23468] Updated weights for policy 0, policy_version 69803 (0.0008) -[2023-10-09 11:05:26,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 143327232. Throughput: 0: 1788.0, 1: 1792.9. Samples: 35843242. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:05:26,078][22500] Avg episode reward: [(0, '9.260'), (1, '9.700')] -[2023-10-09 11:05:26,261][23468] Updated weights for policy 0, policy_version 69813 (0.0010) -[2023-10-09 11:05:26,628][23468] Updated weights for policy 0, policy_version 69823 (0.0007) -[2023-10-09 11:05:27,119][23469] Updated weights for policy 1, policy_version 70181 (0.0009) -[2023-10-09 11:05:27,474][23469] Updated weights for policy 1, policy_version 70191 (0.0007) -[2023-10-09 11:05:27,849][23469] Updated weights for policy 1, policy_version 70201 (0.0008) -[2023-10-09 11:05:30,345][23468] Updated weights for policy 0, policy_version 69833 (0.0008) -[2023-10-09 11:05:30,711][23468] Updated weights for policy 0, policy_version 69843 (0.0008) -[2023-10-09 11:05:31,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 143392768. Throughput: 0: 1809.2, 1: 1792.9. Samples: 35865474. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:05:31,078][22500] Avg episode reward: [(0, '9.420'), (1, '9.710')] -[2023-10-09 11:05:31,090][23468] Updated weights for policy 0, policy_version 69853 (0.0010) -[2023-10-09 11:05:31,582][23469] Updated weights for policy 1, policy_version 70211 (0.0010) -[2023-10-09 11:05:31,943][23469] Updated weights for policy 1, policy_version 70221 (0.0011) -[2023-10-09 11:05:32,311][23469] Updated weights for policy 1, policy_version 70231 (0.0011) -[2023-10-09 11:05:34,745][23468] Updated weights for policy 0, policy_version 69863 (0.0008) -[2023-10-09 11:05:35,106][23468] Updated weights for policy 0, policy_version 69873 (0.0009) -[2023-10-09 11:05:35,481][23468] Updated weights for policy 0, policy_version 69883 (0.0008) -[2023-10-09 11:05:35,911][23469] Updated weights for policy 1, policy_version 70241 (0.0010) -[2023-10-09 11:05:36,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 143491072. Throughput: 0: 1784.6, 1: 1790.8. Samples: 35875574. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:05:36,078][22500] Avg episode reward: [(0, '10.060'), (1, '9.780')] -[2023-10-09 11:05:36,287][23469] Updated weights for policy 1, policy_version 70251 (0.0009) -[2023-10-09 11:05:36,648][23469] Updated weights for policy 1, policy_version 70261 (0.0008) -[2023-10-09 11:05:37,017][23469] Updated weights for policy 1, policy_version 70271 (0.0011) -[2023-10-09 11:05:39,413][23468] Updated weights for policy 0, policy_version 69893 (0.0008) -[2023-10-09 11:05:39,786][23468] Updated weights for policy 0, policy_version 69903 (0.0007) -[2023-10-09 11:05:40,161][23468] Updated weights for policy 0, policy_version 69913 (0.0009) -[2023-10-09 11:05:40,761][23469] Updated weights for policy 1, policy_version 70281 (0.0009) -[2023-10-09 11:05:41,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 143556608. Throughput: 0: 1808.2, 1: 1794.5. Samples: 35898106. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 11:05:41,078][22500] Avg episode reward: [(0, '9.780'), (1, '9.730')] -[2023-10-09 11:05:41,134][23469] Updated weights for policy 1, policy_version 70291 (0.0008) -[2023-10-09 11:05:41,498][23469] Updated weights for policy 1, policy_version 70301 (0.0009) -[2023-10-09 11:05:43,956][23468] Updated weights for policy 0, policy_version 69923 (0.0011) -[2023-10-09 11:05:44,331][23468] Updated weights for policy 0, policy_version 69933 (0.0010) -[2023-10-09 11:05:44,711][23468] Updated weights for policy 0, policy_version 69943 (0.0008) -[2023-10-09 11:05:45,307][23469] Updated weights for policy 1, policy_version 70311 (0.0008) -[2023-10-09 11:05:45,686][23469] Updated weights for policy 1, policy_version 70321 (0.0011) -[2023-10-09 11:05:46,061][23469] Updated weights for policy 1, policy_version 70331 (0.0009) -[2023-10-09 11:05:46,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 143622144. Throughput: 0: 1782.1, 1: 1807.9. Samples: 35918128. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 11:05:46,079][22500] Avg episode reward: [(0, '10.290'), (1, '9.510')] -[2023-10-09 11:05:48,535][23468] Updated weights for policy 0, policy_version 69953 (0.0009) -[2023-10-09 11:05:48,907][23468] Updated weights for policy 0, policy_version 69963 (0.0009) -[2023-10-09 11:05:49,289][23468] Updated weights for policy 0, policy_version 69973 (0.0009) -[2023-10-09 11:05:49,670][23468] Updated weights for policy 0, policy_version 69983 (0.0008) -[2023-10-09 11:05:49,761][23469] Updated weights for policy 1, policy_version 70341 (0.0008) -[2023-10-09 11:05:50,138][23469] Updated weights for policy 1, policy_version 70351 (0.0008) -[2023-10-09 11:05:50,511][23469] Updated weights for policy 1, policy_version 70361 (0.0010) -[2023-10-09 11:05:51,077][22500] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 143720448. Throughput: 0: 1808.6, 1: 1790.7. Samples: 35930102. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 11:05:51,078][22500] Avg episode reward: [(0, '10.380'), (1, '8.880')] -[2023-10-09 11:05:53,346][23468] Updated weights for policy 0, policy_version 69993 (0.0009) -[2023-10-09 11:05:53,725][23468] Updated weights for policy 0, policy_version 70003 (0.0007) -[2023-10-09 11:05:54,096][23468] Updated weights for policy 0, policy_version 70013 (0.0008) -[2023-10-09 11:05:54,242][23469] Updated weights for policy 1, policy_version 70371 (0.0010) -[2023-10-09 11:05:54,617][23469] Updated weights for policy 1, policy_version 70381 (0.0007) -[2023-10-09 11:05:54,985][23469] Updated weights for policy 1, policy_version 70391 (0.0008) -[2023-10-09 11:05:56,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 143785984. Throughput: 0: 1783.9, 1: 1802.5. Samples: 35950178. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 11:05:56,078][22500] Avg episode reward: [(0, '10.320'), (1, '9.460')] -[2023-10-09 11:05:57,750][23468] Updated weights for policy 0, policy_version 70023 (0.0009) -[2023-10-09 11:05:58,111][23468] Updated weights for policy 0, policy_version 70033 (0.0009) -[2023-10-09 11:05:58,488][23468] Updated weights for policy 0, policy_version 70043 (0.0008) -[2023-10-09 11:05:58,789][23469] Updated weights for policy 1, policy_version 70401 (0.0009) -[2023-10-09 11:05:59,154][23469] Updated weights for policy 1, policy_version 70411 (0.0009) -[2023-10-09 11:05:59,526][23469] Updated weights for policy 1, policy_version 70421 (0.0008) -[2023-10-09 11:05:59,906][23469] Updated weights for policy 1, policy_version 70431 (0.0007) -[2023-10-09 11:06:01,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 143851520. Throughput: 0: 1785.3, 1: 1797.3. Samples: 35971894. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 11:06:01,079][22500] Avg episode reward: [(0, '10.840'), (1, '9.340')] -[2023-10-09 11:06:02,337][23468] Updated weights for policy 0, policy_version 70053 (0.0010) -[2023-10-09 11:06:02,714][23468] Updated weights for policy 0, policy_version 70063 (0.0009) -[2023-10-09 11:06:03,093][23468] Updated weights for policy 0, policy_version 70073 (0.0010) -[2023-10-09 11:06:03,678][23469] Updated weights for policy 1, policy_version 70441 (0.0009) -[2023-10-09 11:06:04,045][23469] Updated weights for policy 1, policy_version 70451 (0.0010) -[2023-10-09 11:06:04,421][23469] Updated weights for policy 1, policy_version 70461 (0.0008) -[2023-10-09 11:06:06,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 143917056. Throughput: 0: 1787.1, 1: 1808.1. Samples: 35982732. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 11:06:06,079][22500] Avg episode reward: [(0, '9.200'), (1, '9.410')] -[2023-10-09 11:06:06,884][23468] Updated weights for policy 0, policy_version 70083 (0.0009) -[2023-10-09 11:06:07,283][23468] Updated weights for policy 0, policy_version 70093 (0.0008) -[2023-10-09 11:06:07,661][23468] Updated weights for policy 0, policy_version 70103 (0.0009) -[2023-10-09 11:06:08,197][23469] Updated weights for policy 1, policy_version 70471 (0.0008) -[2023-10-09 11:06:08,574][23469] Updated weights for policy 1, policy_version 70481 (0.0008) -[2023-10-09 11:06:08,936][23469] Updated weights for policy 1, policy_version 70491 (0.0009) -[2023-10-09 11:06:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 143982592. Throughput: 0: 1778.0, 1: 1796.8. Samples: 36004112. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 11:06:11,078][22500] Avg episode reward: [(0, '9.630'), (1, '8.840')] -[2023-10-09 11:06:11,405][23468] Updated weights for policy 0, policy_version 70113 (0.0008) -[2023-10-09 11:06:11,786][23468] Updated weights for policy 0, policy_version 70123 (0.0007) -[2023-10-09 11:06:12,156][23468] Updated weights for policy 0, policy_version 70133 (0.0009) -[2023-10-09 11:06:12,531][23468] Updated weights for policy 0, policy_version 70143 (0.0009) -[2023-10-09 11:06:12,768][23469] Updated weights for policy 1, policy_version 70501 (0.0009) -[2023-10-09 11:06:13,145][23469] Updated weights for policy 1, policy_version 70511 (0.0009) -[2023-10-09 11:06:13,523][23469] Updated weights for policy 1, policy_version 70521 (0.0009) -[2023-10-09 11:06:16,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 144048128. Throughput: 0: 1783.1, 1: 1792.9. Samples: 36026392. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 11:06:16,078][22500] Avg episode reward: [(0, '8.470'), (1, '8.710')] -[2023-10-09 11:06:16,084][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000070528_72220672.pth... -[2023-10-09 11:06:16,122][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000068864_70516736.pth -[2023-10-09 11:06:16,326][23468] Updated weights for policy 0, policy_version 70153 (0.0008) -[2023-10-09 11:06:16,698][23468] Updated weights for policy 0, policy_version 70163 (0.0007) -[2023-10-09 11:06:17,069][23468] Updated weights for policy 0, policy_version 70173 (0.0009) -[2023-10-09 11:06:17,179][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000070176_71860224.pth... -[2023-10-09 11:06:17,180][23469] Updated weights for policy 1, policy_version 70531 (0.0008) -[2023-10-09 11:06:17,212][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000068480_70123520.pth -[2023-10-09 11:06:17,551][23469] Updated weights for policy 1, policy_version 70541 (0.0009) -[2023-10-09 11:06:17,918][23469] Updated weights for policy 1, policy_version 70551 (0.0008) -[2023-10-09 11:06:20,851][23468] Updated weights for policy 0, policy_version 70183 (0.0007) -[2023-10-09 11:06:21,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 144113664. Throughput: 0: 1773.7, 1: 1797.4. Samples: 36036276. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 11:06:21,078][22500] Avg episode reward: [(0, '9.360'), (1, '9.090')] -[2023-10-09 11:06:21,235][23468] Updated weights for policy 0, policy_version 70193 (0.0007) -[2023-10-09 11:06:21,608][23468] Updated weights for policy 0, policy_version 70203 (0.0007) -[2023-10-09 11:06:21,626][23469] Updated weights for policy 1, policy_version 70561 (0.0009) -[2023-10-09 11:06:22,001][23469] Updated weights for policy 1, policy_version 70571 (0.0007) -[2023-10-09 11:06:22,377][23469] Updated weights for policy 1, policy_version 70581 (0.0008) -[2023-10-09 11:06:22,751][23469] Updated weights for policy 1, policy_version 70591 (0.0009) -[2023-10-09 11:06:25,334][23468] Updated weights for policy 0, policy_version 70213 (0.0009) -[2023-10-09 11:06:25,703][23468] Updated weights for policy 0, policy_version 70223 (0.0008) -[2023-10-09 11:06:26,073][23468] Updated weights for policy 0, policy_version 70233 (0.0007) -[2023-10-09 11:06:26,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 144179200. Throughput: 0: 1772.5, 1: 1790.4. Samples: 36058436. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 11:06:26,078][22500] Avg episode reward: [(0, '10.010'), (1, '9.200')] -[2023-10-09 11:06:26,409][23469] Updated weights for policy 1, policy_version 70601 (0.0008) -[2023-10-09 11:06:26,779][23469] Updated weights for policy 1, policy_version 70611 (0.0007) -[2023-10-09 11:06:27,149][23469] Updated weights for policy 1, policy_version 70621 (0.0008) -[2023-10-09 11:06:29,840][23468] Updated weights for policy 0, policy_version 70243 (0.0007) -[2023-10-09 11:06:30,211][23468] Updated weights for policy 0, policy_version 70253 (0.0008) -[2023-10-09 11:06:30,583][23468] Updated weights for policy 0, policy_version 70263 (0.0007) -[2023-10-09 11:06:31,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 144277504. Throughput: 0: 1794.7, 1: 1808.2. Samples: 36080256. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:06:31,078][22500] Avg episode reward: [(0, '9.890'), (1, '9.420')] -[2023-10-09 11:06:31,139][23469] Updated weights for policy 1, policy_version 70631 (0.0008) -[2023-10-09 11:06:31,533][23469] Updated weights for policy 1, policy_version 70641 (0.0008) -[2023-10-09 11:06:31,907][23469] Updated weights for policy 1, policy_version 70651 (0.0010) -[2023-10-09 11:06:34,191][23468] Updated weights for policy 0, policy_version 70273 (0.0010) -[2023-10-09 11:06:34,569][23468] Updated weights for policy 0, policy_version 70283 (0.0007) -[2023-10-09 11:06:34,945][23468] Updated weights for policy 0, policy_version 70293 (0.0007) -[2023-10-09 11:06:35,317][23468] Updated weights for policy 0, policy_version 70303 (0.0008) -[2023-10-09 11:06:35,688][23469] Updated weights for policy 1, policy_version 70661 (0.0009) -[2023-10-09 11:06:36,062][23469] Updated weights for policy 1, policy_version 70671 (0.0008) -[2023-10-09 11:06:36,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 144343040. Throughput: 0: 1780.2, 1: 1785.2. Samples: 36090542. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:06:36,078][22500] Avg episode reward: [(0, '10.600'), (1, '9.330')] -[2023-10-09 11:06:36,429][23469] Updated weights for policy 1, policy_version 70681 (0.0007) -[2023-10-09 11:06:38,818][23468] Updated weights for policy 0, policy_version 70313 (0.0008) -[2023-10-09 11:06:39,190][23468] Updated weights for policy 0, policy_version 70323 (0.0007) -[2023-10-09 11:06:39,566][23468] Updated weights for policy 0, policy_version 70333 (0.0009) -[2023-10-09 11:06:40,220][23469] Updated weights for policy 1, policy_version 70691 (0.0008) -[2023-10-09 11:06:40,593][23469] Updated weights for policy 1, policy_version 70701 (0.0008) -[2023-10-09 11:06:40,971][23469] Updated weights for policy 1, policy_version 70711 (0.0010) -[2023-10-09 11:06:41,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 144408576. Throughput: 0: 1800.9, 1: 1798.3. Samples: 36112144. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:06:41,078][22500] Avg episode reward: [(0, '10.430'), (1, '9.390')] -[2023-10-09 11:06:43,412][23468] Updated weights for policy 0, policy_version 70343 (0.0007) -[2023-10-09 11:06:43,781][23468] Updated weights for policy 0, policy_version 70353 (0.0008) -[2023-10-09 11:06:44,166][23468] Updated weights for policy 0, policy_version 70363 (0.0008) -[2023-10-09 11:06:44,703][23469] Updated weights for policy 1, policy_version 70721 (0.0009) -[2023-10-09 11:06:45,081][23469] Updated weights for policy 1, policy_version 70731 (0.0009) -[2023-10-09 11:06:45,448][23469] Updated weights for policy 1, policy_version 70741 (0.0007) -[2023-10-09 11:06:45,818][23469] Updated weights for policy 1, policy_version 70751 (0.0009) -[2023-10-09 11:06:46,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 144506880. Throughput: 0: 1786.5, 1: 1787.0. Samples: 36132702. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:06:46,078][22500] Avg episode reward: [(0, '9.960'), (1, '9.630')] -[2023-10-09 11:06:47,913][23468] Updated weights for policy 0, policy_version 70373 (0.0010) -[2023-10-09 11:06:48,278][23468] Updated weights for policy 0, policy_version 70383 (0.0010) -[2023-10-09 11:06:48,668][23468] Updated weights for policy 0, policy_version 70393 (0.0010) -[2023-10-09 11:06:49,465][23469] Updated weights for policy 1, policy_version 70761 (0.0008) -[2023-10-09 11:06:49,847][23469] Updated weights for policy 1, policy_version 70771 (0.0008) -[2023-10-09 11:06:50,209][23469] Updated weights for policy 1, policy_version 70781 (0.0010) -[2023-10-09 11:06:51,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 144572416. Throughput: 0: 1802.9, 1: 1795.8. Samples: 36144674. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:06:51,078][22500] Avg episode reward: [(0, '10.350'), (1, '9.760')] -[2023-10-09 11:06:52,437][23468] Updated weights for policy 0, policy_version 70403 (0.0009) -[2023-10-09 11:06:52,812][23468] Updated weights for policy 0, policy_version 70413 (0.0007) -[2023-10-09 11:06:53,186][23468] Updated weights for policy 0, policy_version 70423 (0.0009) -[2023-10-09 11:06:53,882][23469] Updated weights for policy 1, policy_version 70791 (0.0008) -[2023-10-09 11:06:54,248][23469] Updated weights for policy 1, policy_version 70801 (0.0007) -[2023-10-09 11:06:54,623][23469] Updated weights for policy 1, policy_version 70811 (0.0007) -[2023-10-09 11:06:56,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 144637952. Throughput: 0: 1791.0, 1: 1787.0. Samples: 36165124. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:06:56,078][22500] Avg episode reward: [(0, '10.190'), (1, '9.620')] -[2023-10-09 11:06:56,874][23468] Updated weights for policy 0, policy_version 70433 (0.0010) -[2023-10-09 11:06:57,284][23468] Updated weights for policy 0, policy_version 70443 (0.0010) -[2023-10-09 11:06:57,651][23468] Updated weights for policy 0, policy_version 70453 (0.0010) -[2023-10-09 11:06:58,020][23468] Updated weights for policy 0, policy_version 70463 (0.0008) -[2023-10-09 11:06:58,354][23469] Updated weights for policy 1, policy_version 70821 (0.0008) -[2023-10-09 11:06:58,719][23469] Updated weights for policy 1, policy_version 70831 (0.0010) -[2023-10-09 11:06:59,087][23469] Updated weights for policy 1, policy_version 70841 (0.0010) -[2023-10-09 11:07:01,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 144703488. Throughput: 0: 1789.2, 1: 1789.5. Samples: 36187436. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:07:01,079][22500] Avg episode reward: [(0, '9.560'), (1, '8.950')] -[2023-10-09 11:07:01,801][23468] Updated weights for policy 0, policy_version 70473 (0.0009) -[2023-10-09 11:07:02,173][23468] Updated weights for policy 0, policy_version 70483 (0.0008) -[2023-10-09 11:07:02,548][23468] Updated weights for policy 0, policy_version 70493 (0.0009) -[2023-10-09 11:07:02,829][23469] Updated weights for policy 1, policy_version 70851 (0.0009) -[2023-10-09 11:07:03,195][23469] Updated weights for policy 1, policy_version 70861 (0.0008) -[2023-10-09 11:07:03,555][23469] Updated weights for policy 1, policy_version 70871 (0.0007) -[2023-10-09 11:07:06,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 144769024. Throughput: 0: 1787.9, 1: 1791.0. Samples: 36197326. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:07:06,079][22500] Avg episode reward: [(0, '10.630'), (1, '9.410')] -[2023-10-09 11:07:06,502][23468] Updated weights for policy 0, policy_version 70503 (0.0007) -[2023-10-09 11:07:06,873][23468] Updated weights for policy 0, policy_version 70513 (0.0007) -[2023-10-09 11:07:07,237][23468] Updated weights for policy 0, policy_version 70523 (0.0007) -[2023-10-09 11:07:07,237][23469] Updated weights for policy 1, policy_version 70881 (0.0010) -[2023-10-09 11:07:07,601][23469] Updated weights for policy 1, policy_version 70891 (0.0009) -[2023-10-09 11:07:07,969][23469] Updated weights for policy 1, policy_version 70901 (0.0008) -[2023-10-09 11:07:08,349][23469] Updated weights for policy 1, policy_version 70911 (0.0009) -[2023-10-09 11:07:11,029][23468] Updated weights for policy 0, policy_version 70533 (0.0009) -[2023-10-09 11:07:11,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 144834560. Throughput: 0: 1792.1, 1: 1790.2. Samples: 36219642. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:07:11,078][22500] Avg episode reward: [(0, '10.130'), (1, '9.610')] -[2023-10-09 11:07:11,402][23468] Updated weights for policy 0, policy_version 70543 (0.0008) -[2023-10-09 11:07:11,779][23468] Updated weights for policy 0, policy_version 70553 (0.0010) -[2023-10-09 11:07:12,050][23469] Updated weights for policy 1, policy_version 70921 (0.0009) -[2023-10-09 11:07:12,420][23469] Updated weights for policy 1, policy_version 70931 (0.0007) -[2023-10-09 11:07:12,791][23469] Updated weights for policy 1, policy_version 70941 (0.0008) -[2023-10-09 11:07:15,540][23468] Updated weights for policy 0, policy_version 70563 (0.0008) -[2023-10-09 11:07:15,908][23468] Updated weights for policy 0, policy_version 70573 (0.0007) -[2023-10-09 11:07:16,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 144900096. Throughput: 0: 1807.3, 1: 1791.7. Samples: 36242210. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:07:16,078][22500] Avg episode reward: [(0, '10.350'), (1, '9.110')] -[2023-10-09 11:07:16,280][23468] Updated weights for policy 0, policy_version 70583 (0.0008) -[2023-10-09 11:07:16,713][23469] Updated weights for policy 1, policy_version 70951 (0.0007) -[2023-10-09 11:07:17,083][23469] Updated weights for policy 1, policy_version 70961 (0.0007) -[2023-10-09 11:07:17,451][23469] Updated weights for policy 1, policy_version 70971 (0.0008) -[2023-10-09 11:07:20,018][23468] Updated weights for policy 0, policy_version 70593 (0.0007) -[2023-10-09 11:07:20,392][23468] Updated weights for policy 0, policy_version 70603 (0.0009) -[2023-10-09 11:07:20,758][23468] Updated weights for policy 0, policy_version 70613 (0.0008) -[2023-10-09 11:07:21,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 144965632. Throughput: 0: 1789.2, 1: 1795.0. Samples: 36251828. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:07:21,078][22500] Avg episode reward: [(0, '10.520'), (1, '9.470')] -[2023-10-09 11:07:21,102][23469] Updated weights for policy 1, policy_version 70981 (0.0009) -[2023-10-09 11:07:21,132][23468] Updated weights for policy 0, policy_version 70623 (0.0008) -[2023-10-09 11:07:21,480][23469] Updated weights for policy 1, policy_version 70991 (0.0007) -[2023-10-09 11:07:21,838][23469] Updated weights for policy 1, policy_version 71001 (0.0009) -[2023-10-09 11:07:24,837][23468] Updated weights for policy 0, policy_version 70633 (0.0007) -[2023-10-09 11:07:25,206][23468] Updated weights for policy 0, policy_version 70643 (0.0008) -[2023-10-09 11:07:25,580][23469] Updated weights for policy 1, policy_version 71011 (0.0010) -[2023-10-09 11:07:25,584][23468] Updated weights for policy 0, policy_version 70653 (0.0007) -[2023-10-09 11:07:25,950][23469] Updated weights for policy 1, policy_version 71021 (0.0011) -[2023-10-09 11:07:26,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 145063936. Throughput: 0: 1802.0, 1: 1803.2. Samples: 36274374. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:07:26,078][22500] Avg episode reward: [(0, '9.930'), (1, '9.470')] -[2023-10-09 11:07:26,311][23469] Updated weights for policy 1, policy_version 71031 (0.0009) -[2023-10-09 11:07:29,310][23468] Updated weights for policy 0, policy_version 70663 (0.0008) -[2023-10-09 11:07:29,681][23468] Updated weights for policy 0, policy_version 70673 (0.0008) -[2023-10-09 11:07:30,059][23469] Updated weights for policy 1, policy_version 71041 (0.0010) -[2023-10-09 11:07:30,063][23468] Updated weights for policy 0, policy_version 70683 (0.0008) -[2023-10-09 11:07:30,430][23469] Updated weights for policy 1, policy_version 71051 (0.0008) -[2023-10-09 11:07:30,808][23469] Updated weights for policy 1, policy_version 71061 (0.0007) -[2023-10-09 11:07:31,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 145129472. Throughput: 0: 1783.6, 1: 1812.0. Samples: 36294502. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:07:31,078][22500] Avg episode reward: [(0, '9.870'), (1, '9.450')] -[2023-10-09 11:07:31,177][23469] Updated weights for policy 1, policy_version 71071 (0.0007) -[2023-10-09 11:07:33,785][23468] Updated weights for policy 0, policy_version 70693 (0.0010) -[2023-10-09 11:07:34,159][23468] Updated weights for policy 0, policy_version 70703 (0.0011) -[2023-10-09 11:07:34,538][23468] Updated weights for policy 0, policy_version 70713 (0.0009) -[2023-10-09 11:07:34,932][23469] Updated weights for policy 1, policy_version 71081 (0.0007) -[2023-10-09 11:07:35,295][23469] Updated weights for policy 1, policy_version 71091 (0.0007) -[2023-10-09 11:07:35,670][23469] Updated weights for policy 1, policy_version 71101 (0.0010) -[2023-10-09 11:07:36,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 145227776. Throughput: 0: 1798.5, 1: 1800.5. Samples: 36306630. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:07:36,078][22500] Avg episode reward: [(0, '9.380'), (1, '9.620')] -[2023-10-09 11:07:38,364][23468] Updated weights for policy 0, policy_version 70723 (0.0009) -[2023-10-09 11:07:38,744][23468] Updated weights for policy 0, policy_version 70733 (0.0008) -[2023-10-09 11:07:39,114][23468] Updated weights for policy 0, policy_version 70743 (0.0010) -[2023-10-09 11:07:39,471][23469] Updated weights for policy 1, policy_version 71111 (0.0009) -[2023-10-09 11:07:39,852][23469] Updated weights for policy 1, policy_version 71121 (0.0011) -[2023-10-09 11:07:40,217][23469] Updated weights for policy 1, policy_version 71131 (0.0010) -[2023-10-09 11:07:41,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 145293312. Throughput: 0: 1783.9, 1: 1810.0. Samples: 36326852. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:07:41,078][22500] Avg episode reward: [(0, '9.730'), (1, '9.300')] -[2023-10-09 11:07:43,099][23468] Updated weights for policy 0, policy_version 70753 (0.0009) -[2023-10-09 11:07:43,507][23468] Updated weights for policy 0, policy_version 70763 (0.0009) -[2023-10-09 11:07:43,830][23469] Updated weights for policy 1, policy_version 71141 (0.0008) -[2023-10-09 11:07:43,881][23468] Updated weights for policy 0, policy_version 70773 (0.0009) -[2023-10-09 11:07:44,197][23469] Updated weights for policy 1, policy_version 71151 (0.0007) -[2023-10-09 11:07:44,246][23468] Updated weights for policy 0, policy_version 70783 (0.0009) -[2023-10-09 11:07:44,563][23469] Updated weights for policy 1, policy_version 71161 (0.0008) -[2023-10-09 11:07:46,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 145358848. Throughput: 0: 1770.2, 1: 1796.6. Samples: 36347942. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:07:46,079][22500] Avg episode reward: [(0, '9.210'), (1, '8.770')] -[2023-10-09 11:07:48,084][23468] Updated weights for policy 0, policy_version 70793 (0.0009) -[2023-10-09 11:07:48,271][23469] Updated weights for policy 1, policy_version 71171 (0.0007) -[2023-10-09 11:07:48,466][23468] Updated weights for policy 0, policy_version 70803 (0.0009) -[2023-10-09 11:07:48,638][23469] Updated weights for policy 1, policy_version 71181 (0.0007) -[2023-10-09 11:07:48,842][23468] Updated weights for policy 0, policy_version 70813 (0.0009) -[2023-10-09 11:07:49,003][23469] Updated weights for policy 1, policy_version 71191 (0.0007) -[2023-10-09 11:07:51,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 145424384. Throughput: 0: 1791.3, 1: 1808.9. Samples: 36359330. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:07:51,078][22500] Avg episode reward: [(0, '8.960'), (1, '8.700')] -[2023-10-09 11:07:52,542][23468] Updated weights for policy 0, policy_version 70823 (0.0009) -[2023-10-09 11:07:52,764][23469] Updated weights for policy 1, policy_version 71201 (0.0009) -[2023-10-09 11:07:52,915][23468] Updated weights for policy 0, policy_version 70833 (0.0009) -[2023-10-09 11:07:53,130][23469] Updated weights for policy 1, policy_version 71211 (0.0008) -[2023-10-09 11:07:53,288][23468] Updated weights for policy 0, policy_version 70843 (0.0008) -[2023-10-09 11:07:53,511][23469] Updated weights for policy 1, policy_version 71221 (0.0007) -[2023-10-09 11:07:53,883][23469] Updated weights for policy 1, policy_version 71231 (0.0008) -[2023-10-09 11:07:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 145489920. Throughput: 0: 1771.9, 1: 1795.4. Samples: 36380172. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:07:56,079][22500] Avg episode reward: [(0, '9.440'), (1, '8.450')] -[2023-10-09 11:07:57,219][23468] Updated weights for policy 0, policy_version 70853 (0.0008) -[2023-10-09 11:07:57,591][23468] Updated weights for policy 0, policy_version 70863 (0.0009) -[2023-10-09 11:07:57,603][23469] Updated weights for policy 1, policy_version 71241 (0.0007) -[2023-10-09 11:07:57,965][23468] Updated weights for policy 0, policy_version 70873 (0.0009) -[2023-10-09 11:07:57,975][23469] Updated weights for policy 1, policy_version 71251 (0.0009) -[2023-10-09 11:07:58,343][23469] Updated weights for policy 1, policy_version 71261 (0.0008) -[2023-10-09 11:08:01,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 145555456. Throughput: 0: 1763.7, 1: 1791.2. Samples: 36402180. Policy #0 lag: (min: 2.0, avg: 2.8, max: 21.0) -[2023-10-09 11:08:01,078][22500] Avg episode reward: [(0, '9.310'), (1, '9.050')] -[2023-10-09 11:08:01,752][23468] Updated weights for policy 0, policy_version 70883 (0.0008) -[2023-10-09 11:08:02,125][23468] Updated weights for policy 0, policy_version 70893 (0.0007) -[2023-10-09 11:08:02,360][23469] Updated weights for policy 1, policy_version 71271 (0.0009) -[2023-10-09 11:08:02,506][23468] Updated weights for policy 0, policy_version 70903 (0.0008) -[2023-10-09 11:08:02,745][23469] Updated weights for policy 1, policy_version 71281 (0.0008) -[2023-10-09 11:08:03,107][23469] Updated weights for policy 1, policy_version 71291 (0.0009) -[2023-10-09 11:08:06,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 145620992. Throughput: 0: 1761.1, 1: 1790.4. Samples: 36411644. Policy #0 lag: (min: 2.0, avg: 2.8, max: 21.0) -[2023-10-09 11:08:06,078][22500] Avg episode reward: [(0, '9.670'), (1, '9.510')] -[2023-10-09 11:08:06,318][23468] Updated weights for policy 0, policy_version 70913 (0.0009) -[2023-10-09 11:08:06,668][23469] Updated weights for policy 1, policy_version 71301 (0.0008) -[2023-10-09 11:08:06,703][23468] Updated weights for policy 0, policy_version 70923 (0.0008) -[2023-10-09 11:08:07,036][23469] Updated weights for policy 1, policy_version 71311 (0.0007) -[2023-10-09 11:08:07,081][23468] Updated weights for policy 0, policy_version 70933 (0.0007) -[2023-10-09 11:08:07,399][23469] Updated weights for policy 1, policy_version 71321 (0.0009) -[2023-10-09 11:08:07,444][23468] Updated weights for policy 0, policy_version 70943 (0.0008) -[2023-10-09 11:08:11,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 145686528. Throughput: 0: 1762.5, 1: 1787.5. Samples: 36434124. Policy #0 lag: (min: 2.0, avg: 2.8, max: 21.0) -[2023-10-09 11:08:11,078][22500] Avg episode reward: [(0, '9.720'), (1, '9.840')] -[2023-10-09 11:08:11,143][23468] Updated weights for policy 0, policy_version 70953 (0.0011) -[2023-10-09 11:08:11,174][23469] Updated weights for policy 1, policy_version 71331 (0.0007) -[2023-10-09 11:08:11,515][23468] Updated weights for policy 0, policy_version 70963 (0.0008) -[2023-10-09 11:08:11,539][23469] Updated weights for policy 1, policy_version 71341 (0.0008) -[2023-10-09 11:08:11,879][23468] Updated weights for policy 0, policy_version 70973 (0.0009) -[2023-10-09 11:08:11,915][23469] Updated weights for policy 1, policy_version 71351 (0.0008) -[2023-10-09 11:08:15,615][23468] Updated weights for policy 0, policy_version 70983 (0.0007) -[2023-10-09 11:08:15,861][23469] Updated weights for policy 1, policy_version 71361 (0.0009) -[2023-10-09 11:08:15,984][23468] Updated weights for policy 0, policy_version 70993 (0.0008) -[2023-10-09 11:08:16,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 145752064. Throughput: 0: 1794.8, 1: 1803.1. Samples: 36456406. Policy #0 lag: (min: 2.0, avg: 2.8, max: 21.0) -[2023-10-09 11:08:16,078][22500] Avg episode reward: [(0, '9.570'), (1, '10.300')] -[2023-10-09 11:08:16,230][23469] Updated weights for policy 1, policy_version 71371 (0.0008) -[2023-10-09 11:08:16,350][23468] Updated weights for policy 0, policy_version 71003 (0.0008) -[2023-10-09 11:08:16,532][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000071008_72712192.pth... -[2023-10-09 11:08:16,562][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000069312_70975488.pth -[2023-10-09 11:08:16,599][23469] Updated weights for policy 1, policy_version 71381 (0.0008) -[2023-10-09 11:08:16,972][23469] Updated weights for policy 1, policy_version 71391 (0.0009) -[2023-10-09 11:08:17,007][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000071392_73105408.pth... -[2023-10-09 11:08:17,046][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000069696_71368704.pth -[2023-10-09 11:08:17,051][23343] Saving new best policy, reward=10.300! -[2023-10-09 11:08:20,055][23468] Updated weights for policy 0, policy_version 71013 (0.0008) -[2023-10-09 11:08:20,428][23468] Updated weights for policy 0, policy_version 71023 (0.0008) -[2023-10-09 11:08:20,629][23469] Updated weights for policy 1, policy_version 71401 (0.0007) -[2023-10-09 11:08:20,795][23468] Updated weights for policy 0, policy_version 71033 (0.0007) -[2023-10-09 11:08:20,997][23469] Updated weights for policy 1, policy_version 71411 (0.0008) -[2023-10-09 11:08:21,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 145850368. Throughput: 0: 1762.4, 1: 1781.7. Samples: 36466118. Policy #0 lag: (min: 2.0, avg: 2.8, max: 21.0) -[2023-10-09 11:08:21,078][22500] Avg episode reward: [(0, '9.750'), (1, '9.820')] -[2023-10-09 11:08:21,357][23469] Updated weights for policy 1, policy_version 71421 (0.0007) -[2023-10-09 11:08:24,570][23468] Updated weights for policy 0, policy_version 71043 (0.0007) -[2023-10-09 11:08:24,947][23468] Updated weights for policy 0, policy_version 71053 (0.0008) -[2023-10-09 11:08:25,159][23469] Updated weights for policy 1, policy_version 71431 (0.0007) -[2023-10-09 11:08:25,325][23468] Updated weights for policy 0, policy_version 71063 (0.0009) -[2023-10-09 11:08:25,518][23469] Updated weights for policy 1, policy_version 71441 (0.0008) -[2023-10-09 11:08:25,889][23469] Updated weights for policy 1, policy_version 71451 (0.0011) -[2023-10-09 11:08:26,077][22500] Fps is (10 sec: 19660.5, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 145948672. Throughput: 0: 1794.4, 1: 1797.4. Samples: 36488482. Policy #0 lag: (min: 2.0, avg: 2.8, max: 21.0) -[2023-10-09 11:08:26,079][22500] Avg episode reward: [(0, '10.450'), (1, '9.870')] -[2023-10-09 11:08:29,016][23468] Updated weights for policy 0, policy_version 71073 (0.0009) -[2023-10-09 11:08:29,413][23468] Updated weights for policy 0, policy_version 71083 (0.0009) -[2023-10-09 11:08:29,683][23469] Updated weights for policy 1, policy_version 71461 (0.0008) -[2023-10-09 11:08:29,791][23468] Updated weights for policy 0, policy_version 71093 (0.0008) -[2023-10-09 11:08:30,053][23469] Updated weights for policy 1, policy_version 71471 (0.0007) -[2023-10-09 11:08:30,157][23468] Updated weights for policy 0, policy_version 71103 (0.0010) -[2023-10-09 11:08:30,415][23469] Updated weights for policy 1, policy_version 71481 (0.0009) -[2023-10-09 11:08:31,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 146014208. Throughput: 0: 1774.9, 1: 1780.6. Samples: 36507938. Policy #0 lag: (min: 2.0, avg: 2.8, max: 21.0) -[2023-10-09 11:08:31,078][22500] Avg episode reward: [(0, '11.060'), (1, '9.810')] -[2023-10-09 11:08:33,799][23468] Updated weights for policy 0, policy_version 71113 (0.0008) -[2023-10-09 11:08:34,063][23469] Updated weights for policy 1, policy_version 71491 (0.0009) -[2023-10-09 11:08:34,167][23468] Updated weights for policy 0, policy_version 71123 (0.0007) -[2023-10-09 11:08:34,422][23469] Updated weights for policy 1, policy_version 71501 (0.0008) -[2023-10-09 11:08:34,544][23468] Updated weights for policy 0, policy_version 71133 (0.0007) -[2023-10-09 11:08:34,795][23469] Updated weights for policy 1, policy_version 71511 (0.0010) -[2023-10-09 11:08:36,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 146079744. Throughput: 0: 1792.3, 1: 1797.2. Samples: 36520860. Policy #0 lag: (min: 2.0, avg: 2.8, max: 21.0) -[2023-10-09 11:08:36,079][22500] Avg episode reward: [(0, '10.770'), (1, '9.850')] -[2023-10-09 11:08:38,235][23468] Updated weights for policy 0, policy_version 71143 (0.0010) -[2023-10-09 11:08:38,614][23468] Updated weights for policy 0, policy_version 71153 (0.0010) -[2023-10-09 11:08:38,658][23469] Updated weights for policy 1, policy_version 71521 (0.0008) -[2023-10-09 11:08:38,977][23468] Updated weights for policy 0, policy_version 71163 (0.0008) -[2023-10-09 11:08:39,015][23469] Updated weights for policy 1, policy_version 71531 (0.0008) -[2023-10-09 11:08:39,388][23469] Updated weights for policy 1, policy_version 71541 (0.0008) -[2023-10-09 11:08:39,763][23469] Updated weights for policy 1, policy_version 71551 (0.0010) -[2023-10-09 11:08:41,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 146145280. Throughput: 0: 1778.2, 1: 1784.4. Samples: 36540492. Policy #0 lag: (min: 2.0, avg: 2.8, max: 21.0) -[2023-10-09 11:08:41,078][22500] Avg episode reward: [(0, '11.200'), (1, '9.610')] -[2023-10-09 11:08:42,907][23468] Updated weights for policy 0, policy_version 71173 (0.0008) -[2023-10-09 11:08:43,271][23468] Updated weights for policy 0, policy_version 71183 (0.0008) -[2023-10-09 11:08:43,512][23469] Updated weights for policy 1, policy_version 71561 (0.0007) -[2023-10-09 11:08:43,642][23468] Updated weights for policy 0, policy_version 71193 (0.0008) -[2023-10-09 11:08:43,884][23469] Updated weights for policy 1, policy_version 71571 (0.0008) -[2023-10-09 11:08:44,270][23469] Updated weights for policy 1, policy_version 71581 (0.0009) -[2023-10-09 11:08:46,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 146210816. Throughput: 0: 1785.8, 1: 1787.8. Samples: 36562992. Policy #0 lag: (min: 0.0, avg: 14.9, max: 32.0) -[2023-10-09 11:08:46,079][22500] Avg episode reward: [(0, '10.430'), (1, '8.990')] -[2023-10-09 11:08:47,394][23468] Updated weights for policy 0, policy_version 71203 (0.0009) -[2023-10-09 11:08:47,760][23468] Updated weights for policy 0, policy_version 71213 (0.0010) -[2023-10-09 11:08:48,100][23469] Updated weights for policy 1, policy_version 71591 (0.0007) -[2023-10-09 11:08:48,142][23468] Updated weights for policy 0, policy_version 71223 (0.0008) -[2023-10-09 11:08:48,476][23469] Updated weights for policy 1, policy_version 71601 (0.0009) -[2023-10-09 11:08:48,850][23469] Updated weights for policy 1, policy_version 71611 (0.0010) -[2023-10-09 11:08:51,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 146276352. Throughput: 0: 1793.7, 1: 1794.8. Samples: 36573128. Policy #0 lag: (min: 0.0, avg: 14.9, max: 32.0) -[2023-10-09 11:08:51,078][22500] Avg episode reward: [(0, '10.170'), (1, '9.300')] -[2023-10-09 11:08:51,987][23468] Updated weights for policy 0, policy_version 71233 (0.0008) -[2023-10-09 11:08:52,359][23468] Updated weights for policy 0, policy_version 71243 (0.0007) -[2023-10-09 11:08:52,529][23469] Updated weights for policy 1, policy_version 71621 (0.0010) -[2023-10-09 11:08:52,727][23468] Updated weights for policy 0, policy_version 71253 (0.0007) -[2023-10-09 11:08:52,892][23469] Updated weights for policy 1, policy_version 71631 (0.0007) -[2023-10-09 11:08:53,097][23468] Updated weights for policy 0, policy_version 71263 (0.0007) -[2023-10-09 11:08:53,261][23469] Updated weights for policy 1, policy_version 71641 (0.0008) -[2023-10-09 11:08:56,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 146341888. Throughput: 0: 1790.8, 1: 1782.0. Samples: 36594902. Policy #0 lag: (min: 0.0, avg: 14.9, max: 32.0) -[2023-10-09 11:08:56,078][22500] Avg episode reward: [(0, '10.650'), (1, '8.930')] -[2023-10-09 11:08:56,632][23468] Updated weights for policy 0, policy_version 71273 (0.0008) -[2023-10-09 11:08:56,949][23469] Updated weights for policy 1, policy_version 71651 (0.0008) -[2023-10-09 11:08:57,008][23468] Updated weights for policy 0, policy_version 71283 (0.0007) -[2023-10-09 11:08:57,316][23469] Updated weights for policy 1, policy_version 71661 (0.0007) -[2023-10-09 11:08:57,366][23468] Updated weights for policy 0, policy_version 71293 (0.0008) -[2023-10-09 11:08:57,690][23469] Updated weights for policy 1, policy_version 71671 (0.0009) -[2023-10-09 11:09:01,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 146407424. Throughput: 0: 1792.7, 1: 1787.7. Samples: 36617524. Policy #0 lag: (min: 0.0, avg: 14.9, max: 32.0) -[2023-10-09 11:09:01,078][22500] Avg episode reward: [(0, '10.060'), (1, '9.470')] -[2023-10-09 11:09:01,171][23468] Updated weights for policy 0, policy_version 71303 (0.0008) -[2023-10-09 11:09:01,399][23469] Updated weights for policy 1, policy_version 71681 (0.0010) -[2023-10-09 11:09:01,535][23468] Updated weights for policy 0, policy_version 71313 (0.0008) -[2023-10-09 11:09:01,756][23469] Updated weights for policy 1, policy_version 71691 (0.0007) -[2023-10-09 11:09:01,905][23468] Updated weights for policy 0, policy_version 71323 (0.0008) -[2023-10-09 11:09:02,131][23469] Updated weights for policy 1, policy_version 71701 (0.0007) -[2023-10-09 11:09:02,500][23469] Updated weights for policy 1, policy_version 71711 (0.0008) -[2023-10-09 11:09:05,566][23468] Updated weights for policy 0, policy_version 71333 (0.0008) -[2023-10-09 11:09:05,938][23468] Updated weights for policy 0, policy_version 71343 (0.0009) -[2023-10-09 11:09:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 146472960. Throughput: 0: 1795.2, 1: 1790.7. Samples: 36627484. Policy #0 lag: (min: 0.0, avg: 14.9, max: 32.0) -[2023-10-09 11:09:06,078][22500] Avg episode reward: [(0, '10.020'), (1, '9.200')] -[2023-10-09 11:09:06,319][23468] Updated weights for policy 0, policy_version 71353 (0.0010) -[2023-10-09 11:09:06,349][23469] Updated weights for policy 1, policy_version 71721 (0.0009) -[2023-10-09 11:09:06,728][23469] Updated weights for policy 1, policy_version 71731 (0.0008) -[2023-10-09 11:09:07,093][23469] Updated weights for policy 1, policy_version 71741 (0.0007) -[2023-10-09 11:09:10,215][23468] Updated weights for policy 0, policy_version 71363 (0.0009) -[2023-10-09 11:09:10,587][23468] Updated weights for policy 0, policy_version 71373 (0.0009) -[2023-10-09 11:09:10,832][23469] Updated weights for policy 1, policy_version 71751 (0.0008) -[2023-10-09 11:09:10,961][23468] Updated weights for policy 0, policy_version 71383 (0.0009) -[2023-10-09 11:09:11,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 146538496. Throughput: 0: 1794.2, 1: 1789.0. Samples: 36649726. Policy #0 lag: (min: 0.0, avg: 14.9, max: 32.0) -[2023-10-09 11:09:11,078][22500] Avg episode reward: [(0, '10.710'), (1, '9.330')] -[2023-10-09 11:09:11,204][23469] Updated weights for policy 1, policy_version 71761 (0.0009) -[2023-10-09 11:09:11,580][23469] Updated weights for policy 1, policy_version 71771 (0.0008) -[2023-10-09 11:09:14,756][23468] Updated weights for policy 0, policy_version 71393 (0.0009) -[2023-10-09 11:09:15,127][23468] Updated weights for policy 0, policy_version 71403 (0.0011) -[2023-10-09 11:09:15,440][23469] Updated weights for policy 1, policy_version 71781 (0.0009) -[2023-10-09 11:09:15,504][23468] Updated weights for policy 0, policy_version 71413 (0.0008) -[2023-10-09 11:09:15,808][23469] Updated weights for policy 1, policy_version 71791 (0.0007) -[2023-10-09 11:09:15,864][23468] Updated weights for policy 0, policy_version 71423 (0.0009) -[2023-10-09 11:09:16,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 146636800. Throughput: 0: 1811.6, 1: 1802.8. Samples: 36670588. Policy #0 lag: (min: 0.0, avg: 14.9, max: 32.0) -[2023-10-09 11:09:16,078][22500] Avg episode reward: [(0, '9.900'), (1, '9.750')] -[2023-10-09 11:09:16,188][23469] Updated weights for policy 1, policy_version 71801 (0.0008) -[2023-10-09 11:09:19,584][23468] Updated weights for policy 0, policy_version 71433 (0.0009) -[2023-10-09 11:09:19,911][23469] Updated weights for policy 1, policy_version 71811 (0.0008) -[2023-10-09 11:09:19,944][23468] Updated weights for policy 0, policy_version 71443 (0.0008) -[2023-10-09 11:09:20,268][23469] Updated weights for policy 1, policy_version 71821 (0.0008) -[2023-10-09 11:09:20,314][23468] Updated weights for policy 0, policy_version 71453 (0.0008) -[2023-10-09 11:09:20,639][23469] Updated weights for policy 1, policy_version 71831 (0.0010) -[2023-10-09 11:09:21,077][22500] Fps is (10 sec: 19661.1, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 146735104. Throughput: 0: 1795.6, 1: 1779.9. Samples: 36681756. Policy #0 lag: (min: 0.0, avg: 14.9, max: 32.0) -[2023-10-09 11:09:21,078][22500] Avg episode reward: [(0, '10.310'), (1, '9.830')] -[2023-10-09 11:09:23,993][23468] Updated weights for policy 0, policy_version 71463 (0.0010) -[2023-10-09 11:09:24,369][23468] Updated weights for policy 0, policy_version 71473 (0.0010) -[2023-10-09 11:09:24,421][23469] Updated weights for policy 1, policy_version 71841 (0.0009) -[2023-10-09 11:09:24,742][23468] Updated weights for policy 0, policy_version 71483 (0.0007) -[2023-10-09 11:09:24,786][23469] Updated weights for policy 1, policy_version 71851 (0.0009) -[2023-10-09 11:09:25,161][23469] Updated weights for policy 1, policy_version 71861 (0.0009) -[2023-10-09 11:09:25,522][23469] Updated weights for policy 1, policy_version 71871 (0.0008) -[2023-10-09 11:09:26,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 146800640. Throughput: 0: 1811.2, 1: 1798.9. Samples: 36702942. Policy #0 lag: (min: 0.0, avg: 14.9, max: 32.0) -[2023-10-09 11:09:26,078][22500] Avg episode reward: [(0, '9.910'), (1, '9.350')] -[2023-10-09 11:09:28,629][23468] Updated weights for policy 0, policy_version 71493 (0.0007) -[2023-10-09 11:09:28,996][23468] Updated weights for policy 0, policy_version 71503 (0.0009) -[2023-10-09 11:09:29,195][23469] Updated weights for policy 1, policy_version 71881 (0.0009) -[2023-10-09 11:09:29,374][23468] Updated weights for policy 0, policy_version 71513 (0.0007) -[2023-10-09 11:09:29,555][23469] Updated weights for policy 1, policy_version 71891 (0.0007) -[2023-10-09 11:09:29,926][23469] Updated weights for policy 1, policy_version 71901 (0.0007) -[2023-10-09 11:09:31,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 146866176. Throughput: 0: 1790.0, 1: 1780.0. Samples: 36723638. Policy #0 lag: (min: 31.0, avg: 31.3, max: 42.0) -[2023-10-09 11:09:31,078][22500] Avg episode reward: [(0, '9.930'), (1, '9.260')] -[2023-10-09 11:09:33,120][23468] Updated weights for policy 0, policy_version 71523 (0.0007) -[2023-10-09 11:09:33,493][23468] Updated weights for policy 0, policy_version 71533 (0.0007) -[2023-10-09 11:09:33,775][23469] Updated weights for policy 1, policy_version 71911 (0.0007) -[2023-10-09 11:09:33,862][23468] Updated weights for policy 0, policy_version 71543 (0.0008) -[2023-10-09 11:09:34,163][23469] Updated weights for policy 1, policy_version 71921 (0.0007) -[2023-10-09 11:09:34,523][23469] Updated weights for policy 1, policy_version 71931 (0.0010) -[2023-10-09 11:09:36,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 146931712. Throughput: 0: 1808.5, 1: 1801.3. Samples: 36735570. Policy #0 lag: (min: 31.0, avg: 31.3, max: 42.0) -[2023-10-09 11:09:36,078][22500] Avg episode reward: [(0, '9.610'), (1, '9.380')] -[2023-10-09 11:09:37,495][23468] Updated weights for policy 0, policy_version 71553 (0.0007) -[2023-10-09 11:09:37,870][23468] Updated weights for policy 0, policy_version 71563 (0.0008) -[2023-10-09 11:09:38,235][23468] Updated weights for policy 0, policy_version 71573 (0.0008) -[2023-10-09 11:09:38,282][23469] Updated weights for policy 1, policy_version 71941 (0.0010) -[2023-10-09 11:09:38,609][23468] Updated weights for policy 0, policy_version 71583 (0.0009) -[2023-10-09 11:09:38,652][23469] Updated weights for policy 1, policy_version 71951 (0.0007) -[2023-10-09 11:09:39,024][23469] Updated weights for policy 1, policy_version 71961 (0.0007) -[2023-10-09 11:09:41,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 146997248. Throughput: 0: 1789.1, 1: 1784.7. Samples: 36755722. Policy #0 lag: (min: 31.0, avg: 31.3, max: 42.0) -[2023-10-09 11:09:41,078][22500] Avg episode reward: [(0, '9.720'), (1, '8.920')] -[2023-10-09 11:09:42,510][23468] Updated weights for policy 0, policy_version 71593 (0.0008) -[2023-10-09 11:09:42,785][23469] Updated weights for policy 1, policy_version 71971 (0.0007) -[2023-10-09 11:09:42,872][23468] Updated weights for policy 0, policy_version 71603 (0.0009) -[2023-10-09 11:09:43,159][23469] Updated weights for policy 1, policy_version 71981 (0.0008) -[2023-10-09 11:09:43,239][23468] Updated weights for policy 0, policy_version 71613 (0.0009) -[2023-10-09 11:09:43,526][23469] Updated weights for policy 1, policy_version 71991 (0.0009) -[2023-10-09 11:09:46,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 147062784. Throughput: 0: 1786.1, 1: 1783.2. Samples: 36778144. Policy #0 lag: (min: 31.0, avg: 31.3, max: 42.0) -[2023-10-09 11:09:46,078][22500] Avg episode reward: [(0, '9.820'), (1, '8.930')] -[2023-10-09 11:09:47,075][23468] Updated weights for policy 0, policy_version 71623 (0.0007) -[2023-10-09 11:09:47,193][23469] Updated weights for policy 1, policy_version 72001 (0.0009) -[2023-10-09 11:09:47,443][23468] Updated weights for policy 0, policy_version 71633 (0.0009) -[2023-10-09 11:09:47,566][23469] Updated weights for policy 1, policy_version 72011 (0.0010) -[2023-10-09 11:09:47,810][23468] Updated weights for policy 0, policy_version 71643 (0.0007) -[2023-10-09 11:09:47,921][23469] Updated weights for policy 1, policy_version 72021 (0.0009) -[2023-10-09 11:09:48,295][23469] Updated weights for policy 1, policy_version 72031 (0.0007) -[2023-10-09 11:09:51,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 147128320. Throughput: 0: 1777.6, 1: 1786.3. Samples: 36787860. Policy #0 lag: (min: 31.0, avg: 31.3, max: 42.0) -[2023-10-09 11:09:51,079][22500] Avg episode reward: [(0, '10.030'), (1, '9.210')] -[2023-10-09 11:09:51,607][23468] Updated weights for policy 0, policy_version 71653 (0.0010) -[2023-10-09 11:09:51,957][23469] Updated weights for policy 1, policy_version 72041 (0.0009) -[2023-10-09 11:09:51,983][23468] Updated weights for policy 0, policy_version 71663 (0.0008) -[2023-10-09 11:09:52,325][23469] Updated weights for policy 1, policy_version 72051 (0.0010) -[2023-10-09 11:09:52,354][23468] Updated weights for policy 0, policy_version 71673 (0.0007) -[2023-10-09 11:09:52,697][23469] Updated weights for policy 1, policy_version 72061 (0.0009) -[2023-10-09 11:09:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 147193856. Throughput: 0: 1776.0, 1: 1791.4. Samples: 36810256. Policy #0 lag: (min: 31.0, avg: 31.3, max: 42.0) -[2023-10-09 11:09:56,078][22500] Avg episode reward: [(0, '9.760'), (1, '9.060')] -[2023-10-09 11:09:56,151][23468] Updated weights for policy 0, policy_version 71683 (0.0008) -[2023-10-09 11:09:56,523][23468] Updated weights for policy 0, policy_version 71693 (0.0007) -[2023-10-09 11:09:56,556][23469] Updated weights for policy 1, policy_version 72071 (0.0007) -[2023-10-09 11:09:56,903][23468] Updated weights for policy 0, policy_version 71703 (0.0007) -[2023-10-09 11:09:56,931][23469] Updated weights for policy 1, policy_version 72081 (0.0008) -[2023-10-09 11:09:57,301][23469] Updated weights for policy 1, policy_version 72091 (0.0008) -[2023-10-09 11:10:00,658][23468] Updated weights for policy 0, policy_version 71713 (0.0007) -[2023-10-09 11:10:01,003][23469] Updated weights for policy 1, policy_version 72101 (0.0009) -[2023-10-09 11:10:01,075][23468] Updated weights for policy 0, policy_version 71723 (0.0007) -[2023-10-09 11:10:01,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 147259392. Throughput: 0: 1792.2, 1: 1809.3. Samples: 36832656. Policy #0 lag: (min: 31.0, avg: 31.3, max: 42.0) -[2023-10-09 11:10:01,078][22500] Avg episode reward: [(0, '10.300'), (1, '9.110')] -[2023-10-09 11:10:01,367][23469] Updated weights for policy 1, policy_version 72111 (0.0009) -[2023-10-09 11:10:01,441][23468] Updated weights for policy 0, policy_version 71733 (0.0008) -[2023-10-09 11:10:01,748][23469] Updated weights for policy 1, policy_version 72121 (0.0008) -[2023-10-09 11:10:01,820][23468] Updated weights for policy 0, policy_version 71743 (0.0008) -[2023-10-09 11:10:05,582][23468] Updated weights for policy 0, policy_version 71753 (0.0009) -[2023-10-09 11:10:05,592][23469] Updated weights for policy 1, policy_version 72131 (0.0007) -[2023-10-09 11:10:05,953][23468] Updated weights for policy 0, policy_version 71763 (0.0008) -[2023-10-09 11:10:05,957][23469] Updated weights for policy 1, policy_version 72141 (0.0007) -[2023-10-09 11:10:06,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 147324928. Throughput: 0: 1767.5, 1: 1794.0. Samples: 36842026. Policy #0 lag: (min: 31.0, avg: 31.3, max: 42.0) -[2023-10-09 11:10:06,079][22500] Avg episode reward: [(0, '10.440'), (1, '8.390')] -[2023-10-09 11:10:06,328][23468] Updated weights for policy 0, policy_version 71773 (0.0007) -[2023-10-09 11:10:06,334][23469] Updated weights for policy 1, policy_version 72151 (0.0009) -[2023-10-09 11:10:10,127][23468] Updated weights for policy 0, policy_version 71783 (0.0007) -[2023-10-09 11:10:10,166][23469] Updated weights for policy 1, policy_version 72161 (0.0007) -[2023-10-09 11:10:10,504][23468] Updated weights for policy 0, policy_version 71793 (0.0010) -[2023-10-09 11:10:10,527][23469] Updated weights for policy 1, policy_version 72171 (0.0009) -[2023-10-09 11:10:10,866][23468] Updated weights for policy 0, policy_version 71803 (0.0008) -[2023-10-09 11:10:10,890][23469] Updated weights for policy 1, policy_version 72181 (0.0008) -[2023-10-09 11:10:11,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 147423232. Throughput: 0: 1784.3, 1: 1799.9. Samples: 36864230. Policy #0 lag: (min: 31.0, avg: 31.3, max: 42.0) -[2023-10-09 11:10:11,078][22500] Avg episode reward: [(0, '10.460'), (1, '7.870')] -[2023-10-09 11:10:11,261][23469] Updated weights for policy 1, policy_version 72191 (0.0009) -[2023-10-09 11:10:14,651][23468] Updated weights for policy 0, policy_version 71813 (0.0008) -[2023-10-09 11:10:15,018][23468] Updated weights for policy 0, policy_version 71823 (0.0008) -[2023-10-09 11:10:15,055][23469] Updated weights for policy 1, policy_version 72201 (0.0009) -[2023-10-09 11:10:15,398][23468] Updated weights for policy 0, policy_version 71833 (0.0008) -[2023-10-09 11:10:15,424][23469] Updated weights for policy 1, policy_version 72211 (0.0009) -[2023-10-09 11:10:15,791][23469] Updated weights for policy 1, policy_version 72221 (0.0008) -[2023-10-09 11:10:16,077][22500] Fps is (10 sec: 19661.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 147521536. Throughput: 0: 1782.7, 1: 1786.2. Samples: 36884236. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:10:16,078][22500] Avg episode reward: [(0, '10.450'), (1, '8.430')] -[2023-10-09 11:10:16,086][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000071840_73564160.pth... -[2023-10-09 11:10:16,086][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000072224_73957376.pth... -[2023-10-09 11:10:16,115][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000070176_71860224.pth -[2023-10-09 11:10:16,127][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000070528_72220672.pth -[2023-10-09 11:10:19,298][23468] Updated weights for policy 0, policy_version 71843 (0.0008) -[2023-10-09 11:10:19,674][23469] Updated weights for policy 1, policy_version 72231 (0.0008) -[2023-10-09 11:10:19,675][23468] Updated weights for policy 0, policy_version 71853 (0.0008) -[2023-10-09 11:10:20,041][23468] Updated weights for policy 0, policy_version 71863 (0.0008) -[2023-10-09 11:10:20,042][23469] Updated weights for policy 1, policy_version 72241 (0.0007) -[2023-10-09 11:10:20,415][23469] Updated weights for policy 1, policy_version 72251 (0.0008) -[2023-10-09 11:10:21,077][22500] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 147587072. Throughput: 0: 1781.5, 1: 1790.8. Samples: 36896322. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:10:21,078][22500] Avg episode reward: [(0, '9.670'), (1, '8.810')] -[2023-10-09 11:10:23,692][23468] Updated weights for policy 0, policy_version 71873 (0.0010) -[2023-10-09 11:10:24,067][23468] Updated weights for policy 0, policy_version 71883 (0.0008) -[2023-10-09 11:10:24,187][23469] Updated weights for policy 1, policy_version 72261 (0.0008) -[2023-10-09 11:10:24,442][23468] Updated weights for policy 0, policy_version 71893 (0.0009) -[2023-10-09 11:10:24,553][23469] Updated weights for policy 1, policy_version 72271 (0.0007) -[2023-10-09 11:10:24,809][23468] Updated weights for policy 0, policy_version 71903 (0.0009) -[2023-10-09 11:10:24,918][23469] Updated weights for policy 1, policy_version 72281 (0.0007) -[2023-10-09 11:10:26,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 147652608. Throughput: 0: 1782.3, 1: 1793.2. Samples: 36916620. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:10:26,078][22500] Avg episode reward: [(0, '9.230'), (1, '9.310')] -[2023-10-09 11:10:28,619][23468] Updated weights for policy 0, policy_version 71913 (0.0011) -[2023-10-09 11:10:28,696][23469] Updated weights for policy 1, policy_version 72291 (0.0008) -[2023-10-09 11:10:28,990][23468] Updated weights for policy 0, policy_version 71923 (0.0009) -[2023-10-09 11:10:29,067][23469] Updated weights for policy 1, policy_version 72301 (0.0008) -[2023-10-09 11:10:29,352][23468] Updated weights for policy 0, policy_version 71933 (0.0010) -[2023-10-09 11:10:29,441][23469] Updated weights for policy 1, policy_version 72311 (0.0008) -[2023-10-09 11:10:31,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 147718144. Throughput: 0: 1764.8, 1: 1776.3. Samples: 36937496. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:10:31,079][22500] Avg episode reward: [(0, '9.580'), (1, '10.120')] -[2023-10-09 11:10:33,136][23469] Updated weights for policy 1, policy_version 72321 (0.0007) -[2023-10-09 11:10:33,196][23468] Updated weights for policy 0, policy_version 71943 (0.0008) -[2023-10-09 11:10:33,508][23469] Updated weights for policy 1, policy_version 72331 (0.0008) -[2023-10-09 11:10:33,563][23468] Updated weights for policy 0, policy_version 71953 (0.0008) -[2023-10-09 11:10:33,873][23469] Updated weights for policy 1, policy_version 72341 (0.0007) -[2023-10-09 11:10:33,944][23468] Updated weights for policy 0, policy_version 71963 (0.0008) -[2023-10-09 11:10:34,236][23469] Updated weights for policy 1, policy_version 72351 (0.0009) -[2023-10-09 11:10:36,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 147783680. Throughput: 0: 1792.5, 1: 1789.4. Samples: 36949046. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:10:36,078][22500] Avg episode reward: [(0, '9.520'), (1, '10.120')] -[2023-10-09 11:10:37,571][23468] Updated weights for policy 0, policy_version 71973 (0.0008) -[2023-10-09 11:10:37,941][23468] Updated weights for policy 0, policy_version 71983 (0.0008) -[2023-10-09 11:10:38,033][23469] Updated weights for policy 1, policy_version 72361 (0.0007) -[2023-10-09 11:10:38,320][23468] Updated weights for policy 0, policy_version 71993 (0.0010) -[2023-10-09 11:10:38,401][23469] Updated weights for policy 1, policy_version 72371 (0.0010) -[2023-10-09 11:10:38,773][23469] Updated weights for policy 1, policy_version 72381 (0.0009) -[2023-10-09 11:10:41,077][22500] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 147849216. Throughput: 0: 1775.6, 1: 1772.0. Samples: 36969900. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:10:41,078][22500] Avg episode reward: [(0, '10.020'), (1, '10.000')] -[2023-10-09 11:10:42,251][23468] Updated weights for policy 0, policy_version 72003 (0.0007) -[2023-10-09 11:10:42,505][23469] Updated weights for policy 1, policy_version 72391 (0.0007) -[2023-10-09 11:10:42,620][23468] Updated weights for policy 0, policy_version 72013 (0.0007) -[2023-10-09 11:10:42,873][23469] Updated weights for policy 1, policy_version 72401 (0.0007) -[2023-10-09 11:10:42,985][23468] Updated weights for policy 0, policy_version 72023 (0.0007) -[2023-10-09 11:10:43,254][23469] Updated weights for policy 1, policy_version 72411 (0.0008) -[2023-10-09 11:10:46,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 147914752. Throughput: 0: 1774.6, 1: 1768.3. Samples: 36992086. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:10:46,078][22500] Avg episode reward: [(0, '10.150'), (1, '9.240')] -[2023-10-09 11:10:46,749][23468] Updated weights for policy 0, policy_version 72033 (0.0008) -[2023-10-09 11:10:47,081][23469] Updated weights for policy 1, policy_version 72421 (0.0010) -[2023-10-09 11:10:47,157][23468] Updated weights for policy 0, policy_version 72043 (0.0008) -[2023-10-09 11:10:47,453][23469] Updated weights for policy 1, policy_version 72431 (0.0008) -[2023-10-09 11:10:47,525][23468] Updated weights for policy 0, policy_version 72053 (0.0008) -[2023-10-09 11:10:47,831][23469] Updated weights for policy 1, policy_version 72441 (0.0007) -[2023-10-09 11:10:47,896][23468] Updated weights for policy 0, policy_version 72063 (0.0010) -[2023-10-09 11:10:51,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 147980288. Throughput: 0: 1773.4, 1: 1770.8. Samples: 37001514. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:10:51,078][22500] Avg episode reward: [(0, '9.610'), (1, '8.660')] -[2023-10-09 11:10:51,514][23468] Updated weights for policy 0, policy_version 72073 (0.0008) -[2023-10-09 11:10:51,660][23469] Updated weights for policy 1, policy_version 72451 (0.0008) -[2023-10-09 11:10:51,885][23468] Updated weights for policy 0, policy_version 72083 (0.0009) -[2023-10-09 11:10:52,027][23469] Updated weights for policy 1, policy_version 72461 (0.0010) -[2023-10-09 11:10:52,266][23468] Updated weights for policy 0, policy_version 72093 (0.0008) -[2023-10-09 11:10:52,408][23469] Updated weights for policy 1, policy_version 72471 (0.0008) -[2023-10-09 11:10:56,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 148045824. Throughput: 0: 1776.2, 1: 1770.8. Samples: 37023844. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:10:56,078][22500] Avg episode reward: [(0, '10.540'), (1, '8.920')] -[2023-10-09 11:10:56,095][23469] Updated weights for policy 1, policy_version 72481 (0.0008) -[2023-10-09 11:10:56,194][23468] Updated weights for policy 0, policy_version 72103 (0.0008) -[2023-10-09 11:10:56,463][23469] Updated weights for policy 1, policy_version 72491 (0.0008) -[2023-10-09 11:10:56,572][23468] Updated weights for policy 0, policy_version 72113 (0.0009) -[2023-10-09 11:10:56,832][23469] Updated weights for policy 1, policy_version 72501 (0.0008) -[2023-10-09 11:10:56,947][23468] Updated weights for policy 0, policy_version 72123 (0.0009) -[2023-10-09 11:10:57,194][23469] Updated weights for policy 1, policy_version 72511 (0.0008) -[2023-10-09 11:11:00,641][23468] Updated weights for policy 0, policy_version 72133 (0.0009) -[2023-10-09 11:11:00,996][23469] Updated weights for policy 1, policy_version 72521 (0.0008) -[2023-10-09 11:11:01,013][23468] Updated weights for policy 0, policy_version 72143 (0.0010) -[2023-10-09 11:11:01,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 148111360. Throughput: 0: 1794.8, 1: 1801.6. Samples: 37046072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:11:01,078][22500] Avg episode reward: [(0, '10.860'), (1, '8.630')] -[2023-10-09 11:11:01,365][23469] Updated weights for policy 1, policy_version 72531 (0.0009) -[2023-10-09 11:11:01,386][23468] Updated weights for policy 0, policy_version 72153 (0.0008) -[2023-10-09 11:11:01,726][23469] Updated weights for policy 1, policy_version 72541 (0.0008) -[2023-10-09 11:11:05,059][23468] Updated weights for policy 0, policy_version 72163 (0.0008) -[2023-10-09 11:11:05,433][23468] Updated weights for policy 0, policy_version 72173 (0.0008) -[2023-10-09 11:11:05,565][23469] Updated weights for policy 1, policy_version 72551 (0.0010) -[2023-10-09 11:11:05,800][23468] Updated weights for policy 0, policy_version 72183 (0.0009) -[2023-10-09 11:11:05,947][23469] Updated weights for policy 1, policy_version 72561 (0.0007) -[2023-10-09 11:11:06,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 148176896. Throughput: 0: 1773.7, 1: 1779.7. Samples: 37056224. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:11:06,078][22500] Avg episode reward: [(0, '10.520'), (1, '8.770')] -[2023-10-09 11:11:06,314][23469] Updated weights for policy 1, policy_version 72571 (0.0009) -[2023-10-09 11:11:09,364][23468] Updated weights for policy 0, policy_version 72193 (0.0009) -[2023-10-09 11:11:09,726][23468] Updated weights for policy 0, policy_version 72203 (0.0008) -[2023-10-09 11:11:10,107][23468] Updated weights for policy 0, policy_version 72213 (0.0008) -[2023-10-09 11:11:10,125][23469] Updated weights for policy 1, policy_version 72581 (0.0009) -[2023-10-09 11:11:10,464][23468] Updated weights for policy 0, policy_version 72223 (0.0008) -[2023-10-09 11:11:10,484][23469] Updated weights for policy 1, policy_version 72591 (0.0007) -[2023-10-09 11:11:10,851][23469] Updated weights for policy 1, policy_version 72601 (0.0009) -[2023-10-09 11:11:11,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 148275200. Throughput: 0: 1803.8, 1: 1796.4. Samples: 37078628. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:11:11,078][22500] Avg episode reward: [(0, '11.080'), (1, '9.650')] -[2023-10-09 11:11:14,137][23468] Updated weights for policy 0, policy_version 72233 (0.0008) -[2023-10-09 11:11:14,503][23468] Updated weights for policy 0, policy_version 72243 (0.0007) -[2023-10-09 11:11:14,620][23469] Updated weights for policy 1, policy_version 72611 (0.0008) -[2023-10-09 11:11:14,884][23468] Updated weights for policy 0, policy_version 72253 (0.0008) -[2023-10-09 11:11:14,984][23469] Updated weights for policy 1, policy_version 72621 (0.0007) -[2023-10-09 11:11:15,358][23469] Updated weights for policy 1, policy_version 72631 (0.0008) -[2023-10-09 11:11:16,077][22500] Fps is (10 sec: 19661.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 148373504. Throughput: 0: 1789.9, 1: 1775.3. Samples: 37097930. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:11:16,078][22500] Avg episode reward: [(0, '10.610'), (1, '9.060')] -[2023-10-09 11:11:18,551][23468] Updated weights for policy 0, policy_version 72263 (0.0007) -[2023-10-09 11:11:18,931][23468] Updated weights for policy 0, policy_version 72273 (0.0009) -[2023-10-09 11:11:18,970][23469] Updated weights for policy 1, policy_version 72641 (0.0009) -[2023-10-09 11:11:19,296][23468] Updated weights for policy 0, policy_version 72283 (0.0007) -[2023-10-09 11:11:19,348][23469] Updated weights for policy 1, policy_version 72651 (0.0009) -[2023-10-09 11:11:19,714][23469] Updated weights for policy 1, policy_version 72661 (0.0008) -[2023-10-09 11:11:20,079][23469] Updated weights for policy 1, policy_version 72671 (0.0008) -[2023-10-09 11:11:21,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 148439040. Throughput: 0: 1799.5, 1: 1796.3. Samples: 37110854. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:11:21,078][22500] Avg episode reward: [(0, '9.450'), (1, '9.120')] -[2023-10-09 11:11:23,274][23468] Updated weights for policy 0, policy_version 72293 (0.0008) -[2023-10-09 11:11:23,645][23468] Updated weights for policy 0, policy_version 72303 (0.0007) -[2023-10-09 11:11:23,932][23469] Updated weights for policy 1, policy_version 72681 (0.0007) -[2023-10-09 11:11:24,018][23468] Updated weights for policy 0, policy_version 72313 (0.0008) -[2023-10-09 11:11:24,309][23469] Updated weights for policy 1, policy_version 72691 (0.0007) -[2023-10-09 11:11:24,678][23469] Updated weights for policy 1, policy_version 72701 (0.0008) -[2023-10-09 11:11:26,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 148504576. Throughput: 0: 1784.5, 1: 1778.4. Samples: 37130228. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:11:26,078][22500] Avg episode reward: [(0, '9.650'), (1, '8.220')] -[2023-10-09 11:11:27,850][23468] Updated weights for policy 0, policy_version 72323 (0.0008) -[2023-10-09 11:11:28,217][23468] Updated weights for policy 0, policy_version 72333 (0.0009) -[2023-10-09 11:11:28,553][23469] Updated weights for policy 1, policy_version 72711 (0.0007) -[2023-10-09 11:11:28,590][23468] Updated weights for policy 0, policy_version 72343 (0.0008) -[2023-10-09 11:11:28,928][23469] Updated weights for policy 1, policy_version 72721 (0.0008) -[2023-10-09 11:11:29,297][23469] Updated weights for policy 1, policy_version 72731 (0.0009) -[2023-10-09 11:11:31,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 148570112. Throughput: 0: 1784.4, 1: 1783.2. Samples: 37152630. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:11:31,079][22500] Avg episode reward: [(0, '8.840'), (1, '8.670')] -[2023-10-09 11:11:32,383][23468] Updated weights for policy 0, policy_version 72353 (0.0008) -[2023-10-09 11:11:32,806][23468] Updated weights for policy 0, policy_version 72363 (0.0007) -[2023-10-09 11:11:33,029][23469] Updated weights for policy 1, policy_version 72741 (0.0007) -[2023-10-09 11:11:33,186][23468] Updated weights for policy 0, policy_version 72373 (0.0008) -[2023-10-09 11:11:33,394][23469] Updated weights for policy 1, policy_version 72751 (0.0008) -[2023-10-09 11:11:33,562][23468] Updated weights for policy 0, policy_version 72383 (0.0008) -[2023-10-09 11:11:33,763][23469] Updated weights for policy 1, policy_version 72761 (0.0009) -[2023-10-09 11:11:36,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 148635648. Throughput: 0: 1792.3, 1: 1791.6. Samples: 37162786. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:11:36,078][22500] Avg episode reward: [(0, '9.500'), (1, '9.780')] -[2023-10-09 11:11:37,288][23468] Updated weights for policy 0, policy_version 72393 (0.0010) -[2023-10-09 11:11:37,519][23469] Updated weights for policy 1, policy_version 72771 (0.0011) -[2023-10-09 11:11:37,662][23468] Updated weights for policy 0, policy_version 72403 (0.0008) -[2023-10-09 11:11:37,885][23469] Updated weights for policy 1, policy_version 72781 (0.0010) -[2023-10-09 11:11:38,030][23468] Updated weights for policy 0, policy_version 72413 (0.0009) -[2023-10-09 11:11:38,262][23469] Updated weights for policy 1, policy_version 72791 (0.0008) -[2023-10-09 11:11:41,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 148701184. Throughput: 0: 1780.4, 1: 1785.8. Samples: 37184320. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:11:41,078][22500] Avg episode reward: [(0, '9.360'), (1, '9.730')] -[2023-10-09 11:11:41,918][23468] Updated weights for policy 0, policy_version 72423 (0.0007) -[2023-10-09 11:11:42,122][23469] Updated weights for policy 1, policy_version 72801 (0.0009) -[2023-10-09 11:11:42,279][23468] Updated weights for policy 0, policy_version 72433 (0.0007) -[2023-10-09 11:11:42,485][23469] Updated weights for policy 1, policy_version 72811 (0.0007) -[2023-10-09 11:11:42,654][23468] Updated weights for policy 0, policy_version 72443 (0.0007) -[2023-10-09 11:11:42,855][23469] Updated weights for policy 1, policy_version 72821 (0.0007) -[2023-10-09 11:11:43,225][23469] Updated weights for policy 1, policy_version 72831 (0.0007) -[2023-10-09 11:11:46,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 148766720. Throughput: 0: 1783.6, 1: 1781.0. Samples: 37206480. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:11:46,079][22500] Avg episode reward: [(0, '9.680'), (1, '8.950')] -[2023-10-09 11:11:46,431][23468] Updated weights for policy 0, policy_version 72453 (0.0009) -[2023-10-09 11:11:46,787][23468] Updated weights for policy 0, policy_version 72463 (0.0008) -[2023-10-09 11:11:46,985][23469] Updated weights for policy 1, policy_version 72841 (0.0007) -[2023-10-09 11:11:47,164][23468] Updated weights for policy 0, policy_version 72473 (0.0008) -[2023-10-09 11:11:47,359][23469] Updated weights for policy 1, policy_version 72851 (0.0008) -[2023-10-09 11:11:47,733][23469] Updated weights for policy 1, policy_version 72861 (0.0009) -[2023-10-09 11:11:50,891][23468] Updated weights for policy 0, policy_version 72483 (0.0007) -[2023-10-09 11:11:51,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 148832256. Throughput: 0: 1782.0, 1: 1772.9. Samples: 37216196. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:11:51,078][22500] Avg episode reward: [(0, '9.380'), (1, '9.030')] -[2023-10-09 11:11:51,272][23468] Updated weights for policy 0, policy_version 72493 (0.0007) -[2023-10-09 11:11:51,389][23469] Updated weights for policy 1, policy_version 72871 (0.0009) -[2023-10-09 11:11:51,641][23468] Updated weights for policy 0, policy_version 72503 (0.0007) -[2023-10-09 11:11:51,750][23469] Updated weights for policy 1, policy_version 72881 (0.0009) -[2023-10-09 11:11:52,116][23469] Updated weights for policy 1, policy_version 72891 (0.0009) -[2023-10-09 11:11:55,342][23468] Updated weights for policy 0, policy_version 72513 (0.0007) -[2023-10-09 11:11:55,714][23468] Updated weights for policy 0, policy_version 72523 (0.0008) -[2023-10-09 11:11:55,996][23469] Updated weights for policy 1, policy_version 72901 (0.0007) -[2023-10-09 11:11:56,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 148897792. Throughput: 0: 1776.9, 1: 1778.6. Samples: 37238624. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:11:56,078][22500] Avg episode reward: [(0, '8.780'), (1, '8.760')] -[2023-10-09 11:11:56,087][23468] Updated weights for policy 0, policy_version 72533 (0.0007) -[2023-10-09 11:11:56,358][23469] Updated weights for policy 1, policy_version 72911 (0.0007) -[2023-10-09 11:11:56,457][23468] Updated weights for policy 0, policy_version 72543 (0.0008) -[2023-10-09 11:11:56,729][23469] Updated weights for policy 1, policy_version 72921 (0.0007) -[2023-10-09 11:12:00,365][23468] Updated weights for policy 0, policy_version 72553 (0.0009) -[2023-10-09 11:12:00,473][23469] Updated weights for policy 1, policy_version 72931 (0.0007) -[2023-10-09 11:12:00,740][23468] Updated weights for policy 0, policy_version 72563 (0.0007) -[2023-10-09 11:12:00,841][23469] Updated weights for policy 1, policy_version 72941 (0.0007) -[2023-10-09 11:12:01,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 148963328. Throughput: 0: 1799.4, 1: 1800.5. Samples: 37259926. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:12:01,078][22500] Avg episode reward: [(0, '9.580'), (1, '8.850')] -[2023-10-09 11:12:01,117][23468] Updated weights for policy 0, policy_version 72573 (0.0008) -[2023-10-09 11:12:01,215][23469] Updated weights for policy 1, policy_version 72951 (0.0007) -[2023-10-09 11:12:04,867][23468] Updated weights for policy 0, policy_version 72583 (0.0010) -[2023-10-09 11:12:05,114][23469] Updated weights for policy 1, policy_version 72961 (0.0008) -[2023-10-09 11:12:05,237][23468] Updated weights for policy 0, policy_version 72593 (0.0007) -[2023-10-09 11:12:05,472][23469] Updated weights for policy 1, policy_version 72971 (0.0009) -[2023-10-09 11:12:05,610][23468] Updated weights for policy 0, policy_version 72603 (0.0007) -[2023-10-09 11:12:05,845][23469] Updated weights for policy 1, policy_version 72981 (0.0008) -[2023-10-09 11:12:06,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 149061632. Throughput: 0: 1775.3, 1: 1774.6. Samples: 37270598. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:12:06,078][22500] Avg episode reward: [(0, '9.560'), (1, '9.000')] -[2023-10-09 11:12:06,219][23469] Updated weights for policy 1, policy_version 72991 (0.0008) -[2023-10-09 11:12:09,252][23468] Updated weights for policy 0, policy_version 72613 (0.0010) -[2023-10-09 11:12:09,617][23468] Updated weights for policy 0, policy_version 72623 (0.0009) -[2023-10-09 11:12:09,893][23469] Updated weights for policy 1, policy_version 73001 (0.0010) -[2023-10-09 11:12:09,989][23468] Updated weights for policy 0, policy_version 72633 (0.0009) -[2023-10-09 11:12:10,271][23469] Updated weights for policy 1, policy_version 73011 (0.0009) -[2023-10-09 11:12:10,632][23469] Updated weights for policy 1, policy_version 73021 (0.0009) -[2023-10-09 11:12:11,078][22500] Fps is (10 sec: 19660.5, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 149159936. Throughput: 0: 1805.9, 1: 1802.6. Samples: 37292614. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:12:11,079][22500] Avg episode reward: [(0, '9.550'), (1, '9.150')] -[2023-10-09 11:12:13,737][23468] Updated weights for policy 0, policy_version 72643 (0.0009) -[2023-10-09 11:12:14,115][23468] Updated weights for policy 0, policy_version 72653 (0.0010) -[2023-10-09 11:12:14,389][23469] Updated weights for policy 1, policy_version 73031 (0.0007) -[2023-10-09 11:12:14,485][23468] Updated weights for policy 0, policy_version 72663 (0.0008) -[2023-10-09 11:12:14,754][23469] Updated weights for policy 1, policy_version 73041 (0.0008) -[2023-10-09 11:12:15,115][23469] Updated weights for policy 1, policy_version 73051 (0.0008) -[2023-10-09 11:12:16,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 149225472. Throughput: 0: 1778.8, 1: 1773.3. Samples: 37312474. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:12:16,078][22500] Avg episode reward: [(0, '10.190'), (1, '9.640')] -[2023-10-09 11:12:16,086][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000073056_74809344.pth... -[2023-10-09 11:12:16,086][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000072672_74416128.pth... -[2023-10-09 11:12:16,122][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000071008_72712192.pth -[2023-10-09 11:12:16,125][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000071392_73105408.pth -[2023-10-09 11:12:18,366][23468] Updated weights for policy 0, policy_version 72673 (0.0008) -[2023-10-09 11:12:18,696][23469] Updated weights for policy 1, policy_version 73061 (0.0008) -[2023-10-09 11:12:18,773][23468] Updated weights for policy 0, policy_version 72683 (0.0008) -[2023-10-09 11:12:19,063][23469] Updated weights for policy 1, policy_version 73071 (0.0008) -[2023-10-09 11:12:19,140][23468] Updated weights for policy 0, policy_version 72693 (0.0008) -[2023-10-09 11:12:19,428][23469] Updated weights for policy 1, policy_version 73081 (0.0009) -[2023-10-09 11:12:19,513][23468] Updated weights for policy 0, policy_version 72703 (0.0008) -[2023-10-09 11:12:21,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 149291008. Throughput: 0: 1807.1, 1: 1794.2. Samples: 37324844. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:12:21,078][22500] Avg episode reward: [(0, '9.250'), (1, '9.920')] -[2023-10-09 11:12:23,301][23469] Updated weights for policy 1, policy_version 73091 (0.0009) -[2023-10-09 11:12:23,358][23468] Updated weights for policy 0, policy_version 72713 (0.0008) -[2023-10-09 11:12:23,676][23469] Updated weights for policy 1, policy_version 73101 (0.0007) -[2023-10-09 11:12:23,729][23468] Updated weights for policy 0, policy_version 72723 (0.0009) -[2023-10-09 11:12:24,050][23469] Updated weights for policy 1, policy_version 73111 (0.0008) -[2023-10-09 11:12:24,113][23468] Updated weights for policy 0, policy_version 72733 (0.0009) -[2023-10-09 11:12:26,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 149356544. Throughput: 0: 1776.8, 1: 1776.5. Samples: 37344220. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:12:26,078][22500] Avg episode reward: [(0, '9.890'), (1, '9.710')] -[2023-10-09 11:12:27,857][23469] Updated weights for policy 1, policy_version 73121 (0.0009) -[2023-10-09 11:12:27,914][23468] Updated weights for policy 0, policy_version 72743 (0.0008) -[2023-10-09 11:12:28,222][23469] Updated weights for policy 1, policy_version 73131 (0.0009) -[2023-10-09 11:12:28,289][23468] Updated weights for policy 0, policy_version 72753 (0.0007) -[2023-10-09 11:12:28,598][23469] Updated weights for policy 1, policy_version 73141 (0.0007) -[2023-10-09 11:12:28,653][23468] Updated weights for policy 0, policy_version 72763 (0.0009) -[2023-10-09 11:12:28,959][23469] Updated weights for policy 1, policy_version 73151 (0.0008) -[2023-10-09 11:12:31,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 149422080. Throughput: 0: 1773.8, 1: 1782.2. Samples: 37366500. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:12:31,078][22500] Avg episode reward: [(0, '10.200'), (1, '10.200')] -[2023-10-09 11:12:32,445][23468] Updated weights for policy 0, policy_version 72773 (0.0009) -[2023-10-09 11:12:32,813][23468] Updated weights for policy 0, policy_version 72783 (0.0008) -[2023-10-09 11:12:32,818][23469] Updated weights for policy 1, policy_version 73161 (0.0009) -[2023-10-09 11:12:33,182][23469] Updated weights for policy 1, policy_version 73171 (0.0008) -[2023-10-09 11:12:33,189][23468] Updated weights for policy 0, policy_version 72793 (0.0007) -[2023-10-09 11:12:33,556][23469] Updated weights for policy 1, policy_version 73181 (0.0008) -[2023-10-09 11:12:36,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 149487616. Throughput: 0: 1774.7, 1: 1781.1. Samples: 37376204. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:12:36,078][22500] Avg episode reward: [(0, '10.010'), (1, '9.930')] -[2023-10-09 11:12:36,970][23468] Updated weights for policy 0, policy_version 72803 (0.0007) -[2023-10-09 11:12:37,275][23469] Updated weights for policy 1, policy_version 73191 (0.0008) -[2023-10-09 11:12:37,349][23468] Updated weights for policy 0, policy_version 72813 (0.0008) -[2023-10-09 11:12:37,644][23469] Updated weights for policy 1, policy_version 73201 (0.0007) -[2023-10-09 11:12:37,725][23468] Updated weights for policy 0, policy_version 72823 (0.0008) -[2023-10-09 11:12:38,011][23469] Updated weights for policy 1, policy_version 73211 (0.0007) -[2023-10-09 11:12:41,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 149553152. Throughput: 0: 1763.6, 1: 1778.0. Samples: 37398000. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:12:41,079][22500] Avg episode reward: [(0, '9.750'), (1, '10.260')] -[2023-10-09 11:12:41,654][23468] Updated weights for policy 0, policy_version 72833 (0.0008) -[2023-10-09 11:12:41,733][23469] Updated weights for policy 1, policy_version 73221 (0.0007) -[2023-10-09 11:12:42,017][23468] Updated weights for policy 0, policy_version 72843 (0.0008) -[2023-10-09 11:12:42,105][23469] Updated weights for policy 1, policy_version 73231 (0.0009) -[2023-10-09 11:12:42,393][23468] Updated weights for policy 0, policy_version 72853 (0.0007) -[2023-10-09 11:12:42,474][23469] Updated weights for policy 1, policy_version 73241 (0.0008) -[2023-10-09 11:12:42,763][23468] Updated weights for policy 0, policy_version 72863 (0.0007) -[2023-10-09 11:12:46,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 149618688. Throughput: 0: 1774.3, 1: 1788.8. Samples: 37420266. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:12:46,078][22500] Avg episode reward: [(0, '9.880'), (1, '9.330')] -[2023-10-09 11:12:46,191][23469] Updated weights for policy 1, policy_version 73251 (0.0008) -[2023-10-09 11:12:46,397][23468] Updated weights for policy 0, policy_version 72873 (0.0008) -[2023-10-09 11:12:46,556][23469] Updated weights for policy 1, policy_version 73261 (0.0008) -[2023-10-09 11:12:46,766][23468] Updated weights for policy 0, policy_version 72883 (0.0008) -[2023-10-09 11:12:46,923][23469] Updated weights for policy 1, policy_version 73271 (0.0008) -[2023-10-09 11:12:47,137][23468] Updated weights for policy 0, policy_version 72893 (0.0007) -[2023-10-09 11:12:50,956][23469] Updated weights for policy 1, policy_version 73281 (0.0008) -[2023-10-09 11:12:51,034][23468] Updated weights for policy 0, policy_version 72903 (0.0007) -[2023-10-09 11:12:51,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 149684224. Throughput: 0: 1765.0, 1: 1775.5. Samples: 37429918. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:12:51,078][22500] Avg episode reward: [(0, '9.550'), (1, '8.890')] -[2023-10-09 11:12:51,324][23469] Updated weights for policy 1, policy_version 73291 (0.0009) -[2023-10-09 11:12:51,404][23468] Updated weights for policy 0, policy_version 72913 (0.0009) -[2023-10-09 11:12:51,686][23469] Updated weights for policy 1, policy_version 73301 (0.0008) -[2023-10-09 11:12:51,771][23468] Updated weights for policy 0, policy_version 72923 (0.0009) -[2023-10-09 11:12:52,053][23469] Updated weights for policy 1, policy_version 73311 (0.0009) -[2023-10-09 11:12:55,406][23468] Updated weights for policy 0, policy_version 72933 (0.0009) -[2023-10-09 11:12:55,747][23469] Updated weights for policy 1, policy_version 73321 (0.0010) -[2023-10-09 11:12:55,770][23468] Updated weights for policy 0, policy_version 72943 (0.0008) -[2023-10-09 11:12:56,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 149749760. Throughput: 0: 1767.2, 1: 1779.5. Samples: 37452212. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:12:56,078][22500] Avg episode reward: [(0, '10.230'), (1, '9.550')] -[2023-10-09 11:12:56,114][23469] Updated weights for policy 1, policy_version 73331 (0.0008) -[2023-10-09 11:12:56,142][23468] Updated weights for policy 0, policy_version 72953 (0.0007) -[2023-10-09 11:12:56,478][23469] Updated weights for policy 1, policy_version 73341 (0.0008) -[2023-10-09 11:12:59,911][23468] Updated weights for policy 0, policy_version 72963 (0.0010) -[2023-10-09 11:13:00,224][23469] Updated weights for policy 1, policy_version 73351 (0.0007) -[2023-10-09 11:13:00,284][23468] Updated weights for policy 0, policy_version 72973 (0.0010) -[2023-10-09 11:13:00,593][23469] Updated weights for policy 1, policy_version 73361 (0.0008) -[2023-10-09 11:13:00,652][23468] Updated weights for policy 0, policy_version 72983 (0.0009) -[2023-10-09 11:13:00,957][23469] Updated weights for policy 1, policy_version 73371 (0.0008) -[2023-10-09 11:13:01,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 149848064. Throughput: 0: 1784.2, 1: 1787.6. Samples: 37473204. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:13:01,078][22500] Avg episode reward: [(0, '9.830'), (1, '9.380')] -[2023-10-09 11:13:04,600][23468] Updated weights for policy 0, policy_version 72993 (0.0008) -[2023-10-09 11:13:04,837][23469] Updated weights for policy 1, policy_version 73381 (0.0008) -[2023-10-09 11:13:04,985][23468] Updated weights for policy 0, policy_version 73003 (0.0008) -[2023-10-09 11:13:05,207][23469] Updated weights for policy 1, policy_version 73391 (0.0008) -[2023-10-09 11:13:05,357][23468] Updated weights for policy 0, policy_version 73013 (0.0008) -[2023-10-09 11:13:05,572][23469] Updated weights for policy 1, policy_version 73401 (0.0008) -[2023-10-09 11:13:05,731][23468] Updated weights for policy 0, policy_version 73023 (0.0007) -[2023-10-09 11:13:06,077][22500] Fps is (10 sec: 19660.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 149946368. Throughput: 0: 1765.6, 1: 1779.6. Samples: 37484378. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:13:06,078][22500] Avg episode reward: [(0, '9.910'), (1, '9.430')] -[2023-10-09 11:13:09,331][23468] Updated weights for policy 0, policy_version 73033 (0.0009) -[2023-10-09 11:13:09,493][23469] Updated weights for policy 1, policy_version 73411 (0.0008) -[2023-10-09 11:13:09,700][23468] Updated weights for policy 0, policy_version 73043 (0.0007) -[2023-10-09 11:13:09,867][23469] Updated weights for policy 1, policy_version 73421 (0.0008) -[2023-10-09 11:13:10,072][23468] Updated weights for policy 0, policy_version 73053 (0.0007) -[2023-10-09 11:13:10,227][23469] Updated weights for policy 1, policy_version 73431 (0.0008) -[2023-10-09 11:13:11,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 150011904. Throughput: 0: 1797.0, 1: 1793.3. Samples: 37505784. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:13:11,078][22500] Avg episode reward: [(0, '10.980'), (1, '9.080')] -[2023-10-09 11:13:13,894][23468] Updated weights for policy 0, policy_version 73063 (0.0008) -[2023-10-09 11:13:13,960][23469] Updated weights for policy 1, policy_version 73441 (0.0010) -[2023-10-09 11:13:14,265][23468] Updated weights for policy 0, policy_version 73073 (0.0008) -[2023-10-09 11:13:14,323][23469] Updated weights for policy 1, policy_version 73451 (0.0008) -[2023-10-09 11:13:14,626][23468] Updated weights for policy 0, policy_version 73083 (0.0008) -[2023-10-09 11:13:14,696][23469] Updated weights for policy 1, policy_version 73461 (0.0008) -[2023-10-09 11:13:15,057][23469] Updated weights for policy 1, policy_version 73471 (0.0008) -[2023-10-09 11:13:16,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 150077440. Throughput: 0: 1775.1, 1: 1770.1. Samples: 37526034. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:13:16,079][22500] Avg episode reward: [(0, '10.870'), (1, '8.670')] -[2023-10-09 11:13:18,346][23468] Updated weights for policy 0, policy_version 73093 (0.0009) -[2023-10-09 11:13:18,595][23469] Updated weights for policy 1, policy_version 73481 (0.0007) -[2023-10-09 11:13:18,726][23468] Updated weights for policy 0, policy_version 73103 (0.0008) -[2023-10-09 11:13:18,963][23469] Updated weights for policy 1, policy_version 73491 (0.0009) -[2023-10-09 11:13:19,097][23468] Updated weights for policy 0, policy_version 73113 (0.0009) -[2023-10-09 11:13:19,334][23469] Updated weights for policy 1, policy_version 73501 (0.0007) -[2023-10-09 11:13:21,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 150142976. Throughput: 0: 1800.4, 1: 1798.2. Samples: 37538140. Policy #0 lag: (min: 31.0, avg: 32.7, max: 58.0) -[2023-10-09 11:13:21,078][22500] Avg episode reward: [(0, '10.650'), (1, '9.300')] -[2023-10-09 11:13:22,850][23468] Updated weights for policy 0, policy_version 73123 (0.0008) -[2023-10-09 11:13:23,157][23469] Updated weights for policy 1, policy_version 73511 (0.0009) -[2023-10-09 11:13:23,230][23468] Updated weights for policy 0, policy_version 73133 (0.0007) -[2023-10-09 11:13:23,531][23469] Updated weights for policy 1, policy_version 73521 (0.0008) -[2023-10-09 11:13:23,605][23468] Updated weights for policy 0, policy_version 73143 (0.0007) -[2023-10-09 11:13:23,899][23469] Updated weights for policy 1, policy_version 73531 (0.0008) -[2023-10-09 11:13:26,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 150208512. Throughput: 0: 1781.5, 1: 1785.5. Samples: 37558514. Policy #0 lag: (min: 31.0, avg: 32.7, max: 58.0) -[2023-10-09 11:13:26,078][22500] Avg episode reward: [(0, '10.590'), (1, '9.110')] -[2023-10-09 11:13:27,336][23468] Updated weights for policy 0, policy_version 73153 (0.0008) -[2023-10-09 11:13:27,624][23469] Updated weights for policy 1, policy_version 73541 (0.0008) -[2023-10-09 11:13:27,716][23468] Updated weights for policy 0, policy_version 73163 (0.0008) -[2023-10-09 11:13:27,989][23469] Updated weights for policy 1, policy_version 73551 (0.0008) -[2023-10-09 11:13:28,088][23468] Updated weights for policy 0, policy_version 73173 (0.0008) -[2023-10-09 11:13:28,352][23469] Updated weights for policy 1, policy_version 73561 (0.0009) -[2023-10-09 11:13:28,450][23468] Updated weights for policy 0, policy_version 73183 (0.0007) -[2023-10-09 11:13:31,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 150274048. Throughput: 0: 1778.1, 1: 1791.0. Samples: 37580876. Policy #0 lag: (min: 31.0, avg: 32.7, max: 58.0) -[2023-10-09 11:13:31,078][22500] Avg episode reward: [(0, '9.890'), (1, '9.180')] -[2023-10-09 11:13:32,106][23469] Updated weights for policy 1, policy_version 73571 (0.0009) -[2023-10-09 11:13:32,389][23468] Updated weights for policy 0, policy_version 73193 (0.0007) -[2023-10-09 11:13:32,472][23469] Updated weights for policy 1, policy_version 73581 (0.0011) -[2023-10-09 11:13:32,764][23468] Updated weights for policy 0, policy_version 73203 (0.0008) -[2023-10-09 11:13:32,844][23469] Updated weights for policy 1, policy_version 73591 (0.0007) -[2023-10-09 11:13:33,133][23468] Updated weights for policy 0, policy_version 73213 (0.0009) -[2023-10-09 11:13:36,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 150339584. Throughput: 0: 1777.5, 1: 1788.9. Samples: 37590406. Policy #0 lag: (min: 31.0, avg: 32.7, max: 58.0) -[2023-10-09 11:13:36,078][22500] Avg episode reward: [(0, '9.620'), (1, '8.250')] -[2023-10-09 11:13:36,594][23469] Updated weights for policy 1, policy_version 73601 (0.0009) -[2023-10-09 11:13:36,971][23469] Updated weights for policy 1, policy_version 73611 (0.0008) -[2023-10-09 11:13:36,979][23468] Updated weights for policy 0, policy_version 73223 (0.0008) -[2023-10-09 11:13:37,334][23469] Updated weights for policy 1, policy_version 73621 (0.0008) -[2023-10-09 11:13:37,359][23468] Updated weights for policy 0, policy_version 73233 (0.0009) -[2023-10-09 11:13:37,706][23469] Updated weights for policy 1, policy_version 73631 (0.0008) -[2023-10-09 11:13:37,717][23468] Updated weights for policy 0, policy_version 73243 (0.0009) -[2023-10-09 11:13:41,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 150405120. Throughput: 0: 1769.9, 1: 1787.8. Samples: 37612310. Policy #0 lag: (min: 31.0, avg: 32.7, max: 58.0) -[2023-10-09 11:13:41,078][22500] Avg episode reward: [(0, '9.910'), (1, '8.660')] -[2023-10-09 11:13:41,521][23468] Updated weights for policy 0, policy_version 73253 (0.0007) -[2023-10-09 11:13:41,630][23469] Updated weights for policy 1, policy_version 73641 (0.0007) -[2023-10-09 11:13:41,894][23468] Updated weights for policy 0, policy_version 73263 (0.0008) -[2023-10-09 11:13:42,004][23469] Updated weights for policy 1, policy_version 73651 (0.0008) -[2023-10-09 11:13:42,263][23468] Updated weights for policy 0, policy_version 73273 (0.0008) -[2023-10-09 11:13:42,365][23469] Updated weights for policy 1, policy_version 73661 (0.0007) -[2023-10-09 11:13:46,007][23468] Updated weights for policy 0, policy_version 73283 (0.0007) -[2023-10-09 11:13:46,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 150470656. Throughput: 0: 1784.1, 1: 1805.8. Samples: 37634750. Policy #0 lag: (min: 31.0, avg: 32.7, max: 58.0) -[2023-10-09 11:13:46,078][22500] Avg episode reward: [(0, '9.850'), (1, '9.000')] -[2023-10-09 11:13:46,137][23469] Updated weights for policy 1, policy_version 73671 (0.0007) -[2023-10-09 11:13:46,376][23468] Updated weights for policy 0, policy_version 73293 (0.0008) -[2023-10-09 11:13:46,503][23469] Updated weights for policy 1, policy_version 73681 (0.0007) -[2023-10-09 11:13:46,742][23468] Updated weights for policy 0, policy_version 73303 (0.0007) -[2023-10-09 11:13:46,877][23469] Updated weights for policy 1, policy_version 73691 (0.0007) -[2023-10-09 11:13:50,585][23468] Updated weights for policy 0, policy_version 73313 (0.0007) -[2023-10-09 11:13:50,829][23469] Updated weights for policy 1, policy_version 73701 (0.0007) -[2023-10-09 11:13:50,981][23468] Updated weights for policy 0, policy_version 73323 (0.0007) -[2023-10-09 11:13:51,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 150536192. Throughput: 0: 1771.6, 1: 1780.3. Samples: 37644214. Policy #0 lag: (min: 31.0, avg: 32.7, max: 58.0) -[2023-10-09 11:13:51,078][22500] Avg episode reward: [(0, '10.050'), (1, '9.200')] -[2023-10-09 11:13:51,187][23469] Updated weights for policy 1, policy_version 73711 (0.0007) -[2023-10-09 11:13:51,355][23468] Updated weights for policy 0, policy_version 73333 (0.0008) -[2023-10-09 11:13:51,563][23469] Updated weights for policy 1, policy_version 73721 (0.0007) -[2023-10-09 11:13:51,718][23468] Updated weights for policy 0, policy_version 73343 (0.0008) -[2023-10-09 11:13:55,368][23469] Updated weights for policy 1, policy_version 73731 (0.0008) -[2023-10-09 11:13:55,400][23468] Updated weights for policy 0, policy_version 73353 (0.0007) -[2023-10-09 11:13:55,734][23469] Updated weights for policy 1, policy_version 73741 (0.0009) -[2023-10-09 11:13:55,777][23468] Updated weights for policy 0, policy_version 73363 (0.0008) -[2023-10-09 11:13:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 150601728. Throughput: 0: 1782.3, 1: 1792.1. Samples: 37666632. Policy #0 lag: (min: 31.0, avg: 32.7, max: 58.0) -[2023-10-09 11:13:56,078][22500] Avg episode reward: [(0, '9.790'), (1, '9.270')] -[2023-10-09 11:13:56,105][23469] Updated weights for policy 1, policy_version 73751 (0.0009) -[2023-10-09 11:13:56,142][23468] Updated weights for policy 0, policy_version 73373 (0.0009) -[2023-10-09 11:13:59,760][23468] Updated weights for policy 0, policy_version 73383 (0.0007) -[2023-10-09 11:13:59,974][23469] Updated weights for policy 1, policy_version 73761 (0.0010) -[2023-10-09 11:14:00,132][23468] Updated weights for policy 0, policy_version 73393 (0.0009) -[2023-10-09 11:14:00,348][23469] Updated weights for policy 1, policy_version 73771 (0.0008) -[2023-10-09 11:14:00,507][23468] Updated weights for policy 0, policy_version 73403 (0.0007) -[2023-10-09 11:14:00,726][23469] Updated weights for policy 1, policy_version 73781 (0.0009) -[2023-10-09 11:14:01,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 150700032. Throughput: 0: 1786.1, 1: 1789.7. Samples: 37686944. Policy #0 lag: (min: 31.0, avg: 32.7, max: 58.0) -[2023-10-09 11:14:01,078][22500] Avg episode reward: [(0, '10.410'), (1, '8.970')] -[2023-10-09 11:14:01,084][23469] Updated weights for policy 1, policy_version 73791 (0.0007) -[2023-10-09 11:14:04,397][23468] Updated weights for policy 0, policy_version 73413 (0.0009) -[2023-10-09 11:14:04,770][23468] Updated weights for policy 0, policy_version 73423 (0.0007) -[2023-10-09 11:14:04,823][23469] Updated weights for policy 1, policy_version 73801 (0.0007) -[2023-10-09 11:14:05,135][23468] Updated weights for policy 0, policy_version 73433 (0.0010) -[2023-10-09 11:14:05,194][23469] Updated weights for policy 1, policy_version 73811 (0.0008) -[2023-10-09 11:14:05,555][23469] Updated weights for policy 1, policy_version 73821 (0.0008) -[2023-10-09 11:14:06,077][22500] Fps is (10 sec: 19660.4, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 150798336. Throughput: 0: 1776.6, 1: 1792.1. Samples: 37698732. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-09 11:14:06,078][22500] Avg episode reward: [(0, '9.930'), (1, '8.740')] -[2023-10-09 11:14:08,909][23468] Updated weights for policy 0, policy_version 73443 (0.0008) -[2023-10-09 11:14:09,286][23468] Updated weights for policy 0, policy_version 73453 (0.0007) -[2023-10-09 11:14:09,335][23469] Updated weights for policy 1, policy_version 73831 (0.0010) -[2023-10-09 11:14:09,654][23468] Updated weights for policy 0, policy_version 73463 (0.0008) -[2023-10-09 11:14:09,717][23469] Updated weights for policy 1, policy_version 73841 (0.0009) -[2023-10-09 11:14:10,089][23469] Updated weights for policy 1, policy_version 73851 (0.0009) -[2023-10-09 11:14:11,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 150863872. Throughput: 0: 1788.3, 1: 1785.2. Samples: 37719320. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-09 11:14:11,078][22500] Avg episode reward: [(0, '10.220'), (1, '8.740')] -[2023-10-09 11:14:13,455][23468] Updated weights for policy 0, policy_version 73473 (0.0010) -[2023-10-09 11:14:13,823][23468] Updated weights for policy 0, policy_version 73483 (0.0010) -[2023-10-09 11:14:13,887][23469] Updated weights for policy 1, policy_version 73861 (0.0010) -[2023-10-09 11:14:14,192][23468] Updated weights for policy 0, policy_version 73493 (0.0009) -[2023-10-09 11:14:14,258][23469] Updated weights for policy 1, policy_version 73871 (0.0007) -[2023-10-09 11:14:14,565][23468] Updated weights for policy 0, policy_version 73503 (0.0007) -[2023-10-09 11:14:14,637][23469] Updated weights for policy 1, policy_version 73881 (0.0010) -[2023-10-09 11:14:16,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 150929408. Throughput: 0: 1772.3, 1: 1767.7. Samples: 37740174. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-09 11:14:16,078][22500] Avg episode reward: [(0, '9.530'), (1, '8.950')] -[2023-10-09 11:14:16,085][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000073888_75661312.pth... -[2023-10-09 11:14:16,085][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000073504_75268096.pth... -[2023-10-09 11:14:16,122][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000071840_73564160.pth -[2023-10-09 11:14:16,124][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000072224_73957376.pth -[2023-10-09 11:14:18,210][23468] Updated weights for policy 0, policy_version 73513 (0.0010) -[2023-10-09 11:14:18,421][23469] Updated weights for policy 1, policy_version 73891 (0.0007) -[2023-10-09 11:14:18,582][23468] Updated weights for policy 0, policy_version 73523 (0.0009) -[2023-10-09 11:14:18,792][23469] Updated weights for policy 1, policy_version 73901 (0.0007) -[2023-10-09 11:14:18,948][23468] Updated weights for policy 0, policy_version 73533 (0.0007) -[2023-10-09 11:14:19,151][23469] Updated weights for policy 1, policy_version 73911 (0.0008) -[2023-10-09 11:14:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 150994944. Throughput: 0: 1798.2, 1: 1795.4. Samples: 37752118. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-09 11:14:21,078][22500] Avg episode reward: [(0, '10.010'), (1, '8.760')] -[2023-10-09 11:14:22,735][23468] Updated weights for policy 0, policy_version 73543 (0.0009) -[2023-10-09 11:14:22,973][23469] Updated weights for policy 1, policy_version 73921 (0.0008) -[2023-10-09 11:14:23,106][23468] Updated weights for policy 0, policy_version 73553 (0.0007) -[2023-10-09 11:14:23,341][23469] Updated weights for policy 1, policy_version 73931 (0.0007) -[2023-10-09 11:14:23,476][23468] Updated weights for policy 0, policy_version 73563 (0.0007) -[2023-10-09 11:14:23,701][23469] Updated weights for policy 1, policy_version 73941 (0.0007) -[2023-10-09 11:14:24,071][23469] Updated weights for policy 1, policy_version 73951 (0.0007) -[2023-10-09 11:14:26,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 151060480. Throughput: 0: 1787.7, 1: 1776.6. Samples: 37772702. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-09 11:14:26,078][22500] Avg episode reward: [(0, '9.710'), (1, '9.310')] -[2023-10-09 11:14:27,239][23468] Updated weights for policy 0, policy_version 73573 (0.0008) -[2023-10-09 11:14:27,615][23468] Updated weights for policy 0, policy_version 73583 (0.0009) -[2023-10-09 11:14:27,640][23469] Updated weights for policy 1, policy_version 73961 (0.0007) -[2023-10-09 11:14:27,978][23468] Updated weights for policy 0, policy_version 73593 (0.0009) -[2023-10-09 11:14:28,004][23469] Updated weights for policy 1, policy_version 73971 (0.0007) -[2023-10-09 11:14:28,375][23469] Updated weights for policy 1, policy_version 73981 (0.0008) -[2023-10-09 11:14:31,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 151126016. Throughput: 0: 1785.3, 1: 1776.8. Samples: 37795044. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-09 11:14:31,078][22500] Avg episode reward: [(0, '10.080'), (1, '8.630')] -[2023-10-09 11:14:31,801][23468] Updated weights for policy 0, policy_version 73603 (0.0008) -[2023-10-09 11:14:32,182][23468] Updated weights for policy 0, policy_version 73613 (0.0007) -[2023-10-09 11:14:32,225][23469] Updated weights for policy 1, policy_version 73991 (0.0007) -[2023-10-09 11:14:32,552][23468] Updated weights for policy 0, policy_version 73623 (0.0007) -[2023-10-09 11:14:32,592][23469] Updated weights for policy 1, policy_version 74001 (0.0008) -[2023-10-09 11:14:32,952][23469] Updated weights for policy 1, policy_version 74011 (0.0010) -[2023-10-09 11:14:36,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 151191552. Throughput: 0: 1784.5, 1: 1779.6. Samples: 37804602. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-09 11:14:36,078][22500] Avg episode reward: [(0, '9.900'), (1, '9.240')] -[2023-10-09 11:14:36,275][23468] Updated weights for policy 0, policy_version 73633 (0.0007) -[2023-10-09 11:14:36,666][23468] Updated weights for policy 0, policy_version 73643 (0.0008) -[2023-10-09 11:14:36,747][23469] Updated weights for policy 1, policy_version 74021 (0.0010) -[2023-10-09 11:14:37,039][23468] Updated weights for policy 0, policy_version 73653 (0.0008) -[2023-10-09 11:14:37,111][23469] Updated weights for policy 1, policy_version 74031 (0.0008) -[2023-10-09 11:14:37,407][23468] Updated weights for policy 0, policy_version 73663 (0.0009) -[2023-10-09 11:14:37,482][23469] Updated weights for policy 1, policy_version 74041 (0.0007) -[2023-10-09 11:14:41,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 151257088. Throughput: 0: 1784.0, 1: 1783.6. Samples: 37827176. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-09 11:14:41,078][22500] Avg episode reward: [(0, '10.110'), (1, '8.890')] -[2023-10-09 11:14:41,127][23468] Updated weights for policy 0, policy_version 73673 (0.0009) -[2023-10-09 11:14:41,222][23469] Updated weights for policy 1, policy_version 74051 (0.0007) -[2023-10-09 11:14:41,502][23468] Updated weights for policy 0, policy_version 73683 (0.0008) -[2023-10-09 11:14:41,596][23469] Updated weights for policy 1, policy_version 74061 (0.0008) -[2023-10-09 11:14:41,866][23468] Updated weights for policy 0, policy_version 73693 (0.0009) -[2023-10-09 11:14:41,960][23469] Updated weights for policy 1, policy_version 74071 (0.0009) -[2023-10-09 11:14:45,516][23469] Updated weights for policy 1, policy_version 74081 (0.0010) -[2023-10-09 11:14:45,749][23468] Updated weights for policy 0, policy_version 73703 (0.0009) -[2023-10-09 11:14:45,880][23469] Updated weights for policy 1, policy_version 74091 (0.0007) -[2023-10-09 11:14:46,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 151322624. Throughput: 0: 1799.7, 1: 1803.4. Samples: 37849082. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-09 11:14:46,078][22500] Avg episode reward: [(0, '11.040'), (1, '9.150')] -[2023-10-09 11:14:46,129][23468] Updated weights for policy 0, policy_version 73713 (0.0008) -[2023-10-09 11:14:46,245][23469] Updated weights for policy 1, policy_version 74101 (0.0008) -[2023-10-09 11:14:46,492][23468] Updated weights for policy 0, policy_version 73723 (0.0009) -[2023-10-09 11:14:46,616][23469] Updated weights for policy 1, policy_version 74111 (0.0008) -[2023-10-09 11:14:50,152][23468] Updated weights for policy 0, policy_version 73733 (0.0008) -[2023-10-09 11:14:50,345][23469] Updated weights for policy 1, policy_version 74121 (0.0009) -[2023-10-09 11:14:50,520][23468] Updated weights for policy 0, policy_version 73743 (0.0007) -[2023-10-09 11:14:50,717][23469] Updated weights for policy 1, policy_version 74131 (0.0009) -[2023-10-09 11:14:50,901][23468] Updated weights for policy 0, policy_version 73753 (0.0008) -[2023-10-09 11:14:51,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 151388160. Throughput: 0: 1783.3, 1: 1783.3. Samples: 37859224. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-09 11:14:51,078][22500] Avg episode reward: [(0, '11.650'), (1, '9.340')] -[2023-10-09 11:14:51,085][23469] Updated weights for policy 1, policy_version 74141 (0.0009) -[2023-10-09 11:14:51,151][23265] Saving new best policy, reward=11.650! -[2023-10-09 11:14:54,609][23468] Updated weights for policy 0, policy_version 73763 (0.0007) -[2023-10-09 11:14:54,877][23469] Updated weights for policy 1, policy_version 74151 (0.0007) -[2023-10-09 11:14:54,985][23468] Updated weights for policy 0, policy_version 73773 (0.0007) -[2023-10-09 11:14:55,251][23469] Updated weights for policy 1, policy_version 74161 (0.0008) -[2023-10-09 11:14:55,350][23468] Updated weights for policy 0, policy_version 73783 (0.0007) -[2023-10-09 11:14:55,612][23469] Updated weights for policy 1, policy_version 74171 (0.0010) -[2023-10-09 11:14:56,077][22500] Fps is (10 sec: 19660.9, 60 sec: 15291.7, 300 sec: 14440.1). Total num frames: 151519232. Throughput: 0: 1800.0, 1: 1802.7. Samples: 37881440. Policy #0 lag: (min: 22.0, avg: 22.0, max: 25.0) -[2023-10-09 11:14:56,078][22500] Avg episode reward: [(0, '11.260'), (1, '8.900')] -[2023-10-09 11:14:59,147][23468] Updated weights for policy 0, policy_version 73793 (0.0008) -[2023-10-09 11:14:59,290][23469] Updated weights for policy 1, policy_version 74181 (0.0007) -[2023-10-09 11:14:59,518][23468] Updated weights for policy 0, policy_version 73803 (0.0007) -[2023-10-09 11:14:59,658][23469] Updated weights for policy 1, policy_version 74191 (0.0007) -[2023-10-09 11:14:59,891][23468] Updated weights for policy 0, policy_version 73813 (0.0009) -[2023-10-09 11:15:00,027][23469] Updated weights for policy 1, policy_version 74201 (0.0008) -[2023-10-09 11:15:00,261][23468] Updated weights for policy 0, policy_version 73823 (0.0007) -[2023-10-09 11:15:01,078][22500] Fps is (10 sec: 19660.2, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 151584768. Throughput: 0: 1784.4, 1: 1790.7. Samples: 37901054. Policy #0 lag: (min: 22.0, avg: 22.0, max: 25.0) -[2023-10-09 11:15:01,079][22500] Avg episode reward: [(0, '10.890'), (1, '9.480')] -[2023-10-09 11:15:03,789][23469] Updated weights for policy 1, policy_version 74211 (0.0009) -[2023-10-09 11:15:04,160][23469] Updated weights for policy 1, policy_version 74221 (0.0007) -[2023-10-09 11:15:04,209][23468] Updated weights for policy 0, policy_version 73833 (0.0008) -[2023-10-09 11:15:04,526][23469] Updated weights for policy 1, policy_version 74231 (0.0008) -[2023-10-09 11:15:04,581][23468] Updated weights for policy 0, policy_version 73843 (0.0009) -[2023-10-09 11:15:04,948][23468] Updated weights for policy 0, policy_version 73853 (0.0010) -[2023-10-09 11:15:06,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 151650304. Throughput: 0: 1788.0, 1: 1796.3. Samples: 37913410. Policy #0 lag: (min: 22.0, avg: 22.0, max: 25.0) -[2023-10-09 11:15:06,078][22500] Avg episode reward: [(0, '10.620'), (1, '8.860')] -[2023-10-09 11:15:08,248][23469] Updated weights for policy 1, policy_version 74241 (0.0009) -[2023-10-09 11:15:08,616][23469] Updated weights for policy 1, policy_version 74251 (0.0007) -[2023-10-09 11:15:08,691][23468] Updated weights for policy 0, policy_version 73863 (0.0009) -[2023-10-09 11:15:08,990][23469] Updated weights for policy 1, policy_version 74261 (0.0008) -[2023-10-09 11:15:09,064][23468] Updated weights for policy 0, policy_version 73873 (0.0008) -[2023-10-09 11:15:09,355][23469] Updated weights for policy 1, policy_version 74271 (0.0007) -[2023-10-09 11:15:09,439][23468] Updated weights for policy 0, policy_version 73883 (0.0007) -[2023-10-09 11:15:11,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 151715840. Throughput: 0: 1782.8, 1: 1787.6. Samples: 37933372. Policy #0 lag: (min: 22.0, avg: 22.0, max: 25.0) -[2023-10-09 11:15:11,079][22500] Avg episode reward: [(0, '10.370'), (1, '9.020')] -[2023-10-09 11:15:13,199][23469] Updated weights for policy 1, policy_version 74281 (0.0007) -[2023-10-09 11:15:13,292][23468] Updated weights for policy 0, policy_version 73893 (0.0007) -[2023-10-09 11:15:13,572][23469] Updated weights for policy 1, policy_version 74291 (0.0007) -[2023-10-09 11:15:13,663][23468] Updated weights for policy 0, policy_version 73903 (0.0008) -[2023-10-09 11:15:13,941][23469] Updated weights for policy 1, policy_version 74301 (0.0009) -[2023-10-09 11:15:14,031][23468] Updated weights for policy 0, policy_version 73913 (0.0008) -[2023-10-09 11:15:16,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 151781376. Throughput: 0: 1771.9, 1: 1785.8. Samples: 37955144. Policy #0 lag: (min: 22.0, avg: 22.0, max: 25.0) -[2023-10-09 11:15:16,079][22500] Avg episode reward: [(0, '10.830'), (1, '9.310')] -[2023-10-09 11:15:17,639][23468] Updated weights for policy 0, policy_version 73923 (0.0009) -[2023-10-09 11:15:17,697][23469] Updated weights for policy 1, policy_version 74311 (0.0009) -[2023-10-09 11:15:18,001][23468] Updated weights for policy 0, policy_version 73933 (0.0008) -[2023-10-09 11:15:18,070][23469] Updated weights for policy 1, policy_version 74321 (0.0007) -[2023-10-09 11:15:18,369][23468] Updated weights for policy 0, policy_version 73943 (0.0009) -[2023-10-09 11:15:18,439][23469] Updated weights for policy 1, policy_version 74331 (0.0009) -[2023-10-09 11:15:21,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 151846912. Throughput: 0: 1786.2, 1: 1791.8. Samples: 37965612. Policy #0 lag: (min: 22.0, avg: 22.0, max: 25.0) -[2023-10-09 11:15:21,078][22500] Avg episode reward: [(0, '11.270'), (1, '8.960')] -[2023-10-09 11:15:22,178][23468] Updated weights for policy 0, policy_version 73953 (0.0009) -[2023-10-09 11:15:22,269][23469] Updated weights for policy 1, policy_version 74341 (0.0008) -[2023-10-09 11:15:22,558][23468] Updated weights for policy 0, policy_version 73963 (0.0009) -[2023-10-09 11:15:22,632][23469] Updated weights for policy 1, policy_version 74351 (0.0007) -[2023-10-09 11:15:22,926][23468] Updated weights for policy 0, policy_version 73973 (0.0008) -[2023-10-09 11:15:23,004][23469] Updated weights for policy 1, policy_version 74361 (0.0009) -[2023-10-09 11:15:23,302][23468] Updated weights for policy 0, policy_version 73983 (0.0008) -[2023-10-09 11:15:26,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 151912448. Throughput: 0: 1774.4, 1: 1783.7. Samples: 37987290. Policy #0 lag: (min: 22.0, avg: 22.0, max: 25.0) -[2023-10-09 11:15:26,079][22500] Avg episode reward: [(0, '10.330'), (1, '9.330')] -[2023-10-09 11:15:26,797][23469] Updated weights for policy 1, policy_version 74371 (0.0010) -[2023-10-09 11:15:27,164][23469] Updated weights for policy 1, policy_version 74381 (0.0008) -[2023-10-09 11:15:27,241][23468] Updated weights for policy 0, policy_version 73993 (0.0008) -[2023-10-09 11:15:27,528][23469] Updated weights for policy 1, policy_version 74391 (0.0009) -[2023-10-09 11:15:27,613][23468] Updated weights for policy 0, policy_version 74003 (0.0008) -[2023-10-09 11:15:27,986][23468] Updated weights for policy 0, policy_version 74013 (0.0007) -[2023-10-09 11:15:31,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 151977984. Throughput: 0: 1773.4, 1: 1789.6. Samples: 38009416. Policy #0 lag: (min: 22.0, avg: 22.0, max: 25.0) -[2023-10-09 11:15:31,078][22500] Avg episode reward: [(0, '10.160'), (1, '8.940')] -[2023-10-09 11:15:31,298][23469] Updated weights for policy 1, policy_version 74401 (0.0008) -[2023-10-09 11:15:31,664][23469] Updated weights for policy 1, policy_version 74411 (0.0008) -[2023-10-09 11:15:31,779][23468] Updated weights for policy 0, policy_version 74023 (0.0008) -[2023-10-09 11:15:32,037][23469] Updated weights for policy 1, policy_version 74421 (0.0008) -[2023-10-09 11:15:32,148][23468] Updated weights for policy 0, policy_version 74033 (0.0007) -[2023-10-09 11:15:32,401][23469] Updated weights for policy 1, policy_version 74431 (0.0007) -[2023-10-09 11:15:32,520][23468] Updated weights for policy 0, policy_version 74043 (0.0008) -[2023-10-09 11:15:36,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 152043520. Throughput: 0: 1772.7, 1: 1782.1. Samples: 38019192. Policy #0 lag: (min: 22.0, avg: 22.0, max: 25.0) -[2023-10-09 11:15:36,078][22500] Avg episode reward: [(0, '9.920'), (1, '9.190')] -[2023-10-09 11:15:36,104][23469] Updated weights for policy 1, policy_version 74441 (0.0008) -[2023-10-09 11:15:36,202][23468] Updated weights for policy 0, policy_version 74053 (0.0009) -[2023-10-09 11:15:36,462][23469] Updated weights for policy 1, policy_version 74451 (0.0007) -[2023-10-09 11:15:36,570][23468] Updated weights for policy 0, policy_version 74063 (0.0007) -[2023-10-09 11:15:36,837][23469] Updated weights for policy 1, policy_version 74461 (0.0010) -[2023-10-09 11:15:36,949][23468] Updated weights for policy 0, policy_version 74073 (0.0009) -[2023-10-09 11:15:40,441][23469] Updated weights for policy 1, policy_version 74471 (0.0008) -[2023-10-09 11:15:40,717][23468] Updated weights for policy 0, policy_version 74083 (0.0007) -[2023-10-09 11:15:40,812][23469] Updated weights for policy 1, policy_version 74481 (0.0009) -[2023-10-09 11:15:41,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 152109056. Throughput: 0: 1770.6, 1: 1792.1. Samples: 38041762. Policy #0 lag: (min: 22.0, avg: 22.0, max: 25.0) -[2023-10-09 11:15:41,078][22500] Avg episode reward: [(0, '10.290'), (1, '9.270')] -[2023-10-09 11:15:41,089][23468] Updated weights for policy 0, policy_version 74093 (0.0007) -[2023-10-09 11:15:41,181][23469] Updated weights for policy 1, policy_version 74491 (0.0008) -[2023-10-09 11:15:41,463][23468] Updated weights for policy 0, policy_version 74103 (0.0008) -[2023-10-09 11:15:44,957][23469] Updated weights for policy 1, policy_version 74501 (0.0008) -[2023-10-09 11:15:45,309][23468] Updated weights for policy 0, policy_version 74113 (0.0010) -[2023-10-09 11:15:45,325][23469] Updated weights for policy 1, policy_version 74511 (0.0007) -[2023-10-09 11:15:45,681][23468] Updated weights for policy 0, policy_version 74123 (0.0008) -[2023-10-09 11:15:45,686][23469] Updated weights for policy 1, policy_version 74521 (0.0008) -[2023-10-09 11:15:46,054][23468] Updated weights for policy 0, policy_version 74133 (0.0008) -[2023-10-09 11:15:46,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 152207360. Throughput: 0: 1799.7, 1: 1794.7. Samples: 38062802. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:15:46,078][22500] Avg episode reward: [(0, '10.190'), (1, '8.720')] -[2023-10-09 11:15:46,434][23468] Updated weights for policy 0, policy_version 74143 (0.0008) -[2023-10-09 11:15:49,471][23469] Updated weights for policy 1, policy_version 74531 (0.0008) -[2023-10-09 11:15:49,833][23469] Updated weights for policy 1, policy_version 74541 (0.0008) -[2023-10-09 11:15:50,199][23468] Updated weights for policy 0, policy_version 74153 (0.0008) -[2023-10-09 11:15:50,202][23469] Updated weights for policy 1, policy_version 74551 (0.0008) -[2023-10-09 11:15:50,569][23468] Updated weights for policy 0, policy_version 74163 (0.0008) -[2023-10-09 11:15:50,939][23468] Updated weights for policy 0, policy_version 74173 (0.0010) -[2023-10-09 11:15:51,077][22500] Fps is (10 sec: 19660.8, 60 sec: 15291.7, 300 sec: 14440.1). Total num frames: 152305664. Throughput: 0: 1768.3, 1: 1793.4. Samples: 38073684. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:15:51,078][22500] Avg episode reward: [(0, '10.350'), (1, '8.960')] -[2023-10-09 11:15:53,919][23469] Updated weights for policy 1, policy_version 74561 (0.0008) -[2023-10-09 11:15:54,285][23469] Updated weights for policy 1, policy_version 74571 (0.0010) -[2023-10-09 11:15:54,665][23469] Updated weights for policy 1, policy_version 74581 (0.0009) -[2023-10-09 11:15:54,787][23468] Updated weights for policy 0, policy_version 74183 (0.0007) -[2023-10-09 11:15:55,024][23469] Updated weights for policy 1, policy_version 74591 (0.0007) -[2023-10-09 11:15:55,157][23468] Updated weights for policy 0, policy_version 74193 (0.0008) -[2023-10-09 11:15:55,528][23468] Updated weights for policy 0, policy_version 74203 (0.0008) -[2023-10-09 11:15:56,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 152371200. Throughput: 0: 1789.4, 1: 1797.5. Samples: 38094782. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:15:56,079][22500] Avg episode reward: [(0, '10.060'), (1, '9.050')] -[2023-10-09 11:15:58,654][23469] Updated weights for policy 1, policy_version 74601 (0.0008) -[2023-10-09 11:15:59,021][23469] Updated weights for policy 1, policy_version 74611 (0.0007) -[2023-10-09 11:15:59,386][23469] Updated weights for policy 1, policy_version 74621 (0.0008) -[2023-10-09 11:15:59,509][23468] Updated weights for policy 0, policy_version 74213 (0.0007) -[2023-10-09 11:15:59,888][23468] Updated weights for policy 0, policy_version 74223 (0.0007) -[2023-10-09 11:16:00,257][23468] Updated weights for policy 0, policy_version 74233 (0.0008) -[2023-10-09 11:16:01,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 152436736. Throughput: 0: 1770.1, 1: 1799.4. Samples: 38115770. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:16:01,078][22500] Avg episode reward: [(0, '9.850'), (1, '9.000')] -[2023-10-09 11:16:03,131][23469] Updated weights for policy 1, policy_version 74631 (0.0008) -[2023-10-09 11:16:03,489][23469] Updated weights for policy 1, policy_version 74641 (0.0009) -[2023-10-09 11:16:03,859][23469] Updated weights for policy 1, policy_version 74651 (0.0008) -[2023-10-09 11:16:04,062][23468] Updated weights for policy 0, policy_version 74243 (0.0007) -[2023-10-09 11:16:04,437][23468] Updated weights for policy 0, policy_version 74253 (0.0007) -[2023-10-09 11:16:04,804][23468] Updated weights for policy 0, policy_version 74263 (0.0008) -[2023-10-09 11:16:06,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 152502272. Throughput: 0: 1782.6, 1: 1801.6. Samples: 38126902. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:16:06,078][22500] Avg episode reward: [(0, '10.160'), (1, '9.230')] -[2023-10-09 11:16:07,648][23469] Updated weights for policy 1, policy_version 74661 (0.0008) -[2023-10-09 11:16:08,018][23469] Updated weights for policy 1, policy_version 74671 (0.0008) -[2023-10-09 11:16:08,379][23469] Updated weights for policy 1, policy_version 74681 (0.0007) -[2023-10-09 11:16:08,452][23468] Updated weights for policy 0, policy_version 74273 (0.0009) -[2023-10-09 11:16:08,828][23468] Updated weights for policy 0, policy_version 74283 (0.0008) -[2023-10-09 11:16:09,200][23468] Updated weights for policy 0, policy_version 74293 (0.0010) -[2023-10-09 11:16:09,576][23468] Updated weights for policy 0, policy_version 74303 (0.0007) -[2023-10-09 11:16:11,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 152567808. Throughput: 0: 1774.3, 1: 1802.0. Samples: 38148220. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:16:11,078][22500] Avg episode reward: [(0, '10.310'), (1, '9.500')] -[2023-10-09 11:16:12,141][23469] Updated weights for policy 1, policy_version 74691 (0.0008) -[2023-10-09 11:16:12,514][23469] Updated weights for policy 1, policy_version 74701 (0.0008) -[2023-10-09 11:16:12,887][23469] Updated weights for policy 1, policy_version 74711 (0.0008) -[2023-10-09 11:16:13,416][23468] Updated weights for policy 0, policy_version 74313 (0.0009) -[2023-10-09 11:16:13,778][23468] Updated weights for policy 0, policy_version 74323 (0.0008) -[2023-10-09 11:16:14,155][23468] Updated weights for policy 0, policy_version 74333 (0.0010) -[2023-10-09 11:16:16,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 152633344. Throughput: 0: 1768.7, 1: 1800.4. Samples: 38170024. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:16:16,079][22500] Avg episode reward: [(0, '10.250'), (1, '9.600')] -[2023-10-09 11:16:16,091][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000074720_76513280.pth... -[2023-10-09 11:16:16,091][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000074336_76120064.pth... -[2023-10-09 11:16:16,127][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000072672_74416128.pth -[2023-10-09 11:16:16,131][23265] Saving a milestone ./train_atari/atari_berzerk_APPO/checkpoint_p0/milestones/checkpoint_000074336_76120064.pth -[2023-10-09 11:16:16,131][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000073056_74809344.pth -[2023-10-09 11:16:16,135][23343] Saving a milestone ./train_atari/atari_berzerk_APPO/checkpoint_p1/milestones/checkpoint_000074720_76513280.pth -[2023-10-09 11:16:16,611][23469] Updated weights for policy 1, policy_version 74721 (0.0008) -[2023-10-09 11:16:16,974][23469] Updated weights for policy 1, policy_version 74731 (0.0008) -[2023-10-09 11:16:17,351][23469] Updated weights for policy 1, policy_version 74741 (0.0008) -[2023-10-09 11:16:17,713][23469] Updated weights for policy 1, policy_version 74751 (0.0008) -[2023-10-09 11:16:17,871][23468] Updated weights for policy 0, policy_version 74343 (0.0008) -[2023-10-09 11:16:18,246][23468] Updated weights for policy 0, policy_version 74353 (0.0010) -[2023-10-09 11:16:18,634][23468] Updated weights for policy 0, policy_version 74363 (0.0010) -[2023-10-09 11:16:21,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 152698880. Throughput: 0: 1783.6, 1: 1801.5. Samples: 38180522. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:16:21,079][22500] Avg episode reward: [(0, '10.150'), (1, '9.180')] -[2023-10-09 11:16:21,534][23469] Updated weights for policy 1, policy_version 74761 (0.0007) -[2023-10-09 11:16:21,900][23469] Updated weights for policy 1, policy_version 74771 (0.0008) -[2023-10-09 11:16:22,277][23469] Updated weights for policy 1, policy_version 74781 (0.0008) -[2023-10-09 11:16:22,378][23468] Updated weights for policy 0, policy_version 74373 (0.0008) -[2023-10-09 11:16:22,745][23468] Updated weights for policy 0, policy_version 74383 (0.0009) -[2023-10-09 11:16:23,113][23468] Updated weights for policy 0, policy_version 74393 (0.0010) -[2023-10-09 11:16:26,078][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 152764416. Throughput: 0: 1769.6, 1: 1794.2. Samples: 38202136. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:16:26,079][22500] Avg episode reward: [(0, '9.050'), (1, '9.320')] -[2023-10-09 11:16:26,100][23469] Updated weights for policy 1, policy_version 74791 (0.0008) -[2023-10-09 11:16:26,477][23469] Updated weights for policy 1, policy_version 74801 (0.0007) -[2023-10-09 11:16:26,784][23468] Updated weights for policy 0, policy_version 74403 (0.0007) -[2023-10-09 11:16:26,844][23469] Updated weights for policy 1, policy_version 74811 (0.0007) -[2023-10-09 11:16:27,144][23468] Updated weights for policy 0, policy_version 74413 (0.0009) -[2023-10-09 11:16:27,511][23468] Updated weights for policy 0, policy_version 74423 (0.0010) -[2023-10-09 11:16:30,561][23469] Updated weights for policy 1, policy_version 74821 (0.0008) -[2023-10-09 11:16:30,932][23469] Updated weights for policy 1, policy_version 74831 (0.0009) -[2023-10-09 11:16:31,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 152829952. Throughput: 0: 1772.4, 1: 1807.4. Samples: 38223894. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:16:31,078][22500] Avg episode reward: [(0, '10.100'), (1, '9.280')] -[2023-10-09 11:16:31,300][23469] Updated weights for policy 1, policy_version 74841 (0.0010) -[2023-10-09 11:16:31,303][23468] Updated weights for policy 0, policy_version 74433 (0.0009) -[2023-10-09 11:16:31,684][23468] Updated weights for policy 0, policy_version 74443 (0.0008) -[2023-10-09 11:16:32,054][23468] Updated weights for policy 0, policy_version 74453 (0.0010) -[2023-10-09 11:16:32,430][23468] Updated weights for policy 0, policy_version 74463 (0.0009) -[2023-10-09 11:16:35,055][23469] Updated weights for policy 1, policy_version 74851 (0.0009) -[2023-10-09 11:16:35,419][23469] Updated weights for policy 1, policy_version 74861 (0.0008) -[2023-10-09 11:16:35,792][23469] Updated weights for policy 1, policy_version 74871 (0.0008) -[2023-10-09 11:16:36,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 152895488. Throughput: 0: 1776.4, 1: 1790.7. Samples: 38234202. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) -[2023-10-09 11:16:36,078][22500] Avg episode reward: [(0, '10.410'), (1, '9.080')] -[2023-10-09 11:16:36,144][23468] Updated weights for policy 0, policy_version 74473 (0.0010) -[2023-10-09 11:16:36,532][23468] Updated weights for policy 0, policy_version 74483 (0.0009) -[2023-10-09 11:16:36,908][23468] Updated weights for policy 0, policy_version 74493 (0.0008) -[2023-10-09 11:16:39,549][23469] Updated weights for policy 1, policy_version 74881 (0.0007) -[2023-10-09 11:16:39,927][23469] Updated weights for policy 1, policy_version 74891 (0.0007) -[2023-10-09 11:16:40,298][23469] Updated weights for policy 1, policy_version 74901 (0.0009) -[2023-10-09 11:16:40,505][23468] Updated weights for policy 0, policy_version 74503 (0.0008) -[2023-10-09 11:16:40,656][23469] Updated weights for policy 1, policy_version 74911 (0.0007) -[2023-10-09 11:16:40,878][23468] Updated weights for policy 0, policy_version 74513 (0.0008) -[2023-10-09 11:16:41,078][22500] Fps is (10 sec: 16383.4, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 152993792. Throughput: 0: 1781.7, 1: 1810.3. Samples: 38256420. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) -[2023-10-09 11:16:41,079][22500] Avg episode reward: [(0, '10.010'), (1, '9.570')] -[2023-10-09 11:16:41,260][23468] Updated weights for policy 0, policy_version 74523 (0.0007) -[2023-10-09 11:16:44,389][23469] Updated weights for policy 1, policy_version 74921 (0.0007) -[2023-10-09 11:16:44,764][23469] Updated weights for policy 1, policy_version 74931 (0.0007) -[2023-10-09 11:16:44,985][23468] Updated weights for policy 0, policy_version 74533 (0.0007) -[2023-10-09 11:16:45,136][23469] Updated weights for policy 1, policy_version 74941 (0.0007) -[2023-10-09 11:16:45,351][23468] Updated weights for policy 0, policy_version 74543 (0.0009) -[2023-10-09 11:16:45,722][23468] Updated weights for policy 0, policy_version 74553 (0.0009) -[2023-10-09 11:16:46,077][22500] Fps is (10 sec: 19661.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 153092096. Throughput: 0: 1804.0, 1: 1785.9. Samples: 38277316. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) -[2023-10-09 11:16:46,078][22500] Avg episode reward: [(0, '10.760'), (1, '9.480')] -[2023-10-09 11:16:48,767][23469] Updated weights for policy 1, policy_version 74951 (0.0008) -[2023-10-09 11:16:49,135][23469] Updated weights for policy 1, policy_version 74961 (0.0009) -[2023-10-09 11:16:49,486][23468] Updated weights for policy 0, policy_version 74563 (0.0007) -[2023-10-09 11:16:49,505][23469] Updated weights for policy 1, policy_version 74971 (0.0008) -[2023-10-09 11:16:49,842][23468] Updated weights for policy 0, policy_version 74573 (0.0008) -[2023-10-09 11:16:50,211][23468] Updated weights for policy 0, policy_version 74583 (0.0011) -[2023-10-09 11:16:51,077][22500] Fps is (10 sec: 16384.6, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 153157632. Throughput: 0: 1792.4, 1: 1809.9. Samples: 38289006. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) -[2023-10-09 11:16:51,078][22500] Avg episode reward: [(0, '9.910'), (1, '10.040')] -[2023-10-09 11:16:53,528][23469] Updated weights for policy 1, policy_version 74981 (0.0007) -[2023-10-09 11:16:53,899][23469] Updated weights for policy 1, policy_version 74991 (0.0010) -[2023-10-09 11:16:54,034][23468] Updated weights for policy 0, policy_version 74593 (0.0010) -[2023-10-09 11:16:54,271][23469] Updated weights for policy 1, policy_version 75001 (0.0009) -[2023-10-09 11:16:54,411][23468] Updated weights for policy 0, policy_version 74603 (0.0008) -[2023-10-09 11:16:54,788][23468] Updated weights for policy 0, policy_version 74613 (0.0008) -[2023-10-09 11:16:55,160][23468] Updated weights for policy 0, policy_version 74623 (0.0007) -[2023-10-09 11:16:56,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 153223168. Throughput: 0: 1807.2, 1: 1780.7. Samples: 38309676. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) -[2023-10-09 11:16:56,078][22500] Avg episode reward: [(0, '10.110'), (1, '9.830')] -[2023-10-09 11:16:57,921][23469] Updated weights for policy 1, policy_version 75011 (0.0008) -[2023-10-09 11:16:58,286][23469] Updated weights for policy 1, policy_version 75021 (0.0008) -[2023-10-09 11:16:58,657][23469] Updated weights for policy 1, policy_version 75031 (0.0007) -[2023-10-09 11:16:59,116][23468] Updated weights for policy 0, policy_version 74633 (0.0010) -[2023-10-09 11:16:59,489][23468] Updated weights for policy 0, policy_version 74643 (0.0008) -[2023-10-09 11:16:59,862][23468] Updated weights for policy 0, policy_version 74653 (0.0007) -[2023-10-09 11:17:01,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 153288704. Throughput: 0: 1785.3, 1: 1790.2. Samples: 38330922. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) -[2023-10-09 11:17:01,078][22500] Avg episode reward: [(0, '10.180'), (1, '9.920')] -[2023-10-09 11:17:02,380][23469] Updated weights for policy 1, policy_version 75041 (0.0008) -[2023-10-09 11:17:02,753][23469] Updated weights for policy 1, policy_version 75051 (0.0007) -[2023-10-09 11:17:03,119][23469] Updated weights for policy 1, policy_version 75061 (0.0008) -[2023-10-09 11:17:03,496][23469] Updated weights for policy 1, policy_version 75071 (0.0007) -[2023-10-09 11:17:03,518][23468] Updated weights for policy 0, policy_version 74663 (0.0008) -[2023-10-09 11:17:03,896][23468] Updated weights for policy 0, policy_version 74673 (0.0008) -[2023-10-09 11:17:04,276][23468] Updated weights for policy 0, policy_version 74683 (0.0011) -[2023-10-09 11:17:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 153354240. Throughput: 0: 1803.1, 1: 1789.3. Samples: 38342182. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) -[2023-10-09 11:17:06,078][22500] Avg episode reward: [(0, '10.350'), (1, '10.200')] -[2023-10-09 11:17:07,312][23469] Updated weights for policy 1, policy_version 75081 (0.0009) -[2023-10-09 11:17:07,677][23469] Updated weights for policy 1, policy_version 75091 (0.0009) -[2023-10-09 11:17:07,957][23468] Updated weights for policy 0, policy_version 74693 (0.0008) -[2023-10-09 11:17:08,049][23469] Updated weights for policy 1, policy_version 75101 (0.0010) -[2023-10-09 11:17:08,335][23468] Updated weights for policy 0, policy_version 74703 (0.0007) -[2023-10-09 11:17:08,709][23468] Updated weights for policy 0, policy_version 74713 (0.0008) -[2023-10-09 11:17:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 153419776. Throughput: 0: 1787.1, 1: 1792.4. Samples: 38363214. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) -[2023-10-09 11:17:11,078][22500] Avg episode reward: [(0, '10.830'), (1, '9.320')] -[2023-10-09 11:17:11,787][23469] Updated weights for policy 1, policy_version 75111 (0.0009) -[2023-10-09 11:17:12,163][23469] Updated weights for policy 1, policy_version 75121 (0.0007) -[2023-10-09 11:17:12,539][23468] Updated weights for policy 0, policy_version 74723 (0.0009) -[2023-10-09 11:17:12,549][23469] Updated weights for policy 1, policy_version 75131 (0.0008) -[2023-10-09 11:17:12,920][23468] Updated weights for policy 0, policy_version 74733 (0.0009) -[2023-10-09 11:17:13,294][23468] Updated weights for policy 0, policy_version 74743 (0.0008) -[2023-10-09 11:17:16,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 153485312. Throughput: 0: 1784.3, 1: 1806.5. Samples: 38385478. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) -[2023-10-09 11:17:16,078][22500] Avg episode reward: [(0, '10.400'), (1, '9.340')] -[2023-10-09 11:17:16,110][23469] Updated weights for policy 1, policy_version 75141 (0.0008) -[2023-10-09 11:17:16,482][23469] Updated weights for policy 1, policy_version 75151 (0.0007) -[2023-10-09 11:17:16,848][23469] Updated weights for policy 1, policy_version 75161 (0.0009) -[2023-10-09 11:17:17,065][23468] Updated weights for policy 0, policy_version 74753 (0.0009) -[2023-10-09 11:17:17,432][23468] Updated weights for policy 0, policy_version 74763 (0.0008) -[2023-10-09 11:17:17,797][23468] Updated weights for policy 0, policy_version 74773 (0.0007) -[2023-10-09 11:17:18,171][23468] Updated weights for policy 0, policy_version 74783 (0.0007) -[2023-10-09 11:17:20,576][23469] Updated weights for policy 1, policy_version 75171 (0.0008) -[2023-10-09 11:17:20,943][23469] Updated weights for policy 1, policy_version 75181 (0.0011) -[2023-10-09 11:17:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 153550848. Throughput: 0: 1783.0, 1: 1798.4. Samples: 38395364. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) -[2023-10-09 11:17:21,078][22500] Avg episode reward: [(0, '10.620'), (1, '8.850')] -[2023-10-09 11:17:21,312][23469] Updated weights for policy 1, policy_version 75191 (0.0010) -[2023-10-09 11:17:22,033][23468] Updated weights for policy 0, policy_version 74793 (0.0007) -[2023-10-09 11:17:22,408][23468] Updated weights for policy 0, policy_version 74803 (0.0007) -[2023-10-09 11:17:22,776][23468] Updated weights for policy 0, policy_version 74813 (0.0007) -[2023-10-09 11:17:25,082][23469] Updated weights for policy 1, policy_version 75201 (0.0008) -[2023-10-09 11:17:25,449][23469] Updated weights for policy 1, policy_version 75211 (0.0008) -[2023-10-09 11:17:25,827][23469] Updated weights for policy 1, policy_version 75221 (0.0009) -[2023-10-09 11:17:26,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 153616384. Throughput: 0: 1780.3, 1: 1801.9. Samples: 38417620. Policy #0 lag: (min: 18.0, avg: 22.3, max: 50.0) -[2023-10-09 11:17:26,078][22500] Avg episode reward: [(0, '10.450'), (1, '8.480')] -[2023-10-09 11:17:26,192][23469] Updated weights for policy 1, policy_version 75231 (0.0010) -[2023-10-09 11:17:26,560][23468] Updated weights for policy 0, policy_version 74823 (0.0008) -[2023-10-09 11:17:26,941][23468] Updated weights for policy 0, policy_version 74833 (0.0009) -[2023-10-09 11:17:27,317][23468] Updated weights for policy 0, policy_version 74843 (0.0007) -[2023-10-09 11:17:29,935][23469] Updated weights for policy 1, policy_version 75241 (0.0008) -[2023-10-09 11:17:30,297][23469] Updated weights for policy 1, policy_version 75251 (0.0008) -[2023-10-09 11:17:30,664][23469] Updated weights for policy 1, policy_version 75261 (0.0007) -[2023-10-09 11:17:31,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 153714688. Throughput: 0: 1787.1, 1: 1803.1. Samples: 38438874. Policy #0 lag: (min: 18.0, avg: 22.3, max: 50.0) -[2023-10-09 11:17:31,078][22500] Avg episode reward: [(0, '10.440'), (1, '8.420')] -[2023-10-09 11:17:31,082][23468] Updated weights for policy 0, policy_version 74853 (0.0009) -[2023-10-09 11:17:31,442][23468] Updated weights for policy 0, policy_version 74863 (0.0009) -[2023-10-09 11:17:31,816][23468] Updated weights for policy 0, policy_version 74873 (0.0008) -[2023-10-09 11:17:34,312][23469] Updated weights for policy 1, policy_version 75271 (0.0008) -[2023-10-09 11:17:34,677][23469] Updated weights for policy 1, policy_version 75281 (0.0008) -[2023-10-09 11:17:35,040][23469] Updated weights for policy 1, policy_version 75291 (0.0008) -[2023-10-09 11:17:35,593][23468] Updated weights for policy 0, policy_version 74883 (0.0010) -[2023-10-09 11:17:35,966][23468] Updated weights for policy 0, policy_version 74893 (0.0008) -[2023-10-09 11:17:36,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 153780224. Throughput: 0: 1774.9, 1: 1806.7. Samples: 38450178. Policy #0 lag: (min: 18.0, avg: 22.3, max: 50.0) -[2023-10-09 11:17:36,078][22500] Avg episode reward: [(0, '10.650'), (1, '9.160')] -[2023-10-09 11:17:36,337][23468] Updated weights for policy 0, policy_version 74903 (0.0008) -[2023-10-09 11:17:38,772][23469] Updated weights for policy 1, policy_version 75301 (0.0010) -[2023-10-09 11:17:39,135][23469] Updated weights for policy 1, policy_version 75311 (0.0011) -[2023-10-09 11:17:39,510][23469] Updated weights for policy 1, policy_version 75321 (0.0008) -[2023-10-09 11:17:40,164][23468] Updated weights for policy 0, policy_version 74913 (0.0008) -[2023-10-09 11:17:40,535][23468] Updated weights for policy 0, policy_version 74923 (0.0011) -[2023-10-09 11:17:40,906][23468] Updated weights for policy 0, policy_version 74933 (0.0007) -[2023-10-09 11:17:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 153845760. Throughput: 0: 1777.0, 1: 1812.3. Samples: 38471196. Policy #0 lag: (min: 18.0, avg: 22.3, max: 50.0) -[2023-10-09 11:17:41,078][22500] Avg episode reward: [(0, '10.760'), (1, '9.070')] -[2023-10-09 11:17:41,282][23468] Updated weights for policy 0, policy_version 74943 (0.0007) -[2023-10-09 11:17:43,252][23469] Updated weights for policy 1, policy_version 75331 (0.0008) -[2023-10-09 11:17:43,628][23469] Updated weights for policy 1, policy_version 75341 (0.0009) -[2023-10-09 11:17:44,002][23469] Updated weights for policy 1, policy_version 75351 (0.0010) -[2023-10-09 11:17:45,021][23468] Updated weights for policy 0, policy_version 74953 (0.0007) -[2023-10-09 11:17:45,397][23468] Updated weights for policy 0, policy_version 74963 (0.0007) -[2023-10-09 11:17:45,780][23468] Updated weights for policy 0, policy_version 74973 (0.0010) -[2023-10-09 11:17:46,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 153944064. Throughput: 0: 1793.1, 1: 1802.0. Samples: 38492700. Policy #0 lag: (min: 18.0, avg: 22.3, max: 50.0) -[2023-10-09 11:17:46,078][22500] Avg episode reward: [(0, '10.900'), (1, '9.380')] -[2023-10-09 11:17:47,832][23469] Updated weights for policy 1, policy_version 75361 (0.0010) -[2023-10-09 11:17:48,206][23469] Updated weights for policy 1, policy_version 75371 (0.0008) -[2023-10-09 11:17:48,574][23469] Updated weights for policy 1, policy_version 75381 (0.0007) -[2023-10-09 11:17:48,937][23469] Updated weights for policy 1, policy_version 75391 (0.0008) -[2023-10-09 11:17:49,398][23468] Updated weights for policy 0, policy_version 74983 (0.0009) -[2023-10-09 11:17:49,766][23468] Updated weights for policy 0, policy_version 74993 (0.0008) -[2023-10-09 11:17:50,134][23468] Updated weights for policy 0, policy_version 75003 (0.0007) -[2023-10-09 11:17:51,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 154009600. Throughput: 0: 1778.4, 1: 1807.6. Samples: 38503550. Policy #0 lag: (min: 18.0, avg: 22.3, max: 50.0) -[2023-10-09 11:17:51,079][22500] Avg episode reward: [(0, '10.920'), (1, '9.380')] -[2023-10-09 11:17:52,806][23469] Updated weights for policy 1, policy_version 75401 (0.0008) -[2023-10-09 11:17:53,179][23469] Updated weights for policy 1, policy_version 75411 (0.0010) -[2023-10-09 11:17:53,544][23469] Updated weights for policy 1, policy_version 75421 (0.0010) -[2023-10-09 11:17:53,884][23468] Updated weights for policy 0, policy_version 75013 (0.0009) -[2023-10-09 11:17:54,249][23468] Updated weights for policy 0, policy_version 75023 (0.0010) -[2023-10-09 11:17:54,626][23468] Updated weights for policy 0, policy_version 75033 (0.0009) -[2023-10-09 11:17:56,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 154075136. Throughput: 0: 1794.3, 1: 1793.5. Samples: 38524666. Policy #0 lag: (min: 18.0, avg: 22.3, max: 50.0) -[2023-10-09 11:17:56,078][22500] Avg episode reward: [(0, '10.430'), (1, '9.820')] -[2023-10-09 11:17:57,384][23469] Updated weights for policy 1, policy_version 75431 (0.0009) -[2023-10-09 11:17:57,770][23469] Updated weights for policy 1, policy_version 75441 (0.0009) -[2023-10-09 11:17:58,135][23469] Updated weights for policy 1, policy_version 75451 (0.0010) -[2023-10-09 11:17:58,361][23468] Updated weights for policy 0, policy_version 75043 (0.0009) -[2023-10-09 11:17:58,736][23468] Updated weights for policy 0, policy_version 75053 (0.0009) -[2023-10-09 11:17:59,111][23468] Updated weights for policy 0, policy_version 75063 (0.0010) -[2023-10-09 11:18:01,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 154140672. Throughput: 0: 1784.9, 1: 1790.2. Samples: 38546360. Policy #0 lag: (min: 18.0, avg: 22.3, max: 50.0) -[2023-10-09 11:18:01,079][22500] Avg episode reward: [(0, '10.140'), (1, '10.110')] -[2023-10-09 11:18:01,727][23469] Updated weights for policy 1, policy_version 75461 (0.0008) -[2023-10-09 11:18:02,096][23469] Updated weights for policy 1, policy_version 75471 (0.0009) -[2023-10-09 11:18:02,475][23469] Updated weights for policy 1, policy_version 75481 (0.0010) -[2023-10-09 11:18:02,893][23468] Updated weights for policy 0, policy_version 75073 (0.0007) -[2023-10-09 11:18:03,275][23468] Updated weights for policy 0, policy_version 75083 (0.0009) -[2023-10-09 11:18:03,655][23468] Updated weights for policy 0, policy_version 75093 (0.0009) -[2023-10-09 11:18:04,016][23468] Updated weights for policy 0, policy_version 75103 (0.0009) -[2023-10-09 11:18:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 154206208. Throughput: 0: 1805.9, 1: 1791.2. Samples: 38557234. Policy #0 lag: (min: 18.0, avg: 22.3, max: 50.0) -[2023-10-09 11:18:06,078][22500] Avg episode reward: [(0, '10.380'), (1, '9.900')] -[2023-10-09 11:18:06,270][23469] Updated weights for policy 1, policy_version 75491 (0.0008) -[2023-10-09 11:18:06,635][23469] Updated weights for policy 1, policy_version 75501 (0.0007) -[2023-10-09 11:18:07,006][23469] Updated weights for policy 1, policy_version 75511 (0.0007) -[2023-10-09 11:18:07,858][23468] Updated weights for policy 0, policy_version 75113 (0.0008) -[2023-10-09 11:18:08,235][23468] Updated weights for policy 0, policy_version 75123 (0.0010) -[2023-10-09 11:18:08,616][23468] Updated weights for policy 0, policy_version 75133 (0.0007) -[2023-10-09 11:18:10,698][23469] Updated weights for policy 1, policy_version 75521 (0.0007) -[2023-10-09 11:18:11,069][23469] Updated weights for policy 1, policy_version 75531 (0.0009) -[2023-10-09 11:18:11,077][22500] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 154271744. Throughput: 0: 1784.8, 1: 1795.7. Samples: 38578744. Policy #0 lag: (min: 18.0, avg: 22.3, max: 50.0) -[2023-10-09 11:18:11,078][22500] Avg episode reward: [(0, '11.240'), (1, '9.700')] -[2023-10-09 11:18:11,431][23469] Updated weights for policy 1, policy_version 75541 (0.0007) -[2023-10-09 11:18:11,802][23469] Updated weights for policy 1, policy_version 75551 (0.0008) -[2023-10-09 11:18:12,248][23468] Updated weights for policy 0, policy_version 75143 (0.0009) -[2023-10-09 11:18:12,622][23468] Updated weights for policy 0, policy_version 75153 (0.0007) -[2023-10-09 11:18:12,999][23468] Updated weights for policy 0, policy_version 75163 (0.0007) -[2023-10-09 11:18:15,611][23469] Updated weights for policy 1, policy_version 75561 (0.0008) -[2023-10-09 11:18:15,978][23469] Updated weights for policy 1, policy_version 75571 (0.0008) -[2023-10-09 11:18:16,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 154337280. Throughput: 0: 1788.2, 1: 1804.9. Samples: 38600562. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:18:16,078][22500] Avg episode reward: [(0, '11.280'), (1, '9.960')] -[2023-10-09 11:18:16,085][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000075168_76972032.pth... -[2023-10-09 11:18:16,117][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000073504_75268096.pth -[2023-10-09 11:18:16,341][23469] Updated weights for policy 1, policy_version 75581 (0.0008) -[2023-10-09 11:18:16,453][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000075584_77398016.pth... -[2023-10-09 11:18:16,483][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000073888_75661312.pth -[2023-10-09 11:18:16,725][23468] Updated weights for policy 0, policy_version 75173 (0.0008) -[2023-10-09 11:18:17,096][23468] Updated weights for policy 0, policy_version 75183 (0.0007) -[2023-10-09 11:18:17,471][23468] Updated weights for policy 0, policy_version 75193 (0.0008) -[2023-10-09 11:18:20,124][23469] Updated weights for policy 1, policy_version 75591 (0.0008) -[2023-10-09 11:18:20,498][23469] Updated weights for policy 1, policy_version 75601 (0.0009) -[2023-10-09 11:18:20,867][23469] Updated weights for policy 1, policy_version 75611 (0.0009) -[2023-10-09 11:18:21,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 154435584. Throughput: 0: 1783.0, 1: 1785.4. Samples: 38610754. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:18:21,078][22500] Avg episode reward: [(0, '11.480'), (1, '9.700')] -[2023-10-09 11:18:21,284][23468] Updated weights for policy 0, policy_version 75203 (0.0008) -[2023-10-09 11:18:21,655][23468] Updated weights for policy 0, policy_version 75213 (0.0008) -[2023-10-09 11:18:22,028][23468] Updated weights for policy 0, policy_version 75223 (0.0008) -[2023-10-09 11:18:24,689][23469] Updated weights for policy 1, policy_version 75621 (0.0011) -[2023-10-09 11:18:25,055][23469] Updated weights for policy 1, policy_version 75631 (0.0010) -[2023-10-09 11:18:25,425][23469] Updated weights for policy 1, policy_version 75641 (0.0008) -[2023-10-09 11:18:25,879][23468] Updated weights for policy 0, policy_version 75233 (0.0008) -[2023-10-09 11:18:26,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 154501120. Throughput: 0: 1785.5, 1: 1803.6. Samples: 38632706. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:18:26,078][22500] Avg episode reward: [(0, '11.130'), (1, '9.200')] -[2023-10-09 11:18:26,244][23468] Updated weights for policy 0, policy_version 75243 (0.0008) -[2023-10-09 11:18:26,629][23468] Updated weights for policy 0, policy_version 75253 (0.0008) -[2023-10-09 11:18:26,991][23468] Updated weights for policy 0, policy_version 75263 (0.0008) -[2023-10-09 11:18:29,158][23469] Updated weights for policy 1, policy_version 75651 (0.0010) -[2023-10-09 11:18:29,525][23469] Updated weights for policy 1, policy_version 75661 (0.0009) -[2023-10-09 11:18:29,886][23469] Updated weights for policy 1, policy_version 75671 (0.0007) -[2023-10-09 11:18:30,721][23468] Updated weights for policy 0, policy_version 75273 (0.0010) -[2023-10-09 11:18:31,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 154566656. Throughput: 0: 1809.4, 1: 1786.1. Samples: 38654498. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:18:31,078][22500] Avg episode reward: [(0, '10.780'), (1, '9.180')] -[2023-10-09 11:18:31,099][23468] Updated weights for policy 0, policy_version 75283 (0.0009) -[2023-10-09 11:18:31,466][23468] Updated weights for policy 0, policy_version 75293 (0.0009) -[2023-10-09 11:18:33,657][23469] Updated weights for policy 1, policy_version 75681 (0.0008) -[2023-10-09 11:18:34,026][23469] Updated weights for policy 1, policy_version 75691 (0.0010) -[2023-10-09 11:18:34,392][23469] Updated weights for policy 1, policy_version 75701 (0.0010) -[2023-10-09 11:18:34,766][23469] Updated weights for policy 1, policy_version 75711 (0.0008) -[2023-10-09 11:18:35,178][23468] Updated weights for policy 0, policy_version 75303 (0.0009) -[2023-10-09 11:18:35,550][23468] Updated weights for policy 0, policy_version 75313 (0.0010) -[2023-10-09 11:18:35,920][23468] Updated weights for policy 0, policy_version 75323 (0.0008) -[2023-10-09 11:18:36,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 154632192. Throughput: 0: 1788.1, 1: 1809.4. Samples: 38665440. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:18:36,078][22500] Avg episode reward: [(0, '10.650'), (1, '8.830')] -[2023-10-09 11:18:38,485][23469] Updated weights for policy 1, policy_version 75721 (0.0007) -[2023-10-09 11:18:38,857][23469] Updated weights for policy 1, policy_version 75731 (0.0007) -[2023-10-09 11:18:39,216][23469] Updated weights for policy 1, policy_version 75741 (0.0009) -[2023-10-09 11:18:39,668][23468] Updated weights for policy 0, policy_version 75333 (0.0008) -[2023-10-09 11:18:40,041][23468] Updated weights for policy 0, policy_version 75343 (0.0007) -[2023-10-09 11:18:40,415][23468] Updated weights for policy 0, policy_version 75353 (0.0007) -[2023-10-09 11:18:41,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 154730496. Throughput: 0: 1806.5, 1: 1798.4. Samples: 38686886. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:18:41,078][22500] Avg episode reward: [(0, '10.210'), (1, '8.860')] -[2023-10-09 11:18:42,997][23469] Updated weights for policy 1, policy_version 75751 (0.0010) -[2023-10-09 11:18:43,393][23469] Updated weights for policy 1, policy_version 75761 (0.0010) -[2023-10-09 11:18:43,769][23469] Updated weights for policy 1, policy_version 75771 (0.0010) -[2023-10-09 11:18:44,099][23468] Updated weights for policy 0, policy_version 75363 (0.0008) -[2023-10-09 11:18:44,477][23468] Updated weights for policy 0, policy_version 75373 (0.0007) -[2023-10-09 11:18:44,855][23468] Updated weights for policy 0, policy_version 75383 (0.0007) -[2023-10-09 11:18:46,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 154796032. Throughput: 0: 1788.7, 1: 1791.6. Samples: 38707472. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:18:46,078][22500] Avg episode reward: [(0, '10.040'), (1, '9.090')] -[2023-10-09 11:18:47,505][23469] Updated weights for policy 1, policy_version 75781 (0.0009) -[2023-10-09 11:18:47,882][23469] Updated weights for policy 1, policy_version 75791 (0.0009) -[2023-10-09 11:18:48,254][23469] Updated weights for policy 1, policy_version 75801 (0.0007) -[2023-10-09 11:18:48,634][23468] Updated weights for policy 0, policy_version 75393 (0.0007) -[2023-10-09 11:18:49,004][23468] Updated weights for policy 0, policy_version 75403 (0.0007) -[2023-10-09 11:18:49,385][23468] Updated weights for policy 0, policy_version 75413 (0.0008) -[2023-10-09 11:18:49,759][23468] Updated weights for policy 0, policy_version 75423 (0.0008) -[2023-10-09 11:18:51,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 154861568. Throughput: 0: 1799.6, 1: 1788.1. Samples: 38718680. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:18:51,078][22500] Avg episode reward: [(0, '10.840'), (1, '8.790')] -[2023-10-09 11:18:52,032][23469] Updated weights for policy 1, policy_version 75811 (0.0007) -[2023-10-09 11:18:52,404][23469] Updated weights for policy 1, policy_version 75821 (0.0007) -[2023-10-09 11:18:52,777][23469] Updated weights for policy 1, policy_version 75831 (0.0009) -[2023-10-09 11:18:53,577][23468] Updated weights for policy 0, policy_version 75433 (0.0008) -[2023-10-09 11:18:53,955][23468] Updated weights for policy 0, policy_version 75443 (0.0007) -[2023-10-09 11:18:54,329][23468] Updated weights for policy 0, policy_version 75453 (0.0008) -[2023-10-09 11:18:56,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 154927104. Throughput: 0: 1792.9, 1: 1785.7. Samples: 38739780. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:18:56,078][22500] Avg episode reward: [(0, '10.080'), (1, '9.670')] -[2023-10-09 11:18:56,573][23469] Updated weights for policy 1, policy_version 75841 (0.0007) -[2023-10-09 11:18:56,956][23469] Updated weights for policy 1, policy_version 75851 (0.0007) -[2023-10-09 11:18:57,330][23469] Updated weights for policy 1, policy_version 75861 (0.0007) -[2023-10-09 11:18:57,706][23469] Updated weights for policy 1, policy_version 75871 (0.0007) -[2023-10-09 11:18:58,026][23468] Updated weights for policy 0, policy_version 75463 (0.0009) -[2023-10-09 11:18:58,393][23468] Updated weights for policy 0, policy_version 75473 (0.0010) -[2023-10-09 11:18:58,778][23468] Updated weights for policy 0, policy_version 75483 (0.0009) -[2023-10-09 11:19:01,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 154992640. Throughput: 0: 1786.9, 1: 1797.3. Samples: 38761854. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:19:01,079][22500] Avg episode reward: [(0, '10.730'), (1, '9.700')] -[2023-10-09 11:19:01,450][23469] Updated weights for policy 1, policy_version 75881 (0.0008) -[2023-10-09 11:19:01,822][23469] Updated weights for policy 1, policy_version 75891 (0.0008) -[2023-10-09 11:19:02,198][23469] Updated weights for policy 1, policy_version 75901 (0.0010) -[2023-10-09 11:19:02,584][23468] Updated weights for policy 0, policy_version 75493 (0.0010) -[2023-10-09 11:19:02,969][23468] Updated weights for policy 0, policy_version 75503 (0.0009) -[2023-10-09 11:19:03,348][23468] Updated weights for policy 0, policy_version 75513 (0.0008) -[2023-10-09 11:19:06,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 155058176. Throughput: 0: 1799.7, 1: 1780.8. Samples: 38771878. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:19:06,078][22500] Avg episode reward: [(0, '10.310'), (1, '10.010')] -[2023-10-09 11:19:06,078][23469] Updated weights for policy 1, policy_version 75911 (0.0008) -[2023-10-09 11:19:06,445][23469] Updated weights for policy 1, policy_version 75921 (0.0007) -[2023-10-09 11:19:06,818][23469] Updated weights for policy 1, policy_version 75931 (0.0009) -[2023-10-09 11:19:07,072][23468] Updated weights for policy 0, policy_version 75523 (0.0009) -[2023-10-09 11:19:07,453][23468] Updated weights for policy 0, policy_version 75533 (0.0009) -[2023-10-09 11:19:07,829][23468] Updated weights for policy 0, policy_version 75543 (0.0009) -[2023-10-09 11:19:10,434][23469] Updated weights for policy 1, policy_version 75941 (0.0007) -[2023-10-09 11:19:10,800][23469] Updated weights for policy 1, policy_version 75951 (0.0008) -[2023-10-09 11:19:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 155123712. Throughput: 0: 1789.2, 1: 1792.2. Samples: 38793870. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:19:11,078][22500] Avg episode reward: [(0, '9.820'), (1, '9.730')] -[2023-10-09 11:19:11,163][23469] Updated weights for policy 1, policy_version 75961 (0.0007) -[2023-10-09 11:19:11,682][23468] Updated weights for policy 0, policy_version 75553 (0.0009) -[2023-10-09 11:19:12,056][23468] Updated weights for policy 0, policy_version 75563 (0.0008) -[2023-10-09 11:19:12,428][23468] Updated weights for policy 0, policy_version 75573 (0.0007) -[2023-10-09 11:19:12,802][23468] Updated weights for policy 0, policy_version 75583 (0.0008) -[2023-10-09 11:19:14,862][23469] Updated weights for policy 1, policy_version 75971 (0.0007) -[2023-10-09 11:19:15,233][23469] Updated weights for policy 1, policy_version 75981 (0.0007) -[2023-10-09 11:19:15,599][23469] Updated weights for policy 1, policy_version 75991 (0.0009) -[2023-10-09 11:19:16,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 155222016. Throughput: 0: 1785.4, 1: 1790.1. Samples: 38815394. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:19:16,078][22500] Avg episode reward: [(0, '9.870'), (1, '9.410')] -[2023-10-09 11:19:16,409][23468] Updated weights for policy 0, policy_version 75593 (0.0008) -[2023-10-09 11:19:16,786][23468] Updated weights for policy 0, policy_version 75603 (0.0007) -[2023-10-09 11:19:17,164][23468] Updated weights for policy 0, policy_version 75613 (0.0008) -[2023-10-09 11:19:19,406][23469] Updated weights for policy 1, policy_version 76001 (0.0008) -[2023-10-09 11:19:19,773][23469] Updated weights for policy 1, policy_version 76011 (0.0008) -[2023-10-09 11:19:20,139][23469] Updated weights for policy 1, policy_version 76021 (0.0008) -[2023-10-09 11:19:20,507][23469] Updated weights for policy 1, policy_version 76031 (0.0009) -[2023-10-09 11:19:21,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 155287552. Throughput: 0: 1784.2, 1: 1785.6. Samples: 38826084. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:19:21,078][22500] Avg episode reward: [(0, '9.620'), (1, '9.880')] -[2023-10-09 11:19:21,089][23468] Updated weights for policy 0, policy_version 75623 (0.0007) -[2023-10-09 11:19:21,468][23468] Updated weights for policy 0, policy_version 75633 (0.0008) -[2023-10-09 11:19:21,847][23468] Updated weights for policy 0, policy_version 75643 (0.0009) -[2023-10-09 11:19:24,131][23469] Updated weights for policy 1, policy_version 76041 (0.0008) -[2023-10-09 11:19:24,494][23469] Updated weights for policy 1, policy_version 76051 (0.0007) -[2023-10-09 11:19:24,871][23469] Updated weights for policy 1, policy_version 76061 (0.0007) -[2023-10-09 11:19:25,709][23468] Updated weights for policy 0, policy_version 75653 (0.0008) -[2023-10-09 11:19:26,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 155353088. Throughput: 0: 1778.5, 1: 1789.7. Samples: 38847458. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:19:26,078][22500] Avg episode reward: [(0, '10.300'), (1, '9.250')] -[2023-10-09 11:19:26,087][23468] Updated weights for policy 0, policy_version 75663 (0.0008) -[2023-10-09 11:19:26,470][23468] Updated weights for policy 0, policy_version 75673 (0.0009) -[2023-10-09 11:19:28,546][23469] Updated weights for policy 1, policy_version 76071 (0.0008) -[2023-10-09 11:19:28,921][23469] Updated weights for policy 1, policy_version 76081 (0.0009) -[2023-10-09 11:19:29,284][23469] Updated weights for policy 1, policy_version 76091 (0.0008) -[2023-10-09 11:19:30,078][23468] Updated weights for policy 0, policy_version 75683 (0.0009) -[2023-10-09 11:19:30,463][23468] Updated weights for policy 0, policy_version 75693 (0.0008) -[2023-10-09 11:19:30,825][23468] Updated weights for policy 0, policy_version 75703 (0.0008) -[2023-10-09 11:19:31,078][22500] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 155418624. Throughput: 0: 1802.6, 1: 1794.6. Samples: 38869344. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:19:31,079][22500] Avg episode reward: [(0, '10.620'), (1, '9.620')] -[2023-10-09 11:19:33,004][23469] Updated weights for policy 1, policy_version 76101 (0.0008) -[2023-10-09 11:19:33,371][23469] Updated weights for policy 1, policy_version 76111 (0.0009) -[2023-10-09 11:19:33,734][23469] Updated weights for policy 1, policy_version 76121 (0.0008) -[2023-10-09 11:19:34,529][23468] Updated weights for policy 0, policy_version 75713 (0.0010) -[2023-10-09 11:19:34,894][23468] Updated weights for policy 0, policy_version 75723 (0.0008) -[2023-10-09 11:19:35,270][23468] Updated weights for policy 0, policy_version 75733 (0.0007) -[2023-10-09 11:19:35,651][23468] Updated weights for policy 0, policy_version 75743 (0.0009) -[2023-10-09 11:19:36,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 155516928. Throughput: 0: 1782.9, 1: 1802.4. Samples: 38880018. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:19:36,078][22500] Avg episode reward: [(0, '10.650'), (1, '9.340')] -[2023-10-09 11:19:37,523][23469] Updated weights for policy 1, policy_version 76131 (0.0007) -[2023-10-09 11:19:37,889][23469] Updated weights for policy 1, policy_version 76141 (0.0007) -[2023-10-09 11:19:38,266][23469] Updated weights for policy 1, policy_version 76151 (0.0009) -[2023-10-09 11:19:39,210][23468] Updated weights for policy 0, policy_version 75753 (0.0010) -[2023-10-09 11:19:39,591][23468] Updated weights for policy 0, policy_version 75763 (0.0011) -[2023-10-09 11:19:39,968][23468] Updated weights for policy 0, policy_version 75773 (0.0008) -[2023-10-09 11:19:41,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 155582464. Throughput: 0: 1810.9, 1: 1793.5. Samples: 38901978. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:19:41,078][22500] Avg episode reward: [(0, '10.760'), (1, '9.610')] -[2023-10-09 11:19:42,127][23469] Updated weights for policy 1, policy_version 76161 (0.0009) -[2023-10-09 11:19:42,493][23469] Updated weights for policy 1, policy_version 76171 (0.0009) -[2023-10-09 11:19:42,865][23469] Updated weights for policy 1, policy_version 76181 (0.0011) -[2023-10-09 11:19:43,236][23469] Updated weights for policy 1, policy_version 76191 (0.0010) -[2023-10-09 11:19:43,601][23468] Updated weights for policy 0, policy_version 75783 (0.0008) -[2023-10-09 11:19:43,984][23468] Updated weights for policy 0, policy_version 75793 (0.0009) -[2023-10-09 11:19:44,356][23468] Updated weights for policy 0, policy_version 75803 (0.0008) -[2023-10-09 11:19:46,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 155648000. Throughput: 0: 1793.3, 1: 1798.0. Samples: 38923464. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:19:46,078][22500] Avg episode reward: [(0, '11.630'), (1, '9.500')] -[2023-10-09 11:19:46,865][23469] Updated weights for policy 1, policy_version 76201 (0.0009) -[2023-10-09 11:19:47,244][23469] Updated weights for policy 1, policy_version 76211 (0.0011) -[2023-10-09 11:19:47,611][23469] Updated weights for policy 1, policy_version 76221 (0.0009) -[2023-10-09 11:19:48,090][23468] Updated weights for policy 0, policy_version 75813 (0.0007) -[2023-10-09 11:19:48,464][23468] Updated weights for policy 0, policy_version 75823 (0.0008) -[2023-10-09 11:19:48,833][23468] Updated weights for policy 0, policy_version 75833 (0.0009) -[2023-10-09 11:19:51,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 155713536. Throughput: 0: 1807.6, 1: 1799.9. Samples: 38934218. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:19:51,078][22500] Avg episode reward: [(0, '11.560'), (1, '9.590')] -[2023-10-09 11:19:51,388][23469] Updated weights for policy 1, policy_version 76231 (0.0007) -[2023-10-09 11:19:51,761][23469] Updated weights for policy 1, policy_version 76241 (0.0007) -[2023-10-09 11:19:52,121][23469] Updated weights for policy 1, policy_version 76251 (0.0008) -[2023-10-09 11:19:52,490][23468] Updated weights for policy 0, policy_version 75843 (0.0010) -[2023-10-09 11:19:52,864][23468] Updated weights for policy 0, policy_version 75853 (0.0009) -[2023-10-09 11:19:53,239][23468] Updated weights for policy 0, policy_version 75863 (0.0008) -[2023-10-09 11:19:55,697][23469] Updated weights for policy 1, policy_version 76261 (0.0009) -[2023-10-09 11:19:56,074][23469] Updated weights for policy 1, policy_version 76271 (0.0008) -[2023-10-09 11:19:56,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 155779072. Throughput: 0: 1799.1, 1: 1807.1. Samples: 38956146. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-10-09 11:19:56,078][22500] Avg episode reward: [(0, '10.910'), (1, '9.450')] -[2023-10-09 11:19:56,430][23469] Updated weights for policy 1, policy_version 76281 (0.0007) -[2023-10-09 11:19:56,866][23468] Updated weights for policy 0, policy_version 75873 (0.0010) -[2023-10-09 11:19:57,236][23468] Updated weights for policy 0, policy_version 75883 (0.0009) -[2023-10-09 11:19:57,616][23468] Updated weights for policy 0, policy_version 75893 (0.0010) -[2023-10-09 11:19:57,994][23468] Updated weights for policy 0, policy_version 75903 (0.0009) -[2023-10-09 11:20:00,103][23469] Updated weights for policy 1, policy_version 76291 (0.0008) -[2023-10-09 11:20:00,463][23469] Updated weights for policy 1, policy_version 76301 (0.0009) -[2023-10-09 11:20:00,839][23469] Updated weights for policy 1, policy_version 76311 (0.0009) -[2023-10-09 11:20:01,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 155844608. Throughput: 0: 1799.7, 1: 1813.1. Samples: 38977970. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-10-09 11:20:01,078][22500] Avg episode reward: [(0, '10.450'), (1, '9.180')] -[2023-10-09 11:20:01,924][23468] Updated weights for policy 0, policy_version 75913 (0.0009) -[2023-10-09 11:20:02,308][23468] Updated weights for policy 0, policy_version 75923 (0.0008) -[2023-10-09 11:20:02,673][23468] Updated weights for policy 0, policy_version 75933 (0.0009) -[2023-10-09 11:20:04,550][23469] Updated weights for policy 1, policy_version 76321 (0.0008) -[2023-10-09 11:20:04,924][23469] Updated weights for policy 1, policy_version 76331 (0.0009) -[2023-10-09 11:20:05,290][23469] Updated weights for policy 1, policy_version 76341 (0.0008) -[2023-10-09 11:20:05,658][23469] Updated weights for policy 1, policy_version 76351 (0.0010) -[2023-10-09 11:20:06,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 155942912. Throughput: 0: 1800.7, 1: 1811.5. Samples: 38988632. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-10-09 11:20:06,078][22500] Avg episode reward: [(0, '10.270'), (1, '9.080')] -[2023-10-09 11:20:06,517][23468] Updated weights for policy 0, policy_version 75943 (0.0007) -[2023-10-09 11:20:06,890][23468] Updated weights for policy 0, policy_version 75953 (0.0009) -[2023-10-09 11:20:07,268][23468] Updated weights for policy 0, policy_version 75963 (0.0010) -[2023-10-09 11:20:09,330][23469] Updated weights for policy 1, policy_version 76361 (0.0009) -[2023-10-09 11:20:09,700][23469] Updated weights for policy 1, policy_version 76371 (0.0011) -[2023-10-09 11:20:10,075][23469] Updated weights for policy 1, policy_version 76381 (0.0008) -[2023-10-09 11:20:11,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 156008448. Throughput: 0: 1802.0, 1: 1815.1. Samples: 39010228. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-10-09 11:20:11,078][22500] Avg episode reward: [(0, '10.040'), (1, '9.500')] -[2023-10-09 11:20:11,110][23468] Updated weights for policy 0, policy_version 75973 (0.0008) -[2023-10-09 11:20:11,484][23468] Updated weights for policy 0, policy_version 75983 (0.0009) -[2023-10-09 11:20:11,866][23468] Updated weights for policy 0, policy_version 75993 (0.0009) -[2023-10-09 11:20:13,788][23469] Updated weights for policy 1, policy_version 76391 (0.0009) -[2023-10-09 11:20:14,159][23469] Updated weights for policy 1, policy_version 76401 (0.0008) -[2023-10-09 11:20:14,537][23469] Updated weights for policy 1, policy_version 76411 (0.0008) -[2023-10-09 11:20:15,485][23468] Updated weights for policy 0, policy_version 76003 (0.0009) -[2023-10-09 11:20:15,858][23468] Updated weights for policy 0, policy_version 76013 (0.0010) -[2023-10-09 11:20:16,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 156073984. Throughput: 0: 1814.9, 1: 1808.0. Samples: 39032372. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-10-09 11:20:16,078][22500] Avg episode reward: [(0, '10.420'), (1, '9.190')] -[2023-10-09 11:20:16,089][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000076416_78249984.pth... -[2023-10-09 11:20:16,123][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000074720_76513280.pth -[2023-10-09 11:20:16,230][23468] Updated weights for policy 0, policy_version 76023 (0.0008) -[2023-10-09 11:20:16,569][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000076032_77856768.pth... -[2023-10-09 11:20:16,598][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000074336_76120064.pth -[2023-10-09 11:20:18,127][23469] Updated weights for policy 1, policy_version 76421 (0.0007) -[2023-10-09 11:20:18,499][23469] Updated weights for policy 1, policy_version 76431 (0.0007) -[2023-10-09 11:20:18,869][23469] Updated weights for policy 1, policy_version 76441 (0.0008) -[2023-10-09 11:20:19,999][23468] Updated weights for policy 0, policy_version 76033 (0.0009) -[2023-10-09 11:20:20,372][23468] Updated weights for policy 0, policy_version 76043 (0.0011) -[2023-10-09 11:20:20,741][23468] Updated weights for policy 0, policy_version 76053 (0.0010) -[2023-10-09 11:20:21,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 156139520. Throughput: 0: 1801.4, 1: 1815.5. Samples: 39042778. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-10-09 11:20:21,079][22500] Avg episode reward: [(0, '10.620'), (1, '9.860')] -[2023-10-09 11:20:21,127][23468] Updated weights for policy 0, policy_version 76063 (0.0011) -[2023-10-09 11:20:22,796][23469] Updated weights for policy 1, policy_version 76451 (0.0010) -[2023-10-09 11:20:23,172][23469] Updated weights for policy 1, policy_version 76461 (0.0008) -[2023-10-09 11:20:23,544][23469] Updated weights for policy 1, policy_version 76471 (0.0008) -[2023-10-09 11:20:24,899][23468] Updated weights for policy 0, policy_version 76073 (0.0008) -[2023-10-09 11:20:25,284][23468] Updated weights for policy 0, policy_version 76083 (0.0008) -[2023-10-09 11:20:25,647][23468] Updated weights for policy 0, policy_version 76093 (0.0007) -[2023-10-09 11:20:26,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 156237824. Throughput: 0: 1800.1, 1: 1809.1. Samples: 39064392. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-10-09 11:20:26,078][22500] Avg episode reward: [(0, '10.010'), (1, '9.720')] -[2023-10-09 11:20:27,292][23469] Updated weights for policy 1, policy_version 76481 (0.0009) -[2023-10-09 11:20:27,667][23469] Updated weights for policy 1, policy_version 76491 (0.0008) -[2023-10-09 11:20:28,043][23469] Updated weights for policy 1, policy_version 76501 (0.0007) -[2023-10-09 11:20:28,411][23469] Updated weights for policy 1, policy_version 76511 (0.0008) -[2023-10-09 11:20:29,298][23468] Updated weights for policy 0, policy_version 76103 (0.0009) -[2023-10-09 11:20:29,675][23468] Updated weights for policy 0, policy_version 76113 (0.0008) -[2023-10-09 11:20:30,040][23468] Updated weights for policy 0, policy_version 76123 (0.0007) -[2023-10-09 11:20:31,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 156303360. Throughput: 0: 1791.2, 1: 1811.5. Samples: 39085588. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-10-09 11:20:31,078][22500] Avg episode reward: [(0, '9.860'), (1, '10.250')] -[2023-10-09 11:20:32,177][23469] Updated weights for policy 1, policy_version 76521 (0.0010) -[2023-10-09 11:20:32,546][23469] Updated weights for policy 1, policy_version 76531 (0.0011) -[2023-10-09 11:20:32,912][23469] Updated weights for policy 1, policy_version 76541 (0.0010) -[2023-10-09 11:20:33,803][23468] Updated weights for policy 0, policy_version 76133 (0.0008) -[2023-10-09 11:20:34,176][23468] Updated weights for policy 0, policy_version 76143 (0.0009) -[2023-10-09 11:20:34,542][23468] Updated weights for policy 0, policy_version 76153 (0.0007) -[2023-10-09 11:20:36,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 156368896. Throughput: 0: 1804.4, 1: 1807.2. Samples: 39096738. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-10-09 11:20:36,078][22500] Avg episode reward: [(0, '9.500'), (1, '10.240')] -[2023-10-09 11:20:36,617][23469] Updated weights for policy 1, policy_version 76551 (0.0010) -[2023-10-09 11:20:36,988][23469] Updated weights for policy 1, policy_version 76561 (0.0011) -[2023-10-09 11:20:37,363][23469] Updated weights for policy 1, policy_version 76571 (0.0009) -[2023-10-09 11:20:38,277][23468] Updated weights for policy 0, policy_version 76163 (0.0007) -[2023-10-09 11:20:38,656][23468] Updated weights for policy 0, policy_version 76173 (0.0009) -[2023-10-09 11:20:39,022][23468] Updated weights for policy 0, policy_version 76183 (0.0007) -[2023-10-09 11:20:41,021][23469] Updated weights for policy 1, policy_version 76581 (0.0008) -[2023-10-09 11:20:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 156434432. Throughput: 0: 1792.6, 1: 1805.7. Samples: 39118068. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-10-09 11:20:41,078][22500] Avg episode reward: [(0, '10.030'), (1, '9.830')] -[2023-10-09 11:20:41,390][23469] Updated weights for policy 1, policy_version 76591 (0.0010) -[2023-10-09 11:20:41,760][23469] Updated weights for policy 1, policy_version 76601 (0.0008) -[2023-10-09 11:20:42,851][23468] Updated weights for policy 0, policy_version 76193 (0.0008) -[2023-10-09 11:20:43,229][23468] Updated weights for policy 0, policy_version 76203 (0.0008) -[2023-10-09 11:20:43,604][23468] Updated weights for policy 0, policy_version 76213 (0.0009) -[2023-10-09 11:20:43,980][23468] Updated weights for policy 0, policy_version 76223 (0.0009) -[2023-10-09 11:20:45,444][23469] Updated weights for policy 1, policy_version 76611 (0.0008) -[2023-10-09 11:20:45,822][23469] Updated weights for policy 1, policy_version 76621 (0.0009) -[2023-10-09 11:20:46,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 156499968. Throughput: 0: 1782.5, 1: 1812.7. Samples: 39139754. Policy #0 lag: (min: 8.0, avg: 33.6, max: 40.0) -[2023-10-09 11:20:46,078][22500] Avg episode reward: [(0, '10.420'), (1, '9.600')] -[2023-10-09 11:20:46,190][23469] Updated weights for policy 1, policy_version 76631 (0.0008) -[2023-10-09 11:20:47,791][23468] Updated weights for policy 0, policy_version 76233 (0.0008) -[2023-10-09 11:20:48,170][23468] Updated weights for policy 0, policy_version 76243 (0.0009) -[2023-10-09 11:20:48,533][23468] Updated weights for policy 0, policy_version 76253 (0.0010) -[2023-10-09 11:20:50,020][23469] Updated weights for policy 1, policy_version 76641 (0.0011) -[2023-10-09 11:20:50,390][23469] Updated weights for policy 1, policy_version 76651 (0.0008) -[2023-10-09 11:20:50,759][23469] Updated weights for policy 1, policy_version 76661 (0.0008) -[2023-10-09 11:20:51,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 156565504. Throughput: 0: 1790.6, 1: 1801.8. Samples: 39150292. Policy #0 lag: (min: 8.0, avg: 33.6, max: 40.0) -[2023-10-09 11:20:51,078][22500] Avg episode reward: [(0, '10.630'), (1, '9.390')] -[2023-10-09 11:20:51,124][23469] Updated weights for policy 1, policy_version 76671 (0.0009) -[2023-10-09 11:20:52,281][23468] Updated weights for policy 0, policy_version 76263 (0.0011) -[2023-10-09 11:20:52,648][23468] Updated weights for policy 0, policy_version 76273 (0.0009) -[2023-10-09 11:20:53,018][23468] Updated weights for policy 0, policy_version 76283 (0.0011) -[2023-10-09 11:20:54,893][23469] Updated weights for policy 1, policy_version 76681 (0.0010) -[2023-10-09 11:20:55,273][23469] Updated weights for policy 1, policy_version 76691 (0.0009) -[2023-10-09 11:20:55,640][23469] Updated weights for policy 1, policy_version 76701 (0.0010) -[2023-10-09 11:20:56,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 156663808. Throughput: 0: 1779.7, 1: 1808.5. Samples: 39171698. Policy #0 lag: (min: 8.0, avg: 33.6, max: 40.0) -[2023-10-09 11:20:56,078][22500] Avg episode reward: [(0, '10.800'), (1, '9.550')] -[2023-10-09 11:20:56,707][23468] Updated weights for policy 0, policy_version 76293 (0.0009) -[2023-10-09 11:20:57,078][23468] Updated weights for policy 0, policy_version 76303 (0.0007) -[2023-10-09 11:20:57,456][23468] Updated weights for policy 0, policy_version 76313 (0.0007) -[2023-10-09 11:20:59,403][23469] Updated weights for policy 1, policy_version 76711 (0.0010) -[2023-10-09 11:20:59,768][23469] Updated weights for policy 1, policy_version 76721 (0.0009) -[2023-10-09 11:21:00,136][23469] Updated weights for policy 1, policy_version 76731 (0.0009) -[2023-10-09 11:21:01,078][22500] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 156729344. Throughput: 0: 1779.1, 1: 1790.0. Samples: 39192982. Policy #0 lag: (min: 8.0, avg: 33.6, max: 40.0) -[2023-10-09 11:21:01,079][22500] Avg episode reward: [(0, '10.060'), (1, '9.700')] -[2023-10-09 11:21:01,155][23468] Updated weights for policy 0, policy_version 76323 (0.0009) -[2023-10-09 11:21:01,524][23468] Updated weights for policy 0, policy_version 76333 (0.0009) -[2023-10-09 11:21:01,900][23468] Updated weights for policy 0, policy_version 76343 (0.0009) -[2023-10-09 11:21:03,757][23469] Updated weights for policy 1, policy_version 76741 (0.0009) -[2023-10-09 11:21:04,127][23469] Updated weights for policy 1, policy_version 76751 (0.0009) -[2023-10-09 11:21:04,487][23469] Updated weights for policy 1, policy_version 76761 (0.0009) -[2023-10-09 11:21:05,624][23468] Updated weights for policy 0, policy_version 76353 (0.0010) -[2023-10-09 11:21:06,011][23468] Updated weights for policy 0, policy_version 76363 (0.0007) -[2023-10-09 11:21:06,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 156794880. Throughput: 0: 1778.3, 1: 1802.8. Samples: 39203926. Policy #0 lag: (min: 8.0, avg: 33.6, max: 40.0) -[2023-10-09 11:21:06,078][22500] Avg episode reward: [(0, '10.400'), (1, '9.850')] -[2023-10-09 11:21:06,377][23468] Updated weights for policy 0, policy_version 76373 (0.0010) -[2023-10-09 11:21:06,758][23468] Updated weights for policy 0, policy_version 76383 (0.0007) -[2023-10-09 11:21:08,223][23469] Updated weights for policy 1, policy_version 76771 (0.0011) -[2023-10-09 11:21:08,586][23469] Updated weights for policy 1, policy_version 76781 (0.0010) -[2023-10-09 11:21:08,955][23469] Updated weights for policy 1, policy_version 76791 (0.0010) -[2023-10-09 11:21:10,430][23468] Updated weights for policy 0, policy_version 76393 (0.0008) -[2023-10-09 11:21:10,811][23468] Updated weights for policy 0, policy_version 76403 (0.0008) -[2023-10-09 11:21:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 156860416. Throughput: 0: 1785.0, 1: 1790.4. Samples: 39225288. Policy #0 lag: (min: 8.0, avg: 33.6, max: 40.0) -[2023-10-09 11:21:11,078][22500] Avg episode reward: [(0, '9.910'), (1, '9.310')] -[2023-10-09 11:21:11,181][23468] Updated weights for policy 0, policy_version 76413 (0.0007) -[2023-10-09 11:21:12,675][23469] Updated weights for policy 1, policy_version 76801 (0.0009) -[2023-10-09 11:21:13,043][23469] Updated weights for policy 1, policy_version 76811 (0.0007) -[2023-10-09 11:21:13,415][23469] Updated weights for policy 1, policy_version 76821 (0.0007) -[2023-10-09 11:21:13,787][23469] Updated weights for policy 1, policy_version 76831 (0.0008) -[2023-10-09 11:21:14,927][23468] Updated weights for policy 0, policy_version 76423 (0.0009) -[2023-10-09 11:21:15,296][23468] Updated weights for policy 0, policy_version 76433 (0.0009) -[2023-10-09 11:21:15,681][23468] Updated weights for policy 0, policy_version 76443 (0.0009) -[2023-10-09 11:21:16,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 156958720. Throughput: 0: 1799.6, 1: 1790.8. Samples: 39247154. Policy #0 lag: (min: 8.0, avg: 33.6, max: 40.0) -[2023-10-09 11:21:16,078][22500] Avg episode reward: [(0, '10.080'), (1, '8.740')] -[2023-10-09 11:21:17,534][23469] Updated weights for policy 1, policy_version 76841 (0.0008) -[2023-10-09 11:21:17,907][23469] Updated weights for policy 1, policy_version 76851 (0.0007) -[2023-10-09 11:21:18,280][23469] Updated weights for policy 1, policy_version 76861 (0.0010) -[2023-10-09 11:21:19,332][23468] Updated weights for policy 0, policy_version 76453 (0.0009) -[2023-10-09 11:21:19,716][23468] Updated weights for policy 0, policy_version 76463 (0.0007) -[2023-10-09 11:21:20,093][23468] Updated weights for policy 0, policy_version 76473 (0.0007) -[2023-10-09 11:21:21,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 157024256. Throughput: 0: 1783.6, 1: 1793.2. Samples: 39257692. Policy #0 lag: (min: 8.0, avg: 33.6, max: 40.0) -[2023-10-09 11:21:21,078][22500] Avg episode reward: [(0, '10.290'), (1, '8.810')] -[2023-10-09 11:21:22,064][23469] Updated weights for policy 1, policy_version 76871 (0.0010) -[2023-10-09 11:21:22,431][23469] Updated weights for policy 1, policy_version 76881 (0.0007) -[2023-10-09 11:21:22,800][23469] Updated weights for policy 1, policy_version 76891 (0.0010) -[2023-10-09 11:21:23,913][23468] Updated weights for policy 0, policy_version 76483 (0.0008) -[2023-10-09 11:21:24,290][23468] Updated weights for policy 0, policy_version 76493 (0.0008) -[2023-10-09 11:21:24,659][23468] Updated weights for policy 0, policy_version 76503 (0.0010) -[2023-10-09 11:21:26,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 157089792. Throughput: 0: 1796.5, 1: 1781.2. Samples: 39279064. Policy #0 lag: (min: 8.0, avg: 33.6, max: 40.0) -[2023-10-09 11:21:26,078][22500] Avg episode reward: [(0, '10.420'), (1, '8.890')] -[2023-10-09 11:21:26,583][23469] Updated weights for policy 1, policy_version 76901 (0.0011) -[2023-10-09 11:21:26,957][23469] Updated weights for policy 1, policy_version 76911 (0.0010) -[2023-10-09 11:21:27,319][23469] Updated weights for policy 1, policy_version 76921 (0.0010) -[2023-10-09 11:21:28,349][23468] Updated weights for policy 0, policy_version 76513 (0.0009) -[2023-10-09 11:21:28,716][23468] Updated weights for policy 0, policy_version 76523 (0.0011) -[2023-10-09 11:21:29,085][23468] Updated weights for policy 0, policy_version 76533 (0.0009) -[2023-10-09 11:21:29,469][23468] Updated weights for policy 0, policy_version 76543 (0.0007) -[2023-10-09 11:21:31,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 157155328. Throughput: 0: 1785.6, 1: 1789.3. Samples: 39300626. Policy #0 lag: (min: 8.0, avg: 33.6, max: 40.0) -[2023-10-09 11:21:31,079][22500] Avg episode reward: [(0, '10.600'), (1, '9.250')] -[2023-10-09 11:21:31,119][23469] Updated weights for policy 1, policy_version 76931 (0.0009) -[2023-10-09 11:21:31,475][23469] Updated weights for policy 1, policy_version 76941 (0.0008) -[2023-10-09 11:21:31,847][23469] Updated weights for policy 1, policy_version 76951 (0.0010) -[2023-10-09 11:21:33,372][23468] Updated weights for policy 0, policy_version 76553 (0.0008) -[2023-10-09 11:21:33,755][23468] Updated weights for policy 0, policy_version 76563 (0.0008) -[2023-10-09 11:21:34,121][23468] Updated weights for policy 0, policy_version 76573 (0.0010) -[2023-10-09 11:21:35,664][23469] Updated weights for policy 1, policy_version 76961 (0.0008) -[2023-10-09 11:21:36,044][23469] Updated weights for policy 1, policy_version 76971 (0.0011) -[2023-10-09 11:21:36,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 157220864. Throughput: 0: 1803.5, 1: 1776.0. Samples: 39311366. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:21:36,079][22500] Avg episode reward: [(0, '10.790'), (1, '9.100')] -[2023-10-09 11:21:36,402][23469] Updated weights for policy 1, policy_version 76981 (0.0011) -[2023-10-09 11:21:36,778][23469] Updated weights for policy 1, policy_version 76991 (0.0009) -[2023-10-09 11:21:37,950][23468] Updated weights for policy 0, policy_version 76583 (0.0010) -[2023-10-09 11:21:38,329][23468] Updated weights for policy 0, policy_version 76593 (0.0011) -[2023-10-09 11:21:38,707][23468] Updated weights for policy 0, policy_version 76603 (0.0010) -[2023-10-09 11:21:40,535][23469] Updated weights for policy 1, policy_version 77001 (0.0010) -[2023-10-09 11:21:40,906][23469] Updated weights for policy 1, policy_version 77011 (0.0011) -[2023-10-09 11:21:41,077][22500] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 157286400. Throughput: 0: 1785.3, 1: 1783.0. Samples: 39332270. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:21:41,078][22500] Avg episode reward: [(0, '11.150'), (1, '9.430')] -[2023-10-09 11:21:41,271][23469] Updated weights for policy 1, policy_version 77021 (0.0007) -[2023-10-09 11:21:42,487][23468] Updated weights for policy 0, policy_version 76613 (0.0010) -[2023-10-09 11:21:42,857][23468] Updated weights for policy 0, policy_version 76623 (0.0010) -[2023-10-09 11:21:43,216][23468] Updated weights for policy 0, policy_version 76633 (0.0010) -[2023-10-09 11:21:45,185][23469] Updated weights for policy 1, policy_version 77031 (0.0008) -[2023-10-09 11:21:45,572][23469] Updated weights for policy 1, policy_version 77041 (0.0009) -[2023-10-09 11:21:45,944][23469] Updated weights for policy 1, policy_version 77051 (0.0008) -[2023-10-09 11:21:46,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 157351936. Throughput: 0: 1777.1, 1: 1788.4. Samples: 39353428. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:21:46,078][22500] Avg episode reward: [(0, '11.060'), (1, '9.840')] -[2023-10-09 11:21:46,984][23468] Updated weights for policy 0, policy_version 76643 (0.0010) -[2023-10-09 11:21:47,358][23468] Updated weights for policy 0, policy_version 76653 (0.0008) -[2023-10-09 11:21:47,730][23468] Updated weights for policy 0, policy_version 76663 (0.0009) -[2023-10-09 11:21:49,755][23469] Updated weights for policy 1, policy_version 77061 (0.0009) -[2023-10-09 11:21:50,127][23469] Updated weights for policy 1, policy_version 77071 (0.0009) -[2023-10-09 11:21:50,490][23469] Updated weights for policy 1, policy_version 77081 (0.0010) -[2023-10-09 11:21:51,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 157450240. Throughput: 0: 1780.1, 1: 1778.5. Samples: 39364066. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:21:51,078][22500] Avg episode reward: [(0, '11.220'), (1, '9.760')] -[2023-10-09 11:21:51,568][23468] Updated weights for policy 0, policy_version 76673 (0.0009) -[2023-10-09 11:21:51,936][23468] Updated weights for policy 0, policy_version 76683 (0.0010) -[2023-10-09 11:21:52,311][23468] Updated weights for policy 0, policy_version 76693 (0.0008) -[2023-10-09 11:21:52,699][23468] Updated weights for policy 0, policy_version 76703 (0.0009) -[2023-10-09 11:21:54,173][23469] Updated weights for policy 1, policy_version 77091 (0.0009) -[2023-10-09 11:21:54,534][23469] Updated weights for policy 1, policy_version 77101 (0.0009) -[2023-10-09 11:21:54,901][23469] Updated weights for policy 1, policy_version 77111 (0.0007) -[2023-10-09 11:21:56,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 157515776. Throughput: 0: 1774.0, 1: 1790.0. Samples: 39385672. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:21:56,078][22500] Avg episode reward: [(0, '10.470'), (1, '9.260')] -[2023-10-09 11:21:56,506][23468] Updated weights for policy 0, policy_version 76713 (0.0008) -[2023-10-09 11:21:56,883][23468] Updated weights for policy 0, policy_version 76723 (0.0007) -[2023-10-09 11:21:57,253][23468] Updated weights for policy 0, policy_version 76733 (0.0008) -[2023-10-09 11:21:58,549][23469] Updated weights for policy 1, policy_version 77121 (0.0008) -[2023-10-09 11:21:58,919][23469] Updated weights for policy 1, policy_version 77131 (0.0009) -[2023-10-09 11:21:59,293][23469] Updated weights for policy 1, policy_version 77141 (0.0010) -[2023-10-09 11:21:59,665][23469] Updated weights for policy 1, policy_version 77151 (0.0007) -[2023-10-09 11:22:00,978][23468] Updated weights for policy 0, policy_version 76743 (0.0009) -[2023-10-09 11:22:01,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 157581312. Throughput: 0: 1793.1, 1: 1779.4. Samples: 39407914. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:22:01,078][22500] Avg episode reward: [(0, '9.970'), (1, '9.730')] -[2023-10-09 11:22:01,360][23468] Updated weights for policy 0, policy_version 76753 (0.0010) -[2023-10-09 11:22:01,735][23468] Updated weights for policy 0, policy_version 76763 (0.0011) -[2023-10-09 11:22:03,550][23469] Updated weights for policy 1, policy_version 77161 (0.0007) -[2023-10-09 11:22:03,923][23469] Updated weights for policy 1, policy_version 77171 (0.0008) -[2023-10-09 11:22:04,287][23469] Updated weights for policy 1, policy_version 77181 (0.0008) -[2023-10-09 11:22:05,496][23468] Updated weights for policy 0, policy_version 76773 (0.0010) -[2023-10-09 11:22:05,877][23468] Updated weights for policy 0, policy_version 76783 (0.0010) -[2023-10-09 11:22:06,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 157646848. Throughput: 0: 1770.1, 1: 1802.5. Samples: 39418460. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:22:06,078][22500] Avg episode reward: [(0, '9.750'), (1, '9.050')] -[2023-10-09 11:22:06,246][23468] Updated weights for policy 0, policy_version 76793 (0.0010) -[2023-10-09 11:22:08,075][23469] Updated weights for policy 1, policy_version 77191 (0.0007) -[2023-10-09 11:22:08,446][23469] Updated weights for policy 1, policy_version 77201 (0.0009) -[2023-10-09 11:22:08,819][23469] Updated weights for policy 1, policy_version 77211 (0.0009) -[2023-10-09 11:22:09,955][23468] Updated weights for policy 0, policy_version 76803 (0.0009) -[2023-10-09 11:22:10,328][23468] Updated weights for policy 0, policy_version 76813 (0.0010) -[2023-10-09 11:22:10,709][23468] Updated weights for policy 0, policy_version 76823 (0.0007) -[2023-10-09 11:22:11,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14440.2). Total num frames: 157745152. Throughput: 0: 1790.8, 1: 1787.9. Samples: 39440102. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:22:11,078][22500] Avg episode reward: [(0, '9.520'), (1, '9.240')] -[2023-10-09 11:22:12,551][23469] Updated weights for policy 1, policy_version 77221 (0.0008) -[2023-10-09 11:22:12,923][23469] Updated weights for policy 1, policy_version 77231 (0.0008) -[2023-10-09 11:22:13,289][23469] Updated weights for policy 1, policy_version 77241 (0.0008) -[2023-10-09 11:22:14,441][23468] Updated weights for policy 0, policy_version 76833 (0.0008) -[2023-10-09 11:22:14,809][23468] Updated weights for policy 0, policy_version 76843 (0.0008) -[2023-10-09 11:22:15,189][23468] Updated weights for policy 0, policy_version 76853 (0.0009) -[2023-10-09 11:22:15,560][23468] Updated weights for policy 0, policy_version 76863 (0.0008) -[2023-10-09 11:22:16,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 157810688. Throughput: 0: 1786.5, 1: 1794.8. Samples: 39461784. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:22:16,078][22500] Avg episode reward: [(0, '10.300'), (1, '9.140')] -[2023-10-09 11:22:16,086][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000077248_79101952.pth... -[2023-10-09 11:22:16,087][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000076864_78708736.pth... -[2023-10-09 11:22:16,116][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000075584_77398016.pth -[2023-10-09 11:22:16,123][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000075168_76972032.pth -[2023-10-09 11:22:16,907][23469] Updated weights for policy 1, policy_version 77251 (0.0008) -[2023-10-09 11:22:17,280][23469] Updated weights for policy 1, policy_version 77261 (0.0009) -[2023-10-09 11:22:17,659][23469] Updated weights for policy 1, policy_version 77271 (0.0007) -[2023-10-09 11:22:19,395][23468] Updated weights for policy 0, policy_version 76873 (0.0010) -[2023-10-09 11:22:19,764][23468] Updated weights for policy 0, policy_version 76883 (0.0009) -[2023-10-09 11:22:20,140][23468] Updated weights for policy 0, policy_version 76893 (0.0008) -[2023-10-09 11:22:21,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 157876224. Throughput: 0: 1787.7, 1: 1795.1. Samples: 39472592. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:22:21,078][22500] Avg episode reward: [(0, '10.560'), (1, '9.040')] -[2023-10-09 11:22:21,453][23469] Updated weights for policy 1, policy_version 77281 (0.0008) -[2023-10-09 11:22:21,823][23469] Updated weights for policy 1, policy_version 77291 (0.0010) -[2023-10-09 11:22:22,200][23469] Updated weights for policy 1, policy_version 77301 (0.0009) -[2023-10-09 11:22:22,580][23469] Updated weights for policy 1, policy_version 77311 (0.0010) -[2023-10-09 11:22:24,112][23468] Updated weights for policy 0, policy_version 76903 (0.0008) -[2023-10-09 11:22:24,489][23468] Updated weights for policy 0, policy_version 76913 (0.0008) -[2023-10-09 11:22:24,861][23468] Updated weights for policy 0, policy_version 76923 (0.0009) -[2023-10-09 11:22:26,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 157941760. Throughput: 0: 1798.1, 1: 1799.5. Samples: 39494164. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:22:26,078][22500] Avg episode reward: [(0, '10.370'), (1, '9.790')] -[2023-10-09 11:22:26,337][23469] Updated weights for policy 1, policy_version 77321 (0.0008) -[2023-10-09 11:22:26,716][23469] Updated weights for policy 1, policy_version 77331 (0.0010) -[2023-10-09 11:22:27,088][23469] Updated weights for policy 1, policy_version 77341 (0.0008) -[2023-10-09 11:22:28,448][23468] Updated weights for policy 0, policy_version 76933 (0.0008) -[2023-10-09 11:22:28,831][23468] Updated weights for policy 0, policy_version 76943 (0.0008) -[2023-10-09 11:22:29,202][23468] Updated weights for policy 0, policy_version 76953 (0.0007) -[2023-10-09 11:22:30,881][23469] Updated weights for policy 1, policy_version 77351 (0.0008) -[2023-10-09 11:22:31,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 158007296. Throughput: 0: 1782.2, 1: 1816.1. Samples: 39515350. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:22:31,078][22500] Avg episode reward: [(0, '10.050'), (1, '10.070')] -[2023-10-09 11:22:31,264][23469] Updated weights for policy 1, policy_version 77361 (0.0009) -[2023-10-09 11:22:31,633][23469] Updated weights for policy 1, policy_version 77371 (0.0008) -[2023-10-09 11:22:32,936][23468] Updated weights for policy 0, policy_version 76963 (0.0009) -[2023-10-09 11:22:33,307][23468] Updated weights for policy 0, policy_version 76973 (0.0009) -[2023-10-09 11:22:33,671][23468] Updated weights for policy 0, policy_version 76983 (0.0007) -[2023-10-09 11:22:35,190][23469] Updated weights for policy 1, policy_version 77381 (0.0009) -[2023-10-09 11:22:35,563][23469] Updated weights for policy 1, policy_version 77391 (0.0009) -[2023-10-09 11:22:35,920][23469] Updated weights for policy 1, policy_version 77401 (0.0007) -[2023-10-09 11:22:36,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 158072832. Throughput: 0: 1802.5, 1: 1805.5. Samples: 39526426. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:22:36,078][22500] Avg episode reward: [(0, '9.940'), (1, '10.160')] -[2023-10-09 11:22:37,431][23468] Updated weights for policy 0, policy_version 76993 (0.0008) -[2023-10-09 11:22:37,810][23468] Updated weights for policy 0, policy_version 77003 (0.0008) -[2023-10-09 11:22:38,182][23468] Updated weights for policy 0, policy_version 77013 (0.0009) -[2023-10-09 11:22:38,551][23468] Updated weights for policy 0, policy_version 77023 (0.0010) -[2023-10-09 11:22:39,767][23469] Updated weights for policy 1, policy_version 77411 (0.0009) -[2023-10-09 11:22:40,138][23469] Updated weights for policy 1, policy_version 77421 (0.0007) -[2023-10-09 11:22:40,501][23469] Updated weights for policy 1, policy_version 77431 (0.0008) -[2023-10-09 11:22:41,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 158171136. Throughput: 0: 1784.8, 1: 1814.7. Samples: 39547648. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:22:41,079][22500] Avg episode reward: [(0, '9.310'), (1, '10.090')] -[2023-10-09 11:22:42,370][23468] Updated weights for policy 0, policy_version 77033 (0.0009) -[2023-10-09 11:22:42,741][23468] Updated weights for policy 0, policy_version 77043 (0.0011) -[2023-10-09 11:22:43,111][23468] Updated weights for policy 0, policy_version 77053 (0.0011) -[2023-10-09 11:22:44,294][23469] Updated weights for policy 1, policy_version 77441 (0.0010) -[2023-10-09 11:22:44,664][23469] Updated weights for policy 1, policy_version 77451 (0.0007) -[2023-10-09 11:22:45,031][23469] Updated weights for policy 1, policy_version 77461 (0.0010) -[2023-10-09 11:22:45,397][23469] Updated weights for policy 1, policy_version 77471 (0.0010) -[2023-10-09 11:22:46,078][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 158236672. Throughput: 0: 1779.4, 1: 1792.6. Samples: 39568654. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:22:46,079][22500] Avg episode reward: [(0, '9.340'), (1, '9.610')] -[2023-10-09 11:22:46,849][23468] Updated weights for policy 0, policy_version 77063 (0.0008) -[2023-10-09 11:22:47,221][23468] Updated weights for policy 0, policy_version 77073 (0.0008) -[2023-10-09 11:22:47,596][23468] Updated weights for policy 0, policy_version 77083 (0.0009) -[2023-10-09 11:22:49,066][23469] Updated weights for policy 1, policy_version 77481 (0.0009) -[2023-10-09 11:22:49,434][23469] Updated weights for policy 1, policy_version 77491 (0.0008) -[2023-10-09 11:22:49,805][23469] Updated weights for policy 1, policy_version 77501 (0.0007) -[2023-10-09 11:22:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 158302208. Throughput: 0: 1782.4, 1: 1805.2. Samples: 39579902. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:22:51,079][22500] Avg episode reward: [(0, '9.560'), (1, '9.430')] -[2023-10-09 11:22:51,436][23468] Updated weights for policy 0, policy_version 77093 (0.0007) -[2023-10-09 11:22:51,798][23468] Updated weights for policy 0, policy_version 77103 (0.0009) -[2023-10-09 11:22:52,180][23468] Updated weights for policy 0, policy_version 77113 (0.0010) -[2023-10-09 11:22:53,656][23469] Updated weights for policy 1, policy_version 77511 (0.0009) -[2023-10-09 11:22:54,013][23469] Updated weights for policy 1, policy_version 77521 (0.0007) -[2023-10-09 11:22:54,390][23469] Updated weights for policy 1, policy_version 77531 (0.0009) -[2023-10-09 11:22:55,848][23468] Updated weights for policy 0, policy_version 77123 (0.0009) -[2023-10-09 11:22:56,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 158367744. Throughput: 0: 1779.7, 1: 1790.3. Samples: 39600750. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:22:56,078][22500] Avg episode reward: [(0, '10.450'), (1, '9.520')] -[2023-10-09 11:22:56,232][23468] Updated weights for policy 0, policy_version 77133 (0.0010) -[2023-10-09 11:22:56,601][23468] Updated weights for policy 0, policy_version 77143 (0.0012) -[2023-10-09 11:22:58,086][23469] Updated weights for policy 1, policy_version 77541 (0.0012) -[2023-10-09 11:22:58,457][23469] Updated weights for policy 1, policy_version 77551 (0.0009) -[2023-10-09 11:22:58,834][23469] Updated weights for policy 1, policy_version 77561 (0.0008) -[2023-10-09 11:23:00,416][23468] Updated weights for policy 0, policy_version 77153 (0.0010) -[2023-10-09 11:23:00,787][23468] Updated weights for policy 0, policy_version 77163 (0.0009) -[2023-10-09 11:23:01,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 158433280. Throughput: 0: 1800.7, 1: 1787.0. Samples: 39623230. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:23:01,078][22500] Avg episode reward: [(0, '10.780'), (1, '9.400')] -[2023-10-09 11:23:01,172][23468] Updated weights for policy 0, policy_version 77173 (0.0008) -[2023-10-09 11:23:01,540][23468] Updated weights for policy 0, policy_version 77183 (0.0010) -[2023-10-09 11:23:02,669][23469] Updated weights for policy 1, policy_version 77571 (0.0010) -[2023-10-09 11:23:03,027][23469] Updated weights for policy 1, policy_version 77581 (0.0008) -[2023-10-09 11:23:03,395][23469] Updated weights for policy 1, policy_version 77591 (0.0009) -[2023-10-09 11:23:05,295][23468] Updated weights for policy 0, policy_version 77193 (0.0008) -[2023-10-09 11:23:05,668][23468] Updated weights for policy 0, policy_version 77203 (0.0008) -[2023-10-09 11:23:06,039][23468] Updated weights for policy 0, policy_version 77213 (0.0011) -[2023-10-09 11:23:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 158498816. Throughput: 0: 1776.3, 1: 1788.7. Samples: 39633016. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:23:06,078][22500] Avg episode reward: [(0, '11.880'), (1, '9.750')] -[2023-10-09 11:23:06,149][23265] Saving new best policy, reward=11.880! -[2023-10-09 11:23:07,088][23469] Updated weights for policy 1, policy_version 77601 (0.0009) -[2023-10-09 11:23:07,450][23469] Updated weights for policy 1, policy_version 77611 (0.0007) -[2023-10-09 11:23:07,817][23469] Updated weights for policy 1, policy_version 77621 (0.0008) -[2023-10-09 11:23:08,175][23469] Updated weights for policy 1, policy_version 77631 (0.0008) -[2023-10-09 11:23:09,749][23468] Updated weights for policy 0, policy_version 77223 (0.0008) -[2023-10-09 11:23:10,123][23468] Updated weights for policy 0, policy_version 77233 (0.0009) -[2023-10-09 11:23:10,498][23468] Updated weights for policy 0, policy_version 77243 (0.0009) -[2023-10-09 11:23:11,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 158597120. Throughput: 0: 1797.6, 1: 1791.2. Samples: 39655662. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:23:11,078][22500] Avg episode reward: [(0, '11.210'), (1, '9.660')] -[2023-10-09 11:23:11,797][23469] Updated weights for policy 1, policy_version 77641 (0.0009) -[2023-10-09 11:23:12,172][23469] Updated weights for policy 1, policy_version 77651 (0.0009) -[2023-10-09 11:23:12,534][23469] Updated weights for policy 1, policy_version 77661 (0.0007) -[2023-10-09 11:23:14,178][23468] Updated weights for policy 0, policy_version 77253 (0.0009) -[2023-10-09 11:23:14,552][23468] Updated weights for policy 0, policy_version 77263 (0.0008) -[2023-10-09 11:23:14,937][23468] Updated weights for policy 0, policy_version 77273 (0.0008) -[2023-10-09 11:23:16,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 158662656. Throughput: 0: 1786.4, 1: 1801.6. Samples: 39676814. Policy #0 lag: (min: 18.0, avg: 18.4, max: 31.0) -[2023-10-09 11:23:16,078][22500] Avg episode reward: [(0, '11.060'), (1, '9.500')] -[2023-10-09 11:23:16,299][23469] Updated weights for policy 1, policy_version 77671 (0.0009) -[2023-10-09 11:23:16,663][23469] Updated weights for policy 1, policy_version 77681 (0.0008) -[2023-10-09 11:23:17,025][23469] Updated weights for policy 1, policy_version 77691 (0.0008) -[2023-10-09 11:23:18,657][23468] Updated weights for policy 0, policy_version 77283 (0.0007) -[2023-10-09 11:23:19,027][23468] Updated weights for policy 0, policy_version 77293 (0.0010) -[2023-10-09 11:23:19,398][23468] Updated weights for policy 0, policy_version 77303 (0.0007) -[2023-10-09 11:23:20,660][23469] Updated weights for policy 1, policy_version 77701 (0.0010) -[2023-10-09 11:23:21,030][23469] Updated weights for policy 1, policy_version 77711 (0.0008) -[2023-10-09 11:23:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 158728192. Throughput: 0: 1798.3, 1: 1792.9. Samples: 39688026. Policy #0 lag: (min: 18.0, avg: 18.4, max: 31.0) -[2023-10-09 11:23:21,078][22500] Avg episode reward: [(0, '10.830'), (1, '8.360')] -[2023-10-09 11:23:21,399][23469] Updated weights for policy 1, policy_version 77721 (0.0010) -[2023-10-09 11:23:23,157][23468] Updated weights for policy 0, policy_version 77313 (0.0010) -[2023-10-09 11:23:23,526][23468] Updated weights for policy 0, policy_version 77323 (0.0009) -[2023-10-09 11:23:23,900][23468] Updated weights for policy 0, policy_version 77333 (0.0009) -[2023-10-09 11:23:24,263][23468] Updated weights for policy 0, policy_version 77343 (0.0008) -[2023-10-09 11:23:25,302][23469] Updated weights for policy 1, policy_version 77731 (0.0009) -[2023-10-09 11:23:25,679][23469] Updated weights for policy 1, policy_version 77741 (0.0011) -[2023-10-09 11:23:26,043][23469] Updated weights for policy 1, policy_version 77751 (0.0008) -[2023-10-09 11:23:26,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 158793728. Throughput: 0: 1785.7, 1: 1795.4. Samples: 39708796. Policy #0 lag: (min: 18.0, avg: 18.4, max: 31.0) -[2023-10-09 11:23:26,078][22500] Avg episode reward: [(0, '10.960'), (1, '8.650')] -[2023-10-09 11:23:28,064][23468] Updated weights for policy 0, policy_version 77353 (0.0009) -[2023-10-09 11:23:28,446][23468] Updated weights for policy 0, policy_version 77363 (0.0009) -[2023-10-09 11:23:28,799][23468] Updated weights for policy 0, policy_version 77373 (0.0007) -[2023-10-09 11:23:29,869][23469] Updated weights for policy 1, policy_version 77761 (0.0009) -[2023-10-09 11:23:30,236][23469] Updated weights for policy 1, policy_version 77771 (0.0008) -[2023-10-09 11:23:30,604][23469] Updated weights for policy 1, policy_version 77781 (0.0007) -[2023-10-09 11:23:30,977][23469] Updated weights for policy 1, policy_version 77791 (0.0007) -[2023-10-09 11:23:31,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 158892032. Throughput: 0: 1781.0, 1: 1803.0. Samples: 39729932. Policy #0 lag: (min: 18.0, avg: 18.4, max: 31.0) -[2023-10-09 11:23:31,078][22500] Avg episode reward: [(0, '10.990'), (1, '9.420')] -[2023-10-09 11:23:32,569][23468] Updated weights for policy 0, policy_version 77383 (0.0008) -[2023-10-09 11:23:32,934][23468] Updated weights for policy 0, policy_version 77393 (0.0008) -[2023-10-09 11:23:33,318][23468] Updated weights for policy 0, policy_version 77403 (0.0010) -[2023-10-09 11:23:34,578][23469] Updated weights for policy 1, policy_version 77801 (0.0007) -[2023-10-09 11:23:34,946][23469] Updated weights for policy 1, policy_version 77811 (0.0008) -[2023-10-09 11:23:35,325][23469] Updated weights for policy 1, policy_version 77821 (0.0009) -[2023-10-09 11:23:36,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 158957568. Throughput: 0: 1788.2, 1: 1801.0. Samples: 39741414. Policy #0 lag: (min: 18.0, avg: 18.4, max: 31.0) -[2023-10-09 11:23:36,078][22500] Avg episode reward: [(0, '11.450'), (1, '9.570')] -[2023-10-09 11:23:37,104][23468] Updated weights for policy 0, policy_version 77413 (0.0009) -[2023-10-09 11:23:37,473][23468] Updated weights for policy 0, policy_version 77423 (0.0007) -[2023-10-09 11:23:37,844][23468] Updated weights for policy 0, policy_version 77433 (0.0007) -[2023-10-09 11:23:38,792][23469] Updated weights for policy 1, policy_version 77831 (0.0010) -[2023-10-09 11:23:39,171][23469] Updated weights for policy 1, policy_version 77841 (0.0010) -[2023-10-09 11:23:39,540][23469] Updated weights for policy 1, policy_version 77851 (0.0009) -[2023-10-09 11:23:41,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 159023104. Throughput: 0: 1779.0, 1: 1810.0. Samples: 39762258. Policy #0 lag: (min: 18.0, avg: 18.4, max: 31.0) -[2023-10-09 11:23:41,078][22500] Avg episode reward: [(0, '10.090'), (1, '9.680')] -[2023-10-09 11:23:41,640][23468] Updated weights for policy 0, policy_version 77443 (0.0007) -[2023-10-09 11:23:42,020][23468] Updated weights for policy 0, policy_version 77453 (0.0009) -[2023-10-09 11:23:42,394][23468] Updated weights for policy 0, policy_version 77463 (0.0010) -[2023-10-09 11:23:43,357][23469] Updated weights for policy 1, policy_version 77861 (0.0008) -[2023-10-09 11:23:43,726][23469] Updated weights for policy 1, policy_version 77871 (0.0008) -[2023-10-09 11:23:44,101][23469] Updated weights for policy 1, policy_version 77881 (0.0010) -[2023-10-09 11:23:46,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 159088640. Throughput: 0: 1782.3, 1: 1807.1. Samples: 39784754. Policy #0 lag: (min: 18.0, avg: 18.4, max: 31.0) -[2023-10-09 11:23:46,079][22500] Avg episode reward: [(0, '10.000'), (1, '9.120')] -[2023-10-09 11:23:46,085][23468] Updated weights for policy 0, policy_version 77473 (0.0010) -[2023-10-09 11:23:46,450][23468] Updated weights for policy 0, policy_version 77483 (0.0008) -[2023-10-09 11:23:46,822][23468] Updated weights for policy 0, policy_version 77493 (0.0007) -[2023-10-09 11:23:47,198][23468] Updated weights for policy 0, policy_version 77503 (0.0008) -[2023-10-09 11:23:47,915][23469] Updated weights for policy 1, policy_version 77891 (0.0008) -[2023-10-09 11:23:48,284][23469] Updated weights for policy 1, policy_version 77901 (0.0009) -[2023-10-09 11:23:48,653][23469] Updated weights for policy 1, policy_version 77911 (0.0010) -[2023-10-09 11:23:51,024][23468] Updated weights for policy 0, policy_version 77513 (0.0008) -[2023-10-09 11:23:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 159154176. Throughput: 0: 1780.4, 1: 1813.4. Samples: 39794740. Policy #0 lag: (min: 18.0, avg: 18.4, max: 31.0) -[2023-10-09 11:23:51,078][22500] Avg episode reward: [(0, '11.120'), (1, '9.080')] -[2023-10-09 11:23:51,402][23468] Updated weights for policy 0, policy_version 77523 (0.0007) -[2023-10-09 11:23:51,778][23468] Updated weights for policy 0, policy_version 77533 (0.0008) -[2023-10-09 11:23:52,429][23469] Updated weights for policy 1, policy_version 77921 (0.0008) -[2023-10-09 11:23:52,792][23469] Updated weights for policy 1, policy_version 77931 (0.0008) -[2023-10-09 11:23:53,159][23469] Updated weights for policy 1, policy_version 77941 (0.0008) -[2023-10-09 11:23:53,535][23469] Updated weights for policy 1, policy_version 77951 (0.0009) -[2023-10-09 11:23:55,363][23468] Updated weights for policy 0, policy_version 77543 (0.0009) -[2023-10-09 11:23:55,730][23468] Updated weights for policy 0, policy_version 77553 (0.0009) -[2023-10-09 11:23:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 159219712. Throughput: 0: 1782.7, 1: 1800.0. Samples: 39816882. Policy #0 lag: (min: 18.0, avg: 18.4, max: 31.0) -[2023-10-09 11:23:56,079][22500] Avg episode reward: [(0, '10.740'), (1, '8.090')] -[2023-10-09 11:23:56,116][23468] Updated weights for policy 0, policy_version 77563 (0.0007) -[2023-10-09 11:23:57,350][23469] Updated weights for policy 1, policy_version 77961 (0.0009) -[2023-10-09 11:23:57,712][23469] Updated weights for policy 1, policy_version 77971 (0.0010) -[2023-10-09 11:23:58,085][23469] Updated weights for policy 1, policy_version 77981 (0.0011) -[2023-10-09 11:23:59,657][23468] Updated weights for policy 0, policy_version 77573 (0.0009) -[2023-10-09 11:24:00,025][23468] Updated weights for policy 0, policy_version 77583 (0.0009) -[2023-10-09 11:24:00,394][23468] Updated weights for policy 0, policy_version 77593 (0.0009) -[2023-10-09 11:24:01,078][22500] Fps is (10 sec: 16383.5, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 159318016. Throughput: 0: 1797.9, 1: 1795.6. Samples: 39838522. Policy #0 lag: (min: 18.0, avg: 18.4, max: 31.0) -[2023-10-09 11:24:01,079][22500] Avg episode reward: [(0, '10.310'), (1, '8.030')] -[2023-10-09 11:24:01,993][23469] Updated weights for policy 1, policy_version 77991 (0.0010) -[2023-10-09 11:24:02,368][23469] Updated weights for policy 1, policy_version 78001 (0.0008) -[2023-10-09 11:24:02,734][23469] Updated weights for policy 1, policy_version 78011 (0.0007) -[2023-10-09 11:24:04,042][23468] Updated weights for policy 0, policy_version 77603 (0.0009) -[2023-10-09 11:24:04,420][23468] Updated weights for policy 0, policy_version 77613 (0.0008) -[2023-10-09 11:24:04,796][23468] Updated weights for policy 0, policy_version 77623 (0.0009) -[2023-10-09 11:24:06,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 159383552. Throughput: 0: 1792.5, 1: 1792.1. Samples: 39849332. Policy #0 lag: (min: 0.0, avg: 23.7, max: 32.0) -[2023-10-09 11:24:06,078][22500] Avg episode reward: [(0, '11.170'), (1, '8.020')] -[2023-10-09 11:24:06,458][23469] Updated weights for policy 1, policy_version 78021 (0.0008) -[2023-10-09 11:24:06,830][23469] Updated weights for policy 1, policy_version 78031 (0.0009) -[2023-10-09 11:24:07,194][23469] Updated weights for policy 1, policy_version 78041 (0.0007) -[2023-10-09 11:24:08,666][23468] Updated weights for policy 0, policy_version 77633 (0.0008) -[2023-10-09 11:24:09,039][23468] Updated weights for policy 0, policy_version 77643 (0.0008) -[2023-10-09 11:24:09,416][23468] Updated weights for policy 0, policy_version 77653 (0.0009) -[2023-10-09 11:24:09,786][23468] Updated weights for policy 0, policy_version 77663 (0.0007) -[2023-10-09 11:24:10,908][23469] Updated weights for policy 1, policy_version 78051 (0.0008) -[2023-10-09 11:24:11,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 159449088. Throughput: 0: 1805.6, 1: 1796.7. Samples: 39870900. Policy #0 lag: (min: 0.0, avg: 23.7, max: 32.0) -[2023-10-09 11:24:11,078][22500] Avg episode reward: [(0, '10.390'), (1, '8.720')] -[2023-10-09 11:24:11,283][23469] Updated weights for policy 1, policy_version 78061 (0.0009) -[2023-10-09 11:24:11,654][23469] Updated weights for policy 1, policy_version 78071 (0.0008) -[2023-10-09 11:24:13,493][23468] Updated weights for policy 0, policy_version 77673 (0.0007) -[2023-10-09 11:24:13,863][23468] Updated weights for policy 0, policy_version 77683 (0.0007) -[2023-10-09 11:24:14,232][23468] Updated weights for policy 0, policy_version 77693 (0.0007) -[2023-10-09 11:24:15,296][23469] Updated weights for policy 1, policy_version 78081 (0.0007) -[2023-10-09 11:24:15,665][23469] Updated weights for policy 1, policy_version 78091 (0.0009) -[2023-10-09 11:24:16,043][23469] Updated weights for policy 1, policy_version 78101 (0.0009) -[2023-10-09 11:24:16,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 159514624. Throughput: 0: 1799.6, 1: 1806.7. Samples: 39892218. Policy #0 lag: (min: 0.0, avg: 23.7, max: 32.0) -[2023-10-09 11:24:16,078][22500] Avg episode reward: [(0, '10.830'), (1, '9.190')] -[2023-10-09 11:24:16,087][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000077696_79560704.pth... -[2023-10-09 11:24:16,130][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000076032_77856768.pth -[2023-10-09 11:24:16,421][23469] Updated weights for policy 1, policy_version 78111 (0.0010) -[2023-10-09 11:24:16,456][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000078112_79986688.pth... -[2023-10-09 11:24:16,486][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000076416_78249984.pth -[2023-10-09 11:24:17,927][23468] Updated weights for policy 0, policy_version 77703 (0.0010) -[2023-10-09 11:24:18,295][23468] Updated weights for policy 0, policy_version 77713 (0.0009) -[2023-10-09 11:24:18,670][23468] Updated weights for policy 0, policy_version 77723 (0.0010) -[2023-10-09 11:24:20,000][23469] Updated weights for policy 1, policy_version 78121 (0.0010) -[2023-10-09 11:24:20,376][23469] Updated weights for policy 1, policy_version 78131 (0.0009) -[2023-10-09 11:24:20,739][23469] Updated weights for policy 1, policy_version 78141 (0.0008) -[2023-10-09 11:24:21,078][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 159612928. Throughput: 0: 1810.5, 1: 1788.2. Samples: 39903356. Policy #0 lag: (min: 0.0, avg: 23.7, max: 32.0) -[2023-10-09 11:24:21,079][22500] Avg episode reward: [(0, '10.820'), (1, '9.050')] -[2023-10-09 11:24:22,594][23468] Updated weights for policy 0, policy_version 77733 (0.0009) -[2023-10-09 11:24:22,965][23468] Updated weights for policy 0, policy_version 77743 (0.0008) -[2023-10-09 11:24:23,332][23468] Updated weights for policy 0, policy_version 77753 (0.0008) -[2023-10-09 11:24:24,490][23469] Updated weights for policy 1, policy_version 78151 (0.0010) -[2023-10-09 11:24:24,853][23469] Updated weights for policy 1, policy_version 78161 (0.0009) -[2023-10-09 11:24:25,214][23469] Updated weights for policy 1, policy_version 78171 (0.0009) -[2023-10-09 11:24:26,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 159678464. Throughput: 0: 1801.6, 1: 1800.2. Samples: 39924338. Policy #0 lag: (min: 0.0, avg: 23.7, max: 32.0) -[2023-10-09 11:24:26,078][22500] Avg episode reward: [(0, '10.200'), (1, '8.940')] -[2023-10-09 11:24:27,213][23468] Updated weights for policy 0, policy_version 77763 (0.0007) -[2023-10-09 11:24:27,593][23468] Updated weights for policy 0, policy_version 77773 (0.0007) -[2023-10-09 11:24:27,964][23468] Updated weights for policy 0, policy_version 77783 (0.0007) -[2023-10-09 11:24:29,149][23469] Updated weights for policy 1, policy_version 78181 (0.0009) -[2023-10-09 11:24:29,523][23469] Updated weights for policy 1, policy_version 78191 (0.0010) -[2023-10-09 11:24:29,892][23469] Updated weights for policy 1, policy_version 78201 (0.0007) -[2023-10-09 11:24:31,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 159744000. Throughput: 0: 1803.0, 1: 1780.2. Samples: 39945998. Policy #0 lag: (min: 0.0, avg: 23.7, max: 32.0) -[2023-10-09 11:24:31,078][22500] Avg episode reward: [(0, '9.970'), (1, '9.260')] -[2023-10-09 11:24:31,662][23468] Updated weights for policy 0, policy_version 77793 (0.0007) -[2023-10-09 11:24:32,037][23468] Updated weights for policy 0, policy_version 77803 (0.0009) -[2023-10-09 11:24:32,406][23468] Updated weights for policy 0, policy_version 77813 (0.0009) -[2023-10-09 11:24:32,792][23468] Updated weights for policy 0, policy_version 77823 (0.0008) -[2023-10-09 11:24:33,542][23469] Updated weights for policy 1, policy_version 78211 (0.0008) -[2023-10-09 11:24:33,910][23469] Updated weights for policy 1, policy_version 78221 (0.0009) -[2023-10-09 11:24:34,278][23469] Updated weights for policy 1, policy_version 78231 (0.0007) -[2023-10-09 11:24:36,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 159809536. Throughput: 0: 1801.2, 1: 1799.9. Samples: 39956790. Policy #0 lag: (min: 0.0, avg: 23.7, max: 32.0) -[2023-10-09 11:24:36,078][22500] Avg episode reward: [(0, '10.210'), (1, '9.420')] -[2023-10-09 11:24:36,678][23468] Updated weights for policy 0, policy_version 77833 (0.0008) -[2023-10-09 11:24:37,051][23468] Updated weights for policy 0, policy_version 77843 (0.0007) -[2023-10-09 11:24:37,425][23468] Updated weights for policy 0, policy_version 77853 (0.0009) -[2023-10-09 11:24:37,858][23469] Updated weights for policy 1, policy_version 78241 (0.0007) -[2023-10-09 11:24:38,232][23469] Updated weights for policy 1, policy_version 78251 (0.0007) -[2023-10-09 11:24:38,599][23469] Updated weights for policy 1, policy_version 78261 (0.0007) -[2023-10-09 11:24:38,972][23469] Updated weights for policy 1, policy_version 78271 (0.0007) -[2023-10-09 11:24:41,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 159875072. Throughput: 0: 1797.5, 1: 1794.9. Samples: 39978540. Policy #0 lag: (min: 0.0, avg: 23.7, max: 32.0) -[2023-10-09 11:24:41,078][22500] Avg episode reward: [(0, '10.420'), (1, '9.280')] -[2023-10-09 11:24:41,118][23468] Updated weights for policy 0, policy_version 77863 (0.0009) -[2023-10-09 11:24:41,503][23468] Updated weights for policy 0, policy_version 77873 (0.0010) -[2023-10-09 11:24:41,867][23468] Updated weights for policy 0, policy_version 77883 (0.0007) -[2023-10-09 11:24:42,701][23469] Updated weights for policy 1, policy_version 78281 (0.0008) -[2023-10-09 11:24:43,077][23469] Updated weights for policy 1, policy_version 78291 (0.0007) -[2023-10-09 11:24:43,447][23469] Updated weights for policy 1, policy_version 78301 (0.0008) -[2023-10-09 11:24:45,599][23468] Updated weights for policy 0, policy_version 77893 (0.0008) -[2023-10-09 11:24:45,970][23468] Updated weights for policy 0, policy_version 77903 (0.0010) -[2023-10-09 11:24:46,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 159940608. Throughput: 0: 1811.7, 1: 1794.6. Samples: 40000808. Policy #0 lag: (min: 0.0, avg: 23.7, max: 32.0) -[2023-10-09 11:24:46,078][22500] Avg episode reward: [(0, '10.940'), (1, '9.500')] -[2023-10-09 11:24:46,349][23468] Updated weights for policy 0, policy_version 77913 (0.0010) -[2023-10-09 11:24:47,349][23469] Updated weights for policy 1, policy_version 78311 (0.0008) -[2023-10-09 11:24:47,734][23469] Updated weights for policy 1, policy_version 78321 (0.0007) -[2023-10-09 11:24:48,094][23469] Updated weights for policy 1, policy_version 78331 (0.0008) -[2023-10-09 11:24:50,195][23468] Updated weights for policy 0, policy_version 77923 (0.0009) -[2023-10-09 11:24:50,560][23468] Updated weights for policy 0, policy_version 77933 (0.0007) -[2023-10-09 11:24:50,933][23468] Updated weights for policy 0, policy_version 77943 (0.0008) -[2023-10-09 11:24:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 160006144. Throughput: 0: 1782.0, 1: 1794.3. Samples: 40010264. Policy #0 lag: (min: 0.0, avg: 23.7, max: 32.0) -[2023-10-09 11:24:51,078][22500] Avg episode reward: [(0, '10.350'), (1, '9.900')] -[2023-10-09 11:24:51,841][23469] Updated weights for policy 1, policy_version 78341 (0.0009) -[2023-10-09 11:24:52,217][23469] Updated weights for policy 1, policy_version 78351 (0.0007) -[2023-10-09 11:24:52,597][23469] Updated weights for policy 1, policy_version 78361 (0.0008) -[2023-10-09 11:24:54,724][23468] Updated weights for policy 0, policy_version 77953 (0.0007) -[2023-10-09 11:24:55,094][23468] Updated weights for policy 0, policy_version 77963 (0.0008) -[2023-10-09 11:24:55,453][23468] Updated weights for policy 0, policy_version 77973 (0.0007) -[2023-10-09 11:24:55,827][23468] Updated weights for policy 0, policy_version 77983 (0.0008) -[2023-10-09 11:24:56,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 160104448. Throughput: 0: 1802.1, 1: 1790.5. Samples: 40032570. Policy #0 lag: (min: 30.0, avg: 35.6, max: 62.0) -[2023-10-09 11:24:56,078][22500] Avg episode reward: [(0, '10.530'), (1, '9.050')] -[2023-10-09 11:24:56,368][23469] Updated weights for policy 1, policy_version 78371 (0.0008) -[2023-10-09 11:24:56,738][23469] Updated weights for policy 1, policy_version 78381 (0.0010) -[2023-10-09 11:24:57,111][23469] Updated weights for policy 1, policy_version 78391 (0.0007) -[2023-10-09 11:24:59,569][23468] Updated weights for policy 0, policy_version 77993 (0.0008) -[2023-10-09 11:24:59,942][23468] Updated weights for policy 0, policy_version 78003 (0.0007) -[2023-10-09 11:25:00,313][23468] Updated weights for policy 0, policy_version 78013 (0.0009) -[2023-10-09 11:25:00,885][23469] Updated weights for policy 1, policy_version 78401 (0.0007) -[2023-10-09 11:25:01,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 160169984. Throughput: 0: 1782.2, 1: 1804.5. Samples: 40053620. Policy #0 lag: (min: 30.0, avg: 35.6, max: 62.0) -[2023-10-09 11:25:01,078][22500] Avg episode reward: [(0, '11.020'), (1, '8.810')] -[2023-10-09 11:25:01,249][23469] Updated weights for policy 1, policy_version 78411 (0.0007) -[2023-10-09 11:25:01,613][23469] Updated weights for policy 1, policy_version 78421 (0.0008) -[2023-10-09 11:25:01,991][23469] Updated weights for policy 1, policy_version 78431 (0.0008) -[2023-10-09 11:25:03,818][23468] Updated weights for policy 0, policy_version 78023 (0.0009) -[2023-10-09 11:25:04,184][23468] Updated weights for policy 0, policy_version 78033 (0.0008) -[2023-10-09 11:25:04,564][23468] Updated weights for policy 0, policy_version 78043 (0.0010) -[2023-10-09 11:25:05,764][23469] Updated weights for policy 1, policy_version 78441 (0.0011) -[2023-10-09 11:25:06,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 160235520. Throughput: 0: 1797.7, 1: 1791.5. Samples: 40064868. Policy #0 lag: (min: 30.0, avg: 35.6, max: 62.0) -[2023-10-09 11:25:06,078][22500] Avg episode reward: [(0, '10.750'), (1, '8.940')] -[2023-10-09 11:25:06,127][23469] Updated weights for policy 1, policy_version 78451 (0.0007) -[2023-10-09 11:25:06,491][23469] Updated weights for policy 1, policy_version 78461 (0.0008) -[2023-10-09 11:25:08,509][23468] Updated weights for policy 0, policy_version 78053 (0.0010) -[2023-10-09 11:25:08,881][23468] Updated weights for policy 0, policy_version 78063 (0.0008) -[2023-10-09 11:25:09,246][23468] Updated weights for policy 0, policy_version 78073 (0.0008) -[2023-10-09 11:25:10,290][23469] Updated weights for policy 1, policy_version 78471 (0.0008) -[2023-10-09 11:25:10,656][23469] Updated weights for policy 1, policy_version 78481 (0.0010) -[2023-10-09 11:25:11,024][23469] Updated weights for policy 1, policy_version 78491 (0.0008) -[2023-10-09 11:25:11,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 160301056. Throughput: 0: 1783.6, 1: 1806.6. Samples: 40085898. Policy #0 lag: (min: 30.0, avg: 35.6, max: 62.0) -[2023-10-09 11:25:11,078][22500] Avg episode reward: [(0, '11.180'), (1, '8.850')] -[2023-10-09 11:25:13,121][23468] Updated weights for policy 0, policy_version 78083 (0.0009) -[2023-10-09 11:25:13,494][23468] Updated weights for policy 0, policy_version 78093 (0.0008) -[2023-10-09 11:25:13,875][23468] Updated weights for policy 0, policy_version 78103 (0.0008) -[2023-10-09 11:25:14,782][23469] Updated weights for policy 1, policy_version 78501 (0.0008) -[2023-10-09 11:25:15,157][23469] Updated weights for policy 1, policy_version 78511 (0.0008) -[2023-10-09 11:25:15,527][23469] Updated weights for policy 1, policy_version 78521 (0.0011) -[2023-10-09 11:25:16,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 160399360. Throughput: 0: 1770.4, 1: 1800.2. Samples: 40106676. Policy #0 lag: (min: 30.0, avg: 35.6, max: 62.0) -[2023-10-09 11:25:16,078][22500] Avg episode reward: [(0, '11.530'), (1, '9.130')] -[2023-10-09 11:25:17,820][23468] Updated weights for policy 0, policy_version 78113 (0.0010) -[2023-10-09 11:25:18,203][23468] Updated weights for policy 0, policy_version 78123 (0.0009) -[2023-10-09 11:25:18,567][23468] Updated weights for policy 0, policy_version 78133 (0.0008) -[2023-10-09 11:25:18,936][23468] Updated weights for policy 0, policy_version 78143 (0.0008) -[2023-10-09 11:25:19,128][23469] Updated weights for policy 1, policy_version 78531 (0.0007) -[2023-10-09 11:25:19,488][23469] Updated weights for policy 1, policy_version 78541 (0.0009) -[2023-10-09 11:25:19,861][23469] Updated weights for policy 1, policy_version 78551 (0.0008) -[2023-10-09 11:25:21,077][22500] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 160464896. Throughput: 0: 1792.1, 1: 1805.6. Samples: 40118686. Policy #0 lag: (min: 30.0, avg: 35.6, max: 62.0) -[2023-10-09 11:25:21,078][22500] Avg episode reward: [(0, '11.150'), (1, '9.030')] -[2023-10-09 11:25:22,699][23468] Updated weights for policy 0, policy_version 78153 (0.0009) -[2023-10-09 11:25:23,078][23468] Updated weights for policy 0, policy_version 78163 (0.0010) -[2023-10-09 11:25:23,448][23468] Updated weights for policy 0, policy_version 78173 (0.0010) -[2023-10-09 11:25:23,580][23469] Updated weights for policy 1, policy_version 78561 (0.0011) -[2023-10-09 11:25:23,946][23469] Updated weights for policy 1, policy_version 78571 (0.0010) -[2023-10-09 11:25:24,314][23469] Updated weights for policy 1, policy_version 78581 (0.0007) -[2023-10-09 11:25:24,680][23469] Updated weights for policy 1, policy_version 78591 (0.0007) -[2023-10-09 11:25:26,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 160530432. Throughput: 0: 1769.3, 1: 1787.1. Samples: 40138580. Policy #0 lag: (min: 30.0, avg: 35.6, max: 62.0) -[2023-10-09 11:25:26,078][22500] Avg episode reward: [(0, '10.960'), (1, '8.870')] -[2023-10-09 11:25:27,236][23468] Updated weights for policy 0, policy_version 78183 (0.0007) -[2023-10-09 11:25:27,619][23468] Updated weights for policy 0, policy_version 78193 (0.0007) -[2023-10-09 11:25:27,991][23468] Updated weights for policy 0, policy_version 78203 (0.0007) -[2023-10-09 11:25:28,466][23469] Updated weights for policy 1, policy_version 78601 (0.0008) -[2023-10-09 11:25:28,833][23469] Updated weights for policy 1, policy_version 78611 (0.0007) -[2023-10-09 11:25:29,204][23469] Updated weights for policy 1, policy_version 78621 (0.0010) -[2023-10-09 11:25:31,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 160595968. Throughput: 0: 1769.5, 1: 1789.3. Samples: 40160952. Policy #0 lag: (min: 30.0, avg: 35.6, max: 62.0) -[2023-10-09 11:25:31,079][22500] Avg episode reward: [(0, '11.130'), (1, '8.710')] -[2023-10-09 11:25:31,765][23468] Updated weights for policy 0, policy_version 78213 (0.0009) -[2023-10-09 11:25:32,134][23468] Updated weights for policy 0, policy_version 78223 (0.0010) -[2023-10-09 11:25:32,503][23468] Updated weights for policy 0, policy_version 78233 (0.0010) -[2023-10-09 11:25:33,072][23469] Updated weights for policy 1, policy_version 78631 (0.0007) -[2023-10-09 11:25:33,440][23469] Updated weights for policy 1, policy_version 78641 (0.0009) -[2023-10-09 11:25:33,807][23469] Updated weights for policy 1, policy_version 78651 (0.0009) -[2023-10-09 11:25:36,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 160661504. Throughput: 0: 1769.5, 1: 1798.7. Samples: 40170834. Policy #0 lag: (min: 30.0, avg: 35.6, max: 62.0) -[2023-10-09 11:25:36,078][22500] Avg episode reward: [(0, '10.800'), (1, '8.860')] -[2023-10-09 11:25:36,295][23468] Updated weights for policy 0, policy_version 78243 (0.0008) -[2023-10-09 11:25:36,669][23468] Updated weights for policy 0, policy_version 78253 (0.0008) -[2023-10-09 11:25:37,049][23468] Updated weights for policy 0, policy_version 78263 (0.0009) -[2023-10-09 11:25:37,494][23469] Updated weights for policy 1, policy_version 78661 (0.0007) -[2023-10-09 11:25:37,875][23469] Updated weights for policy 1, policy_version 78671 (0.0008) -[2023-10-09 11:25:38,243][23469] Updated weights for policy 1, policy_version 78681 (0.0011) -[2023-10-09 11:25:40,780][23468] Updated weights for policy 0, policy_version 78273 (0.0007) -[2023-10-09 11:25:41,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 160727040. Throughput: 0: 1768.4, 1: 1796.9. Samples: 40193008. Policy #0 lag: (min: 30.0, avg: 35.6, max: 62.0) -[2023-10-09 11:25:41,078][22500] Avg episode reward: [(0, '10.350'), (1, '9.270')] -[2023-10-09 11:25:41,158][23468] Updated weights for policy 0, policy_version 78283 (0.0009) -[2023-10-09 11:25:41,523][23468] Updated weights for policy 0, policy_version 78293 (0.0008) -[2023-10-09 11:25:41,899][23468] Updated weights for policy 0, policy_version 78303 (0.0008) -[2023-10-09 11:25:41,989][23469] Updated weights for policy 1, policy_version 78691 (0.0009) -[2023-10-09 11:25:42,355][23469] Updated weights for policy 1, policy_version 78701 (0.0010) -[2023-10-09 11:25:42,737][23469] Updated weights for policy 1, policy_version 78711 (0.0010) -[2023-10-09 11:25:45,562][23468] Updated weights for policy 0, policy_version 78313 (0.0009) -[2023-10-09 11:25:45,936][23468] Updated weights for policy 0, policy_version 78323 (0.0007) -[2023-10-09 11:25:46,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 160792576. Throughput: 0: 1801.3, 1: 1790.5. Samples: 40215250. Policy #0 lag: (min: 30.0, avg: 35.6, max: 62.0) -[2023-10-09 11:25:46,078][22500] Avg episode reward: [(0, '10.510'), (1, '9.130')] -[2023-10-09 11:25:46,315][23468] Updated weights for policy 0, policy_version 78333 (0.0008) -[2023-10-09 11:25:46,514][23469] Updated weights for policy 1, policy_version 78721 (0.0011) -[2023-10-09 11:25:46,891][23469] Updated weights for policy 1, policy_version 78731 (0.0010) -[2023-10-09 11:25:47,260][23469] Updated weights for policy 1, policy_version 78741 (0.0007) -[2023-10-09 11:25:47,640][23469] Updated weights for policy 1, policy_version 78751 (0.0008) -[2023-10-09 11:25:49,978][23468] Updated weights for policy 0, policy_version 78343 (0.0008) -[2023-10-09 11:25:50,348][23468] Updated weights for policy 0, policy_version 78353 (0.0010) -[2023-10-09 11:25:50,725][23468] Updated weights for policy 0, policy_version 78363 (0.0009) -[2023-10-09 11:25:51,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 160890880. Throughput: 0: 1769.9, 1: 1789.7. Samples: 40225050. Policy #0 lag: (min: 27.0, avg: 28.5, max: 54.0) -[2023-10-09 11:25:51,078][22500] Avg episode reward: [(0, '10.590'), (1, '8.920')] -[2023-10-09 11:25:51,302][23469] Updated weights for policy 1, policy_version 78761 (0.0008) -[2023-10-09 11:25:51,675][23469] Updated weights for policy 1, policy_version 78771 (0.0009) -[2023-10-09 11:25:52,045][23469] Updated weights for policy 1, policy_version 78781 (0.0007) -[2023-10-09 11:25:54,537][23468] Updated weights for policy 0, policy_version 78373 (0.0008) -[2023-10-09 11:25:54,923][23468] Updated weights for policy 0, policy_version 78383 (0.0010) -[2023-10-09 11:25:55,295][23468] Updated weights for policy 0, policy_version 78393 (0.0010) -[2023-10-09 11:25:55,763][23469] Updated weights for policy 1, policy_version 78791 (0.0008) -[2023-10-09 11:25:56,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 160956416. Throughput: 0: 1805.9, 1: 1791.5. Samples: 40247778. Policy #0 lag: (min: 27.0, avg: 28.5, max: 54.0) -[2023-10-09 11:25:56,078][22500] Avg episode reward: [(0, '10.470'), (1, '8.860')] -[2023-10-09 11:25:56,137][23469] Updated weights for policy 1, policy_version 78801 (0.0008) -[2023-10-09 11:25:56,501][23469] Updated weights for policy 1, policy_version 78811 (0.0007) -[2023-10-09 11:25:58,866][23468] Updated weights for policy 0, policy_version 78403 (0.0008) -[2023-10-09 11:25:59,244][23468] Updated weights for policy 0, policy_version 78413 (0.0008) -[2023-10-09 11:25:59,615][23468] Updated weights for policy 0, policy_version 78423 (0.0009) -[2023-10-09 11:26:00,324][23469] Updated weights for policy 1, policy_version 78821 (0.0008) -[2023-10-09 11:26:00,697][23469] Updated weights for policy 1, policy_version 78831 (0.0009) -[2023-10-09 11:26:01,060][23469] Updated weights for policy 1, policy_version 78841 (0.0007) -[2023-10-09 11:26:01,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 161021952. Throughput: 0: 1783.9, 1: 1798.0. Samples: 40267862. Policy #0 lag: (min: 27.0, avg: 28.5, max: 54.0) -[2023-10-09 11:26:01,078][22500] Avg episode reward: [(0, '10.330'), (1, '8.780')] -[2023-10-09 11:26:03,302][23468] Updated weights for policy 0, policy_version 78433 (0.0009) -[2023-10-09 11:26:03,682][23468] Updated weights for policy 0, policy_version 78443 (0.0010) -[2023-10-09 11:26:04,048][23468] Updated weights for policy 0, policy_version 78453 (0.0010) -[2023-10-09 11:26:04,423][23468] Updated weights for policy 0, policy_version 78463 (0.0008) -[2023-10-09 11:26:04,831][23469] Updated weights for policy 1, policy_version 78851 (0.0007) -[2023-10-09 11:26:05,196][23469] Updated weights for policy 1, policy_version 78861 (0.0012) -[2023-10-09 11:26:05,561][23469] Updated weights for policy 1, policy_version 78871 (0.0011) -[2023-10-09 11:26:06,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 161120256. Throughput: 0: 1799.2, 1: 1785.2. Samples: 40279986. Policy #0 lag: (min: 27.0, avg: 28.5, max: 54.0) -[2023-10-09 11:26:06,079][22500] Avg episode reward: [(0, '10.400'), (1, '9.710')] -[2023-10-09 11:26:08,122][23468] Updated weights for policy 0, policy_version 78473 (0.0008) -[2023-10-09 11:26:08,494][23468] Updated weights for policy 0, policy_version 78483 (0.0009) -[2023-10-09 11:26:08,866][23468] Updated weights for policy 0, policy_version 78493 (0.0009) -[2023-10-09 11:26:09,242][23469] Updated weights for policy 1, policy_version 78881 (0.0010) -[2023-10-09 11:26:09,611][23469] Updated weights for policy 1, policy_version 78891 (0.0009) -[2023-10-09 11:26:09,991][23469] Updated weights for policy 1, policy_version 78901 (0.0010) -[2023-10-09 11:26:10,357][23469] Updated weights for policy 1, policy_version 78911 (0.0011) -[2023-10-09 11:26:11,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 161185792. Throughput: 0: 1791.0, 1: 1807.4. Samples: 40300508. Policy #0 lag: (min: 27.0, avg: 28.5, max: 54.0) -[2023-10-09 11:26:11,078][22500] Avg episode reward: [(0, '10.090'), (1, '9.600')] -[2023-10-09 11:26:12,807][23468] Updated weights for policy 0, policy_version 78503 (0.0007) -[2023-10-09 11:26:13,185][23468] Updated weights for policy 0, policy_version 78513 (0.0007) -[2023-10-09 11:26:13,565][23468] Updated weights for policy 0, policy_version 78523 (0.0007) -[2023-10-09 11:26:14,084][23469] Updated weights for policy 1, policy_version 78921 (0.0009) -[2023-10-09 11:26:14,448][23469] Updated weights for policy 1, policy_version 78931 (0.0010) -[2023-10-09 11:26:14,813][23469] Updated weights for policy 1, policy_version 78941 (0.0010) -[2023-10-09 11:26:16,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 161251328. Throughput: 0: 1795.5, 1: 1785.9. Samples: 40322114. Policy #0 lag: (min: 27.0, avg: 28.5, max: 54.0) -[2023-10-09 11:26:16,079][22500] Avg episode reward: [(0, '10.950'), (1, '9.590')] -[2023-10-09 11:26:16,089][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000078944_80838656.pth... -[2023-10-09 11:26:16,089][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000078528_80412672.pth... -[2023-10-09 11:26:16,121][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000076864_78708736.pth -[2023-10-09 11:26:16,129][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000077248_79101952.pth -[2023-10-09 11:26:17,166][23468] Updated weights for policy 0, policy_version 78533 (0.0009) -[2023-10-09 11:26:17,539][23468] Updated weights for policy 0, policy_version 78543 (0.0007) -[2023-10-09 11:26:17,924][23468] Updated weights for policy 0, policy_version 78553 (0.0007) -[2023-10-09 11:26:18,818][23469] Updated weights for policy 1, policy_version 78951 (0.0011) -[2023-10-09 11:26:19,187][23469] Updated weights for policy 1, policy_version 78961 (0.0011) -[2023-10-09 11:26:19,556][23469] Updated weights for policy 1, policy_version 78971 (0.0008) -[2023-10-09 11:26:21,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 161316864. Throughput: 0: 1794.9, 1: 1805.2. Samples: 40332838. Policy #0 lag: (min: 27.0, avg: 28.5, max: 54.0) -[2023-10-09 11:26:21,079][22500] Avg episode reward: [(0, '10.500'), (1, '8.730')] -[2023-10-09 11:26:21,662][23468] Updated weights for policy 0, policy_version 78563 (0.0009) -[2023-10-09 11:26:22,038][23468] Updated weights for policy 0, policy_version 78573 (0.0007) -[2023-10-09 11:26:22,406][23468] Updated weights for policy 0, policy_version 78583 (0.0007) -[2023-10-09 11:26:23,260][23469] Updated weights for policy 1, policy_version 78981 (0.0007) -[2023-10-09 11:26:23,628][23469] Updated weights for policy 1, policy_version 78991 (0.0009) -[2023-10-09 11:26:23,992][23469] Updated weights for policy 1, policy_version 79001 (0.0008) -[2023-10-09 11:26:26,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 161382400. Throughput: 0: 1792.2, 1: 1784.3. Samples: 40353950. Policy #0 lag: (min: 27.0, avg: 28.5, max: 54.0) -[2023-10-09 11:26:26,078][22500] Avg episode reward: [(0, '10.360'), (1, '8.410')] -[2023-10-09 11:26:26,134][23468] Updated weights for policy 0, policy_version 78593 (0.0008) -[2023-10-09 11:26:26,509][23468] Updated weights for policy 0, policy_version 78603 (0.0010) -[2023-10-09 11:26:26,875][23468] Updated weights for policy 0, policy_version 78613 (0.0009) -[2023-10-09 11:26:27,242][23468] Updated weights for policy 0, policy_version 78623 (0.0008) -[2023-10-09 11:26:27,798][23469] Updated weights for policy 1, policy_version 79011 (0.0008) -[2023-10-09 11:26:28,180][23469] Updated weights for policy 1, policy_version 79021 (0.0008) -[2023-10-09 11:26:28,536][23469] Updated weights for policy 1, policy_version 79031 (0.0009) -[2023-10-09 11:26:31,074][23468] Updated weights for policy 0, policy_version 78633 (0.0009) -[2023-10-09 11:26:31,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 161447936. Throughput: 0: 1790.8, 1: 1794.4. Samples: 40376588. Policy #0 lag: (min: 27.0, avg: 28.5, max: 54.0) -[2023-10-09 11:26:31,078][22500] Avg episode reward: [(0, '10.700'), (1, '8.350')] -[2023-10-09 11:26:31,448][23468] Updated weights for policy 0, policy_version 78643 (0.0007) -[2023-10-09 11:26:31,820][23468] Updated weights for policy 0, policy_version 78653 (0.0010) -[2023-10-09 11:26:32,159][23469] Updated weights for policy 1, policy_version 79041 (0.0009) -[2023-10-09 11:26:32,541][23469] Updated weights for policy 1, policy_version 79051 (0.0008) -[2023-10-09 11:26:32,903][23469] Updated weights for policy 1, policy_version 79061 (0.0009) -[2023-10-09 11:26:33,279][23469] Updated weights for policy 1, policy_version 79071 (0.0011) -[2023-10-09 11:26:35,555][23468] Updated weights for policy 0, policy_version 78663 (0.0007) -[2023-10-09 11:26:35,924][23468] Updated weights for policy 0, policy_version 78673 (0.0011) -[2023-10-09 11:26:36,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 161513472. Throughput: 0: 1790.0, 1: 1797.0. Samples: 40386464. Policy #0 lag: (min: 27.0, avg: 28.5, max: 54.0) -[2023-10-09 11:26:36,078][22500] Avg episode reward: [(0, '9.900'), (1, '8.880')] -[2023-10-09 11:26:36,309][23468] Updated weights for policy 0, policy_version 78683 (0.0010) -[2023-10-09 11:26:37,118][23469] Updated weights for policy 1, policy_version 79081 (0.0008) -[2023-10-09 11:26:37,487][23469] Updated weights for policy 1, policy_version 79091 (0.0009) -[2023-10-09 11:26:37,863][23469] Updated weights for policy 1, policy_version 79101 (0.0008) -[2023-10-09 11:26:40,209][23468] Updated weights for policy 0, policy_version 78693 (0.0009) -[2023-10-09 11:26:40,569][23468] Updated weights for policy 0, policy_version 78703 (0.0009) -[2023-10-09 11:26:40,949][23468] Updated weights for policy 0, policy_version 78713 (0.0010) -[2023-10-09 11:26:41,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 161579008. Throughput: 0: 1783.5, 1: 1792.0. Samples: 40408676. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:26:41,078][22500] Avg episode reward: [(0, '10.400'), (1, '9.040')] -[2023-10-09 11:26:41,514][23469] Updated weights for policy 1, policy_version 79111 (0.0010) -[2023-10-09 11:26:41,882][23469] Updated weights for policy 1, policy_version 79121 (0.0011) -[2023-10-09 11:26:42,261][23469] Updated weights for policy 1, policy_version 79131 (0.0008) -[2023-10-09 11:26:44,671][23468] Updated weights for policy 0, policy_version 78723 (0.0008) -[2023-10-09 11:26:45,043][23468] Updated weights for policy 0, policy_version 78733 (0.0008) -[2023-10-09 11:26:45,403][23468] Updated weights for policy 0, policy_version 78743 (0.0008) -[2023-10-09 11:26:45,986][23469] Updated weights for policy 1, policy_version 79141 (0.0008) -[2023-10-09 11:26:46,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 161677312. Throughput: 0: 1796.2, 1: 1818.0. Samples: 40430502. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:26:46,078][22500] Avg episode reward: [(0, '10.310'), (1, '8.740')] -[2023-10-09 11:26:46,361][23469] Updated weights for policy 1, policy_version 79151 (0.0009) -[2023-10-09 11:26:46,743][23469] Updated weights for policy 1, policy_version 79161 (0.0009) -[2023-10-09 11:26:49,182][23468] Updated weights for policy 0, policy_version 78753 (0.0008) -[2023-10-09 11:26:49,560][23468] Updated weights for policy 0, policy_version 78763 (0.0007) -[2023-10-09 11:26:49,927][23468] Updated weights for policy 0, policy_version 78773 (0.0008) -[2023-10-09 11:26:50,307][23468] Updated weights for policy 0, policy_version 78783 (0.0008) -[2023-10-09 11:26:50,479][23469] Updated weights for policy 1, policy_version 79171 (0.0008) -[2023-10-09 11:26:50,846][23469] Updated weights for policy 1, policy_version 79181 (0.0009) -[2023-10-09 11:26:51,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 161742848. Throughput: 0: 1783.9, 1: 1797.8. Samples: 40441164. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:26:51,078][22500] Avg episode reward: [(0, '10.040'), (1, '8.740')] -[2023-10-09 11:26:51,226][23469] Updated weights for policy 1, policy_version 79191 (0.0007) -[2023-10-09 11:26:53,898][23468] Updated weights for policy 0, policy_version 78793 (0.0010) -[2023-10-09 11:26:54,276][23468] Updated weights for policy 0, policy_version 78803 (0.0010) -[2023-10-09 11:26:54,649][23468] Updated weights for policy 0, policy_version 78813 (0.0010) -[2023-10-09 11:26:54,931][23469] Updated weights for policy 1, policy_version 79201 (0.0008) -[2023-10-09 11:26:55,292][23469] Updated weights for policy 1, policy_version 79211 (0.0009) -[2023-10-09 11:26:55,664][23469] Updated weights for policy 1, policy_version 79221 (0.0008) -[2023-10-09 11:26:56,037][23469] Updated weights for policy 1, policy_version 79231 (0.0007) -[2023-10-09 11:26:56,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 161841152. Throughput: 0: 1795.0, 1: 1815.4. Samples: 40462974. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:26:56,078][22500] Avg episode reward: [(0, '10.430'), (1, '8.620')] -[2023-10-09 11:26:58,629][23468] Updated weights for policy 0, policy_version 78823 (0.0009) -[2023-10-09 11:26:59,010][23468] Updated weights for policy 0, policy_version 78833 (0.0010) -[2023-10-09 11:26:59,395][23468] Updated weights for policy 0, policy_version 78843 (0.0008) -[2023-10-09 11:26:59,691][23469] Updated weights for policy 1, policy_version 79241 (0.0007) -[2023-10-09 11:27:00,057][23469] Updated weights for policy 1, policy_version 79251 (0.0007) -[2023-10-09 11:27:00,427][23469] Updated weights for policy 1, policy_version 79261 (0.0008) -[2023-10-09 11:27:01,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 161906688. Throughput: 0: 1773.2, 1: 1804.5. Samples: 40483110. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:27:01,078][22500] Avg episode reward: [(0, '10.200'), (1, '9.310')] -[2023-10-09 11:27:03,258][23468] Updated weights for policy 0, policy_version 78853 (0.0008) -[2023-10-09 11:27:03,619][23468] Updated weights for policy 0, policy_version 78863 (0.0008) -[2023-10-09 11:27:04,001][23468] Updated weights for policy 0, policy_version 78873 (0.0007) -[2023-10-09 11:27:04,147][23469] Updated weights for policy 1, policy_version 79271 (0.0010) -[2023-10-09 11:27:04,525][23469] Updated weights for policy 1, policy_version 79281 (0.0009) -[2023-10-09 11:27:04,910][23469] Updated weights for policy 1, policy_version 79291 (0.0010) -[2023-10-09 11:27:06,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 161972224. Throughput: 0: 1800.8, 1: 1817.4. Samples: 40495656. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:27:06,078][22500] Avg episode reward: [(0, '10.590'), (1, '9.930')] -[2023-10-09 11:27:07,723][23468] Updated weights for policy 0, policy_version 78883 (0.0008) -[2023-10-09 11:27:08,102][23468] Updated weights for policy 0, policy_version 78893 (0.0009) -[2023-10-09 11:27:08,466][23468] Updated weights for policy 0, policy_version 78903 (0.0009) -[2023-10-09 11:27:08,656][23469] Updated weights for policy 1, policy_version 79301 (0.0010) -[2023-10-09 11:27:09,025][23469] Updated weights for policy 1, policy_version 79311 (0.0009) -[2023-10-09 11:27:09,392][23469] Updated weights for policy 1, policy_version 79321 (0.0009) -[2023-10-09 11:27:11,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 162037760. Throughput: 0: 1774.7, 1: 1808.5. Samples: 40515194. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:27:11,078][22500] Avg episode reward: [(0, '10.170'), (1, '9.320')] -[2023-10-09 11:27:12,288][23468] Updated weights for policy 0, policy_version 78913 (0.0008) -[2023-10-09 11:27:12,667][23468] Updated weights for policy 0, policy_version 78923 (0.0007) -[2023-10-09 11:27:13,014][23469] Updated weights for policy 1, policy_version 79331 (0.0007) -[2023-10-09 11:27:13,041][23468] Updated weights for policy 0, policy_version 78933 (0.0007) -[2023-10-09 11:27:13,382][23469] Updated weights for policy 1, policy_version 79341 (0.0008) -[2023-10-09 11:27:13,408][23468] Updated weights for policy 0, policy_version 78943 (0.0009) -[2023-10-09 11:27:13,749][23469] Updated weights for policy 1, policy_version 79351 (0.0009) -[2023-10-09 11:27:16,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 162103296. Throughput: 0: 1770.3, 1: 1806.7. Samples: 40537556. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:27:16,079][22500] Avg episode reward: [(0, '10.280'), (1, '9.100')] -[2023-10-09 11:27:17,129][23468] Updated weights for policy 0, policy_version 78953 (0.0010) -[2023-10-09 11:27:17,474][23469] Updated weights for policy 1, policy_version 79361 (0.0010) -[2023-10-09 11:27:17,491][23468] Updated weights for policy 0, policy_version 78963 (0.0008) -[2023-10-09 11:27:17,837][23469] Updated weights for policy 1, policy_version 79371 (0.0007) -[2023-10-09 11:27:17,869][23468] Updated weights for policy 0, policy_version 78973 (0.0007) -[2023-10-09 11:27:18,203][23469] Updated weights for policy 1, policy_version 79381 (0.0007) -[2023-10-09 11:27:18,578][23469] Updated weights for policy 1, policy_version 79391 (0.0008) -[2023-10-09 11:27:21,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 162168832. Throughput: 0: 1767.3, 1: 1809.3. Samples: 40547412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:27:21,079][22500] Avg episode reward: [(0, '10.120'), (1, '8.400')] -[2023-10-09 11:27:21,543][23468] Updated weights for policy 0, policy_version 78983 (0.0009) -[2023-10-09 11:27:21,915][23468] Updated weights for policy 0, policy_version 78993 (0.0008) -[2023-10-09 11:27:22,192][23469] Updated weights for policy 1, policy_version 79401 (0.0009) -[2023-10-09 11:27:22,290][23468] Updated weights for policy 0, policy_version 79003 (0.0007) -[2023-10-09 11:27:22,563][23469] Updated weights for policy 1, policy_version 79411 (0.0007) -[2023-10-09 11:27:22,943][23469] Updated weights for policy 1, policy_version 79421 (0.0007) -[2023-10-09 11:27:26,040][23468] Updated weights for policy 0, policy_version 79013 (0.0008) -[2023-10-09 11:27:26,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 162234368. Throughput: 0: 1770.1, 1: 1811.4. Samples: 40569842. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:27:26,078][22500] Avg episode reward: [(0, '10.080'), (1, '8.720')] -[2023-10-09 11:27:26,415][23468] Updated weights for policy 0, policy_version 79023 (0.0009) -[2023-10-09 11:27:26,756][23469] Updated weights for policy 1, policy_version 79431 (0.0008) -[2023-10-09 11:27:26,789][23468] Updated weights for policy 0, policy_version 79033 (0.0009) -[2023-10-09 11:27:27,132][23469] Updated weights for policy 1, policy_version 79441 (0.0008) -[2023-10-09 11:27:27,495][23469] Updated weights for policy 1, policy_version 79451 (0.0009) -[2023-10-09 11:27:30,680][23468] Updated weights for policy 0, policy_version 79043 (0.0009) -[2023-10-09 11:27:31,041][23468] Updated weights for policy 0, policy_version 79053 (0.0010) -[2023-10-09 11:27:31,078][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 162299904. Throughput: 0: 1783.8, 1: 1806.3. Samples: 40592056. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:27:31,079][22500] Avg episode reward: [(0, '10.540'), (1, '8.530')] -[2023-10-09 11:27:31,199][23469] Updated weights for policy 1, policy_version 79461 (0.0007) -[2023-10-09 11:27:31,418][23468] Updated weights for policy 0, policy_version 79063 (0.0008) -[2023-10-09 11:27:31,567][23469] Updated weights for policy 1, policy_version 79471 (0.0007) -[2023-10-09 11:27:31,944][23469] Updated weights for policy 1, policy_version 79481 (0.0008) -[2023-10-09 11:27:35,294][23468] Updated weights for policy 0, policy_version 79073 (0.0009) -[2023-10-09 11:27:35,630][23469] Updated weights for policy 1, policy_version 79491 (0.0008) -[2023-10-09 11:27:35,671][23468] Updated weights for policy 0, policy_version 79083 (0.0008) -[2023-10-09 11:27:35,989][23469] Updated weights for policy 1, policy_version 79501 (0.0007) -[2023-10-09 11:27:36,036][23468] Updated weights for policy 0, policy_version 79093 (0.0008) -[2023-10-09 11:27:36,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 162365440. Throughput: 0: 1758.9, 1: 1806.7. Samples: 40601618. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:27:36,078][22500] Avg episode reward: [(0, '10.970'), (1, '9.220')] -[2023-10-09 11:27:36,356][23469] Updated weights for policy 1, policy_version 79511 (0.0008) -[2023-10-09 11:27:36,416][23468] Updated weights for policy 0, policy_version 79103 (0.0008) -[2023-10-09 11:27:40,259][23469] Updated weights for policy 1, policy_version 79521 (0.0007) -[2023-10-09 11:27:40,346][23468] Updated weights for policy 0, policy_version 79113 (0.0009) -[2023-10-09 11:27:40,624][23469] Updated weights for policy 1, policy_version 79531 (0.0007) -[2023-10-09 11:27:40,721][23468] Updated weights for policy 0, policy_version 79123 (0.0009) -[2023-10-09 11:27:40,985][23469] Updated weights for policy 1, policy_version 79541 (0.0007) -[2023-10-09 11:27:41,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 162430976. Throughput: 0: 1779.7, 1: 1804.0. Samples: 40624238. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:27:41,078][22500] Avg episode reward: [(0, '10.850'), (1, '9.440')] -[2023-10-09 11:27:41,088][23468] Updated weights for policy 0, policy_version 79133 (0.0007) -[2023-10-09 11:27:41,349][23469] Updated weights for policy 1, policy_version 79551 (0.0008) -[2023-10-09 11:27:44,802][23468] Updated weights for policy 0, policy_version 79143 (0.0007) -[2023-10-09 11:27:45,029][23469] Updated weights for policy 1, policy_version 79561 (0.0007) -[2023-10-09 11:27:45,182][23468] Updated weights for policy 0, policy_version 79153 (0.0008) -[2023-10-09 11:27:45,390][23469] Updated weights for policy 1, policy_version 79571 (0.0010) -[2023-10-09 11:27:45,547][23468] Updated weights for policy 0, policy_version 79163 (0.0008) -[2023-10-09 11:27:45,757][23469] Updated weights for policy 1, policy_version 79581 (0.0008) -[2023-10-09 11:27:46,077][22500] Fps is (10 sec: 19660.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 162562048. Throughput: 0: 1777.4, 1: 1807.8. Samples: 40644444. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:27:46,078][22500] Avg episode reward: [(0, '10.620'), (1, '9.550')] -[2023-10-09 11:27:49,297][23468] Updated weights for policy 0, policy_version 79173 (0.0008) -[2023-10-09 11:27:49,446][23469] Updated weights for policy 1, policy_version 79591 (0.0008) -[2023-10-09 11:27:49,674][23468] Updated weights for policy 0, policy_version 79183 (0.0007) -[2023-10-09 11:27:49,810][23469] Updated weights for policy 1, policy_version 79601 (0.0008) -[2023-10-09 11:27:50,055][23468] Updated weights for policy 0, policy_version 79193 (0.0007) -[2023-10-09 11:27:50,177][23469] Updated weights for policy 1, policy_version 79611 (0.0007) -[2023-10-09 11:27:51,077][22500] Fps is (10 sec: 19661.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 162627584. Throughput: 0: 1771.3, 1: 1800.2. Samples: 40656374. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:27:51,078][22500] Avg episode reward: [(0, '10.530'), (1, '9.730')] -[2023-10-09 11:27:53,755][23468] Updated weights for policy 0, policy_version 79203 (0.0008) -[2023-10-09 11:27:54,088][23469] Updated weights for policy 1, policy_version 79621 (0.0009) -[2023-10-09 11:27:54,125][23468] Updated weights for policy 0, policy_version 79213 (0.0010) -[2023-10-09 11:27:54,454][23469] Updated weights for policy 1, policy_version 79631 (0.0008) -[2023-10-09 11:27:54,492][23468] Updated weights for policy 0, policy_version 79223 (0.0007) -[2023-10-09 11:27:54,820][23469] Updated weights for policy 1, policy_version 79641 (0.0008) -[2023-10-09 11:27:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 162693120. Throughput: 0: 1784.6, 1: 1806.3. Samples: 40676782. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:27:56,078][22500] Avg episode reward: [(0, '11.520'), (1, '8.670')] -[2023-10-09 11:27:58,381][23468] Updated weights for policy 0, policy_version 79233 (0.0008) -[2023-10-09 11:27:58,613][23469] Updated weights for policy 1, policy_version 79651 (0.0007) -[2023-10-09 11:27:58,752][23468] Updated weights for policy 0, policy_version 79243 (0.0007) -[2023-10-09 11:27:58,980][23469] Updated weights for policy 1, policy_version 79661 (0.0007) -[2023-10-09 11:27:59,119][23468] Updated weights for policy 0, policy_version 79253 (0.0008) -[2023-10-09 11:27:59,346][23469] Updated weights for policy 1, policy_version 79671 (0.0007) -[2023-10-09 11:27:59,493][23468] Updated weights for policy 0, policy_version 79263 (0.0007) -[2023-10-09 11:28:01,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 162758656. Throughput: 0: 1769.1, 1: 1791.8. Samples: 40697796. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:28:01,078][22500] Avg episode reward: [(0, '11.020'), (1, '8.860')] -[2023-10-09 11:28:03,048][23469] Updated weights for policy 1, policy_version 79681 (0.0007) -[2023-10-09 11:28:03,305][23468] Updated weights for policy 0, policy_version 79273 (0.0007) -[2023-10-09 11:28:03,425][23469] Updated weights for policy 1, policy_version 79691 (0.0009) -[2023-10-09 11:28:03,671][23468] Updated weights for policy 0, policy_version 79283 (0.0009) -[2023-10-09 11:28:03,788][23469] Updated weights for policy 1, policy_version 79701 (0.0007) -[2023-10-09 11:28:04,044][23468] Updated weights for policy 0, policy_version 79293 (0.0008) -[2023-10-09 11:28:04,155][23469] Updated weights for policy 1, policy_version 79711 (0.0009) -[2023-10-09 11:28:06,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 162824192. Throughput: 0: 1795.5, 1: 1803.0. Samples: 40709344. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:28:06,078][22500] Avg episode reward: [(0, '10.920'), (1, '8.280')] -[2023-10-09 11:28:07,798][23469] Updated weights for policy 1, policy_version 79721 (0.0008) -[2023-10-09 11:28:07,864][23468] Updated weights for policy 0, policy_version 79303 (0.0008) -[2023-10-09 11:28:08,169][23469] Updated weights for policy 1, policy_version 79731 (0.0007) -[2023-10-09 11:28:08,230][23468] Updated weights for policy 0, policy_version 79313 (0.0008) -[2023-10-09 11:28:08,531][23469] Updated weights for policy 1, policy_version 79741 (0.0007) -[2023-10-09 11:28:08,614][23468] Updated weights for policy 0, policy_version 79323 (0.0009) -[2023-10-09 11:28:11,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 162889728. Throughput: 0: 1764.0, 1: 1790.6. Samples: 40729798. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:28:11,078][22500] Avg episode reward: [(0, '11.360'), (1, '8.660')] -[2023-10-09 11:28:12,318][23469] Updated weights for policy 1, policy_version 79751 (0.0007) -[2023-10-09 11:28:12,403][23468] Updated weights for policy 0, policy_version 79333 (0.0008) -[2023-10-09 11:28:12,682][23469] Updated weights for policy 1, policy_version 79761 (0.0009) -[2023-10-09 11:28:12,764][23468] Updated weights for policy 0, policy_version 79343 (0.0009) -[2023-10-09 11:28:13,058][23469] Updated weights for policy 1, policy_version 79771 (0.0007) -[2023-10-09 11:28:13,133][23468] Updated weights for policy 0, policy_version 79353 (0.0009) -[2023-10-09 11:28:16,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 162955264. Throughput: 0: 1770.0, 1: 1786.1. Samples: 40752080. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:28:16,078][22500] Avg episode reward: [(0, '11.110'), (1, '8.680')] -[2023-10-09 11:28:16,088][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000079776_81690624.pth... -[2023-10-09 11:28:16,088][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000079360_81264640.pth... -[2023-10-09 11:28:16,117][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000078112_79986688.pth -[2023-10-09 11:28:16,130][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000077696_79560704.pth -[2023-10-09 11:28:16,789][23469] Updated weights for policy 1, policy_version 79781 (0.0009) -[2023-10-09 11:28:16,912][23468] Updated weights for policy 0, policy_version 79363 (0.0007) -[2023-10-09 11:28:17,146][23469] Updated weights for policy 1, policy_version 79791 (0.0008) -[2023-10-09 11:28:17,292][23468] Updated weights for policy 0, policy_version 79373 (0.0007) -[2023-10-09 11:28:17,514][23469] Updated weights for policy 1, policy_version 79801 (0.0008) -[2023-10-09 11:28:17,665][23468] Updated weights for policy 0, policy_version 79383 (0.0007) -[2023-10-09 11:28:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 163020800. Throughput: 0: 1773.4, 1: 1788.5. Samples: 40761902. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-09 11:28:21,078][22500] Avg episode reward: [(0, '10.510'), (1, '8.780')] -[2023-10-09 11:28:21,306][23469] Updated weights for policy 1, policy_version 79811 (0.0008) -[2023-10-09 11:28:21,528][23468] Updated weights for policy 0, policy_version 79393 (0.0009) -[2023-10-09 11:28:21,689][23469] Updated weights for policy 1, policy_version 79821 (0.0009) -[2023-10-09 11:28:21,894][23468] Updated weights for policy 0, policy_version 79403 (0.0008) -[2023-10-09 11:28:22,061][23469] Updated weights for policy 1, policy_version 79831 (0.0009) -[2023-10-09 11:28:22,280][23468] Updated weights for policy 0, policy_version 79413 (0.0010) -[2023-10-09 11:28:22,649][23468] Updated weights for policy 0, policy_version 79423 (0.0010) -[2023-10-09 11:28:26,015][23469] Updated weights for policy 1, policy_version 79841 (0.0007) -[2023-10-09 11:28:26,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 163086336. Throughput: 0: 1770.5, 1: 1780.4. Samples: 40784028. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-09 11:28:26,078][22500] Avg episode reward: [(0, '10.200'), (1, '9.350')] -[2023-10-09 11:28:26,381][23469] Updated weights for policy 1, policy_version 79851 (0.0007) -[2023-10-09 11:28:26,619][23468] Updated weights for policy 0, policy_version 79433 (0.0007) -[2023-10-09 11:28:26,753][23469] Updated weights for policy 1, policy_version 79861 (0.0008) -[2023-10-09 11:28:26,992][23468] Updated weights for policy 0, policy_version 79443 (0.0008) -[2023-10-09 11:28:27,122][23469] Updated weights for policy 1, policy_version 79871 (0.0007) -[2023-10-09 11:28:27,368][23468] Updated weights for policy 0, policy_version 79453 (0.0008) -[2023-10-09 11:28:30,887][23469] Updated weights for policy 1, policy_version 79881 (0.0009) -[2023-10-09 11:28:31,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 163151872. Throughput: 0: 1789.3, 1: 1799.5. Samples: 40805942. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-09 11:28:31,078][22500] Avg episode reward: [(0, '9.620'), (1, '9.530')] -[2023-10-09 11:28:31,087][23468] Updated weights for policy 0, policy_version 79463 (0.0009) -[2023-10-09 11:28:31,255][23469] Updated weights for policy 1, policy_version 79891 (0.0008) -[2023-10-09 11:28:31,468][23468] Updated weights for policy 0, policy_version 79473 (0.0007) -[2023-10-09 11:28:31,615][23469] Updated weights for policy 1, policy_version 79901 (0.0008) -[2023-10-09 11:28:31,836][23468] Updated weights for policy 0, policy_version 79483 (0.0010) -[2023-10-09 11:28:35,290][23469] Updated weights for policy 1, policy_version 79911 (0.0007) -[2023-10-09 11:28:35,334][23468] Updated weights for policy 0, policy_version 79493 (0.0009) -[2023-10-09 11:28:35,654][23469] Updated weights for policy 1, policy_version 79921 (0.0008) -[2023-10-09 11:28:35,697][23468] Updated weights for policy 0, policy_version 79503 (0.0008) -[2023-10-09 11:28:36,030][23469] Updated weights for policy 1, policy_version 79931 (0.0008) -[2023-10-09 11:28:36,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 163217408. Throughput: 0: 1770.8, 1: 1777.6. Samples: 40816048. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-09 11:28:36,078][22500] Avg episode reward: [(0, '9.540'), (1, '9.070')] -[2023-10-09 11:28:36,079][23468] Updated weights for policy 0, policy_version 79513 (0.0008) -[2023-10-09 11:28:39,836][23469] Updated weights for policy 1, policy_version 79941 (0.0009) -[2023-10-09 11:28:39,883][23468] Updated weights for policy 0, policy_version 79523 (0.0009) -[2023-10-09 11:28:40,207][23469] Updated weights for policy 1, policy_version 79951 (0.0008) -[2023-10-09 11:28:40,257][23468] Updated weights for policy 0, policy_version 79533 (0.0008) -[2023-10-09 11:28:40,577][23469] Updated weights for policy 1, policy_version 79961 (0.0008) -[2023-10-09 11:28:40,630][23468] Updated weights for policy 0, policy_version 79543 (0.0008) -[2023-10-09 11:28:41,077][22500] Fps is (10 sec: 19660.7, 60 sec: 15291.8, 300 sec: 14440.1). Total num frames: 163348480. Throughput: 0: 1787.3, 1: 1801.0. Samples: 40838256. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-09 11:28:41,078][22500] Avg episode reward: [(0, '9.580'), (1, '8.160')] -[2023-10-09 11:28:44,290][23468] Updated weights for policy 0, policy_version 79553 (0.0008) -[2023-10-09 11:28:44,412][23469] Updated weights for policy 1, policy_version 79971 (0.0008) -[2023-10-09 11:28:44,664][23468] Updated weights for policy 0, policy_version 79563 (0.0009) -[2023-10-09 11:28:44,778][23469] Updated weights for policy 1, policy_version 79981 (0.0007) -[2023-10-09 11:28:45,039][23468] Updated weights for policy 0, policy_version 79573 (0.0008) -[2023-10-09 11:28:45,149][23469] Updated weights for policy 1, policy_version 79991 (0.0008) -[2023-10-09 11:28:45,411][23468] Updated weights for policy 0, policy_version 79583 (0.0009) -[2023-10-09 11:28:46,077][22500] Fps is (10 sec: 19660.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 163414016. Throughput: 0: 1778.1, 1: 1778.4. Samples: 40857840. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-09 11:28:46,078][22500] Avg episode reward: [(0, '9.830'), (1, '8.530')] -[2023-10-09 11:28:48,857][23469] Updated weights for policy 1, policy_version 80001 (0.0008) -[2023-10-09 11:28:49,220][23469] Updated weights for policy 1, policy_version 80011 (0.0008) -[2023-10-09 11:28:49,275][23468] Updated weights for policy 0, policy_version 79593 (0.0008) -[2023-10-09 11:28:49,594][23469] Updated weights for policy 1, policy_version 80021 (0.0007) -[2023-10-09 11:28:49,638][23468] Updated weights for policy 0, policy_version 79603 (0.0008) -[2023-10-09 11:28:49,966][23469] Updated weights for policy 1, policy_version 80031 (0.0008) -[2023-10-09 11:28:50,011][23468] Updated weights for policy 0, policy_version 79613 (0.0009) -[2023-10-09 11:28:51,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 163479552. Throughput: 0: 1776.2, 1: 1798.3. Samples: 40870198. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-09 11:28:51,078][22500] Avg episode reward: [(0, '10.300'), (1, '8.900')] -[2023-10-09 11:28:53,602][23469] Updated weights for policy 1, policy_version 80041 (0.0010) -[2023-10-09 11:28:53,947][23468] Updated weights for policy 0, policy_version 79623 (0.0007) -[2023-10-09 11:28:53,966][23469] Updated weights for policy 1, policy_version 80051 (0.0008) -[2023-10-09 11:28:54,317][23468] Updated weights for policy 0, policy_version 79633 (0.0008) -[2023-10-09 11:28:54,351][23469] Updated weights for policy 1, policy_version 80061 (0.0009) -[2023-10-09 11:28:54,697][23468] Updated weights for policy 0, policy_version 79643 (0.0009) -[2023-10-09 11:28:56,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 163545088. Throughput: 0: 1789.0, 1: 1781.1. Samples: 40890454. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-09 11:28:56,079][22500] Avg episode reward: [(0, '10.340'), (1, '9.660')] -[2023-10-09 11:28:58,259][23469] Updated weights for policy 1, policy_version 80071 (0.0010) -[2023-10-09 11:28:58,534][23468] Updated weights for policy 0, policy_version 79653 (0.0007) -[2023-10-09 11:28:58,616][23469] Updated weights for policy 1, policy_version 80081 (0.0008) -[2023-10-09 11:28:58,901][23468] Updated weights for policy 0, policy_version 79663 (0.0008) -[2023-10-09 11:28:58,990][23469] Updated weights for policy 1, policy_version 80091 (0.0008) -[2023-10-09 11:28:59,272][23468] Updated weights for policy 0, policy_version 79673 (0.0008) -[2023-10-09 11:29:01,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 163610624. Throughput: 0: 1767.2, 1: 1786.4. Samples: 40911994. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-09 11:29:01,078][22500] Avg episode reward: [(0, '10.510'), (1, '9.370')] -[2023-10-09 11:29:02,796][23469] Updated weights for policy 1, policy_version 80101 (0.0007) -[2023-10-09 11:29:03,140][23468] Updated weights for policy 0, policy_version 79683 (0.0009) -[2023-10-09 11:29:03,170][23469] Updated weights for policy 1, policy_version 80111 (0.0008) -[2023-10-09 11:29:03,516][23468] Updated weights for policy 0, policy_version 79693 (0.0007) -[2023-10-09 11:29:03,541][23469] Updated weights for policy 1, policy_version 80121 (0.0007) -[2023-10-09 11:29:03,889][23468] Updated weights for policy 0, policy_version 79703 (0.0008) -[2023-10-09 11:29:06,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 163676160. Throughput: 0: 1789.4, 1: 1785.9. Samples: 40922792. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-09 11:29:06,079][22500] Avg episode reward: [(0, '10.480'), (1, '10.260')] -[2023-10-09 11:29:07,218][23469] Updated weights for policy 1, policy_version 80131 (0.0009) -[2023-10-09 11:29:07,581][23469] Updated weights for policy 1, policy_version 80141 (0.0010) -[2023-10-09 11:29:07,649][23468] Updated weights for policy 0, policy_version 79713 (0.0010) -[2023-10-09 11:29:07,944][23469] Updated weights for policy 1, policy_version 80151 (0.0008) -[2023-10-09 11:29:08,018][23468] Updated weights for policy 0, policy_version 79723 (0.0007) -[2023-10-09 11:29:08,391][23468] Updated weights for policy 0, policy_version 79733 (0.0008) -[2023-10-09 11:29:08,762][23468] Updated weights for policy 0, policy_version 79743 (0.0009) -[2023-10-09 11:29:11,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 163741696. Throughput: 0: 1764.3, 1: 1792.0. Samples: 40944066. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 11:29:11,079][22500] Avg episode reward: [(0, '9.700'), (1, '8.910')] -[2023-10-09 11:29:11,675][23469] Updated weights for policy 1, policy_version 80161 (0.0011) -[2023-10-09 11:29:12,048][23469] Updated weights for policy 1, policy_version 80171 (0.0009) -[2023-10-09 11:29:12,418][23469] Updated weights for policy 1, policy_version 80181 (0.0007) -[2023-10-09 11:29:12,474][23468] Updated weights for policy 0, policy_version 79753 (0.0008) -[2023-10-09 11:29:12,790][23469] Updated weights for policy 1, policy_version 80191 (0.0007) -[2023-10-09 11:29:12,835][23468] Updated weights for policy 0, policy_version 79763 (0.0008) -[2023-10-09 11:29:13,213][23468] Updated weights for policy 0, policy_version 79773 (0.0008) -[2023-10-09 11:29:16,078][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 163807232. Throughput: 0: 1769.1, 1: 1798.3. Samples: 40966472. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 11:29:16,079][22500] Avg episode reward: [(0, '11.290'), (1, '8.970')] -[2023-10-09 11:29:16,637][23469] Updated weights for policy 1, policy_version 80201 (0.0011) -[2023-10-09 11:29:17,015][23469] Updated weights for policy 1, policy_version 80211 (0.0007) -[2023-10-09 11:29:17,070][23468] Updated weights for policy 0, policy_version 79783 (0.0008) -[2023-10-09 11:29:17,381][23469] Updated weights for policy 1, policy_version 80221 (0.0008) -[2023-10-09 11:29:17,439][23468] Updated weights for policy 0, policy_version 79793 (0.0008) -[2023-10-09 11:29:17,812][23468] Updated weights for policy 0, policy_version 79803 (0.0008) -[2023-10-09 11:29:21,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 163872768. Throughput: 0: 1765.2, 1: 1788.1. Samples: 40975948. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 11:29:21,078][22500] Avg episode reward: [(0, '10.730'), (1, '9.680')] -[2023-10-09 11:29:21,158][23469] Updated weights for policy 1, policy_version 80231 (0.0009) -[2023-10-09 11:29:21,532][23469] Updated weights for policy 1, policy_version 80241 (0.0009) -[2023-10-09 11:29:21,655][23468] Updated weights for policy 0, policy_version 79813 (0.0009) -[2023-10-09 11:29:21,901][23469] Updated weights for policy 1, policy_version 80251 (0.0008) -[2023-10-09 11:29:22,020][23468] Updated weights for policy 0, policy_version 79823 (0.0008) -[2023-10-09 11:29:22,392][23468] Updated weights for policy 0, policy_version 79833 (0.0007) -[2023-10-09 11:29:25,475][23469] Updated weights for policy 1, policy_version 80261 (0.0008) -[2023-10-09 11:29:25,843][23469] Updated weights for policy 1, policy_version 80271 (0.0008) -[2023-10-09 11:29:26,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 163938304. Throughput: 0: 1761.3, 1: 1793.3. Samples: 40998214. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 11:29:26,078][22500] Avg episode reward: [(0, '11.100'), (1, '9.330')] -[2023-10-09 11:29:26,195][23468] Updated weights for policy 0, policy_version 79843 (0.0007) -[2023-10-09 11:29:26,211][23469] Updated weights for policy 1, policy_version 80281 (0.0008) -[2023-10-09 11:29:26,572][23468] Updated weights for policy 0, policy_version 79853 (0.0008) -[2023-10-09 11:29:26,940][23468] Updated weights for policy 0, policy_version 79863 (0.0008) -[2023-10-09 11:29:29,881][23469] Updated weights for policy 1, policy_version 80291 (0.0009) -[2023-10-09 11:29:30,244][23469] Updated weights for policy 1, policy_version 80301 (0.0007) -[2023-10-09 11:29:30,593][23468] Updated weights for policy 0, policy_version 79873 (0.0009) -[2023-10-09 11:29:30,618][23469] Updated weights for policy 1, policy_version 80311 (0.0007) -[2023-10-09 11:29:30,958][23468] Updated weights for policy 0, policy_version 79883 (0.0009) -[2023-10-09 11:29:31,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 164036608. Throughput: 0: 1795.6, 1: 1804.1. Samples: 41019828. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 11:29:31,078][22500] Avg episode reward: [(0, '11.070'), (1, '9.690')] -[2023-10-09 11:29:31,332][23468] Updated weights for policy 0, policy_version 79893 (0.0010) -[2023-10-09 11:29:31,717][23468] Updated weights for policy 0, policy_version 79903 (0.0008) -[2023-10-09 11:29:34,290][23469] Updated weights for policy 1, policy_version 80321 (0.0008) -[2023-10-09 11:29:34,663][23469] Updated weights for policy 1, policy_version 80331 (0.0008) -[2023-10-09 11:29:35,026][23469] Updated weights for policy 1, policy_version 80341 (0.0008) -[2023-10-09 11:29:35,403][23469] Updated weights for policy 1, policy_version 80351 (0.0008) -[2023-10-09 11:29:35,522][23468] Updated weights for policy 0, policy_version 79913 (0.0008) -[2023-10-09 11:29:35,892][23468] Updated weights for policy 0, policy_version 79923 (0.0008) -[2023-10-09 11:29:36,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 164102144. Throughput: 0: 1771.0, 1: 1800.7. Samples: 41030922. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 11:29:36,078][22500] Avg episode reward: [(0, '10.790'), (1, '9.500')] -[2023-10-09 11:29:36,264][23468] Updated weights for policy 0, policy_version 79933 (0.0007) -[2023-10-09 11:29:39,020][23469] Updated weights for policy 1, policy_version 80361 (0.0007) -[2023-10-09 11:29:39,386][23469] Updated weights for policy 1, policy_version 80371 (0.0008) -[2023-10-09 11:29:39,761][23469] Updated weights for policy 1, policy_version 80381 (0.0007) -[2023-10-09 11:29:40,035][23468] Updated weights for policy 0, policy_version 79943 (0.0009) -[2023-10-09 11:29:40,409][23468] Updated weights for policy 0, policy_version 79953 (0.0008) -[2023-10-09 11:29:40,780][23468] Updated weights for policy 0, policy_version 79963 (0.0008) -[2023-10-09 11:29:41,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 164200448. Throughput: 0: 1790.2, 1: 1808.1. Samples: 41052376. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 11:29:41,078][22500] Avg episode reward: [(0, '10.080'), (1, '9.070')] -[2023-10-09 11:29:43,483][23469] Updated weights for policy 1, policy_version 80391 (0.0007) -[2023-10-09 11:29:43,848][23469] Updated weights for policy 1, policy_version 80401 (0.0008) -[2023-10-09 11:29:44,217][23469] Updated weights for policy 1, policy_version 80411 (0.0009) -[2023-10-09 11:29:44,505][23468] Updated weights for policy 0, policy_version 79973 (0.0008) -[2023-10-09 11:29:44,881][23468] Updated weights for policy 0, policy_version 79983 (0.0007) -[2023-10-09 11:29:45,250][23468] Updated weights for policy 0, policy_version 79993 (0.0008) -[2023-10-09 11:29:46,078][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 164265984. Throughput: 0: 1787.9, 1: 1802.9. Samples: 41073582. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 11:29:46,078][22500] Avg episode reward: [(0, '9.830'), (1, '9.310')] -[2023-10-09 11:29:48,045][23469] Updated weights for policy 1, policy_version 80421 (0.0009) -[2023-10-09 11:29:48,415][23469] Updated weights for policy 1, policy_version 80431 (0.0009) -[2023-10-09 11:29:48,795][23469] Updated weights for policy 1, policy_version 80441 (0.0010) -[2023-10-09 11:29:48,821][23468] Updated weights for policy 0, policy_version 80003 (0.0010) -[2023-10-09 11:29:49,185][23468] Updated weights for policy 0, policy_version 80013 (0.0009) -[2023-10-09 11:29:49,563][23468] Updated weights for policy 0, policy_version 80023 (0.0009) -[2023-10-09 11:29:51,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 164331520. Throughput: 0: 1788.3, 1: 1807.3. Samples: 41084594. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 11:29:51,078][22500] Avg episode reward: [(0, '10.800'), (1, '9.290')] -[2023-10-09 11:29:52,638][23469] Updated weights for policy 1, policy_version 80451 (0.0009) -[2023-10-09 11:29:53,006][23469] Updated weights for policy 1, policy_version 80461 (0.0008) -[2023-10-09 11:29:53,369][23468] Updated weights for policy 0, policy_version 80033 (0.0007) -[2023-10-09 11:29:53,375][23469] Updated weights for policy 1, policy_version 80471 (0.0009) -[2023-10-09 11:29:53,741][23468] Updated weights for policy 0, policy_version 80043 (0.0008) -[2023-10-09 11:29:54,111][23468] Updated weights for policy 0, policy_version 80053 (0.0010) -[2023-10-09 11:29:54,487][23468] Updated weights for policy 0, policy_version 80063 (0.0007) -[2023-10-09 11:29:56,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 164397056. Throughput: 0: 1793.0, 1: 1793.8. Samples: 41105472. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 11:29:56,079][22500] Avg episode reward: [(0, '10.300'), (1, '8.850')] -[2023-10-09 11:29:57,137][23469] Updated weights for policy 1, policy_version 80481 (0.0008) -[2023-10-09 11:29:57,513][23469] Updated weights for policy 1, policy_version 80491 (0.0007) -[2023-10-09 11:29:57,875][23469] Updated weights for policy 1, policy_version 80501 (0.0010) -[2023-10-09 11:29:58,245][23469] Updated weights for policy 1, policy_version 80511 (0.0009) -[2023-10-09 11:29:58,299][23468] Updated weights for policy 0, policy_version 80073 (0.0008) -[2023-10-09 11:29:58,670][23468] Updated weights for policy 0, policy_version 80083 (0.0008) -[2023-10-09 11:29:59,039][23468] Updated weights for policy 0, policy_version 80093 (0.0009) -[2023-10-09 11:30:01,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 164462592. Throughput: 0: 1782.8, 1: 1797.8. Samples: 41127598. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:30:01,078][22500] Avg episode reward: [(0, '10.840'), (1, '8.970')] -[2023-10-09 11:30:02,034][23469] Updated weights for policy 1, policy_version 80521 (0.0008) -[2023-10-09 11:30:02,404][23469] Updated weights for policy 1, policy_version 80531 (0.0007) -[2023-10-09 11:30:02,776][23469] Updated weights for policy 1, policy_version 80541 (0.0009) -[2023-10-09 11:30:02,885][23468] Updated weights for policy 0, policy_version 80103 (0.0008) -[2023-10-09 11:30:03,262][23468] Updated weights for policy 0, policy_version 80113 (0.0008) -[2023-10-09 11:30:03,624][23468] Updated weights for policy 0, policy_version 80123 (0.0009) -[2023-10-09 11:30:06,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 164528128. Throughput: 0: 1799.1, 1: 1799.3. Samples: 41137876. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:30:06,078][22500] Avg episode reward: [(0, '10.410'), (1, '9.110')] -[2023-10-09 11:30:06,432][23469] Updated weights for policy 1, policy_version 80551 (0.0007) -[2023-10-09 11:30:06,812][23469] Updated weights for policy 1, policy_version 80561 (0.0007) -[2023-10-09 11:30:07,185][23469] Updated weights for policy 1, policy_version 80571 (0.0008) -[2023-10-09 11:30:07,329][23468] Updated weights for policy 0, policy_version 80133 (0.0009) -[2023-10-09 11:30:07,712][23468] Updated weights for policy 0, policy_version 80143 (0.0008) -[2023-10-09 11:30:08,075][23468] Updated weights for policy 0, policy_version 80153 (0.0008) -[2023-10-09 11:30:10,907][23469] Updated weights for policy 1, policy_version 80581 (0.0008) -[2023-10-09 11:30:11,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 164593664. Throughput: 0: 1785.3, 1: 1800.8. Samples: 41159590. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:30:11,079][22500] Avg episode reward: [(0, '10.820'), (1, '9.090')] -[2023-10-09 11:30:11,268][23469] Updated weights for policy 1, policy_version 80591 (0.0009) -[2023-10-09 11:30:11,649][23469] Updated weights for policy 1, policy_version 80601 (0.0009) -[2023-10-09 11:30:11,912][23468] Updated weights for policy 0, policy_version 80163 (0.0010) -[2023-10-09 11:30:12,281][23468] Updated weights for policy 0, policy_version 80173 (0.0011) -[2023-10-09 11:30:12,646][23468] Updated weights for policy 0, policy_version 80183 (0.0009) -[2023-10-09 11:30:15,493][23469] Updated weights for policy 1, policy_version 80611 (0.0008) -[2023-10-09 11:30:15,854][23469] Updated weights for policy 1, policy_version 80621 (0.0008) -[2023-10-09 11:30:16,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 164659200. Throughput: 0: 1780.1, 1: 1814.7. Samples: 41181596. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:30:16,078][22500] Avg episode reward: [(0, '11.100'), (1, '9.440')] -[2023-10-09 11:30:16,088][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000080192_82116608.pth... -[2023-10-09 11:30:16,121][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000078528_80412672.pth -[2023-10-09 11:30:16,224][23469] Updated weights for policy 1, policy_version 80631 (0.0007) -[2023-10-09 11:30:16,458][23468] Updated weights for policy 0, policy_version 80193 (0.0009) -[2023-10-09 11:30:16,549][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000080640_82575360.pth... -[2023-10-09 11:30:16,589][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000078944_80838656.pth -[2023-10-09 11:30:16,828][23468] Updated weights for policy 0, policy_version 80203 (0.0007) -[2023-10-09 11:30:17,195][23468] Updated weights for policy 0, policy_version 80213 (0.0010) -[2023-10-09 11:30:17,566][23468] Updated weights for policy 0, policy_version 80223 (0.0008) -[2023-10-09 11:30:19,843][23469] Updated weights for policy 1, policy_version 80641 (0.0007) -[2023-10-09 11:30:20,203][23469] Updated weights for policy 1, policy_version 80651 (0.0008) -[2023-10-09 11:30:20,565][23469] Updated weights for policy 1, policy_version 80661 (0.0010) -[2023-10-09 11:30:20,932][23469] Updated weights for policy 1, policy_version 80671 (0.0010) -[2023-10-09 11:30:21,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 164757504. Throughput: 0: 1784.7, 1: 1794.8. Samples: 41192002. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:30:21,078][22500] Avg episode reward: [(0, '10.410'), (1, '8.810')] -[2023-10-09 11:30:21,206][23468] Updated weights for policy 0, policy_version 80233 (0.0009) -[2023-10-09 11:30:21,589][23468] Updated weights for policy 0, policy_version 80243 (0.0009) -[2023-10-09 11:30:21,956][23468] Updated weights for policy 0, policy_version 80253 (0.0008) -[2023-10-09 11:30:24,771][23469] Updated weights for policy 1, policy_version 80681 (0.0007) -[2023-10-09 11:30:25,143][23469] Updated weights for policy 1, policy_version 80691 (0.0008) -[2023-10-09 11:30:25,509][23469] Updated weights for policy 1, policy_version 80701 (0.0009) -[2023-10-09 11:30:25,593][23468] Updated weights for policy 0, policy_version 80263 (0.0008) -[2023-10-09 11:30:25,966][23468] Updated weights for policy 0, policy_version 80273 (0.0010) -[2023-10-09 11:30:26,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 164823040. Throughput: 0: 1786.6, 1: 1811.1. Samples: 41214274. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:30:26,078][22500] Avg episode reward: [(0, '10.090'), (1, '9.550')] -[2023-10-09 11:30:26,334][23468] Updated weights for policy 0, policy_version 80283 (0.0011) -[2023-10-09 11:30:29,239][23469] Updated weights for policy 1, policy_version 80711 (0.0008) -[2023-10-09 11:30:29,617][23469] Updated weights for policy 1, policy_version 80721 (0.0009) -[2023-10-09 11:30:29,980][23469] Updated weights for policy 1, policy_version 80731 (0.0008) -[2023-10-09 11:30:30,115][23468] Updated weights for policy 0, policy_version 80293 (0.0009) -[2023-10-09 11:30:30,491][23468] Updated weights for policy 0, policy_version 80303 (0.0007) -[2023-10-09 11:30:30,869][23468] Updated weights for policy 0, policy_version 80313 (0.0008) -[2023-10-09 11:30:31,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 164888576. Throughput: 0: 1799.2, 1: 1787.2. Samples: 41234974. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:30:31,079][22500] Avg episode reward: [(0, '9.580'), (1, '8.710')] -[2023-10-09 11:30:33,698][23469] Updated weights for policy 1, policy_version 80741 (0.0010) -[2023-10-09 11:30:34,075][23469] Updated weights for policy 1, policy_version 80751 (0.0009) -[2023-10-09 11:30:34,440][23469] Updated weights for policy 1, policy_version 80761 (0.0008) -[2023-10-09 11:30:34,615][23468] Updated weights for policy 0, policy_version 80323 (0.0009) -[2023-10-09 11:30:34,997][23468] Updated weights for policy 0, policy_version 80333 (0.0009) -[2023-10-09 11:30:35,374][23468] Updated weights for policy 0, policy_version 80343 (0.0008) -[2023-10-09 11:30:36,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 164986880. Throughput: 0: 1787.1, 1: 1809.4. Samples: 41246436. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:30:36,078][22500] Avg episode reward: [(0, '9.840'), (1, '9.380')] -[2023-10-09 11:30:37,991][23469] Updated weights for policy 1, policy_version 80771 (0.0008) -[2023-10-09 11:30:38,360][23469] Updated weights for policy 1, policy_version 80781 (0.0010) -[2023-10-09 11:30:38,729][23469] Updated weights for policy 1, policy_version 80791 (0.0008) -[2023-10-09 11:30:39,200][23468] Updated weights for policy 0, policy_version 80353 (0.0010) -[2023-10-09 11:30:39,568][23468] Updated weights for policy 0, policy_version 80363 (0.0007) -[2023-10-09 11:30:39,940][23468] Updated weights for policy 0, policy_version 80373 (0.0009) -[2023-10-09 11:30:40,303][23468] Updated weights for policy 0, policy_version 80383 (0.0009) -[2023-10-09 11:30:41,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 165052416. Throughput: 0: 1801.7, 1: 1806.0. Samples: 41267818. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:30:41,078][22500] Avg episode reward: [(0, '10.160'), (1, '8.960')] -[2023-10-09 11:30:42,506][23469] Updated weights for policy 1, policy_version 80801 (0.0010) -[2023-10-09 11:30:42,863][23469] Updated weights for policy 1, policy_version 80811 (0.0008) -[2023-10-09 11:30:43,231][23469] Updated weights for policy 1, policy_version 80821 (0.0007) -[2023-10-09 11:30:43,610][23469] Updated weights for policy 1, policy_version 80831 (0.0008) -[2023-10-09 11:30:44,057][23468] Updated weights for policy 0, policy_version 80393 (0.0008) -[2023-10-09 11:30:44,423][23468] Updated weights for policy 0, policy_version 80403 (0.0007) -[2023-10-09 11:30:44,800][23468] Updated weights for policy 0, policy_version 80413 (0.0007) -[2023-10-09 11:30:46,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 165117952. Throughput: 0: 1779.6, 1: 1803.9. Samples: 41288856. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:30:46,078][22500] Avg episode reward: [(0, '10.380'), (1, '9.830')] -[2023-10-09 11:30:47,311][23469] Updated weights for policy 1, policy_version 80841 (0.0007) -[2023-10-09 11:30:47,681][23469] Updated weights for policy 1, policy_version 80851 (0.0009) -[2023-10-09 11:30:48,048][23469] Updated weights for policy 1, policy_version 80861 (0.0009) -[2023-10-09 11:30:48,716][23468] Updated weights for policy 0, policy_version 80423 (0.0009) -[2023-10-09 11:30:49,088][23468] Updated weights for policy 0, policy_version 80433 (0.0008) -[2023-10-09 11:30:49,452][23468] Updated weights for policy 0, policy_version 80443 (0.0008) -[2023-10-09 11:30:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 165183488. Throughput: 0: 1804.3, 1: 1804.1. Samples: 41300252. Policy #0 lag: (min: 10.0, avg: 17.7, max: 42.0) -[2023-10-09 11:30:51,079][22500] Avg episode reward: [(0, '10.840'), (1, '9.780')] -[2023-10-09 11:30:51,781][23469] Updated weights for policy 1, policy_version 80871 (0.0011) -[2023-10-09 11:30:52,154][23469] Updated weights for policy 1, policy_version 80881 (0.0008) -[2023-10-09 11:30:52,526][23469] Updated weights for policy 1, policy_version 80891 (0.0009) -[2023-10-09 11:30:52,983][23468] Updated weights for policy 0, policy_version 80453 (0.0010) -[2023-10-09 11:30:53,355][23468] Updated weights for policy 0, policy_version 80463 (0.0010) -[2023-10-09 11:30:53,739][23468] Updated weights for policy 0, policy_version 80473 (0.0007) -[2023-10-09 11:30:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 165249024. Throughput: 0: 1784.9, 1: 1802.9. Samples: 41321042. Policy #0 lag: (min: 10.0, avg: 17.7, max: 42.0) -[2023-10-09 11:30:56,078][22500] Avg episode reward: [(0, '10.380'), (1, '9.930')] -[2023-10-09 11:30:56,278][23469] Updated weights for policy 1, policy_version 80901 (0.0009) -[2023-10-09 11:30:56,664][23469] Updated weights for policy 1, policy_version 80911 (0.0008) -[2023-10-09 11:30:57,035][23469] Updated weights for policy 1, policy_version 80921 (0.0007) -[2023-10-09 11:30:57,491][23468] Updated weights for policy 0, policy_version 80483 (0.0008) -[2023-10-09 11:30:57,863][23468] Updated weights for policy 0, policy_version 80493 (0.0008) -[2023-10-09 11:30:58,240][23468] Updated weights for policy 0, policy_version 80503 (0.0010) -[2023-10-09 11:31:00,591][23469] Updated weights for policy 1, policy_version 80931 (0.0009) -[2023-10-09 11:31:00,965][23469] Updated weights for policy 1, policy_version 80941 (0.0008) -[2023-10-09 11:31:01,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 165314560. Throughput: 0: 1784.1, 1: 1805.4. Samples: 41343122. Policy #0 lag: (min: 10.0, avg: 17.7, max: 42.0) -[2023-10-09 11:31:01,078][22500] Avg episode reward: [(0, '10.210'), (1, '10.340')] -[2023-10-09 11:31:01,341][23469] Updated weights for policy 1, policy_version 80951 (0.0008) -[2023-10-09 11:31:01,672][23343] Saving new best policy, reward=10.340! -[2023-10-09 11:31:02,106][23468] Updated weights for policy 0, policy_version 80513 (0.0008) -[2023-10-09 11:31:02,472][23468] Updated weights for policy 0, policy_version 80523 (0.0009) -[2023-10-09 11:31:02,838][23468] Updated weights for policy 0, policy_version 80533 (0.0008) -[2023-10-09 11:31:03,215][23468] Updated weights for policy 0, policy_version 80543 (0.0007) -[2023-10-09 11:31:05,066][23469] Updated weights for policy 1, policy_version 80961 (0.0010) -[2023-10-09 11:31:05,432][23469] Updated weights for policy 1, policy_version 80971 (0.0008) -[2023-10-09 11:31:05,807][23469] Updated weights for policy 1, policy_version 80981 (0.0010) -[2023-10-09 11:31:06,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 165380096. Throughput: 0: 1781.3, 1: 1805.5. Samples: 41353408. Policy #0 lag: (min: 10.0, avg: 17.7, max: 42.0) -[2023-10-09 11:31:06,078][22500] Avg episode reward: [(0, '10.630'), (1, '9.910')] -[2023-10-09 11:31:06,179][23469] Updated weights for policy 1, policy_version 80991 (0.0008) -[2023-10-09 11:31:07,140][23468] Updated weights for policy 0, policy_version 80553 (0.0010) -[2023-10-09 11:31:07,521][23468] Updated weights for policy 0, policy_version 80563 (0.0008) -[2023-10-09 11:31:07,899][23468] Updated weights for policy 0, policy_version 80573 (0.0008) -[2023-10-09 11:31:09,985][23469] Updated weights for policy 1, policy_version 81001 (0.0008) -[2023-10-09 11:31:10,363][23469] Updated weights for policy 1, policy_version 81011 (0.0010) -[2023-10-09 11:31:10,730][23469] Updated weights for policy 1, policy_version 81021 (0.0009) -[2023-10-09 11:31:11,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 165478400. Throughput: 0: 1771.2, 1: 1810.9. Samples: 41375464. Policy #0 lag: (min: 10.0, avg: 17.7, max: 42.0) -[2023-10-09 11:31:11,078][22500] Avg episode reward: [(0, '9.890'), (1, '9.580')] -[2023-10-09 11:31:11,779][23468] Updated weights for policy 0, policy_version 80583 (0.0011) -[2023-10-09 11:31:12,157][23468] Updated weights for policy 0, policy_version 80593 (0.0007) -[2023-10-09 11:31:12,534][23468] Updated weights for policy 0, policy_version 80603 (0.0007) -[2023-10-09 11:31:14,345][23469] Updated weights for policy 1, policy_version 81031 (0.0009) -[2023-10-09 11:31:14,723][23469] Updated weights for policy 1, policy_version 81041 (0.0007) -[2023-10-09 11:31:15,097][23469] Updated weights for policy 1, policy_version 81051 (0.0008) -[2023-10-09 11:31:16,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 165543936. Throughput: 0: 1781.2, 1: 1811.2. Samples: 41396632. Policy #0 lag: (min: 10.0, avg: 17.7, max: 42.0) -[2023-10-09 11:31:16,078][22500] Avg episode reward: [(0, '10.520'), (1, '9.760')] -[2023-10-09 11:31:16,292][23468] Updated weights for policy 0, policy_version 80613 (0.0007) -[2023-10-09 11:31:16,667][23468] Updated weights for policy 0, policy_version 80623 (0.0008) -[2023-10-09 11:31:17,047][23468] Updated weights for policy 0, policy_version 80633 (0.0009) -[2023-10-09 11:31:18,817][23469] Updated weights for policy 1, policy_version 81061 (0.0008) -[2023-10-09 11:31:19,179][23469] Updated weights for policy 1, policy_version 81071 (0.0009) -[2023-10-09 11:31:19,555][23469] Updated weights for policy 1, policy_version 81081 (0.0008) -[2023-10-09 11:31:20,748][23468] Updated weights for policy 0, policy_version 80643 (0.0009) -[2023-10-09 11:31:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 165609472. Throughput: 0: 1768.5, 1: 1816.3. Samples: 41407754. Policy #0 lag: (min: 10.0, avg: 17.7, max: 42.0) -[2023-10-09 11:31:21,078][22500] Avg episode reward: [(0, '10.550'), (1, '9.230')] -[2023-10-09 11:31:21,113][23468] Updated weights for policy 0, policy_version 80653 (0.0010) -[2023-10-09 11:31:21,484][23468] Updated weights for policy 0, policy_version 80663 (0.0008) -[2023-10-09 11:31:23,364][23469] Updated weights for policy 1, policy_version 81091 (0.0008) -[2023-10-09 11:31:23,742][23469] Updated weights for policy 1, policy_version 81101 (0.0009) -[2023-10-09 11:31:24,111][23469] Updated weights for policy 1, policy_version 81111 (0.0008) -[2023-10-09 11:31:25,129][23468] Updated weights for policy 0, policy_version 80673 (0.0009) -[2023-10-09 11:31:25,500][23468] Updated weights for policy 0, policy_version 80683 (0.0011) -[2023-10-09 11:31:25,877][23468] Updated weights for policy 0, policy_version 80693 (0.0009) -[2023-10-09 11:31:26,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 165675008. Throughput: 0: 1774.9, 1: 1798.1. Samples: 41428602. Policy #0 lag: (min: 10.0, avg: 17.7, max: 42.0) -[2023-10-09 11:31:26,078][22500] Avg episode reward: [(0, '10.890'), (1, '9.070')] -[2023-10-09 11:31:26,247][23468] Updated weights for policy 0, policy_version 80703 (0.0009) -[2023-10-09 11:31:27,915][23469] Updated weights for policy 1, policy_version 81121 (0.0009) -[2023-10-09 11:31:28,297][23469] Updated weights for policy 1, policy_version 81131 (0.0008) -[2023-10-09 11:31:28,670][23469] Updated weights for policy 1, policy_version 81141 (0.0007) -[2023-10-09 11:31:29,032][23469] Updated weights for policy 1, policy_version 81151 (0.0010) -[2023-10-09 11:31:29,989][23468] Updated weights for policy 0, policy_version 80713 (0.0011) -[2023-10-09 11:31:30,360][23468] Updated weights for policy 0, policy_version 80723 (0.0010) -[2023-10-09 11:31:30,739][23468] Updated weights for policy 0, policy_version 80733 (0.0008) -[2023-10-09 11:31:31,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 165773312. Throughput: 0: 1789.2, 1: 1799.1. Samples: 41450328. Policy #0 lag: (min: 10.0, avg: 17.7, max: 42.0) -[2023-10-09 11:31:31,078][22500] Avg episode reward: [(0, '11.010'), (1, '8.470')] -[2023-10-09 11:31:32,938][23469] Updated weights for policy 1, policy_version 81161 (0.0009) -[2023-10-09 11:31:33,308][23469] Updated weights for policy 1, policy_version 81171 (0.0010) -[2023-10-09 11:31:33,679][23469] Updated weights for policy 1, policy_version 81181 (0.0011) -[2023-10-09 11:31:34,756][23468] Updated weights for policy 0, policy_version 80743 (0.0007) -[2023-10-09 11:31:35,135][23468] Updated weights for policy 0, policy_version 80753 (0.0007) -[2023-10-09 11:31:35,502][23468] Updated weights for policy 0, policy_version 80763 (0.0009) -[2023-10-09 11:31:36,078][22500] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 165838848. Throughput: 0: 1767.0, 1: 1798.0. Samples: 41460676. Policy #0 lag: (min: 10.0, avg: 17.7, max: 42.0) -[2023-10-09 11:31:36,079][22500] Avg episode reward: [(0, '11.180'), (1, '8.110')] -[2023-10-09 11:31:37,445][23469] Updated weights for policy 1, policy_version 81191 (0.0008) -[2023-10-09 11:31:37,817][23469] Updated weights for policy 1, policy_version 81201 (0.0008) -[2023-10-09 11:31:38,193][23469] Updated weights for policy 1, policy_version 81211 (0.0009) -[2023-10-09 11:31:39,275][23468] Updated weights for policy 0, policy_version 80773 (0.0010) -[2023-10-09 11:31:39,644][23468] Updated weights for policy 0, policy_version 80783 (0.0007) -[2023-10-09 11:31:40,010][23468] Updated weights for policy 0, policy_version 80793 (0.0010) -[2023-10-09 11:31:41,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 165904384. Throughput: 0: 1794.0, 1: 1797.3. Samples: 41482654. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:31:41,079][22500] Avg episode reward: [(0, '10.660'), (1, '8.980')] -[2023-10-09 11:31:42,134][23469] Updated weights for policy 1, policy_version 81221 (0.0011) -[2023-10-09 11:31:42,531][23469] Updated weights for policy 1, policy_version 81231 (0.0010) -[2023-10-09 11:31:42,910][23469] Updated weights for policy 1, policy_version 81241 (0.0009) -[2023-10-09 11:31:44,034][23468] Updated weights for policy 0, policy_version 80803 (0.0010) -[2023-10-09 11:31:44,406][23468] Updated weights for policy 0, policy_version 80813 (0.0010) -[2023-10-09 11:31:44,781][23468] Updated weights for policy 0, policy_version 80823 (0.0010) -[2023-10-09 11:31:46,078][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 165969920. Throughput: 0: 1764.5, 1: 1790.8. Samples: 41503112. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:31:46,079][22500] Avg episode reward: [(0, '10.590'), (1, '9.290')] -[2023-10-09 11:31:46,672][23469] Updated weights for policy 1, policy_version 81251 (0.0009) -[2023-10-09 11:31:47,050][23469] Updated weights for policy 1, policy_version 81261 (0.0009) -[2023-10-09 11:31:47,423][23469] Updated weights for policy 1, policy_version 81271 (0.0009) -[2023-10-09 11:31:48,679][23468] Updated weights for policy 0, policy_version 80833 (0.0010) -[2023-10-09 11:31:49,047][23468] Updated weights for policy 0, policy_version 80843 (0.0008) -[2023-10-09 11:31:49,418][23468] Updated weights for policy 0, policy_version 80853 (0.0008) -[2023-10-09 11:31:49,793][23468] Updated weights for policy 0, policy_version 80863 (0.0007) -[2023-10-09 11:31:50,989][23469] Updated weights for policy 1, policy_version 81281 (0.0009) -[2023-10-09 11:31:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 166035456. Throughput: 0: 1797.1, 1: 1778.9. Samples: 41514328. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:31:51,078][22500] Avg episode reward: [(0, '10.970'), (1, '9.180')] -[2023-10-09 11:31:51,366][23469] Updated weights for policy 1, policy_version 81291 (0.0009) -[2023-10-09 11:31:51,721][23469] Updated weights for policy 1, policy_version 81301 (0.0008) -[2023-10-09 11:31:52,092][23469] Updated weights for policy 1, policy_version 81311 (0.0007) -[2023-10-09 11:31:53,523][23468] Updated weights for policy 0, policy_version 80873 (0.0010) -[2023-10-09 11:31:53,891][23468] Updated weights for policy 0, policy_version 80883 (0.0010) -[2023-10-09 11:31:54,254][23468] Updated weights for policy 0, policy_version 80893 (0.0010) -[2023-10-09 11:31:55,738][23469] Updated weights for policy 1, policy_version 81321 (0.0009) -[2023-10-09 11:31:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 166100992. Throughput: 0: 1772.1, 1: 1782.8. Samples: 41535434. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:31:56,078][22500] Avg episode reward: [(0, '11.210'), (1, '9.060')] -[2023-10-09 11:31:56,109][23469] Updated weights for policy 1, policy_version 81331 (0.0011) -[2023-10-09 11:31:56,467][23469] Updated weights for policy 1, policy_version 81341 (0.0010) -[2023-10-09 11:31:58,035][23468] Updated weights for policy 0, policy_version 80903 (0.0009) -[2023-10-09 11:31:58,408][23468] Updated weights for policy 0, policy_version 80913 (0.0010) -[2023-10-09 11:31:58,781][23468] Updated weights for policy 0, policy_version 80923 (0.0010) -[2023-10-09 11:32:00,226][23469] Updated weights for policy 1, policy_version 81351 (0.0009) -[2023-10-09 11:32:00,602][23469] Updated weights for policy 1, policy_version 81361 (0.0011) -[2023-10-09 11:32:00,963][23469] Updated weights for policy 1, policy_version 81371 (0.0010) -[2023-10-09 11:32:01,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 166166528. Throughput: 0: 1768.7, 1: 1791.3. Samples: 41556830. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:32:01,078][22500] Avg episode reward: [(0, '10.980'), (1, '9.110')] -[2023-10-09 11:32:02,471][23468] Updated weights for policy 0, policy_version 80933 (0.0009) -[2023-10-09 11:32:02,839][23468] Updated weights for policy 0, policy_version 80943 (0.0009) -[2023-10-09 11:32:03,218][23468] Updated weights for policy 0, policy_version 80953 (0.0010) -[2023-10-09 11:32:04,847][23469] Updated weights for policy 1, policy_version 81381 (0.0011) -[2023-10-09 11:32:05,215][23469] Updated weights for policy 1, policy_version 81391 (0.0007) -[2023-10-09 11:32:05,592][23469] Updated weights for policy 1, policy_version 81401 (0.0008) -[2023-10-09 11:32:06,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 166264832. Throughput: 0: 1777.7, 1: 1780.9. Samples: 41567892. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:32:06,078][22500] Avg episode reward: [(0, '10.790'), (1, '9.030')] -[2023-10-09 11:32:06,999][23468] Updated weights for policy 0, policy_version 80963 (0.0007) -[2023-10-09 11:32:07,357][23468] Updated weights for policy 0, policy_version 80973 (0.0008) -[2023-10-09 11:32:07,739][23468] Updated weights for policy 0, policy_version 80983 (0.0009) -[2023-10-09 11:32:09,242][23469] Updated weights for policy 1, policy_version 81411 (0.0008) -[2023-10-09 11:32:09,603][23469] Updated weights for policy 1, policy_version 81421 (0.0008) -[2023-10-09 11:32:09,970][23469] Updated weights for policy 1, policy_version 81431 (0.0010) -[2023-10-09 11:32:11,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 166330368. Throughput: 0: 1776.6, 1: 1802.0. Samples: 41589640. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:32:11,078][22500] Avg episode reward: [(0, '10.830'), (1, '9.400')] -[2023-10-09 11:32:11,375][23468] Updated weights for policy 0, policy_version 80993 (0.0008) -[2023-10-09 11:32:11,744][23468] Updated weights for policy 0, policy_version 81003 (0.0009) -[2023-10-09 11:32:12,113][23468] Updated weights for policy 0, policy_version 81013 (0.0007) -[2023-10-09 11:32:12,485][23468] Updated weights for policy 0, policy_version 81023 (0.0007) -[2023-10-09 11:32:13,780][23469] Updated weights for policy 1, policy_version 81441 (0.0010) -[2023-10-09 11:32:14,155][23469] Updated weights for policy 1, policy_version 81451 (0.0009) -[2023-10-09 11:32:14,533][23469] Updated weights for policy 1, policy_version 81461 (0.0008) -[2023-10-09 11:32:14,907][23469] Updated weights for policy 1, policy_version 81471 (0.0008) -[2023-10-09 11:32:16,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 166395904. Throughput: 0: 1796.6, 1: 1784.9. Samples: 41611496. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:32:16,078][22500] Avg episode reward: [(0, '11.460'), (1, '9.740')] -[2023-10-09 11:32:16,088][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000081472_83427328.pth... -[2023-10-09 11:32:16,106][23468] Updated weights for policy 0, policy_version 81033 (0.0008) -[2023-10-09 11:32:16,123][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000079776_81690624.pth -[2023-10-09 11:32:16,488][23468] Updated weights for policy 0, policy_version 81043 (0.0009) -[2023-10-09 11:32:16,863][23468] Updated weights for policy 0, policy_version 81053 (0.0007) -[2023-10-09 11:32:16,972][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000081056_83001344.pth... -[2023-10-09 11:32:17,001][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000079360_81264640.pth -[2023-10-09 11:32:18,537][23469] Updated weights for policy 1, policy_version 81481 (0.0007) -[2023-10-09 11:32:18,911][23469] Updated weights for policy 1, policy_version 81491 (0.0008) -[2023-10-09 11:32:19,284][23469] Updated weights for policy 1, policy_version 81501 (0.0010) -[2023-10-09 11:32:20,898][23468] Updated weights for policy 0, policy_version 81063 (0.0008) -[2023-10-09 11:32:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 166461440. Throughput: 0: 1779.8, 1: 1807.9. Samples: 41622124. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:32:21,078][22500] Avg episode reward: [(0, '11.490'), (1, '10.030')] -[2023-10-09 11:32:21,284][23468] Updated weights for policy 0, policy_version 81073 (0.0007) -[2023-10-09 11:32:21,650][23468] Updated weights for policy 0, policy_version 81083 (0.0008) -[2023-10-09 11:32:23,043][23469] Updated weights for policy 1, policy_version 81511 (0.0007) -[2023-10-09 11:32:23,423][23469] Updated weights for policy 1, policy_version 81521 (0.0010) -[2023-10-09 11:32:23,790][23469] Updated weights for policy 1, policy_version 81531 (0.0011) -[2023-10-09 11:32:25,192][23468] Updated weights for policy 0, policy_version 81093 (0.0010) -[2023-10-09 11:32:25,566][23468] Updated weights for policy 0, policy_version 81103 (0.0009) -[2023-10-09 11:32:25,932][23468] Updated weights for policy 0, policy_version 81113 (0.0010) -[2023-10-09 11:32:26,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 166526976. Throughput: 0: 1786.9, 1: 1790.7. Samples: 41643646. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:32:26,079][22500] Avg episode reward: [(0, '11.350'), (1, '10.030')] -[2023-10-09 11:32:27,633][23469] Updated weights for policy 1, policy_version 81541 (0.0007) -[2023-10-09 11:32:28,028][23469] Updated weights for policy 1, policy_version 81551 (0.0008) -[2023-10-09 11:32:28,404][23469] Updated weights for policy 1, policy_version 81561 (0.0007) -[2023-10-09 11:32:29,621][23468] Updated weights for policy 0, policy_version 81123 (0.0009) -[2023-10-09 11:32:30,000][23468] Updated weights for policy 0, policy_version 81133 (0.0007) -[2023-10-09 11:32:30,381][23468] Updated weights for policy 0, policy_version 81143 (0.0007) -[2023-10-09 11:32:31,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 166625280. Throughput: 0: 1798.8, 1: 1799.1. Samples: 41665016. Policy #0 lag: (min: 8.0, avg: 32.2, max: 40.0) -[2023-10-09 11:32:31,078][22500] Avg episode reward: [(0, '11.210'), (1, '10.590')] -[2023-10-09 11:32:31,087][23343] Saving new best policy, reward=10.590! -[2023-10-09 11:32:32,056][23469] Updated weights for policy 1, policy_version 81571 (0.0010) -[2023-10-09 11:32:32,424][23469] Updated weights for policy 1, policy_version 81581 (0.0008) -[2023-10-09 11:32:32,795][23469] Updated weights for policy 1, policy_version 81591 (0.0007) -[2023-10-09 11:32:34,029][23468] Updated weights for policy 0, policy_version 81153 (0.0009) -[2023-10-09 11:32:34,405][23468] Updated weights for policy 0, policy_version 81163 (0.0008) -[2023-10-09 11:32:34,769][23468] Updated weights for policy 0, policy_version 81173 (0.0010) -[2023-10-09 11:32:35,139][23468] Updated weights for policy 0, policy_version 81183 (0.0010) -[2023-10-09 11:32:36,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 166690816. Throughput: 0: 1790.6, 1: 1801.2. Samples: 41675958. Policy #0 lag: (min: 8.0, avg: 32.2, max: 40.0) -[2023-10-09 11:32:36,078][22500] Avg episode reward: [(0, '11.990'), (1, '9.490')] -[2023-10-09 11:32:36,080][23265] Saving new best policy, reward=11.990! -[2023-10-09 11:32:36,547][23469] Updated weights for policy 1, policy_version 81601 (0.0008) -[2023-10-09 11:32:36,912][23469] Updated weights for policy 1, policy_version 81611 (0.0007) -[2023-10-09 11:32:37,285][23469] Updated weights for policy 1, policy_version 81621 (0.0008) -[2023-10-09 11:32:37,662][23469] Updated weights for policy 1, policy_version 81631 (0.0008) -[2023-10-09 11:32:38,865][23468] Updated weights for policy 0, policy_version 81193 (0.0010) -[2023-10-09 11:32:39,252][23468] Updated weights for policy 0, policy_version 81203 (0.0010) -[2023-10-09 11:32:39,629][23468] Updated weights for policy 0, policy_version 81213 (0.0009) -[2023-10-09 11:32:41,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 166756352. Throughput: 0: 1800.4, 1: 1802.2. Samples: 41697554. Policy #0 lag: (min: 8.0, avg: 32.2, max: 40.0) -[2023-10-09 11:32:41,078][22500] Avg episode reward: [(0, '11.110'), (1, '9.980')] -[2023-10-09 11:32:41,330][23469] Updated weights for policy 1, policy_version 81641 (0.0009) -[2023-10-09 11:32:41,696][23469] Updated weights for policy 1, policy_version 81651 (0.0009) -[2023-10-09 11:32:42,072][23469] Updated weights for policy 1, policy_version 81661 (0.0007) -[2023-10-09 11:32:43,459][23468] Updated weights for policy 0, policy_version 81223 (0.0009) -[2023-10-09 11:32:43,824][23468] Updated weights for policy 0, policy_version 81233 (0.0008) -[2023-10-09 11:32:44,202][23468] Updated weights for policy 0, policy_version 81243 (0.0009) -[2023-10-09 11:32:45,751][23469] Updated weights for policy 1, policy_version 81671 (0.0007) -[2023-10-09 11:32:46,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 166821888. Throughput: 0: 1787.2, 1: 1813.5. Samples: 41718864. Policy #0 lag: (min: 8.0, avg: 32.2, max: 40.0) -[2023-10-09 11:32:46,079][22500] Avg episode reward: [(0, '11.220'), (1, '10.100')] -[2023-10-09 11:32:46,118][23469] Updated weights for policy 1, policy_version 81681 (0.0007) -[2023-10-09 11:32:46,493][23469] Updated weights for policy 1, policy_version 81691 (0.0008) -[2023-10-09 11:32:47,876][23468] Updated weights for policy 0, policy_version 81253 (0.0009) -[2023-10-09 11:32:48,248][23468] Updated weights for policy 0, policy_version 81263 (0.0009) -[2023-10-09 11:32:48,620][23468] Updated weights for policy 0, policy_version 81273 (0.0010) -[2023-10-09 11:32:50,320][23469] Updated weights for policy 1, policy_version 81701 (0.0008) -[2023-10-09 11:32:50,691][23469] Updated weights for policy 1, policy_version 81711 (0.0007) -[2023-10-09 11:32:51,057][23469] Updated weights for policy 1, policy_version 81721 (0.0010) -[2023-10-09 11:32:51,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 166887424. Throughput: 0: 1802.4, 1: 1798.1. Samples: 41729916. Policy #0 lag: (min: 8.0, avg: 32.2, max: 40.0) -[2023-10-09 11:32:51,078][22500] Avg episode reward: [(0, '11.000'), (1, '9.550')] -[2023-10-09 11:32:52,299][23468] Updated weights for policy 0, policy_version 81283 (0.0009) -[2023-10-09 11:32:52,666][23468] Updated weights for policy 0, policy_version 81293 (0.0007) -[2023-10-09 11:32:53,042][23468] Updated weights for policy 0, policy_version 81303 (0.0007) -[2023-10-09 11:32:54,738][23469] Updated weights for policy 1, policy_version 81731 (0.0011) -[2023-10-09 11:32:55,113][23469] Updated weights for policy 1, policy_version 81741 (0.0010) -[2023-10-09 11:32:55,477][23469] Updated weights for policy 1, policy_version 81751 (0.0010) -[2023-10-09 11:32:56,078][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 166985728. Throughput: 0: 1791.3, 1: 1808.6. Samples: 41751636. Policy #0 lag: (min: 8.0, avg: 32.2, max: 40.0) -[2023-10-09 11:32:56,079][22500] Avg episode reward: [(0, '9.970'), (1, '9.750')] -[2023-10-09 11:32:56,727][23468] Updated weights for policy 0, policy_version 81313 (0.0008) -[2023-10-09 11:32:57,091][23468] Updated weights for policy 0, policy_version 81323 (0.0007) -[2023-10-09 11:32:57,466][23468] Updated weights for policy 0, policy_version 81333 (0.0010) -[2023-10-09 11:32:57,829][23468] Updated weights for policy 0, policy_version 81343 (0.0008) -[2023-10-09 11:32:59,287][23469] Updated weights for policy 1, policy_version 81761 (0.0009) -[2023-10-09 11:32:59,652][23469] Updated weights for policy 1, policy_version 81771 (0.0007) -[2023-10-09 11:33:00,020][23469] Updated weights for policy 1, policy_version 81781 (0.0007) -[2023-10-09 11:33:00,388][23469] Updated weights for policy 1, policy_version 81791 (0.0007) -[2023-10-09 11:33:01,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 167051264. Throughput: 0: 1792.6, 1: 1792.9. Samples: 41772846. Policy #0 lag: (min: 8.0, avg: 32.2, max: 40.0) -[2023-10-09 11:33:01,078][22500] Avg episode reward: [(0, '11.460'), (1, '8.310')] -[2023-10-09 11:33:01,603][23468] Updated weights for policy 0, policy_version 81353 (0.0010) -[2023-10-09 11:33:01,969][23468] Updated weights for policy 0, policy_version 81363 (0.0011) -[2023-10-09 11:33:02,340][23468] Updated weights for policy 0, policy_version 81373 (0.0011) -[2023-10-09 11:33:03,897][23469] Updated weights for policy 1, policy_version 81801 (0.0010) -[2023-10-09 11:33:04,276][23469] Updated weights for policy 1, policy_version 81811 (0.0009) -[2023-10-09 11:33:04,640][23469] Updated weights for policy 1, policy_version 81821 (0.0007) -[2023-10-09 11:33:06,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 167116800. Throughput: 0: 1787.4, 1: 1804.9. Samples: 41783780. Policy #0 lag: (min: 8.0, avg: 32.2, max: 40.0) -[2023-10-09 11:33:06,078][22500] Avg episode reward: [(0, '11.250'), (1, '9.280')] -[2023-10-09 11:33:06,251][23468] Updated weights for policy 0, policy_version 81383 (0.0009) -[2023-10-09 11:33:06,634][23468] Updated weights for policy 0, policy_version 81393 (0.0008) -[2023-10-09 11:33:07,006][23468] Updated weights for policy 0, policy_version 81403 (0.0007) -[2023-10-09 11:33:08,429][23469] Updated weights for policy 1, policy_version 81831 (0.0007) -[2023-10-09 11:33:08,803][23469] Updated weights for policy 1, policy_version 81841 (0.0009) -[2023-10-09 11:33:09,161][23469] Updated weights for policy 1, policy_version 81851 (0.0010) -[2023-10-09 11:33:10,776][23468] Updated weights for policy 0, policy_version 81413 (0.0008) -[2023-10-09 11:33:11,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 167182336. Throughput: 0: 1788.8, 1: 1794.0. Samples: 41804872. Policy #0 lag: (min: 8.0, avg: 32.2, max: 40.0) -[2023-10-09 11:33:11,078][22500] Avg episode reward: [(0, '10.820'), (1, '8.870')] -[2023-10-09 11:33:11,152][23468] Updated weights for policy 0, policy_version 81423 (0.0008) -[2023-10-09 11:33:11,518][23468] Updated weights for policy 0, policy_version 81433 (0.0008) -[2023-10-09 11:33:12,969][23469] Updated weights for policy 1, policy_version 81861 (0.0008) -[2023-10-09 11:33:13,355][23469] Updated weights for policy 1, policy_version 81871 (0.0007) -[2023-10-09 11:33:13,726][23469] Updated weights for policy 1, policy_version 81881 (0.0007) -[2023-10-09 11:33:15,346][23468] Updated weights for policy 0, policy_version 81443 (0.0008) -[2023-10-09 11:33:15,717][23468] Updated weights for policy 0, policy_version 81453 (0.0009) -[2023-10-09 11:33:16,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 167247872. Throughput: 0: 1802.0, 1: 1801.9. Samples: 41827192. Policy #0 lag: (min: 8.0, avg: 32.2, max: 40.0) -[2023-10-09 11:33:16,078][22500] Avg episode reward: [(0, '11.310'), (1, '9.590')] -[2023-10-09 11:33:16,088][23468] Updated weights for policy 0, policy_version 81463 (0.0007) -[2023-10-09 11:33:17,198][23469] Updated weights for policy 1, policy_version 81891 (0.0009) -[2023-10-09 11:33:17,557][23469] Updated weights for policy 1, policy_version 81901 (0.0009) -[2023-10-09 11:33:17,931][23469] Updated weights for policy 1, policy_version 81911 (0.0007) -[2023-10-09 11:33:19,775][23468] Updated weights for policy 0, policy_version 81473 (0.0008) -[2023-10-09 11:33:20,143][23468] Updated weights for policy 0, policy_version 81483 (0.0008) -[2023-10-09 11:33:20,521][23468] Updated weights for policy 0, policy_version 81493 (0.0008) -[2023-10-09 11:33:20,896][23468] Updated weights for policy 0, policy_version 81503 (0.0010) -[2023-10-09 11:33:21,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 167346176. Throughput: 0: 1783.3, 1: 1803.9. Samples: 41837382. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:33:21,078][22500] Avg episode reward: [(0, '10.140'), (1, '9.600')] -[2023-10-09 11:33:21,639][23469] Updated weights for policy 1, policy_version 81921 (0.0010) -[2023-10-09 11:33:22,010][23469] Updated weights for policy 1, policy_version 81931 (0.0009) -[2023-10-09 11:33:22,375][23469] Updated weights for policy 1, policy_version 81941 (0.0009) -[2023-10-09 11:33:22,742][23469] Updated weights for policy 1, policy_version 81951 (0.0009) -[2023-10-09 11:33:24,746][23468] Updated weights for policy 0, policy_version 81513 (0.0009) -[2023-10-09 11:33:25,124][23468] Updated weights for policy 0, policy_version 81523 (0.0008) -[2023-10-09 11:33:25,492][23468] Updated weights for policy 0, policy_version 81533 (0.0010) -[2023-10-09 11:33:26,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 167411712. Throughput: 0: 1801.1, 1: 1802.4. Samples: 41859710. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:33:26,078][22500] Avg episode reward: [(0, '10.440'), (1, '9.690')] -[2023-10-09 11:33:26,480][23469] Updated weights for policy 1, policy_version 81961 (0.0010) -[2023-10-09 11:33:26,851][23469] Updated weights for policy 1, policy_version 81971 (0.0010) -[2023-10-09 11:33:27,225][23469] Updated weights for policy 1, policy_version 81981 (0.0011) -[2023-10-09 11:33:29,172][23468] Updated weights for policy 0, policy_version 81543 (0.0009) -[2023-10-09 11:33:29,539][23468] Updated weights for policy 0, policy_version 81553 (0.0008) -[2023-10-09 11:33:29,912][23468] Updated weights for policy 0, policy_version 81563 (0.0008) -[2023-10-09 11:33:31,047][23469] Updated weights for policy 1, policy_version 81991 (0.0008) -[2023-10-09 11:33:31,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 167477248. Throughput: 0: 1783.4, 1: 1812.5. Samples: 41880680. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:33:31,078][22500] Avg episode reward: [(0, '10.520'), (1, '10.170')] -[2023-10-09 11:33:31,411][23469] Updated weights for policy 1, policy_version 82001 (0.0008) -[2023-10-09 11:33:31,777][23469] Updated weights for policy 1, policy_version 82011 (0.0008) -[2023-10-09 11:33:33,718][23468] Updated weights for policy 0, policy_version 81573 (0.0010) -[2023-10-09 11:33:34,088][23468] Updated weights for policy 0, policy_version 81583 (0.0010) -[2023-10-09 11:33:34,456][23468] Updated weights for policy 0, policy_version 81593 (0.0010) -[2023-10-09 11:33:35,476][23469] Updated weights for policy 1, policy_version 82021 (0.0008) -[2023-10-09 11:33:35,849][23469] Updated weights for policy 1, policy_version 82031 (0.0009) -[2023-10-09 11:33:36,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 167542784. Throughput: 0: 1794.7, 1: 1807.0. Samples: 41891990. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:33:36,078][22500] Avg episode reward: [(0, '10.830'), (1, '9.660')] -[2023-10-09 11:33:36,224][23469] Updated weights for policy 1, policy_version 82041 (0.0009) -[2023-10-09 11:33:38,112][23468] Updated weights for policy 0, policy_version 81603 (0.0007) -[2023-10-09 11:33:38,479][23468] Updated weights for policy 0, policy_version 81613 (0.0008) -[2023-10-09 11:33:38,857][23468] Updated weights for policy 0, policy_version 81623 (0.0009) -[2023-10-09 11:33:39,981][23469] Updated weights for policy 1, policy_version 82051 (0.0009) -[2023-10-09 11:33:40,353][23469] Updated weights for policy 1, policy_version 82061 (0.0009) -[2023-10-09 11:33:40,731][23469] Updated weights for policy 1, policy_version 82071 (0.0008) -[2023-10-09 11:33:41,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 167641088. Throughput: 0: 1779.7, 1: 1812.0. Samples: 41913262. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:33:41,079][22500] Avg episode reward: [(0, '10.640'), (1, '10.030')] -[2023-10-09 11:33:42,551][23468] Updated weights for policy 0, policy_version 81633 (0.0011) -[2023-10-09 11:33:42,918][23468] Updated weights for policy 0, policy_version 81643 (0.0009) -[2023-10-09 11:33:43,282][23468] Updated weights for policy 0, policy_version 81653 (0.0010) -[2023-10-09 11:33:43,662][23468] Updated weights for policy 0, policy_version 81663 (0.0008) -[2023-10-09 11:33:44,395][23469] Updated weights for policy 1, policy_version 82081 (0.0008) -[2023-10-09 11:33:44,765][23469] Updated weights for policy 1, policy_version 82091 (0.0007) -[2023-10-09 11:33:45,137][23469] Updated weights for policy 1, policy_version 82101 (0.0007) -[2023-10-09 11:33:45,513][23469] Updated weights for policy 1, policy_version 82111 (0.0008) -[2023-10-09 11:33:46,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 167706624. Throughput: 0: 1776.2, 1: 1814.9. Samples: 41934448. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:33:46,078][22500] Avg episode reward: [(0, '10.740'), (1, '9.950')] -[2023-10-09 11:33:47,414][23468] Updated weights for policy 0, policy_version 81673 (0.0007) -[2023-10-09 11:33:47,784][23468] Updated weights for policy 0, policy_version 81683 (0.0009) -[2023-10-09 11:33:48,158][23468] Updated weights for policy 0, policy_version 81693 (0.0010) -[2023-10-09 11:33:49,073][23469] Updated weights for policy 1, policy_version 82121 (0.0009) -[2023-10-09 11:33:49,447][23469] Updated weights for policy 1, policy_version 82131 (0.0007) -[2023-10-09 11:33:49,820][23469] Updated weights for policy 1, policy_version 82141 (0.0010) -[2023-10-09 11:33:51,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 167772160. Throughput: 0: 1783.8, 1: 1817.0. Samples: 41945816. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:33:51,078][22500] Avg episode reward: [(0, '10.990'), (1, '9.590')] -[2023-10-09 11:33:52,075][23468] Updated weights for policy 0, policy_version 81703 (0.0007) -[2023-10-09 11:33:52,434][23468] Updated weights for policy 0, policy_version 81713 (0.0007) -[2023-10-09 11:33:52,827][23468] Updated weights for policy 0, policy_version 81723 (0.0010) -[2023-10-09 11:33:53,601][23469] Updated weights for policy 1, policy_version 82151 (0.0008) -[2023-10-09 11:33:53,965][23469] Updated weights for policy 1, policy_version 82161 (0.0009) -[2023-10-09 11:33:54,336][23469] Updated weights for policy 1, policy_version 82171 (0.0010) -[2023-10-09 11:33:56,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 167837696. Throughput: 0: 1783.1, 1: 1816.0. Samples: 41966836. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:33:56,079][22500] Avg episode reward: [(0, '11.390'), (1, '9.400')] -[2023-10-09 11:33:56,655][23468] Updated weights for policy 0, policy_version 81733 (0.0009) -[2023-10-09 11:33:57,046][23468] Updated weights for policy 0, policy_version 81743 (0.0008) -[2023-10-09 11:33:57,417][23468] Updated weights for policy 0, policy_version 81753 (0.0008) -[2023-10-09 11:33:58,183][23469] Updated weights for policy 1, policy_version 82181 (0.0009) -[2023-10-09 11:33:58,577][23469] Updated weights for policy 1, policy_version 82191 (0.0008) -[2023-10-09 11:33:58,940][23469] Updated weights for policy 1, policy_version 82201 (0.0009) -[2023-10-09 11:34:01,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 167903232. Throughput: 0: 1785.7, 1: 1808.8. Samples: 41988944. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:34:01,078][22500] Avg episode reward: [(0, '11.330'), (1, '9.280')] -[2023-10-09 11:34:01,154][23468] Updated weights for policy 0, policy_version 81763 (0.0007) -[2023-10-09 11:34:01,528][23468] Updated weights for policy 0, policy_version 81773 (0.0009) -[2023-10-09 11:34:01,890][23468] Updated weights for policy 0, policy_version 81783 (0.0010) -[2023-10-09 11:34:02,710][23469] Updated weights for policy 1, policy_version 82211 (0.0007) -[2023-10-09 11:34:03,085][23469] Updated weights for policy 1, policy_version 82221 (0.0009) -[2023-10-09 11:34:03,458][23469] Updated weights for policy 1, policy_version 82231 (0.0009) -[2023-10-09 11:34:05,422][23468] Updated weights for policy 0, policy_version 81793 (0.0007) -[2023-10-09 11:34:05,798][23468] Updated weights for policy 0, policy_version 81803 (0.0008) -[2023-10-09 11:34:06,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 167968768. Throughput: 0: 1782.9, 1: 1808.4. Samples: 41998992. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:34:06,078][22500] Avg episode reward: [(0, '10.630'), (1, '9.550')] -[2023-10-09 11:34:06,168][23468] Updated weights for policy 0, policy_version 81813 (0.0007) -[2023-10-09 11:34:06,539][23468] Updated weights for policy 0, policy_version 81823 (0.0007) -[2023-10-09 11:34:07,188][23469] Updated weights for policy 1, policy_version 82241 (0.0008) -[2023-10-09 11:34:07,544][23469] Updated weights for policy 1, policy_version 82251 (0.0008) -[2023-10-09 11:34:07,908][23469] Updated weights for policy 1, policy_version 82261 (0.0009) -[2023-10-09 11:34:08,281][23469] Updated weights for policy 1, policy_version 82271 (0.0008) -[2023-10-09 11:34:10,402][23468] Updated weights for policy 0, policy_version 81833 (0.0010) -[2023-10-09 11:34:10,776][23468] Updated weights for policy 0, policy_version 81843 (0.0011) -[2023-10-09 11:34:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 168034304. Throughput: 0: 1792.4, 1: 1807.3. Samples: 42021700. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:34:11,078][22500] Avg episode reward: [(0, '9.650'), (1, '9.370')] -[2023-10-09 11:34:11,147][23468] Updated weights for policy 0, policy_version 81853 (0.0011) -[2023-10-09 11:34:11,868][23469] Updated weights for policy 1, policy_version 82281 (0.0010) -[2023-10-09 11:34:12,234][23469] Updated weights for policy 1, policy_version 82291 (0.0011) -[2023-10-09 11:34:12,603][23469] Updated weights for policy 1, policy_version 82301 (0.0008) -[2023-10-09 11:34:15,036][23468] Updated weights for policy 0, policy_version 81863 (0.0011) -[2023-10-09 11:34:15,406][23468] Updated weights for policy 0, policy_version 81873 (0.0011) -[2023-10-09 11:34:15,772][23468] Updated weights for policy 0, policy_version 81883 (0.0011) -[2023-10-09 11:34:16,078][22500] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 168132608. Throughput: 0: 1811.4, 1: 1806.7. Samples: 42043498. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:34:16,079][22500] Avg episode reward: [(0, '10.300'), (1, '9.680')] -[2023-10-09 11:34:16,090][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000081888_83853312.pth... -[2023-10-09 11:34:16,124][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000080192_82116608.pth -[2023-10-09 11:34:16,374][23469] Updated weights for policy 1, policy_version 82311 (0.0009) -[2023-10-09 11:34:16,744][23469] Updated weights for policy 1, policy_version 82321 (0.0010) -[2023-10-09 11:34:17,123][23469] Updated weights for policy 1, policy_version 82331 (0.0011) -[2023-10-09 11:34:17,304][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000082336_84312064.pth... -[2023-10-09 11:34:17,342][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000080640_82575360.pth -[2023-10-09 11:34:19,367][23468] Updated weights for policy 0, policy_version 81893 (0.0009) -[2023-10-09 11:34:19,741][23468] Updated weights for policy 0, policy_version 81903 (0.0010) -[2023-10-09 11:34:20,111][23468] Updated weights for policy 0, policy_version 81913 (0.0009) -[2023-10-09 11:34:20,655][23469] Updated weights for policy 1, policy_version 82341 (0.0008) -[2023-10-09 11:34:21,019][23469] Updated weights for policy 1, policy_version 82351 (0.0009) -[2023-10-09 11:34:21,077][22500] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 168198144. Throughput: 0: 1795.2, 1: 1805.9. Samples: 42054040. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:34:21,079][22500] Avg episode reward: [(0, '9.800'), (1, '9.180')] -[2023-10-09 11:34:21,392][23469] Updated weights for policy 1, policy_version 82361 (0.0007) -[2023-10-09 11:34:23,778][23468] Updated weights for policy 0, policy_version 81923 (0.0010) -[2023-10-09 11:34:24,150][23468] Updated weights for policy 0, policy_version 81933 (0.0008) -[2023-10-09 11:34:24,520][23468] Updated weights for policy 0, policy_version 81943 (0.0007) -[2023-10-09 11:34:25,291][23469] Updated weights for policy 1, policy_version 82371 (0.0008) -[2023-10-09 11:34:25,651][23469] Updated weights for policy 1, policy_version 82381 (0.0008) -[2023-10-09 11:34:26,016][23469] Updated weights for policy 1, policy_version 82391 (0.0007) -[2023-10-09 11:34:26,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 168263680. Throughput: 0: 1812.4, 1: 1803.1. Samples: 42075960. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:34:26,078][22500] Avg episode reward: [(0, '10.540'), (1, '9.360')] -[2023-10-09 11:34:28,275][23468] Updated weights for policy 0, policy_version 81953 (0.0008) -[2023-10-09 11:34:28,647][23468] Updated weights for policy 0, policy_version 81963 (0.0009) -[2023-10-09 11:34:29,021][23468] Updated weights for policy 0, policy_version 81973 (0.0008) -[2023-10-09 11:34:29,392][23468] Updated weights for policy 0, policy_version 81983 (0.0007) -[2023-10-09 11:34:29,775][23469] Updated weights for policy 1, policy_version 82401 (0.0008) -[2023-10-09 11:34:30,147][23469] Updated weights for policy 1, policy_version 82411 (0.0008) -[2023-10-09 11:34:30,513][23469] Updated weights for policy 1, policy_version 82421 (0.0007) -[2023-10-09 11:34:30,874][23469] Updated weights for policy 1, policy_version 82431 (0.0007) -[2023-10-09 11:34:31,078][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 168361984. Throughput: 0: 1795.6, 1: 1804.3. Samples: 42096444. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:34:31,079][22500] Avg episode reward: [(0, '11.270'), (1, '9.240')] -[2023-10-09 11:34:33,117][23468] Updated weights for policy 0, policy_version 81993 (0.0009) -[2023-10-09 11:34:33,493][23468] Updated weights for policy 0, policy_version 82003 (0.0011) -[2023-10-09 11:34:33,866][23468] Updated weights for policy 0, policy_version 82013 (0.0008) -[2023-10-09 11:34:34,586][23469] Updated weights for policy 1, policy_version 82441 (0.0008) -[2023-10-09 11:34:34,952][23469] Updated weights for policy 1, policy_version 82451 (0.0007) -[2023-10-09 11:34:35,322][23469] Updated weights for policy 1, policy_version 82461 (0.0009) -[2023-10-09 11:34:36,077][22500] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 168427520. Throughput: 0: 1815.5, 1: 1796.5. Samples: 42108358. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:34:36,078][22500] Avg episode reward: [(0, '10.830'), (1, '9.590')] -[2023-10-09 11:34:37,654][23468] Updated weights for policy 0, policy_version 82023 (0.0008) -[2023-10-09 11:34:38,023][23468] Updated weights for policy 0, policy_version 82033 (0.0009) -[2023-10-09 11:34:38,401][23468] Updated weights for policy 0, policy_version 82043 (0.0008) -[2023-10-09 11:34:38,990][23469] Updated weights for policy 1, policy_version 82471 (0.0008) -[2023-10-09 11:34:39,372][23469] Updated weights for policy 1, policy_version 82481 (0.0007) -[2023-10-09 11:34:39,757][23469] Updated weights for policy 1, policy_version 82491 (0.0009) -[2023-10-09 11:34:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 168493056. Throughput: 0: 1795.4, 1: 1804.0. Samples: 42128810. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:34:41,079][22500] Avg episode reward: [(0, '10.930'), (1, '9.930')] -[2023-10-09 11:34:42,221][23468] Updated weights for policy 0, policy_version 82053 (0.0008) -[2023-10-09 11:34:42,611][23468] Updated weights for policy 0, policy_version 82063 (0.0008) -[2023-10-09 11:34:42,976][23468] Updated weights for policy 0, policy_version 82073 (0.0010) -[2023-10-09 11:34:43,569][23469] Updated weights for policy 1, policy_version 82501 (0.0010) -[2023-10-09 11:34:43,952][23469] Updated weights for policy 1, policy_version 82511 (0.0008) -[2023-10-09 11:34:44,315][23469] Updated weights for policy 1, policy_version 82521 (0.0010) -[2023-10-09 11:34:46,078][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 168558592. Throughput: 0: 1804.8, 1: 1795.2. Samples: 42150942. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:34:46,079][22500] Avg episode reward: [(0, '10.400'), (1, '9.480')] -[2023-10-09 11:34:46,637][23468] Updated weights for policy 0, policy_version 82083 (0.0009) -[2023-10-09 11:34:47,011][23468] Updated weights for policy 0, policy_version 82093 (0.0008) -[2023-10-09 11:34:47,383][23468] Updated weights for policy 0, policy_version 82103 (0.0011) -[2023-10-09 11:34:48,194][23469] Updated weights for policy 1, policy_version 82531 (0.0011) -[2023-10-09 11:34:48,565][23469] Updated weights for policy 1, policy_version 82541 (0.0009) -[2023-10-09 11:34:48,943][23469] Updated weights for policy 1, policy_version 82551 (0.0007) -[2023-10-09 11:34:50,956][23468] Updated weights for policy 0, policy_version 82113 (0.0010) -[2023-10-09 11:34:51,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 168624128. Throughput: 0: 1795.2, 1: 1808.8. Samples: 42161168. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:34:51,078][22500] Avg episode reward: [(0, '10.290'), (1, '9.910')] -[2023-10-09 11:34:51,339][23468] Updated weights for policy 0, policy_version 82123 (0.0008) -[2023-10-09 11:34:51,712][23468] Updated weights for policy 0, policy_version 82133 (0.0009) -[2023-10-09 11:34:52,075][23468] Updated weights for policy 0, policy_version 82143 (0.0007) -[2023-10-09 11:34:52,692][23469] Updated weights for policy 1, policy_version 82561 (0.0009) -[2023-10-09 11:34:53,063][23469] Updated weights for policy 1, policy_version 82571 (0.0008) -[2023-10-09 11:34:53,429][23469] Updated weights for policy 1, policy_version 82581 (0.0008) -[2023-10-09 11:34:53,801][23469] Updated weights for policy 1, policy_version 82591 (0.0008) -[2023-10-09 11:34:55,828][23468] Updated weights for policy 0, policy_version 82153 (0.0009) -[2023-10-09 11:34:56,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 168689664. Throughput: 0: 1794.8, 1: 1789.2. Samples: 42182976. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:34:56,078][22500] Avg episode reward: [(0, '10.350'), (1, '9.350')] -[2023-10-09 11:34:56,195][23468] Updated weights for policy 0, policy_version 82163 (0.0011) -[2023-10-09 11:34:56,569][23468] Updated weights for policy 0, policy_version 82173 (0.0010) -[2023-10-09 11:34:57,614][23469] Updated weights for policy 1, policy_version 82601 (0.0008) -[2023-10-09 11:34:57,989][23469] Updated weights for policy 1, policy_version 82611 (0.0010) -[2023-10-09 11:34:58,361][23469] Updated weights for policy 1, policy_version 82621 (0.0009) -[2023-10-09 11:35:00,484][23468] Updated weights for policy 0, policy_version 82183 (0.0008) -[2023-10-09 11:35:00,847][23468] Updated weights for policy 0, policy_version 82193 (0.0007) -[2023-10-09 11:35:01,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 168755200. Throughput: 0: 1803.7, 1: 1787.3. Samples: 42205090. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:35:01,078][22500] Avg episode reward: [(0, '9.960'), (1, '9.680')] -[2023-10-09 11:35:01,227][23468] Updated weights for policy 0, policy_version 82203 (0.0009) -[2023-10-09 11:35:02,271][23469] Updated weights for policy 1, policy_version 82631 (0.0008) -[2023-10-09 11:35:02,649][23469] Updated weights for policy 1, policy_version 82641 (0.0008) -[2023-10-09 11:35:03,027][23469] Updated weights for policy 1, policy_version 82651 (0.0009) -[2023-10-09 11:35:04,941][23468] Updated weights for policy 0, policy_version 82213 (0.0008) -[2023-10-09 11:35:05,321][23468] Updated weights for policy 0, policy_version 82223 (0.0008) -[2023-10-09 11:35:05,685][23468] Updated weights for policy 0, policy_version 82233 (0.0009) -[2023-10-09 11:35:06,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 168853504. Throughput: 0: 1791.3, 1: 1785.5. Samples: 42214994. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:35:06,078][22500] Avg episode reward: [(0, '9.950'), (1, '9.350')] -[2023-10-09 11:35:06,790][23469] Updated weights for policy 1, policy_version 82661 (0.0009) -[2023-10-09 11:35:07,151][23469] Updated weights for policy 1, policy_version 82671 (0.0007) -[2023-10-09 11:35:07,525][23469] Updated weights for policy 1, policy_version 82681 (0.0007) -[2023-10-09 11:35:09,471][23468] Updated weights for policy 0, policy_version 82243 (0.0008) -[2023-10-09 11:35:09,852][23468] Updated weights for policy 0, policy_version 82253 (0.0008) -[2023-10-09 11:35:10,228][23468] Updated weights for policy 0, policy_version 82263 (0.0008) -[2023-10-09 11:35:11,078][22500] Fps is (10 sec: 16383.5, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 168919040. Throughput: 0: 1799.3, 1: 1788.5. Samples: 42237412. Policy #0 lag: (min: 9.0, avg: 28.7, max: 41.0) -[2023-10-09 11:35:11,079][22500] Avg episode reward: [(0, '9.680'), (1, '9.700')] -[2023-10-09 11:35:11,170][23469] Updated weights for policy 1, policy_version 82691 (0.0008) -[2023-10-09 11:35:11,539][23469] Updated weights for policy 1, policy_version 82701 (0.0010) -[2023-10-09 11:35:11,907][23469] Updated weights for policy 1, policy_version 82711 (0.0009) -[2023-10-09 11:35:13,894][23468] Updated weights for policy 0, policy_version 82273 (0.0008) -[2023-10-09 11:35:14,262][23468] Updated weights for policy 0, policy_version 82283 (0.0009) -[2023-10-09 11:35:14,646][23468] Updated weights for policy 0, policy_version 82293 (0.0010) -[2023-10-09 11:35:15,021][23468] Updated weights for policy 0, policy_version 82303 (0.0011) -[2023-10-09 11:35:15,506][23469] Updated weights for policy 1, policy_version 82721 (0.0009) -[2023-10-09 11:35:15,874][23469] Updated weights for policy 1, policy_version 82731 (0.0008) -[2023-10-09 11:35:16,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 168984576. Throughput: 0: 1777.6, 1: 1809.9. Samples: 42257878. Policy #0 lag: (min: 9.0, avg: 28.7, max: 41.0) -[2023-10-09 11:35:16,078][22500] Avg episode reward: [(0, '10.310'), (1, '9.660')] -[2023-10-09 11:35:16,239][23469] Updated weights for policy 1, policy_version 82741 (0.0007) -[2023-10-09 11:35:16,617][23469] Updated weights for policy 1, policy_version 82751 (0.0008) -[2023-10-09 11:35:18,642][23468] Updated weights for policy 0, policy_version 82313 (0.0008) -[2023-10-09 11:35:19,012][23468] Updated weights for policy 0, policy_version 82323 (0.0011) -[2023-10-09 11:35:19,392][23468] Updated weights for policy 0, policy_version 82333 (0.0008) -[2023-10-09 11:35:20,222][23469] Updated weights for policy 1, policy_version 82761 (0.0007) -[2023-10-09 11:35:20,603][23469] Updated weights for policy 1, policy_version 82771 (0.0011) -[2023-10-09 11:35:20,981][23469] Updated weights for policy 1, policy_version 82781 (0.0010) -[2023-10-09 11:35:21,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 169050112. Throughput: 0: 1796.2, 1: 1791.6. Samples: 42269806. Policy #0 lag: (min: 9.0, avg: 28.7, max: 41.0) -[2023-10-09 11:35:21,078][22500] Avg episode reward: [(0, '10.290'), (1, '9.490')] -[2023-10-09 11:35:23,263][23468] Updated weights for policy 0, policy_version 82343 (0.0008) -[2023-10-09 11:35:23,633][23468] Updated weights for policy 0, policy_version 82353 (0.0008) -[2023-10-09 11:35:24,006][23468] Updated weights for policy 0, policy_version 82363 (0.0010) -[2023-10-09 11:35:24,715][23469] Updated weights for policy 1, policy_version 82791 (0.0009) -[2023-10-09 11:35:25,090][23469] Updated weights for policy 1, policy_version 82801 (0.0007) -[2023-10-09 11:35:25,462][23469] Updated weights for policy 1, policy_version 82811 (0.0009) -[2023-10-09 11:35:26,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 169148416. Throughput: 0: 1783.4, 1: 1807.8. Samples: 42290414. Policy #0 lag: (min: 9.0, avg: 28.7, max: 41.0) -[2023-10-09 11:35:26,078][22500] Avg episode reward: [(0, '10.490'), (1, '9.670')] -[2023-10-09 11:35:27,832][23468] Updated weights for policy 0, policy_version 82373 (0.0008) -[2023-10-09 11:35:28,204][23468] Updated weights for policy 0, policy_version 82383 (0.0007) -[2023-10-09 11:35:28,581][23468] Updated weights for policy 0, policy_version 82393 (0.0008) -[2023-10-09 11:35:29,119][23469] Updated weights for policy 1, policy_version 82821 (0.0008) -[2023-10-09 11:35:29,504][23469] Updated weights for policy 1, policy_version 82831 (0.0010) -[2023-10-09 11:35:29,875][23469] Updated weights for policy 1, policy_version 82841 (0.0011) -[2023-10-09 11:35:31,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 169213952. Throughput: 0: 1781.7, 1: 1797.0. Samples: 42311984. Policy #0 lag: (min: 9.0, avg: 28.7, max: 41.0) -[2023-10-09 11:35:31,078][22500] Avg episode reward: [(0, '10.790'), (1, '9.820')] -[2023-10-09 11:35:32,215][23468] Updated weights for policy 0, policy_version 82403 (0.0010) -[2023-10-09 11:35:32,584][23468] Updated weights for policy 0, policy_version 82413 (0.0008) -[2023-10-09 11:35:32,964][23468] Updated weights for policy 0, policy_version 82423 (0.0008) -[2023-10-09 11:35:33,492][23469] Updated weights for policy 1, policy_version 82851 (0.0009) -[2023-10-09 11:35:33,860][23469] Updated weights for policy 1, policy_version 82861 (0.0011) -[2023-10-09 11:35:34,233][23469] Updated weights for policy 1, policy_version 82871 (0.0009) -[2023-10-09 11:35:36,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 169279488. Throughput: 0: 1789.1, 1: 1807.2. Samples: 42323002. Policy #0 lag: (min: 9.0, avg: 28.7, max: 41.0) -[2023-10-09 11:35:36,078][22500] Avg episode reward: [(0, '9.870'), (1, '9.680')] -[2023-10-09 11:35:36,757][23468] Updated weights for policy 0, policy_version 82433 (0.0008) -[2023-10-09 11:35:37,123][23468] Updated weights for policy 0, policy_version 82443 (0.0007) -[2023-10-09 11:35:37,504][23468] Updated weights for policy 0, policy_version 82453 (0.0007) -[2023-10-09 11:35:37,869][23468] Updated weights for policy 0, policy_version 82463 (0.0010) -[2023-10-09 11:35:38,047][23469] Updated weights for policy 1, policy_version 82881 (0.0008) -[2023-10-09 11:35:38,418][23469] Updated weights for policy 1, policy_version 82891 (0.0009) -[2023-10-09 11:35:38,788][23469] Updated weights for policy 1, policy_version 82901 (0.0011) -[2023-10-09 11:35:39,157][23469] Updated weights for policy 1, policy_version 82911 (0.0009) -[2023-10-09 11:35:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 169345024. Throughput: 0: 1784.8, 1: 1801.8. Samples: 42344370. Policy #0 lag: (min: 9.0, avg: 28.7, max: 41.0) -[2023-10-09 11:35:41,078][22500] Avg episode reward: [(0, '10.440'), (1, '9.760')] -[2023-10-09 11:35:41,515][23468] Updated weights for policy 0, policy_version 82473 (0.0009) -[2023-10-09 11:35:41,885][23468] Updated weights for policy 0, policy_version 82483 (0.0008) -[2023-10-09 11:35:42,264][23468] Updated weights for policy 0, policy_version 82493 (0.0009) -[2023-10-09 11:35:42,906][23469] Updated weights for policy 1, policy_version 82921 (0.0008) -[2023-10-09 11:35:43,280][23469] Updated weights for policy 1, policy_version 82931 (0.0008) -[2023-10-09 11:35:43,649][23469] Updated weights for policy 1, policy_version 82941 (0.0007) -[2023-10-09 11:35:46,049][23468] Updated weights for policy 0, policy_version 82503 (0.0010) -[2023-10-09 11:35:46,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 169410560. Throughput: 0: 1792.4, 1: 1804.6. Samples: 42366958. Policy #0 lag: (min: 9.0, avg: 28.7, max: 41.0) -[2023-10-09 11:35:46,078][22500] Avg episode reward: [(0, '10.160'), (1, '9.190')] -[2023-10-09 11:35:46,423][23468] Updated weights for policy 0, policy_version 82513 (0.0009) -[2023-10-09 11:35:46,799][23468] Updated weights for policy 0, policy_version 82523 (0.0007) -[2023-10-09 11:35:47,271][23469] Updated weights for policy 1, policy_version 82951 (0.0009) -[2023-10-09 11:35:47,639][23469] Updated weights for policy 1, policy_version 82961 (0.0009) -[2023-10-09 11:35:48,004][23469] Updated weights for policy 1, policy_version 82971 (0.0010) -[2023-10-09 11:35:50,586][23468] Updated weights for policy 0, policy_version 82533 (0.0009) -[2023-10-09 11:35:50,962][23468] Updated weights for policy 0, policy_version 82543 (0.0007) -[2023-10-09 11:35:51,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 169476096. Throughput: 0: 1789.2, 1: 1807.4. Samples: 42376844. Policy #0 lag: (min: 9.0, avg: 28.7, max: 41.0) -[2023-10-09 11:35:51,078][22500] Avg episode reward: [(0, '10.070'), (1, '8.830')] -[2023-10-09 11:35:51,340][23468] Updated weights for policy 0, policy_version 82553 (0.0007) -[2023-10-09 11:35:51,839][23469] Updated weights for policy 1, policy_version 82981 (0.0009) -[2023-10-09 11:35:52,207][23469] Updated weights for policy 1, policy_version 82991 (0.0007) -[2023-10-09 11:35:52,575][23469] Updated weights for policy 1, policy_version 83001 (0.0009) -[2023-10-09 11:35:55,122][23468] Updated weights for policy 0, policy_version 82563 (0.0008) -[2023-10-09 11:35:55,490][23468] Updated weights for policy 0, policy_version 82573 (0.0008) -[2023-10-09 11:35:55,864][23468] Updated weights for policy 0, policy_version 82583 (0.0009) -[2023-10-09 11:35:56,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 169541632. Throughput: 0: 1794.1, 1: 1801.0. Samples: 42399190. Policy #0 lag: (min: 9.0, avg: 28.7, max: 41.0) -[2023-10-09 11:35:56,078][22500] Avg episode reward: [(0, '10.620'), (1, '8.740')] -[2023-10-09 11:35:56,318][23469] Updated weights for policy 1, policy_version 83011 (0.0009) -[2023-10-09 11:35:56,695][23469] Updated weights for policy 1, policy_version 83021 (0.0007) -[2023-10-09 11:35:57,071][23469] Updated weights for policy 1, policy_version 83031 (0.0008) -[2023-10-09 11:35:59,548][23468] Updated weights for policy 0, policy_version 82593 (0.0008) -[2023-10-09 11:35:59,919][23468] Updated weights for policy 0, policy_version 82603 (0.0007) -[2023-10-09 11:36:00,289][23468] Updated weights for policy 0, policy_version 82613 (0.0007) -[2023-10-09 11:36:00,660][23468] Updated weights for policy 0, policy_version 82623 (0.0009) -[2023-10-09 11:36:00,825][23469] Updated weights for policy 1, policy_version 83041 (0.0008) -[2023-10-09 11:36:01,078][22500] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 169639936. Throughput: 0: 1809.9, 1: 1811.9. Samples: 42420856. Policy #0 lag: (min: 9.0, avg: 28.7, max: 41.0) -[2023-10-09 11:36:01,079][22500] Avg episode reward: [(0, '11.490'), (1, '8.860')] -[2023-10-09 11:36:01,186][23469] Updated weights for policy 1, policy_version 83051 (0.0011) -[2023-10-09 11:36:01,559][23469] Updated weights for policy 1, policy_version 83061 (0.0009) -[2023-10-09 11:36:01,927][23469] Updated weights for policy 1, policy_version 83071 (0.0008) -[2023-10-09 11:36:04,448][23468] Updated weights for policy 0, policy_version 82633 (0.0007) -[2023-10-09 11:36:04,819][23468] Updated weights for policy 0, policy_version 82643 (0.0007) -[2023-10-09 11:36:05,202][23468] Updated weights for policy 0, policy_version 82653 (0.0009) -[2023-10-09 11:36:05,604][23469] Updated weights for policy 1, policy_version 83081 (0.0009) -[2023-10-09 11:36:05,982][23469] Updated weights for policy 1, policy_version 83091 (0.0007) -[2023-10-09 11:36:06,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 169705472. Throughput: 0: 1796.7, 1: 1803.0. Samples: 42431792. Policy #0 lag: (min: 20.0, avg: 20.5, max: 34.0) -[2023-10-09 11:36:06,078][22500] Avg episode reward: [(0, '11.130'), (1, '9.080')] -[2023-10-09 11:36:06,362][23469] Updated weights for policy 1, policy_version 83101 (0.0009) -[2023-10-09 11:36:08,884][23468] Updated weights for policy 0, policy_version 82663 (0.0008) -[2023-10-09 11:36:09,258][23468] Updated weights for policy 0, policy_version 82673 (0.0009) -[2023-10-09 11:36:09,634][23468] Updated weights for policy 0, policy_version 82683 (0.0008) -[2023-10-09 11:36:09,962][23469] Updated weights for policy 1, policy_version 83111 (0.0008) -[2023-10-09 11:36:10,331][23469] Updated weights for policy 1, policy_version 83121 (0.0009) -[2023-10-09 11:36:10,701][23469] Updated weights for policy 1, policy_version 83131 (0.0008) -[2023-10-09 11:36:11,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 169803776. Throughput: 0: 1816.4, 1: 1812.0. Samples: 42453696. Policy #0 lag: (min: 20.0, avg: 20.5, max: 34.0) -[2023-10-09 11:36:11,078][22500] Avg episode reward: [(0, '11.160'), (1, '9.310')] -[2023-10-09 11:36:13,398][23468] Updated weights for policy 0, policy_version 82693 (0.0009) -[2023-10-09 11:36:13,789][23468] Updated weights for policy 0, policy_version 82703 (0.0010) -[2023-10-09 11:36:14,161][23468] Updated weights for policy 0, policy_version 82713 (0.0009) -[2023-10-09 11:36:14,512][23469] Updated weights for policy 1, policy_version 83141 (0.0010) -[2023-10-09 11:36:14,894][23469] Updated weights for policy 1, policy_version 83151 (0.0007) -[2023-10-09 11:36:15,267][23469] Updated weights for policy 1, policy_version 83161 (0.0008) -[2023-10-09 11:36:16,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 169869312. Throughput: 0: 1796.8, 1: 1804.8. Samples: 42474052. Policy #0 lag: (min: 20.0, avg: 20.5, max: 34.0) -[2023-10-09 11:36:16,078][22500] Avg episode reward: [(0, '10.240'), (1, '9.640')] -[2023-10-09 11:36:16,085][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000083168_85164032.pth... -[2023-10-09 11:36:16,085][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000082720_84705280.pth... -[2023-10-09 11:36:16,115][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000081056_83001344.pth -[2023-10-09 11:36:16,115][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000081472_83427328.pth -[2023-10-09 11:36:16,119][23343] Saving a milestone ./train_atari/atari_berzerk_APPO/checkpoint_p1/milestones/checkpoint_000083168_85164032.pth -[2023-10-09 11:36:16,119][23265] Saving a milestone ./train_atari/atari_berzerk_APPO/checkpoint_p0/milestones/checkpoint_000082720_84705280.pth -[2023-10-09 11:36:17,845][23468] Updated weights for policy 0, policy_version 82723 (0.0007) -[2023-10-09 11:36:18,223][23468] Updated weights for policy 0, policy_version 82733 (0.0008) -[2023-10-09 11:36:18,593][23468] Updated weights for policy 0, policy_version 82743 (0.0009) -[2023-10-09 11:36:18,926][23469] Updated weights for policy 1, policy_version 83171 (0.0009) -[2023-10-09 11:36:19,308][23469] Updated weights for policy 1, policy_version 83181 (0.0008) -[2023-10-09 11:36:19,672][23469] Updated weights for policy 1, policy_version 83191 (0.0008) -[2023-10-09 11:36:21,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 169934848. Throughput: 0: 1814.3, 1: 1812.5. Samples: 42486210. Policy #0 lag: (min: 20.0, avg: 20.5, max: 34.0) -[2023-10-09 11:36:21,079][22500] Avg episode reward: [(0, '9.960'), (1, '9.800')] -[2023-10-09 11:36:22,360][23468] Updated weights for policy 0, policy_version 82753 (0.0009) -[2023-10-09 11:36:22,732][23468] Updated weights for policy 0, policy_version 82763 (0.0010) -[2023-10-09 11:36:23,100][23468] Updated weights for policy 0, policy_version 82773 (0.0007) -[2023-10-09 11:36:23,474][23468] Updated weights for policy 0, policy_version 82783 (0.0007) -[2023-10-09 11:36:23,511][23469] Updated weights for policy 1, policy_version 83201 (0.0009) -[2023-10-09 11:36:23,873][23469] Updated weights for policy 1, policy_version 83211 (0.0011) -[2023-10-09 11:36:24,256][23469] Updated weights for policy 1, policy_version 83221 (0.0011) -[2023-10-09 11:36:24,627][23469] Updated weights for policy 1, policy_version 83231 (0.0010) -[2023-10-09 11:36:26,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 170000384. Throughput: 0: 1797.9, 1: 1797.7. Samples: 42506174. Policy #0 lag: (min: 20.0, avg: 20.5, max: 34.0) -[2023-10-09 11:36:26,078][22500] Avg episode reward: [(0, '10.310'), (1, '9.470')] -[2023-10-09 11:36:27,214][23468] Updated weights for policy 0, policy_version 82793 (0.0008) -[2023-10-09 11:36:27,594][23468] Updated weights for policy 0, policy_version 82803 (0.0010) -[2023-10-09 11:36:27,961][23468] Updated weights for policy 0, policy_version 82813 (0.0009) -[2023-10-09 11:36:28,457][23469] Updated weights for policy 1, policy_version 83241 (0.0010) -[2023-10-09 11:36:28,822][23469] Updated weights for policy 1, policy_version 83251 (0.0008) -[2023-10-09 11:36:29,193][23469] Updated weights for policy 1, policy_version 83261 (0.0009) -[2023-10-09 11:36:31,078][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 170065920. Throughput: 0: 1797.6, 1: 1793.2. Samples: 42528548. Policy #0 lag: (min: 20.0, avg: 20.5, max: 34.0) -[2023-10-09 11:36:31,079][22500] Avg episode reward: [(0, '10.270'), (1, '8.770')] -[2023-10-09 11:36:31,672][23468] Updated weights for policy 0, policy_version 82823 (0.0009) -[2023-10-09 11:36:32,038][23468] Updated weights for policy 0, policy_version 82833 (0.0008) -[2023-10-09 11:36:32,421][23468] Updated weights for policy 0, policy_version 82843 (0.0008) -[2023-10-09 11:36:33,097][23469] Updated weights for policy 1, policy_version 83271 (0.0010) -[2023-10-09 11:36:33,462][23469] Updated weights for policy 1, policy_version 83281 (0.0008) -[2023-10-09 11:36:33,841][23469] Updated weights for policy 1, policy_version 83291 (0.0008) -[2023-10-09 11:36:36,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 170131456. Throughput: 0: 1797.0, 1: 1801.2. Samples: 42538766. Policy #0 lag: (min: 20.0, avg: 20.5, max: 34.0) -[2023-10-09 11:36:36,078][22500] Avg episode reward: [(0, '11.020'), (1, '8.930')] -[2023-10-09 11:36:36,120][23468] Updated weights for policy 0, policy_version 82853 (0.0008) -[2023-10-09 11:36:36,497][23468] Updated weights for policy 0, policy_version 82863 (0.0009) -[2023-10-09 11:36:36,874][23468] Updated weights for policy 0, policy_version 82873 (0.0009) -[2023-10-09 11:36:37,610][23469] Updated weights for policy 1, policy_version 83301 (0.0010) -[2023-10-09 11:36:37,981][23469] Updated weights for policy 1, policy_version 83311 (0.0009) -[2023-10-09 11:36:38,346][23469] Updated weights for policy 1, policy_version 83321 (0.0009) -[2023-10-09 11:36:40,564][23468] Updated weights for policy 0, policy_version 82883 (0.0008) -[2023-10-09 11:36:40,940][23468] Updated weights for policy 0, policy_version 82893 (0.0008) -[2023-10-09 11:36:41,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 170196992. Throughput: 0: 1801.5, 1: 1792.5. Samples: 42560920. Policy #0 lag: (min: 20.0, avg: 20.5, max: 34.0) -[2023-10-09 11:36:41,078][22500] Avg episode reward: [(0, '11.000'), (1, '9.130')] -[2023-10-09 11:36:41,305][23468] Updated weights for policy 0, policy_version 82903 (0.0009) -[2023-10-09 11:36:42,061][23469] Updated weights for policy 1, policy_version 83331 (0.0009) -[2023-10-09 11:36:42,426][23469] Updated weights for policy 1, policy_version 83341 (0.0007) -[2023-10-09 11:36:42,793][23469] Updated weights for policy 1, policy_version 83351 (0.0009) -[2023-10-09 11:36:44,958][23468] Updated weights for policy 0, policy_version 82913 (0.0009) -[2023-10-09 11:36:45,337][23468] Updated weights for policy 0, policy_version 82923 (0.0011) -[2023-10-09 11:36:45,714][23468] Updated weights for policy 0, policy_version 82933 (0.0008) -[2023-10-09 11:36:46,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 170262528. Throughput: 0: 1814.8, 1: 1785.8. Samples: 42582882. Policy #0 lag: (min: 20.0, avg: 20.5, max: 34.0) -[2023-10-09 11:36:46,079][22500] Avg episode reward: [(0, '10.130'), (1, '8.860')] -[2023-10-09 11:36:46,095][23468] Updated weights for policy 0, policy_version 82943 (0.0007) -[2023-10-09 11:36:46,599][23469] Updated weights for policy 1, policy_version 83361 (0.0008) -[2023-10-09 11:36:46,957][23469] Updated weights for policy 1, policy_version 83371 (0.0007) -[2023-10-09 11:36:47,333][23469] Updated weights for policy 1, policy_version 83381 (0.0007) -[2023-10-09 11:36:47,703][23469] Updated weights for policy 1, policy_version 83391 (0.0009) -[2023-10-09 11:36:49,990][23468] Updated weights for policy 0, policy_version 82953 (0.0008) -[2023-10-09 11:36:50,368][23468] Updated weights for policy 0, policy_version 82963 (0.0007) -[2023-10-09 11:36:50,727][23468] Updated weights for policy 0, policy_version 82973 (0.0008) -[2023-10-09 11:36:51,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 170360832. Throughput: 0: 1797.2, 1: 1786.6. Samples: 42593062. Policy #0 lag: (min: 20.0, avg: 20.5, max: 34.0) -[2023-10-09 11:36:51,078][22500] Avg episode reward: [(0, '10.560'), (1, '9.150')] -[2023-10-09 11:36:51,593][23469] Updated weights for policy 1, policy_version 83401 (0.0007) -[2023-10-09 11:36:51,972][23469] Updated weights for policy 1, policy_version 83411 (0.0008) -[2023-10-09 11:36:52,331][23469] Updated weights for policy 1, policy_version 83421 (0.0008) -[2023-10-09 11:36:54,499][23468] Updated weights for policy 0, policy_version 82983 (0.0007) -[2023-10-09 11:36:54,882][23468] Updated weights for policy 0, policy_version 82993 (0.0007) -[2023-10-09 11:36:55,252][23468] Updated weights for policy 0, policy_version 83003 (0.0008) -[2023-10-09 11:36:56,014][23469] Updated weights for policy 1, policy_version 83431 (0.0008) -[2023-10-09 11:36:56,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 170426368. Throughput: 0: 1810.4, 1: 1785.2. Samples: 42615500. Policy #0 lag: (min: 20.0, avg: 20.5, max: 34.0) -[2023-10-09 11:36:56,079][22500] Avg episode reward: [(0, '10.710'), (1, '9.010')] -[2023-10-09 11:36:56,390][23469] Updated weights for policy 1, policy_version 83441 (0.0008) -[2023-10-09 11:36:56,758][23469] Updated weights for policy 1, policy_version 83451 (0.0007) -[2023-10-09 11:36:58,890][23468] Updated weights for policy 0, policy_version 83013 (0.0009) -[2023-10-09 11:36:59,267][23468] Updated weights for policy 0, policy_version 83023 (0.0011) -[2023-10-09 11:36:59,637][23468] Updated weights for policy 0, policy_version 83033 (0.0011) -[2023-10-09 11:37:00,412][23469] Updated weights for policy 1, policy_version 83461 (0.0008) -[2023-10-09 11:37:00,798][23469] Updated weights for policy 1, policy_version 83471 (0.0008) -[2023-10-09 11:37:01,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 170491904. Throughput: 0: 1798.6, 1: 1798.6. Samples: 42635926. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:37:01,078][22500] Avg episode reward: [(0, '10.410'), (1, '9.540')] -[2023-10-09 11:37:01,168][23469] Updated weights for policy 1, policy_version 83481 (0.0007) -[2023-10-09 11:37:03,370][23468] Updated weights for policy 0, policy_version 83043 (0.0009) -[2023-10-09 11:37:03,741][23468] Updated weights for policy 0, policy_version 83053 (0.0007) -[2023-10-09 11:37:04,112][23468] Updated weights for policy 0, policy_version 83063 (0.0007) -[2023-10-09 11:37:04,693][23469] Updated weights for policy 1, policy_version 83491 (0.0008) -[2023-10-09 11:37:05,060][23469] Updated weights for policy 1, policy_version 83501 (0.0008) -[2023-10-09 11:37:05,441][23469] Updated weights for policy 1, policy_version 83511 (0.0008) -[2023-10-09 11:37:06,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 170590208. Throughput: 0: 1815.5, 1: 1780.7. Samples: 42648040. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:37:06,078][22500] Avg episode reward: [(0, '10.370'), (1, '8.890')] -[2023-10-09 11:37:07,761][23468] Updated weights for policy 0, policy_version 83073 (0.0008) -[2023-10-09 11:37:08,140][23468] Updated weights for policy 0, policy_version 83083 (0.0010) -[2023-10-09 11:37:08,510][23468] Updated weights for policy 0, policy_version 83093 (0.0009) -[2023-10-09 11:37:08,894][23468] Updated weights for policy 0, policy_version 83103 (0.0008) -[2023-10-09 11:37:09,195][23469] Updated weights for policy 1, policy_version 83521 (0.0011) -[2023-10-09 11:37:09,562][23469] Updated weights for policy 1, policy_version 83531 (0.0009) -[2023-10-09 11:37:09,932][23469] Updated weights for policy 1, policy_version 83541 (0.0008) -[2023-10-09 11:37:10,300][23469] Updated weights for policy 1, policy_version 83551 (0.0010) -[2023-10-09 11:37:11,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 170655744. Throughput: 0: 1800.1, 1: 1805.4. Samples: 42668422. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:37:11,078][22500] Avg episode reward: [(0, '9.910'), (1, '8.740')] -[2023-10-09 11:37:12,713][23468] Updated weights for policy 0, policy_version 83113 (0.0008) -[2023-10-09 11:37:13,078][23468] Updated weights for policy 0, policy_version 83123 (0.0008) -[2023-10-09 11:37:13,452][23468] Updated weights for policy 0, policy_version 83133 (0.0009) -[2023-10-09 11:37:14,063][23469] Updated weights for policy 1, policy_version 83561 (0.0008) -[2023-10-09 11:37:14,434][23469] Updated weights for policy 1, policy_version 83571 (0.0009) -[2023-10-09 11:37:14,806][23469] Updated weights for policy 1, policy_version 83581 (0.0008) -[2023-10-09 11:37:16,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 170721280. Throughput: 0: 1797.7, 1: 1788.5. Samples: 42689924. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:37:16,078][22500] Avg episode reward: [(0, '10.350'), (1, '8.730')] -[2023-10-09 11:37:17,149][23468] Updated weights for policy 0, policy_version 83143 (0.0010) -[2023-10-09 11:37:17,522][23468] Updated weights for policy 0, policy_version 83153 (0.0009) -[2023-10-09 11:37:17,894][23468] Updated weights for policy 0, policy_version 83163 (0.0009) -[2023-10-09 11:37:18,551][23469] Updated weights for policy 1, policy_version 83591 (0.0008) -[2023-10-09 11:37:18,923][23469] Updated weights for policy 1, policy_version 83601 (0.0007) -[2023-10-09 11:37:19,283][23469] Updated weights for policy 1, policy_version 83611 (0.0009) -[2023-10-09 11:37:21,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 170786816. Throughput: 0: 1795.6, 1: 1799.5. Samples: 42700544. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:37:21,078][22500] Avg episode reward: [(0, '10.610'), (1, '9.080')] -[2023-10-09 11:37:21,676][23468] Updated weights for policy 0, policy_version 83173 (0.0008) -[2023-10-09 11:37:22,046][23468] Updated weights for policy 0, policy_version 83183 (0.0008) -[2023-10-09 11:37:22,425][23468] Updated weights for policy 0, policy_version 83193 (0.0007) -[2023-10-09 11:37:22,904][23469] Updated weights for policy 1, policy_version 83621 (0.0008) -[2023-10-09 11:37:23,266][23469] Updated weights for policy 1, policy_version 83631 (0.0007) -[2023-10-09 11:37:23,633][23469] Updated weights for policy 1, policy_version 83641 (0.0008) -[2023-10-09 11:37:26,026][23468] Updated weights for policy 0, policy_version 83203 (0.0008) -[2023-10-09 11:37:26,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 170852352. Throughput: 0: 1791.3, 1: 1796.5. Samples: 42722372. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:37:26,078][22500] Avg episode reward: [(0, '10.710'), (1, '8.830')] -[2023-10-09 11:37:26,389][23468] Updated weights for policy 0, policy_version 83213 (0.0009) -[2023-10-09 11:37:26,766][23468] Updated weights for policy 0, policy_version 83223 (0.0007) -[2023-10-09 11:37:27,307][23469] Updated weights for policy 1, policy_version 83651 (0.0010) -[2023-10-09 11:37:27,675][23469] Updated weights for policy 1, policy_version 83661 (0.0007) -[2023-10-09 11:37:28,047][23469] Updated weights for policy 1, policy_version 83671 (0.0008) -[2023-10-09 11:37:30,685][23468] Updated weights for policy 0, policy_version 83233 (0.0007) -[2023-10-09 11:37:31,066][23468] Updated weights for policy 0, policy_version 83243 (0.0009) -[2023-10-09 11:37:31,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 170917888. Throughput: 0: 1796.8, 1: 1799.3. Samples: 42744706. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:37:31,078][22500] Avg episode reward: [(0, '11.110'), (1, '8.860')] -[2023-10-09 11:37:31,425][23468] Updated weights for policy 0, policy_version 83253 (0.0010) -[2023-10-09 11:37:31,780][23469] Updated weights for policy 1, policy_version 83681 (0.0008) -[2023-10-09 11:37:31,801][23468] Updated weights for policy 0, policy_version 83263 (0.0009) -[2023-10-09 11:37:32,147][23469] Updated weights for policy 1, policy_version 83691 (0.0007) -[2023-10-09 11:37:32,522][23469] Updated weights for policy 1, policy_version 83701 (0.0008) -[2023-10-09 11:37:32,886][23469] Updated weights for policy 1, policy_version 83711 (0.0010) -[2023-10-09 11:37:35,338][23468] Updated weights for policy 0, policy_version 83273 (0.0008) -[2023-10-09 11:37:35,708][23468] Updated weights for policy 0, policy_version 83283 (0.0009) -[2023-10-09 11:37:36,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 170983424. Throughput: 0: 1790.1, 1: 1799.6. Samples: 42754598. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:37:36,078][22500] Avg episode reward: [(0, '10.840'), (1, '8.930')] -[2023-10-09 11:37:36,084][23468] Updated weights for policy 0, policy_version 83293 (0.0009) -[2023-10-09 11:37:36,650][23469] Updated weights for policy 1, policy_version 83721 (0.0008) -[2023-10-09 11:37:37,024][23469] Updated weights for policy 1, policy_version 83731 (0.0009) -[2023-10-09 11:37:37,402][23469] Updated weights for policy 1, policy_version 83741 (0.0008) -[2023-10-09 11:37:39,890][23468] Updated weights for policy 0, policy_version 83303 (0.0009) -[2023-10-09 11:37:40,266][23468] Updated weights for policy 0, policy_version 83313 (0.0009) -[2023-10-09 11:37:40,634][23468] Updated weights for policy 0, policy_version 83323 (0.0010) -[2023-10-09 11:37:41,078][22500] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 171081728. Throughput: 0: 1796.8, 1: 1800.8. Samples: 42777392. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:37:41,079][22500] Avg episode reward: [(0, '11.040'), (1, '9.200')] -[2023-10-09 11:37:41,285][23469] Updated weights for policy 1, policy_version 83751 (0.0007) -[2023-10-09 11:37:41,661][23469] Updated weights for policy 1, policy_version 83761 (0.0009) -[2023-10-09 11:37:42,029][23469] Updated weights for policy 1, policy_version 83771 (0.0008) -[2023-10-09 11:37:44,541][23468] Updated weights for policy 0, policy_version 83333 (0.0008) -[2023-10-09 11:37:44,925][23468] Updated weights for policy 0, policy_version 83343 (0.0008) -[2023-10-09 11:37:45,306][23468] Updated weights for policy 0, policy_version 83353 (0.0010) -[2023-10-09 11:37:45,842][23469] Updated weights for policy 1, policy_version 83781 (0.0008) -[2023-10-09 11:37:46,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 171147264. Throughput: 0: 1794.8, 1: 1812.3. Samples: 42798246. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:37:46,078][22500] Avg episode reward: [(0, '11.250'), (1, '10.270')] -[2023-10-09 11:37:46,235][23469] Updated weights for policy 1, policy_version 83791 (0.0008) -[2023-10-09 11:37:46,614][23469] Updated weights for policy 1, policy_version 83801 (0.0010) -[2023-10-09 11:37:49,139][23468] Updated weights for policy 0, policy_version 83363 (0.0009) -[2023-10-09 11:37:49,516][23468] Updated weights for policy 0, policy_version 83373 (0.0007) -[2023-10-09 11:37:49,887][23468] Updated weights for policy 0, policy_version 83383 (0.0008) -[2023-10-09 11:37:50,270][23469] Updated weights for policy 1, policy_version 83811 (0.0008) -[2023-10-09 11:37:50,640][23469] Updated weights for policy 1, policy_version 83821 (0.0009) -[2023-10-09 11:37:51,005][23469] Updated weights for policy 1, policy_version 83831 (0.0010) -[2023-10-09 11:37:51,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 171212800. Throughput: 0: 1784.6, 1: 1796.4. Samples: 42809186. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:37:51,078][22500] Avg episode reward: [(0, '10.740'), (1, '10.450')] -[2023-10-09 11:37:53,482][23468] Updated weights for policy 0, policy_version 83393 (0.0010) -[2023-10-09 11:37:53,854][23468] Updated weights for policy 0, policy_version 83403 (0.0011) -[2023-10-09 11:37:54,229][23468] Updated weights for policy 0, policy_version 83413 (0.0011) -[2023-10-09 11:37:54,613][23468] Updated weights for policy 0, policy_version 83423 (0.0007) -[2023-10-09 11:37:54,864][23469] Updated weights for policy 1, policy_version 83841 (0.0009) -[2023-10-09 11:37:55,234][23469] Updated weights for policy 1, policy_version 83851 (0.0009) -[2023-10-09 11:37:55,598][23469] Updated weights for policy 1, policy_version 83861 (0.0010) -[2023-10-09 11:37:55,969][23469] Updated weights for policy 1, policy_version 83871 (0.0008) -[2023-10-09 11:37:56,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 171311104. Throughput: 0: 1791.0, 1: 1812.3. Samples: 42830574. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-09 11:37:56,079][22500] Avg episode reward: [(0, '11.610'), (1, '10.120')] -[2023-10-09 11:37:58,346][23468] Updated weights for policy 0, policy_version 83433 (0.0010) -[2023-10-09 11:37:58,720][23468] Updated weights for policy 0, policy_version 83443 (0.0009) -[2023-10-09 11:37:59,089][23468] Updated weights for policy 0, policy_version 83453 (0.0010) -[2023-10-09 11:37:59,724][23469] Updated weights for policy 1, policy_version 83881 (0.0010) -[2023-10-09 11:38:00,098][23469] Updated weights for policy 1, policy_version 83891 (0.0010) -[2023-10-09 11:38:00,460][23469] Updated weights for policy 1, policy_version 83901 (0.0008) -[2023-10-09 11:38:01,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 171376640. Throughput: 0: 1782.7, 1: 1800.2. Samples: 42851156. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-09 11:38:01,078][22500] Avg episode reward: [(0, '10.910'), (1, '10.380')] -[2023-10-09 11:38:02,876][23468] Updated weights for policy 0, policy_version 83463 (0.0008) -[2023-10-09 11:38:03,255][23468] Updated weights for policy 0, policy_version 83473 (0.0007) -[2023-10-09 11:38:03,619][23468] Updated weights for policy 0, policy_version 83483 (0.0009) -[2023-10-09 11:38:04,185][23469] Updated weights for policy 1, policy_version 83911 (0.0008) -[2023-10-09 11:38:04,542][23469] Updated weights for policy 1, policy_version 83921 (0.0008) -[2023-10-09 11:38:04,911][23469] Updated weights for policy 1, policy_version 83931 (0.0009) -[2023-10-09 11:38:06,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 171442176. Throughput: 0: 1800.2, 1: 1813.0. Samples: 42863140. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-09 11:38:06,078][22500] Avg episode reward: [(0, '10.650'), (1, '10.160')] -[2023-10-09 11:38:07,179][23468] Updated weights for policy 0, policy_version 83493 (0.0009) -[2023-10-09 11:38:07,554][23468] Updated weights for policy 0, policy_version 83503 (0.0008) -[2023-10-09 11:38:07,926][23468] Updated weights for policy 0, policy_version 83513 (0.0008) -[2023-10-09 11:38:08,707][23469] Updated weights for policy 1, policy_version 83941 (0.0009) -[2023-10-09 11:38:09,079][23469] Updated weights for policy 1, policy_version 83951 (0.0010) -[2023-10-09 11:38:09,455][23469] Updated weights for policy 1, policy_version 83961 (0.0009) -[2023-10-09 11:38:11,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 171507712. Throughput: 0: 1794.2, 1: 1793.0. Samples: 42883798. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-09 11:38:11,078][22500] Avg episode reward: [(0, '11.040'), (1, '9.620')] -[2023-10-09 11:38:11,729][23468] Updated weights for policy 0, policy_version 83523 (0.0008) -[2023-10-09 11:38:12,107][23468] Updated weights for policy 0, policy_version 83533 (0.0010) -[2023-10-09 11:38:12,474][23468] Updated weights for policy 0, policy_version 83543 (0.0009) -[2023-10-09 11:38:13,070][23469] Updated weights for policy 1, policy_version 83971 (0.0008) -[2023-10-09 11:38:13,435][23469] Updated weights for policy 1, policy_version 83981 (0.0009) -[2023-10-09 11:38:13,807][23469] Updated weights for policy 1, policy_version 83991 (0.0011) -[2023-10-09 11:38:16,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 171573248. Throughput: 0: 1798.4, 1: 1791.3. Samples: 42906244. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-09 11:38:16,078][22500] Avg episode reward: [(0, '10.380'), (1, '9.730')] -[2023-10-09 11:38:16,090][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000084000_86016000.pth... -[2023-10-09 11:38:16,124][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000082336_84312064.pth -[2023-10-09 11:38:16,208][23468] Updated weights for policy 0, policy_version 83553 (0.0008) -[2023-10-09 11:38:16,585][23468] Updated weights for policy 0, policy_version 83563 (0.0010) -[2023-10-09 11:38:16,954][23468] Updated weights for policy 0, policy_version 83573 (0.0010) -[2023-10-09 11:38:17,328][23468] Updated weights for policy 0, policy_version 83583 (0.0007) -[2023-10-09 11:38:17,358][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000083584_85590016.pth... -[2023-10-09 11:38:17,398][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000081888_83853312.pth -[2023-10-09 11:38:17,593][23469] Updated weights for policy 1, policy_version 84001 (0.0010) -[2023-10-09 11:38:17,972][23469] Updated weights for policy 1, policy_version 84011 (0.0009) -[2023-10-09 11:38:18,342][23469] Updated weights for policy 1, policy_version 84021 (0.0010) -[2023-10-09 11:38:18,704][23469] Updated weights for policy 1, policy_version 84031 (0.0010) -[2023-10-09 11:38:21,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 171638784. Throughput: 0: 1796.1, 1: 1792.2. Samples: 42916074. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-09 11:38:21,078][22500] Avg episode reward: [(0, '10.750'), (1, '9.820')] -[2023-10-09 11:38:21,154][23468] Updated weights for policy 0, policy_version 83593 (0.0009) -[2023-10-09 11:38:21,522][23468] Updated weights for policy 0, policy_version 83603 (0.0009) -[2023-10-09 11:38:21,890][23468] Updated weights for policy 0, policy_version 83613 (0.0010) -[2023-10-09 11:38:22,406][23469] Updated weights for policy 1, policy_version 84041 (0.0007) -[2023-10-09 11:38:22,770][23469] Updated weights for policy 1, policy_version 84051 (0.0007) -[2023-10-09 11:38:23,146][23469] Updated weights for policy 1, policy_version 84061 (0.0011) -[2023-10-09 11:38:25,571][23468] Updated weights for policy 0, policy_version 83623 (0.0009) -[2023-10-09 11:38:25,939][23468] Updated weights for policy 0, policy_version 83633 (0.0007) -[2023-10-09 11:38:26,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 171704320. Throughput: 0: 1790.6, 1: 1786.0. Samples: 42938338. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-09 11:38:26,078][22500] Avg episode reward: [(0, '10.230'), (1, '9.090')] -[2023-10-09 11:38:26,313][23468] Updated weights for policy 0, policy_version 83643 (0.0008) -[2023-10-09 11:38:26,891][23469] Updated weights for policy 1, policy_version 84071 (0.0009) -[2023-10-09 11:38:27,261][23469] Updated weights for policy 1, policy_version 84081 (0.0008) -[2023-10-09 11:38:27,643][23469] Updated weights for policy 1, policy_version 84091 (0.0008) -[2023-10-09 11:38:30,049][23468] Updated weights for policy 0, policy_version 83653 (0.0009) -[2023-10-09 11:38:30,434][23468] Updated weights for policy 0, policy_version 83663 (0.0010) -[2023-10-09 11:38:30,811][23468] Updated weights for policy 0, policy_version 83673 (0.0010) -[2023-10-09 11:38:31,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 171802624. Throughput: 0: 1809.8, 1: 1790.1. Samples: 42960242. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-09 11:38:31,078][22500] Avg episode reward: [(0, '10.010'), (1, '9.410')] -[2023-10-09 11:38:31,589][23469] Updated weights for policy 1, policy_version 84101 (0.0009) -[2023-10-09 11:38:31,972][23469] Updated weights for policy 1, policy_version 84111 (0.0010) -[2023-10-09 11:38:32,349][23469] Updated weights for policy 1, policy_version 84121 (0.0008) -[2023-10-09 11:38:34,400][23468] Updated weights for policy 0, policy_version 83683 (0.0008) -[2023-10-09 11:38:34,768][23468] Updated weights for policy 0, policy_version 83693 (0.0007) -[2023-10-09 11:38:35,139][23468] Updated weights for policy 0, policy_version 83703 (0.0007) -[2023-10-09 11:38:36,052][23469] Updated weights for policy 1, policy_version 84131 (0.0008) -[2023-10-09 11:38:36,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 171868160. Throughput: 0: 1798.7, 1: 1786.1. Samples: 42970502. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-09 11:38:36,078][22500] Avg episode reward: [(0, '10.300'), (1, '9.670')] -[2023-10-09 11:38:36,425][23469] Updated weights for policy 1, policy_version 84141 (0.0008) -[2023-10-09 11:38:36,790][23469] Updated weights for policy 1, policy_version 84151 (0.0007) -[2023-10-09 11:38:38,950][23468] Updated weights for policy 0, policy_version 83713 (0.0008) -[2023-10-09 11:38:39,325][23468] Updated weights for policy 0, policy_version 83723 (0.0008) -[2023-10-09 11:38:39,690][23468] Updated weights for policy 0, policy_version 83733 (0.0008) -[2023-10-09 11:38:40,071][23468] Updated weights for policy 0, policy_version 83743 (0.0008) -[2023-10-09 11:38:40,542][23469] Updated weights for policy 1, policy_version 84161 (0.0009) -[2023-10-09 11:38:40,909][23469] Updated weights for policy 1, policy_version 84171 (0.0010) -[2023-10-09 11:38:41,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 171933696. Throughput: 0: 1813.8, 1: 1784.4. Samples: 42992494. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-09 11:38:41,078][22500] Avg episode reward: [(0, '10.680'), (1, '9.900')] -[2023-10-09 11:38:41,275][23469] Updated weights for policy 1, policy_version 84181 (0.0008) -[2023-10-09 11:38:41,634][23469] Updated weights for policy 1, policy_version 84191 (0.0008) -[2023-10-09 11:38:43,715][23468] Updated weights for policy 0, policy_version 83753 (0.0011) -[2023-10-09 11:38:44,089][23468] Updated weights for policy 0, policy_version 83763 (0.0009) -[2023-10-09 11:38:44,459][23468] Updated weights for policy 0, policy_version 83773 (0.0007) -[2023-10-09 11:38:45,297][23469] Updated weights for policy 1, policy_version 84201 (0.0008) -[2023-10-09 11:38:45,659][23469] Updated weights for policy 1, policy_version 84211 (0.0008) -[2023-10-09 11:38:46,030][23469] Updated weights for policy 1, policy_version 84221 (0.0008) -[2023-10-09 11:38:46,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 171999232. Throughput: 0: 1806.4, 1: 1794.8. Samples: 43013214. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-09 11:38:46,078][22500] Avg episode reward: [(0, '10.720'), (1, '9.700')] -[2023-10-09 11:38:48,241][23468] Updated weights for policy 0, policy_version 83783 (0.0010) -[2023-10-09 11:38:48,615][23468] Updated weights for policy 0, policy_version 83793 (0.0009) -[2023-10-09 11:38:48,991][23468] Updated weights for policy 0, policy_version 83803 (0.0007) -[2023-10-09 11:38:49,828][23469] Updated weights for policy 1, policy_version 84231 (0.0008) -[2023-10-09 11:38:50,188][23469] Updated weights for policy 1, policy_version 84241 (0.0009) -[2023-10-09 11:38:50,567][23469] Updated weights for policy 1, policy_version 84251 (0.0009) -[2023-10-09 11:38:51,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 172097536. Throughput: 0: 1812.2, 1: 1782.4. Samples: 43024898. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-09 11:38:51,078][22500] Avg episode reward: [(0, '10.520'), (1, '9.250')] -[2023-10-09 11:38:52,800][23468] Updated weights for policy 0, policy_version 83813 (0.0007) -[2023-10-09 11:38:53,187][23468] Updated weights for policy 0, policy_version 83823 (0.0007) -[2023-10-09 11:38:53,570][23468] Updated weights for policy 0, policy_version 83833 (0.0007) -[2023-10-09 11:38:54,233][23469] Updated weights for policy 1, policy_version 84261 (0.0010) -[2023-10-09 11:38:54,610][23469] Updated weights for policy 1, policy_version 84271 (0.0011) -[2023-10-09 11:38:54,994][23469] Updated weights for policy 1, policy_version 84281 (0.0011) -[2023-10-09 11:38:56,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 172163072. Throughput: 0: 1792.2, 1: 1799.4. Samples: 43045422. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-09 11:38:56,078][22500] Avg episode reward: [(0, '10.300'), (1, '9.760')] -[2023-10-09 11:38:57,307][23468] Updated weights for policy 0, policy_version 83843 (0.0008) -[2023-10-09 11:38:57,677][23468] Updated weights for policy 0, policy_version 83853 (0.0009) -[2023-10-09 11:38:58,047][23468] Updated weights for policy 0, policy_version 83863 (0.0008) -[2023-10-09 11:38:58,775][23469] Updated weights for policy 1, policy_version 84291 (0.0010) -[2023-10-09 11:38:59,144][23469] Updated weights for policy 1, policy_version 84301 (0.0008) -[2023-10-09 11:38:59,503][23469] Updated weights for policy 1, policy_version 84311 (0.0007) -[2023-10-09 11:39:01,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 172228608. Throughput: 0: 1793.0, 1: 1784.3. Samples: 43067222. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-09 11:39:01,078][22500] Avg episode reward: [(0, '10.800'), (1, '9.680')] -[2023-10-09 11:39:01,956][23468] Updated weights for policy 0, policy_version 83873 (0.0008) -[2023-10-09 11:39:02,331][23468] Updated weights for policy 0, policy_version 83883 (0.0009) -[2023-10-09 11:39:02,709][23468] Updated weights for policy 0, policy_version 83893 (0.0011) -[2023-10-09 11:39:03,085][23468] Updated weights for policy 0, policy_version 83903 (0.0009) -[2023-10-09 11:39:03,220][23469] Updated weights for policy 1, policy_version 84321 (0.0008) -[2023-10-09 11:39:03,585][23469] Updated weights for policy 1, policy_version 84331 (0.0009) -[2023-10-09 11:39:03,953][23469] Updated weights for policy 1, policy_version 84341 (0.0010) -[2023-10-09 11:39:04,323][23469] Updated weights for policy 1, policy_version 84351 (0.0011) -[2023-10-09 11:39:06,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 172294144. Throughput: 0: 1788.9, 1: 1804.8. Samples: 43077792. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-09 11:39:06,078][22500] Avg episode reward: [(0, '10.730'), (1, '9.970')] -[2023-10-09 11:39:06,714][23468] Updated weights for policy 0, policy_version 83913 (0.0009) -[2023-10-09 11:39:07,092][23468] Updated weights for policy 0, policy_version 83923 (0.0009) -[2023-10-09 11:39:07,468][23468] Updated weights for policy 0, policy_version 83933 (0.0009) -[2023-10-09 11:39:07,940][23469] Updated weights for policy 1, policy_version 84361 (0.0009) -[2023-10-09 11:39:08,305][23469] Updated weights for policy 1, policy_version 84371 (0.0010) -[2023-10-09 11:39:08,673][23469] Updated weights for policy 1, policy_version 84381 (0.0010) -[2023-10-09 11:39:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 172359680. Throughput: 0: 1792.2, 1: 1792.8. Samples: 43099666. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-09 11:39:11,078][22500] Avg episode reward: [(0, '11.100'), (1, '10.520')] -[2023-10-09 11:39:11,159][23468] Updated weights for policy 0, policy_version 83943 (0.0008) -[2023-10-09 11:39:11,542][23468] Updated weights for policy 0, policy_version 83953 (0.0009) -[2023-10-09 11:39:11,916][23468] Updated weights for policy 0, policy_version 83963 (0.0009) -[2023-10-09 11:39:12,514][23469] Updated weights for policy 1, policy_version 84391 (0.0007) -[2023-10-09 11:39:12,889][23469] Updated weights for policy 1, policy_version 84401 (0.0011) -[2023-10-09 11:39:13,259][23469] Updated weights for policy 1, policy_version 84411 (0.0008) -[2023-10-09 11:39:15,764][23468] Updated weights for policy 0, policy_version 83973 (0.0009) -[2023-10-09 11:39:16,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 172425216. Throughput: 0: 1801.1, 1: 1793.5. Samples: 43121998. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-09 11:39:16,078][22500] Avg episode reward: [(0, '11.350'), (1, '9.610')] -[2023-10-09 11:39:16,162][23468] Updated weights for policy 0, policy_version 83983 (0.0008) -[2023-10-09 11:39:16,530][23468] Updated weights for policy 0, policy_version 83993 (0.0009) -[2023-10-09 11:39:17,004][23469] Updated weights for policy 1, policy_version 84421 (0.0009) -[2023-10-09 11:39:17,380][23469] Updated weights for policy 1, policy_version 84431 (0.0008) -[2023-10-09 11:39:17,748][23469] Updated weights for policy 1, policy_version 84441 (0.0010) -[2023-10-09 11:39:20,208][23468] Updated weights for policy 0, policy_version 84003 (0.0008) -[2023-10-09 11:39:20,595][23468] Updated weights for policy 0, policy_version 84013 (0.0010) -[2023-10-09 11:39:20,964][23468] Updated weights for policy 0, policy_version 84023 (0.0009) -[2023-10-09 11:39:21,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 172490752. Throughput: 0: 1782.3, 1: 1795.4. Samples: 43131498. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-09 11:39:21,078][22500] Avg episode reward: [(0, '10.580'), (1, '9.910')] -[2023-10-09 11:39:21,483][23469] Updated weights for policy 1, policy_version 84451 (0.0008) -[2023-10-09 11:39:21,857][23469] Updated weights for policy 1, policy_version 84461 (0.0007) -[2023-10-09 11:39:22,225][23469] Updated weights for policy 1, policy_version 84471 (0.0009) -[2023-10-09 11:39:24,705][23468] Updated weights for policy 0, policy_version 84033 (0.0009) -[2023-10-09 11:39:25,076][23468] Updated weights for policy 0, policy_version 84043 (0.0008) -[2023-10-09 11:39:25,447][23468] Updated weights for policy 0, policy_version 84053 (0.0009) -[2023-10-09 11:39:25,813][23468] Updated weights for policy 0, policy_version 84063 (0.0008) -[2023-10-09 11:39:25,866][23469] Updated weights for policy 1, policy_version 84481 (0.0011) -[2023-10-09 11:39:26,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 172589056. Throughput: 0: 1793.5, 1: 1802.3. Samples: 43154304. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-09 11:39:26,078][22500] Avg episode reward: [(0, '10.470'), (1, '9.380')] -[2023-10-09 11:39:26,245][23469] Updated weights for policy 1, policy_version 84491 (0.0011) -[2023-10-09 11:39:26,622][23469] Updated weights for policy 1, policy_version 84501 (0.0010) -[2023-10-09 11:39:26,998][23469] Updated weights for policy 1, policy_version 84511 (0.0007) -[2023-10-09 11:39:29,461][23468] Updated weights for policy 0, policy_version 84073 (0.0008) -[2023-10-09 11:39:29,835][23468] Updated weights for policy 0, policy_version 84083 (0.0008) -[2023-10-09 11:39:30,212][23468] Updated weights for policy 0, policy_version 84093 (0.0008) -[2023-10-09 11:39:30,764][23469] Updated weights for policy 1, policy_version 84521 (0.0008) -[2023-10-09 11:39:31,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 172654592. Throughput: 0: 1783.8, 1: 1814.7. Samples: 43175144. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-09 11:39:31,078][22500] Avg episode reward: [(0, '10.640'), (1, '9.630')] -[2023-10-09 11:39:31,137][23469] Updated weights for policy 1, policy_version 84531 (0.0011) -[2023-10-09 11:39:31,507][23469] Updated weights for policy 1, policy_version 84541 (0.0009) -[2023-10-09 11:39:33,905][23468] Updated weights for policy 0, policy_version 84103 (0.0010) -[2023-10-09 11:39:34,280][23468] Updated weights for policy 0, policy_version 84113 (0.0007) -[2023-10-09 11:39:34,655][23468] Updated weights for policy 0, policy_version 84123 (0.0007) -[2023-10-09 11:39:35,306][23469] Updated weights for policy 1, policy_version 84551 (0.0009) -[2023-10-09 11:39:35,664][23469] Updated weights for policy 1, policy_version 84561 (0.0010) -[2023-10-09 11:39:36,033][23469] Updated weights for policy 1, policy_version 84571 (0.0010) -[2023-10-09 11:39:36,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 172720128. Throughput: 0: 1795.3, 1: 1800.4. Samples: 43186706. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-09 11:39:36,078][22500] Avg episode reward: [(0, '10.190'), (1, '9.410')] -[2023-10-09 11:39:38,313][23468] Updated weights for policy 0, policy_version 84133 (0.0007) -[2023-10-09 11:39:38,679][23468] Updated weights for policy 0, policy_version 84143 (0.0008) -[2023-10-09 11:39:39,048][23468] Updated weights for policy 0, policy_version 84153 (0.0011) -[2023-10-09 11:39:39,715][23469] Updated weights for policy 1, policy_version 84581 (0.0008) -[2023-10-09 11:39:40,090][23469] Updated weights for policy 1, policy_version 84591 (0.0009) -[2023-10-09 11:39:40,464][23469] Updated weights for policy 1, policy_version 84601 (0.0007) -[2023-10-09 11:39:41,078][22500] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 172818432. Throughput: 0: 1792.4, 1: 1815.4. Samples: 43207774. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-09 11:39:41,079][22500] Avg episode reward: [(0, '10.470'), (1, '9.630')] -[2023-10-09 11:39:42,833][23468] Updated weights for policy 0, policy_version 84163 (0.0007) -[2023-10-09 11:39:43,203][23468] Updated weights for policy 0, policy_version 84173 (0.0008) -[2023-10-09 11:39:43,582][23468] Updated weights for policy 0, policy_version 84183 (0.0008) -[2023-10-09 11:39:44,189][23469] Updated weights for policy 1, policy_version 84611 (0.0009) -[2023-10-09 11:39:44,559][23469] Updated weights for policy 1, policy_version 84621 (0.0008) -[2023-10-09 11:39:44,920][23469] Updated weights for policy 1, policy_version 84631 (0.0007) -[2023-10-09 11:39:46,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 172883968. Throughput: 0: 1785.6, 1: 1806.2. Samples: 43228854. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 11:39:46,079][22500] Avg episode reward: [(0, '11.190'), (1, '9.560')] -[2023-10-09 11:39:47,396][23468] Updated weights for policy 0, policy_version 84193 (0.0009) -[2023-10-09 11:39:47,759][23468] Updated weights for policy 0, policy_version 84203 (0.0009) -[2023-10-09 11:39:48,134][23468] Updated weights for policy 0, policy_version 84213 (0.0008) -[2023-10-09 11:39:48,498][23468] Updated weights for policy 0, policy_version 84223 (0.0010) -[2023-10-09 11:39:48,604][23469] Updated weights for policy 1, policy_version 84641 (0.0009) -[2023-10-09 11:39:48,967][23469] Updated weights for policy 1, policy_version 84651 (0.0010) -[2023-10-09 11:39:49,334][23469] Updated weights for policy 1, policy_version 84661 (0.0009) -[2023-10-09 11:39:49,704][23469] Updated weights for policy 1, policy_version 84671 (0.0010) -[2023-10-09 11:39:51,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 172949504. Throughput: 0: 1797.0, 1: 1813.0. Samples: 43240242. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 11:39:51,078][22500] Avg episode reward: [(0, '11.330'), (1, '9.640')] -[2023-10-09 11:39:52,356][23468] Updated weights for policy 0, policy_version 84233 (0.0010) -[2023-10-09 11:39:52,734][23468] Updated weights for policy 0, policy_version 84243 (0.0010) -[2023-10-09 11:39:53,095][23468] Updated weights for policy 0, policy_version 84253 (0.0010) -[2023-10-09 11:39:53,466][23469] Updated weights for policy 1, policy_version 84681 (0.0007) -[2023-10-09 11:39:53,828][23469] Updated weights for policy 1, policy_version 84691 (0.0008) -[2023-10-09 11:39:54,194][23469] Updated weights for policy 1, policy_version 84701 (0.0008) -[2023-10-09 11:39:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 173015040. Throughput: 0: 1782.9, 1: 1802.5. Samples: 43261008. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 11:39:56,078][22500] Avg episode reward: [(0, '11.570'), (1, '9.300')] -[2023-10-09 11:39:56,910][23468] Updated weights for policy 0, policy_version 84263 (0.0010) -[2023-10-09 11:39:57,276][23468] Updated weights for policy 0, policy_version 84273 (0.0009) -[2023-10-09 11:39:57,644][23468] Updated weights for policy 0, policy_version 84283 (0.0008) -[2023-10-09 11:39:57,865][23469] Updated weights for policy 1, policy_version 84711 (0.0008) -[2023-10-09 11:39:58,241][23469] Updated weights for policy 1, policy_version 84721 (0.0008) -[2023-10-09 11:39:58,613][23469] Updated weights for policy 1, policy_version 84731 (0.0010) -[2023-10-09 11:40:01,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 173080576. Throughput: 0: 1780.0, 1: 1807.0. Samples: 43283412. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 11:40:01,079][22500] Avg episode reward: [(0, '11.490'), (1, '9.530')] -[2023-10-09 11:40:01,610][23468] Updated weights for policy 0, policy_version 84293 (0.0007) -[2023-10-09 11:40:01,991][23468] Updated weights for policy 0, policy_version 84303 (0.0007) -[2023-10-09 11:40:02,259][23469] Updated weights for policy 1, policy_version 84741 (0.0007) -[2023-10-09 11:40:02,357][23468] Updated weights for policy 0, policy_version 84313 (0.0007) -[2023-10-09 11:40:02,630][23469] Updated weights for policy 1, policy_version 84751 (0.0007) -[2023-10-09 11:40:03,003][23469] Updated weights for policy 1, policy_version 84761 (0.0008) -[2023-10-09 11:40:05,933][23468] Updated weights for policy 0, policy_version 84323 (0.0007) -[2023-10-09 11:40:06,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 173146112. Throughput: 0: 1781.4, 1: 1807.7. Samples: 43293008. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 11:40:06,078][22500] Avg episode reward: [(0, '10.920'), (1, '9.520')] -[2023-10-09 11:40:06,303][23468] Updated weights for policy 0, policy_version 84333 (0.0007) -[2023-10-09 11:40:06,665][23468] Updated weights for policy 0, policy_version 84343 (0.0007) -[2023-10-09 11:40:06,737][23469] Updated weights for policy 1, policy_version 84771 (0.0007) -[2023-10-09 11:40:07,115][23469] Updated weights for policy 1, policy_version 84781 (0.0008) -[2023-10-09 11:40:07,485][23469] Updated weights for policy 1, policy_version 84791 (0.0008) -[2023-10-09 11:40:10,442][23468] Updated weights for policy 0, policy_version 84353 (0.0008) -[2023-10-09 11:40:10,818][23468] Updated weights for policy 0, policy_version 84363 (0.0010) -[2023-10-09 11:40:11,078][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 173211648. Throughput: 0: 1782.0, 1: 1802.8. Samples: 43315622. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 11:40:11,079][22500] Avg episode reward: [(0, '10.760'), (1, '9.510')] -[2023-10-09 11:40:11,095][23469] Updated weights for policy 1, policy_version 84801 (0.0007) -[2023-10-09 11:40:11,185][23468] Updated weights for policy 0, policy_version 84373 (0.0010) -[2023-10-09 11:40:11,473][23469] Updated weights for policy 1, policy_version 84811 (0.0007) -[2023-10-09 11:40:11,551][23468] Updated weights for policy 0, policy_version 84383 (0.0007) -[2023-10-09 11:40:11,836][23469] Updated weights for policy 1, policy_version 84821 (0.0010) -[2023-10-09 11:40:12,220][23469] Updated weights for policy 1, policy_version 84831 (0.0011) -[2023-10-09 11:40:15,234][23468] Updated weights for policy 0, policy_version 84393 (0.0010) -[2023-10-09 11:40:15,609][23468] Updated weights for policy 0, policy_version 84403 (0.0011) -[2023-10-09 11:40:15,983][23468] Updated weights for policy 0, policy_version 84413 (0.0008) -[2023-10-09 11:40:16,039][23469] Updated weights for policy 1, policy_version 84841 (0.0009) -[2023-10-09 11:40:16,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 173277184. Throughput: 0: 1800.4, 1: 1812.1. Samples: 43337708. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 11:40:16,078][22500] Avg episode reward: [(0, '10.640'), (1, '10.140')] -[2023-10-09 11:40:16,089][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000084416_86441984.pth... -[2023-10-09 11:40:16,123][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000082720_84705280.pth -[2023-10-09 11:40:16,408][23469] Updated weights for policy 1, policy_version 84851 (0.0009) -[2023-10-09 11:40:16,778][23469] Updated weights for policy 1, policy_version 84861 (0.0010) -[2023-10-09 11:40:16,888][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000084864_86900736.pth... -[2023-10-09 11:40:16,916][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000083168_85164032.pth -[2023-10-09 11:40:19,856][23468] Updated weights for policy 0, policy_version 84423 (0.0010) -[2023-10-09 11:40:20,226][23468] Updated weights for policy 0, policy_version 84433 (0.0009) -[2023-10-09 11:40:20,470][23469] Updated weights for policy 1, policy_version 84871 (0.0008) -[2023-10-09 11:40:20,598][23468] Updated weights for policy 0, policy_version 84443 (0.0008) -[2023-10-09 11:40:20,834][23469] Updated weights for policy 1, policy_version 84881 (0.0007) -[2023-10-09 11:40:21,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 173375488. Throughput: 0: 1780.1, 1: 1806.8. Samples: 43348116. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 11:40:21,078][22500] Avg episode reward: [(0, '10.350'), (1, '9.980')] -[2023-10-09 11:40:21,201][23469] Updated weights for policy 1, policy_version 84891 (0.0008) -[2023-10-09 11:40:24,418][23468] Updated weights for policy 0, policy_version 84453 (0.0009) -[2023-10-09 11:40:24,798][23468] Updated weights for policy 0, policy_version 84463 (0.0009) -[2023-10-09 11:40:24,970][23469] Updated weights for policy 1, policy_version 84901 (0.0008) -[2023-10-09 11:40:25,179][23468] Updated weights for policy 0, policy_version 84473 (0.0009) -[2023-10-09 11:40:25,339][23469] Updated weights for policy 1, policy_version 84911 (0.0008) -[2023-10-09 11:40:25,713][23469] Updated weights for policy 1, policy_version 84921 (0.0009) -[2023-10-09 11:40:26,077][22500] Fps is (10 sec: 19660.5, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 173473792. Throughput: 0: 1805.6, 1: 1810.5. Samples: 43370496. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 11:40:26,078][22500] Avg episode reward: [(0, '10.870'), (1, '10.390')] -[2023-10-09 11:40:28,770][23468] Updated weights for policy 0, policy_version 84483 (0.0008) -[2023-10-09 11:40:29,138][23468] Updated weights for policy 0, policy_version 84493 (0.0008) -[2023-10-09 11:40:29,476][23469] Updated weights for policy 1, policy_version 84931 (0.0009) -[2023-10-09 11:40:29,509][23468] Updated weights for policy 0, policy_version 84503 (0.0009) -[2023-10-09 11:40:29,851][23469] Updated weights for policy 1, policy_version 84941 (0.0008) -[2023-10-09 11:40:30,223][23469] Updated weights for policy 1, policy_version 84951 (0.0011) -[2023-10-09 11:40:31,078][22500] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 173539328. Throughput: 0: 1777.4, 1: 1802.7. Samples: 43389956. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 11:40:31,079][22500] Avg episode reward: [(0, '10.390'), (1, '9.720')] -[2023-10-09 11:40:33,377][23468] Updated weights for policy 0, policy_version 84513 (0.0008) -[2023-10-09 11:40:33,752][23468] Updated weights for policy 0, policy_version 84523 (0.0009) -[2023-10-09 11:40:33,952][23469] Updated weights for policy 1, policy_version 84961 (0.0010) -[2023-10-09 11:40:34,125][23468] Updated weights for policy 0, policy_version 84533 (0.0009) -[2023-10-09 11:40:34,322][23469] Updated weights for policy 1, policy_version 84971 (0.0009) -[2023-10-09 11:40:34,502][23468] Updated weights for policy 0, policy_version 84543 (0.0007) -[2023-10-09 11:40:34,703][23469] Updated weights for policy 1, policy_version 84981 (0.0009) -[2023-10-09 11:40:35,071][23469] Updated weights for policy 1, policy_version 84991 (0.0007) -[2023-10-09 11:40:36,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 173604864. Throughput: 0: 1797.9, 1: 1804.6. Samples: 43402352. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 11:40:36,078][22500] Avg episode reward: [(0, '10.440'), (1, '9.220')] -[2023-10-09 11:40:38,390][23468] Updated weights for policy 0, policy_version 84553 (0.0008) -[2023-10-09 11:40:38,771][23468] Updated weights for policy 0, policy_version 84563 (0.0008) -[2023-10-09 11:40:38,842][23469] Updated weights for policy 1, policy_version 85001 (0.0009) -[2023-10-09 11:40:39,141][23468] Updated weights for policy 0, policy_version 84573 (0.0008) -[2023-10-09 11:40:39,200][23469] Updated weights for policy 1, policy_version 85011 (0.0007) -[2023-10-09 11:40:39,585][23469] Updated weights for policy 1, policy_version 85021 (0.0009) -[2023-10-09 11:40:41,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 173670400. Throughput: 0: 1770.4, 1: 1795.7. Samples: 43421484. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:40:41,078][22500] Avg episode reward: [(0, '10.570'), (1, '9.380')] -[2023-10-09 11:40:43,031][23468] Updated weights for policy 0, policy_version 84583 (0.0009) -[2023-10-09 11:40:43,375][23469] Updated weights for policy 1, policy_version 85031 (0.0008) -[2023-10-09 11:40:43,402][23468] Updated weights for policy 0, policy_version 84593 (0.0008) -[2023-10-09 11:40:43,744][23469] Updated weights for policy 1, policy_version 85041 (0.0008) -[2023-10-09 11:40:43,773][23468] Updated weights for policy 0, policy_version 84603 (0.0008) -[2023-10-09 11:40:44,120][23469] Updated weights for policy 1, policy_version 85051 (0.0009) -[2023-10-09 11:40:46,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 173735936. Throughput: 0: 1772.4, 1: 1790.4. Samples: 43443736. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:40:46,078][22500] Avg episode reward: [(0, '10.560'), (1, '9.700')] -[2023-10-09 11:40:47,532][23468] Updated weights for policy 0, policy_version 84613 (0.0008) -[2023-10-09 11:40:47,925][23468] Updated weights for policy 0, policy_version 84623 (0.0008) -[2023-10-09 11:40:47,933][23469] Updated weights for policy 1, policy_version 85061 (0.0008) -[2023-10-09 11:40:48,285][23468] Updated weights for policy 0, policy_version 84633 (0.0008) -[2023-10-09 11:40:48,316][23469] Updated weights for policy 1, policy_version 85071 (0.0007) -[2023-10-09 11:40:48,687][23469] Updated weights for policy 1, policy_version 85081 (0.0007) -[2023-10-09 11:40:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 173801472. Throughput: 0: 1781.6, 1: 1793.3. Samples: 43453880. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:40:51,078][22500] Avg episode reward: [(0, '11.520'), (1, '9.620')] -[2023-10-09 11:40:52,123][23468] Updated weights for policy 0, policy_version 84643 (0.0008) -[2023-10-09 11:40:52,495][23468] Updated weights for policy 0, policy_version 84653 (0.0007) -[2023-10-09 11:40:52,535][23469] Updated weights for policy 1, policy_version 85091 (0.0007) -[2023-10-09 11:40:52,878][23468] Updated weights for policy 0, policy_version 84663 (0.0007) -[2023-10-09 11:40:52,900][23469] Updated weights for policy 1, policy_version 85101 (0.0008) -[2023-10-09 11:40:53,265][23469] Updated weights for policy 1, policy_version 85111 (0.0008) -[2023-10-09 11:40:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 173867008. Throughput: 0: 1767.0, 1: 1780.5. Samples: 43475262. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:40:56,078][22500] Avg episode reward: [(0, '11.000'), (1, '10.210')] -[2023-10-09 11:40:56,693][23468] Updated weights for policy 0, policy_version 84673 (0.0008) -[2023-10-09 11:40:57,018][23469] Updated weights for policy 1, policy_version 85121 (0.0008) -[2023-10-09 11:40:57,076][23468] Updated weights for policy 0, policy_version 84683 (0.0008) -[2023-10-09 11:40:57,394][23469] Updated weights for policy 1, policy_version 85131 (0.0009) -[2023-10-09 11:40:57,446][23468] Updated weights for policy 0, policy_version 84693 (0.0008) -[2023-10-09 11:40:57,768][23469] Updated weights for policy 1, policy_version 85141 (0.0009) -[2023-10-09 11:40:57,811][23468] Updated weights for policy 0, policy_version 84703 (0.0009) -[2023-10-09 11:40:58,138][23469] Updated weights for policy 1, policy_version 85151 (0.0010) -[2023-10-09 11:41:01,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 173932544. Throughput: 0: 1772.0, 1: 1780.1. Samples: 43497554. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:41:01,078][22500] Avg episode reward: [(0, '10.930'), (1, '9.750')] -[2023-10-09 11:41:01,739][23468] Updated weights for policy 0, policy_version 84713 (0.0008) -[2023-10-09 11:41:01,988][23469] Updated weights for policy 1, policy_version 85161 (0.0007) -[2023-10-09 11:41:02,114][23468] Updated weights for policy 0, policy_version 84723 (0.0007) -[2023-10-09 11:41:02,348][23469] Updated weights for policy 1, policy_version 85171 (0.0008) -[2023-10-09 11:41:02,476][23468] Updated weights for policy 0, policy_version 84733 (0.0007) -[2023-10-09 11:41:02,723][23469] Updated weights for policy 1, policy_version 85181 (0.0007) -[2023-10-09 11:41:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 173998080. Throughput: 0: 1757.1, 1: 1778.4. Samples: 43507212. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:41:06,078][22500] Avg episode reward: [(0, '10.410'), (1, '9.570')] -[2023-10-09 11:41:06,383][23468] Updated weights for policy 0, policy_version 84743 (0.0007) -[2023-10-09 11:41:06,455][23469] Updated weights for policy 1, policy_version 85191 (0.0007) -[2023-10-09 11:41:06,746][23468] Updated weights for policy 0, policy_version 84753 (0.0009) -[2023-10-09 11:41:06,829][23469] Updated weights for policy 1, policy_version 85201 (0.0007) -[2023-10-09 11:41:07,118][23468] Updated weights for policy 0, policy_version 84763 (0.0007) -[2023-10-09 11:41:07,209][23469] Updated weights for policy 1, policy_version 85211 (0.0009) -[2023-10-09 11:41:10,875][23469] Updated weights for policy 1, policy_version 85221 (0.0010) -[2023-10-09 11:41:10,954][23468] Updated weights for policy 0, policy_version 84773 (0.0007) -[2023-10-09 11:41:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 174063616. Throughput: 0: 1756.1, 1: 1775.1. Samples: 43529402. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:41:11,078][22500] Avg episode reward: [(0, '9.840'), (1, '8.830')] -[2023-10-09 11:41:11,249][23469] Updated weights for policy 1, policy_version 85231 (0.0009) -[2023-10-09 11:41:11,324][23468] Updated weights for policy 0, policy_version 84783 (0.0007) -[2023-10-09 11:41:11,618][23469] Updated weights for policy 1, policy_version 85241 (0.0010) -[2023-10-09 11:41:11,705][23468] Updated weights for policy 0, policy_version 84793 (0.0007) -[2023-10-09 11:41:15,294][23469] Updated weights for policy 1, policy_version 85251 (0.0008) -[2023-10-09 11:41:15,452][23468] Updated weights for policy 0, policy_version 84803 (0.0008) -[2023-10-09 11:41:15,662][23469] Updated weights for policy 1, policy_version 85261 (0.0009) -[2023-10-09 11:41:15,814][23468] Updated weights for policy 0, policy_version 84813 (0.0007) -[2023-10-09 11:41:16,034][23469] Updated weights for policy 1, policy_version 85271 (0.0008) -[2023-10-09 11:41:16,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 174129152. Throughput: 0: 1785.8, 1: 1798.8. Samples: 43551260. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:41:16,079][22500] Avg episode reward: [(0, '10.530'), (1, '8.930')] -[2023-10-09 11:41:16,188][23468] Updated weights for policy 0, policy_version 84823 (0.0008) -[2023-10-09 11:41:19,818][23469] Updated weights for policy 1, policy_version 85281 (0.0009) -[2023-10-09 11:41:20,021][23468] Updated weights for policy 0, policy_version 84833 (0.0008) -[2023-10-09 11:41:20,180][23469] Updated weights for policy 1, policy_version 85291 (0.0010) -[2023-10-09 11:41:20,393][23468] Updated weights for policy 0, policy_version 84843 (0.0008) -[2023-10-09 11:41:20,559][23469] Updated weights for policy 1, policy_version 85301 (0.0009) -[2023-10-09 11:41:20,759][23468] Updated weights for policy 0, policy_version 84853 (0.0009) -[2023-10-09 11:41:20,917][23469] Updated weights for policy 1, policy_version 85311 (0.0007) -[2023-10-09 11:41:21,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 174227456. Throughput: 0: 1757.3, 1: 1782.3. Samples: 43561636. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:41:21,078][22500] Avg episode reward: [(0, '10.290'), (1, '9.330')] -[2023-10-09 11:41:21,130][23468] Updated weights for policy 0, policy_version 84863 (0.0010) -[2023-10-09 11:41:24,785][23469] Updated weights for policy 1, policy_version 85321 (0.0007) -[2023-10-09 11:41:24,861][23468] Updated weights for policy 0, policy_version 84873 (0.0009) -[2023-10-09 11:41:25,158][23469] Updated weights for policy 1, policy_version 85331 (0.0008) -[2023-10-09 11:41:25,245][23468] Updated weights for policy 0, policy_version 84883 (0.0008) -[2023-10-09 11:41:25,533][23469] Updated weights for policy 1, policy_version 85341 (0.0009) -[2023-10-09 11:41:25,606][23468] Updated weights for policy 0, policy_version 84893 (0.0008) -[2023-10-09 11:41:26,077][22500] Fps is (10 sec: 19661.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 174325760. Throughput: 0: 1788.1, 1: 1807.9. Samples: 43583302. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:41:26,078][22500] Avg episode reward: [(0, '11.110'), (1, '9.330')] -[2023-10-09 11:41:29,212][23469] Updated weights for policy 1, policy_version 85351 (0.0008) -[2023-10-09 11:41:29,309][23468] Updated weights for policy 0, policy_version 84903 (0.0009) -[2023-10-09 11:41:29,584][23469] Updated weights for policy 1, policy_version 85361 (0.0008) -[2023-10-09 11:41:29,687][23468] Updated weights for policy 0, policy_version 84913 (0.0010) -[2023-10-09 11:41:29,952][23469] Updated weights for policy 1, policy_version 85371 (0.0008) -[2023-10-09 11:41:30,063][23468] Updated weights for policy 0, policy_version 84923 (0.0008) -[2023-10-09 11:41:31,078][22500] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 174391296. Throughput: 0: 1756.0, 1: 1790.6. Samples: 43603334. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:41:31,079][22500] Avg episode reward: [(0, '11.010'), (1, '9.950')] -[2023-10-09 11:41:33,770][23469] Updated weights for policy 1, policy_version 85381 (0.0007) -[2023-10-09 11:41:34,051][23468] Updated weights for policy 0, policy_version 84933 (0.0009) -[2023-10-09 11:41:34,152][23469] Updated weights for policy 1, policy_version 85391 (0.0007) -[2023-10-09 11:41:34,433][23468] Updated weights for policy 0, policy_version 84943 (0.0008) -[2023-10-09 11:41:34,522][23469] Updated weights for policy 1, policy_version 85401 (0.0007) -[2023-10-09 11:41:34,811][23468] Updated weights for policy 0, policy_version 84953 (0.0009) -[2023-10-09 11:41:36,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 174456832. Throughput: 0: 1777.8, 1: 1811.0. Samples: 43615374. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:41:36,078][22500] Avg episode reward: [(0, '10.100'), (1, '9.590')] -[2023-10-09 11:41:38,324][23469] Updated weights for policy 1, policy_version 85411 (0.0008) -[2023-10-09 11:41:38,575][23468] Updated weights for policy 0, policy_version 84963 (0.0009) -[2023-10-09 11:41:38,694][23469] Updated weights for policy 1, policy_version 85421 (0.0007) -[2023-10-09 11:41:38,944][23468] Updated weights for policy 0, policy_version 84973 (0.0008) -[2023-10-09 11:41:39,064][23469] Updated weights for policy 1, policy_version 85431 (0.0007) -[2023-10-09 11:41:39,316][23468] Updated weights for policy 0, policy_version 84983 (0.0007) -[2023-10-09 11:41:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 174522368. Throughput: 0: 1762.5, 1: 1795.8. Samples: 43635386. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:41:41,079][22500] Avg episode reward: [(0, '9.300'), (1, '9.250')] -[2023-10-09 11:41:42,742][23469] Updated weights for policy 1, policy_version 85441 (0.0007) -[2023-10-09 11:41:42,855][23468] Updated weights for policy 0, policy_version 84993 (0.0011) -[2023-10-09 11:41:43,113][23469] Updated weights for policy 1, policy_version 85451 (0.0008) -[2023-10-09 11:41:43,228][23468] Updated weights for policy 0, policy_version 85003 (0.0007) -[2023-10-09 11:41:43,486][23469] Updated weights for policy 1, policy_version 85461 (0.0008) -[2023-10-09 11:41:43,596][23468] Updated weights for policy 0, policy_version 85013 (0.0007) -[2023-10-09 11:41:43,852][23469] Updated weights for policy 1, policy_version 85471 (0.0008) -[2023-10-09 11:41:43,966][23468] Updated weights for policy 0, policy_version 85023 (0.0009) -[2023-10-09 11:41:46,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 174587904. Throughput: 0: 1759.3, 1: 1791.7. Samples: 43657344. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:41:46,078][22500] Avg episode reward: [(0, '9.840'), (1, '9.220')] -[2023-10-09 11:41:47,746][23469] Updated weights for policy 1, policy_version 85481 (0.0008) -[2023-10-09 11:41:47,951][23468] Updated weights for policy 0, policy_version 85033 (0.0009) -[2023-10-09 11:41:48,111][23469] Updated weights for policy 1, policy_version 85491 (0.0009) -[2023-10-09 11:41:48,320][23468] Updated weights for policy 0, policy_version 85043 (0.0008) -[2023-10-09 11:41:48,483][23469] Updated weights for policy 1, policy_version 85501 (0.0008) -[2023-10-09 11:41:48,687][23468] Updated weights for policy 0, policy_version 85053 (0.0007) -[2023-10-09 11:41:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 174653440. Throughput: 0: 1772.6, 1: 1790.2. Samples: 43667536. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:41:51,079][22500] Avg episode reward: [(0, '9.810'), (1, '9.050')] -[2023-10-09 11:41:52,204][23469] Updated weights for policy 1, policy_version 85511 (0.0008) -[2023-10-09 11:41:52,572][23469] Updated weights for policy 1, policy_version 85521 (0.0007) -[2023-10-09 11:41:52,688][23468] Updated weights for policy 0, policy_version 85063 (0.0008) -[2023-10-09 11:41:52,939][23469] Updated weights for policy 1, policy_version 85531 (0.0008) -[2023-10-09 11:41:53,064][23468] Updated weights for policy 0, policy_version 85073 (0.0009) -[2023-10-09 11:41:53,437][23468] Updated weights for policy 0, policy_version 85083 (0.0008) -[2023-10-09 11:41:56,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 174718976. Throughput: 0: 1749.6, 1: 1795.4. Samples: 43688928. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:41:56,078][22500] Avg episode reward: [(0, '10.480'), (1, '10.030')] -[2023-10-09 11:41:56,746][23469] Updated weights for policy 1, policy_version 85541 (0.0008) -[2023-10-09 11:41:57,118][23469] Updated weights for policy 1, policy_version 85551 (0.0008) -[2023-10-09 11:41:57,263][23468] Updated weights for policy 0, policy_version 85093 (0.0008) -[2023-10-09 11:41:57,490][23469] Updated weights for policy 1, policy_version 85561 (0.0008) -[2023-10-09 11:41:57,643][23468] Updated weights for policy 0, policy_version 85103 (0.0008) -[2023-10-09 11:41:58,022][23468] Updated weights for policy 0, policy_version 85113 (0.0009) -[2023-10-09 11:42:01,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 174784512. Throughput: 0: 1746.9, 1: 1805.1. Samples: 43711100. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:42:01,078][22500] Avg episode reward: [(0, '11.650'), (1, '9.750')] -[2023-10-09 11:42:01,243][23469] Updated weights for policy 1, policy_version 85571 (0.0008) -[2023-10-09 11:42:01,605][23469] Updated weights for policy 1, policy_version 85581 (0.0007) -[2023-10-09 11:42:01,707][23468] Updated weights for policy 0, policy_version 85123 (0.0008) -[2023-10-09 11:42:01,977][23469] Updated weights for policy 1, policy_version 85591 (0.0009) -[2023-10-09 11:42:02,072][23468] Updated weights for policy 0, policy_version 85133 (0.0009) -[2023-10-09 11:42:02,448][23468] Updated weights for policy 0, policy_version 85143 (0.0008) -[2023-10-09 11:42:05,789][23469] Updated weights for policy 1, policy_version 85601 (0.0008) -[2023-10-09 11:42:06,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 174850048. Throughput: 0: 1746.9, 1: 1791.1. Samples: 43720846. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:42:06,078][22500] Avg episode reward: [(0, '11.130'), (1, '9.850')] -[2023-10-09 11:42:06,145][23469] Updated weights for policy 1, policy_version 85611 (0.0007) -[2023-10-09 11:42:06,439][23468] Updated weights for policy 0, policy_version 85153 (0.0008) -[2023-10-09 11:42:06,522][23469] Updated weights for policy 1, policy_version 85621 (0.0008) -[2023-10-09 11:42:06,812][23468] Updated weights for policy 0, policy_version 85163 (0.0007) -[2023-10-09 11:42:06,879][23469] Updated weights for policy 1, policy_version 85631 (0.0007) -[2023-10-09 11:42:07,183][23468] Updated weights for policy 0, policy_version 85173 (0.0010) -[2023-10-09 11:42:07,555][23468] Updated weights for policy 0, policy_version 85183 (0.0010) -[2023-10-09 11:42:10,439][23469] Updated weights for policy 1, policy_version 85641 (0.0008) -[2023-10-09 11:42:10,818][23469] Updated weights for policy 1, policy_version 85651 (0.0008) -[2023-10-09 11:42:11,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 174915584. Throughput: 0: 1752.1, 1: 1804.8. Samples: 43743364. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:42:11,078][22500] Avg episode reward: [(0, '10.790'), (1, '10.060')] -[2023-10-09 11:42:11,183][23469] Updated weights for policy 1, policy_version 85661 (0.0008) -[2023-10-09 11:42:11,398][23468] Updated weights for policy 0, policy_version 85193 (0.0008) -[2023-10-09 11:42:11,768][23468] Updated weights for policy 0, policy_version 85203 (0.0009) -[2023-10-09 11:42:12,142][23468] Updated weights for policy 0, policy_version 85213 (0.0008) -[2023-10-09 11:42:14,891][23469] Updated weights for policy 1, policy_version 85671 (0.0009) -[2023-10-09 11:42:15,269][23469] Updated weights for policy 1, policy_version 85681 (0.0008) -[2023-10-09 11:42:15,627][23469] Updated weights for policy 1, policy_version 85691 (0.0008) -[2023-10-09 11:42:16,014][23468] Updated weights for policy 0, policy_version 85223 (0.0007) -[2023-10-09 11:42:16,078][22500] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 175013888. Throughput: 0: 1781.0, 1: 1792.1. Samples: 43764124. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:42:16,079][22500] Avg episode reward: [(0, '11.450'), (1, '9.340')] -[2023-10-09 11:42:16,089][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000085696_87752704.pth... -[2023-10-09 11:42:16,128][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000084000_86016000.pth -[2023-10-09 11:42:16,376][23468] Updated weights for policy 0, policy_version 85233 (0.0007) -[2023-10-09 11:42:16,749][23468] Updated weights for policy 0, policy_version 85243 (0.0007) -[2023-10-09 11:42:16,932][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000085248_87293952.pth... -[2023-10-09 11:42:16,969][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000083584_85590016.pth -[2023-10-09 11:42:19,467][23469] Updated weights for policy 1, policy_version 85701 (0.0009) -[2023-10-09 11:42:19,849][23469] Updated weights for policy 1, policy_version 85711 (0.0008) -[2023-10-09 11:42:20,216][23469] Updated weights for policy 1, policy_version 85721 (0.0008) -[2023-10-09 11:42:20,452][23468] Updated weights for policy 0, policy_version 85253 (0.0008) -[2023-10-09 11:42:20,834][23468] Updated weights for policy 0, policy_version 85263 (0.0010) -[2023-10-09 11:42:21,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 175079424. Throughput: 0: 1750.4, 1: 1803.2. Samples: 43775288. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:42:21,078][22500] Avg episode reward: [(0, '10.860'), (1, '9.310')] -[2023-10-09 11:42:21,217][23468] Updated weights for policy 0, policy_version 85273 (0.0010) -[2023-10-09 11:42:23,862][23469] Updated weights for policy 1, policy_version 85731 (0.0008) -[2023-10-09 11:42:24,227][23469] Updated weights for policy 1, policy_version 85741 (0.0007) -[2023-10-09 11:42:24,598][23469] Updated weights for policy 1, policy_version 85751 (0.0009) -[2023-10-09 11:42:25,054][23468] Updated weights for policy 0, policy_version 85283 (0.0008) -[2023-10-09 11:42:25,423][23468] Updated weights for policy 0, policy_version 85293 (0.0009) -[2023-10-09 11:42:25,800][23468] Updated weights for policy 0, policy_version 85303 (0.0008) -[2023-10-09 11:42:26,077][22500] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 14329.1). Total num frames: 175144960. Throughput: 0: 1774.2, 1: 1801.0. Samples: 43796270. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:42:26,078][22500] Avg episode reward: [(0, '11.010'), (1, '8.970')] -[2023-10-09 11:42:28,253][23469] Updated weights for policy 1, policy_version 85761 (0.0009) -[2023-10-09 11:42:28,617][23469] Updated weights for policy 1, policy_version 85771 (0.0008) -[2023-10-09 11:42:28,983][23469] Updated weights for policy 1, policy_version 85781 (0.0010) -[2023-10-09 11:42:29,357][23469] Updated weights for policy 1, policy_version 85791 (0.0009) -[2023-10-09 11:42:29,552][23468] Updated weights for policy 0, policy_version 85313 (0.0007) -[2023-10-09 11:42:29,912][23468] Updated weights for policy 0, policy_version 85323 (0.0008) -[2023-10-09 11:42:30,288][23468] Updated weights for policy 0, policy_version 85333 (0.0008) -[2023-10-09 11:42:30,661][23468] Updated weights for policy 0, policy_version 85343 (0.0007) -[2023-10-09 11:42:31,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 175243264. Throughput: 0: 1760.7, 1: 1801.6. Samples: 43817646. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-10-09 11:42:31,078][22500] Avg episode reward: [(0, '11.200'), (1, '8.660')] -[2023-10-09 11:42:33,109][23469] Updated weights for policy 1, policy_version 85801 (0.0009) -[2023-10-09 11:42:33,479][23469] Updated weights for policy 1, policy_version 85811 (0.0008) -[2023-10-09 11:42:33,840][23469] Updated weights for policy 1, policy_version 85821 (0.0007) -[2023-10-09 11:42:34,384][23468] Updated weights for policy 0, policy_version 85353 (0.0007) -[2023-10-09 11:42:34,753][23468] Updated weights for policy 0, policy_version 85363 (0.0008) -[2023-10-09 11:42:35,141][23468] Updated weights for policy 0, policy_version 85373 (0.0008) -[2023-10-09 11:42:36,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 175308800. Throughput: 0: 1773.3, 1: 1809.7. Samples: 43828768. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-10-09 11:42:36,078][22500] Avg episode reward: [(0, '9.900'), (1, '8.750')] -[2023-10-09 11:42:37,380][23469] Updated weights for policy 1, policy_version 85831 (0.0007) -[2023-10-09 11:42:37,748][23469] Updated weights for policy 1, policy_version 85841 (0.0008) -[2023-10-09 11:42:38,127][23469] Updated weights for policy 1, policy_version 85851 (0.0008) -[2023-10-09 11:42:38,929][23468] Updated weights for policy 0, policy_version 85383 (0.0010) -[2023-10-09 11:42:39,303][23468] Updated weights for policy 0, policy_version 85393 (0.0009) -[2023-10-09 11:42:39,675][23468] Updated weights for policy 0, policy_version 85403 (0.0010) -[2023-10-09 11:42:41,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 175374336. Throughput: 0: 1782.8, 1: 1813.1. Samples: 43850742. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-10-09 11:42:41,078][22500] Avg episode reward: [(0, '10.720'), (1, '9.130')] -[2023-10-09 11:42:41,830][23469] Updated weights for policy 1, policy_version 85861 (0.0009) -[2023-10-09 11:42:42,202][23469] Updated weights for policy 1, policy_version 85871 (0.0008) -[2023-10-09 11:42:42,577][23469] Updated weights for policy 1, policy_version 85881 (0.0008) -[2023-10-09 11:42:43,298][23468] Updated weights for policy 0, policy_version 85413 (0.0008) -[2023-10-09 11:42:43,666][23468] Updated weights for policy 0, policy_version 85423 (0.0008) -[2023-10-09 11:42:44,033][23468] Updated weights for policy 0, policy_version 85433 (0.0007) -[2023-10-09 11:42:46,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 175439872. Throughput: 0: 1779.5, 1: 1811.2. Samples: 43872680. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-10-09 11:42:46,078][22500] Avg episode reward: [(0, '10.710'), (1, '9.580')] -[2023-10-09 11:42:46,379][23469] Updated weights for policy 1, policy_version 85891 (0.0007) -[2023-10-09 11:42:46,750][23469] Updated weights for policy 1, policy_version 85901 (0.0008) -[2023-10-09 11:42:47,132][23469] Updated weights for policy 1, policy_version 85911 (0.0007) -[2023-10-09 11:42:47,722][23468] Updated weights for policy 0, policy_version 85443 (0.0007) -[2023-10-09 11:42:48,093][23468] Updated weights for policy 0, policy_version 85453 (0.0008) -[2023-10-09 11:42:48,466][23468] Updated weights for policy 0, policy_version 85463 (0.0008) -[2023-10-09 11:42:50,802][23469] Updated weights for policy 1, policy_version 85921 (0.0009) -[2023-10-09 11:42:51,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 175505408. Throughput: 0: 1793.7, 1: 1813.1. Samples: 43883154. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-10-09 11:42:51,078][22500] Avg episode reward: [(0, '11.120'), (1, '9.370')] -[2023-10-09 11:42:51,162][23469] Updated weights for policy 1, policy_version 85931 (0.0010) -[2023-10-09 11:42:51,530][23469] Updated weights for policy 1, policy_version 85941 (0.0011) -[2023-10-09 11:42:51,909][23469] Updated weights for policy 1, policy_version 85951 (0.0011) -[2023-10-09 11:42:52,326][23468] Updated weights for policy 0, policy_version 85473 (0.0009) -[2023-10-09 11:42:52,699][23468] Updated weights for policy 0, policy_version 85483 (0.0008) -[2023-10-09 11:42:53,080][23468] Updated weights for policy 0, policy_version 85493 (0.0007) -[2023-10-09 11:42:53,452][23468] Updated weights for policy 0, policy_version 85503 (0.0008) -[2023-10-09 11:42:55,612][23469] Updated weights for policy 1, policy_version 85961 (0.0011) -[2023-10-09 11:42:55,986][23469] Updated weights for policy 1, policy_version 85971 (0.0009) -[2023-10-09 11:42:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 175570944. Throughput: 0: 1774.4, 1: 1807.7. Samples: 43904562. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-10-09 11:42:56,078][22500] Avg episode reward: [(0, '10.810'), (1, '9.120')] -[2023-10-09 11:42:56,350][23469] Updated weights for policy 1, policy_version 85981 (0.0008) -[2023-10-09 11:42:57,377][23468] Updated weights for policy 0, policy_version 85513 (0.0009) -[2023-10-09 11:42:57,743][23468] Updated weights for policy 0, policy_version 85523 (0.0008) -[2023-10-09 11:42:58,109][23468] Updated weights for policy 0, policy_version 85533 (0.0008) -[2023-10-09 11:43:00,118][23469] Updated weights for policy 1, policy_version 85991 (0.0008) -[2023-10-09 11:43:00,491][23469] Updated weights for policy 1, policy_version 86001 (0.0009) -[2023-10-09 11:43:00,852][23469] Updated weights for policy 1, policy_version 86011 (0.0012) -[2023-10-09 11:43:01,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 175669248. Throughput: 0: 1775.5, 1: 1818.1. Samples: 43925836. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-10-09 11:43:01,078][22500] Avg episode reward: [(0, '11.170'), (1, '9.760')] -[2023-10-09 11:43:01,782][23468] Updated weights for policy 0, policy_version 85543 (0.0009) -[2023-10-09 11:43:02,161][23468] Updated weights for policy 0, policy_version 85553 (0.0009) -[2023-10-09 11:43:02,541][23468] Updated weights for policy 0, policy_version 85563 (0.0009) -[2023-10-09 11:43:04,573][23469] Updated weights for policy 1, policy_version 86021 (0.0008) -[2023-10-09 11:43:04,961][23469] Updated weights for policy 1, policy_version 86031 (0.0007) -[2023-10-09 11:43:05,329][23469] Updated weights for policy 1, policy_version 86041 (0.0010) -[2023-10-09 11:43:06,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 175734784. Throughput: 0: 1778.1, 1: 1809.2. Samples: 43936716. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-10-09 11:43:06,078][22500] Avg episode reward: [(0, '10.830'), (1, '9.720')] -[2023-10-09 11:43:06,282][23468] Updated weights for policy 0, policy_version 85573 (0.0010) -[2023-10-09 11:43:06,669][23468] Updated weights for policy 0, policy_version 85583 (0.0008) -[2023-10-09 11:43:07,038][23468] Updated weights for policy 0, policy_version 85593 (0.0007) -[2023-10-09 11:43:08,906][23469] Updated weights for policy 1, policy_version 86051 (0.0009) -[2023-10-09 11:43:09,282][23469] Updated weights for policy 1, policy_version 86061 (0.0007) -[2023-10-09 11:43:09,644][23469] Updated weights for policy 1, policy_version 86071 (0.0007) -[2023-10-09 11:43:10,829][23468] Updated weights for policy 0, policy_version 85603 (0.0008) -[2023-10-09 11:43:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 175800320. Throughput: 0: 1776.6, 1: 1816.8. Samples: 43957974. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-10-09 11:43:11,078][22500] Avg episode reward: [(0, '10.770'), (1, '10.490')] -[2023-10-09 11:43:11,207][23468] Updated weights for policy 0, policy_version 85613 (0.0009) -[2023-10-09 11:43:11,577][23468] Updated weights for policy 0, policy_version 85623 (0.0008) -[2023-10-09 11:43:13,345][23469] Updated weights for policy 1, policy_version 86081 (0.0008) -[2023-10-09 11:43:13,717][23469] Updated weights for policy 1, policy_version 86091 (0.0008) -[2023-10-09 11:43:14,084][23469] Updated weights for policy 1, policy_version 86101 (0.0009) -[2023-10-09 11:43:14,446][23469] Updated weights for policy 1, policy_version 86111 (0.0007) -[2023-10-09 11:43:15,360][23468] Updated weights for policy 0, policy_version 85633 (0.0009) -[2023-10-09 11:43:15,727][23468] Updated weights for policy 0, policy_version 85643 (0.0010) -[2023-10-09 11:43:16,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 175865856. Throughput: 0: 1799.7, 1: 1811.6. Samples: 43980154. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-10-09 11:43:16,079][22500] Avg episode reward: [(0, '10.730'), (1, '9.380')] -[2023-10-09 11:43:16,104][23468] Updated weights for policy 0, policy_version 85653 (0.0010) -[2023-10-09 11:43:16,486][23468] Updated weights for policy 0, policy_version 85663 (0.0009) -[2023-10-09 11:43:18,144][23469] Updated weights for policy 1, policy_version 86121 (0.0009) -[2023-10-09 11:43:18,509][23469] Updated weights for policy 1, policy_version 86131 (0.0009) -[2023-10-09 11:43:18,880][23469] Updated weights for policy 1, policy_version 86141 (0.0008) -[2023-10-09 11:43:20,258][23468] Updated weights for policy 0, policy_version 85673 (0.0010) -[2023-10-09 11:43:20,631][23468] Updated weights for policy 0, policy_version 85683 (0.0010) -[2023-10-09 11:43:21,000][23468] Updated weights for policy 0, policy_version 85693 (0.0010) -[2023-10-09 11:43:21,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 175931392. Throughput: 0: 1774.8, 1: 1813.5. Samples: 43990244. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-10-09 11:43:21,078][22500] Avg episode reward: [(0, '10.860'), (1, '9.580')] -[2023-10-09 11:43:22,665][23469] Updated weights for policy 1, policy_version 86151 (0.0009) -[2023-10-09 11:43:23,025][23469] Updated weights for policy 1, policy_version 86161 (0.0007) -[2023-10-09 11:43:23,401][23469] Updated weights for policy 1, policy_version 86171 (0.0007) -[2023-10-09 11:43:24,706][23468] Updated weights for policy 0, policy_version 85703 (0.0008) -[2023-10-09 11:43:25,078][23468] Updated weights for policy 0, policy_version 85713 (0.0008) -[2023-10-09 11:43:25,447][23468] Updated weights for policy 0, policy_version 85723 (0.0007) -[2023-10-09 11:43:26,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 176029696. Throughput: 0: 1796.0, 1: 1793.3. Samples: 44012258. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:43:26,078][22500] Avg episode reward: [(0, '10.680'), (1, '8.580')] -[2023-10-09 11:43:27,165][23469] Updated weights for policy 1, policy_version 86181 (0.0008) -[2023-10-09 11:43:27,537][23469] Updated weights for policy 1, policy_version 86191 (0.0008) -[2023-10-09 11:43:27,911][23469] Updated weights for policy 1, policy_version 86201 (0.0008) -[2023-10-09 11:43:29,186][23468] Updated weights for policy 0, policy_version 85733 (0.0009) -[2023-10-09 11:43:29,558][23468] Updated weights for policy 0, policy_version 85743 (0.0011) -[2023-10-09 11:43:29,930][23468] Updated weights for policy 0, policy_version 85753 (0.0009) -[2023-10-09 11:43:31,078][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 176095232. Throughput: 0: 1769.9, 1: 1805.1. Samples: 44033558. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:43:31,079][22500] Avg episode reward: [(0, '11.590'), (1, '9.360')] -[2023-10-09 11:43:31,551][23469] Updated weights for policy 1, policy_version 86211 (0.0009) -[2023-10-09 11:43:31,925][23469] Updated weights for policy 1, policy_version 86221 (0.0008) -[2023-10-09 11:43:32,302][23469] Updated weights for policy 1, policy_version 86231 (0.0008) -[2023-10-09 11:43:33,659][23468] Updated weights for policy 0, policy_version 85763 (0.0010) -[2023-10-09 11:43:34,029][23468] Updated weights for policy 0, policy_version 85773 (0.0010) -[2023-10-09 11:43:34,395][23468] Updated weights for policy 0, policy_version 85783 (0.0009) -[2023-10-09 11:43:35,946][23469] Updated weights for policy 1, policy_version 86241 (0.0008) -[2023-10-09 11:43:36,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 176160768. Throughput: 0: 1792.1, 1: 1803.3. Samples: 44044944. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:43:36,078][22500] Avg episode reward: [(0, '11.440'), (1, '9.650')] -[2023-10-09 11:43:36,321][23469] Updated weights for policy 1, policy_version 86251 (0.0007) -[2023-10-09 11:43:36,696][23469] Updated weights for policy 1, policy_version 86261 (0.0007) -[2023-10-09 11:43:37,060][23469] Updated weights for policy 1, policy_version 86271 (0.0007) -[2023-10-09 11:43:38,230][23468] Updated weights for policy 0, policy_version 85793 (0.0010) -[2023-10-09 11:43:38,600][23468] Updated weights for policy 0, policy_version 85803 (0.0008) -[2023-10-09 11:43:38,975][23468] Updated weights for policy 0, policy_version 85813 (0.0009) -[2023-10-09 11:43:39,347][23468] Updated weights for policy 0, policy_version 85823 (0.0010) -[2023-10-09 11:43:40,786][23469] Updated weights for policy 1, policy_version 86281 (0.0008) -[2023-10-09 11:43:41,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 176226304. Throughput: 0: 1778.7, 1: 1809.3. Samples: 44066022. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:43:41,078][22500] Avg episode reward: [(0, '11.610'), (1, '9.740')] -[2023-10-09 11:43:41,155][23469] Updated weights for policy 1, policy_version 86291 (0.0007) -[2023-10-09 11:43:41,530][23469] Updated weights for policy 1, policy_version 86301 (0.0007) -[2023-10-09 11:43:43,090][23468] Updated weights for policy 0, policy_version 85833 (0.0009) -[2023-10-09 11:43:43,455][23468] Updated weights for policy 0, policy_version 85843 (0.0009) -[2023-10-09 11:43:43,823][23468] Updated weights for policy 0, policy_version 85853 (0.0010) -[2023-10-09 11:43:45,119][23469] Updated weights for policy 1, policy_version 86311 (0.0009) -[2023-10-09 11:43:45,484][23469] Updated weights for policy 1, policy_version 86321 (0.0008) -[2023-10-09 11:43:45,849][23469] Updated weights for policy 1, policy_version 86331 (0.0009) -[2023-10-09 11:43:46,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 176324608. Throughput: 0: 1776.3, 1: 1812.5. Samples: 44087330. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:43:46,078][22500] Avg episode reward: [(0, '10.260'), (1, '9.520')] -[2023-10-09 11:43:47,641][23468] Updated weights for policy 0, policy_version 85863 (0.0008) -[2023-10-09 11:43:48,019][23468] Updated weights for policy 0, policy_version 85873 (0.0008) -[2023-10-09 11:43:48,397][23468] Updated weights for policy 0, policy_version 85883 (0.0008) -[2023-10-09 11:43:49,601][23469] Updated weights for policy 1, policy_version 86341 (0.0007) -[2023-10-09 11:43:49,995][23469] Updated weights for policy 1, policy_version 86351 (0.0008) -[2023-10-09 11:43:50,351][23469] Updated weights for policy 1, policy_version 86361 (0.0009) -[2023-10-09 11:43:51,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 176390144. Throughput: 0: 1786.0, 1: 1813.0. Samples: 44098672. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:43:51,079][22500] Avg episode reward: [(0, '9.780'), (1, '9.370')] -[2023-10-09 11:43:52,261][23468] Updated weights for policy 0, policy_version 85893 (0.0010) -[2023-10-09 11:43:52,631][23468] Updated weights for policy 0, policy_version 85903 (0.0010) -[2023-10-09 11:43:53,013][23468] Updated weights for policy 0, policy_version 85913 (0.0007) -[2023-10-09 11:43:54,056][23469] Updated weights for policy 1, policy_version 86371 (0.0008) -[2023-10-09 11:43:54,428][23469] Updated weights for policy 1, policy_version 86381 (0.0010) -[2023-10-09 11:43:54,803][23469] Updated weights for policy 1, policy_version 86391 (0.0007) -[2023-10-09 11:43:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 176455680. Throughput: 0: 1780.9, 1: 1810.8. Samples: 44119604. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:43:56,078][22500] Avg episode reward: [(0, '10.170'), (1, '9.650')] -[2023-10-09 11:43:56,833][23468] Updated weights for policy 0, policy_version 85923 (0.0008) -[2023-10-09 11:43:57,225][23468] Updated weights for policy 0, policy_version 85933 (0.0009) -[2023-10-09 11:43:57,605][23468] Updated weights for policy 0, policy_version 85943 (0.0007) -[2023-10-09 11:43:58,453][23469] Updated weights for policy 1, policy_version 86401 (0.0010) -[2023-10-09 11:43:58,827][23469] Updated weights for policy 1, policy_version 86411 (0.0008) -[2023-10-09 11:43:59,203][23469] Updated weights for policy 1, policy_version 86421 (0.0009) -[2023-10-09 11:43:59,580][23469] Updated weights for policy 1, policy_version 86431 (0.0009) -[2023-10-09 11:44:01,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 176521216. Throughput: 0: 1772.0, 1: 1809.7. Samples: 44141330. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:44:01,079][22500] Avg episode reward: [(0, '10.690'), (1, '9.720')] -[2023-10-09 11:44:01,520][23468] Updated weights for policy 0, policy_version 85953 (0.0009) -[2023-10-09 11:44:01,886][23468] Updated weights for policy 0, policy_version 85963 (0.0012) -[2023-10-09 11:44:02,255][23468] Updated weights for policy 0, policy_version 85973 (0.0009) -[2023-10-09 11:44:02,635][23468] Updated weights for policy 0, policy_version 85983 (0.0008) -[2023-10-09 11:44:03,385][23469] Updated weights for policy 1, policy_version 86441 (0.0007) -[2023-10-09 11:44:03,757][23469] Updated weights for policy 1, policy_version 86451 (0.0008) -[2023-10-09 11:44:04,119][23469] Updated weights for policy 1, policy_version 86461 (0.0010) -[2023-10-09 11:44:06,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 176586752. Throughput: 0: 1769.9, 1: 1815.5. Samples: 44151584. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:44:06,078][22500] Avg episode reward: [(0, '11.140'), (1, '10.610')] -[2023-10-09 11:44:06,079][23343] Saving new best policy, reward=10.610! -[2023-10-09 11:44:06,308][23468] Updated weights for policy 0, policy_version 85993 (0.0007) -[2023-10-09 11:44:06,678][23468] Updated weights for policy 0, policy_version 86003 (0.0009) -[2023-10-09 11:44:07,061][23468] Updated weights for policy 0, policy_version 86013 (0.0009) -[2023-10-09 11:44:07,866][23469] Updated weights for policy 1, policy_version 86471 (0.0008) -[2023-10-09 11:44:08,238][23469] Updated weights for policy 1, policy_version 86481 (0.0007) -[2023-10-09 11:44:08,613][23469] Updated weights for policy 1, policy_version 86491 (0.0007) -[2023-10-09 11:44:10,899][23468] Updated weights for policy 0, policy_version 86023 (0.0009) -[2023-10-09 11:44:11,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 176652288. Throughput: 0: 1766.3, 1: 1818.9. Samples: 44173590. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:44:11,078][22500] Avg episode reward: [(0, '10.600'), (1, '10.190')] -[2023-10-09 11:44:11,282][23468] Updated weights for policy 0, policy_version 86033 (0.0011) -[2023-10-09 11:44:11,644][23468] Updated weights for policy 0, policy_version 86043 (0.0010) -[2023-10-09 11:44:12,239][23469] Updated weights for policy 1, policy_version 86501 (0.0009) -[2023-10-09 11:44:12,611][23469] Updated weights for policy 1, policy_version 86511 (0.0010) -[2023-10-09 11:44:12,982][23469] Updated weights for policy 1, policy_version 86521 (0.0008) -[2023-10-09 11:44:15,548][23468] Updated weights for policy 0, policy_version 86053 (0.0009) -[2023-10-09 11:44:15,927][23468] Updated weights for policy 0, policy_version 86063 (0.0009) -[2023-10-09 11:44:16,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 176717824. Throughput: 0: 1799.0, 1: 1806.2. Samples: 44195792. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:44:16,078][22500] Avg episode reward: [(0, '10.570'), (1, '9.650')] -[2023-10-09 11:44:16,087][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000086528_88604672.pth... -[2023-10-09 11:44:16,124][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000084864_86900736.pth -[2023-10-09 11:44:16,293][23468] Updated weights for policy 0, policy_version 86073 (0.0010) -[2023-10-09 11:44:16,550][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000086080_88145920.pth... -[2023-10-09 11:44:16,579][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000084416_86441984.pth -[2023-10-09 11:44:16,862][23469] Updated weights for policy 1, policy_version 86531 (0.0008) -[2023-10-09 11:44:17,230][23469] Updated weights for policy 1, policy_version 86541 (0.0008) -[2023-10-09 11:44:17,596][23469] Updated weights for policy 1, policy_version 86551 (0.0008) -[2023-10-09 11:44:20,110][23468] Updated weights for policy 0, policy_version 86083 (0.0009) -[2023-10-09 11:44:20,482][23468] Updated weights for policy 0, policy_version 86093 (0.0007) -[2023-10-09 11:44:20,849][23468] Updated weights for policy 0, policy_version 86103 (0.0008) -[2023-10-09 11:44:21,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 176783360. Throughput: 0: 1763.5, 1: 1804.9. Samples: 44205522. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:44:21,078][22500] Avg episode reward: [(0, '9.920'), (1, '8.750')] -[2023-10-09 11:44:21,452][23469] Updated weights for policy 1, policy_version 86561 (0.0009) -[2023-10-09 11:44:21,821][23469] Updated weights for policy 1, policy_version 86571 (0.0007) -[2023-10-09 11:44:22,202][23469] Updated weights for policy 1, policy_version 86581 (0.0008) -[2023-10-09 11:44:22,575][23469] Updated weights for policy 1, policy_version 86591 (0.0008) -[2023-10-09 11:44:24,574][23468] Updated weights for policy 0, policy_version 86113 (0.0010) -[2023-10-09 11:44:24,945][23468] Updated weights for policy 0, policy_version 86123 (0.0010) -[2023-10-09 11:44:25,325][23468] Updated weights for policy 0, policy_version 86133 (0.0009) -[2023-10-09 11:44:25,692][23468] Updated weights for policy 0, policy_version 86143 (0.0009) -[2023-10-09 11:44:26,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 176881664. Throughput: 0: 1796.2, 1: 1801.2. Samples: 44227902. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:44:26,078][22500] Avg episode reward: [(0, '10.120'), (1, '8.980')] -[2023-10-09 11:44:26,300][23469] Updated weights for policy 1, policy_version 86601 (0.0008) -[2023-10-09 11:44:26,667][23469] Updated weights for policy 1, policy_version 86611 (0.0007) -[2023-10-09 11:44:27,039][23469] Updated weights for policy 1, policy_version 86621 (0.0007) -[2023-10-09 11:44:29,454][23468] Updated weights for policy 0, policy_version 86153 (0.0008) -[2023-10-09 11:44:29,816][23468] Updated weights for policy 0, policy_version 86163 (0.0007) -[2023-10-09 11:44:30,189][23468] Updated weights for policy 0, policy_version 86173 (0.0008) -[2023-10-09 11:44:30,751][23469] Updated weights for policy 1, policy_version 86631 (0.0007) -[2023-10-09 11:44:31,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 176947200. Throughput: 0: 1773.5, 1: 1808.4. Samples: 44248516. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:44:31,078][22500] Avg episode reward: [(0, '10.540'), (1, '10.020')] -[2023-10-09 11:44:31,122][23469] Updated weights for policy 1, policy_version 86641 (0.0007) -[2023-10-09 11:44:31,489][23469] Updated weights for policy 1, policy_version 86651 (0.0008) -[2023-10-09 11:44:33,911][23468] Updated weights for policy 0, policy_version 86183 (0.0010) -[2023-10-09 11:44:34,287][23468] Updated weights for policy 0, policy_version 86193 (0.0008) -[2023-10-09 11:44:34,656][23468] Updated weights for policy 0, policy_version 86203 (0.0007) -[2023-10-09 11:44:35,148][23469] Updated weights for policy 1, policy_version 86661 (0.0008) -[2023-10-09 11:44:35,509][23469] Updated weights for policy 1, policy_version 86671 (0.0008) -[2023-10-09 11:44:35,882][23469] Updated weights for policy 1, policy_version 86681 (0.0008) -[2023-10-09 11:44:36,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 177012736. Throughput: 0: 1795.3, 1: 1788.8. Samples: 44259958. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:44:36,078][22500] Avg episode reward: [(0, '10.660'), (1, '9.300')] -[2023-10-09 11:44:38,444][23468] Updated weights for policy 0, policy_version 86213 (0.0010) -[2023-10-09 11:44:38,803][23468] Updated weights for policy 0, policy_version 86223 (0.0010) -[2023-10-09 11:44:39,171][23468] Updated weights for policy 0, policy_version 86233 (0.0010) -[2023-10-09 11:44:39,693][23469] Updated weights for policy 1, policy_version 86691 (0.0009) -[2023-10-09 11:44:40,064][23469] Updated weights for policy 1, policy_version 86701 (0.0007) -[2023-10-09 11:44:40,432][23469] Updated weights for policy 1, policy_version 86711 (0.0009) -[2023-10-09 11:44:41,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 177111040. Throughput: 0: 1779.6, 1: 1808.8. Samples: 44281082. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:44:41,078][22500] Avg episode reward: [(0, '10.380'), (1, '10.300')] -[2023-10-09 11:44:43,035][23468] Updated weights for policy 0, policy_version 86243 (0.0009) -[2023-10-09 11:44:43,432][23468] Updated weights for policy 0, policy_version 86253 (0.0009) -[2023-10-09 11:44:43,800][23468] Updated weights for policy 0, policy_version 86263 (0.0009) -[2023-10-09 11:44:44,205][23469] Updated weights for policy 1, policy_version 86721 (0.0008) -[2023-10-09 11:44:44,578][23469] Updated weights for policy 1, policy_version 86731 (0.0008) -[2023-10-09 11:44:44,948][23469] Updated weights for policy 1, policy_version 86741 (0.0008) -[2023-10-09 11:44:45,313][23469] Updated weights for policy 1, policy_version 86751 (0.0008) -[2023-10-09 11:44:46,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 177176576. Throughput: 0: 1778.7, 1: 1789.7. Samples: 44301906. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:44:46,078][22500] Avg episode reward: [(0, '10.850'), (1, '9.710')] -[2023-10-09 11:44:47,492][23468] Updated weights for policy 0, policy_version 86273 (0.0008) -[2023-10-09 11:44:47,858][23468] Updated weights for policy 0, policy_version 86283 (0.0008) -[2023-10-09 11:44:48,225][23468] Updated weights for policy 0, policy_version 86293 (0.0008) -[2023-10-09 11:44:48,599][23468] Updated weights for policy 0, policy_version 86303 (0.0008) -[2023-10-09 11:44:49,196][23469] Updated weights for policy 1, policy_version 86761 (0.0009) -[2023-10-09 11:44:49,557][23469] Updated weights for policy 1, policy_version 86771 (0.0008) -[2023-10-09 11:44:49,938][23469] Updated weights for policy 1, policy_version 86781 (0.0007) -[2023-10-09 11:44:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 177242112. Throughput: 0: 1794.7, 1: 1805.0. Samples: 44313570. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:44:51,078][22500] Avg episode reward: [(0, '11.000'), (1, '9.820')] -[2023-10-09 11:44:52,308][23468] Updated weights for policy 0, policy_version 86313 (0.0010) -[2023-10-09 11:44:52,691][23468] Updated weights for policy 0, policy_version 86323 (0.0010) -[2023-10-09 11:44:53,068][23468] Updated weights for policy 0, policy_version 86333 (0.0009) -[2023-10-09 11:44:53,569][23469] Updated weights for policy 1, policy_version 86791 (0.0010) -[2023-10-09 11:44:53,934][23469] Updated weights for policy 1, policy_version 86801 (0.0008) -[2023-10-09 11:44:54,302][23469] Updated weights for policy 1, policy_version 86811 (0.0008) -[2023-10-09 11:44:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 177307648. Throughput: 0: 1786.5, 1: 1785.3. Samples: 44334324. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:44:56,078][22500] Avg episode reward: [(0, '11.940'), (1, '9.250')] -[2023-10-09 11:44:56,840][23468] Updated weights for policy 0, policy_version 86343 (0.0009) -[2023-10-09 11:44:57,216][23468] Updated weights for policy 0, policy_version 86353 (0.0009) -[2023-10-09 11:44:57,593][23468] Updated weights for policy 0, policy_version 86363 (0.0008) -[2023-10-09 11:44:57,992][23469] Updated weights for policy 1, policy_version 86821 (0.0008) -[2023-10-09 11:44:58,345][23469] Updated weights for policy 1, policy_version 86831 (0.0007) -[2023-10-09 11:44:58,717][23469] Updated weights for policy 1, policy_version 86841 (0.0007) -[2023-10-09 11:45:01,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 177373184. Throughput: 0: 1789.6, 1: 1793.6. Samples: 44357036. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:45:01,078][22500] Avg episode reward: [(0, '11.430'), (1, '9.180')] -[2023-10-09 11:45:01,292][23468] Updated weights for policy 0, policy_version 86373 (0.0009) -[2023-10-09 11:45:01,674][23468] Updated weights for policy 0, policy_version 86383 (0.0010) -[2023-10-09 11:45:02,038][23468] Updated weights for policy 0, policy_version 86393 (0.0009) -[2023-10-09 11:45:02,380][23469] Updated weights for policy 1, policy_version 86851 (0.0009) -[2023-10-09 11:45:02,749][23469] Updated weights for policy 1, policy_version 86861 (0.0011) -[2023-10-09 11:45:03,114][23469] Updated weights for policy 1, policy_version 86871 (0.0008) -[2023-10-09 11:45:05,740][23468] Updated weights for policy 0, policy_version 86403 (0.0009) -[2023-10-09 11:45:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 177438720. Throughput: 0: 1791.2, 1: 1792.1. Samples: 44366770. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:45:06,078][22500] Avg episode reward: [(0, '11.300'), (1, '8.920')] -[2023-10-09 11:45:06,123][23468] Updated weights for policy 0, policy_version 86413 (0.0009) -[2023-10-09 11:45:06,490][23468] Updated weights for policy 0, policy_version 86423 (0.0009) -[2023-10-09 11:45:07,009][23469] Updated weights for policy 1, policy_version 86881 (0.0007) -[2023-10-09 11:45:07,384][23469] Updated weights for policy 1, policy_version 86891 (0.0010) -[2023-10-09 11:45:07,747][23469] Updated weights for policy 1, policy_version 86901 (0.0007) -[2023-10-09 11:45:08,123][23469] Updated weights for policy 1, policy_version 86911 (0.0008) -[2023-10-09 11:45:10,055][23468] Updated weights for policy 0, policy_version 86433 (0.0007) -[2023-10-09 11:45:10,432][23468] Updated weights for policy 0, policy_version 86443 (0.0010) -[2023-10-09 11:45:10,810][23468] Updated weights for policy 0, policy_version 86453 (0.0011) -[2023-10-09 11:45:11,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 177504256. Throughput: 0: 1796.4, 1: 1792.9. Samples: 44389420. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:45:11,078][22500] Avg episode reward: [(0, '11.400'), (1, '9.320')] -[2023-10-09 11:45:11,181][23468] Updated weights for policy 0, policy_version 86463 (0.0011) -[2023-10-09 11:45:11,893][23469] Updated weights for policy 1, policy_version 86921 (0.0008) -[2023-10-09 11:45:12,255][23469] Updated weights for policy 1, policy_version 86931 (0.0008) -[2023-10-09 11:45:12,625][23469] Updated weights for policy 1, policy_version 86941 (0.0007) -[2023-10-09 11:45:14,924][23468] Updated weights for policy 0, policy_version 86473 (0.0008) -[2023-10-09 11:45:15,294][23468] Updated weights for policy 0, policy_version 86483 (0.0010) -[2023-10-09 11:45:15,667][23468] Updated weights for policy 0, policy_version 86493 (0.0009) -[2023-10-09 11:45:16,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 177602560. Throughput: 0: 1807.6, 1: 1809.2. Samples: 44411272. Policy #0 lag: (min: 7.0, avg: 7.7, max: 25.0) -[2023-10-09 11:45:16,078][22500] Avg episode reward: [(0, '9.970'), (1, '9.670')] -[2023-10-09 11:45:16,246][23469] Updated weights for policy 1, policy_version 86951 (0.0008) -[2023-10-09 11:45:16,614][23469] Updated weights for policy 1, policy_version 86961 (0.0007) -[2023-10-09 11:45:16,980][23469] Updated weights for policy 1, policy_version 86971 (0.0007) -[2023-10-09 11:45:19,380][23468] Updated weights for policy 0, policy_version 86503 (0.0008) -[2023-10-09 11:45:19,762][23468] Updated weights for policy 0, policy_version 86513 (0.0007) -[2023-10-09 11:45:20,141][23468] Updated weights for policy 0, policy_version 86523 (0.0009) -[2023-10-09 11:45:20,770][23469] Updated weights for policy 1, policy_version 86981 (0.0010) -[2023-10-09 11:45:21,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 177668096. Throughput: 0: 1798.5, 1: 1801.5. Samples: 44421958. Policy #0 lag: (min: 7.0, avg: 7.7, max: 25.0) -[2023-10-09 11:45:21,078][22500] Avg episode reward: [(0, '10.510'), (1, '9.710')] -[2023-10-09 11:45:21,158][23469] Updated weights for policy 1, policy_version 86991 (0.0010) -[2023-10-09 11:45:21,528][23469] Updated weights for policy 1, policy_version 87001 (0.0007) -[2023-10-09 11:45:23,744][23468] Updated weights for policy 0, policy_version 86533 (0.0009) -[2023-10-09 11:45:24,117][23468] Updated weights for policy 0, policy_version 86543 (0.0008) -[2023-10-09 11:45:24,496][23468] Updated weights for policy 0, policy_version 86553 (0.0007) -[2023-10-09 11:45:25,275][23469] Updated weights for policy 1, policy_version 87011 (0.0010) -[2023-10-09 11:45:25,642][23469] Updated weights for policy 1, policy_version 87021 (0.0010) -[2023-10-09 11:45:26,017][23469] Updated weights for policy 1, policy_version 87031 (0.0007) -[2023-10-09 11:45:26,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 177733632. Throughput: 0: 1809.9, 1: 1807.1. Samples: 44443844. Policy #0 lag: (min: 7.0, avg: 7.7, max: 25.0) -[2023-10-09 11:45:26,078][22500] Avg episode reward: [(0, '10.230'), (1, '9.980')] -[2023-10-09 11:45:28,454][23468] Updated weights for policy 0, policy_version 86563 (0.0008) -[2023-10-09 11:45:28,824][23468] Updated weights for policy 0, policy_version 86573 (0.0008) -[2023-10-09 11:45:29,199][23468] Updated weights for policy 0, policy_version 86583 (0.0009) -[2023-10-09 11:45:29,785][23469] Updated weights for policy 1, policy_version 87041 (0.0009) -[2023-10-09 11:45:30,147][23469] Updated weights for policy 1, policy_version 87051 (0.0007) -[2023-10-09 11:45:30,517][23469] Updated weights for policy 1, policy_version 87061 (0.0008) -[2023-10-09 11:45:30,885][23469] Updated weights for policy 1, policy_version 87071 (0.0008) -[2023-10-09 11:45:31,078][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 177831936. Throughput: 0: 1800.3, 1: 1807.1. Samples: 44464238. Policy #0 lag: (min: 7.0, avg: 7.7, max: 25.0) -[2023-10-09 11:45:31,078][22500] Avg episode reward: [(0, '10.160'), (1, '9.170')] -[2023-10-09 11:45:33,017][23468] Updated weights for policy 0, policy_version 86593 (0.0010) -[2023-10-09 11:45:33,386][23468] Updated weights for policy 0, policy_version 86603 (0.0009) -[2023-10-09 11:45:33,755][23468] Updated weights for policy 0, policy_version 86613 (0.0007) -[2023-10-09 11:45:34,134][23468] Updated weights for policy 0, policy_version 86623 (0.0008) -[2023-10-09 11:45:34,626][23469] Updated weights for policy 1, policy_version 87081 (0.0009) -[2023-10-09 11:45:35,001][23469] Updated weights for policy 1, policy_version 87091 (0.0009) -[2023-10-09 11:45:35,379][23469] Updated weights for policy 1, policy_version 87101 (0.0011) -[2023-10-09 11:45:36,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 177897472. Throughput: 0: 1811.8, 1: 1804.0. Samples: 44476280. Policy #0 lag: (min: 7.0, avg: 7.7, max: 25.0) -[2023-10-09 11:45:36,078][22500] Avg episode reward: [(0, '10.790'), (1, '8.720')] -[2023-10-09 11:45:37,713][23468] Updated weights for policy 0, policy_version 86633 (0.0007) -[2023-10-09 11:45:38,084][23468] Updated weights for policy 0, policy_version 86643 (0.0008) -[2023-10-09 11:45:38,459][23468] Updated weights for policy 0, policy_version 86653 (0.0008) -[2023-10-09 11:45:39,016][23469] Updated weights for policy 1, policy_version 87111 (0.0008) -[2023-10-09 11:45:39,382][23469] Updated weights for policy 1, policy_version 87121 (0.0008) -[2023-10-09 11:45:39,755][23469] Updated weights for policy 1, policy_version 87131 (0.0009) -[2023-10-09 11:45:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 177963008. Throughput: 0: 1798.9, 1: 1807.6. Samples: 44496616. Policy #0 lag: (min: 7.0, avg: 7.7, max: 25.0) -[2023-10-09 11:45:41,078][22500] Avg episode reward: [(0, '10.530'), (1, '9.230')] -[2023-10-09 11:45:42,282][23468] Updated weights for policy 0, policy_version 86663 (0.0008) -[2023-10-09 11:45:42,648][23468] Updated weights for policy 0, policy_version 86673 (0.0008) -[2023-10-09 11:45:43,020][23468] Updated weights for policy 0, policy_version 86683 (0.0008) -[2023-10-09 11:45:43,555][23469] Updated weights for policy 1, policy_version 87141 (0.0008) -[2023-10-09 11:45:43,920][23469] Updated weights for policy 1, policy_version 87151 (0.0008) -[2023-10-09 11:45:44,291][23469] Updated weights for policy 1, policy_version 87161 (0.0007) -[2023-10-09 11:45:46,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 178028544. Throughput: 0: 1798.5, 1: 1799.3. Samples: 44518936. Policy #0 lag: (min: 7.0, avg: 7.7, max: 25.0) -[2023-10-09 11:45:46,078][22500] Avg episode reward: [(0, '10.670'), (1, '8.920')] -[2023-10-09 11:45:46,769][23468] Updated weights for policy 0, policy_version 86693 (0.0007) -[2023-10-09 11:45:47,139][23468] Updated weights for policy 0, policy_version 86703 (0.0008) -[2023-10-09 11:45:47,507][23468] Updated weights for policy 0, policy_version 86713 (0.0009) -[2023-10-09 11:45:47,959][23469] Updated weights for policy 1, policy_version 87171 (0.0009) -[2023-10-09 11:45:48,324][23469] Updated weights for policy 1, policy_version 87181 (0.0009) -[2023-10-09 11:45:48,698][23469] Updated weights for policy 1, policy_version 87191 (0.0007) -[2023-10-09 11:45:51,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 178094080. Throughput: 0: 1797.6, 1: 1811.1. Samples: 44529160. Policy #0 lag: (min: 7.0, avg: 7.7, max: 25.0) -[2023-10-09 11:45:51,078][22500] Avg episode reward: [(0, '11.060'), (1, '9.230')] -[2023-10-09 11:45:51,220][23468] Updated weights for policy 0, policy_version 86723 (0.0009) -[2023-10-09 11:45:51,586][23468] Updated weights for policy 0, policy_version 86733 (0.0009) -[2023-10-09 11:45:51,961][23468] Updated weights for policy 0, policy_version 86743 (0.0008) -[2023-10-09 11:45:52,361][23469] Updated weights for policy 1, policy_version 87201 (0.0007) -[2023-10-09 11:45:52,738][23469] Updated weights for policy 1, policy_version 87211 (0.0007) -[2023-10-09 11:45:53,112][23469] Updated weights for policy 1, policy_version 87221 (0.0008) -[2023-10-09 11:45:53,481][23469] Updated weights for policy 1, policy_version 87231 (0.0007) -[2023-10-09 11:45:55,592][23468] Updated weights for policy 0, policy_version 86753 (0.0007) -[2023-10-09 11:45:55,969][23468] Updated weights for policy 0, policy_version 86763 (0.0008) -[2023-10-09 11:45:56,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 178159616. Throughput: 0: 1796.8, 1: 1805.5. Samples: 44551522. Policy #0 lag: (min: 7.0, avg: 7.7, max: 25.0) -[2023-10-09 11:45:56,078][22500] Avg episode reward: [(0, '11.040'), (1, '9.090')] -[2023-10-09 11:45:56,343][23468] Updated weights for policy 0, policy_version 86773 (0.0009) -[2023-10-09 11:45:56,721][23468] Updated weights for policy 0, policy_version 86783 (0.0007) -[2023-10-09 11:45:57,074][23469] Updated weights for policy 1, policy_version 87241 (0.0008) -[2023-10-09 11:45:57,440][23469] Updated weights for policy 1, policy_version 87251 (0.0008) -[2023-10-09 11:45:57,823][23469] Updated weights for policy 1, policy_version 87261 (0.0008) -[2023-10-09 11:46:00,656][23468] Updated weights for policy 0, policy_version 86793 (0.0010) -[2023-10-09 11:46:01,028][23468] Updated weights for policy 0, policy_version 86803 (0.0009) -[2023-10-09 11:46:01,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 178225152. Throughput: 0: 1814.6, 1: 1804.1. Samples: 44574114. Policy #0 lag: (min: 7.0, avg: 7.7, max: 25.0) -[2023-10-09 11:46:01,078][22500] Avg episode reward: [(0, '10.140'), (1, '9.160')] -[2023-10-09 11:46:01,406][23468] Updated weights for policy 0, policy_version 86813 (0.0008) -[2023-10-09 11:46:01,464][23469] Updated weights for policy 1, policy_version 87271 (0.0008) -[2023-10-09 11:46:01,829][23469] Updated weights for policy 1, policy_version 87281 (0.0011) -[2023-10-09 11:46:02,198][23469] Updated weights for policy 1, policy_version 87291 (0.0010) -[2023-10-09 11:46:05,051][23468] Updated weights for policy 0, policy_version 86823 (0.0008) -[2023-10-09 11:46:05,429][23468] Updated weights for policy 0, policy_version 86833 (0.0009) -[2023-10-09 11:46:05,805][23468] Updated weights for policy 0, policy_version 86843 (0.0007) -[2023-10-09 11:46:05,857][23469] Updated weights for policy 1, policy_version 87301 (0.0010) -[2023-10-09 11:46:06,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 178323456. Throughput: 0: 1795.3, 1: 1805.6. Samples: 44584002. Policy #0 lag: (min: 7.0, avg: 7.7, max: 25.0) -[2023-10-09 11:46:06,078][22500] Avg episode reward: [(0, '10.470'), (1, '9.490')] -[2023-10-09 11:46:06,221][23469] Updated weights for policy 1, policy_version 87311 (0.0007) -[2023-10-09 11:46:06,593][23469] Updated weights for policy 1, policy_version 87321 (0.0007) -[2023-10-09 11:46:09,616][23468] Updated weights for policy 0, policy_version 86853 (0.0009) -[2023-10-09 11:46:09,997][23468] Updated weights for policy 0, policy_version 86863 (0.0008) -[2023-10-09 11:46:10,282][23469] Updated weights for policy 1, policy_version 87331 (0.0007) -[2023-10-09 11:46:10,362][23468] Updated weights for policy 0, policy_version 86873 (0.0009) -[2023-10-09 11:46:10,648][23469] Updated weights for policy 1, policy_version 87341 (0.0008) -[2023-10-09 11:46:11,009][23469] Updated weights for policy 1, policy_version 87351 (0.0009) -[2023-10-09 11:46:11,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 178388992. Throughput: 0: 1807.9, 1: 1808.4. Samples: 44606576. Policy #0 lag: (min: 30.0, avg: 33.0, max: 62.0) -[2023-10-09 11:46:11,078][22500] Avg episode reward: [(0, '10.010'), (1, '8.910')] -[2023-10-09 11:46:14,123][23468] Updated weights for policy 0, policy_version 86883 (0.0009) -[2023-10-09 11:46:14,509][23468] Updated weights for policy 0, policy_version 86893 (0.0007) -[2023-10-09 11:46:14,884][23468] Updated weights for policy 0, policy_version 86903 (0.0007) -[2023-10-09 11:46:14,900][23469] Updated weights for policy 1, policy_version 87361 (0.0010) -[2023-10-09 11:46:15,262][23469] Updated weights for policy 1, policy_version 87371 (0.0009) -[2023-10-09 11:46:15,642][23469] Updated weights for policy 1, policy_version 87381 (0.0011) -[2023-10-09 11:46:15,999][23469] Updated weights for policy 1, policy_version 87391 (0.0009) -[2023-10-09 11:46:16,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 178487296. Throughput: 0: 1789.8, 1: 1812.4. Samples: 44626340. Policy #0 lag: (min: 30.0, avg: 33.0, max: 62.0) -[2023-10-09 11:46:16,078][22500] Avg episode reward: [(0, '9.730'), (1, '8.730')] -[2023-10-09 11:46:16,088][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000087392_89489408.pth... -[2023-10-09 11:46:16,089][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000086912_88997888.pth... -[2023-10-09 11:46:16,126][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000085248_87293952.pth -[2023-10-09 11:46:16,130][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000085696_87752704.pth -[2023-10-09 11:46:18,542][23468] Updated weights for policy 0, policy_version 86913 (0.0008) -[2023-10-09 11:46:18,912][23468] Updated weights for policy 0, policy_version 86923 (0.0008) -[2023-10-09 11:46:19,271][23468] Updated weights for policy 0, policy_version 86933 (0.0008) -[2023-10-09 11:46:19,643][23468] Updated weights for policy 0, policy_version 86943 (0.0008) -[2023-10-09 11:46:19,724][23469] Updated weights for policy 1, policy_version 87401 (0.0008) -[2023-10-09 11:46:20,096][23469] Updated weights for policy 1, policy_version 87411 (0.0010) -[2023-10-09 11:46:20,463][23469] Updated weights for policy 1, policy_version 87421 (0.0010) -[2023-10-09 11:46:21,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 178552832. Throughput: 0: 1801.5, 1: 1811.6. Samples: 44638872. Policy #0 lag: (min: 30.0, avg: 33.0, max: 62.0) -[2023-10-09 11:46:21,078][22500] Avg episode reward: [(0, '10.670'), (1, '8.880')] -[2023-10-09 11:46:23,296][23468] Updated weights for policy 0, policy_version 86953 (0.0009) -[2023-10-09 11:46:23,679][23468] Updated weights for policy 0, policy_version 86963 (0.0009) -[2023-10-09 11:46:24,043][23468] Updated weights for policy 0, policy_version 86973 (0.0009) -[2023-10-09 11:46:24,246][23469] Updated weights for policy 1, policy_version 87431 (0.0007) -[2023-10-09 11:46:24,619][23469] Updated weights for policy 1, policy_version 87441 (0.0010) -[2023-10-09 11:46:24,986][23469] Updated weights for policy 1, policy_version 87451 (0.0008) -[2023-10-09 11:46:26,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 178618368. Throughput: 0: 1791.3, 1: 1814.4. Samples: 44658874. Policy #0 lag: (min: 30.0, avg: 33.0, max: 62.0) -[2023-10-09 11:46:26,078][22500] Avg episode reward: [(0, '10.240'), (1, '9.210')] -[2023-10-09 11:46:27,762][23468] Updated weights for policy 0, policy_version 86983 (0.0007) -[2023-10-09 11:46:28,136][23468] Updated weights for policy 0, policy_version 86993 (0.0008) -[2023-10-09 11:46:28,505][23468] Updated weights for policy 0, policy_version 87003 (0.0008) -[2023-10-09 11:46:28,719][23469] Updated weights for policy 1, policy_version 87461 (0.0007) -[2023-10-09 11:46:29,090][23469] Updated weights for policy 1, policy_version 87471 (0.0010) -[2023-10-09 11:46:29,466][23469] Updated weights for policy 1, policy_version 87481 (0.0007) -[2023-10-09 11:46:31,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 178683904. Throughput: 0: 1791.9, 1: 1809.2. Samples: 44680988. Policy #0 lag: (min: 30.0, avg: 33.0, max: 62.0) -[2023-10-09 11:46:31,078][22500] Avg episode reward: [(0, '9.970'), (1, '9.510')] -[2023-10-09 11:46:32,367][23468] Updated weights for policy 0, policy_version 87013 (0.0008) -[2023-10-09 11:46:32,727][23468] Updated weights for policy 0, policy_version 87023 (0.0007) -[2023-10-09 11:46:33,107][23468] Updated weights for policy 0, policy_version 87033 (0.0008) -[2023-10-09 11:46:33,176][23469] Updated weights for policy 1, policy_version 87491 (0.0008) -[2023-10-09 11:46:33,547][23469] Updated weights for policy 1, policy_version 87501 (0.0007) -[2023-10-09 11:46:33,910][23469] Updated weights for policy 1, policy_version 87511 (0.0009) -[2023-10-09 11:46:36,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 178749440. Throughput: 0: 1792.1, 1: 1813.7. Samples: 44691422. Policy #0 lag: (min: 30.0, avg: 33.0, max: 62.0) -[2023-10-09 11:46:36,078][22500] Avg episode reward: [(0, '10.470'), (1, '9.610')] -[2023-10-09 11:46:36,816][23468] Updated weights for policy 0, policy_version 87043 (0.0008) -[2023-10-09 11:46:37,183][23468] Updated weights for policy 0, policy_version 87053 (0.0007) -[2023-10-09 11:46:37,553][23468] Updated weights for policy 0, policy_version 87063 (0.0008) -[2023-10-09 11:46:37,641][23469] Updated weights for policy 1, policy_version 87521 (0.0007) -[2023-10-09 11:46:38,009][23469] Updated weights for policy 1, policy_version 87531 (0.0008) -[2023-10-09 11:46:38,385][23469] Updated weights for policy 1, policy_version 87541 (0.0009) -[2023-10-09 11:46:38,755][23469] Updated weights for policy 1, policy_version 87551 (0.0009) -[2023-10-09 11:46:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 178814976. Throughput: 0: 1788.1, 1: 1806.0. Samples: 44713256. Policy #0 lag: (min: 30.0, avg: 33.0, max: 62.0) -[2023-10-09 11:46:41,078][22500] Avg episode reward: [(0, '9.340'), (1, '9.270')] -[2023-10-09 11:46:41,355][23468] Updated weights for policy 0, policy_version 87073 (0.0009) -[2023-10-09 11:46:41,726][23468] Updated weights for policy 0, policy_version 87083 (0.0009) -[2023-10-09 11:46:42,108][23468] Updated weights for policy 0, policy_version 87093 (0.0008) -[2023-10-09 11:46:42,475][23468] Updated weights for policy 0, policy_version 87103 (0.0010) -[2023-10-09 11:46:42,627][23469] Updated weights for policy 1, policy_version 87561 (0.0008) -[2023-10-09 11:46:43,003][23469] Updated weights for policy 1, policy_version 87571 (0.0008) -[2023-10-09 11:46:43,367][23469] Updated weights for policy 1, policy_version 87581 (0.0008) -[2023-10-09 11:46:46,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 178880512. Throughput: 0: 1790.6, 1: 1802.1. Samples: 44735786. Policy #0 lag: (min: 30.0, avg: 33.0, max: 62.0) -[2023-10-09 11:46:46,079][22500] Avg episode reward: [(0, '10.310'), (1, '9.570')] -[2023-10-09 11:46:46,166][23468] Updated weights for policy 0, policy_version 87113 (0.0007) -[2023-10-09 11:46:46,548][23468] Updated weights for policy 0, policy_version 87123 (0.0007) -[2023-10-09 11:46:46,918][23468] Updated weights for policy 0, policy_version 87133 (0.0007) -[2023-10-09 11:46:47,001][23469] Updated weights for policy 1, policy_version 87591 (0.0008) -[2023-10-09 11:46:47,378][23469] Updated weights for policy 1, policy_version 87601 (0.0013) -[2023-10-09 11:46:47,741][23469] Updated weights for policy 1, policy_version 87611 (0.0008) -[2023-10-09 11:46:50,545][23468] Updated weights for policy 0, policy_version 87143 (0.0007) -[2023-10-09 11:46:50,918][23468] Updated weights for policy 0, policy_version 87153 (0.0009) -[2023-10-09 11:46:51,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 178946048. Throughput: 0: 1787.5, 1: 1806.0. Samples: 44745712. Policy #0 lag: (min: 30.0, avg: 33.0, max: 62.0) -[2023-10-09 11:46:51,078][22500] Avg episode reward: [(0, '10.890'), (1, '9.000')] -[2023-10-09 11:46:51,299][23468] Updated weights for policy 0, policy_version 87163 (0.0007) -[2023-10-09 11:46:51,530][23469] Updated weights for policy 1, policy_version 87621 (0.0009) -[2023-10-09 11:46:51,906][23469] Updated weights for policy 1, policy_version 87631 (0.0009) -[2023-10-09 11:46:52,266][23469] Updated weights for policy 1, policy_version 87641 (0.0011) -[2023-10-09 11:46:55,066][23468] Updated weights for policy 0, policy_version 87173 (0.0008) -[2023-10-09 11:46:55,428][23468] Updated weights for policy 0, policy_version 87183 (0.0008) -[2023-10-09 11:46:55,804][23468] Updated weights for policy 0, policy_version 87193 (0.0009) -[2023-10-09 11:46:55,991][23469] Updated weights for policy 1, policy_version 87651 (0.0009) -[2023-10-09 11:46:56,077][22500] Fps is (10 sec: 16384.6, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 179044352. Throughput: 0: 1793.0, 1: 1792.6. Samples: 44767928. Policy #0 lag: (min: 30.0, avg: 33.0, max: 62.0) -[2023-10-09 11:46:56,078][22500] Avg episode reward: [(0, '10.690'), (1, '9.480')] -[2023-10-09 11:46:56,361][23469] Updated weights for policy 1, policy_version 87661 (0.0008) -[2023-10-09 11:46:56,731][23469] Updated weights for policy 1, policy_version 87671 (0.0010) -[2023-10-09 11:46:59,529][23468] Updated weights for policy 0, policy_version 87203 (0.0008) -[2023-10-09 11:46:59,920][23468] Updated weights for policy 0, policy_version 87213 (0.0011) -[2023-10-09 11:47:00,294][23468] Updated weights for policy 0, policy_version 87223 (0.0010) -[2023-10-09 11:47:00,537][23469] Updated weights for policy 1, policy_version 87681 (0.0011) -[2023-10-09 11:47:00,909][23469] Updated weights for policy 1, policy_version 87691 (0.0009) -[2023-10-09 11:47:01,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 179109888. Throughput: 0: 1805.5, 1: 1809.7. Samples: 44789024. Policy #0 lag: (min: 30.0, avg: 33.0, max: 62.0) -[2023-10-09 11:47:01,079][22500] Avg episode reward: [(0, '11.570'), (1, '9.190')] -[2023-10-09 11:47:01,280][23469] Updated weights for policy 1, policy_version 87701 (0.0009) -[2023-10-09 11:47:01,648][23469] Updated weights for policy 1, policy_version 87711 (0.0007) -[2023-10-09 11:47:03,965][23468] Updated weights for policy 0, policy_version 87233 (0.0009) -[2023-10-09 11:47:04,327][23468] Updated weights for policy 0, policy_version 87243 (0.0008) -[2023-10-09 11:47:04,706][23468] Updated weights for policy 0, policy_version 87253 (0.0008) -[2023-10-09 11:47:05,072][23468] Updated weights for policy 0, policy_version 87263 (0.0008) -[2023-10-09 11:47:05,272][23469] Updated weights for policy 1, policy_version 87721 (0.0008) -[2023-10-09 11:47:05,637][23469] Updated weights for policy 1, policy_version 87731 (0.0010) -[2023-10-09 11:47:06,004][23469] Updated weights for policy 1, policy_version 87741 (0.0011) -[2023-10-09 11:47:06,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 179175424. Throughput: 0: 1794.3, 1: 1791.6. Samples: 44800238. Policy #0 lag: (min: 11.0, avg: 19.0, max: 43.0) -[2023-10-09 11:47:06,078][22500] Avg episode reward: [(0, '10.870'), (1, '9.690')] -[2023-10-09 11:47:08,930][23468] Updated weights for policy 0, policy_version 87273 (0.0008) -[2023-10-09 11:47:09,303][23468] Updated weights for policy 0, policy_version 87283 (0.0009) -[2023-10-09 11:47:09,639][23469] Updated weights for policy 1, policy_version 87751 (0.0009) -[2023-10-09 11:47:09,682][23468] Updated weights for policy 0, policy_version 87293 (0.0009) -[2023-10-09 11:47:10,012][23469] Updated weights for policy 1, policy_version 87761 (0.0009) -[2023-10-09 11:47:10,375][23469] Updated weights for policy 1, policy_version 87771 (0.0008) -[2023-10-09 11:47:11,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14440.2). Total num frames: 179273728. Throughput: 0: 1803.3, 1: 1810.3. Samples: 44821484. Policy #0 lag: (min: 11.0, avg: 19.0, max: 43.0) -[2023-10-09 11:47:11,078][22500] Avg episode reward: [(0, '10.760'), (1, '9.880')] -[2023-10-09 11:47:13,470][23468] Updated weights for policy 0, policy_version 87303 (0.0009) -[2023-10-09 11:47:13,851][23468] Updated weights for policy 0, policy_version 87313 (0.0010) -[2023-10-09 11:47:14,201][23469] Updated weights for policy 1, policy_version 87781 (0.0007) -[2023-10-09 11:47:14,211][23468] Updated weights for policy 0, policy_version 87323 (0.0008) -[2023-10-09 11:47:14,571][23469] Updated weights for policy 1, policy_version 87791 (0.0009) -[2023-10-09 11:47:14,940][23469] Updated weights for policy 1, policy_version 87801 (0.0008) -[2023-10-09 11:47:16,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 179339264. Throughput: 0: 1784.5, 1: 1797.4. Samples: 44842174. Policy #0 lag: (min: 11.0, avg: 19.0, max: 43.0) -[2023-10-09 11:47:16,078][22500] Avg episode reward: [(0, '11.270'), (1, '9.820')] -[2023-10-09 11:47:18,033][23468] Updated weights for policy 0, policy_version 87333 (0.0009) -[2023-10-09 11:47:18,406][23468] Updated weights for policy 0, policy_version 87343 (0.0009) -[2023-10-09 11:47:18,678][23469] Updated weights for policy 1, policy_version 87811 (0.0008) -[2023-10-09 11:47:18,773][23468] Updated weights for policy 0, policy_version 87353 (0.0008) -[2023-10-09 11:47:19,042][23469] Updated weights for policy 1, policy_version 87821 (0.0008) -[2023-10-09 11:47:19,414][23469] Updated weights for policy 1, policy_version 87831 (0.0008) -[2023-10-09 11:47:21,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 179404800. Throughput: 0: 1805.2, 1: 1813.4. Samples: 44854260. Policy #0 lag: (min: 11.0, avg: 19.0, max: 43.0) -[2023-10-09 11:47:21,079][22500] Avg episode reward: [(0, '11.160'), (1, '9.790')] -[2023-10-09 11:47:22,695][23468] Updated weights for policy 0, policy_version 87363 (0.0009) -[2023-10-09 11:47:23,063][23468] Updated weights for policy 0, policy_version 87373 (0.0009) -[2023-10-09 11:47:23,106][23469] Updated weights for policy 1, policy_version 87841 (0.0009) -[2023-10-09 11:47:23,447][23468] Updated weights for policy 0, policy_version 87383 (0.0009) -[2023-10-09 11:47:23,469][23469] Updated weights for policy 1, policy_version 87851 (0.0009) -[2023-10-09 11:47:23,834][23469] Updated weights for policy 1, policy_version 87861 (0.0009) -[2023-10-09 11:47:24,218][23469] Updated weights for policy 1, policy_version 87871 (0.0011) -[2023-10-09 11:47:26,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 179470336. Throughput: 0: 1780.8, 1: 1800.9. Samples: 44874430. Policy #0 lag: (min: 11.0, avg: 19.0, max: 43.0) -[2023-10-09 11:47:26,078][22500] Avg episode reward: [(0, '10.710'), (1, '9.810')] -[2023-10-09 11:47:27,256][23468] Updated weights for policy 0, policy_version 87393 (0.0009) -[2023-10-09 11:47:27,630][23468] Updated weights for policy 0, policy_version 87403 (0.0008) -[2023-10-09 11:47:27,789][23469] Updated weights for policy 1, policy_version 87881 (0.0007) -[2023-10-09 11:47:28,004][23468] Updated weights for policy 0, policy_version 87413 (0.0007) -[2023-10-09 11:47:28,149][23469] Updated weights for policy 1, policy_version 87891 (0.0009) -[2023-10-09 11:47:28,369][23468] Updated weights for policy 0, policy_version 87423 (0.0007) -[2023-10-09 11:47:28,522][23469] Updated weights for policy 1, policy_version 87901 (0.0007) -[2023-10-09 11:47:31,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 179535872. Throughput: 0: 1775.5, 1: 1803.8. Samples: 44896852. Policy #0 lag: (min: 11.0, avg: 19.0, max: 43.0) -[2023-10-09 11:47:31,078][22500] Avg episode reward: [(0, '10.570'), (1, '9.500')] -[2023-10-09 11:47:32,165][23468] Updated weights for policy 0, policy_version 87433 (0.0009) -[2023-10-09 11:47:32,373][23469] Updated weights for policy 1, policy_version 87911 (0.0008) -[2023-10-09 11:47:32,524][23468] Updated weights for policy 0, policy_version 87443 (0.0007) -[2023-10-09 11:47:32,744][23469] Updated weights for policy 1, policy_version 87921 (0.0008) -[2023-10-09 11:47:32,892][23468] Updated weights for policy 0, policy_version 87453 (0.0007) -[2023-10-09 11:47:33,105][23469] Updated weights for policy 1, policy_version 87931 (0.0008) -[2023-10-09 11:47:36,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 179601408. Throughput: 0: 1775.9, 1: 1798.3. Samples: 44906550. Policy #0 lag: (min: 11.0, avg: 19.0, max: 43.0) -[2023-10-09 11:47:36,078][22500] Avg episode reward: [(0, '10.690'), (1, '8.960')] -[2023-10-09 11:47:36,686][23468] Updated weights for policy 0, policy_version 87463 (0.0008) -[2023-10-09 11:47:36,957][23469] Updated weights for policy 1, policy_version 87941 (0.0009) -[2023-10-09 11:47:37,048][23468] Updated weights for policy 0, policy_version 87473 (0.0007) -[2023-10-09 11:47:37,321][23469] Updated weights for policy 1, policy_version 87951 (0.0008) -[2023-10-09 11:47:37,423][23468] Updated weights for policy 0, policy_version 87483 (0.0007) -[2023-10-09 11:47:37,689][23469] Updated weights for policy 1, policy_version 87961 (0.0007) -[2023-10-09 11:47:41,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 179666944. Throughput: 0: 1772.7, 1: 1803.1. Samples: 44928840. Policy #0 lag: (min: 11.0, avg: 19.0, max: 43.0) -[2023-10-09 11:47:41,078][22500] Avg episode reward: [(0, '10.710'), (1, '9.150')] -[2023-10-09 11:47:41,143][23468] Updated weights for policy 0, policy_version 87493 (0.0010) -[2023-10-09 11:47:41,389][23469] Updated weights for policy 1, policy_version 87971 (0.0007) -[2023-10-09 11:47:41,517][23468] Updated weights for policy 0, policy_version 87503 (0.0009) -[2023-10-09 11:47:41,759][23469] Updated weights for policy 1, policy_version 87981 (0.0008) -[2023-10-09 11:47:41,894][23468] Updated weights for policy 0, policy_version 87513 (0.0008) -[2023-10-09 11:47:42,128][23469] Updated weights for policy 1, policy_version 87991 (0.0008) -[2023-10-09 11:47:45,696][23468] Updated weights for policy 0, policy_version 87523 (0.0008) -[2023-10-09 11:47:45,921][23469] Updated weights for policy 1, policy_version 88001 (0.0010) -[2023-10-09 11:47:46,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 179732480. Throughput: 0: 1796.6, 1: 1812.5. Samples: 44951434. Policy #0 lag: (min: 11.0, avg: 19.0, max: 43.0) -[2023-10-09 11:47:46,078][22500] Avg episode reward: [(0, '11.140'), (1, '9.570')] -[2023-10-09 11:47:46,088][23468] Updated weights for policy 0, policy_version 87533 (0.0009) -[2023-10-09 11:47:46,284][23469] Updated weights for policy 1, policy_version 88011 (0.0007) -[2023-10-09 11:47:46,456][23468] Updated weights for policy 0, policy_version 87543 (0.0009) -[2023-10-09 11:47:46,663][23469] Updated weights for policy 1, policy_version 88021 (0.0007) -[2023-10-09 11:47:47,043][23469] Updated weights for policy 1, policy_version 88031 (0.0008) -[2023-10-09 11:47:50,117][23468] Updated weights for policy 0, policy_version 87553 (0.0009) -[2023-10-09 11:47:50,486][23468] Updated weights for policy 0, policy_version 87563 (0.0009) -[2023-10-09 11:47:50,822][23469] Updated weights for policy 1, policy_version 88041 (0.0010) -[2023-10-09 11:47:50,865][23468] Updated weights for policy 0, policy_version 87573 (0.0008) -[2023-10-09 11:47:51,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 179798016. Throughput: 0: 1766.4, 1: 1802.4. Samples: 44960830. Policy #0 lag: (min: 11.0, avg: 19.0, max: 43.0) -[2023-10-09 11:47:51,078][22500] Avg episode reward: [(0, '10.610'), (1, '9.750')] -[2023-10-09 11:47:51,190][23469] Updated weights for policy 1, policy_version 88051 (0.0009) -[2023-10-09 11:47:51,229][23468] Updated weights for policy 0, policy_version 87583 (0.0008) -[2023-10-09 11:47:51,554][23469] Updated weights for policy 1, policy_version 88061 (0.0009) -[2023-10-09 11:47:54,925][23468] Updated weights for policy 0, policy_version 87593 (0.0008) -[2023-10-09 11:47:55,298][23468] Updated weights for policy 0, policy_version 87603 (0.0007) -[2023-10-09 11:47:55,313][23469] Updated weights for policy 1, policy_version 88071 (0.0010) -[2023-10-09 11:47:55,672][23468] Updated weights for policy 0, policy_version 87613 (0.0008) -[2023-10-09 11:47:55,684][23469] Updated weights for policy 1, policy_version 88081 (0.0010) -[2023-10-09 11:47:56,054][23469] Updated weights for policy 1, policy_version 88091 (0.0010) -[2023-10-09 11:47:56,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 179896320. Throughput: 0: 1789.4, 1: 1808.4. Samples: 44983382. Policy #0 lag: (min: 11.0, avg: 19.0, max: 43.0) -[2023-10-09 11:47:56,078][22500] Avg episode reward: [(0, '9.960'), (1, '9.940')] -[2023-10-09 11:47:59,549][23468] Updated weights for policy 0, policy_version 87623 (0.0008) -[2023-10-09 11:47:59,733][23469] Updated weights for policy 1, policy_version 88101 (0.0008) -[2023-10-09 11:47:59,925][23468] Updated weights for policy 0, policy_version 87633 (0.0008) -[2023-10-09 11:48:00,106][23469] Updated weights for policy 1, policy_version 88111 (0.0008) -[2023-10-09 11:48:00,282][23468] Updated weights for policy 0, policy_version 87643 (0.0007) -[2023-10-09 11:48:00,473][23469] Updated weights for policy 1, policy_version 88121 (0.0008) -[2023-10-09 11:48:01,077][22500] Fps is (10 sec: 19660.8, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 179994624. Throughput: 0: 1774.3, 1: 1797.5. Samples: 45002904. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:48:01,078][22500] Avg episode reward: [(0, '9.340'), (1, '9.770')] -[2023-10-09 11:48:04,107][23469] Updated weights for policy 1, policy_version 88131 (0.0008) -[2023-10-09 11:48:04,115][23468] Updated weights for policy 0, policy_version 87653 (0.0009) -[2023-10-09 11:48:04,475][23469] Updated weights for policy 1, policy_version 88141 (0.0007) -[2023-10-09 11:48:04,493][23468] Updated weights for policy 0, policy_version 87663 (0.0007) -[2023-10-09 11:48:04,841][23469] Updated weights for policy 1, policy_version 88151 (0.0008) -[2023-10-09 11:48:04,875][23468] Updated weights for policy 0, policy_version 87673 (0.0007) -[2023-10-09 11:48:06,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 180060160. Throughput: 0: 1775.3, 1: 1799.5. Samples: 45015126. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:48:06,078][22500] Avg episode reward: [(0, '10.280'), (1, '9.740')] -[2023-10-09 11:48:08,613][23469] Updated weights for policy 1, policy_version 88161 (0.0008) -[2023-10-09 11:48:08,680][23468] Updated weights for policy 0, policy_version 87683 (0.0009) -[2023-10-09 11:48:08,977][23469] Updated weights for policy 1, policy_version 88171 (0.0007) -[2023-10-09 11:48:09,054][23468] Updated weights for policy 0, policy_version 87693 (0.0009) -[2023-10-09 11:48:09,360][23469] Updated weights for policy 1, policy_version 88181 (0.0009) -[2023-10-09 11:48:09,426][23468] Updated weights for policy 0, policy_version 87703 (0.0009) -[2023-10-09 11:48:09,726][23469] Updated weights for policy 1, policy_version 88191 (0.0009) -[2023-10-09 11:48:11,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.2). Total num frames: 180125696. Throughput: 0: 1781.3, 1: 1794.0. Samples: 45035320. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:48:11,078][22500] Avg episode reward: [(0, '10.740'), (1, '10.390')] -[2023-10-09 11:48:13,292][23468] Updated weights for policy 0, policy_version 87713 (0.0008) -[2023-10-09 11:48:13,650][23469] Updated weights for policy 1, policy_version 88201 (0.0008) -[2023-10-09 11:48:13,666][23468] Updated weights for policy 0, policy_version 87723 (0.0009) -[2023-10-09 11:48:14,022][23469] Updated weights for policy 1, policy_version 88211 (0.0008) -[2023-10-09 11:48:14,031][23468] Updated weights for policy 0, policy_version 87733 (0.0009) -[2023-10-09 11:48:14,395][23469] Updated weights for policy 1, policy_version 88221 (0.0008) -[2023-10-09 11:48:14,403][23468] Updated weights for policy 0, policy_version 87743 (0.0009) -[2023-10-09 11:48:16,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 180191232. Throughput: 0: 1768.1, 1: 1783.9. Samples: 45056692. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:48:16,079][22500] Avg episode reward: [(0, '10.720'), (1, '9.850')] -[2023-10-09 11:48:16,091][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000088224_90341376.pth... -[2023-10-09 11:48:16,091][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000087744_89849856.pth... -[2023-10-09 11:48:16,126][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000086080_88145920.pth -[2023-10-09 11:48:16,131][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000086528_88604672.pth -[2023-10-09 11:48:18,105][23468] Updated weights for policy 0, policy_version 87753 (0.0008) -[2023-10-09 11:48:18,276][23469] Updated weights for policy 1, policy_version 88231 (0.0008) -[2023-10-09 11:48:18,479][23468] Updated weights for policy 0, policy_version 87763 (0.0008) -[2023-10-09 11:48:18,644][23469] Updated weights for policy 1, policy_version 88241 (0.0007) -[2023-10-09 11:48:18,849][23468] Updated weights for policy 0, policy_version 87773 (0.0008) -[2023-10-09 11:48:19,017][23469] Updated weights for policy 1, policy_version 88251 (0.0007) -[2023-10-09 11:48:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 180256768. Throughput: 0: 1786.2, 1: 1797.2. Samples: 45067804. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:48:21,078][22500] Avg episode reward: [(0, '10.670'), (1, '9.980')] -[2023-10-09 11:48:22,514][23468] Updated weights for policy 0, policy_version 87783 (0.0008) -[2023-10-09 11:48:22,683][23469] Updated weights for policy 1, policy_version 88261 (0.0008) -[2023-10-09 11:48:22,886][23468] Updated weights for policy 0, policy_version 87793 (0.0007) -[2023-10-09 11:48:23,048][23469] Updated weights for policy 1, policy_version 88271 (0.0009) -[2023-10-09 11:48:23,254][23468] Updated weights for policy 0, policy_version 87803 (0.0008) -[2023-10-09 11:48:23,409][23469] Updated weights for policy 1, policy_version 88281 (0.0008) -[2023-10-09 11:48:26,077][22500] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 180322304. Throughput: 0: 1767.7, 1: 1788.8. Samples: 45088880. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:48:26,078][22500] Avg episode reward: [(0, '11.100'), (1, '9.000')] -[2023-10-09 11:48:27,194][23468] Updated weights for policy 0, policy_version 87813 (0.0007) -[2023-10-09 11:48:27,229][23469] Updated weights for policy 1, policy_version 88291 (0.0010) -[2023-10-09 11:48:27,559][23468] Updated weights for policy 0, policy_version 87823 (0.0009) -[2023-10-09 11:48:27,627][23469] Updated weights for policy 1, policy_version 88301 (0.0008) -[2023-10-09 11:48:27,939][23468] Updated weights for policy 0, policy_version 87833 (0.0008) -[2023-10-09 11:48:27,993][23469] Updated weights for policy 1, policy_version 88311 (0.0007) -[2023-10-09 11:48:31,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 180387840. Throughput: 0: 1765.1, 1: 1780.7. Samples: 45110996. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:48:31,078][22500] Avg episode reward: [(0, '11.120'), (1, '9.810')] -[2023-10-09 11:48:31,737][23469] Updated weights for policy 1, policy_version 88321 (0.0008) -[2023-10-09 11:48:31,744][23468] Updated weights for policy 0, policy_version 87843 (0.0008) -[2023-10-09 11:48:32,098][23469] Updated weights for policy 1, policy_version 88331 (0.0008) -[2023-10-09 11:48:32,136][23468] Updated weights for policy 0, policy_version 87853 (0.0007) -[2023-10-09 11:48:32,470][23469] Updated weights for policy 1, policy_version 88341 (0.0008) -[2023-10-09 11:48:32,511][23468] Updated weights for policy 0, policy_version 87863 (0.0009) -[2023-10-09 11:48:32,845][23469] Updated weights for policy 1, policy_version 88351 (0.0008) -[2023-10-09 11:48:36,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 180453376. Throughput: 0: 1767.5, 1: 1779.7. Samples: 45120458. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:48:36,078][22500] Avg episode reward: [(0, '11.020'), (1, '9.520')] -[2023-10-09 11:48:36,380][23468] Updated weights for policy 0, policy_version 87873 (0.0008) -[2023-10-09 11:48:36,688][23469] Updated weights for policy 1, policy_version 88361 (0.0007) -[2023-10-09 11:48:36,747][23468] Updated weights for policy 0, policy_version 87883 (0.0009) -[2023-10-09 11:48:37,058][23469] Updated weights for policy 1, policy_version 88371 (0.0007) -[2023-10-09 11:48:37,112][23468] Updated weights for policy 0, policy_version 87893 (0.0007) -[2023-10-09 11:48:37,425][23469] Updated weights for policy 1, policy_version 88381 (0.0007) -[2023-10-09 11:48:37,483][23468] Updated weights for policy 0, policy_version 87903 (0.0007) -[2023-10-09 11:48:41,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 180518912. Throughput: 0: 1761.2, 1: 1776.1. Samples: 45142564. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:48:41,078][22500] Avg episode reward: [(0, '11.020'), (1, '9.360')] -[2023-10-09 11:48:41,176][23469] Updated weights for policy 1, policy_version 88391 (0.0008) -[2023-10-09 11:48:41,423][23468] Updated weights for policy 0, policy_version 87913 (0.0007) -[2023-10-09 11:48:41,537][23469] Updated weights for policy 1, policy_version 88401 (0.0007) -[2023-10-09 11:48:41,782][23468] Updated weights for policy 0, policy_version 87923 (0.0007) -[2023-10-09 11:48:41,904][23469] Updated weights for policy 1, policy_version 88411 (0.0010) -[2023-10-09 11:48:42,151][23468] Updated weights for policy 0, policy_version 87933 (0.0009) -[2023-10-09 11:48:45,703][23469] Updated weights for policy 1, policy_version 88421 (0.0008) -[2023-10-09 11:48:45,968][23468] Updated weights for policy 0, policy_version 87943 (0.0008) -[2023-10-09 11:48:46,070][23469] Updated weights for policy 1, policy_version 88431 (0.0007) -[2023-10-09 11:48:46,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 180584448. Throughput: 0: 1785.7, 1: 1801.2. Samples: 45164314. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:48:46,078][22500] Avg episode reward: [(0, '10.550'), (1, '9.540')] -[2023-10-09 11:48:46,334][23468] Updated weights for policy 0, policy_version 87953 (0.0007) -[2023-10-09 11:48:46,444][23469] Updated weights for policy 1, policy_version 88441 (0.0008) -[2023-10-09 11:48:46,703][23468] Updated weights for policy 0, policy_version 87963 (0.0008) -[2023-10-09 11:48:50,075][23469] Updated weights for policy 1, policy_version 88451 (0.0007) -[2023-10-09 11:48:50,446][23469] Updated weights for policy 1, policy_version 88461 (0.0010) -[2023-10-09 11:48:50,693][23468] Updated weights for policy 0, policy_version 87973 (0.0008) -[2023-10-09 11:48:50,819][23469] Updated weights for policy 1, policy_version 88471 (0.0008) -[2023-10-09 11:48:51,065][23468] Updated weights for policy 0, policy_version 87983 (0.0008) -[2023-10-09 11:48:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 180649984. Throughput: 0: 1761.8, 1: 1777.0. Samples: 45174374. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:48:51,078][22500] Avg episode reward: [(0, '10.180'), (1, '9.650')] -[2023-10-09 11:48:51,439][23468] Updated weights for policy 0, policy_version 87993 (0.0007) -[2023-10-09 11:48:54,571][23469] Updated weights for policy 1, policy_version 88481 (0.0008) -[2023-10-09 11:48:54,940][23469] Updated weights for policy 1, policy_version 88491 (0.0008) -[2023-10-09 11:48:55,242][23468] Updated weights for policy 0, policy_version 88003 (0.0007) -[2023-10-09 11:48:55,311][23469] Updated weights for policy 1, policy_version 88501 (0.0009) -[2023-10-09 11:48:55,616][23468] Updated weights for policy 0, policy_version 88013 (0.0007) -[2023-10-09 11:48:55,676][23469] Updated weights for policy 1, policy_version 88511 (0.0009) -[2023-10-09 11:48:55,981][23468] Updated weights for policy 0, policy_version 88023 (0.0008) -[2023-10-09 11:48:56,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 180748288. Throughput: 0: 1777.9, 1: 1805.5. Samples: 45196570. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:48:56,078][22500] Avg episode reward: [(0, '10.400'), (1, '10.090')] -[2023-10-09 11:48:59,345][23469] Updated weights for policy 1, policy_version 88521 (0.0007) -[2023-10-09 11:48:59,694][23468] Updated weights for policy 0, policy_version 88033 (0.0008) -[2023-10-09 11:48:59,717][23469] Updated weights for policy 1, policy_version 88531 (0.0007) -[2023-10-09 11:49:00,054][23468] Updated weights for policy 0, policy_version 88043 (0.0007) -[2023-10-09 11:49:00,071][23469] Updated weights for policy 1, policy_version 88541 (0.0009) -[2023-10-09 11:49:00,431][23468] Updated weights for policy 0, policy_version 88053 (0.0010) -[2023-10-09 11:49:00,807][23468] Updated weights for policy 0, policy_version 88063 (0.0008) -[2023-10-09 11:49:01,077][22500] Fps is (10 sec: 19660.5, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 180846592. Throughput: 0: 1776.3, 1: 1789.9. Samples: 45217168. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 11:49:01,078][22500] Avg episode reward: [(0, '9.910'), (1, '9.740')] -[2023-10-09 11:49:03,904][23469] Updated weights for policy 1, policy_version 88551 (0.0009) -[2023-10-09 11:49:04,277][23469] Updated weights for policy 1, policy_version 88561 (0.0009) -[2023-10-09 11:49:04,436][23468] Updated weights for policy 0, policy_version 88073 (0.0007) -[2023-10-09 11:49:04,648][23469] Updated weights for policy 1, policy_version 88571 (0.0010) -[2023-10-09 11:49:04,800][23468] Updated weights for policy 0, policy_version 88083 (0.0008) -[2023-10-09 11:49:05,170][23468] Updated weights for policy 0, policy_version 88093 (0.0011) -[2023-10-09 11:49:06,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 180912128. Throughput: 0: 1777.0, 1: 1806.4. Samples: 45229056. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 11:49:06,078][22500] Avg episode reward: [(0, '10.150'), (1, '9.280')] -[2023-10-09 11:49:08,269][23469] Updated weights for policy 1, policy_version 88581 (0.0008) -[2023-10-09 11:49:08,638][23469] Updated weights for policy 1, policy_version 88591 (0.0008) -[2023-10-09 11:49:08,844][23468] Updated weights for policy 0, policy_version 88103 (0.0008) -[2023-10-09 11:49:09,009][23469] Updated weights for policy 1, policy_version 88601 (0.0009) -[2023-10-09 11:49:09,221][23468] Updated weights for policy 0, policy_version 88113 (0.0007) -[2023-10-09 11:49:09,582][23468] Updated weights for policy 0, policy_version 88123 (0.0007) -[2023-10-09 11:49:11,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 180977664. Throughput: 0: 1777.1, 1: 1790.4. Samples: 45249420. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 11:49:11,078][22500] Avg episode reward: [(0, '10.170'), (1, '10.240')] -[2023-10-09 11:49:12,767][23469] Updated weights for policy 1, policy_version 88611 (0.0008) -[2023-10-09 11:49:13,169][23469] Updated weights for policy 1, policy_version 88621 (0.0007) -[2023-10-09 11:49:13,534][23469] Updated weights for policy 1, policy_version 88631 (0.0007) -[2023-10-09 11:49:13,555][23468] Updated weights for policy 0, policy_version 88133 (0.0007) -[2023-10-09 11:49:13,931][23468] Updated weights for policy 0, policy_version 88143 (0.0009) -[2023-10-09 11:49:14,304][23468] Updated weights for policy 0, policy_version 88153 (0.0007) -[2023-10-09 11:49:16,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 181043200. Throughput: 0: 1756.6, 1: 1792.6. Samples: 45270710. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 11:49:16,078][22500] Avg episode reward: [(0, '10.400'), (1, '9.690')] -[2023-10-09 11:49:17,408][23469] Updated weights for policy 1, policy_version 88641 (0.0007) -[2023-10-09 11:49:17,782][23469] Updated weights for policy 1, policy_version 88651 (0.0008) -[2023-10-09 11:49:18,155][23469] Updated weights for policy 1, policy_version 88661 (0.0008) -[2023-10-09 11:49:18,234][23468] Updated weights for policy 0, policy_version 88163 (0.0007) -[2023-10-09 11:49:18,529][23469] Updated weights for policy 1, policy_version 88671 (0.0007) -[2023-10-09 11:49:18,642][23468] Updated weights for policy 0, policy_version 88173 (0.0010) -[2023-10-09 11:49:19,006][23468] Updated weights for policy 0, policy_version 88183 (0.0010) -[2023-10-09 11:49:21,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 181108736. Throughput: 0: 1785.8, 1: 1793.0. Samples: 45281504. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 11:49:21,079][22500] Avg episode reward: [(0, '10.470'), (1, '10.120')] -[2023-10-09 11:49:22,323][23469] Updated weights for policy 1, policy_version 88681 (0.0007) -[2023-10-09 11:49:22,689][23469] Updated weights for policy 1, policy_version 88691 (0.0007) -[2023-10-09 11:49:22,697][23468] Updated weights for policy 0, policy_version 88193 (0.0007) -[2023-10-09 11:49:23,059][23469] Updated weights for policy 1, policy_version 88701 (0.0007) -[2023-10-09 11:49:23,070][23468] Updated weights for policy 0, policy_version 88203 (0.0007) -[2023-10-09 11:49:23,434][23468] Updated weights for policy 0, policy_version 88213 (0.0009) -[2023-10-09 11:49:23,802][23468] Updated weights for policy 0, policy_version 88223 (0.0007) -[2023-10-09 11:49:26,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 181174272. Throughput: 0: 1763.2, 1: 1793.4. Samples: 45302614. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 11:49:26,078][22500] Avg episode reward: [(0, '10.740'), (1, '9.300')] -[2023-10-09 11:49:26,794][23469] Updated weights for policy 1, policy_version 88711 (0.0007) -[2023-10-09 11:49:27,155][23469] Updated weights for policy 1, policy_version 88721 (0.0008) -[2023-10-09 11:49:27,530][23469] Updated weights for policy 1, policy_version 88731 (0.0007) -[2023-10-09 11:49:27,579][23468] Updated weights for policy 0, policy_version 88233 (0.0010) -[2023-10-09 11:49:27,954][23468] Updated weights for policy 0, policy_version 88243 (0.0008) -[2023-10-09 11:49:28,326][23468] Updated weights for policy 0, policy_version 88253 (0.0007) -[2023-10-09 11:49:31,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 181239808. Throughput: 0: 1773.2, 1: 1800.5. Samples: 45325132. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 11:49:31,078][22500] Avg episode reward: [(0, '11.290'), (1, '9.540')] -[2023-10-09 11:49:31,150][23469] Updated weights for policy 1, policy_version 88741 (0.0008) -[2023-10-09 11:49:31,525][23469] Updated weights for policy 1, policy_version 88751 (0.0008) -[2023-10-09 11:49:31,893][23469] Updated weights for policy 1, policy_version 88761 (0.0008) -[2023-10-09 11:49:31,987][23468] Updated weights for policy 0, policy_version 88263 (0.0007) -[2023-10-09 11:49:32,358][23468] Updated weights for policy 0, policy_version 88273 (0.0009) -[2023-10-09 11:49:32,734][23468] Updated weights for policy 0, policy_version 88283 (0.0008) -[2023-10-09 11:49:35,612][23469] Updated weights for policy 1, policy_version 88771 (0.0007) -[2023-10-09 11:49:35,971][23469] Updated weights for policy 1, policy_version 88781 (0.0011) -[2023-10-09 11:49:36,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 181305344. Throughput: 0: 1776.1, 1: 1792.8. Samples: 45334976. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 11:49:36,078][22500] Avg episode reward: [(0, '10.790'), (1, '9.870')] -[2023-10-09 11:49:36,342][23469] Updated weights for policy 1, policy_version 88791 (0.0011) -[2023-10-09 11:49:36,553][23468] Updated weights for policy 0, policy_version 88293 (0.0008) -[2023-10-09 11:49:36,918][23468] Updated weights for policy 0, policy_version 88303 (0.0009) -[2023-10-09 11:49:37,292][23468] Updated weights for policy 0, policy_version 88313 (0.0011) -[2023-10-09 11:49:40,010][23469] Updated weights for policy 1, policy_version 88801 (0.0008) -[2023-10-09 11:49:40,376][23469] Updated weights for policy 1, policy_version 88811 (0.0007) -[2023-10-09 11:49:40,743][23469] Updated weights for policy 1, policy_version 88821 (0.0009) -[2023-10-09 11:49:41,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 181370880. Throughput: 0: 1775.4, 1: 1797.8. Samples: 45357364. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 11:49:41,078][22500] Avg episode reward: [(0, '10.610'), (1, '10.200')] -[2023-10-09 11:49:41,095][23468] Updated weights for policy 0, policy_version 88323 (0.0009) -[2023-10-09 11:49:41,116][23469] Updated weights for policy 1, policy_version 88831 (0.0009) -[2023-10-09 11:49:41,460][23468] Updated weights for policy 0, policy_version 88333 (0.0008) -[2023-10-09 11:49:41,827][23468] Updated weights for policy 0, policy_version 88343 (0.0009) -[2023-10-09 11:49:44,857][23469] Updated weights for policy 1, policy_version 88841 (0.0008) -[2023-10-09 11:49:45,227][23469] Updated weights for policy 1, policy_version 88851 (0.0009) -[2023-10-09 11:49:45,465][23468] Updated weights for policy 0, policy_version 88353 (0.0010) -[2023-10-09 11:49:45,602][23469] Updated weights for policy 1, policy_version 88861 (0.0007) -[2023-10-09 11:49:45,842][23468] Updated weights for policy 0, policy_version 88363 (0.0007) -[2023-10-09 11:49:46,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 181469184. Throughput: 0: 1793.3, 1: 1790.0. Samples: 45378418. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 11:49:46,078][22500] Avg episode reward: [(0, '10.940'), (1, '9.790')] -[2023-10-09 11:49:46,202][23468] Updated weights for policy 0, policy_version 88373 (0.0009) -[2023-10-09 11:49:46,572][23468] Updated weights for policy 0, policy_version 88383 (0.0010) -[2023-10-09 11:49:49,299][23469] Updated weights for policy 1, policy_version 88871 (0.0008) -[2023-10-09 11:49:49,660][23469] Updated weights for policy 1, policy_version 88881 (0.0009) -[2023-10-09 11:49:50,038][23469] Updated weights for policy 1, policy_version 88891 (0.0008) -[2023-10-09 11:49:50,379][23468] Updated weights for policy 0, policy_version 88393 (0.0010) -[2023-10-09 11:49:50,750][23468] Updated weights for policy 0, policy_version 88403 (0.0011) -[2023-10-09 11:49:51,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 181534720. Throughput: 0: 1771.7, 1: 1795.5. Samples: 45389578. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 11:49:51,078][22500] Avg episode reward: [(0, '10.780'), (1, '9.170')] -[2023-10-09 11:49:51,124][23468] Updated weights for policy 0, policy_version 88413 (0.0010) -[2023-10-09 11:49:53,701][23469] Updated weights for policy 1, policy_version 88901 (0.0009) -[2023-10-09 11:49:54,076][23469] Updated weights for policy 1, policy_version 88911 (0.0011) -[2023-10-09 11:49:54,452][23469] Updated weights for policy 1, policy_version 88921 (0.0009) -[2023-10-09 11:49:54,918][23468] Updated weights for policy 0, policy_version 88423 (0.0008) -[2023-10-09 11:49:55,284][23468] Updated weights for policy 0, policy_version 88433 (0.0008) -[2023-10-09 11:49:55,650][23468] Updated weights for policy 0, policy_version 88443 (0.0011) -[2023-10-09 11:49:56,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 181633024. Throughput: 0: 1792.5, 1: 1788.1. Samples: 45410550. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-09 11:49:56,078][22500] Avg episode reward: [(0, '10.760'), (1, '9.020')] -[2023-10-09 11:49:58,330][23469] Updated weights for policy 1, policy_version 88931 (0.0009) -[2023-10-09 11:49:58,729][23469] Updated weights for policy 1, policy_version 88941 (0.0009) -[2023-10-09 11:49:59,105][23469] Updated weights for policy 1, policy_version 88951 (0.0010) -[2023-10-09 11:49:59,459][23468] Updated weights for policy 0, policy_version 88453 (0.0009) -[2023-10-09 11:49:59,822][23468] Updated weights for policy 0, policy_version 88463 (0.0008) -[2023-10-09 11:50:00,199][23468] Updated weights for policy 0, policy_version 88473 (0.0009) -[2023-10-09 11:50:01,078][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 181698560. Throughput: 0: 1785.3, 1: 1793.5. Samples: 45431756. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-09 11:50:01,079][22500] Avg episode reward: [(0, '10.060'), (1, '9.360')] -[2023-10-09 11:50:02,757][23469] Updated weights for policy 1, policy_version 88961 (0.0008) -[2023-10-09 11:50:03,130][23469] Updated weights for policy 1, policy_version 88971 (0.0009) -[2023-10-09 11:50:03,497][23469] Updated weights for policy 1, policy_version 88981 (0.0011) -[2023-10-09 11:50:03,864][23469] Updated weights for policy 1, policy_version 88991 (0.0010) -[2023-10-09 11:50:03,961][23468] Updated weights for policy 0, policy_version 88483 (0.0009) -[2023-10-09 11:50:04,365][23468] Updated weights for policy 0, policy_version 88493 (0.0009) -[2023-10-09 11:50:04,735][23468] Updated weights for policy 0, policy_version 88503 (0.0007) -[2023-10-09 11:50:06,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 181764096. Throughput: 0: 1785.7, 1: 1802.5. Samples: 45442976. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-09 11:50:06,078][22500] Avg episode reward: [(0, '9.630'), (1, '9.580')] -[2023-10-09 11:50:07,727][23469] Updated weights for policy 1, policy_version 89001 (0.0010) -[2023-10-09 11:50:08,098][23469] Updated weights for policy 1, policy_version 89011 (0.0010) -[2023-10-09 11:50:08,432][23468] Updated weights for policy 0, policy_version 88513 (0.0007) -[2023-10-09 11:50:08,467][23469] Updated weights for policy 1, policy_version 89021 (0.0010) -[2023-10-09 11:50:08,800][23468] Updated weights for policy 0, policy_version 88523 (0.0009) -[2023-10-09 11:50:09,182][23468] Updated weights for policy 0, policy_version 88533 (0.0011) -[2023-10-09 11:50:09,553][23468] Updated weights for policy 0, policy_version 88543 (0.0008) -[2023-10-09 11:50:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 181829632. Throughput: 0: 1788.7, 1: 1797.8. Samples: 45464004. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-09 11:50:11,078][22500] Avg episode reward: [(0, '9.920'), (1, '9.820')] -[2023-10-09 11:50:12,193][23469] Updated weights for policy 1, policy_version 89031 (0.0008) -[2023-10-09 11:50:12,566][23469] Updated weights for policy 1, policy_version 89041 (0.0008) -[2023-10-09 11:50:12,938][23469] Updated weights for policy 1, policy_version 89051 (0.0009) -[2023-10-09 11:50:13,345][23468] Updated weights for policy 0, policy_version 88553 (0.0010) -[2023-10-09 11:50:13,714][23468] Updated weights for policy 0, policy_version 88563 (0.0010) -[2023-10-09 11:50:14,087][23468] Updated weights for policy 0, policy_version 88573 (0.0011) -[2023-10-09 11:50:16,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 181895168. Throughput: 0: 1776.3, 1: 1801.9. Samples: 45486148. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-09 11:50:16,078][22500] Avg episode reward: [(0, '10.160'), (1, '10.160')] -[2023-10-09 11:50:16,086][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000088576_90701824.pth... -[2023-10-09 11:50:16,086][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000089056_91193344.pth... -[2023-10-09 11:50:16,116][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000086912_88997888.pth -[2023-10-09 11:50:16,126][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000087392_89489408.pth -[2023-10-09 11:50:16,697][23469] Updated weights for policy 1, policy_version 89061 (0.0007) -[2023-10-09 11:50:17,063][23469] Updated weights for policy 1, policy_version 89071 (0.0009) -[2023-10-09 11:50:17,425][23469] Updated weights for policy 1, policy_version 89081 (0.0009) -[2023-10-09 11:50:17,794][23468] Updated weights for policy 0, policy_version 88583 (0.0009) -[2023-10-09 11:50:18,164][23468] Updated weights for policy 0, policy_version 88593 (0.0009) -[2023-10-09 11:50:18,536][23468] Updated weights for policy 0, policy_version 88603 (0.0007) -[2023-10-09 11:50:21,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 181960704. Throughput: 0: 1790.7, 1: 1800.1. Samples: 45496564. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-09 11:50:21,078][22500] Avg episode reward: [(0, '11.020'), (1, '9.920')] -[2023-10-09 11:50:21,158][23469] Updated weights for policy 1, policy_version 89091 (0.0008) -[2023-10-09 11:50:21,521][23469] Updated weights for policy 1, policy_version 89101 (0.0010) -[2023-10-09 11:50:21,890][23469] Updated weights for policy 1, policy_version 89111 (0.0011) -[2023-10-09 11:50:22,340][23468] Updated weights for policy 0, policy_version 88613 (0.0009) -[2023-10-09 11:50:22,703][23468] Updated weights for policy 0, policy_version 88623 (0.0008) -[2023-10-09 11:50:23,073][23468] Updated weights for policy 0, policy_version 88633 (0.0008) -[2023-10-09 11:50:25,592][23469] Updated weights for policy 1, policy_version 89121 (0.0010) -[2023-10-09 11:50:25,958][23469] Updated weights for policy 1, policy_version 89131 (0.0009) -[2023-10-09 11:50:26,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 182026240. Throughput: 0: 1775.2, 1: 1801.9. Samples: 45518336. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-09 11:50:26,078][22500] Avg episode reward: [(0, '10.570'), (1, '10.030')] -[2023-10-09 11:50:26,332][23469] Updated weights for policy 1, policy_version 89141 (0.0007) -[2023-10-09 11:50:26,692][23469] Updated weights for policy 1, policy_version 89151 (0.0009) -[2023-10-09 11:50:26,984][23468] Updated weights for policy 0, policy_version 88643 (0.0007) -[2023-10-09 11:50:27,352][23468] Updated weights for policy 0, policy_version 88653 (0.0007) -[2023-10-09 11:50:27,723][23468] Updated weights for policy 0, policy_version 88663 (0.0008) -[2023-10-09 11:50:30,284][23469] Updated weights for policy 1, policy_version 89161 (0.0009) -[2023-10-09 11:50:30,642][23469] Updated weights for policy 1, policy_version 89171 (0.0010) -[2023-10-09 11:50:31,016][23469] Updated weights for policy 1, policy_version 89181 (0.0011) -[2023-10-09 11:50:31,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 182091776. Throughput: 0: 1767.2, 1: 1811.3. Samples: 45539454. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-09 11:50:31,078][22500] Avg episode reward: [(0, '10.120'), (1, '9.030')] -[2023-10-09 11:50:31,561][23468] Updated weights for policy 0, policy_version 88673 (0.0010) -[2023-10-09 11:50:31,933][23468] Updated weights for policy 0, policy_version 88683 (0.0007) -[2023-10-09 11:50:32,297][23468] Updated weights for policy 0, policy_version 88693 (0.0007) -[2023-10-09 11:50:32,664][23468] Updated weights for policy 0, policy_version 88703 (0.0008) -[2023-10-09 11:50:34,806][23469] Updated weights for policy 1, policy_version 89191 (0.0008) -[2023-10-09 11:50:35,177][23469] Updated weights for policy 1, policy_version 89201 (0.0007) -[2023-10-09 11:50:35,544][23469] Updated weights for policy 1, policy_version 89211 (0.0009) -[2023-10-09 11:50:36,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 182190080. Throughput: 0: 1769.6, 1: 1797.4. Samples: 45550092. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-09 11:50:36,078][22500] Avg episode reward: [(0, '9.630'), (1, '9.170')] -[2023-10-09 11:50:36,414][23468] Updated weights for policy 0, policy_version 88713 (0.0009) -[2023-10-09 11:50:36,796][23468] Updated weights for policy 0, policy_version 88723 (0.0007) -[2023-10-09 11:50:37,160][23468] Updated weights for policy 0, policy_version 88733 (0.0007) -[2023-10-09 11:50:39,303][23469] Updated weights for policy 1, policy_version 89221 (0.0010) -[2023-10-09 11:50:39,677][23469] Updated weights for policy 1, policy_version 89231 (0.0007) -[2023-10-09 11:50:40,039][23469] Updated weights for policy 1, policy_version 89241 (0.0007) -[2023-10-09 11:50:41,016][23468] Updated weights for policy 0, policy_version 88743 (0.0008) -[2023-10-09 11:50:41,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 182255616. Throughput: 0: 1773.2, 1: 1812.5. Samples: 45571906. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-09 11:50:41,078][22500] Avg episode reward: [(0, '10.160'), (1, '9.480')] -[2023-10-09 11:50:41,382][23468] Updated weights for policy 0, policy_version 88753 (0.0008) -[2023-10-09 11:50:41,758][23468] Updated weights for policy 0, policy_version 88763 (0.0009) -[2023-10-09 11:50:43,787][23469] Updated weights for policy 1, policy_version 89251 (0.0008) -[2023-10-09 11:50:44,169][23469] Updated weights for policy 1, policy_version 89261 (0.0009) -[2023-10-09 11:50:44,539][23469] Updated weights for policy 1, policy_version 89271 (0.0007) -[2023-10-09 11:50:45,393][23468] Updated weights for policy 0, policy_version 88773 (0.0008) -[2023-10-09 11:50:45,764][23468] Updated weights for policy 0, policy_version 88783 (0.0008) -[2023-10-09 11:50:46,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 182321152. Throughput: 0: 1801.4, 1: 1795.8. Samples: 45593630. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-09 11:50:46,078][22500] Avg episode reward: [(0, '9.940'), (1, '9.280')] -[2023-10-09 11:50:46,140][23468] Updated weights for policy 0, policy_version 88793 (0.0009) -[2023-10-09 11:50:48,110][23469] Updated weights for policy 1, policy_version 89281 (0.0007) -[2023-10-09 11:50:48,488][23469] Updated weights for policy 1, policy_version 89291 (0.0009) -[2023-10-09 11:50:48,862][23469] Updated weights for policy 1, policy_version 89301 (0.0009) -[2023-10-09 11:50:49,231][23469] Updated weights for policy 1, policy_version 89311 (0.0008) -[2023-10-09 11:50:50,032][23468] Updated weights for policy 0, policy_version 88803 (0.0009) -[2023-10-09 11:50:50,416][23468] Updated weights for policy 0, policy_version 88813 (0.0010) -[2023-10-09 11:50:50,782][23468] Updated weights for policy 0, policy_version 88823 (0.0007) -[2023-10-09 11:50:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 182386688. Throughput: 0: 1775.2, 1: 1806.9. Samples: 45604168. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 11:50:51,078][22500] Avg episode reward: [(0, '9.940'), (1, '9.410')] -[2023-10-09 11:50:52,931][23469] Updated weights for policy 1, policy_version 89321 (0.0009) -[2023-10-09 11:50:53,297][23469] Updated weights for policy 1, policy_version 89331 (0.0007) -[2023-10-09 11:50:53,662][23469] Updated weights for policy 1, policy_version 89341 (0.0009) -[2023-10-09 11:50:54,459][23468] Updated weights for policy 0, policy_version 88833 (0.0008) -[2023-10-09 11:50:54,833][23468] Updated weights for policy 0, policy_version 88843 (0.0008) -[2023-10-09 11:50:55,213][23468] Updated weights for policy 0, policy_version 88853 (0.0007) -[2023-10-09 11:50:55,577][23468] Updated weights for policy 0, policy_version 88863 (0.0009) -[2023-10-09 11:50:56,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 182484992. Throughput: 0: 1802.5, 1: 1800.5. Samples: 45626140. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 11:50:56,078][22500] Avg episode reward: [(0, '10.670'), (1, '10.120')] -[2023-10-09 11:50:57,315][23469] Updated weights for policy 1, policy_version 89351 (0.0008) -[2023-10-09 11:50:57,688][23469] Updated weights for policy 1, policy_version 89361 (0.0007) -[2023-10-09 11:50:58,056][23469] Updated weights for policy 1, policy_version 89371 (0.0008) -[2023-10-09 11:50:59,467][23468] Updated weights for policy 0, policy_version 88873 (0.0009) -[2023-10-09 11:50:59,834][23468] Updated weights for policy 0, policy_version 88883 (0.0008) -[2023-10-09 11:51:00,216][23468] Updated weights for policy 0, policy_version 88893 (0.0007) -[2023-10-09 11:51:01,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 182550528. Throughput: 0: 1777.6, 1: 1801.6. Samples: 45647212. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 11:51:01,078][22500] Avg episode reward: [(0, '10.640'), (1, '9.300')] -[2023-10-09 11:51:02,019][23469] Updated weights for policy 1, policy_version 89381 (0.0009) -[2023-10-09 11:51:02,386][23469] Updated weights for policy 1, policy_version 89391 (0.0007) -[2023-10-09 11:51:02,764][23469] Updated weights for policy 1, policy_version 89401 (0.0007) -[2023-10-09 11:51:03,942][23468] Updated weights for policy 0, policy_version 88903 (0.0008) -[2023-10-09 11:51:04,320][23468] Updated weights for policy 0, policy_version 88913 (0.0008) -[2023-10-09 11:51:04,693][23468] Updated weights for policy 0, policy_version 88923 (0.0008) -[2023-10-09 11:51:06,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 182616064. Throughput: 0: 1794.0, 1: 1801.3. Samples: 45658354. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 11:51:06,078][22500] Avg episode reward: [(0, '10.510'), (1, '10.140')] -[2023-10-09 11:51:06,483][23469] Updated weights for policy 1, policy_version 89411 (0.0009) -[2023-10-09 11:51:06,860][23469] Updated weights for policy 1, policy_version 89421 (0.0011) -[2023-10-09 11:51:07,232][23469] Updated weights for policy 1, policy_version 89431 (0.0008) -[2023-10-09 11:51:08,519][23468] Updated weights for policy 0, policy_version 88933 (0.0009) -[2023-10-09 11:51:08,899][23468] Updated weights for policy 0, policy_version 88943 (0.0010) -[2023-10-09 11:51:09,269][23468] Updated weights for policy 0, policy_version 88953 (0.0009) -[2023-10-09 11:51:10,842][23469] Updated weights for policy 1, policy_version 89441 (0.0009) -[2023-10-09 11:51:11,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 182681600. Throughput: 0: 1782.8, 1: 1800.1. Samples: 45679566. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 11:51:11,078][22500] Avg episode reward: [(0, '10.220'), (1, '9.600')] -[2023-10-09 11:51:11,216][23469] Updated weights for policy 1, policy_version 89451 (0.0007) -[2023-10-09 11:51:11,583][23469] Updated weights for policy 1, policy_version 89461 (0.0008) -[2023-10-09 11:51:11,962][23469] Updated weights for policy 1, policy_version 89471 (0.0009) -[2023-10-09 11:51:13,090][23468] Updated weights for policy 0, policy_version 88963 (0.0008) -[2023-10-09 11:51:13,463][23468] Updated weights for policy 0, policy_version 88973 (0.0008) -[2023-10-09 11:51:13,842][23468] Updated weights for policy 0, policy_version 88983 (0.0008) -[2023-10-09 11:51:15,563][23469] Updated weights for policy 1, policy_version 89481 (0.0008) -[2023-10-09 11:51:15,942][23469] Updated weights for policy 1, policy_version 89491 (0.0007) -[2023-10-09 11:51:16,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 182747136. Throughput: 0: 1781.1, 1: 1812.7. Samples: 45701172. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 11:51:16,078][22500] Avg episode reward: [(0, '10.260'), (1, '9.780')] -[2023-10-09 11:51:16,314][23469] Updated weights for policy 1, policy_version 89501 (0.0009) -[2023-10-09 11:51:17,413][23468] Updated weights for policy 0, policy_version 88993 (0.0007) -[2023-10-09 11:51:17,779][23468] Updated weights for policy 0, policy_version 89003 (0.0011) -[2023-10-09 11:51:18,152][23468] Updated weights for policy 0, policy_version 89013 (0.0011) -[2023-10-09 11:51:18,524][23468] Updated weights for policy 0, policy_version 89023 (0.0009) -[2023-10-09 11:51:20,004][23469] Updated weights for policy 1, policy_version 89511 (0.0008) -[2023-10-09 11:51:20,366][23469] Updated weights for policy 1, policy_version 89521 (0.0008) -[2023-10-09 11:51:20,737][23469] Updated weights for policy 1, policy_version 89531 (0.0008) -[2023-10-09 11:51:21,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 182845440. Throughput: 0: 1794.1, 1: 1808.4. Samples: 45712204. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 11:51:21,078][22500] Avg episode reward: [(0, '10.150'), (1, '10.150')] -[2023-10-09 11:51:22,269][23468] Updated weights for policy 0, policy_version 89033 (0.0008) -[2023-10-09 11:51:22,638][23468] Updated weights for policy 0, policy_version 89043 (0.0007) -[2023-10-09 11:51:23,007][23468] Updated weights for policy 0, policy_version 89053 (0.0008) -[2023-10-09 11:51:24,485][23469] Updated weights for policy 1, policy_version 89541 (0.0008) -[2023-10-09 11:51:24,845][23469] Updated weights for policy 1, policy_version 89551 (0.0008) -[2023-10-09 11:51:25,216][23469] Updated weights for policy 1, policy_version 89561 (0.0007) -[2023-10-09 11:51:26,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 182910976. Throughput: 0: 1784.9, 1: 1814.2. Samples: 45733864. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 11:51:26,079][22500] Avg episode reward: [(0, '10.280'), (1, '10.420')] -[2023-10-09 11:51:26,582][23468] Updated weights for policy 0, policy_version 89063 (0.0010) -[2023-10-09 11:51:26,947][23468] Updated weights for policy 0, policy_version 89073 (0.0010) -[2023-10-09 11:51:27,323][23468] Updated weights for policy 0, policy_version 89083 (0.0009) -[2023-10-09 11:51:28,900][23469] Updated weights for policy 1, policy_version 89571 (0.0008) -[2023-10-09 11:51:29,297][23469] Updated weights for policy 1, policy_version 89581 (0.0007) -[2023-10-09 11:51:29,673][23469] Updated weights for policy 1, policy_version 89591 (0.0009) -[2023-10-09 11:51:31,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 182976512. Throughput: 0: 1786.9, 1: 1810.3. Samples: 45755502. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 11:51:31,078][22500] Avg episode reward: [(0, '10.000'), (1, '10.360')] -[2023-10-09 11:51:31,196][23468] Updated weights for policy 0, policy_version 89093 (0.0008) -[2023-10-09 11:51:31,570][23468] Updated weights for policy 0, policy_version 89103 (0.0008) -[2023-10-09 11:51:31,942][23468] Updated weights for policy 0, policy_version 89113 (0.0009) -[2023-10-09 11:51:33,294][23469] Updated weights for policy 1, policy_version 89601 (0.0007) -[2023-10-09 11:51:33,653][23469] Updated weights for policy 1, policy_version 89611 (0.0007) -[2023-10-09 11:51:34,029][23469] Updated weights for policy 1, policy_version 89621 (0.0008) -[2023-10-09 11:51:34,396][23469] Updated weights for policy 1, policy_version 89631 (0.0009) -[2023-10-09 11:51:35,698][23468] Updated weights for policy 0, policy_version 89123 (0.0008) -[2023-10-09 11:51:36,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 183042048. Throughput: 0: 1784.6, 1: 1816.5. Samples: 45766218. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 11:51:36,078][22500] Avg episode reward: [(0, '10.420'), (1, '9.710')] -[2023-10-09 11:51:36,106][23468] Updated weights for policy 0, policy_version 89133 (0.0007) -[2023-10-09 11:51:36,468][23468] Updated weights for policy 0, policy_version 89143 (0.0007) -[2023-10-09 11:51:38,163][23469] Updated weights for policy 1, policy_version 89641 (0.0008) -[2023-10-09 11:51:38,530][23469] Updated weights for policy 1, policy_version 89651 (0.0008) -[2023-10-09 11:51:38,894][23469] Updated weights for policy 1, policy_version 89661 (0.0008) -[2023-10-09 11:51:40,105][23468] Updated weights for policy 0, policy_version 89153 (0.0009) -[2023-10-09 11:51:40,472][23468] Updated weights for policy 0, policy_version 89163 (0.0010) -[2023-10-09 11:51:40,847][23468] Updated weights for policy 0, policy_version 89173 (0.0009) -[2023-10-09 11:51:41,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 183107584. Throughput: 0: 1783.1, 1: 1812.1. Samples: 45787924. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 11:51:41,078][22500] Avg episode reward: [(0, '10.520'), (1, '9.780')] -[2023-10-09 11:51:41,219][23468] Updated weights for policy 0, policy_version 89183 (0.0009) -[2023-10-09 11:51:42,617][23469] Updated weights for policy 1, policy_version 89671 (0.0007) -[2023-10-09 11:51:42,993][23469] Updated weights for policy 1, policy_version 89681 (0.0007) -[2023-10-09 11:51:43,363][23469] Updated weights for policy 1, policy_version 89691 (0.0007) -[2023-10-09 11:51:44,961][23468] Updated weights for policy 0, policy_version 89193 (0.0008) -[2023-10-09 11:51:45,323][23468] Updated weights for policy 0, policy_version 89203 (0.0009) -[2023-10-09 11:51:45,696][23468] Updated weights for policy 0, policy_version 89213 (0.0009) -[2023-10-09 11:51:46,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 183205888. Throughput: 0: 1800.8, 1: 1808.8. Samples: 45809642. Policy #0 lag: (min: 18.0, avg: 19.4, max: 42.0) -[2023-10-09 11:51:46,078][22500] Avg episode reward: [(0, '10.570'), (1, '9.430')] -[2023-10-09 11:51:47,036][23469] Updated weights for policy 1, policy_version 89701 (0.0009) -[2023-10-09 11:51:47,400][23469] Updated weights for policy 1, policy_version 89711 (0.0009) -[2023-10-09 11:51:47,772][23469] Updated weights for policy 1, policy_version 89721 (0.0009) -[2023-10-09 11:51:49,444][23468] Updated weights for policy 0, policy_version 89223 (0.0008) -[2023-10-09 11:51:49,817][23468] Updated weights for policy 0, policy_version 89233 (0.0009) -[2023-10-09 11:51:50,198][23468] Updated weights for policy 0, policy_version 89243 (0.0009) -[2023-10-09 11:51:51,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 183271424. Throughput: 0: 1786.8, 1: 1810.7. Samples: 45820242. Policy #0 lag: (min: 18.0, avg: 19.4, max: 42.0) -[2023-10-09 11:51:51,078][22500] Avg episode reward: [(0, '11.130'), (1, '10.050')] -[2023-10-09 11:51:51,528][23469] Updated weights for policy 1, policy_version 89731 (0.0008) -[2023-10-09 11:51:51,893][23469] Updated weights for policy 1, policy_version 89741 (0.0008) -[2023-10-09 11:51:52,274][23469] Updated weights for policy 1, policy_version 89751 (0.0008) -[2023-10-09 11:51:53,979][23468] Updated weights for policy 0, policy_version 89253 (0.0009) -[2023-10-09 11:51:54,349][23468] Updated weights for policy 0, policy_version 89263 (0.0010) -[2023-10-09 11:51:54,722][23468] Updated weights for policy 0, policy_version 89273 (0.0007) -[2023-10-09 11:51:56,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 183336960. Throughput: 0: 1805.1, 1: 1809.3. Samples: 45842214. Policy #0 lag: (min: 18.0, avg: 19.4, max: 42.0) -[2023-10-09 11:51:56,078][22500] Avg episode reward: [(0, '10.990'), (1, '9.980')] -[2023-10-09 11:51:56,085][23469] Updated weights for policy 1, policy_version 89761 (0.0010) -[2023-10-09 11:51:56,461][23469] Updated weights for policy 1, policy_version 89771 (0.0007) -[2023-10-09 11:51:56,820][23469] Updated weights for policy 1, policy_version 89781 (0.0011) -[2023-10-09 11:51:57,193][23469] Updated weights for policy 1, policy_version 89791 (0.0008) -[2023-10-09 11:51:58,324][23468] Updated weights for policy 0, policy_version 89283 (0.0009) -[2023-10-09 11:51:58,697][23468] Updated weights for policy 0, policy_version 89293 (0.0010) -[2023-10-09 11:51:59,071][23468] Updated weights for policy 0, policy_version 89303 (0.0009) -[2023-10-09 11:52:00,921][23469] Updated weights for policy 1, policy_version 89801 (0.0010) -[2023-10-09 11:52:01,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 183402496. Throughput: 0: 1796.6, 1: 1811.3. Samples: 45863530. Policy #0 lag: (min: 18.0, avg: 19.4, max: 42.0) -[2023-10-09 11:52:01,078][22500] Avg episode reward: [(0, '10.560'), (1, '9.970')] -[2023-10-09 11:52:01,288][23469] Updated weights for policy 1, policy_version 89811 (0.0008) -[2023-10-09 11:52:01,659][23469] Updated weights for policy 1, policy_version 89821 (0.0007) -[2023-10-09 11:52:02,787][23468] Updated weights for policy 0, policy_version 89313 (0.0009) -[2023-10-09 11:52:03,159][23468] Updated weights for policy 0, policy_version 89323 (0.0008) -[2023-10-09 11:52:03,532][23468] Updated weights for policy 0, policy_version 89333 (0.0009) -[2023-10-09 11:52:03,904][23468] Updated weights for policy 0, policy_version 89343 (0.0009) -[2023-10-09 11:52:05,208][23469] Updated weights for policy 1, policy_version 89831 (0.0007) -[2023-10-09 11:52:05,573][23469] Updated weights for policy 1, policy_version 89841 (0.0008) -[2023-10-09 11:52:05,948][23469] Updated weights for policy 1, policy_version 89851 (0.0007) -[2023-10-09 11:52:06,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 183468032. Throughput: 0: 1807.2, 1: 1803.8. Samples: 45874700. Policy #0 lag: (min: 18.0, avg: 19.4, max: 42.0) -[2023-10-09 11:52:06,078][22500] Avg episode reward: [(0, '10.980'), (1, '9.830')] -[2023-10-09 11:52:07,615][23468] Updated weights for policy 0, policy_version 89353 (0.0008) -[2023-10-09 11:52:07,980][23468] Updated weights for policy 0, policy_version 89363 (0.0008) -[2023-10-09 11:52:08,354][23468] Updated weights for policy 0, policy_version 89373 (0.0009) -[2023-10-09 11:52:09,812][23469] Updated weights for policy 1, policy_version 89861 (0.0007) -[2023-10-09 11:52:10,185][23469] Updated weights for policy 1, policy_version 89871 (0.0007) -[2023-10-09 11:52:10,542][23469] Updated weights for policy 1, policy_version 89881 (0.0010) -[2023-10-09 11:52:11,078][22500] Fps is (10 sec: 16383.5, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 183566336. Throughput: 0: 1792.0, 1: 1816.0. Samples: 45896226. Policy #0 lag: (min: 18.0, avg: 19.4, max: 42.0) -[2023-10-09 11:52:11,079][22500] Avg episode reward: [(0, '10.410'), (1, '9.590')] -[2023-10-09 11:52:12,064][23468] Updated weights for policy 0, policy_version 89383 (0.0010) -[2023-10-09 11:52:12,443][23468] Updated weights for policy 0, policy_version 89393 (0.0007) -[2023-10-09 11:52:12,818][23468] Updated weights for policy 0, policy_version 89403 (0.0007) -[2023-10-09 11:52:14,343][23469] Updated weights for policy 1, policy_version 89891 (0.0008) -[2023-10-09 11:52:14,729][23469] Updated weights for policy 1, policy_version 89901 (0.0008) -[2023-10-09 11:52:15,101][23469] Updated weights for policy 1, policy_version 89911 (0.0008) -[2023-10-09 11:52:16,078][22500] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 183631872. Throughput: 0: 1789.0, 1: 1802.0. Samples: 45917096. Policy #0 lag: (min: 18.0, avg: 19.4, max: 42.0) -[2023-10-09 11:52:16,079][22500] Avg episode reward: [(0, '9.880'), (1, '9.190')] -[2023-10-09 11:52:16,091][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000089920_92078080.pth... -[2023-10-09 11:52:16,091][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000089408_91553792.pth... -[2023-10-09 11:52:16,140][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000088224_90341376.pth -[2023-10-09 11:52:16,140][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000087744_89849856.pth -[2023-10-09 11:52:16,651][23468] Updated weights for policy 0, policy_version 89413 (0.0008) -[2023-10-09 11:52:17,021][23468] Updated weights for policy 0, policy_version 89423 (0.0007) -[2023-10-09 11:52:17,388][23468] Updated weights for policy 0, policy_version 89433 (0.0007) -[2023-10-09 11:52:18,644][23469] Updated weights for policy 1, policy_version 89921 (0.0007) -[2023-10-09 11:52:19,010][23469] Updated weights for policy 1, policy_version 89931 (0.0010) -[2023-10-09 11:52:19,380][23469] Updated weights for policy 1, policy_version 89941 (0.0008) -[2023-10-09 11:52:19,749][23469] Updated weights for policy 1, policy_version 89951 (0.0007) -[2023-10-09 11:52:21,071][23468] Updated weights for policy 0, policy_version 89443 (0.0010) -[2023-10-09 11:52:21,077][22500] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 183697408. Throughput: 0: 1786.0, 1: 1810.4. Samples: 45928060. Policy #0 lag: (min: 18.0, avg: 19.4, max: 42.0) -[2023-10-09 11:52:21,078][22500] Avg episode reward: [(0, '10.230'), (1, '9.150')] -[2023-10-09 11:52:21,458][23468] Updated weights for policy 0, policy_version 89453 (0.0010) -[2023-10-09 11:52:21,830][23468] Updated weights for policy 0, policy_version 89463 (0.0010) -[2023-10-09 11:52:23,641][23469] Updated weights for policy 1, policy_version 89961 (0.0010) -[2023-10-09 11:52:24,009][23469] Updated weights for policy 1, policy_version 89971 (0.0008) -[2023-10-09 11:52:24,382][23469] Updated weights for policy 1, policy_version 89981 (0.0010) -[2023-10-09 11:52:25,584][23468] Updated weights for policy 0, policy_version 89473 (0.0010) -[2023-10-09 11:52:25,952][23468] Updated weights for policy 0, policy_version 89483 (0.0010) -[2023-10-09 11:52:26,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 183762944. Throughput: 0: 1787.8, 1: 1796.8. Samples: 45949230. Policy #0 lag: (min: 18.0, avg: 19.4, max: 42.0) -[2023-10-09 11:52:26,078][22500] Avg episode reward: [(0, '10.000'), (1, '9.590')] -[2023-10-09 11:52:26,321][23468] Updated weights for policy 0, policy_version 89493 (0.0010) -[2023-10-09 11:52:26,699][23468] Updated weights for policy 0, policy_version 89503 (0.0009) -[2023-10-09 11:52:28,147][23469] Updated weights for policy 1, policy_version 89991 (0.0009) -[2023-10-09 11:52:28,516][23469] Updated weights for policy 1, policy_version 90001 (0.0009) -[2023-10-09 11:52:28,897][23469] Updated weights for policy 1, policy_version 90011 (0.0007) -[2023-10-09 11:52:30,540][23468] Updated weights for policy 0, policy_version 89513 (0.0007) -[2023-10-09 11:52:30,910][23468] Updated weights for policy 0, policy_version 89523 (0.0011) -[2023-10-09 11:52:31,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 183828480. Throughput: 0: 1804.4, 1: 1799.2. Samples: 45971806. Policy #0 lag: (min: 18.0, avg: 19.4, max: 42.0) -[2023-10-09 11:52:31,078][22500] Avg episode reward: [(0, '10.030'), (1, '9.830')] -[2023-10-09 11:52:31,284][23468] Updated weights for policy 0, policy_version 89533 (0.0010) -[2023-10-09 11:52:32,629][23469] Updated weights for policy 1, policy_version 90021 (0.0009) -[2023-10-09 11:52:33,000][23469] Updated weights for policy 1, policy_version 90031 (0.0008) -[2023-10-09 11:52:33,367][23469] Updated weights for policy 1, policy_version 90041 (0.0008) -[2023-10-09 11:52:35,037][23468] Updated weights for policy 0, policy_version 89543 (0.0007) -[2023-10-09 11:52:35,406][23468] Updated weights for policy 0, policy_version 89553 (0.0007) -[2023-10-09 11:52:35,786][23468] Updated weights for policy 0, policy_version 89563 (0.0008) -[2023-10-09 11:52:36,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 183926784. Throughput: 0: 1786.4, 1: 1797.5. Samples: 45981518. Policy #0 lag: (min: 25.0, avg: 25.0, max: 25.0) -[2023-10-09 11:52:36,078][22500] Avg episode reward: [(0, '10.110'), (1, '9.730')] -[2023-10-09 11:52:37,078][23469] Updated weights for policy 1, policy_version 90051 (0.0009) -[2023-10-09 11:52:37,446][23469] Updated weights for policy 1, policy_version 90061 (0.0010) -[2023-10-09 11:52:37,815][23469] Updated weights for policy 1, policy_version 90071 (0.0007) -[2023-10-09 11:52:39,599][23468] Updated weights for policy 0, policy_version 89573 (0.0009) -[2023-10-09 11:52:39,976][23468] Updated weights for policy 0, policy_version 89583 (0.0009) -[2023-10-09 11:52:40,340][23468] Updated weights for policy 0, policy_version 89593 (0.0011) -[2023-10-09 11:52:41,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 183992320. Throughput: 0: 1803.8, 1: 1788.4. Samples: 46003862. Policy #0 lag: (min: 25.0, avg: 25.0, max: 25.0) -[2023-10-09 11:52:41,079][22500] Avg episode reward: [(0, '10.080'), (1, '9.950')] -[2023-10-09 11:52:41,651][23469] Updated weights for policy 1, policy_version 90081 (0.0011) -[2023-10-09 11:52:42,028][23469] Updated weights for policy 1, policy_version 90091 (0.0009) -[2023-10-09 11:52:42,407][23469] Updated weights for policy 1, policy_version 90101 (0.0009) -[2023-10-09 11:52:42,776][23469] Updated weights for policy 1, policy_version 90111 (0.0009) -[2023-10-09 11:52:44,262][23468] Updated weights for policy 0, policy_version 89603 (0.0010) -[2023-10-09 11:52:44,631][23468] Updated weights for policy 0, policy_version 89613 (0.0009) -[2023-10-09 11:52:45,004][23468] Updated weights for policy 0, policy_version 89623 (0.0011) -[2023-10-09 11:52:46,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 184057856. Throughput: 0: 1790.0, 1: 1794.3. Samples: 46024824. Policy #0 lag: (min: 25.0, avg: 25.0, max: 25.0) -[2023-10-09 11:52:46,078][22500] Avg episode reward: [(0, '10.040'), (1, '9.940')] -[2023-10-09 11:52:46,573][23469] Updated weights for policy 1, policy_version 90121 (0.0008) -[2023-10-09 11:52:46,944][23469] Updated weights for policy 1, policy_version 90131 (0.0007) -[2023-10-09 11:52:47,318][23469] Updated weights for policy 1, policy_version 90141 (0.0007) -[2023-10-09 11:52:48,692][23468] Updated weights for policy 0, policy_version 89633 (0.0009) -[2023-10-09 11:52:49,075][23468] Updated weights for policy 0, policy_version 89643 (0.0010) -[2023-10-09 11:52:49,450][23468] Updated weights for policy 0, policy_version 89653 (0.0009) -[2023-10-09 11:52:49,827][23468] Updated weights for policy 0, policy_version 89663 (0.0009) -[2023-10-09 11:52:51,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 184123392. Throughput: 0: 1798.3, 1: 1783.6. Samples: 46035886. Policy #0 lag: (min: 25.0, avg: 25.0, max: 25.0) -[2023-10-09 11:52:51,078][22500] Avg episode reward: [(0, '10.370'), (1, '10.220')] -[2023-10-09 11:52:51,196][23469] Updated weights for policy 1, policy_version 90151 (0.0008) -[2023-10-09 11:52:51,567][23469] Updated weights for policy 1, policy_version 90161 (0.0008) -[2023-10-09 11:52:51,930][23469] Updated weights for policy 1, policy_version 90171 (0.0011) -[2023-10-09 11:52:53,463][23468] Updated weights for policy 0, policy_version 89673 (0.0009) -[2023-10-09 11:52:53,833][23468] Updated weights for policy 0, policy_version 89683 (0.0009) -[2023-10-09 11:52:54,215][23468] Updated weights for policy 0, policy_version 89693 (0.0010) -[2023-10-09 11:52:55,581][23469] Updated weights for policy 1, policy_version 90181 (0.0008) -[2023-10-09 11:52:55,951][23469] Updated weights for policy 1, policy_version 90191 (0.0009) -[2023-10-09 11:52:56,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 184188928. Throughput: 0: 1791.2, 1: 1780.6. Samples: 46056956. Policy #0 lag: (min: 25.0, avg: 25.0, max: 25.0) -[2023-10-09 11:52:56,079][22500] Avg episode reward: [(0, '11.470'), (1, '10.240')] -[2023-10-09 11:52:56,327][23469] Updated weights for policy 1, policy_version 90201 (0.0008) -[2023-10-09 11:52:58,028][23468] Updated weights for policy 0, policy_version 89703 (0.0011) -[2023-10-09 11:52:58,406][23468] Updated weights for policy 0, policy_version 89713 (0.0010) -[2023-10-09 11:52:58,792][23468] Updated weights for policy 0, policy_version 89723 (0.0011) -[2023-10-09 11:53:00,033][23469] Updated weights for policy 1, policy_version 90211 (0.0008) -[2023-10-09 11:53:00,427][23469] Updated weights for policy 1, policy_version 90221 (0.0009) -[2023-10-09 11:53:00,787][23469] Updated weights for policy 1, policy_version 90231 (0.0009) -[2023-10-09 11:53:01,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 184254464. Throughput: 0: 1788.9, 1: 1796.6. Samples: 46078442. Policy #0 lag: (min: 25.0, avg: 25.0, max: 25.0) -[2023-10-09 11:53:01,078][22500] Avg episode reward: [(0, '11.090'), (1, '10.730')] -[2023-10-09 11:53:01,114][23343] Saving new best policy, reward=10.730! -[2023-10-09 11:53:02,488][23468] Updated weights for policy 0, policy_version 89733 (0.0007) -[2023-10-09 11:53:02,861][23468] Updated weights for policy 0, policy_version 89743 (0.0007) -[2023-10-09 11:53:03,229][23468] Updated weights for policy 0, policy_version 89753 (0.0008) -[2023-10-09 11:53:04,498][23469] Updated weights for policy 1, policy_version 90241 (0.0010) -[2023-10-09 11:53:04,875][23469] Updated weights for policy 1, policy_version 90251 (0.0007) -[2023-10-09 11:53:05,243][23469] Updated weights for policy 1, policy_version 90261 (0.0007) -[2023-10-09 11:53:05,618][23469] Updated weights for policy 1, policy_version 90271 (0.0008) -[2023-10-09 11:53:06,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 184352768. Throughput: 0: 1799.8, 1: 1789.1. Samples: 46089562. Policy #0 lag: (min: 25.0, avg: 25.0, max: 25.0) -[2023-10-09 11:53:06,078][22500] Avg episode reward: [(0, '10.060'), (1, '10.070')] -[2023-10-09 11:53:06,859][23468] Updated weights for policy 0, policy_version 89763 (0.0008) -[2023-10-09 11:53:07,233][23468] Updated weights for policy 0, policy_version 89773 (0.0007) -[2023-10-09 11:53:07,613][23468] Updated weights for policy 0, policy_version 89783 (0.0007) -[2023-10-09 11:53:09,428][23469] Updated weights for policy 1, policy_version 90281 (0.0009) -[2023-10-09 11:53:09,797][23469] Updated weights for policy 1, policy_version 90291 (0.0008) -[2023-10-09 11:53:10,172][23469] Updated weights for policy 1, policy_version 90301 (0.0010) -[2023-10-09 11:53:11,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.6, 300 sec: 14329.1). Total num frames: 184418304. Throughput: 0: 1790.5, 1: 1800.4. Samples: 46110818. Policy #0 lag: (min: 25.0, avg: 25.0, max: 25.0) -[2023-10-09 11:53:11,078][22500] Avg episode reward: [(0, '9.940'), (1, '10.080')] -[2023-10-09 11:53:11,499][23468] Updated weights for policy 0, policy_version 89793 (0.0010) -[2023-10-09 11:53:11,867][23468] Updated weights for policy 0, policy_version 89803 (0.0008) -[2023-10-09 11:53:12,237][23468] Updated weights for policy 0, policy_version 89813 (0.0008) -[2023-10-09 11:53:12,602][23468] Updated weights for policy 0, policy_version 89823 (0.0009) -[2023-10-09 11:53:13,919][23469] Updated weights for policy 1, policy_version 90311 (0.0007) -[2023-10-09 11:53:14,282][23469] Updated weights for policy 1, policy_version 90321 (0.0007) -[2023-10-09 11:53:14,660][23469] Updated weights for policy 1, policy_version 90331 (0.0008) -[2023-10-09 11:53:16,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 184483840. Throughput: 0: 1796.8, 1: 1782.4. Samples: 46132870. Policy #0 lag: (min: 25.0, avg: 25.0, max: 25.0) -[2023-10-09 11:53:16,079][22500] Avg episode reward: [(0, '9.910'), (1, '9.340')] -[2023-10-09 11:53:16,262][23468] Updated weights for policy 0, policy_version 89833 (0.0009) -[2023-10-09 11:53:16,635][23468] Updated weights for policy 0, policy_version 89843 (0.0009) -[2023-10-09 11:53:17,005][23468] Updated weights for policy 0, policy_version 89853 (0.0008) -[2023-10-09 11:53:18,535][23469] Updated weights for policy 1, policy_version 90341 (0.0008) -[2023-10-09 11:53:18,905][23469] Updated weights for policy 1, policy_version 90351 (0.0009) -[2023-10-09 11:53:19,286][23469] Updated weights for policy 1, policy_version 90361 (0.0009) -[2023-10-09 11:53:20,732][23468] Updated weights for policy 0, policy_version 89863 (0.0008) -[2023-10-09 11:53:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 184549376. Throughput: 0: 1793.2, 1: 1805.8. Samples: 46143472. Policy #0 lag: (min: 25.0, avg: 25.0, max: 25.0) -[2023-10-09 11:53:21,078][22500] Avg episode reward: [(0, '10.920'), (1, '9.400')] -[2023-10-09 11:53:21,094][23468] Updated weights for policy 0, policy_version 89873 (0.0007) -[2023-10-09 11:53:21,476][23468] Updated weights for policy 0, policy_version 89883 (0.0007) -[2023-10-09 11:53:22,971][23469] Updated weights for policy 1, policy_version 90371 (0.0007) -[2023-10-09 11:53:23,336][23469] Updated weights for policy 1, policy_version 90381 (0.0007) -[2023-10-09 11:53:23,698][23469] Updated weights for policy 1, policy_version 90391 (0.0007) -[2023-10-09 11:53:25,249][23468] Updated weights for policy 0, policy_version 89893 (0.0008) -[2023-10-09 11:53:25,620][23468] Updated weights for policy 0, policy_version 89903 (0.0009) -[2023-10-09 11:53:25,995][23468] Updated weights for policy 0, policy_version 89913 (0.0009) -[2023-10-09 11:53:26,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 184614912. Throughput: 0: 1792.2, 1: 1788.6. Samples: 46165000. Policy #0 lag: (min: 25.0, avg: 25.0, max: 25.0) -[2023-10-09 11:53:26,078][22500] Avg episode reward: [(0, '11.730'), (1, '9.580')] -[2023-10-09 11:53:27,332][23469] Updated weights for policy 1, policy_version 90401 (0.0008) -[2023-10-09 11:53:27,704][23469] Updated weights for policy 1, policy_version 90411 (0.0007) -[2023-10-09 11:53:28,060][23469] Updated weights for policy 1, policy_version 90421 (0.0009) -[2023-10-09 11:53:28,428][23469] Updated weights for policy 1, policy_version 90431 (0.0008) -[2023-10-09 11:53:29,848][23468] Updated weights for policy 0, policy_version 89923 (0.0009) -[2023-10-09 11:53:30,226][23468] Updated weights for policy 0, policy_version 89933 (0.0009) -[2023-10-09 11:53:30,603][23468] Updated weights for policy 0, policy_version 89943 (0.0010) -[2023-10-09 11:53:31,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 184713216. Throughput: 0: 1807.6, 1: 1792.6. Samples: 46186832. Policy #0 lag: (min: 25.0, avg: 25.0, max: 25.0) -[2023-10-09 11:53:31,078][22500] Avg episode reward: [(0, '11.490'), (1, '10.060')] -[2023-10-09 11:53:32,179][23469] Updated weights for policy 1, policy_version 90441 (0.0008) -[2023-10-09 11:53:32,549][23469] Updated weights for policy 1, policy_version 90451 (0.0009) -[2023-10-09 11:53:32,916][23469] Updated weights for policy 1, policy_version 90461 (0.0009) -[2023-10-09 11:53:34,349][23468] Updated weights for policy 0, policy_version 89953 (0.0009) -[2023-10-09 11:53:34,721][23468] Updated weights for policy 0, policy_version 89963 (0.0007) -[2023-10-09 11:53:35,102][23468] Updated weights for policy 0, policy_version 89973 (0.0009) -[2023-10-09 11:53:35,470][23468] Updated weights for policy 0, policy_version 89983 (0.0010) -[2023-10-09 11:53:36,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 184778752. Throughput: 0: 1792.2, 1: 1797.6. Samples: 46197428. Policy #0 lag: (min: 7.0, avg: 10.6, max: 39.0) -[2023-10-09 11:53:36,078][22500] Avg episode reward: [(0, '11.270'), (1, '10.190')] -[2023-10-09 11:53:36,589][23469] Updated weights for policy 1, policy_version 90471 (0.0008) -[2023-10-09 11:53:36,955][23469] Updated weights for policy 1, policy_version 90481 (0.0007) -[2023-10-09 11:53:37,332][23469] Updated weights for policy 1, policy_version 90491 (0.0008) -[2023-10-09 11:53:39,101][23468] Updated weights for policy 0, policy_version 89993 (0.0008) -[2023-10-09 11:53:39,479][23468] Updated weights for policy 0, policy_version 90003 (0.0008) -[2023-10-09 11:53:39,839][23468] Updated weights for policy 0, policy_version 90013 (0.0011) -[2023-10-09 11:53:41,062][23469] Updated weights for policy 1, policy_version 90501 (0.0010) -[2023-10-09 11:53:41,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 184844288. Throughput: 0: 1807.4, 1: 1802.6. Samples: 46219404. Policy #0 lag: (min: 7.0, avg: 10.6, max: 39.0) -[2023-10-09 11:53:41,079][22500] Avg episode reward: [(0, '10.750'), (1, '10.390')] -[2023-10-09 11:53:41,421][23469] Updated weights for policy 1, policy_version 90511 (0.0011) -[2023-10-09 11:53:41,797][23469] Updated weights for policy 1, policy_version 90521 (0.0009) -[2023-10-09 11:53:43,695][23468] Updated weights for policy 0, policy_version 90023 (0.0010) -[2023-10-09 11:53:44,073][23468] Updated weights for policy 0, policy_version 90033 (0.0009) -[2023-10-09 11:53:44,441][23468] Updated weights for policy 0, policy_version 90043 (0.0009) -[2023-10-09 11:53:45,518][23469] Updated weights for policy 1, policy_version 90531 (0.0008) -[2023-10-09 11:53:45,901][23469] Updated weights for policy 1, policy_version 90541 (0.0008) -[2023-10-09 11:53:46,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 184909824. Throughput: 0: 1790.8, 1: 1811.7. Samples: 46240558. Policy #0 lag: (min: 7.0, avg: 10.6, max: 39.0) -[2023-10-09 11:53:46,078][22500] Avg episode reward: [(0, '9.990'), (1, '10.080')] -[2023-10-09 11:53:46,272][23469] Updated weights for policy 1, policy_version 90551 (0.0008) -[2023-10-09 11:53:48,276][23468] Updated weights for policy 0, policy_version 90053 (0.0009) -[2023-10-09 11:53:48,647][23468] Updated weights for policy 0, policy_version 90063 (0.0010) -[2023-10-09 11:53:49,029][23468] Updated weights for policy 0, policy_version 90073 (0.0010) -[2023-10-09 11:53:49,861][23469] Updated weights for policy 1, policy_version 90561 (0.0008) -[2023-10-09 11:53:50,231][23469] Updated weights for policy 1, policy_version 90571 (0.0008) -[2023-10-09 11:53:50,600][23469] Updated weights for policy 1, policy_version 90581 (0.0007) -[2023-10-09 11:53:50,971][23469] Updated weights for policy 1, policy_version 90591 (0.0009) -[2023-10-09 11:53:51,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 185008128. Throughput: 0: 1813.1, 1: 1798.4. Samples: 46252080. Policy #0 lag: (min: 7.0, avg: 10.6, max: 39.0) -[2023-10-09 11:53:51,078][22500] Avg episode reward: [(0, '10.160'), (1, '9.670')] -[2023-10-09 11:53:52,741][23468] Updated weights for policy 0, policy_version 90083 (0.0008) -[2023-10-09 11:53:53,114][23468] Updated weights for policy 0, policy_version 90093 (0.0007) -[2023-10-09 11:53:53,484][23468] Updated weights for policy 0, policy_version 90103 (0.0008) -[2023-10-09 11:53:54,770][23469] Updated weights for policy 1, policy_version 90601 (0.0010) -[2023-10-09 11:53:55,130][23469] Updated weights for policy 1, policy_version 90611 (0.0010) -[2023-10-09 11:53:55,500][23469] Updated weights for policy 1, policy_version 90621 (0.0010) -[2023-10-09 11:53:56,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 185073664. Throughput: 0: 1792.7, 1: 1811.7. Samples: 46273018. Policy #0 lag: (min: 7.0, avg: 10.6, max: 39.0) -[2023-10-09 11:53:56,078][22500] Avg episode reward: [(0, '9.800'), (1, '9.960')] -[2023-10-09 11:53:57,237][23468] Updated weights for policy 0, policy_version 90113 (0.0007) -[2023-10-09 11:53:57,662][23468] Updated weights for policy 0, policy_version 90123 (0.0007) -[2023-10-09 11:53:58,044][23468] Updated weights for policy 0, policy_version 90133 (0.0008) -[2023-10-09 11:53:58,414][23468] Updated weights for policy 0, policy_version 90143 (0.0010) -[2023-10-09 11:53:59,273][23469] Updated weights for policy 1, policy_version 90631 (0.0007) -[2023-10-09 11:53:59,636][23469] Updated weights for policy 1, policy_version 90641 (0.0007) -[2023-10-09 11:54:00,000][23469] Updated weights for policy 1, policy_version 90651 (0.0007) -[2023-10-09 11:54:01,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 185139200. Throughput: 0: 1781.5, 1: 1803.1. Samples: 46294174. Policy #0 lag: (min: 7.0, avg: 10.6, max: 39.0) -[2023-10-09 11:54:01,079][22500] Avg episode reward: [(0, '10.540'), (1, '10.040')] -[2023-10-09 11:54:02,047][23468] Updated weights for policy 0, policy_version 90153 (0.0012) -[2023-10-09 11:54:02,414][23468] Updated weights for policy 0, policy_version 90163 (0.0011) -[2023-10-09 11:54:02,787][23468] Updated weights for policy 0, policy_version 90173 (0.0007) -[2023-10-09 11:54:03,731][23469] Updated weights for policy 1, policy_version 90661 (0.0008) -[2023-10-09 11:54:04,102][23469] Updated weights for policy 1, policy_version 90671 (0.0008) -[2023-10-09 11:54:04,483][23469] Updated weights for policy 1, policy_version 90681 (0.0008) -[2023-10-09 11:54:06,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 185204736. Throughput: 0: 1781.7, 1: 1805.9. Samples: 46304912. Policy #0 lag: (min: 7.0, avg: 10.6, max: 39.0) -[2023-10-09 11:54:06,078][22500] Avg episode reward: [(0, '10.910'), (1, '9.880')] -[2023-10-09 11:54:06,505][23468] Updated weights for policy 0, policy_version 90183 (0.0008) -[2023-10-09 11:54:06,888][23468] Updated weights for policy 0, policy_version 90193 (0.0007) -[2023-10-09 11:54:07,260][23468] Updated weights for policy 0, policy_version 90203 (0.0007) -[2023-10-09 11:54:08,401][23469] Updated weights for policy 1, policy_version 90691 (0.0007) -[2023-10-09 11:54:08,771][23469] Updated weights for policy 1, policy_version 90701 (0.0008) -[2023-10-09 11:54:09,145][23469] Updated weights for policy 1, policy_version 90711 (0.0012) -[2023-10-09 11:54:11,077][22500] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 185270272. Throughput: 0: 1777.9, 1: 1800.2. Samples: 46326014. Policy #0 lag: (min: 7.0, avg: 10.6, max: 39.0) -[2023-10-09 11:54:11,078][22500] Avg episode reward: [(0, '10.510'), (1, '10.490')] -[2023-10-09 11:54:11,097][23468] Updated weights for policy 0, policy_version 90213 (0.0008) -[2023-10-09 11:54:11,472][23468] Updated weights for policy 0, policy_version 90223 (0.0007) -[2023-10-09 11:54:11,851][23468] Updated weights for policy 0, policy_version 90233 (0.0007) -[2023-10-09 11:54:13,109][23469] Updated weights for policy 1, policy_version 90721 (0.0009) -[2023-10-09 11:54:13,477][23469] Updated weights for policy 1, policy_version 90731 (0.0007) -[2023-10-09 11:54:13,856][23469] Updated weights for policy 1, policy_version 90741 (0.0008) -[2023-10-09 11:54:14,231][23469] Updated weights for policy 1, policy_version 90751 (0.0008) -[2023-10-09 11:54:15,556][23468] Updated weights for policy 0, policy_version 90243 (0.0010) -[2023-10-09 11:54:15,924][23468] Updated weights for policy 0, policy_version 90253 (0.0010) -[2023-10-09 11:54:16,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 185335808. Throughput: 0: 1795.8, 1: 1791.2. Samples: 46348244. Policy #0 lag: (min: 7.0, avg: 10.6, max: 39.0) -[2023-10-09 11:54:16,078][22500] Avg episode reward: [(0, '10.580'), (1, '10.170')] -[2023-10-09 11:54:16,087][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000090752_92930048.pth... -[2023-10-09 11:54:16,115][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000089056_91193344.pth -[2023-10-09 11:54:16,304][23468] Updated weights for policy 0, policy_version 90263 (0.0010) -[2023-10-09 11:54:16,629][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000090272_92438528.pth... -[2023-10-09 11:54:16,657][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000088576_90701824.pth -[2023-10-09 11:54:17,859][23469] Updated weights for policy 1, policy_version 90761 (0.0009) -[2023-10-09 11:54:18,236][23469] Updated weights for policy 1, policy_version 90771 (0.0009) -[2023-10-09 11:54:18,603][23469] Updated weights for policy 1, policy_version 90781 (0.0008) -[2023-10-09 11:54:19,969][23468] Updated weights for policy 0, policy_version 90273 (0.0008) -[2023-10-09 11:54:20,342][23468] Updated weights for policy 0, policy_version 90283 (0.0008) -[2023-10-09 11:54:20,716][23468] Updated weights for policy 0, policy_version 90293 (0.0009) -[2023-10-09 11:54:21,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 185401344. Throughput: 0: 1779.4, 1: 1790.7. Samples: 46358080. Policy #0 lag: (min: 7.0, avg: 10.6, max: 39.0) -[2023-10-09 11:54:21,078][22500] Avg episode reward: [(0, '10.260'), (1, '10.360')] -[2023-10-09 11:54:21,086][23468] Updated weights for policy 0, policy_version 90303 (0.0008) -[2023-10-09 11:54:22,370][23469] Updated weights for policy 1, policy_version 90791 (0.0009) -[2023-10-09 11:54:22,735][23469] Updated weights for policy 1, policy_version 90801 (0.0007) -[2023-10-09 11:54:23,109][23469] Updated weights for policy 1, policy_version 90811 (0.0008) -[2023-10-09 11:54:24,870][23468] Updated weights for policy 0, policy_version 90313 (0.0008) -[2023-10-09 11:54:25,234][23468] Updated weights for policy 0, policy_version 90323 (0.0007) -[2023-10-09 11:54:25,604][23468] Updated weights for policy 0, policy_version 90333 (0.0008) -[2023-10-09 11:54:26,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 185499648. Throughput: 0: 1791.7, 1: 1783.7. Samples: 46380300. Policy #0 lag: (min: 7.0, avg: 10.6, max: 39.0) -[2023-10-09 11:54:26,078][22500] Avg episode reward: [(0, '10.150'), (1, '10.320')] -[2023-10-09 11:54:27,012][23469] Updated weights for policy 1, policy_version 90821 (0.0007) -[2023-10-09 11:54:27,373][23469] Updated weights for policy 1, policy_version 90831 (0.0007) -[2023-10-09 11:54:27,739][23469] Updated weights for policy 1, policy_version 90841 (0.0007) -[2023-10-09 11:54:29,484][23468] Updated weights for policy 0, policy_version 90343 (0.0007) -[2023-10-09 11:54:29,858][23468] Updated weights for policy 0, policy_version 90353 (0.0010) -[2023-10-09 11:54:30,223][23468] Updated weights for policy 0, policy_version 90363 (0.0007) -[2023-10-09 11:54:31,078][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 185565184. Throughput: 0: 1782.1, 1: 1791.4. Samples: 46401366. Policy #0 lag: (min: 1.0, avg: 2.1, max: 18.0) -[2023-10-09 11:54:31,079][22500] Avg episode reward: [(0, '11.220'), (1, '10.150')] -[2023-10-09 11:54:31,446][23469] Updated weights for policy 1, policy_version 90851 (0.0010) -[2023-10-09 11:54:31,842][23469] Updated weights for policy 1, policy_version 90861 (0.0009) -[2023-10-09 11:54:32,202][23469] Updated weights for policy 1, policy_version 90871 (0.0008) -[2023-10-09 11:54:33,829][23468] Updated weights for policy 0, policy_version 90373 (0.0007) -[2023-10-09 11:54:34,200][23468] Updated weights for policy 0, policy_version 90383 (0.0007) -[2023-10-09 11:54:34,580][23468] Updated weights for policy 0, policy_version 90393 (0.0010) -[2023-10-09 11:54:35,873][23469] Updated weights for policy 1, policy_version 90881 (0.0008) -[2023-10-09 11:54:36,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 185630720. Throughput: 0: 1784.9, 1: 1776.8. Samples: 46412358. Policy #0 lag: (min: 1.0, avg: 2.1, max: 18.0) -[2023-10-09 11:54:36,078][22500] Avg episode reward: [(0, '11.040'), (1, '10.190')] -[2023-10-09 11:54:36,239][23469] Updated weights for policy 1, policy_version 90891 (0.0010) -[2023-10-09 11:54:36,609][23469] Updated weights for policy 1, policy_version 90901 (0.0011) -[2023-10-09 11:54:36,974][23469] Updated weights for policy 1, policy_version 90911 (0.0010) -[2023-10-09 11:54:38,207][23468] Updated weights for policy 0, policy_version 90403 (0.0010) -[2023-10-09 11:54:38,576][23468] Updated weights for policy 0, policy_version 90413 (0.0009) -[2023-10-09 11:54:38,946][23468] Updated weights for policy 0, policy_version 90423 (0.0010) -[2023-10-09 11:54:40,765][23469] Updated weights for policy 1, policy_version 90921 (0.0008) -[2023-10-09 11:54:41,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 185696256. Throughput: 0: 1784.4, 1: 1784.1. Samples: 46433602. Policy #0 lag: (min: 1.0, avg: 2.1, max: 18.0) -[2023-10-09 11:54:41,078][22500] Avg episode reward: [(0, '11.050'), (1, '9.400')] -[2023-10-09 11:54:41,132][23469] Updated weights for policy 1, policy_version 90931 (0.0009) -[2023-10-09 11:54:41,506][23469] Updated weights for policy 1, policy_version 90941 (0.0011) -[2023-10-09 11:54:42,840][23468] Updated weights for policy 0, policy_version 90433 (0.0008) -[2023-10-09 11:54:43,235][23468] Updated weights for policy 0, policy_version 90443 (0.0008) -[2023-10-09 11:54:43,609][23468] Updated weights for policy 0, policy_version 90453 (0.0009) -[2023-10-09 11:54:43,986][23468] Updated weights for policy 0, policy_version 90463 (0.0008) -[2023-10-09 11:54:45,257][23469] Updated weights for policy 1, policy_version 90951 (0.0009) -[2023-10-09 11:54:45,621][23469] Updated weights for policy 1, policy_version 90961 (0.0007) -[2023-10-09 11:54:46,003][23469] Updated weights for policy 1, policy_version 90971 (0.0007) -[2023-10-09 11:54:46,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 185761792. Throughput: 0: 1785.6, 1: 1791.1. Samples: 46455124. Policy #0 lag: (min: 1.0, avg: 2.1, max: 18.0) -[2023-10-09 11:54:46,078][22500] Avg episode reward: [(0, '10.840'), (1, '10.180')] -[2023-10-09 11:54:47,816][23468] Updated weights for policy 0, policy_version 90473 (0.0007) -[2023-10-09 11:54:48,196][23468] Updated weights for policy 0, policy_version 90483 (0.0010) -[2023-10-09 11:54:48,561][23468] Updated weights for policy 0, policy_version 90493 (0.0008) -[2023-10-09 11:54:49,674][23469] Updated weights for policy 1, policy_version 90981 (0.0008) -[2023-10-09 11:54:50,032][23469] Updated weights for policy 1, policy_version 90991 (0.0008) -[2023-10-09 11:54:50,408][23469] Updated weights for policy 1, policy_version 91001 (0.0008) -[2023-10-09 11:54:51,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 185860096. Throughput: 0: 1798.2, 1: 1787.1. Samples: 46466248. Policy #0 lag: (min: 1.0, avg: 2.1, max: 18.0) -[2023-10-09 11:54:51,078][22500] Avg episode reward: [(0, '10.490'), (1, '10.250')] -[2023-10-09 11:54:52,270][23468] Updated weights for policy 0, policy_version 90503 (0.0008) -[2023-10-09 11:54:52,655][23468] Updated weights for policy 0, policy_version 90513 (0.0009) -[2023-10-09 11:54:53,020][23468] Updated weights for policy 0, policy_version 90523 (0.0008) -[2023-10-09 11:54:54,193][23469] Updated weights for policy 1, policy_version 91011 (0.0011) -[2023-10-09 11:54:54,561][23469] Updated weights for policy 1, policy_version 91021 (0.0008) -[2023-10-09 11:54:54,938][23469] Updated weights for policy 1, policy_version 91031 (0.0007) -[2023-10-09 11:54:56,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 185925632. Throughput: 0: 1785.3, 1: 1795.9. Samples: 46487168. Policy #0 lag: (min: 1.0, avg: 2.1, max: 18.0) -[2023-10-09 11:54:56,078][22500] Avg episode reward: [(0, '9.910'), (1, '9.680')] -[2023-10-09 11:54:56,867][23468] Updated weights for policy 0, policy_version 90533 (0.0009) -[2023-10-09 11:54:57,240][23468] Updated weights for policy 0, policy_version 90543 (0.0011) -[2023-10-09 11:54:57,626][23468] Updated weights for policy 0, policy_version 90553 (0.0010) -[2023-10-09 11:54:58,505][23469] Updated weights for policy 1, policy_version 91041 (0.0009) -[2023-10-09 11:54:58,877][23469] Updated weights for policy 1, policy_version 91051 (0.0007) -[2023-10-09 11:54:59,252][23469] Updated weights for policy 1, policy_version 91061 (0.0009) -[2023-10-09 11:54:59,624][23469] Updated weights for policy 1, policy_version 91071 (0.0009) -[2023-10-09 11:55:01,078][22500] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 185991168. Throughput: 0: 1785.4, 1: 1790.2. Samples: 46509148. Policy #0 lag: (min: 1.0, avg: 2.1, max: 18.0) -[2023-10-09 11:55:01,079][22500] Avg episode reward: [(0, '10.210'), (1, '9.440')] -[2023-10-09 11:55:01,278][23468] Updated weights for policy 0, policy_version 90563 (0.0009) -[2023-10-09 11:55:01,655][23468] Updated weights for policy 0, policy_version 90573 (0.0008) -[2023-10-09 11:55:02,027][23468] Updated weights for policy 0, policy_version 90583 (0.0007) -[2023-10-09 11:55:03,456][23469] Updated weights for policy 1, policy_version 91081 (0.0008) -[2023-10-09 11:55:03,827][23469] Updated weights for policy 1, policy_version 91091 (0.0009) -[2023-10-09 11:55:04,191][23469] Updated weights for policy 1, policy_version 91101 (0.0009) -[2023-10-09 11:55:05,786][23468] Updated weights for policy 0, policy_version 90593 (0.0007) -[2023-10-09 11:55:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 186056704. Throughput: 0: 1782.8, 1: 1804.4. Samples: 46519500. Policy #0 lag: (min: 1.0, avg: 2.1, max: 18.0) -[2023-10-09 11:55:06,078][22500] Avg episode reward: [(0, '10.920'), (1, '9.100')] -[2023-10-09 11:55:06,157][23468] Updated weights for policy 0, policy_version 90603 (0.0008) -[2023-10-09 11:55:06,531][23468] Updated weights for policy 0, policy_version 90613 (0.0007) -[2023-10-09 11:55:06,904][23468] Updated weights for policy 0, policy_version 90623 (0.0007) -[2023-10-09 11:55:07,764][23469] Updated weights for policy 1, policy_version 91111 (0.0007) -[2023-10-09 11:55:08,139][23469] Updated weights for policy 1, policy_version 91121 (0.0008) -[2023-10-09 11:55:08,506][23469] Updated weights for policy 1, policy_version 91131 (0.0009) -[2023-10-09 11:55:10,636][23468] Updated weights for policy 0, policy_version 90633 (0.0008) -[2023-10-09 11:55:11,015][23468] Updated weights for policy 0, policy_version 90643 (0.0010) -[2023-10-09 11:55:11,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 186122240. Throughput: 0: 1782.3, 1: 1799.8. Samples: 46541494. Policy #0 lag: (min: 1.0, avg: 2.1, max: 18.0) -[2023-10-09 11:55:11,078][22500] Avg episode reward: [(0, '10.470'), (1, '9.810')] -[2023-10-09 11:55:11,380][23468] Updated weights for policy 0, policy_version 90653 (0.0010) -[2023-10-09 11:55:12,315][23469] Updated weights for policy 1, policy_version 91141 (0.0008) -[2023-10-09 11:55:12,684][23469] Updated weights for policy 1, policy_version 91151 (0.0007) -[2023-10-09 11:55:13,055][23469] Updated weights for policy 1, policy_version 91161 (0.0007) -[2023-10-09 11:55:15,236][23468] Updated weights for policy 0, policy_version 90663 (0.0010) -[2023-10-09 11:55:15,607][23468] Updated weights for policy 0, policy_version 90673 (0.0010) -[2023-10-09 11:55:15,975][23468] Updated weights for policy 0, policy_version 90683 (0.0010) -[2023-10-09 11:55:16,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 186187776. Throughput: 0: 1798.7, 1: 1797.3. Samples: 46563186. Policy #0 lag: (min: 1.0, avg: 2.1, max: 18.0) -[2023-10-09 11:55:16,078][22500] Avg episode reward: [(0, '11.070'), (1, '9.350')] -[2023-10-09 11:55:16,808][23469] Updated weights for policy 1, policy_version 91171 (0.0008) -[2023-10-09 11:55:17,175][23469] Updated weights for policy 1, policy_version 91181 (0.0011) -[2023-10-09 11:55:17,550][23469] Updated weights for policy 1, policy_version 91191 (0.0010) -[2023-10-09 11:55:19,793][23468] Updated weights for policy 0, policy_version 90693 (0.0009) -[2023-10-09 11:55:20,164][23468] Updated weights for policy 0, policy_version 90703 (0.0007) -[2023-10-09 11:55:20,533][23468] Updated weights for policy 0, policy_version 90713 (0.0010) -[2023-10-09 11:55:21,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 186286080. Throughput: 0: 1777.5, 1: 1798.9. Samples: 46573294. Policy #0 lag: (min: 1.0, avg: 2.1, max: 18.0) -[2023-10-09 11:55:21,078][22500] Avg episode reward: [(0, '10.220'), (1, '10.120')] -[2023-10-09 11:55:21,483][23469] Updated weights for policy 1, policy_version 91201 (0.0010) -[2023-10-09 11:55:21,850][23469] Updated weights for policy 1, policy_version 91211 (0.0008) -[2023-10-09 11:55:22,219][23469] Updated weights for policy 1, policy_version 91221 (0.0008) -[2023-10-09 11:55:22,593][23469] Updated weights for policy 1, policy_version 91231 (0.0011) -[2023-10-09 11:55:24,296][23468] Updated weights for policy 0, policy_version 90723 (0.0008) -[2023-10-09 11:55:24,665][23468] Updated weights for policy 0, policy_version 90733 (0.0008) -[2023-10-09 11:55:25,032][23468] Updated weights for policy 0, policy_version 90743 (0.0007) -[2023-10-09 11:55:26,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 186351616. Throughput: 0: 1798.7, 1: 1797.6. Samples: 46595432. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-09 11:55:26,078][22500] Avg episode reward: [(0, '10.230'), (1, '10.540')] -[2023-10-09 11:55:26,203][23469] Updated weights for policy 1, policy_version 91241 (0.0007) -[2023-10-09 11:55:26,576][23469] Updated weights for policy 1, policy_version 91251 (0.0008) -[2023-10-09 11:55:26,947][23469] Updated weights for policy 1, policy_version 91261 (0.0009) -[2023-10-09 11:55:28,921][23468] Updated weights for policy 0, policy_version 90753 (0.0009) -[2023-10-09 11:55:29,317][23468] Updated weights for policy 0, policy_version 90763 (0.0007) -[2023-10-09 11:55:29,696][23468] Updated weights for policy 0, policy_version 90773 (0.0009) -[2023-10-09 11:55:30,057][23468] Updated weights for policy 0, policy_version 90783 (0.0008) -[2023-10-09 11:55:30,682][23469] Updated weights for policy 1, policy_version 91271 (0.0010) -[2023-10-09 11:55:31,048][23469] Updated weights for policy 1, policy_version 91281 (0.0010) -[2023-10-09 11:55:31,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 186417152. Throughput: 0: 1771.2, 1: 1805.1. Samples: 46616060. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-09 11:55:31,078][22500] Avg episode reward: [(0, '10.430'), (1, '10.480')] -[2023-10-09 11:55:31,433][23469] Updated weights for policy 1, policy_version 91291 (0.0009) -[2023-10-09 11:55:33,628][23468] Updated weights for policy 0, policy_version 90793 (0.0008) -[2023-10-09 11:55:34,001][23468] Updated weights for policy 0, policy_version 90803 (0.0010) -[2023-10-09 11:55:34,372][23468] Updated weights for policy 0, policy_version 90813 (0.0009) -[2023-10-09 11:55:35,167][23469] Updated weights for policy 1, policy_version 91301 (0.0009) -[2023-10-09 11:55:35,546][23469] Updated weights for policy 1, policy_version 91311 (0.0008) -[2023-10-09 11:55:35,913][23469] Updated weights for policy 1, policy_version 91321 (0.0007) -[2023-10-09 11:55:36,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 186482688. Throughput: 0: 1798.8, 1: 1792.9. Samples: 46627876. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-09 11:55:36,078][22500] Avg episode reward: [(0, '10.490'), (1, '10.920')] -[2023-10-09 11:55:36,169][23343] Saving new best policy, reward=10.920! -[2023-10-09 11:55:38,235][23468] Updated weights for policy 0, policy_version 90823 (0.0009) -[2023-10-09 11:55:38,610][23468] Updated weights for policy 0, policy_version 90833 (0.0009) -[2023-10-09 11:55:38,987][23468] Updated weights for policy 0, policy_version 90843 (0.0010) -[2023-10-09 11:55:39,595][23469] Updated weights for policy 1, policy_version 91331 (0.0007) -[2023-10-09 11:55:39,961][23469] Updated weights for policy 1, policy_version 91341 (0.0010) -[2023-10-09 11:55:40,337][23469] Updated weights for policy 1, policy_version 91351 (0.0009) -[2023-10-09 11:55:41,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 186580992. Throughput: 0: 1777.7, 1: 1814.6. Samples: 46648822. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-09 11:55:41,078][22500] Avg episode reward: [(0, '11.740'), (1, '10.220')] -[2023-10-09 11:55:42,949][23468] Updated weights for policy 0, policy_version 90853 (0.0009) -[2023-10-09 11:55:43,317][23468] Updated weights for policy 0, policy_version 90863 (0.0007) -[2023-10-09 11:55:43,696][23468] Updated weights for policy 0, policy_version 90873 (0.0007) -[2023-10-09 11:55:43,973][23469] Updated weights for policy 1, policy_version 91361 (0.0008) -[2023-10-09 11:55:44,344][23469] Updated weights for policy 1, policy_version 91371 (0.0007) -[2023-10-09 11:55:44,720][23469] Updated weights for policy 1, policy_version 91381 (0.0008) -[2023-10-09 11:55:45,093][23469] Updated weights for policy 1, policy_version 91391 (0.0008) -[2023-10-09 11:55:46,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 186646528. Throughput: 0: 1778.2, 1: 1803.0. Samples: 46670302. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-09 11:55:46,078][22500] Avg episode reward: [(0, '10.850'), (1, '9.630')] -[2023-10-09 11:55:47,357][23468] Updated weights for policy 0, policy_version 90883 (0.0009) -[2023-10-09 11:55:47,725][23468] Updated weights for policy 0, policy_version 90893 (0.0008) -[2023-10-09 11:55:48,098][23468] Updated weights for policy 0, policy_version 90903 (0.0008) -[2023-10-09 11:55:48,856][23469] Updated weights for policy 1, policy_version 91401 (0.0009) -[2023-10-09 11:55:49,234][23469] Updated weights for policy 1, policy_version 91411 (0.0009) -[2023-10-09 11:55:49,603][23469] Updated weights for policy 1, policy_version 91421 (0.0011) -[2023-10-09 11:55:51,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 186712064. Throughput: 0: 1785.5, 1: 1812.1. Samples: 46681390. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-09 11:55:51,078][22500] Avg episode reward: [(0, '10.580'), (1, '10.360')] -[2023-10-09 11:55:52,048][23468] Updated weights for policy 0, policy_version 90913 (0.0010) -[2023-10-09 11:55:52,420][23468] Updated weights for policy 0, policy_version 90923 (0.0007) -[2023-10-09 11:55:52,783][23468] Updated weights for policy 0, policy_version 90933 (0.0009) -[2023-10-09 11:55:53,163][23468] Updated weights for policy 0, policy_version 90943 (0.0008) -[2023-10-09 11:55:53,399][23469] Updated weights for policy 1, policy_version 91431 (0.0007) -[2023-10-09 11:55:53,771][23469] Updated weights for policy 1, policy_version 91441 (0.0008) -[2023-10-09 11:55:54,137][23469] Updated weights for policy 1, policy_version 91451 (0.0008) -[2023-10-09 11:55:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 186777600. Throughput: 0: 1774.8, 1: 1794.7. Samples: 46702120. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-09 11:55:56,078][22500] Avg episode reward: [(0, '10.240'), (1, '9.520')] -[2023-10-09 11:55:56,785][23468] Updated weights for policy 0, policy_version 90953 (0.0010) -[2023-10-09 11:55:57,156][23468] Updated weights for policy 0, policy_version 90963 (0.0008) -[2023-10-09 11:55:57,524][23468] Updated weights for policy 0, policy_version 90973 (0.0009) -[2023-10-09 11:55:57,984][23469] Updated weights for policy 1, policy_version 91461 (0.0008) -[2023-10-09 11:55:58,352][23469] Updated weights for policy 1, policy_version 91471 (0.0008) -[2023-10-09 11:55:58,723][23469] Updated weights for policy 1, policy_version 91481 (0.0007) -[2023-10-09 11:56:01,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.6, 300 sec: 14329.1). Total num frames: 186843136. Throughput: 0: 1788.1, 1: 1801.8. Samples: 46724734. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-09 11:56:01,078][22500] Avg episode reward: [(0, '10.040'), (1, '9.700')] -[2023-10-09 11:56:01,251][23468] Updated weights for policy 0, policy_version 90983 (0.0008) -[2023-10-09 11:56:01,632][23468] Updated weights for policy 0, policy_version 90993 (0.0008) -[2023-10-09 11:56:01,997][23468] Updated weights for policy 0, policy_version 91003 (0.0008) -[2023-10-09 11:56:02,501][23469] Updated weights for policy 1, policy_version 91491 (0.0008) -[2023-10-09 11:56:02,895][23469] Updated weights for policy 1, policy_version 91501 (0.0007) -[2023-10-09 11:56:03,272][23469] Updated weights for policy 1, policy_version 91511 (0.0009) -[2023-10-09 11:56:05,727][23468] Updated weights for policy 0, policy_version 91013 (0.0010) -[2023-10-09 11:56:06,078][22500] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 186908672. Throughput: 0: 1779.6, 1: 1803.7. Samples: 46734546. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-09 11:56:06,079][22500] Avg episode reward: [(0, '10.740'), (1, '9.320')] -[2023-10-09 11:56:06,096][23468] Updated weights for policy 0, policy_version 91023 (0.0009) -[2023-10-09 11:56:06,474][23468] Updated weights for policy 0, policy_version 91033 (0.0010) -[2023-10-09 11:56:06,989][23469] Updated weights for policy 1, policy_version 91521 (0.0010) -[2023-10-09 11:56:07,358][23469] Updated weights for policy 1, policy_version 91531 (0.0010) -[2023-10-09 11:56:07,726][23469] Updated weights for policy 1, policy_version 91541 (0.0009) -[2023-10-09 11:56:08,097][23469] Updated weights for policy 1, policy_version 91551 (0.0008) -[2023-10-09 11:56:10,290][23468] Updated weights for policy 0, policy_version 91043 (0.0010) -[2023-10-09 11:56:10,664][23468] Updated weights for policy 0, policy_version 91053 (0.0009) -[2023-10-09 11:56:11,039][23468] Updated weights for policy 0, policy_version 91063 (0.0007) -[2023-10-09 11:56:11,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 186974208. Throughput: 0: 1780.9, 1: 1806.3. Samples: 46756856. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-09 11:56:11,078][22500] Avg episode reward: [(0, '10.670'), (1, '9.590')] -[2023-10-09 11:56:11,932][23469] Updated weights for policy 1, policy_version 91561 (0.0010) -[2023-10-09 11:56:12,303][23469] Updated weights for policy 1, policy_version 91571 (0.0008) -[2023-10-09 11:56:12,669][23469] Updated weights for policy 1, policy_version 91581 (0.0007) -[2023-10-09 11:56:14,958][23468] Updated weights for policy 0, policy_version 91073 (0.0009) -[2023-10-09 11:56:15,322][23468] Updated weights for policy 0, policy_version 91083 (0.0009) -[2023-10-09 11:56:15,695][23468] Updated weights for policy 0, policy_version 91093 (0.0008) -[2023-10-09 11:56:16,075][23468] Updated weights for policy 0, policy_version 91103 (0.0007) -[2023-10-09 11:56:16,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 187039744. Throughput: 0: 1794.8, 1: 1814.7. Samples: 46778486. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-09 11:56:16,078][22500] Avg episode reward: [(0, '9.880'), (1, '10.250')] -[2023-10-09 11:56:16,104][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000091104_93290496.pth... -[2023-10-09 11:56:16,138][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000089408_91553792.pth -[2023-10-09 11:56:16,142][23265] Saving a milestone ./train_atari/atari_berzerk_APPO/checkpoint_p0/milestones/checkpoint_000091104_93290496.pth -[2023-10-09 11:56:16,420][23469] Updated weights for policy 1, policy_version 91591 (0.0008) -[2023-10-09 11:56:16,785][23469] Updated weights for policy 1, policy_version 91601 (0.0008) -[2023-10-09 11:56:17,155][23469] Updated weights for policy 1, policy_version 91611 (0.0008) -[2023-10-09 11:56:17,333][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000091616_93814784.pth... -[2023-10-09 11:56:17,371][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000089920_92078080.pth -[2023-10-09 11:56:17,376][23343] Saving a milestone ./train_atari/atari_berzerk_APPO/checkpoint_p1/milestones/checkpoint_000091616_93814784.pth -[2023-10-09 11:56:19,575][23468] Updated weights for policy 0, policy_version 91113 (0.0007) -[2023-10-09 11:56:19,946][23468] Updated weights for policy 0, policy_version 91123 (0.0007) -[2023-10-09 11:56:20,329][23468] Updated weights for policy 0, policy_version 91133 (0.0008) -[2023-10-09 11:56:20,884][23469] Updated weights for policy 1, policy_version 91621 (0.0010) -[2023-10-09 11:56:21,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 187138048. Throughput: 0: 1772.0, 1: 1802.3. Samples: 46788720. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-09 11:56:21,078][22500] Avg episode reward: [(0, '10.020'), (1, '9.370')] -[2023-10-09 11:56:21,253][23469] Updated weights for policy 1, policy_version 91631 (0.0010) -[2023-10-09 11:56:21,627][23469] Updated weights for policy 1, policy_version 91641 (0.0007) -[2023-10-09 11:56:24,107][23468] Updated weights for policy 0, policy_version 91143 (0.0007) -[2023-10-09 11:56:24,477][23468] Updated weights for policy 0, policy_version 91153 (0.0009) -[2023-10-09 11:56:24,856][23468] Updated weights for policy 0, policy_version 91163 (0.0010) -[2023-10-09 11:56:25,356][23469] Updated weights for policy 1, policy_version 91651 (0.0008) -[2023-10-09 11:56:25,723][23469] Updated weights for policy 1, policy_version 91661 (0.0009) -[2023-10-09 11:56:26,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 187203584. Throughput: 0: 1796.1, 1: 1799.4. Samples: 46810620. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:56:26,078][22500] Avg episode reward: [(0, '10.480'), (1, '9.840')] -[2023-10-09 11:56:26,089][23469] Updated weights for policy 1, policy_version 91671 (0.0007) -[2023-10-09 11:56:28,493][23468] Updated weights for policy 0, policy_version 91173 (0.0009) -[2023-10-09 11:56:28,866][23468] Updated weights for policy 0, policy_version 91183 (0.0010) -[2023-10-09 11:56:29,238][23468] Updated weights for policy 0, policy_version 91193 (0.0008) -[2023-10-09 11:56:29,860][23469] Updated weights for policy 1, policy_version 91681 (0.0007) -[2023-10-09 11:56:30,224][23469] Updated weights for policy 1, policy_version 91691 (0.0007) -[2023-10-09 11:56:30,591][23469] Updated weights for policy 1, policy_version 91701 (0.0008) -[2023-10-09 11:56:30,963][23469] Updated weights for policy 1, policy_version 91711 (0.0010) -[2023-10-09 11:56:31,078][22500] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 187301888. Throughput: 0: 1777.5, 1: 1799.5. Samples: 46831268. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:56:31,079][22500] Avg episode reward: [(0, '10.710'), (1, '9.070')] -[2023-10-09 11:56:33,059][23468] Updated weights for policy 0, policy_version 91203 (0.0008) -[2023-10-09 11:56:33,431][23468] Updated weights for policy 0, policy_version 91213 (0.0008) -[2023-10-09 11:56:33,806][23468] Updated weights for policy 0, policy_version 91223 (0.0008) -[2023-10-09 11:56:34,540][23469] Updated weights for policy 1, policy_version 91721 (0.0009) -[2023-10-09 11:56:34,895][23469] Updated weights for policy 1, policy_version 91731 (0.0010) -[2023-10-09 11:56:35,269][23469] Updated weights for policy 1, policy_version 91741 (0.0008) -[2023-10-09 11:56:36,078][22500] Fps is (10 sec: 16383.4, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 187367424. Throughput: 0: 1794.7, 1: 1803.1. Samples: 46843292. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:56:36,079][22500] Avg episode reward: [(0, '11.650'), (1, '9.120')] -[2023-10-09 11:56:37,576][23468] Updated weights for policy 0, policy_version 91233 (0.0011) -[2023-10-09 11:56:37,947][23468] Updated weights for policy 0, policy_version 91243 (0.0008) -[2023-10-09 11:56:38,314][23468] Updated weights for policy 0, policy_version 91253 (0.0007) -[2023-10-09 11:56:38,687][23468] Updated weights for policy 0, policy_version 91263 (0.0010) -[2023-10-09 11:56:38,899][23469] Updated weights for policy 1, policy_version 91751 (0.0008) -[2023-10-09 11:56:39,266][23469] Updated weights for policy 1, policy_version 91761 (0.0008) -[2023-10-09 11:56:39,641][23469] Updated weights for policy 1, policy_version 91771 (0.0008) -[2023-10-09 11:56:41,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 187432960. Throughput: 0: 1783.9, 1: 1802.2. Samples: 46863494. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:56:41,078][22500] Avg episode reward: [(0, '11.270'), (1, '9.880')] -[2023-10-09 11:56:42,563][23468] Updated weights for policy 0, policy_version 91273 (0.0007) -[2023-10-09 11:56:42,936][23468] Updated weights for policy 0, policy_version 91283 (0.0007) -[2023-10-09 11:56:43,311][23468] Updated weights for policy 0, policy_version 91293 (0.0007) -[2023-10-09 11:56:43,426][23469] Updated weights for policy 1, policy_version 91781 (0.0007) -[2023-10-09 11:56:43,797][23469] Updated weights for policy 1, policy_version 91791 (0.0009) -[2023-10-09 11:56:44,164][23469] Updated weights for policy 1, policy_version 91801 (0.0008) -[2023-10-09 11:56:46,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 187498496. Throughput: 0: 1778.8, 1: 1793.5. Samples: 46885488. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:56:46,078][22500] Avg episode reward: [(0, '10.740'), (1, '10.100')] -[2023-10-09 11:56:47,094][23468] Updated weights for policy 0, policy_version 91303 (0.0009) -[2023-10-09 11:56:47,467][23468] Updated weights for policy 0, policy_version 91313 (0.0008) -[2023-10-09 11:56:47,843][23468] Updated weights for policy 0, policy_version 91323 (0.0007) -[2023-10-09 11:56:47,924][23469] Updated weights for policy 1, policy_version 91811 (0.0008) -[2023-10-09 11:56:48,293][23469] Updated weights for policy 1, policy_version 91821 (0.0008) -[2023-10-09 11:56:48,666][23469] Updated weights for policy 1, policy_version 91831 (0.0007) -[2023-10-09 11:56:51,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 187564032. Throughput: 0: 1778.5, 1: 1800.2. Samples: 46895590. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:56:51,079][22500] Avg episode reward: [(0, '10.190'), (1, '10.270')] -[2023-10-09 11:56:51,661][23468] Updated weights for policy 0, policy_version 91333 (0.0009) -[2023-10-09 11:56:52,031][23468] Updated weights for policy 0, policy_version 91343 (0.0009) -[2023-10-09 11:56:52,272][23469] Updated weights for policy 1, policy_version 91841 (0.0010) -[2023-10-09 11:56:52,409][23468] Updated weights for policy 0, policy_version 91353 (0.0008) -[2023-10-09 11:56:52,643][23469] Updated weights for policy 1, policy_version 91851 (0.0007) -[2023-10-09 11:56:53,018][23469] Updated weights for policy 1, policy_version 91861 (0.0009) -[2023-10-09 11:56:53,377][23469] Updated weights for policy 1, policy_version 91871 (0.0008) -[2023-10-09 11:56:56,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 187629568. Throughput: 0: 1784.1, 1: 1790.7. Samples: 46917722. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:56:56,078][22500] Avg episode reward: [(0, '10.520'), (1, '10.570')] -[2023-10-09 11:56:56,294][23468] Updated weights for policy 0, policy_version 91363 (0.0009) -[2023-10-09 11:56:56,658][23468] Updated weights for policy 0, policy_version 91373 (0.0011) -[2023-10-09 11:56:57,034][23468] Updated weights for policy 0, policy_version 91383 (0.0008) -[2023-10-09 11:56:57,077][23469] Updated weights for policy 1, policy_version 91881 (0.0009) -[2023-10-09 11:56:57,447][23469] Updated weights for policy 1, policy_version 91891 (0.0010) -[2023-10-09 11:56:57,815][23469] Updated weights for policy 1, policy_version 91901 (0.0007) -[2023-10-09 11:57:00,780][23468] Updated weights for policy 0, policy_version 91393 (0.0008) -[2023-10-09 11:57:01,078][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 187695104. Throughput: 0: 1795.4, 1: 1798.0. Samples: 46940188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:57:01,079][22500] Avg episode reward: [(0, '9.690'), (1, '10.670')] -[2023-10-09 11:57:01,192][23468] Updated weights for policy 0, policy_version 91403 (0.0010) -[2023-10-09 11:57:01,562][23468] Updated weights for policy 0, policy_version 91413 (0.0007) -[2023-10-09 11:57:01,646][23469] Updated weights for policy 1, policy_version 91911 (0.0008) -[2023-10-09 11:57:01,943][23468] Updated weights for policy 0, policy_version 91423 (0.0008) -[2023-10-09 11:57:02,015][23469] Updated weights for policy 1, policy_version 91921 (0.0007) -[2023-10-09 11:57:02,390][23469] Updated weights for policy 1, policy_version 91931 (0.0008) -[2023-10-09 11:57:05,717][23468] Updated weights for policy 0, policy_version 91433 (0.0011) -[2023-10-09 11:57:06,005][23469] Updated weights for policy 1, policy_version 91941 (0.0007) -[2023-10-09 11:57:06,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 187760640. Throughput: 0: 1779.0, 1: 1800.7. Samples: 46949806. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:57:06,078][22500] Avg episode reward: [(0, '10.370'), (1, '10.080')] -[2023-10-09 11:57:06,092][23468] Updated weights for policy 0, policy_version 91443 (0.0008) -[2023-10-09 11:57:06,378][23469] Updated weights for policy 1, policy_version 91951 (0.0007) -[2023-10-09 11:57:06,461][23468] Updated weights for policy 0, policy_version 91453 (0.0009) -[2023-10-09 11:57:06,744][23469] Updated weights for policy 1, policy_version 91961 (0.0008) -[2023-10-09 11:57:10,108][23468] Updated weights for policy 0, policy_version 91463 (0.0009) -[2023-10-09 11:57:10,466][23468] Updated weights for policy 0, policy_version 91473 (0.0009) -[2023-10-09 11:57:10,522][23469] Updated weights for policy 1, policy_version 91971 (0.0009) -[2023-10-09 11:57:10,838][23468] Updated weights for policy 0, policy_version 91483 (0.0010) -[2023-10-09 11:57:10,891][23469] Updated weights for policy 1, policy_version 91981 (0.0007) -[2023-10-09 11:57:11,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 187858944. Throughput: 0: 1791.6, 1: 1802.7. Samples: 46972364. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:57:11,078][22500] Avg episode reward: [(0, '9.830'), (1, '9.210')] -[2023-10-09 11:57:11,259][23469] Updated weights for policy 1, policy_version 91991 (0.0008) -[2023-10-09 11:57:14,613][23468] Updated weights for policy 0, policy_version 91493 (0.0008) -[2023-10-09 11:57:14,947][23469] Updated weights for policy 1, policy_version 92001 (0.0007) -[2023-10-09 11:57:14,984][23468] Updated weights for policy 0, policy_version 91503 (0.0009) -[2023-10-09 11:57:15,314][23469] Updated weights for policy 1, policy_version 92011 (0.0008) -[2023-10-09 11:57:15,352][23468] Updated weights for policy 0, policy_version 91513 (0.0009) -[2023-10-09 11:57:15,680][23469] Updated weights for policy 1, policy_version 92021 (0.0008) -[2023-10-09 11:57:16,057][23469] Updated weights for policy 1, policy_version 92031 (0.0008) -[2023-10-09 11:57:16,078][22500] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 187924480. Throughput: 0: 1782.6, 1: 1804.0. Samples: 46992666. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:57:16,079][22500] Avg episode reward: [(0, '10.160'), (1, '9.510')] -[2023-10-09 11:57:19,114][23468] Updated weights for policy 0, policy_version 91523 (0.0007) -[2023-10-09 11:57:19,493][23468] Updated weights for policy 0, policy_version 91533 (0.0009) -[2023-10-09 11:57:19,796][23469] Updated weights for policy 1, policy_version 92041 (0.0009) -[2023-10-09 11:57:19,859][23468] Updated weights for policy 0, policy_version 91543 (0.0009) -[2023-10-09 11:57:20,170][23469] Updated weights for policy 1, policy_version 92051 (0.0009) -[2023-10-09 11:57:20,530][23469] Updated weights for policy 1, policy_version 92061 (0.0008) -[2023-10-09 11:57:21,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 188022784. Throughput: 0: 1784.3, 1: 1803.2. Samples: 47004726. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:57:21,078][22500] Avg episode reward: [(0, '10.710'), (1, '9.570')] -[2023-10-09 11:57:23,742][23468] Updated weights for policy 0, policy_version 91553 (0.0008) -[2023-10-09 11:57:24,109][23468] Updated weights for policy 0, policy_version 91563 (0.0010) -[2023-10-09 11:57:24,399][23469] Updated weights for policy 1, policy_version 92071 (0.0008) -[2023-10-09 11:57:24,472][23468] Updated weights for policy 0, policy_version 91573 (0.0008) -[2023-10-09 11:57:24,781][23469] Updated weights for policy 1, policy_version 92081 (0.0009) -[2023-10-09 11:57:24,841][23468] Updated weights for policy 0, policy_version 91583 (0.0008) -[2023-10-09 11:57:25,151][23469] Updated weights for policy 1, policy_version 92091 (0.0008) -[2023-10-09 11:57:26,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 188088320. Throughput: 0: 1783.3, 1: 1813.3. Samples: 47025340. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:57:26,079][22500] Avg episode reward: [(0, '10.580'), (1, '9.820')] -[2023-10-09 11:57:28,742][23468] Updated weights for policy 0, policy_version 91593 (0.0007) -[2023-10-09 11:57:28,847][23469] Updated weights for policy 1, policy_version 92101 (0.0008) -[2023-10-09 11:57:29,114][23468] Updated weights for policy 0, policy_version 91603 (0.0009) -[2023-10-09 11:57:29,224][23469] Updated weights for policy 1, policy_version 92111 (0.0009) -[2023-10-09 11:57:29,494][23468] Updated weights for policy 0, policy_version 91613 (0.0009) -[2023-10-09 11:57:29,582][23469] Updated weights for policy 1, policy_version 92121 (0.0008) -[2023-10-09 11:57:31,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 188153856. Throughput: 0: 1774.4, 1: 1802.0. Samples: 47046426. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:57:31,079][22500] Avg episode reward: [(0, '10.560'), (1, '10.050')] -[2023-10-09 11:57:33,085][23468] Updated weights for policy 0, policy_version 91623 (0.0008) -[2023-10-09 11:57:33,257][23469] Updated weights for policy 1, policy_version 92131 (0.0009) -[2023-10-09 11:57:33,451][23468] Updated weights for policy 0, policy_version 91633 (0.0009) -[2023-10-09 11:57:33,640][23469] Updated weights for policy 1, policy_version 92141 (0.0008) -[2023-10-09 11:57:33,817][23468] Updated weights for policy 0, policy_version 91643 (0.0008) -[2023-10-09 11:57:34,014][23469] Updated weights for policy 1, policy_version 92151 (0.0009) -[2023-10-09 11:57:36,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 188219392. Throughput: 0: 1797.5, 1: 1812.1. Samples: 47058020. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:57:36,078][22500] Avg episode reward: [(0, '9.850'), (1, '9.970')] -[2023-10-09 11:57:37,591][23468] Updated weights for policy 0, policy_version 91653 (0.0007) -[2023-10-09 11:57:37,695][23469] Updated weights for policy 1, policy_version 92161 (0.0009) -[2023-10-09 11:57:37,970][23468] Updated weights for policy 0, policy_version 91663 (0.0009) -[2023-10-09 11:57:38,071][23469] Updated weights for policy 1, policy_version 92171 (0.0010) -[2023-10-09 11:57:38,347][23468] Updated weights for policy 0, policy_version 91673 (0.0008) -[2023-10-09 11:57:38,432][23469] Updated weights for policy 1, policy_version 92181 (0.0008) -[2023-10-09 11:57:38,800][23469] Updated weights for policy 1, policy_version 92191 (0.0010) -[2023-10-09 11:57:41,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 188284928. Throughput: 0: 1774.0, 1: 1804.2. Samples: 47078744. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:57:41,078][22500] Avg episode reward: [(0, '10.210'), (1, '10.550')] -[2023-10-09 11:57:41,989][23468] Updated weights for policy 0, policy_version 91683 (0.0008) -[2023-10-09 11:57:42,358][23468] Updated weights for policy 0, policy_version 91693 (0.0007) -[2023-10-09 11:57:42,579][23469] Updated weights for policy 1, policy_version 92201 (0.0007) -[2023-10-09 11:57:42,725][23468] Updated weights for policy 0, policy_version 91703 (0.0008) -[2023-10-09 11:57:42,936][23469] Updated weights for policy 1, policy_version 92211 (0.0009) -[2023-10-09 11:57:43,308][23469] Updated weights for policy 1, policy_version 92221 (0.0009) -[2023-10-09 11:57:46,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 188350464. Throughput: 0: 1785.6, 1: 1797.8. Samples: 47101438. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:57:46,079][22500] Avg episode reward: [(0, '10.840'), (1, '9.660')] -[2023-10-09 11:57:46,602][23468] Updated weights for policy 0, policy_version 91713 (0.0007) -[2023-10-09 11:57:47,021][23468] Updated weights for policy 0, policy_version 91723 (0.0007) -[2023-10-09 11:57:47,111][23469] Updated weights for policy 1, policy_version 92231 (0.0007) -[2023-10-09 11:57:47,387][23468] Updated weights for policy 0, policy_version 91733 (0.0008) -[2023-10-09 11:57:47,474][23469] Updated weights for policy 1, policy_version 92241 (0.0008) -[2023-10-09 11:57:47,767][23468] Updated weights for policy 0, policy_version 91743 (0.0008) -[2023-10-09 11:57:47,834][23469] Updated weights for policy 1, policy_version 92251 (0.0010) -[2023-10-09 11:57:51,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 188416000. Throughput: 0: 1784.1, 1: 1797.3. Samples: 47110970. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:57:51,079][22500] Avg episode reward: [(0, '10.910'), (1, '9.940')] -[2023-10-09 11:57:51,539][23469] Updated weights for policy 1, policy_version 92261 (0.0008) -[2023-10-09 11:57:51,548][23468] Updated weights for policy 0, policy_version 91753 (0.0008) -[2023-10-09 11:57:51,902][23469] Updated weights for policy 1, policy_version 92271 (0.0009) -[2023-10-09 11:57:51,906][23468] Updated weights for policy 0, policy_version 91763 (0.0010) -[2023-10-09 11:57:52,271][23469] Updated weights for policy 1, policy_version 92281 (0.0007) -[2023-10-09 11:57:52,288][23468] Updated weights for policy 0, policy_version 91773 (0.0008) -[2023-10-09 11:57:56,034][23469] Updated weights for policy 1, policy_version 92291 (0.0008) -[2023-10-09 11:57:56,036][23468] Updated weights for policy 0, policy_version 91783 (0.0009) -[2023-10-09 11:57:56,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 188481536. Throughput: 0: 1779.0, 1: 1795.2. Samples: 47133204. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:57:56,078][22500] Avg episode reward: [(0, '11.280'), (1, '10.100')] -[2023-10-09 11:57:56,406][23469] Updated weights for policy 1, policy_version 92301 (0.0009) -[2023-10-09 11:57:56,415][23468] Updated weights for policy 0, policy_version 91793 (0.0007) -[2023-10-09 11:57:56,778][23469] Updated weights for policy 1, policy_version 92311 (0.0007) -[2023-10-09 11:57:56,787][23468] Updated weights for policy 0, policy_version 91803 (0.0007) -[2023-10-09 11:58:00,393][23469] Updated weights for policy 1, policy_version 92321 (0.0008) -[2023-10-09 11:58:00,549][23468] Updated weights for policy 0, policy_version 91813 (0.0009) -[2023-10-09 11:58:00,749][23469] Updated weights for policy 1, policy_version 92331 (0.0009) -[2023-10-09 11:58:00,925][23468] Updated weights for policy 0, policy_version 91823 (0.0007) -[2023-10-09 11:58:01,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 188547072. Throughput: 0: 1803.8, 1: 1809.8. Samples: 47155276. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:58:01,078][22500] Avg episode reward: [(0, '11.510'), (1, '9.550')] -[2023-10-09 11:58:01,124][23469] Updated weights for policy 1, policy_version 92341 (0.0008) -[2023-10-09 11:58:01,291][23468] Updated weights for policy 0, policy_version 91833 (0.0008) -[2023-10-09 11:58:01,488][23469] Updated weights for policy 1, policy_version 92351 (0.0008) -[2023-10-09 11:58:04,986][23468] Updated weights for policy 0, policy_version 91843 (0.0008) -[2023-10-09 11:58:05,193][23469] Updated weights for policy 1, policy_version 92361 (0.0008) -[2023-10-09 11:58:05,357][23468] Updated weights for policy 0, policy_version 91853 (0.0007) -[2023-10-09 11:58:05,556][23469] Updated weights for policy 1, policy_version 92371 (0.0008) -[2023-10-09 11:58:05,722][23468] Updated weights for policy 0, policy_version 91863 (0.0011) -[2023-10-09 11:58:05,933][23469] Updated weights for policy 1, policy_version 92381 (0.0009) -[2023-10-09 11:58:06,078][22500] Fps is (10 sec: 19660.3, 60 sec: 15291.7, 300 sec: 14440.1). Total num frames: 188678144. Throughput: 0: 1780.1, 1: 1794.1. Samples: 47165566. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:58:06,079][22500] Avg episode reward: [(0, '10.330'), (1, '9.510')] -[2023-10-09 11:58:09,511][23468] Updated weights for policy 0, policy_version 91873 (0.0007) -[2023-10-09 11:58:09,850][23469] Updated weights for policy 1, policy_version 92391 (0.0007) -[2023-10-09 11:58:09,879][23468] Updated weights for policy 0, policy_version 91883 (0.0008) -[2023-10-09 11:58:10,207][23469] Updated weights for policy 1, policy_version 92401 (0.0007) -[2023-10-09 11:58:10,247][23468] Updated weights for policy 0, policy_version 91893 (0.0007) -[2023-10-09 11:58:10,574][23469] Updated weights for policy 1, policy_version 92411 (0.0007) -[2023-10-09 11:58:10,618][23468] Updated weights for policy 0, policy_version 91903 (0.0008) -[2023-10-09 11:58:11,077][22500] Fps is (10 sec: 19661.1, 60 sec: 14745.7, 300 sec: 14440.2). Total num frames: 188743680. Throughput: 0: 1802.1, 1: 1805.3. Samples: 47187676. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:58:11,078][22500] Avg episode reward: [(0, '11.290'), (1, '9.610')] -[2023-10-09 11:58:14,217][23469] Updated weights for policy 1, policy_version 92421 (0.0009) -[2023-10-09 11:58:14,579][23469] Updated weights for policy 1, policy_version 92431 (0.0009) -[2023-10-09 11:58:14,599][23468] Updated weights for policy 0, policy_version 91913 (0.0007) -[2023-10-09 11:58:14,950][23469] Updated weights for policy 1, policy_version 92441 (0.0008) -[2023-10-09 11:58:14,972][23468] Updated weights for policy 0, policy_version 91923 (0.0007) -[2023-10-09 11:58:15,349][23468] Updated weights for policy 0, policy_version 91933 (0.0010) -[2023-10-09 11:58:16,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 188809216. Throughput: 0: 1784.4, 1: 1795.6. Samples: 47207528. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:58:16,079][22500] Avg episode reward: [(0, '11.250'), (1, '9.520')] -[2023-10-09 11:58:16,093][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000092448_94666752.pth... -[2023-10-09 11:58:16,093][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000091936_94142464.pth... -[2023-10-09 11:58:16,135][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000090272_92438528.pth -[2023-10-09 11:58:16,135][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000090752_92930048.pth -[2023-10-09 11:58:18,879][23469] Updated weights for policy 1, policy_version 92451 (0.0008) -[2023-10-09 11:58:19,100][23468] Updated weights for policy 0, policy_version 91943 (0.0008) -[2023-10-09 11:58:19,282][23469] Updated weights for policy 1, policy_version 92461 (0.0008) -[2023-10-09 11:58:19,466][23468] Updated weights for policy 0, policy_version 91953 (0.0007) -[2023-10-09 11:58:19,655][23469] Updated weights for policy 1, policy_version 92471 (0.0007) -[2023-10-09 11:58:19,840][23468] Updated weights for policy 0, policy_version 91963 (0.0007) -[2023-10-09 11:58:21,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 188874752. Throughput: 0: 1788.0, 1: 1805.2. Samples: 47219716. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 11:58:21,078][22500] Avg episode reward: [(0, '9.770'), (1, '10.130')] -[2023-10-09 11:58:23,433][23469] Updated weights for policy 1, policy_version 92481 (0.0007) -[2023-10-09 11:58:23,630][23468] Updated weights for policy 0, policy_version 91973 (0.0010) -[2023-10-09 11:58:23,796][23469] Updated weights for policy 1, policy_version 92491 (0.0008) -[2023-10-09 11:58:24,002][23468] Updated weights for policy 0, policy_version 91983 (0.0010) -[2023-10-09 11:58:24,160][23469] Updated weights for policy 1, policy_version 92501 (0.0007) -[2023-10-09 11:58:24,369][23468] Updated weights for policy 0, policy_version 91993 (0.0007) -[2023-10-09 11:58:24,522][23469] Updated weights for policy 1, policy_version 92511 (0.0008) -[2023-10-09 11:58:26,077][22500] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 188940288. Throughput: 0: 1786.4, 1: 1784.0. Samples: 47239414. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 11:58:26,078][22500] Avg episode reward: [(0, '8.990'), (1, '9.860')] -[2023-10-09 11:58:28,218][23468] Updated weights for policy 0, policy_version 92003 (0.0008) -[2023-10-09 11:58:28,322][23469] Updated weights for policy 1, policy_version 92521 (0.0008) -[2023-10-09 11:58:28,598][23468] Updated weights for policy 0, policy_version 92013 (0.0008) -[2023-10-09 11:58:28,682][23469] Updated weights for policy 1, policy_version 92531 (0.0007) -[2023-10-09 11:58:28,964][23468] Updated weights for policy 0, policy_version 92023 (0.0008) -[2023-10-09 11:58:29,046][23469] Updated weights for policy 1, policy_version 92541 (0.0007) -[2023-10-09 11:58:31,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 189005824. Throughput: 0: 1769.6, 1: 1783.6. Samples: 47261330. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 11:58:31,079][22500] Avg episode reward: [(0, '9.290'), (1, '10.090')] -[2023-10-09 11:58:32,642][23468] Updated weights for policy 0, policy_version 92033 (0.0009) -[2023-10-09 11:58:32,784][23469] Updated weights for policy 1, policy_version 92551 (0.0009) -[2023-10-09 11:58:33,057][23468] Updated weights for policy 0, policy_version 92043 (0.0009) -[2023-10-09 11:58:33,160][23469] Updated weights for policy 1, policy_version 92561 (0.0008) -[2023-10-09 11:58:33,429][23468] Updated weights for policy 0, policy_version 92053 (0.0008) -[2023-10-09 11:58:33,527][23469] Updated weights for policy 1, policy_version 92571 (0.0008) -[2023-10-09 11:58:33,813][23468] Updated weights for policy 0, policy_version 92063 (0.0007) -[2023-10-09 11:58:36,078][22500] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 189071360. Throughput: 0: 1786.0, 1: 1782.6. Samples: 47271560. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 11:58:36,079][22500] Avg episode reward: [(0, '9.120'), (1, '9.290')] -[2023-10-09 11:58:37,298][23469] Updated weights for policy 1, policy_version 92581 (0.0009) -[2023-10-09 11:58:37,613][23468] Updated weights for policy 0, policy_version 92073 (0.0009) -[2023-10-09 11:58:37,674][23469] Updated weights for policy 1, policy_version 92591 (0.0007) -[2023-10-09 11:58:37,979][23468] Updated weights for policy 0, policy_version 92083 (0.0009) -[2023-10-09 11:58:38,054][23469] Updated weights for policy 1, policy_version 92601 (0.0008) -[2023-10-09 11:58:38,346][23468] Updated weights for policy 0, policy_version 92093 (0.0008) -[2023-10-09 11:58:41,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 189136896. Throughput: 0: 1770.1, 1: 1786.7. Samples: 47293258. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 11:58:41,079][22500] Avg episode reward: [(0, '10.240'), (1, '9.780')] -[2023-10-09 11:58:41,756][23469] Updated weights for policy 1, policy_version 92611 (0.0008) -[2023-10-09 11:58:42,031][23468] Updated weights for policy 0, policy_version 92103 (0.0009) -[2023-10-09 11:58:42,135][23469] Updated weights for policy 1, policy_version 92621 (0.0009) -[2023-10-09 11:58:42,411][23468] Updated weights for policy 0, policy_version 92113 (0.0008) -[2023-10-09 11:58:42,513][23469] Updated weights for policy 1, policy_version 92631 (0.0008) -[2023-10-09 11:58:42,785][23468] Updated weights for policy 0, policy_version 92123 (0.0008) -[2023-10-09 11:58:46,078][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 189202432. Throughput: 0: 1772.8, 1: 1792.9. Samples: 47315732. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 11:58:46,078][22500] Avg episode reward: [(0, '10.770'), (1, '9.910')] -[2023-10-09 11:58:46,295][23469] Updated weights for policy 1, policy_version 92641 (0.0008) -[2023-10-09 11:58:46,604][23468] Updated weights for policy 0, policy_version 92133 (0.0007) -[2023-10-09 11:58:46,674][23469] Updated weights for policy 1, policy_version 92651 (0.0008) -[2023-10-09 11:58:46,974][23468] Updated weights for policy 0, policy_version 92143 (0.0007) -[2023-10-09 11:58:47,034][23469] Updated weights for policy 1, policy_version 92661 (0.0007) -[2023-10-09 11:58:47,345][23468] Updated weights for policy 0, policy_version 92153 (0.0008) -[2023-10-09 11:58:47,398][23469] Updated weights for policy 1, policy_version 92671 (0.0009) -[2023-10-09 11:58:51,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 189267968. Throughput: 0: 1771.4, 1: 1778.7. Samples: 47325318. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 11:58:51,078][22500] Avg episode reward: [(0, '10.670'), (1, '9.930')] -[2023-10-09 11:58:51,176][23469] Updated weights for policy 1, policy_version 92681 (0.0008) -[2023-10-09 11:58:51,207][23468] Updated weights for policy 0, policy_version 92163 (0.0007) -[2023-10-09 11:58:51,545][23469] Updated weights for policy 1, policy_version 92691 (0.0008) -[2023-10-09 11:58:51,577][23468] Updated weights for policy 0, policy_version 92173 (0.0007) -[2023-10-09 11:58:51,918][23469] Updated weights for policy 1, policy_version 92701 (0.0007) -[2023-10-09 11:58:51,950][23468] Updated weights for policy 0, policy_version 92183 (0.0007) -[2023-10-09 11:58:55,571][23468] Updated weights for policy 0, policy_version 92193 (0.0007) -[2023-10-09 11:58:55,823][23469] Updated weights for policy 1, policy_version 92711 (0.0008) -[2023-10-09 11:58:55,941][23468] Updated weights for policy 0, policy_version 92203 (0.0008) -[2023-10-09 11:58:56,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 189333504. Throughput: 0: 1767.5, 1: 1781.0. Samples: 47347358. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 11:58:56,078][22500] Avg episode reward: [(0, '11.020'), (1, '10.280')] -[2023-10-09 11:58:56,194][23469] Updated weights for policy 1, policy_version 92721 (0.0008) -[2023-10-09 11:58:56,307][23468] Updated weights for policy 0, policy_version 92213 (0.0009) -[2023-10-09 11:58:56,552][23469] Updated weights for policy 1, policy_version 92731 (0.0007) -[2023-10-09 11:58:56,680][23468] Updated weights for policy 0, policy_version 92223 (0.0008) -[2023-10-09 11:59:00,242][23469] Updated weights for policy 1, policy_version 92741 (0.0008) -[2023-10-09 11:59:00,616][23469] Updated weights for policy 1, policy_version 92751 (0.0008) -[2023-10-09 11:59:00,624][23468] Updated weights for policy 0, policy_version 92233 (0.0008) -[2023-10-09 11:59:00,971][23469] Updated weights for policy 1, policy_version 92761 (0.0007) -[2023-10-09 11:59:00,995][23468] Updated weights for policy 0, policy_version 92243 (0.0009) -[2023-10-09 11:59:01,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 189399040. Throughput: 0: 1796.1, 1: 1790.5. Samples: 47368920. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 11:59:01,078][22500] Avg episode reward: [(0, '11.030'), (1, '9.770')] -[2023-10-09 11:59:01,373][23468] Updated weights for policy 0, policy_version 92253 (0.0008) -[2023-10-09 11:59:04,656][23469] Updated weights for policy 1, policy_version 92771 (0.0008) -[2023-10-09 11:59:05,049][23469] Updated weights for policy 1, policy_version 92781 (0.0009) -[2023-10-09 11:59:05,093][23468] Updated weights for policy 0, policy_version 92263 (0.0007) -[2023-10-09 11:59:05,420][23469] Updated weights for policy 1, policy_version 92791 (0.0007) -[2023-10-09 11:59:05,464][23468] Updated weights for policy 0, policy_version 92273 (0.0008) -[2023-10-09 11:59:05,842][23468] Updated weights for policy 0, policy_version 92283 (0.0008) -[2023-10-09 11:59:06,077][22500] Fps is (10 sec: 19660.8, 60 sec: 14199.6, 300 sec: 14440.1). Total num frames: 189530112. Throughput: 0: 1772.0, 1: 1787.7. Samples: 47379904. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 11:59:06,078][22500] Avg episode reward: [(0, '11.100'), (1, '10.060')] -[2023-10-09 11:59:09,280][23469] Updated weights for policy 1, policy_version 92801 (0.0009) -[2023-10-09 11:59:09,559][23468] Updated weights for policy 0, policy_version 92293 (0.0008) -[2023-10-09 11:59:09,645][23469] Updated weights for policy 1, policy_version 92811 (0.0009) -[2023-10-09 11:59:09,936][23468] Updated weights for policy 0, policy_version 92303 (0.0007) -[2023-10-09 11:59:10,019][23469] Updated weights for policy 1, policy_version 92821 (0.0009) -[2023-10-09 11:59:10,305][23468] Updated weights for policy 0, policy_version 92313 (0.0007) -[2023-10-09 11:59:10,385][23469] Updated weights for policy 1, policy_version 92831 (0.0008) -[2023-10-09 11:59:11,077][22500] Fps is (10 sec: 19661.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 189595648. Throughput: 0: 1797.7, 1: 1806.7. Samples: 47401612. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 11:59:11,078][22500] Avg episode reward: [(0, '11.110'), (1, '9.860')] -[2023-10-09 11:59:14,069][23468] Updated weights for policy 0, policy_version 92323 (0.0007) -[2023-10-09 11:59:14,099][23469] Updated weights for policy 1, policy_version 92841 (0.0009) -[2023-10-09 11:59:14,436][23468] Updated weights for policy 0, policy_version 92333 (0.0009) -[2023-10-09 11:59:14,467][23469] Updated weights for policy 1, policy_version 92851 (0.0007) -[2023-10-09 11:59:14,812][23468] Updated weights for policy 0, policy_version 92343 (0.0007) -[2023-10-09 11:59:14,833][23469] Updated weights for policy 1, policy_version 92861 (0.0008) -[2023-10-09 11:59:16,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 189661184. Throughput: 0: 1776.0, 1: 1787.1. Samples: 47421670. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 11:59:16,078][22500] Avg episode reward: [(0, '11.000'), (1, '9.910')] -[2023-10-09 11:59:18,487][23469] Updated weights for policy 1, policy_version 92871 (0.0009) -[2023-10-09 11:59:18,639][23468] Updated weights for policy 0, policy_version 92353 (0.0009) -[2023-10-09 11:59:18,863][23469] Updated weights for policy 1, policy_version 92881 (0.0008) -[2023-10-09 11:59:19,021][23468] Updated weights for policy 0, policy_version 92363 (0.0007) -[2023-10-09 11:59:19,221][23469] Updated weights for policy 1, policy_version 92891 (0.0010) -[2023-10-09 11:59:19,386][23468] Updated weights for policy 0, policy_version 92373 (0.0008) -[2023-10-09 11:59:19,763][23468] Updated weights for policy 0, policy_version 92383 (0.0007) -[2023-10-09 11:59:21,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 189726720. Throughput: 0: 1795.1, 1: 1807.8. Samples: 47433690. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 11:59:21,079][22500] Avg episode reward: [(0, '11.140'), (1, '9.880')] -[2023-10-09 11:59:22,969][23469] Updated weights for policy 1, policy_version 92901 (0.0010) -[2023-10-09 11:59:23,339][23469] Updated weights for policy 1, policy_version 92911 (0.0007) -[2023-10-09 11:59:23,565][23468] Updated weights for policy 0, policy_version 92393 (0.0009) -[2023-10-09 11:59:23,699][23469] Updated weights for policy 1, policy_version 92921 (0.0007) -[2023-10-09 11:59:23,937][23468] Updated weights for policy 0, policy_version 92403 (0.0008) -[2023-10-09 11:59:24,308][23468] Updated weights for policy 0, policy_version 92413 (0.0010) -[2023-10-09 11:59:26,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 189792256. Throughput: 0: 1781.5, 1: 1788.6. Samples: 47453912. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 11:59:26,078][22500] Avg episode reward: [(0, '10.850'), (1, '9.600')] -[2023-10-09 11:59:27,340][23469] Updated weights for policy 1, policy_version 92931 (0.0008) -[2023-10-09 11:59:27,714][23469] Updated weights for policy 1, policy_version 92941 (0.0008) -[2023-10-09 11:59:27,899][23468] Updated weights for policy 0, policy_version 92423 (0.0008) -[2023-10-09 11:59:28,090][23469] Updated weights for policy 1, policy_version 92951 (0.0009) -[2023-10-09 11:59:28,271][23468] Updated weights for policy 0, policy_version 92433 (0.0008) -[2023-10-09 11:59:28,640][23468] Updated weights for policy 0, policy_version 92443 (0.0009) -[2023-10-09 11:59:31,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 189857792. Throughput: 0: 1777.0, 1: 1791.3. Samples: 47476308. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 11:59:31,078][22500] Avg episode reward: [(0, '10.760'), (1, '9.730')] -[2023-10-09 11:59:31,867][23469] Updated weights for policy 1, policy_version 92961 (0.0008) -[2023-10-09 11:59:32,236][23469] Updated weights for policy 1, policy_version 92971 (0.0007) -[2023-10-09 11:59:32,305][23468] Updated weights for policy 0, policy_version 92453 (0.0008) -[2023-10-09 11:59:32,601][23469] Updated weights for policy 1, policy_version 92981 (0.0008) -[2023-10-09 11:59:32,678][23468] Updated weights for policy 0, policy_version 92463 (0.0007) -[2023-10-09 11:59:32,968][23469] Updated weights for policy 1, policy_version 92991 (0.0008) -[2023-10-09 11:59:33,048][23468] Updated weights for policy 0, policy_version 92473 (0.0008) -[2023-10-09 11:59:36,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 189923328. Throughput: 0: 1781.2, 1: 1793.7. Samples: 47486192. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 11:59:36,078][22500] Avg episode reward: [(0, '10.950'), (1, '10.540')] -[2023-10-09 11:59:36,795][23469] Updated weights for policy 1, policy_version 93001 (0.0007) -[2023-10-09 11:59:36,916][23468] Updated weights for policy 0, policy_version 92483 (0.0007) -[2023-10-09 11:59:37,166][23469] Updated weights for policy 1, policy_version 93011 (0.0007) -[2023-10-09 11:59:37,288][23468] Updated weights for policy 0, policy_version 92493 (0.0009) -[2023-10-09 11:59:37,531][23469] Updated weights for policy 1, policy_version 93021 (0.0008) -[2023-10-09 11:59:37,664][23468] Updated weights for policy 0, policy_version 92503 (0.0008) -[2023-10-09 11:59:41,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 189988864. Throughput: 0: 1779.5, 1: 1798.8. Samples: 47508382. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 11:59:41,078][22500] Avg episode reward: [(0, '11.610'), (1, '10.160')] -[2023-10-09 11:59:41,330][23469] Updated weights for policy 1, policy_version 93031 (0.0008) -[2023-10-09 11:59:41,429][23468] Updated weights for policy 0, policy_version 92513 (0.0008) -[2023-10-09 11:59:41,697][23469] Updated weights for policy 1, policy_version 93041 (0.0009) -[2023-10-09 11:59:41,800][23468] Updated weights for policy 0, policy_version 92523 (0.0009) -[2023-10-09 11:59:42,072][23469] Updated weights for policy 1, policy_version 93051 (0.0010) -[2023-10-09 11:59:42,169][23468] Updated weights for policy 0, policy_version 92533 (0.0007) -[2023-10-09 11:59:42,546][23468] Updated weights for policy 0, policy_version 92543 (0.0007) -[2023-10-09 11:59:45,864][23469] Updated weights for policy 1, policy_version 93061 (0.0008) -[2023-10-09 11:59:46,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 190054400. Throughput: 0: 1785.4, 1: 1807.9. Samples: 47530618. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 11:59:46,078][22500] Avg episode reward: [(0, '11.170'), (1, '9.730')] -[2023-10-09 11:59:46,239][23469] Updated weights for policy 1, policy_version 93071 (0.0008) -[2023-10-09 11:59:46,350][23468] Updated weights for policy 0, policy_version 92553 (0.0007) -[2023-10-09 11:59:46,609][23469] Updated weights for policy 1, policy_version 93081 (0.0007) -[2023-10-09 11:59:46,716][23468] Updated weights for policy 0, policy_version 92563 (0.0008) -[2023-10-09 11:59:47,091][23468] Updated weights for policy 0, policy_version 92573 (0.0010) -[2023-10-09 11:59:50,548][23469] Updated weights for policy 1, policy_version 93091 (0.0010) -[2023-10-09 11:59:50,879][23468] Updated weights for policy 0, policy_version 92583 (0.0009) -[2023-10-09 11:59:50,919][23469] Updated weights for policy 1, policy_version 93101 (0.0008) -[2023-10-09 11:59:51,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 190119936. Throughput: 0: 1776.4, 1: 1783.8. Samples: 47540112. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 11:59:51,078][22500] Avg episode reward: [(0, '11.960'), (1, '10.050')] -[2023-10-09 11:59:51,258][23468] Updated weights for policy 0, policy_version 92593 (0.0008) -[2023-10-09 11:59:51,288][23469] Updated weights for policy 1, policy_version 93111 (0.0007) -[2023-10-09 11:59:51,628][23468] Updated weights for policy 0, policy_version 92603 (0.0008) -[2023-10-09 11:59:54,997][23469] Updated weights for policy 1, policy_version 93121 (0.0010) -[2023-10-09 11:59:55,371][23469] Updated weights for policy 1, policy_version 93131 (0.0007) -[2023-10-09 11:59:55,433][23468] Updated weights for policy 0, policy_version 92613 (0.0009) -[2023-10-09 11:59:55,736][23469] Updated weights for policy 1, policy_version 93141 (0.0008) -[2023-10-09 11:59:55,806][23468] Updated weights for policy 0, policy_version 92623 (0.0008) -[2023-10-09 11:59:56,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 190185472. Throughput: 0: 1772.3, 1: 1796.6. Samples: 47562216. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 11:59:56,079][22500] Avg episode reward: [(0, '11.640'), (1, '9.010')] -[2023-10-09 11:59:56,105][23469] Updated weights for policy 1, policy_version 93151 (0.0007) -[2023-10-09 11:59:56,182][23468] Updated weights for policy 0, policy_version 92633 (0.0008) -[2023-10-09 11:59:59,940][23469] Updated weights for policy 1, policy_version 93161 (0.0007) -[2023-10-09 11:59:59,965][23468] Updated weights for policy 0, policy_version 92643 (0.0009) -[2023-10-09 12:00:00,303][23469] Updated weights for policy 1, policy_version 93171 (0.0009) -[2023-10-09 12:00:00,341][23468] Updated weights for policy 0, policy_version 92653 (0.0007) -[2023-10-09 12:00:00,672][23469] Updated weights for policy 1, policy_version 93181 (0.0008) -[2023-10-09 12:00:00,708][23468] Updated weights for policy 0, policy_version 92663 (0.0008) -[2023-10-09 12:00:01,077][22500] Fps is (10 sec: 19660.9, 60 sec: 15291.8, 300 sec: 14440.1). Total num frames: 190316544. Throughput: 0: 1796.5, 1: 1784.1. Samples: 47582796. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 12:00:01,078][22500] Avg episode reward: [(0, '10.090'), (1, '9.010')] -[2023-10-09 12:00:04,392][23469] Updated weights for policy 1, policy_version 93191 (0.0008) -[2023-10-09 12:00:04,573][23468] Updated weights for policy 0, policy_version 92673 (0.0008) -[2023-10-09 12:00:04,751][23469] Updated weights for policy 1, policy_version 93201 (0.0008) -[2023-10-09 12:00:04,992][23468] Updated weights for policy 0, policy_version 92683 (0.0009) -[2023-10-09 12:00:05,127][23469] Updated weights for policy 1, policy_version 93211 (0.0008) -[2023-10-09 12:00:05,356][23468] Updated weights for policy 0, policy_version 92693 (0.0010) -[2023-10-09 12:00:05,734][23468] Updated weights for policy 0, policy_version 92703 (0.0010) -[2023-10-09 12:00:06,077][22500] Fps is (10 sec: 19661.3, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 190382080. Throughput: 0: 1776.1, 1: 1797.8. Samples: 47594516. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 12:00:06,078][22500] Avg episode reward: [(0, '10.930'), (1, '9.040')] -[2023-10-09 12:00:08,701][23469] Updated weights for policy 1, policy_version 93221 (0.0009) -[2023-10-09 12:00:09,067][23469] Updated weights for policy 1, policy_version 93231 (0.0009) -[2023-10-09 12:00:09,444][23469] Updated weights for policy 1, policy_version 93241 (0.0009) -[2023-10-09 12:00:09,478][23468] Updated weights for policy 0, policy_version 92713 (0.0008) -[2023-10-09 12:00:09,846][23468] Updated weights for policy 0, policy_version 92723 (0.0007) -[2023-10-09 12:00:10,214][23468] Updated weights for policy 0, policy_version 92733 (0.0010) -[2023-10-09 12:00:11,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 190447616. Throughput: 0: 1802.9, 1: 1788.8. Samples: 47615538. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 12:00:11,078][22500] Avg episode reward: [(0, '10.030'), (1, '9.540')] -[2023-10-09 12:00:13,170][23469] Updated weights for policy 1, policy_version 93251 (0.0007) -[2023-10-09 12:00:13,537][23469] Updated weights for policy 1, policy_version 93261 (0.0009) -[2023-10-09 12:00:13,908][23469] Updated weights for policy 1, policy_version 93271 (0.0008) -[2023-10-09 12:00:14,027][23468] Updated weights for policy 0, policy_version 92743 (0.0009) -[2023-10-09 12:00:14,403][23468] Updated weights for policy 0, policy_version 92753 (0.0008) -[2023-10-09 12:00:14,767][23468] Updated weights for policy 0, policy_version 92763 (0.0008) -[2023-10-09 12:00:16,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 190513152. Throughput: 0: 1772.7, 1: 1795.2. Samples: 47636868. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 12:00:16,079][22500] Avg episode reward: [(0, '10.130'), (1, '9.510')] -[2023-10-09 12:00:16,090][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000093280_95518720.pth... -[2023-10-09 12:00:16,090][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000092768_94994432.pth... -[2023-10-09 12:00:16,130][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000091616_93814784.pth -[2023-10-09 12:00:16,134][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000091104_93290496.pth -[2023-10-09 12:00:17,481][23469] Updated weights for policy 1, policy_version 93281 (0.0007) -[2023-10-09 12:00:17,851][23469] Updated weights for policy 1, policy_version 93291 (0.0009) -[2023-10-09 12:00:18,220][23469] Updated weights for policy 1, policy_version 93301 (0.0010) -[2023-10-09 12:00:18,596][23469] Updated weights for policy 1, policy_version 93311 (0.0009) -[2023-10-09 12:00:18,600][23468] Updated weights for policy 0, policy_version 92773 (0.0008) -[2023-10-09 12:00:18,969][23468] Updated weights for policy 0, policy_version 92783 (0.0009) -[2023-10-09 12:00:19,342][23468] Updated weights for policy 0, policy_version 92793 (0.0008) -[2023-10-09 12:00:21,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 190578688. Throughput: 0: 1803.1, 1: 1796.8. Samples: 47648188. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 12:00:21,078][22500] Avg episode reward: [(0, '10.280'), (1, '9.630')] -[2023-10-09 12:00:22,360][23469] Updated weights for policy 1, policy_version 93321 (0.0009) -[2023-10-09 12:00:22,724][23469] Updated weights for policy 1, policy_version 93331 (0.0010) -[2023-10-09 12:00:23,050][23468] Updated weights for policy 0, policy_version 92803 (0.0007) -[2023-10-09 12:00:23,089][23469] Updated weights for policy 1, policy_version 93341 (0.0009) -[2023-10-09 12:00:23,432][23468] Updated weights for policy 0, policy_version 92813 (0.0009) -[2023-10-09 12:00:23,810][23468] Updated weights for policy 0, policy_version 92823 (0.0007) -[2023-10-09 12:00:26,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 190644224. Throughput: 0: 1772.8, 1: 1795.8. Samples: 47668966. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 12:00:26,078][22500] Avg episode reward: [(0, '9.980'), (1, '9.060')] -[2023-10-09 12:00:26,898][23469] Updated weights for policy 1, policy_version 93351 (0.0009) -[2023-10-09 12:00:27,270][23469] Updated weights for policy 1, policy_version 93361 (0.0008) -[2023-10-09 12:00:27,556][23468] Updated weights for policy 0, policy_version 92833 (0.0008) -[2023-10-09 12:00:27,638][23469] Updated weights for policy 1, policy_version 93371 (0.0007) -[2023-10-09 12:00:27,928][23468] Updated weights for policy 0, policy_version 92843 (0.0009) -[2023-10-09 12:00:28,304][23468] Updated weights for policy 0, policy_version 92853 (0.0010) -[2023-10-09 12:00:28,677][23468] Updated weights for policy 0, policy_version 92863 (0.0009) -[2023-10-09 12:00:31,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 190709760. Throughput: 0: 1772.3, 1: 1797.8. Samples: 47691270. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 12:00:31,078][22500] Avg episode reward: [(0, '10.540'), (1, '9.390')] -[2023-10-09 12:00:31,402][23469] Updated weights for policy 1, policy_version 93381 (0.0010) -[2023-10-09 12:00:31,768][23469] Updated weights for policy 1, policy_version 93391 (0.0008) -[2023-10-09 12:00:32,142][23469] Updated weights for policy 1, policy_version 93401 (0.0007) -[2023-10-09 12:00:32,496][23468] Updated weights for policy 0, policy_version 92873 (0.0008) -[2023-10-09 12:00:32,875][23468] Updated weights for policy 0, policy_version 92883 (0.0008) -[2023-10-09 12:00:33,250][23468] Updated weights for policy 0, policy_version 92893 (0.0009) -[2023-10-09 12:00:35,872][23469] Updated weights for policy 1, policy_version 93411 (0.0008) -[2023-10-09 12:00:36,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 190775296. Throughput: 0: 1776.0, 1: 1799.8. Samples: 47701022. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 12:00:36,078][22500] Avg episode reward: [(0, '10.810'), (1, '9.250')] -[2023-10-09 12:00:36,270][23469] Updated weights for policy 1, policy_version 93421 (0.0007) -[2023-10-09 12:00:36,632][23469] Updated weights for policy 1, policy_version 93431 (0.0007) -[2023-10-09 12:00:36,952][23468] Updated weights for policy 0, policy_version 92903 (0.0008) -[2023-10-09 12:00:37,318][23468] Updated weights for policy 0, policy_version 92913 (0.0011) -[2023-10-09 12:00:37,692][23468] Updated weights for policy 0, policy_version 92923 (0.0010) -[2023-10-09 12:00:40,316][23469] Updated weights for policy 1, policy_version 93441 (0.0009) -[2023-10-09 12:00:40,674][23469] Updated weights for policy 1, policy_version 93451 (0.0010) -[2023-10-09 12:00:41,043][23469] Updated weights for policy 1, policy_version 93461 (0.0010) -[2023-10-09 12:00:41,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 190840832. Throughput: 0: 1780.2, 1: 1801.5. Samples: 47723392. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 12:00:41,078][22500] Avg episode reward: [(0, '11.020'), (1, '9.780')] -[2023-10-09 12:00:41,418][23469] Updated weights for policy 1, policy_version 93471 (0.0009) -[2023-10-09 12:00:41,423][23468] Updated weights for policy 0, policy_version 92933 (0.0008) -[2023-10-09 12:00:41,790][23468] Updated weights for policy 0, policy_version 92943 (0.0009) -[2023-10-09 12:00:42,168][23468] Updated weights for policy 0, policy_version 92953 (0.0007) -[2023-10-09 12:00:45,238][23469] Updated weights for policy 1, policy_version 93481 (0.0008) -[2023-10-09 12:00:45,608][23469] Updated weights for policy 1, policy_version 93491 (0.0008) -[2023-10-09 12:00:45,903][23468] Updated weights for policy 0, policy_version 92963 (0.0009) -[2023-10-09 12:00:45,973][23469] Updated weights for policy 1, policy_version 93501 (0.0008) -[2023-10-09 12:00:46,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 190906368. Throughput: 0: 1788.7, 1: 1809.4. Samples: 47744708. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 12:00:46,078][22500] Avg episode reward: [(0, '10.720'), (1, '9.430')] -[2023-10-09 12:00:46,274][23468] Updated weights for policy 0, policy_version 92973 (0.0007) -[2023-10-09 12:00:46,654][23468] Updated weights for policy 0, policy_version 92983 (0.0007) -[2023-10-09 12:00:49,667][23469] Updated weights for policy 1, policy_version 93511 (0.0007) -[2023-10-09 12:00:50,031][23469] Updated weights for policy 1, policy_version 93521 (0.0009) -[2023-10-09 12:00:50,398][23469] Updated weights for policy 1, policy_version 93531 (0.0011) -[2023-10-09 12:00:50,443][23468] Updated weights for policy 0, policy_version 92993 (0.0007) -[2023-10-09 12:00:50,851][23468] Updated weights for policy 0, policy_version 93003 (0.0009) -[2023-10-09 12:00:51,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 191004672. Throughput: 0: 1776.4, 1: 1801.6. Samples: 47755526. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 12:00:51,078][22500] Avg episode reward: [(0, '10.630'), (1, '9.290')] -[2023-10-09 12:00:51,218][23468] Updated weights for policy 0, policy_version 93013 (0.0007) -[2023-10-09 12:00:51,595][23468] Updated weights for policy 0, policy_version 93023 (0.0007) -[2023-10-09 12:00:54,095][23469] Updated weights for policy 1, policy_version 93541 (0.0008) -[2023-10-09 12:00:54,471][23469] Updated weights for policy 1, policy_version 93551 (0.0008) -[2023-10-09 12:00:54,849][23469] Updated weights for policy 1, policy_version 93561 (0.0009) -[2023-10-09 12:00:55,303][23468] Updated weights for policy 0, policy_version 93033 (0.0009) -[2023-10-09 12:00:55,677][23468] Updated weights for policy 0, policy_version 93043 (0.0008) -[2023-10-09 12:00:56,050][23468] Updated weights for policy 0, policy_version 93053 (0.0009) -[2023-10-09 12:00:56,078][22500] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 191070208. Throughput: 0: 1777.1, 1: 1806.7. Samples: 47776806. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 12:00:56,079][22500] Avg episode reward: [(0, '10.900'), (1, '8.890')] -[2023-10-09 12:00:58,632][23469] Updated weights for policy 1, policy_version 93571 (0.0008) -[2023-10-09 12:00:59,002][23469] Updated weights for policy 1, policy_version 93581 (0.0008) -[2023-10-09 12:00:59,363][23469] Updated weights for policy 1, policy_version 93591 (0.0009) -[2023-10-09 12:00:59,787][23468] Updated weights for policy 0, policy_version 93063 (0.0009) -[2023-10-09 12:01:00,164][23468] Updated weights for policy 0, policy_version 93073 (0.0008) -[2023-10-09 12:01:00,535][23468] Updated weights for policy 0, policy_version 93083 (0.0007) -[2023-10-09 12:01:01,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14440.2). Total num frames: 191168512. Throughput: 0: 1793.9, 1: 1787.4. Samples: 47798024. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 12:01:01,078][22500] Avg episode reward: [(0, '10.420'), (1, '9.500')] -[2023-10-09 12:01:03,129][23469] Updated weights for policy 1, policy_version 93601 (0.0007) -[2023-10-09 12:01:03,490][23469] Updated weights for policy 1, policy_version 93611 (0.0007) -[2023-10-09 12:01:03,861][23469] Updated weights for policy 1, policy_version 93621 (0.0007) -[2023-10-09 12:01:04,226][23469] Updated weights for policy 1, policy_version 93631 (0.0008) -[2023-10-09 12:01:04,252][23468] Updated weights for policy 0, policy_version 93093 (0.0007) -[2023-10-09 12:01:04,631][23468] Updated weights for policy 0, policy_version 93103 (0.0009) -[2023-10-09 12:01:05,013][23468] Updated weights for policy 0, policy_version 93113 (0.0008) -[2023-10-09 12:01:06,077][22500] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 191234048. Throughput: 0: 1783.2, 1: 1799.8. Samples: 47809420. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 12:01:06,078][22500] Avg episode reward: [(0, '10.420'), (1, '10.790')] -[2023-10-09 12:01:08,052][23469] Updated weights for policy 1, policy_version 93641 (0.0009) -[2023-10-09 12:01:08,436][23469] Updated weights for policy 1, policy_version 93651 (0.0010) -[2023-10-09 12:01:08,726][23468] Updated weights for policy 0, policy_version 93123 (0.0008) -[2023-10-09 12:01:08,805][23469] Updated weights for policy 1, policy_version 93661 (0.0008) -[2023-10-09 12:01:09,107][23468] Updated weights for policy 0, policy_version 93133 (0.0007) -[2023-10-09 12:01:09,498][23468] Updated weights for policy 0, policy_version 93143 (0.0008) -[2023-10-09 12:01:11,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 191299584. Throughput: 0: 1805.3, 1: 1786.5. Samples: 47830596. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 12:01:11,078][22500] Avg episode reward: [(0, '10.190'), (1, '10.760')] -[2023-10-09 12:01:12,564][23469] Updated weights for policy 1, policy_version 93671 (0.0008) -[2023-10-09 12:01:12,934][23469] Updated weights for policy 1, policy_version 93681 (0.0009) -[2023-10-09 12:01:13,306][23469] Updated weights for policy 1, policy_version 93691 (0.0008) -[2023-10-09 12:01:13,366][23468] Updated weights for policy 0, policy_version 93153 (0.0010) -[2023-10-09 12:01:13,742][23468] Updated weights for policy 0, policy_version 93163 (0.0007) -[2023-10-09 12:01:14,108][23468] Updated weights for policy 0, policy_version 93173 (0.0007) -[2023-10-09 12:01:14,477][23468] Updated weights for policy 0, policy_version 93183 (0.0009) -[2023-10-09 12:01:16,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 191365120. Throughput: 0: 1782.0, 1: 1793.2. Samples: 47852156. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 12:01:16,078][22500] Avg episode reward: [(0, '10.210'), (1, '11.250')] -[2023-10-09 12:01:16,085][23343] Saving new best policy, reward=11.250! -[2023-10-09 12:01:17,067][23469] Updated weights for policy 1, policy_version 93701 (0.0008) -[2023-10-09 12:01:17,432][23469] Updated weights for policy 1, policy_version 93711 (0.0010) -[2023-10-09 12:01:17,805][23469] Updated weights for policy 1, policy_version 93721 (0.0009) -[2023-10-09 12:01:18,082][23468] Updated weights for policy 0, policy_version 93193 (0.0008) -[2023-10-09 12:01:18,447][23468] Updated weights for policy 0, policy_version 93203 (0.0010) -[2023-10-09 12:01:18,828][23468] Updated weights for policy 0, policy_version 93213 (0.0009) -[2023-10-09 12:01:21,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 191430656. Throughput: 0: 1804.1, 1: 1790.1. Samples: 47862762. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 12:01:21,078][22500] Avg episode reward: [(0, '10.610'), (1, '9.630')] -[2023-10-09 12:01:21,436][23469] Updated weights for policy 1, policy_version 93731 (0.0009) -[2023-10-09 12:01:21,815][23469] Updated weights for policy 1, policy_version 93741 (0.0010) -[2023-10-09 12:01:22,190][23469] Updated weights for policy 1, policy_version 93751 (0.0010) -[2023-10-09 12:01:22,617][23468] Updated weights for policy 0, policy_version 93223 (0.0008) -[2023-10-09 12:01:23,000][23468] Updated weights for policy 0, policy_version 93233 (0.0008) -[2023-10-09 12:01:23,373][23468] Updated weights for policy 0, policy_version 93243 (0.0009) -[2023-10-09 12:01:26,002][23469] Updated weights for policy 1, policy_version 93761 (0.0009) -[2023-10-09 12:01:26,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 191496192. Throughput: 0: 1781.2, 1: 1798.8. Samples: 47884494. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:01:26,078][22500] Avg episode reward: [(0, '10.720'), (1, '9.450')] -[2023-10-09 12:01:26,415][23469] Updated weights for policy 1, policy_version 93771 (0.0007) -[2023-10-09 12:01:26,791][23469] Updated weights for policy 1, policy_version 93781 (0.0008) -[2023-10-09 12:01:27,065][23468] Updated weights for policy 0, policy_version 93253 (0.0008) -[2023-10-09 12:01:27,152][23469] Updated weights for policy 1, policy_version 93791 (0.0009) -[2023-10-09 12:01:27,439][23468] Updated weights for policy 0, policy_version 93263 (0.0010) -[2023-10-09 12:01:27,821][23468] Updated weights for policy 0, policy_version 93273 (0.0007) -[2023-10-09 12:01:30,852][23469] Updated weights for policy 1, policy_version 93801 (0.0007) -[2023-10-09 12:01:31,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 191561728. Throughput: 0: 1783.5, 1: 1812.8. Samples: 47906544. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:01:31,078][22500] Avg episode reward: [(0, '10.500'), (1, '9.310')] -[2023-10-09 12:01:31,221][23469] Updated weights for policy 1, policy_version 93811 (0.0007) -[2023-10-09 12:01:31,584][23469] Updated weights for policy 1, policy_version 93821 (0.0007) -[2023-10-09 12:01:31,645][23468] Updated weights for policy 0, policy_version 93283 (0.0008) -[2023-10-09 12:01:32,008][23468] Updated weights for policy 0, policy_version 93293 (0.0009) -[2023-10-09 12:01:32,389][23468] Updated weights for policy 0, policy_version 93303 (0.0008) -[2023-10-09 12:01:35,286][23469] Updated weights for policy 1, policy_version 93831 (0.0009) -[2023-10-09 12:01:35,663][23469] Updated weights for policy 1, policy_version 93841 (0.0010) -[2023-10-09 12:01:36,030][23469] Updated weights for policy 1, policy_version 93851 (0.0011) -[2023-10-09 12:01:36,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 191627264. Throughput: 0: 1781.5, 1: 1796.9. Samples: 47916556. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:01:36,078][22500] Avg episode reward: [(0, '11.090'), (1, '9.550')] -[2023-10-09 12:01:36,258][23468] Updated weights for policy 0, policy_version 93313 (0.0007) -[2023-10-09 12:01:36,663][23468] Updated weights for policy 0, policy_version 93323 (0.0009) -[2023-10-09 12:01:37,032][23468] Updated weights for policy 0, policy_version 93333 (0.0008) -[2023-10-09 12:01:37,403][23468] Updated weights for policy 0, policy_version 93343 (0.0007) -[2023-10-09 12:01:39,532][23469] Updated weights for policy 1, policy_version 93861 (0.0008) -[2023-10-09 12:01:39,891][23469] Updated weights for policy 1, policy_version 93871 (0.0008) -[2023-10-09 12:01:40,266][23469] Updated weights for policy 1, policy_version 93881 (0.0009) -[2023-10-09 12:01:41,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 191725568. Throughput: 0: 1781.1, 1: 1809.5. Samples: 47938382. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:01:41,078][22500] Avg episode reward: [(0, '11.130'), (1, '9.870')] -[2023-10-09 12:01:41,231][23468] Updated weights for policy 0, policy_version 93353 (0.0008) -[2023-10-09 12:01:41,607][23468] Updated weights for policy 0, policy_version 93363 (0.0009) -[2023-10-09 12:01:41,979][23468] Updated weights for policy 0, policy_version 93373 (0.0008) -[2023-10-09 12:01:43,980][23469] Updated weights for policy 1, policy_version 93891 (0.0009) -[2023-10-09 12:01:44,356][23469] Updated weights for policy 1, policy_version 93901 (0.0010) -[2023-10-09 12:01:44,728][23469] Updated weights for policy 1, policy_version 93911 (0.0007) -[2023-10-09 12:01:45,750][23468] Updated weights for policy 0, policy_version 93383 (0.0008) -[2023-10-09 12:01:46,078][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 191791104. Throughput: 0: 1800.0, 1: 1802.1. Samples: 47960120. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:01:46,079][22500] Avg episode reward: [(0, '10.420'), (1, '9.810')] -[2023-10-09 12:01:46,131][23468] Updated weights for policy 0, policy_version 93393 (0.0009) -[2023-10-09 12:01:46,490][23468] Updated weights for policy 0, policy_version 93403 (0.0010) -[2023-10-09 12:01:48,560][23469] Updated weights for policy 1, policy_version 93921 (0.0007) -[2023-10-09 12:01:48,920][23469] Updated weights for policy 1, policy_version 93931 (0.0007) -[2023-10-09 12:01:49,297][23469] Updated weights for policy 1, policy_version 93941 (0.0008) -[2023-10-09 12:01:49,669][23469] Updated weights for policy 1, policy_version 93951 (0.0007) -[2023-10-09 12:01:50,306][23468] Updated weights for policy 0, policy_version 93413 (0.0010) -[2023-10-09 12:01:50,691][23468] Updated weights for policy 0, policy_version 93423 (0.0007) -[2023-10-09 12:01:51,064][23468] Updated weights for policy 0, policy_version 93433 (0.0008) -[2023-10-09 12:01:51,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 191856640. Throughput: 0: 1774.5, 1: 1813.7. Samples: 47970892. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:01:51,078][22500] Avg episode reward: [(0, '10.560'), (1, '9.240')] -[2023-10-09 12:01:53,486][23469] Updated weights for policy 1, policy_version 93961 (0.0008) -[2023-10-09 12:01:53,857][23469] Updated weights for policy 1, policy_version 93971 (0.0009) -[2023-10-09 12:01:54,226][23469] Updated weights for policy 1, policy_version 93981 (0.0009) -[2023-10-09 12:01:54,737][23468] Updated weights for policy 0, policy_version 93443 (0.0007) -[2023-10-09 12:01:55,106][23468] Updated weights for policy 0, policy_version 93453 (0.0008) -[2023-10-09 12:01:55,477][23468] Updated weights for policy 0, policy_version 93463 (0.0008) -[2023-10-09 12:01:56,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 191954944. Throughput: 0: 1791.0, 1: 1796.3. Samples: 47992026. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:01:56,078][22500] Avg episode reward: [(0, '10.070'), (1, '8.760')] -[2023-10-09 12:01:57,978][23469] Updated weights for policy 1, policy_version 93991 (0.0009) -[2023-10-09 12:01:58,350][23469] Updated weights for policy 1, policy_version 94001 (0.0008) -[2023-10-09 12:01:58,732][23469] Updated weights for policy 1, policy_version 94011 (0.0008) -[2023-10-09 12:01:58,997][23468] Updated weights for policy 0, policy_version 93473 (0.0008) -[2023-10-09 12:01:59,367][23468] Updated weights for policy 0, policy_version 93483 (0.0011) -[2023-10-09 12:01:59,744][23468] Updated weights for policy 0, policy_version 93493 (0.0011) -[2023-10-09 12:02:00,112][23468] Updated weights for policy 0, policy_version 93503 (0.0009) -[2023-10-09 12:02:01,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 192020480. Throughput: 0: 1785.1, 1: 1794.8. Samples: 48013248. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:02:01,078][22500] Avg episode reward: [(0, '10.060'), (1, '8.820')] -[2023-10-09 12:02:02,464][23469] Updated weights for policy 1, policy_version 94021 (0.0008) -[2023-10-09 12:02:02,838][23469] Updated weights for policy 1, policy_version 94031 (0.0007) -[2023-10-09 12:02:03,213][23469] Updated weights for policy 1, policy_version 94041 (0.0008) -[2023-10-09 12:02:03,933][23468] Updated weights for policy 0, policy_version 93513 (0.0008) -[2023-10-09 12:02:04,299][23468] Updated weights for policy 0, policy_version 93523 (0.0008) -[2023-10-09 12:02:04,669][23468] Updated weights for policy 0, policy_version 93533 (0.0007) -[2023-10-09 12:02:06,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 192086016. Throughput: 0: 1800.8, 1: 1796.6. Samples: 48024646. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:02:06,078][22500] Avg episode reward: [(0, '10.540'), (1, '9.080')] -[2023-10-09 12:02:07,004][23469] Updated weights for policy 1, policy_version 94051 (0.0008) -[2023-10-09 12:02:07,376][23469] Updated weights for policy 1, policy_version 94061 (0.0008) -[2023-10-09 12:02:07,733][23469] Updated weights for policy 1, policy_version 94071 (0.0007) -[2023-10-09 12:02:08,387][23468] Updated weights for policy 0, policy_version 93543 (0.0010) -[2023-10-09 12:02:08,756][23468] Updated weights for policy 0, policy_version 93553 (0.0008) -[2023-10-09 12:02:09,135][23468] Updated weights for policy 0, policy_version 93563 (0.0007) -[2023-10-09 12:02:11,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 192151552. Throughput: 0: 1795.8, 1: 1794.4. Samples: 48046052. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:02:11,078][22500] Avg episode reward: [(0, '10.800'), (1, '9.250')] -[2023-10-09 12:02:11,628][23469] Updated weights for policy 1, policy_version 94081 (0.0008) -[2023-10-09 12:02:12,019][23469] Updated weights for policy 1, policy_version 94091 (0.0008) -[2023-10-09 12:02:12,391][23469] Updated weights for policy 1, policy_version 94101 (0.0007) -[2023-10-09 12:02:12,762][23469] Updated weights for policy 1, policy_version 94111 (0.0008) -[2023-10-09 12:02:12,876][23468] Updated weights for policy 0, policy_version 93573 (0.0008) -[2023-10-09 12:02:13,248][23468] Updated weights for policy 0, policy_version 93583 (0.0009) -[2023-10-09 12:02:13,616][23468] Updated weights for policy 0, policy_version 93593 (0.0011) -[2023-10-09 12:02:16,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 192217088. Throughput: 0: 1789.3, 1: 1797.2. Samples: 48067936. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:02:16,078][22500] Avg episode reward: [(0, '11.340'), (1, '9.790')] -[2023-10-09 12:02:16,086][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000093600_95846400.pth... -[2023-10-09 12:02:16,087][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000094112_96370688.pth... -[2023-10-09 12:02:16,126][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000091936_94142464.pth -[2023-10-09 12:02:16,130][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000092448_94666752.pth -[2023-10-09 12:02:16,608][23469] Updated weights for policy 1, policy_version 94121 (0.0008) -[2023-10-09 12:02:16,974][23469] Updated weights for policy 1, policy_version 94131 (0.0007) -[2023-10-09 12:02:17,348][23469] Updated weights for policy 1, policy_version 94141 (0.0007) -[2023-10-09 12:02:17,498][23468] Updated weights for policy 0, policy_version 93603 (0.0009) -[2023-10-09 12:02:17,869][23468] Updated weights for policy 0, policy_version 93613 (0.0007) -[2023-10-09 12:02:18,241][23468] Updated weights for policy 0, policy_version 93623 (0.0008) -[2023-10-09 12:02:20,912][23469] Updated weights for policy 1, policy_version 94151 (0.0008) -[2023-10-09 12:02:21,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 192282624. Throughput: 0: 1803.7, 1: 1791.7. Samples: 48078346. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:02:21,078][22500] Avg episode reward: [(0, '11.050'), (1, '10.430')] -[2023-10-09 12:02:21,286][23469] Updated weights for policy 1, policy_version 94161 (0.0008) -[2023-10-09 12:02:21,658][23469] Updated weights for policy 1, policy_version 94171 (0.0007) -[2023-10-09 12:02:22,083][23468] Updated weights for policy 0, policy_version 93633 (0.0010) -[2023-10-09 12:02:22,463][23468] Updated weights for policy 0, policy_version 93643 (0.0009) -[2023-10-09 12:02:22,829][23468] Updated weights for policy 0, policy_version 93653 (0.0009) -[2023-10-09 12:02:23,193][23468] Updated weights for policy 0, policy_version 93663 (0.0008) -[2023-10-09 12:02:25,458][23469] Updated weights for policy 1, policy_version 94181 (0.0010) -[2023-10-09 12:02:25,831][23469] Updated weights for policy 1, policy_version 94191 (0.0011) -[2023-10-09 12:02:26,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 192348160. Throughput: 0: 1796.1, 1: 1796.9. Samples: 48100068. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-09 12:02:26,078][22500] Avg episode reward: [(0, '10.840'), (1, '9.830')] -[2023-10-09 12:02:26,204][23469] Updated weights for policy 1, policy_version 94201 (0.0010) -[2023-10-09 12:02:26,877][23468] Updated weights for policy 0, policy_version 93673 (0.0007) -[2023-10-09 12:02:27,251][23468] Updated weights for policy 0, policy_version 93683 (0.0008) -[2023-10-09 12:02:27,621][23468] Updated weights for policy 0, policy_version 93693 (0.0008) -[2023-10-09 12:02:30,086][23469] Updated weights for policy 1, policy_version 94211 (0.0009) -[2023-10-09 12:02:30,459][23469] Updated weights for policy 1, policy_version 94221 (0.0008) -[2023-10-09 12:02:30,826][23469] Updated weights for policy 1, policy_version 94231 (0.0008) -[2023-10-09 12:02:31,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 192413696. Throughput: 0: 1793.4, 1: 1790.2. Samples: 48121384. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-09 12:02:31,078][22500] Avg episode reward: [(0, '11.010'), (1, '9.980')] -[2023-10-09 12:02:31,373][23468] Updated weights for policy 0, policy_version 93703 (0.0008) -[2023-10-09 12:02:31,747][23468] Updated weights for policy 0, policy_version 93713 (0.0009) -[2023-10-09 12:02:32,131][23468] Updated weights for policy 0, policy_version 93723 (0.0008) -[2023-10-09 12:02:34,710][23469] Updated weights for policy 1, policy_version 94241 (0.0009) -[2023-10-09 12:02:35,078][23469] Updated weights for policy 1, policy_version 94251 (0.0008) -[2023-10-09 12:02:35,449][23469] Updated weights for policy 1, policy_version 94261 (0.0009) -[2023-10-09 12:02:35,816][23469] Updated weights for policy 1, policy_version 94271 (0.0011) -[2023-10-09 12:02:35,948][23468] Updated weights for policy 0, policy_version 93733 (0.0009) -[2023-10-09 12:02:36,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 192512000. Throughput: 0: 1794.9, 1: 1785.3. Samples: 48132002. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-09 12:02:36,078][22500] Avg episode reward: [(0, '10.320'), (1, '9.870')] -[2023-10-09 12:02:36,331][23468] Updated weights for policy 0, policy_version 93743 (0.0009) -[2023-10-09 12:02:36,710][23468] Updated weights for policy 0, policy_version 93753 (0.0009) -[2023-10-09 12:02:39,455][23469] Updated weights for policy 1, policy_version 94281 (0.0009) -[2023-10-09 12:02:39,825][23469] Updated weights for policy 1, policy_version 94291 (0.0008) -[2023-10-09 12:02:40,195][23469] Updated weights for policy 1, policy_version 94301 (0.0009) -[2023-10-09 12:02:40,477][23468] Updated weights for policy 0, policy_version 93763 (0.0007) -[2023-10-09 12:02:40,850][23468] Updated weights for policy 0, policy_version 93773 (0.0008) -[2023-10-09 12:02:41,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 192577536. Throughput: 0: 1790.5, 1: 1798.7. Samples: 48153544. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-09 12:02:41,079][22500] Avg episode reward: [(0, '11.140'), (1, '10.000')] -[2023-10-09 12:02:41,216][23468] Updated weights for policy 0, policy_version 93783 (0.0008) -[2023-10-09 12:02:43,998][23469] Updated weights for policy 1, policy_version 94311 (0.0009) -[2023-10-09 12:02:44,367][23469] Updated weights for policy 1, policy_version 94321 (0.0011) -[2023-10-09 12:02:44,743][23469] Updated weights for policy 1, policy_version 94331 (0.0010) -[2023-10-09 12:02:45,004][23468] Updated weights for policy 0, policy_version 93793 (0.0008) -[2023-10-09 12:02:45,376][23468] Updated weights for policy 0, policy_version 93803 (0.0009) -[2023-10-09 12:02:45,747][23468] Updated weights for policy 0, policy_version 93813 (0.0010) -[2023-10-09 12:02:46,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 192643072. Throughput: 0: 1806.7, 1: 1780.4. Samples: 48174668. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-09 12:02:46,078][22500] Avg episode reward: [(0, '10.940'), (1, '10.390')] -[2023-10-09 12:02:46,114][23468] Updated weights for policy 0, policy_version 93823 (0.0008) -[2023-10-09 12:02:48,535][23469] Updated weights for policy 1, policy_version 94341 (0.0009) -[2023-10-09 12:02:48,913][23469] Updated weights for policy 1, policy_version 94351 (0.0008) -[2023-10-09 12:02:49,279][23469] Updated weights for policy 1, policy_version 94361 (0.0008) -[2023-10-09 12:02:49,896][23468] Updated weights for policy 0, policy_version 93833 (0.0008) -[2023-10-09 12:02:50,267][23468] Updated weights for policy 0, policy_version 93843 (0.0008) -[2023-10-09 12:02:50,639][23468] Updated weights for policy 0, policy_version 93853 (0.0009) -[2023-10-09 12:02:51,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 192741376. Throughput: 0: 1776.3, 1: 1800.2. Samples: 48185586. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-09 12:02:51,078][22500] Avg episode reward: [(0, '10.370'), (1, '10.550')] -[2023-10-09 12:02:53,019][23469] Updated weights for policy 1, policy_version 94371 (0.0010) -[2023-10-09 12:02:53,386][23469] Updated weights for policy 1, policy_version 94381 (0.0009) -[2023-10-09 12:02:53,758][23469] Updated weights for policy 1, policy_version 94391 (0.0008) -[2023-10-09 12:02:54,469][23468] Updated weights for policy 0, policy_version 93863 (0.0009) -[2023-10-09 12:02:54,838][23468] Updated weights for policy 0, policy_version 93873 (0.0007) -[2023-10-09 12:02:55,209][23468] Updated weights for policy 0, policy_version 93883 (0.0008) -[2023-10-09 12:02:56,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 192806912. Throughput: 0: 1800.2, 1: 1771.6. Samples: 48206784. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-09 12:02:56,078][22500] Avg episode reward: [(0, '10.340'), (1, '9.400')] -[2023-10-09 12:02:57,529][23469] Updated weights for policy 1, policy_version 94401 (0.0011) -[2023-10-09 12:02:57,959][23469] Updated weights for policy 1, policy_version 94411 (0.0008) -[2023-10-09 12:02:58,325][23469] Updated weights for policy 1, policy_version 94421 (0.0008) -[2023-10-09 12:02:58,687][23469] Updated weights for policy 1, policy_version 94431 (0.0008) -[2023-10-09 12:02:58,866][23468] Updated weights for policy 0, policy_version 93893 (0.0009) -[2023-10-09 12:02:59,233][23468] Updated weights for policy 0, policy_version 93903 (0.0009) -[2023-10-09 12:02:59,614][23468] Updated weights for policy 0, policy_version 93913 (0.0009) -[2023-10-09 12:03:01,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 192872448. Throughput: 0: 1777.4, 1: 1776.8. Samples: 48227876. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-09 12:03:01,078][22500] Avg episode reward: [(0, '9.600'), (1, '9.090')] -[2023-10-09 12:03:02,429][23469] Updated weights for policy 1, policy_version 94441 (0.0007) -[2023-10-09 12:03:02,800][23469] Updated weights for policy 1, policy_version 94451 (0.0009) -[2023-10-09 12:03:03,170][23469] Updated weights for policy 1, policy_version 94461 (0.0008) -[2023-10-09 12:03:03,431][23468] Updated weights for policy 0, policy_version 93923 (0.0010) -[2023-10-09 12:03:03,802][23468] Updated weights for policy 0, policy_version 93933 (0.0007) -[2023-10-09 12:03:04,176][23468] Updated weights for policy 0, policy_version 93943 (0.0007) -[2023-10-09 12:03:06,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 192937984. Throughput: 0: 1795.7, 1: 1771.2. Samples: 48238858. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-09 12:03:06,078][22500] Avg episode reward: [(0, '11.080'), (1, '9.950')] -[2023-10-09 12:03:06,883][23469] Updated weights for policy 1, policy_version 94471 (0.0008) -[2023-10-09 12:03:07,266][23469] Updated weights for policy 1, policy_version 94481 (0.0008) -[2023-10-09 12:03:07,634][23469] Updated weights for policy 1, policy_version 94491 (0.0009) -[2023-10-09 12:03:07,909][23468] Updated weights for policy 0, policy_version 93953 (0.0007) -[2023-10-09 12:03:08,320][23468] Updated weights for policy 0, policy_version 93963 (0.0009) -[2023-10-09 12:03:08,699][23468] Updated weights for policy 0, policy_version 93973 (0.0009) -[2023-10-09 12:03:09,067][23468] Updated weights for policy 0, policy_version 93983 (0.0008) -[2023-10-09 12:03:11,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 193003520. Throughput: 0: 1775.5, 1: 1772.7. Samples: 48259736. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-09 12:03:11,078][22500] Avg episode reward: [(0, '10.870'), (1, '10.160')] -[2023-10-09 12:03:11,503][23469] Updated weights for policy 1, policy_version 94501 (0.0008) -[2023-10-09 12:03:11,865][23469] Updated weights for policy 1, policy_version 94511 (0.0009) -[2023-10-09 12:03:12,238][23469] Updated weights for policy 1, policy_version 94521 (0.0008) -[2023-10-09 12:03:12,733][23468] Updated weights for policy 0, policy_version 93993 (0.0007) -[2023-10-09 12:03:13,105][23468] Updated weights for policy 0, policy_version 94003 (0.0008) -[2023-10-09 12:03:13,466][23468] Updated weights for policy 0, policy_version 94013 (0.0008) -[2023-10-09 12:03:15,973][23469] Updated weights for policy 1, policy_version 94531 (0.0008) -[2023-10-09 12:03:16,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 193069056. Throughput: 0: 1779.7, 1: 1793.9. Samples: 48282194. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-09 12:03:16,078][22500] Avg episode reward: [(0, '11.180'), (1, '10.160')] -[2023-10-09 12:03:16,342][23469] Updated weights for policy 1, policy_version 94541 (0.0008) -[2023-10-09 12:03:16,709][23469] Updated weights for policy 1, policy_version 94551 (0.0007) -[2023-10-09 12:03:17,206][23468] Updated weights for policy 0, policy_version 94023 (0.0009) -[2023-10-09 12:03:17,581][23468] Updated weights for policy 0, policy_version 94033 (0.0008) -[2023-10-09 12:03:17,950][23468] Updated weights for policy 0, policy_version 94043 (0.0009) -[2023-10-09 12:03:20,642][23469] Updated weights for policy 1, policy_version 94561 (0.0008) -[2023-10-09 12:03:21,026][23469] Updated weights for policy 1, policy_version 94571 (0.0010) -[2023-10-09 12:03:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 193134592. Throughput: 0: 1780.6, 1: 1771.0. Samples: 48291824. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-09 12:03:21,078][22500] Avg episode reward: [(0, '10.910'), (1, '9.990')] -[2023-10-09 12:03:21,394][23469] Updated weights for policy 1, policy_version 94581 (0.0008) -[2023-10-09 12:03:21,745][23468] Updated weights for policy 0, policy_version 94053 (0.0010) -[2023-10-09 12:03:21,762][23469] Updated weights for policy 1, policy_version 94591 (0.0009) -[2023-10-09 12:03:22,117][23468] Updated weights for policy 0, policy_version 94063 (0.0010) -[2023-10-09 12:03:22,488][23468] Updated weights for policy 0, policy_version 94073 (0.0010) -[2023-10-09 12:03:25,538][23469] Updated weights for policy 1, policy_version 94601 (0.0010) -[2023-10-09 12:03:25,912][23469] Updated weights for policy 1, policy_version 94611 (0.0009) -[2023-10-09 12:03:26,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 193200128. Throughput: 0: 1778.6, 1: 1786.7. Samples: 48313982. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 12:03:26,078][22500] Avg episode reward: [(0, '10.500'), (1, '9.400')] -[2023-10-09 12:03:26,293][23469] Updated weights for policy 1, policy_version 94621 (0.0009) -[2023-10-09 12:03:26,352][23468] Updated weights for policy 0, policy_version 94083 (0.0008) -[2023-10-09 12:03:26,730][23468] Updated weights for policy 0, policy_version 94093 (0.0007) -[2023-10-09 12:03:27,106][23468] Updated weights for policy 0, policy_version 94103 (0.0007) -[2023-10-09 12:03:30,005][23469] Updated weights for policy 1, policy_version 94631 (0.0008) -[2023-10-09 12:03:30,371][23469] Updated weights for policy 1, policy_version 94641 (0.0008) -[2023-10-09 12:03:30,741][23469] Updated weights for policy 1, policy_version 94651 (0.0010) -[2023-10-09 12:03:30,822][23468] Updated weights for policy 0, policy_version 94113 (0.0008) -[2023-10-09 12:03:31,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 193298432. Throughput: 0: 1792.9, 1: 1776.0. Samples: 48335268. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 12:03:31,078][22500] Avg episode reward: [(0, '11.040'), (1, '9.530')] -[2023-10-09 12:03:31,198][23468] Updated weights for policy 0, policy_version 94123 (0.0007) -[2023-10-09 12:03:31,568][23468] Updated weights for policy 0, policy_version 94133 (0.0008) -[2023-10-09 12:03:31,949][23468] Updated weights for policy 0, policy_version 94143 (0.0010) -[2023-10-09 12:03:34,344][23469] Updated weights for policy 1, policy_version 94661 (0.0010) -[2023-10-09 12:03:34,716][23469] Updated weights for policy 1, policy_version 94671 (0.0010) -[2023-10-09 12:03:35,093][23469] Updated weights for policy 1, policy_version 94681 (0.0009) -[2023-10-09 12:03:35,743][23468] Updated weights for policy 0, policy_version 94153 (0.0011) -[2023-10-09 12:03:36,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 193363968. Throughput: 0: 1784.5, 1: 1786.0. Samples: 48346258. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 12:03:36,078][22500] Avg episode reward: [(0, '11.100'), (1, '10.000')] -[2023-10-09 12:03:36,122][23468] Updated weights for policy 0, policy_version 94163 (0.0009) -[2023-10-09 12:03:36,492][23468] Updated weights for policy 0, policy_version 94173 (0.0009) -[2023-10-09 12:03:38,818][23469] Updated weights for policy 1, policy_version 94691 (0.0009) -[2023-10-09 12:03:39,180][23469] Updated weights for policy 1, policy_version 94701 (0.0007) -[2023-10-09 12:03:39,555][23469] Updated weights for policy 1, policy_version 94711 (0.0008) -[2023-10-09 12:03:40,268][23468] Updated weights for policy 0, policy_version 94183 (0.0008) -[2023-10-09 12:03:40,638][23468] Updated weights for policy 0, policy_version 94193 (0.0007) -[2023-10-09 12:03:41,012][23468] Updated weights for policy 0, policy_version 94203 (0.0007) -[2023-10-09 12:03:41,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 193429504. Throughput: 0: 1783.4, 1: 1781.6. Samples: 48367212. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 12:03:41,078][22500] Avg episode reward: [(0, '10.480'), (1, '10.080')] -[2023-10-09 12:03:43,397][23469] Updated weights for policy 1, policy_version 94721 (0.0009) -[2023-10-09 12:03:43,820][23469] Updated weights for policy 1, policy_version 94731 (0.0008) -[2023-10-09 12:03:44,194][23469] Updated weights for policy 1, policy_version 94741 (0.0008) -[2023-10-09 12:03:44,560][23469] Updated weights for policy 1, policy_version 94751 (0.0007) -[2023-10-09 12:03:44,737][23468] Updated weights for policy 0, policy_version 94213 (0.0009) -[2023-10-09 12:03:45,110][23468] Updated weights for policy 0, policy_version 94223 (0.0008) -[2023-10-09 12:03:45,479][23468] Updated weights for policy 0, policy_version 94233 (0.0009) -[2023-10-09 12:03:46,077][22500] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 193527808. Throughput: 0: 1795.1, 1: 1773.4. Samples: 48388458. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 12:03:46,078][22500] Avg episode reward: [(0, '10.480'), (1, '9.880')] -[2023-10-09 12:03:48,301][23469] Updated weights for policy 1, policy_version 94761 (0.0009) -[2023-10-09 12:03:48,664][23469] Updated weights for policy 1, policy_version 94771 (0.0009) -[2023-10-09 12:03:49,033][23469] Updated weights for policy 1, policy_version 94781 (0.0009) -[2023-10-09 12:03:49,171][23468] Updated weights for policy 0, policy_version 94243 (0.0009) -[2023-10-09 12:03:49,554][23468] Updated weights for policy 0, policy_version 94253 (0.0011) -[2023-10-09 12:03:49,921][23468] Updated weights for policy 0, policy_version 94263 (0.0011) -[2023-10-09 12:03:51,078][22500] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 193593344. Throughput: 0: 1782.7, 1: 1789.0. Samples: 48399582. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 12:03:51,079][22500] Avg episode reward: [(0, '9.740'), (1, '9.790')] -[2023-10-09 12:03:52,878][23469] Updated weights for policy 1, policy_version 94791 (0.0009) -[2023-10-09 12:03:53,250][23469] Updated weights for policy 1, policy_version 94801 (0.0010) -[2023-10-09 12:03:53,624][23469] Updated weights for policy 1, policy_version 94811 (0.0009) -[2023-10-09 12:03:53,673][23468] Updated weights for policy 0, policy_version 94273 (0.0010) -[2023-10-09 12:03:54,094][23468] Updated weights for policy 0, policy_version 94283 (0.0011) -[2023-10-09 12:03:54,462][23468] Updated weights for policy 0, policy_version 94293 (0.0010) -[2023-10-09 12:03:54,833][23468] Updated weights for policy 0, policy_version 94303 (0.0007) -[2023-10-09 12:03:56,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 193658880. Throughput: 0: 1800.1, 1: 1778.4. Samples: 48420770. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 12:03:56,078][22500] Avg episode reward: [(0, '10.070'), (1, '9.390')] -[2023-10-09 12:03:57,519][23469] Updated weights for policy 1, policy_version 94821 (0.0010) -[2023-10-09 12:03:57,891][23469] Updated weights for policy 1, policy_version 94831 (0.0009) -[2023-10-09 12:03:58,259][23469] Updated weights for policy 1, policy_version 94841 (0.0009) -[2023-10-09 12:03:58,467][23468] Updated weights for policy 0, policy_version 94313 (0.0007) -[2023-10-09 12:03:58,840][23468] Updated weights for policy 0, policy_version 94323 (0.0008) -[2023-10-09 12:03:59,205][23468] Updated weights for policy 0, policy_version 94333 (0.0010) -[2023-10-09 12:04:01,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 193724416. Throughput: 0: 1778.8, 1: 1783.0. Samples: 48442474. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 12:04:01,078][22500] Avg episode reward: [(0, '10.700'), (1, '10.160')] -[2023-10-09 12:04:01,982][23469] Updated weights for policy 1, policy_version 94851 (0.0007) -[2023-10-09 12:04:02,352][23469] Updated weights for policy 1, policy_version 94861 (0.0010) -[2023-10-09 12:04:02,729][23469] Updated weights for policy 1, policy_version 94871 (0.0007) -[2023-10-09 12:04:03,038][23468] Updated weights for policy 0, policy_version 94343 (0.0008) -[2023-10-09 12:04:03,418][23468] Updated weights for policy 0, policy_version 94353 (0.0007) -[2023-10-09 12:04:03,780][23468] Updated weights for policy 0, policy_version 94363 (0.0008) -[2023-10-09 12:04:06,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 193789952. Throughput: 0: 1796.4, 1: 1780.4. Samples: 48452784. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 12:04:06,078][22500] Avg episode reward: [(0, '10.260'), (1, '9.850')] -[2023-10-09 12:04:06,473][23469] Updated weights for policy 1, policy_version 94881 (0.0009) -[2023-10-09 12:04:06,845][23469] Updated weights for policy 1, policy_version 94891 (0.0011) -[2023-10-09 12:04:07,220][23469] Updated weights for policy 1, policy_version 94901 (0.0009) -[2023-10-09 12:04:07,492][23468] Updated weights for policy 0, policy_version 94373 (0.0008) -[2023-10-09 12:04:07,580][23469] Updated weights for policy 1, policy_version 94911 (0.0007) -[2023-10-09 12:04:07,864][23468] Updated weights for policy 0, policy_version 94383 (0.0008) -[2023-10-09 12:04:08,235][23468] Updated weights for policy 0, policy_version 94393 (0.0009) -[2023-10-09 12:04:11,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 193855488. Throughput: 0: 1780.3, 1: 1784.1. Samples: 48474378. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 12:04:11,078][22500] Avg episode reward: [(0, '10.800'), (1, '9.820')] -[2023-10-09 12:04:11,328][23469] Updated weights for policy 1, policy_version 94921 (0.0007) -[2023-10-09 12:04:11,697][23469] Updated weights for policy 1, policy_version 94931 (0.0009) -[2023-10-09 12:04:12,017][23468] Updated weights for policy 0, policy_version 94403 (0.0010) -[2023-10-09 12:04:12,077][23469] Updated weights for policy 1, policy_version 94941 (0.0009) -[2023-10-09 12:04:12,385][23468] Updated weights for policy 0, policy_version 94413 (0.0007) -[2023-10-09 12:04:12,763][23468] Updated weights for policy 0, policy_version 94423 (0.0008) -[2023-10-09 12:04:15,769][23469] Updated weights for policy 1, policy_version 94951 (0.0008) -[2023-10-09 12:04:16,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 193921024. Throughput: 0: 1778.7, 1: 1804.5. Samples: 48496514. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 12:04:16,078][22500] Avg episode reward: [(0, '10.300'), (1, '9.680')] -[2023-10-09 12:04:16,087][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000094432_96698368.pth... -[2023-10-09 12:04:16,127][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000092768_94994432.pth -[2023-10-09 12:04:16,133][23469] Updated weights for policy 1, policy_version 94961 (0.0007) -[2023-10-09 12:04:16,467][23468] Updated weights for policy 0, policy_version 94433 (0.0008) -[2023-10-09 12:04:16,505][23469] Updated weights for policy 1, policy_version 94971 (0.0007) -[2023-10-09 12:04:16,689][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000094976_97255424.pth... -[2023-10-09 12:04:16,718][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000093280_95518720.pth -[2023-10-09 12:04:16,842][23468] Updated weights for policy 0, policy_version 94443 (0.0009) -[2023-10-09 12:04:17,222][23468] Updated weights for policy 0, policy_version 94453 (0.0010) -[2023-10-09 12:04:17,600][23468] Updated weights for policy 0, policy_version 94463 (0.0008) -[2023-10-09 12:04:20,169][23469] Updated weights for policy 1, policy_version 94981 (0.0008) -[2023-10-09 12:04:20,529][23469] Updated weights for policy 1, policy_version 94991 (0.0010) -[2023-10-09 12:04:20,904][23469] Updated weights for policy 1, policy_version 95001 (0.0010) -[2023-10-09 12:04:21,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 193986560. Throughput: 0: 1779.9, 1: 1784.5. Samples: 48506658. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 12:04:21,078][22500] Avg episode reward: [(0, '10.570'), (1, '10.400')] -[2023-10-09 12:04:21,454][23468] Updated weights for policy 0, policy_version 94473 (0.0009) -[2023-10-09 12:04:21,826][23468] Updated weights for policy 0, policy_version 94483 (0.0009) -[2023-10-09 12:04:22,201][23468] Updated weights for policy 0, policy_version 94493 (0.0011) -[2023-10-09 12:04:24,506][23469] Updated weights for policy 1, policy_version 95011 (0.0009) -[2023-10-09 12:04:24,874][23469] Updated weights for policy 1, policy_version 95021 (0.0009) -[2023-10-09 12:04:25,240][23469] Updated weights for policy 1, policy_version 95031 (0.0009) -[2023-10-09 12:04:26,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 194084864. Throughput: 0: 1778.7, 1: 1805.2. Samples: 48528486. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:04:26,078][22500] Avg episode reward: [(0, '11.150'), (1, '10.140')] -[2023-10-09 12:04:26,086][23468] Updated weights for policy 0, policy_version 94503 (0.0008) -[2023-10-09 12:04:26,460][23468] Updated weights for policy 0, policy_version 94513 (0.0007) -[2023-10-09 12:04:26,825][23468] Updated weights for policy 0, policy_version 94523 (0.0008) -[2023-10-09 12:04:29,070][23469] Updated weights for policy 1, policy_version 95041 (0.0010) -[2023-10-09 12:04:29,461][23469] Updated weights for policy 1, policy_version 95051 (0.0007) -[2023-10-09 12:04:29,828][23469] Updated weights for policy 1, policy_version 95061 (0.0007) -[2023-10-09 12:04:30,200][23469] Updated weights for policy 1, policy_version 95071 (0.0008) -[2023-10-09 12:04:30,406][23468] Updated weights for policy 0, policy_version 94533 (0.0008) -[2023-10-09 12:04:30,783][23468] Updated weights for policy 0, policy_version 94543 (0.0008) -[2023-10-09 12:04:31,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 194150400. Throughput: 0: 1797.7, 1: 1792.5. Samples: 48550016. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:04:31,078][22500] Avg episode reward: [(0, '11.200'), (1, '10.200')] -[2023-10-09 12:04:31,149][23468] Updated weights for policy 0, policy_version 94553 (0.0008) -[2023-10-09 12:04:33,736][23469] Updated weights for policy 1, policy_version 95081 (0.0008) -[2023-10-09 12:04:34,103][23469] Updated weights for policy 1, policy_version 95091 (0.0008) -[2023-10-09 12:04:34,467][23469] Updated weights for policy 1, policy_version 95101 (0.0007) -[2023-10-09 12:04:34,897][23468] Updated weights for policy 0, policy_version 94563 (0.0007) -[2023-10-09 12:04:35,266][23468] Updated weights for policy 0, policy_version 94573 (0.0009) -[2023-10-09 12:04:35,639][23468] Updated weights for policy 0, policy_version 94583 (0.0008) -[2023-10-09 12:04:36,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 194248704. Throughput: 0: 1780.6, 1: 1805.8. Samples: 48560972. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:04:36,079][22500] Avg episode reward: [(0, '11.290'), (1, '9.330')] -[2023-10-09 12:04:38,076][23469] Updated weights for policy 1, policy_version 95111 (0.0007) -[2023-10-09 12:04:38,451][23469] Updated weights for policy 1, policy_version 95121 (0.0010) -[2023-10-09 12:04:38,815][23469] Updated weights for policy 1, policy_version 95131 (0.0010) -[2023-10-09 12:04:39,529][23468] Updated weights for policy 0, policy_version 94593 (0.0010) -[2023-10-09 12:04:39,938][23468] Updated weights for policy 0, policy_version 94603 (0.0008) -[2023-10-09 12:04:40,309][23468] Updated weights for policy 0, policy_version 94613 (0.0007) -[2023-10-09 12:04:40,681][23468] Updated weights for policy 0, policy_version 94623 (0.0009) -[2023-10-09 12:04:41,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 194314240. Throughput: 0: 1800.0, 1: 1799.8. Samples: 48582758. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:04:41,078][22500] Avg episode reward: [(0, '10.950'), (1, '8.760')] -[2023-10-09 12:04:42,549][23469] Updated weights for policy 1, policy_version 95141 (0.0008) -[2023-10-09 12:04:42,910][23469] Updated weights for policy 1, policy_version 95151 (0.0007) -[2023-10-09 12:04:43,287][23469] Updated weights for policy 1, policy_version 95161 (0.0009) -[2023-10-09 12:04:44,438][23468] Updated weights for policy 0, policy_version 94633 (0.0009) -[2023-10-09 12:04:44,815][23468] Updated weights for policy 0, policy_version 94643 (0.0009) -[2023-10-09 12:04:45,193][23468] Updated weights for policy 0, policy_version 94653 (0.0009) -[2023-10-09 12:04:46,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 194379776. Throughput: 0: 1778.9, 1: 1800.9. Samples: 48603564. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:04:46,078][22500] Avg episode reward: [(0, '11.030'), (1, '9.140')] -[2023-10-09 12:04:46,987][23469] Updated weights for policy 1, policy_version 95171 (0.0010) -[2023-10-09 12:04:47,358][23469] Updated weights for policy 1, policy_version 95181 (0.0009) -[2023-10-09 12:04:47,726][23469] Updated weights for policy 1, policy_version 95191 (0.0009) -[2023-10-09 12:04:48,920][23468] Updated weights for policy 0, policy_version 94663 (0.0009) -[2023-10-09 12:04:49,303][23468] Updated weights for policy 0, policy_version 94673 (0.0009) -[2023-10-09 12:04:49,670][23468] Updated weights for policy 0, policy_version 94683 (0.0009) -[2023-10-09 12:04:51,078][22500] Fps is (10 sec: 13106.7, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 194445312. Throughput: 0: 1795.0, 1: 1802.8. Samples: 48614686. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:04:51,079][22500] Avg episode reward: [(0, '10.850'), (1, '10.080')] -[2023-10-09 12:04:51,530][23469] Updated weights for policy 1, policy_version 95201 (0.0008) -[2023-10-09 12:04:51,903][23469] Updated weights for policy 1, policy_version 95211 (0.0011) -[2023-10-09 12:04:52,271][23469] Updated weights for policy 1, policy_version 95221 (0.0011) -[2023-10-09 12:04:52,639][23469] Updated weights for policy 1, policy_version 95231 (0.0011) -[2023-10-09 12:04:53,449][23468] Updated weights for policy 0, policy_version 94693 (0.0007) -[2023-10-09 12:04:53,822][23468] Updated weights for policy 0, policy_version 94703 (0.0008) -[2023-10-09 12:04:54,193][23468] Updated weights for policy 0, policy_version 94713 (0.0008) -[2023-10-09 12:04:56,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 194510848. Throughput: 0: 1787.8, 1: 1801.2. Samples: 48635882. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:04:56,079][22500] Avg episode reward: [(0, '10.610'), (1, '10.200')] -[2023-10-09 12:04:56,469][23469] Updated weights for policy 1, policy_version 95241 (0.0008) -[2023-10-09 12:04:56,846][23469] Updated weights for policy 1, policy_version 95251 (0.0007) -[2023-10-09 12:04:57,207][23469] Updated weights for policy 1, policy_version 95261 (0.0007) -[2023-10-09 12:04:58,004][23468] Updated weights for policy 0, policy_version 94723 (0.0008) -[2023-10-09 12:04:58,375][23468] Updated weights for policy 0, policy_version 94733 (0.0010) -[2023-10-09 12:04:58,743][23468] Updated weights for policy 0, policy_version 94743 (0.0008) -[2023-10-09 12:05:00,848][23469] Updated weights for policy 1, policy_version 95271 (0.0009) -[2023-10-09 12:05:01,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 194576384. Throughput: 0: 1776.7, 1: 1805.8. Samples: 48657726. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:05:01,078][22500] Avg episode reward: [(0, '10.830'), (1, '10.760')] -[2023-10-09 12:05:01,219][23469] Updated weights for policy 1, policy_version 95281 (0.0010) -[2023-10-09 12:05:01,581][23469] Updated weights for policy 1, policy_version 95291 (0.0011) -[2023-10-09 12:05:02,414][23468] Updated weights for policy 0, policy_version 94753 (0.0008) -[2023-10-09 12:05:02,781][23468] Updated weights for policy 0, policy_version 94763 (0.0009) -[2023-10-09 12:05:03,155][23468] Updated weights for policy 0, policy_version 94773 (0.0007) -[2023-10-09 12:05:03,538][23468] Updated weights for policy 0, policy_version 94783 (0.0008) -[2023-10-09 12:05:05,381][23469] Updated weights for policy 1, policy_version 95301 (0.0011) -[2023-10-09 12:05:05,745][23469] Updated weights for policy 1, policy_version 95311 (0.0011) -[2023-10-09 12:05:06,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 194641920. Throughput: 0: 1787.7, 1: 1801.8. Samples: 48668188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:05:06,078][22500] Avg episode reward: [(0, '10.380'), (1, '10.250')] -[2023-10-09 12:05:06,119][23469] Updated weights for policy 1, policy_version 95321 (0.0011) -[2023-10-09 12:05:07,184][23468] Updated weights for policy 0, policy_version 94793 (0.0008) -[2023-10-09 12:05:07,562][23468] Updated weights for policy 0, policy_version 94803 (0.0007) -[2023-10-09 12:05:07,952][23468] Updated weights for policy 0, policy_version 94813 (0.0008) -[2023-10-09 12:05:09,934][23469] Updated weights for policy 1, policy_version 95331 (0.0011) -[2023-10-09 12:05:10,300][23469] Updated weights for policy 1, policy_version 95341 (0.0010) -[2023-10-09 12:05:10,676][23469] Updated weights for policy 1, policy_version 95351 (0.0009) -[2023-10-09 12:05:11,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 194740224. Throughput: 0: 1787.8, 1: 1807.3. Samples: 48690266. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:05:11,078][22500] Avg episode reward: [(0, '10.820'), (1, '9.690')] -[2023-10-09 12:05:11,570][23468] Updated weights for policy 0, policy_version 94823 (0.0011) -[2023-10-09 12:05:11,940][23468] Updated weights for policy 0, policy_version 94833 (0.0009) -[2023-10-09 12:05:12,316][23468] Updated weights for policy 0, policy_version 94843 (0.0010) -[2023-10-09 12:05:14,368][23469] Updated weights for policy 1, policy_version 95361 (0.0010) -[2023-10-09 12:05:14,781][23469] Updated weights for policy 1, policy_version 95371 (0.0008) -[2023-10-09 12:05:15,154][23469] Updated weights for policy 1, policy_version 95381 (0.0008) -[2023-10-09 12:05:15,523][23469] Updated weights for policy 1, policy_version 95391 (0.0008) -[2023-10-09 12:05:16,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 194805760. Throughput: 0: 1787.1, 1: 1799.2. Samples: 48711398. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:05:16,078][22500] Avg episode reward: [(0, '11.260'), (1, '9.660')] -[2023-10-09 12:05:16,140][23468] Updated weights for policy 0, policy_version 94853 (0.0009) -[2023-10-09 12:05:16,522][23468] Updated weights for policy 0, policy_version 94863 (0.0007) -[2023-10-09 12:05:16,890][23468] Updated weights for policy 0, policy_version 94873 (0.0009) -[2023-10-09 12:05:19,024][23469] Updated weights for policy 1, policy_version 95401 (0.0008) -[2023-10-09 12:05:19,399][23469] Updated weights for policy 1, policy_version 95411 (0.0007) -[2023-10-09 12:05:19,764][23469] Updated weights for policy 1, policy_version 95421 (0.0008) -[2023-10-09 12:05:20,633][23468] Updated weights for policy 0, policy_version 94883 (0.0009) -[2023-10-09 12:05:21,004][23468] Updated weights for policy 0, policy_version 94893 (0.0010) -[2023-10-09 12:05:21,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 194871296. Throughput: 0: 1782.6, 1: 1811.4. Samples: 48722704. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:05:21,078][22500] Avg episode reward: [(0, '11.570'), (1, '9.730')] -[2023-10-09 12:05:21,380][23468] Updated weights for policy 0, policy_version 94903 (0.0010) -[2023-10-09 12:05:23,563][23469] Updated weights for policy 1, policy_version 95431 (0.0009) -[2023-10-09 12:05:23,937][23469] Updated weights for policy 1, policy_version 95441 (0.0008) -[2023-10-09 12:05:24,308][23469] Updated weights for policy 1, policy_version 95451 (0.0009) -[2023-10-09 12:05:25,309][23468] Updated weights for policy 0, policy_version 94913 (0.0009) -[2023-10-09 12:05:25,700][23468] Updated weights for policy 0, policy_version 94923 (0.0009) -[2023-10-09 12:05:26,070][23468] Updated weights for policy 0, policy_version 94933 (0.0011) -[2023-10-09 12:05:26,078][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 194936832. Throughput: 0: 1778.6, 1: 1800.2. Samples: 48743804. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 12:05:26,079][22500] Avg episode reward: [(0, '10.880'), (1, '9.710')] -[2023-10-09 12:05:26,438][23468] Updated weights for policy 0, policy_version 94943 (0.0009) -[2023-10-09 12:05:28,135][23469] Updated weights for policy 1, policy_version 95461 (0.0010) -[2023-10-09 12:05:28,494][23469] Updated weights for policy 1, policy_version 95471 (0.0008) -[2023-10-09 12:05:28,859][23469] Updated weights for policy 1, policy_version 95481 (0.0008) -[2023-10-09 12:05:30,236][23468] Updated weights for policy 0, policy_version 94953 (0.0008) -[2023-10-09 12:05:30,600][23468] Updated weights for policy 0, policy_version 94963 (0.0009) -[2023-10-09 12:05:30,979][23468] Updated weights for policy 0, policy_version 94973 (0.0010) -[2023-10-09 12:05:31,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 195002368. Throughput: 0: 1801.1, 1: 1801.5. Samples: 48765682. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 12:05:31,079][22500] Avg episode reward: [(0, '10.330'), (1, '9.710')] -[2023-10-09 12:05:32,553][23469] Updated weights for policy 1, policy_version 95491 (0.0007) -[2023-10-09 12:05:32,919][23469] Updated weights for policy 1, policy_version 95501 (0.0008) -[2023-10-09 12:05:33,288][23469] Updated weights for policy 1, policy_version 95511 (0.0008) -[2023-10-09 12:05:34,710][23468] Updated weights for policy 0, policy_version 94983 (0.0009) -[2023-10-09 12:05:35,084][23468] Updated weights for policy 0, policy_version 94993 (0.0009) -[2023-10-09 12:05:35,456][23468] Updated weights for policy 0, policy_version 95003 (0.0010) -[2023-10-09 12:05:36,077][22500] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 195100672. Throughput: 0: 1779.4, 1: 1800.6. Samples: 48775786. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 12:05:36,078][22500] Avg episode reward: [(0, '10.480'), (1, '10.020')] -[2023-10-09 12:05:37,034][23469] Updated weights for policy 1, policy_version 95521 (0.0007) -[2023-10-09 12:05:37,403][23469] Updated weights for policy 1, policy_version 95531 (0.0007) -[2023-10-09 12:05:37,772][23469] Updated weights for policy 1, policy_version 95541 (0.0007) -[2023-10-09 12:05:38,147][23469] Updated weights for policy 1, policy_version 95551 (0.0009) -[2023-10-09 12:05:39,289][23468] Updated weights for policy 0, policy_version 95013 (0.0008) -[2023-10-09 12:05:39,665][23468] Updated weights for policy 0, policy_version 95023 (0.0007) -[2023-10-09 12:05:40,044][23468] Updated weights for policy 0, policy_version 95033 (0.0007) -[2023-10-09 12:05:41,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 195166208. Throughput: 0: 1798.3, 1: 1802.8. Samples: 48797930. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 12:05:41,079][22500] Avg episode reward: [(0, '10.550'), (1, '9.500')] -[2023-10-09 12:05:41,902][23469] Updated weights for policy 1, policy_version 95561 (0.0008) -[2023-10-09 12:05:42,278][23469] Updated weights for policy 1, policy_version 95571 (0.0009) -[2023-10-09 12:05:42,650][23469] Updated weights for policy 1, policy_version 95581 (0.0009) -[2023-10-09 12:05:43,888][23468] Updated weights for policy 0, policy_version 95043 (0.0008) -[2023-10-09 12:05:44,255][23468] Updated weights for policy 0, policy_version 95053 (0.0008) -[2023-10-09 12:05:44,620][23468] Updated weights for policy 0, policy_version 95063 (0.0007) -[2023-10-09 12:05:46,078][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 195231744. Throughput: 0: 1774.7, 1: 1804.4. Samples: 48818788. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 12:05:46,079][22500] Avg episode reward: [(0, '11.170'), (1, '9.740')] -[2023-10-09 12:05:46,438][23469] Updated weights for policy 1, policy_version 95591 (0.0008) -[2023-10-09 12:05:46,802][23469] Updated weights for policy 1, policy_version 95601 (0.0009) -[2023-10-09 12:05:47,176][23469] Updated weights for policy 1, policy_version 95611 (0.0007) -[2023-10-09 12:05:48,592][23468] Updated weights for policy 0, policy_version 95073 (0.0007) -[2023-10-09 12:05:48,959][23468] Updated weights for policy 0, policy_version 95083 (0.0010) -[2023-10-09 12:05:49,342][23468] Updated weights for policy 0, policy_version 95093 (0.0011) -[2023-10-09 12:05:49,721][23468] Updated weights for policy 0, policy_version 95103 (0.0008) -[2023-10-09 12:05:50,850][23469] Updated weights for policy 1, policy_version 95621 (0.0008) -[2023-10-09 12:05:51,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.6, 300 sec: 14329.1). Total num frames: 195297280. Throughput: 0: 1791.2, 1: 1799.1. Samples: 48829754. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 12:05:51,078][22500] Avg episode reward: [(0, '11.250'), (1, '9.880')] -[2023-10-09 12:05:51,219][23469] Updated weights for policy 1, policy_version 95631 (0.0010) -[2023-10-09 12:05:51,595][23469] Updated weights for policy 1, policy_version 95641 (0.0009) -[2023-10-09 12:05:53,580][23468] Updated weights for policy 0, policy_version 95113 (0.0009) -[2023-10-09 12:05:53,957][23468] Updated weights for policy 0, policy_version 95123 (0.0009) -[2023-10-09 12:05:54,333][23468] Updated weights for policy 0, policy_version 95133 (0.0009) -[2023-10-09 12:05:55,327][23469] Updated weights for policy 1, policy_version 95651 (0.0009) -[2023-10-09 12:05:55,704][23469] Updated weights for policy 1, policy_version 95661 (0.0010) -[2023-10-09 12:05:56,066][23469] Updated weights for policy 1, policy_version 95671 (0.0008) -[2023-10-09 12:05:56,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 195362816. Throughput: 0: 1766.5, 1: 1802.5. Samples: 48850870. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 12:05:56,078][22500] Avg episode reward: [(0, '10.900'), (1, '9.320')] -[2023-10-09 12:05:57,978][23468] Updated weights for policy 0, policy_version 95143 (0.0009) -[2023-10-09 12:05:58,352][23468] Updated weights for policy 0, policy_version 95153 (0.0009) -[2023-10-09 12:05:58,724][23468] Updated weights for policy 0, policy_version 95163 (0.0007) -[2023-10-09 12:05:59,926][23469] Updated weights for policy 1, policy_version 95681 (0.0008) -[2023-10-09 12:06:00,332][23469] Updated weights for policy 1, policy_version 95691 (0.0008) -[2023-10-09 12:06:00,706][23469] Updated weights for policy 1, policy_version 95701 (0.0008) -[2023-10-09 12:06:01,077][23469] Updated weights for policy 1, policy_version 95711 (0.0008) -[2023-10-09 12:06:01,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 195428352. Throughput: 0: 1761.0, 1: 1810.4. Samples: 48872108. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 12:06:01,078][22500] Avg episode reward: [(0, '10.580'), (1, '8.790')] -[2023-10-09 12:06:02,458][23468] Updated weights for policy 0, policy_version 95173 (0.0007) -[2023-10-09 12:06:02,826][23468] Updated weights for policy 0, policy_version 95183 (0.0008) -[2023-10-09 12:06:03,200][23468] Updated weights for policy 0, policy_version 95193 (0.0007) -[2023-10-09 12:06:04,764][23469] Updated weights for policy 1, policy_version 95721 (0.0008) -[2023-10-09 12:06:05,131][23469] Updated weights for policy 1, policy_version 95731 (0.0007) -[2023-10-09 12:06:05,500][23469] Updated weights for policy 1, policy_version 95741 (0.0007) -[2023-10-09 12:06:06,077][22500] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 195526656. Throughput: 0: 1774.8, 1: 1796.8. Samples: 48883428. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 12:06:06,079][22500] Avg episode reward: [(0, '10.400'), (1, '9.080')] -[2023-10-09 12:06:06,966][23468] Updated weights for policy 0, policy_version 95203 (0.0007) -[2023-10-09 12:06:07,343][23468] Updated weights for policy 0, policy_version 95213 (0.0007) -[2023-10-09 12:06:07,713][23468] Updated weights for policy 0, policy_version 95223 (0.0008) -[2023-10-09 12:06:09,100][23469] Updated weights for policy 1, policy_version 95751 (0.0009) -[2023-10-09 12:06:09,459][23469] Updated weights for policy 1, policy_version 95761 (0.0009) -[2023-10-09 12:06:09,833][23469] Updated weights for policy 1, policy_version 95771 (0.0008) -[2023-10-09 12:06:11,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 195592192. Throughput: 0: 1770.5, 1: 1804.2. Samples: 48904664. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 12:06:11,078][22500] Avg episode reward: [(0, '11.770'), (1, '9.060')] -[2023-10-09 12:06:11,371][23468] Updated weights for policy 0, policy_version 95233 (0.0008) -[2023-10-09 12:06:11,790][23468] Updated weights for policy 0, policy_version 95243 (0.0009) -[2023-10-09 12:06:12,165][23468] Updated weights for policy 0, policy_version 95253 (0.0008) -[2023-10-09 12:06:12,538][23468] Updated weights for policy 0, policy_version 95263 (0.0008) -[2023-10-09 12:06:13,491][23469] Updated weights for policy 1, policy_version 95781 (0.0007) -[2023-10-09 12:06:13,867][23469] Updated weights for policy 1, policy_version 95791 (0.0009) -[2023-10-09 12:06:14,226][23469] Updated weights for policy 1, policy_version 95801 (0.0007) -[2023-10-09 12:06:16,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 195657728. Throughput: 0: 1786.9, 1: 1796.6. Samples: 48926938. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 12:06:16,078][22500] Avg episode reward: [(0, '11.560'), (1, '9.500')] -[2023-10-09 12:06:16,084][23468] Updated weights for policy 0, policy_version 95273 (0.0011) -[2023-10-09 12:06:16,085][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000095808_98107392.pth... -[2023-10-09 12:06:16,114][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000094112_96370688.pth -[2023-10-09 12:06:16,447][23468] Updated weights for policy 0, policy_version 95283 (0.0009) -[2023-10-09 12:06:16,818][23468] Updated weights for policy 0, policy_version 95293 (0.0010) -[2023-10-09 12:06:16,928][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000095296_97583104.pth... -[2023-10-09 12:06:16,965][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000093600_95846400.pth -[2023-10-09 12:06:17,954][23469] Updated weights for policy 1, policy_version 95811 (0.0010) -[2023-10-09 12:06:18,318][23469] Updated weights for policy 1, policy_version 95821 (0.0009) -[2023-10-09 12:06:18,700][23469] Updated weights for policy 1, policy_version 95831 (0.0007) -[2023-10-09 12:06:20,747][23468] Updated weights for policy 0, policy_version 95303 (0.0009) -[2023-10-09 12:06:21,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 195723264. Throughput: 0: 1772.7, 1: 1816.4. Samples: 48937294. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 12:06:21,078][22500] Avg episode reward: [(0, '11.590'), (1, '9.990')] -[2023-10-09 12:06:21,124][23468] Updated weights for policy 0, policy_version 95313 (0.0008) -[2023-10-09 12:06:21,491][23468] Updated weights for policy 0, policy_version 95323 (0.0010) -[2023-10-09 12:06:22,454][23469] Updated weights for policy 1, policy_version 95841 (0.0007) -[2023-10-09 12:06:22,817][23469] Updated weights for policy 1, policy_version 95851 (0.0009) -[2023-10-09 12:06:23,187][23469] Updated weights for policy 1, policy_version 95861 (0.0009) -[2023-10-09 12:06:23,561][23469] Updated weights for policy 1, policy_version 95871 (0.0008) -[2023-10-09 12:06:25,268][23468] Updated weights for policy 0, policy_version 95333 (0.0009) -[2023-10-09 12:06:25,637][23468] Updated weights for policy 0, policy_version 95343 (0.0009) -[2023-10-09 12:06:26,016][23468] Updated weights for policy 0, policy_version 95353 (0.0008) -[2023-10-09 12:06:26,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 195788800. Throughput: 0: 1780.2, 1: 1801.3. Samples: 48959096. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) -[2023-10-09 12:06:26,078][22500] Avg episode reward: [(0, '10.120'), (1, '9.620')] -[2023-10-09 12:06:27,379][23469] Updated weights for policy 1, policy_version 95881 (0.0008) -[2023-10-09 12:06:27,757][23469] Updated weights for policy 1, policy_version 95891 (0.0008) -[2023-10-09 12:06:28,119][23469] Updated weights for policy 1, policy_version 95901 (0.0009) -[2023-10-09 12:06:29,693][23468] Updated weights for policy 0, policy_version 95363 (0.0011) -[2023-10-09 12:06:30,071][23468] Updated weights for policy 0, policy_version 95373 (0.0008) -[2023-10-09 12:06:30,449][23468] Updated weights for policy 0, policy_version 95383 (0.0008) -[2023-10-09 12:06:31,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 195887104. Throughput: 0: 1798.5, 1: 1799.2. Samples: 48980684. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) -[2023-10-09 12:06:31,078][22500] Avg episode reward: [(0, '9.920'), (1, '9.660')] -[2023-10-09 12:06:31,970][23469] Updated weights for policy 1, policy_version 95911 (0.0009) -[2023-10-09 12:06:32,341][23469] Updated weights for policy 1, policy_version 95921 (0.0007) -[2023-10-09 12:06:32,706][23469] Updated weights for policy 1, policy_version 95931 (0.0007) -[2023-10-09 12:06:34,213][23468] Updated weights for policy 0, policy_version 95393 (0.0009) -[2023-10-09 12:06:34,577][23468] Updated weights for policy 0, policy_version 95403 (0.0009) -[2023-10-09 12:06:34,952][23468] Updated weights for policy 0, policy_version 95413 (0.0011) -[2023-10-09 12:06:35,320][23468] Updated weights for policy 0, policy_version 95423 (0.0009) -[2023-10-09 12:06:36,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 195952640. Throughput: 0: 1792.0, 1: 1800.3. Samples: 48991410. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) -[2023-10-09 12:06:36,078][22500] Avg episode reward: [(0, '9.540'), (1, '9.600')] -[2023-10-09 12:06:36,294][23469] Updated weights for policy 1, policy_version 95941 (0.0007) -[2023-10-09 12:06:36,662][23469] Updated weights for policy 1, policy_version 95951 (0.0007) -[2023-10-09 12:06:37,035][23469] Updated weights for policy 1, policy_version 95961 (0.0008) -[2023-10-09 12:06:38,945][23468] Updated weights for policy 0, policy_version 95433 (0.0009) -[2023-10-09 12:06:39,319][23468] Updated weights for policy 0, policy_version 95443 (0.0011) -[2023-10-09 12:06:39,698][23468] Updated weights for policy 0, policy_version 95453 (0.0007) -[2023-10-09 12:06:40,800][23469] Updated weights for policy 1, policy_version 95971 (0.0009) -[2023-10-09 12:06:41,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 196018176. Throughput: 0: 1805.4, 1: 1801.4. Samples: 49013178. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) -[2023-10-09 12:06:41,078][22500] Avg episode reward: [(0, '10.170'), (1, '9.930')] -[2023-10-09 12:06:41,171][23469] Updated weights for policy 1, policy_version 95981 (0.0009) -[2023-10-09 12:06:41,548][23469] Updated weights for policy 1, policy_version 95991 (0.0007) -[2023-10-09 12:06:43,487][23468] Updated weights for policy 0, policy_version 95463 (0.0009) -[2023-10-09 12:06:43,846][23468] Updated weights for policy 0, policy_version 95473 (0.0009) -[2023-10-09 12:06:44,224][23468] Updated weights for policy 0, policy_version 95483 (0.0010) -[2023-10-09 12:06:45,176][23469] Updated weights for policy 1, policy_version 96001 (0.0007) -[2023-10-09 12:06:45,579][23469] Updated weights for policy 1, policy_version 96011 (0.0011) -[2023-10-09 12:06:45,950][23469] Updated weights for policy 1, policy_version 96021 (0.0012) -[2023-10-09 12:06:46,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 196083712. Throughput: 0: 1792.0, 1: 1811.9. Samples: 49034286. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) -[2023-10-09 12:06:46,078][22500] Avg episode reward: [(0, '9.860'), (1, '10.410')] -[2023-10-09 12:06:46,325][23469] Updated weights for policy 1, policy_version 96031 (0.0007) -[2023-10-09 12:06:47,941][23468] Updated weights for policy 0, policy_version 95493 (0.0008) -[2023-10-09 12:06:48,311][23468] Updated weights for policy 0, policy_version 95503 (0.0008) -[2023-10-09 12:06:48,697][23468] Updated weights for policy 0, policy_version 95513 (0.0011) -[2023-10-09 12:06:50,094][23469] Updated weights for policy 1, policy_version 96041 (0.0009) -[2023-10-09 12:06:50,467][23469] Updated weights for policy 1, policy_version 96051 (0.0011) -[2023-10-09 12:06:50,833][23469] Updated weights for policy 1, policy_version 96061 (0.0010) -[2023-10-09 12:06:51,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 196182016. Throughput: 0: 1801.0, 1: 1801.4. Samples: 49045536. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) -[2023-10-09 12:06:51,078][22500] Avg episode reward: [(0, '10.000'), (1, '10.230')] -[2023-10-09 12:06:52,675][23468] Updated weights for policy 0, policy_version 95523 (0.0009) -[2023-10-09 12:06:53,047][23468] Updated weights for policy 0, policy_version 95533 (0.0007) -[2023-10-09 12:06:53,419][23468] Updated weights for policy 0, policy_version 95543 (0.0008) -[2023-10-09 12:06:54,580][23469] Updated weights for policy 1, policy_version 96071 (0.0008) -[2023-10-09 12:06:54,958][23469] Updated weights for policy 1, policy_version 96081 (0.0008) -[2023-10-09 12:06:55,321][23469] Updated weights for policy 1, policy_version 96091 (0.0008) -[2023-10-09 12:06:56,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 196247552. Throughput: 0: 1781.3, 1: 1809.3. Samples: 49066238. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) -[2023-10-09 12:06:56,078][22500] Avg episode reward: [(0, '10.890'), (1, '10.460')] -[2023-10-09 12:06:57,139][23468] Updated weights for policy 0, policy_version 95553 (0.0010) -[2023-10-09 12:06:57,555][23468] Updated weights for policy 0, policy_version 95563 (0.0007) -[2023-10-09 12:06:57,932][23468] Updated weights for policy 0, policy_version 95573 (0.0008) -[2023-10-09 12:06:58,293][23468] Updated weights for policy 0, policy_version 95583 (0.0009) -[2023-10-09 12:06:58,997][23469] Updated weights for policy 1, policy_version 96101 (0.0011) -[2023-10-09 12:06:59,366][23469] Updated weights for policy 1, policy_version 96111 (0.0010) -[2023-10-09 12:06:59,730][23469] Updated weights for policy 1, policy_version 96121 (0.0008) -[2023-10-09 12:07:01,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 196313088. Throughput: 0: 1777.7, 1: 1793.3. Samples: 49087634. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) -[2023-10-09 12:07:01,079][22500] Avg episode reward: [(0, '10.790'), (1, '9.790')] -[2023-10-09 12:07:02,023][23468] Updated weights for policy 0, policy_version 95593 (0.0008) -[2023-10-09 12:07:02,397][23468] Updated weights for policy 0, policy_version 95603 (0.0008) -[2023-10-09 12:07:02,764][23468] Updated weights for policy 0, policy_version 95613 (0.0010) -[2023-10-09 12:07:03,372][23469] Updated weights for policy 1, policy_version 96131 (0.0009) -[2023-10-09 12:07:03,737][23469] Updated weights for policy 1, policy_version 96141 (0.0009) -[2023-10-09 12:07:04,103][23469] Updated weights for policy 1, policy_version 96151 (0.0011) -[2023-10-09 12:07:06,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 196378624. Throughput: 0: 1780.0, 1: 1799.2. Samples: 49098356. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) -[2023-10-09 12:07:06,078][22500] Avg episode reward: [(0, '11.360'), (1, '9.850')] -[2023-10-09 12:07:06,602][23468] Updated weights for policy 0, policy_version 95623 (0.0009) -[2023-10-09 12:07:06,969][23468] Updated weights for policy 0, policy_version 95633 (0.0009) -[2023-10-09 12:07:07,344][23468] Updated weights for policy 0, policy_version 95643 (0.0009) -[2023-10-09 12:07:07,912][23469] Updated weights for policy 1, policy_version 96161 (0.0007) -[2023-10-09 12:07:08,277][23469] Updated weights for policy 1, policy_version 96171 (0.0007) -[2023-10-09 12:07:08,643][23469] Updated weights for policy 1, policy_version 96181 (0.0008) -[2023-10-09 12:07:09,013][23469] Updated weights for policy 1, policy_version 96191 (0.0009) -[2023-10-09 12:07:10,953][23468] Updated weights for policy 0, policy_version 95653 (0.0008) -[2023-10-09 12:07:11,077][22500] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 196444160. Throughput: 0: 1785.2, 1: 1792.8. Samples: 49120106. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) -[2023-10-09 12:07:11,078][22500] Avg episode reward: [(0, '11.030'), (1, '9.300')] -[2023-10-09 12:07:11,327][23468] Updated weights for policy 0, policy_version 95663 (0.0010) -[2023-10-09 12:07:11,701][23468] Updated weights for policy 0, policy_version 95673 (0.0007) -[2023-10-09 12:07:12,665][23469] Updated weights for policy 1, policy_version 96201 (0.0008) -[2023-10-09 12:07:13,044][23469] Updated weights for policy 1, policy_version 96211 (0.0010) -[2023-10-09 12:07:13,407][23469] Updated weights for policy 1, policy_version 96221 (0.0009) -[2023-10-09 12:07:15,448][23468] Updated weights for policy 0, policy_version 95683 (0.0008) -[2023-10-09 12:07:15,816][23468] Updated weights for policy 0, policy_version 95693 (0.0009) -[2023-10-09 12:07:16,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 196509696. Throughput: 0: 1805.0, 1: 1796.7. Samples: 49142762. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) -[2023-10-09 12:07:16,078][22500] Avg episode reward: [(0, '11.020'), (1, '9.500')] -[2023-10-09 12:07:16,189][23468] Updated weights for policy 0, policy_version 95703 (0.0009) -[2023-10-09 12:07:17,175][23469] Updated weights for policy 1, policy_version 96231 (0.0009) -[2023-10-09 12:07:17,552][23469] Updated weights for policy 1, policy_version 96241 (0.0009) -[2023-10-09 12:07:17,929][23469] Updated weights for policy 1, policy_version 96251 (0.0008) -[2023-10-09 12:07:19,916][23468] Updated weights for policy 0, policy_version 95713 (0.0007) -[2023-10-09 12:07:20,292][23468] Updated weights for policy 0, policy_version 95723 (0.0008) -[2023-10-09 12:07:20,663][23468] Updated weights for policy 0, policy_version 95733 (0.0008) -[2023-10-09 12:07:21,040][23468] Updated weights for policy 0, policy_version 95743 (0.0008) -[2023-10-09 12:07:21,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 196608000. Throughput: 0: 1787.4, 1: 1796.4. Samples: 49152678. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 12:07:21,079][22500] Avg episode reward: [(0, '11.210'), (1, '9.610')] -[2023-10-09 12:07:21,669][23469] Updated weights for policy 1, policy_version 96261 (0.0008) -[2023-10-09 12:07:22,035][23469] Updated weights for policy 1, policy_version 96271 (0.0008) -[2023-10-09 12:07:22,416][23469] Updated weights for policy 1, policy_version 96281 (0.0009) -[2023-10-09 12:07:24,692][23468] Updated weights for policy 0, policy_version 95753 (0.0009) -[2023-10-09 12:07:25,063][23468] Updated weights for policy 0, policy_version 95763 (0.0007) -[2023-10-09 12:07:25,442][23468] Updated weights for policy 0, policy_version 95773 (0.0009) -[2023-10-09 12:07:26,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 196673536. Throughput: 0: 1807.9, 1: 1797.3. Samples: 49175410. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 12:07:26,078][22500] Avg episode reward: [(0, '10.880'), (1, '9.700')] -[2023-10-09 12:07:26,286][23469] Updated weights for policy 1, policy_version 96291 (0.0009) -[2023-10-09 12:07:26,663][23469] Updated weights for policy 1, policy_version 96301 (0.0007) -[2023-10-09 12:07:27,031][23469] Updated weights for policy 1, policy_version 96311 (0.0009) -[2023-10-09 12:07:29,128][23468] Updated weights for policy 0, policy_version 95783 (0.0010) -[2023-10-09 12:07:29,515][23468] Updated weights for policy 0, policy_version 95793 (0.0009) -[2023-10-09 12:07:29,889][23468] Updated weights for policy 0, policy_version 95803 (0.0011) -[2023-10-09 12:07:30,712][23469] Updated weights for policy 1, policy_version 96321 (0.0008) -[2023-10-09 12:07:31,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 196739072. Throughput: 0: 1795.5, 1: 1807.3. Samples: 49196412. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 12:07:31,078][22500] Avg episode reward: [(0, '10.330'), (1, '9.780')] -[2023-10-09 12:07:31,119][23469] Updated weights for policy 1, policy_version 96331 (0.0008) -[2023-10-09 12:07:31,486][23469] Updated weights for policy 1, policy_version 96341 (0.0009) -[2023-10-09 12:07:31,863][23469] Updated weights for policy 1, policy_version 96351 (0.0009) -[2023-10-09 12:07:33,646][23468] Updated weights for policy 0, policy_version 95813 (0.0009) -[2023-10-09 12:07:34,025][23468] Updated weights for policy 0, policy_version 95823 (0.0009) -[2023-10-09 12:07:34,406][23468] Updated weights for policy 0, policy_version 95833 (0.0007) -[2023-10-09 12:07:35,737][23469] Updated weights for policy 1, policy_version 96361 (0.0010) -[2023-10-09 12:07:36,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 196804608. Throughput: 0: 1814.6, 1: 1792.6. Samples: 49207858. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 12:07:36,078][22500] Avg episode reward: [(0, '10.540'), (1, '10.020')] -[2023-10-09 12:07:36,103][23469] Updated weights for policy 1, policy_version 96371 (0.0008) -[2023-10-09 12:07:36,475][23469] Updated weights for policy 1, policy_version 96381 (0.0009) -[2023-10-09 12:07:38,079][23468] Updated weights for policy 0, policy_version 95843 (0.0009) -[2023-10-09 12:07:38,447][23468] Updated weights for policy 0, policy_version 95853 (0.0011) -[2023-10-09 12:07:38,819][23468] Updated weights for policy 0, policy_version 95863 (0.0010) -[2023-10-09 12:07:40,235][23469] Updated weights for policy 1, policy_version 96391 (0.0010) -[2023-10-09 12:07:40,610][23469] Updated weights for policy 1, policy_version 96401 (0.0009) -[2023-10-09 12:07:40,971][23469] Updated weights for policy 1, policy_version 96411 (0.0008) -[2023-10-09 12:07:41,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 196870144. Throughput: 0: 1807.5, 1: 1811.4. Samples: 49229090. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 12:07:41,078][22500] Avg episode reward: [(0, '10.980'), (1, '9.930')] -[2023-10-09 12:07:42,542][23468] Updated weights for policy 0, policy_version 95873 (0.0009) -[2023-10-09 12:07:42,935][23468] Updated weights for policy 0, policy_version 95883 (0.0007) -[2023-10-09 12:07:43,312][23468] Updated weights for policy 0, policy_version 95893 (0.0007) -[2023-10-09 12:07:43,687][23468] Updated weights for policy 0, policy_version 95903 (0.0008) -[2023-10-09 12:07:44,703][23469] Updated weights for policy 1, policy_version 96421 (0.0008) -[2023-10-09 12:07:45,066][23469] Updated weights for policy 1, policy_version 96431 (0.0008) -[2023-10-09 12:07:45,434][23469] Updated weights for policy 1, policy_version 96441 (0.0010) -[2023-10-09 12:07:46,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 196968448. Throughput: 0: 1811.2, 1: 1798.9. Samples: 49250090. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 12:07:46,078][22500] Avg episode reward: [(0, '11.000'), (1, '10.140')] -[2023-10-09 12:07:47,385][23468] Updated weights for policy 0, policy_version 95913 (0.0007) -[2023-10-09 12:07:47,762][23468] Updated weights for policy 0, policy_version 95923 (0.0008) -[2023-10-09 12:07:48,132][23468] Updated weights for policy 0, policy_version 95933 (0.0010) -[2023-10-09 12:07:49,257][23469] Updated weights for policy 1, policy_version 96451 (0.0010) -[2023-10-09 12:07:49,615][23469] Updated weights for policy 1, policy_version 96461 (0.0008) -[2023-10-09 12:07:49,988][23469] Updated weights for policy 1, policy_version 96471 (0.0007) -[2023-10-09 12:07:51,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 197033984. Throughput: 0: 1812.9, 1: 1812.8. Samples: 49261514. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 12:07:51,078][22500] Avg episode reward: [(0, '11.160'), (1, '9.850')] -[2023-10-09 12:07:51,766][23468] Updated weights for policy 0, policy_version 95943 (0.0009) -[2023-10-09 12:07:52,137][23468] Updated weights for policy 0, policy_version 95953 (0.0008) -[2023-10-09 12:07:52,509][23468] Updated weights for policy 0, policy_version 95963 (0.0008) -[2023-10-09 12:07:53,613][23469] Updated weights for policy 1, policy_version 96481 (0.0009) -[2023-10-09 12:07:53,982][23469] Updated weights for policy 1, policy_version 96491 (0.0008) -[2023-10-09 12:07:54,357][23469] Updated weights for policy 1, policy_version 96501 (0.0010) -[2023-10-09 12:07:54,735][23469] Updated weights for policy 1, policy_version 96511 (0.0009) -[2023-10-09 12:07:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 197099520. Throughput: 0: 1810.5, 1: 1798.5. Samples: 49282512. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 12:07:56,078][22500] Avg episode reward: [(0, '11.560'), (1, '9.600')] -[2023-10-09 12:07:56,265][23468] Updated weights for policy 0, policy_version 95973 (0.0008) -[2023-10-09 12:07:56,637][23468] Updated weights for policy 0, policy_version 95983 (0.0009) -[2023-10-09 12:07:57,021][23468] Updated weights for policy 0, policy_version 95993 (0.0007) -[2023-10-09 12:07:58,257][23469] Updated weights for policy 1, policy_version 96521 (0.0008) -[2023-10-09 12:07:58,632][23469] Updated weights for policy 1, policy_version 96531 (0.0008) -[2023-10-09 12:07:59,007][23469] Updated weights for policy 1, policy_version 96541 (0.0010) -[2023-10-09 12:08:00,775][23468] Updated weights for policy 0, policy_version 96003 (0.0008) -[2023-10-09 12:08:01,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 197165056. Throughput: 0: 1806.5, 1: 1806.7. Samples: 49305358. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 12:08:01,078][22500] Avg episode reward: [(0, '10.670'), (1, '9.970')] -[2023-10-09 12:08:01,139][23468] Updated weights for policy 0, policy_version 96013 (0.0009) -[2023-10-09 12:08:01,514][23468] Updated weights for policy 0, policy_version 96023 (0.0007) -[2023-10-09 12:08:02,808][23469] Updated weights for policy 1, policy_version 96551 (0.0007) -[2023-10-09 12:08:03,178][23469] Updated weights for policy 1, policy_version 96561 (0.0007) -[2023-10-09 12:08:03,549][23469] Updated weights for policy 1, policy_version 96571 (0.0010) -[2023-10-09 12:08:05,237][23468] Updated weights for policy 0, policy_version 96033 (0.0010) -[2023-10-09 12:08:05,609][23468] Updated weights for policy 0, policy_version 96043 (0.0009) -[2023-10-09 12:08:05,986][23468] Updated weights for policy 0, policy_version 96053 (0.0009) -[2023-10-09 12:08:06,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 197230592. Throughput: 0: 1802.1, 1: 1803.2. Samples: 49314918. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 12:08:06,078][22500] Avg episode reward: [(0, '11.190'), (1, '9.970')] -[2023-10-09 12:08:06,351][23468] Updated weights for policy 0, policy_version 96063 (0.0008) -[2023-10-09 12:08:07,343][23469] Updated weights for policy 1, policy_version 96581 (0.0008) -[2023-10-09 12:08:07,708][23469] Updated weights for policy 1, policy_version 96591 (0.0008) -[2023-10-09 12:08:08,082][23469] Updated weights for policy 1, policy_version 96601 (0.0009) -[2023-10-09 12:08:09,966][23468] Updated weights for policy 0, policy_version 96073 (0.0007) -[2023-10-09 12:08:10,331][23468] Updated weights for policy 0, policy_version 96083 (0.0009) -[2023-10-09 12:08:10,704][23468] Updated weights for policy 0, policy_version 96093 (0.0007) -[2023-10-09 12:08:11,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 197328896. Throughput: 0: 1807.8, 1: 1796.2. Samples: 49337590. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 12:08:11,078][22500] Avg episode reward: [(0, '11.080'), (1, '10.520')] -[2023-10-09 12:08:11,807][23469] Updated weights for policy 1, policy_version 96611 (0.0009) -[2023-10-09 12:08:12,165][23469] Updated weights for policy 1, policy_version 96621 (0.0008) -[2023-10-09 12:08:12,537][23469] Updated weights for policy 1, policy_version 96631 (0.0007) -[2023-10-09 12:08:14,347][23468] Updated weights for policy 0, policy_version 96103 (0.0008) -[2023-10-09 12:08:14,720][23468] Updated weights for policy 0, policy_version 96113 (0.0008) -[2023-10-09 12:08:15,094][23468] Updated weights for policy 0, policy_version 96123 (0.0008) -[2023-10-09 12:08:16,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 197394432. Throughput: 0: 1810.4, 1: 1799.5. Samples: 49358860. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 12:08:16,078][22500] Avg episode reward: [(0, '10.300'), (1, '10.910')] -[2023-10-09 12:08:16,088][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000096640_98959360.pth... -[2023-10-09 12:08:16,088][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000096128_98435072.pth... -[2023-10-09 12:08:16,124][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000094976_97255424.pth -[2023-10-09 12:08:16,124][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000094432_96698368.pth -[2023-10-09 12:08:16,434][23469] Updated weights for policy 1, policy_version 96641 (0.0007) -[2023-10-09 12:08:16,839][23469] Updated weights for policy 1, policy_version 96651 (0.0009) -[2023-10-09 12:08:17,200][23469] Updated weights for policy 1, policy_version 96661 (0.0008) -[2023-10-09 12:08:17,569][23469] Updated weights for policy 1, policy_version 96671 (0.0008) -[2023-10-09 12:08:18,860][23468] Updated weights for policy 0, policy_version 96133 (0.0008) -[2023-10-09 12:08:19,230][23468] Updated weights for policy 0, policy_version 96143 (0.0007) -[2023-10-09 12:08:19,615][23468] Updated weights for policy 0, policy_version 96153 (0.0011) -[2023-10-09 12:08:21,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 197459968. Throughput: 0: 1810.5, 1: 1793.1. Samples: 49370020. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 12:08:21,078][22500] Avg episode reward: [(0, '11.240'), (1, '9.600')] -[2023-10-09 12:08:21,381][23469] Updated weights for policy 1, policy_version 96681 (0.0008) -[2023-10-09 12:08:21,755][23469] Updated weights for policy 1, policy_version 96691 (0.0009) -[2023-10-09 12:08:22,129][23469] Updated weights for policy 1, policy_version 96701 (0.0010) -[2023-10-09 12:08:23,294][23468] Updated weights for policy 0, policy_version 96163 (0.0008) -[2023-10-09 12:08:23,676][23468] Updated weights for policy 0, policy_version 96173 (0.0007) -[2023-10-09 12:08:24,046][23468] Updated weights for policy 0, policy_version 96183 (0.0007) -[2023-10-09 12:08:25,748][23469] Updated weights for policy 1, policy_version 96711 (0.0008) -[2023-10-09 12:08:26,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 197525504. Throughput: 0: 1814.5, 1: 1791.1. Samples: 49391340. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-09 12:08:26,078][22500] Avg episode reward: [(0, '11.680'), (1, '9.560')] -[2023-10-09 12:08:26,115][23469] Updated weights for policy 1, policy_version 96721 (0.0007) -[2023-10-09 12:08:26,483][23469] Updated weights for policy 1, policy_version 96731 (0.0007) -[2023-10-09 12:08:27,850][23468] Updated weights for policy 0, policy_version 96193 (0.0007) -[2023-10-09 12:08:28,269][23468] Updated weights for policy 0, policy_version 96203 (0.0010) -[2023-10-09 12:08:28,640][23468] Updated weights for policy 0, policy_version 96213 (0.0011) -[2023-10-09 12:08:29,010][23468] Updated weights for policy 0, policy_version 96223 (0.0009) -[2023-10-09 12:08:30,250][23469] Updated weights for policy 1, policy_version 96741 (0.0008) -[2023-10-09 12:08:30,616][23469] Updated weights for policy 1, policy_version 96751 (0.0009) -[2023-10-09 12:08:30,991][23469] Updated weights for policy 1, policy_version 96761 (0.0008) -[2023-10-09 12:08:31,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 197591040. Throughput: 0: 1804.0, 1: 1810.1. Samples: 49412726. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-09 12:08:31,078][22500] Avg episode reward: [(0, '11.630'), (1, '9.390')] -[2023-10-09 12:08:32,764][23468] Updated weights for policy 0, policy_version 96233 (0.0008) -[2023-10-09 12:08:33,143][23468] Updated weights for policy 0, policy_version 96243 (0.0008) -[2023-10-09 12:08:33,512][23468] Updated weights for policy 0, policy_version 96253 (0.0009) -[2023-10-09 12:08:34,631][23469] Updated weights for policy 1, policy_version 96771 (0.0008) -[2023-10-09 12:08:35,008][23469] Updated weights for policy 1, policy_version 96781 (0.0008) -[2023-10-09 12:08:35,387][23469] Updated weights for policy 1, policy_version 96791 (0.0008) -[2023-10-09 12:08:36,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 197689344. Throughput: 0: 1814.0, 1: 1794.0. Samples: 49423872. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-09 12:08:36,078][22500] Avg episode reward: [(0, '12.240'), (1, '9.160')] -[2023-10-09 12:08:36,078][23265] Saving new best policy, reward=12.240! -[2023-10-09 12:08:37,168][23468] Updated weights for policy 0, policy_version 96263 (0.0008) -[2023-10-09 12:08:37,545][23468] Updated weights for policy 0, policy_version 96273 (0.0010) -[2023-10-09 12:08:37,910][23468] Updated weights for policy 0, policy_version 96283 (0.0009) -[2023-10-09 12:08:39,055][23469] Updated weights for policy 1, policy_version 96801 (0.0007) -[2023-10-09 12:08:39,433][23469] Updated weights for policy 1, policy_version 96811 (0.0009) -[2023-10-09 12:08:39,800][23469] Updated weights for policy 1, policy_version 96821 (0.0007) -[2023-10-09 12:08:40,173][23469] Updated weights for policy 1, policy_version 96831 (0.0009) -[2023-10-09 12:08:41,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 197754880. Throughput: 0: 1800.8, 1: 1810.0. Samples: 49444998. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-09 12:08:41,078][22500] Avg episode reward: [(0, '11.310'), (1, '9.570')] -[2023-10-09 12:08:41,648][23468] Updated weights for policy 0, policy_version 96293 (0.0009) -[2023-10-09 12:08:42,010][23468] Updated weights for policy 0, policy_version 96303 (0.0010) -[2023-10-09 12:08:42,384][23468] Updated weights for policy 0, policy_version 96313 (0.0008) -[2023-10-09 12:08:43,901][23469] Updated weights for policy 1, policy_version 96841 (0.0009) -[2023-10-09 12:08:44,274][23469] Updated weights for policy 1, policy_version 96851 (0.0009) -[2023-10-09 12:08:44,645][23469] Updated weights for policy 1, policy_version 96861 (0.0007) -[2023-10-09 12:08:46,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 197820416. Throughput: 0: 1800.8, 1: 1793.4. Samples: 49467096. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-09 12:08:46,078][22500] Avg episode reward: [(0, '11.330'), (1, '9.660')] -[2023-10-09 12:08:46,196][23468] Updated weights for policy 0, policy_version 96323 (0.0007) -[2023-10-09 12:08:46,574][23468] Updated weights for policy 0, policy_version 96333 (0.0009) -[2023-10-09 12:08:46,945][23468] Updated weights for policy 0, policy_version 96343 (0.0009) -[2023-10-09 12:08:48,280][23469] Updated weights for policy 1, policy_version 96871 (0.0009) -[2023-10-09 12:08:48,651][23469] Updated weights for policy 1, policy_version 96881 (0.0007) -[2023-10-09 12:08:49,025][23469] Updated weights for policy 1, policy_version 96891 (0.0008) -[2023-10-09 12:08:50,865][23468] Updated weights for policy 0, policy_version 96353 (0.0008) -[2023-10-09 12:08:51,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 197885952. Throughput: 0: 1799.0, 1: 1808.9. Samples: 49477272. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-09 12:08:51,078][22500] Avg episode reward: [(0, '11.380'), (1, '9.880')] -[2023-10-09 12:08:51,226][23468] Updated weights for policy 0, policy_version 96363 (0.0008) -[2023-10-09 12:08:51,597][23468] Updated weights for policy 0, policy_version 96373 (0.0007) -[2023-10-09 12:08:51,983][23468] Updated weights for policy 0, policy_version 96383 (0.0007) -[2023-10-09 12:08:52,889][23469] Updated weights for policy 1, policy_version 96901 (0.0009) -[2023-10-09 12:08:53,258][23469] Updated weights for policy 1, policy_version 96911 (0.0010) -[2023-10-09 12:08:53,627][23469] Updated weights for policy 1, policy_version 96921 (0.0007) -[2023-10-09 12:08:55,574][23468] Updated weights for policy 0, policy_version 96393 (0.0009) -[2023-10-09 12:08:55,949][23468] Updated weights for policy 0, policy_version 96403 (0.0009) -[2023-10-09 12:08:56,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 197951488. Throughput: 0: 1789.2, 1: 1799.2. Samples: 49499064. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-09 12:08:56,078][22500] Avg episode reward: [(0, '11.000'), (1, '10.180')] -[2023-10-09 12:08:56,321][23468] Updated weights for policy 0, policy_version 96413 (0.0007) -[2023-10-09 12:08:57,280][23469] Updated weights for policy 1, policy_version 96931 (0.0009) -[2023-10-09 12:08:57,649][23469] Updated weights for policy 1, policy_version 96941 (0.0011) -[2023-10-09 12:08:58,023][23469] Updated weights for policy 1, policy_version 96951 (0.0011) -[2023-10-09 12:09:00,083][23468] Updated weights for policy 0, policy_version 96423 (0.0007) -[2023-10-09 12:09:00,453][23468] Updated weights for policy 0, policy_version 96433 (0.0011) -[2023-10-09 12:09:00,826][23468] Updated weights for policy 0, policy_version 96443 (0.0009) -[2023-10-09 12:09:01,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 198049792. Throughput: 0: 1805.6, 1: 1805.1. Samples: 49521340. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-09 12:09:01,078][22500] Avg episode reward: [(0, '10.470'), (1, '9.840')] -[2023-10-09 12:09:01,734][23469] Updated weights for policy 1, policy_version 96961 (0.0008) -[2023-10-09 12:09:02,148][23469] Updated weights for policy 1, policy_version 96971 (0.0007) -[2023-10-09 12:09:02,516][23469] Updated weights for policy 1, policy_version 96981 (0.0007) -[2023-10-09 12:09:02,882][23469] Updated weights for policy 1, policy_version 96991 (0.0008) -[2023-10-09 12:09:04,657][23468] Updated weights for policy 0, policy_version 96453 (0.0007) -[2023-10-09 12:09:05,034][23468] Updated weights for policy 0, policy_version 96463 (0.0008) -[2023-10-09 12:09:05,402][23468] Updated weights for policy 0, policy_version 96473 (0.0008) -[2023-10-09 12:09:06,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 198115328. Throughput: 0: 1778.4, 1: 1807.6. Samples: 49531394. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-09 12:09:06,078][22500] Avg episode reward: [(0, '10.080'), (1, '9.650')] -[2023-10-09 12:09:06,607][23469] Updated weights for policy 1, policy_version 97001 (0.0010) -[2023-10-09 12:09:06,973][23469] Updated weights for policy 1, policy_version 97011 (0.0009) -[2023-10-09 12:09:07,338][23469] Updated weights for policy 1, policy_version 97021 (0.0009) -[2023-10-09 12:09:09,069][23468] Updated weights for policy 0, policy_version 96483 (0.0008) -[2023-10-09 12:09:09,440][23468] Updated weights for policy 0, policy_version 96493 (0.0007) -[2023-10-09 12:09:09,803][23468] Updated weights for policy 0, policy_version 96503 (0.0007) -[2023-10-09 12:09:11,071][23469] Updated weights for policy 1, policy_version 97031 (0.0008) -[2023-10-09 12:09:11,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 198180864. Throughput: 0: 1800.0, 1: 1804.6. Samples: 49553546. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-09 12:09:11,079][22500] Avg episode reward: [(0, '10.080'), (1, '9.630')] -[2023-10-09 12:09:11,441][23469] Updated weights for policy 1, policy_version 97041 (0.0007) -[2023-10-09 12:09:11,806][23469] Updated weights for policy 1, policy_version 97051 (0.0008) -[2023-10-09 12:09:13,447][23468] Updated weights for policy 0, policy_version 96513 (0.0007) -[2023-10-09 12:09:13,855][23468] Updated weights for policy 0, policy_version 96523 (0.0010) -[2023-10-09 12:09:14,227][23468] Updated weights for policy 0, policy_version 96533 (0.0010) -[2023-10-09 12:09:14,609][23468] Updated weights for policy 0, policy_version 96543 (0.0010) -[2023-10-09 12:09:15,617][23469] Updated weights for policy 1, policy_version 97061 (0.0009) -[2023-10-09 12:09:15,989][23469] Updated weights for policy 1, policy_version 97071 (0.0008) -[2023-10-09 12:09:16,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 198246400. Throughput: 0: 1784.8, 1: 1809.9. Samples: 49574490. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-09 12:09:16,078][22500] Avg episode reward: [(0, '11.010'), (1, '9.650')] -[2023-10-09 12:09:16,358][23469] Updated weights for policy 1, policy_version 97081 (0.0008) -[2023-10-09 12:09:18,251][23468] Updated weights for policy 0, policy_version 96553 (0.0009) -[2023-10-09 12:09:18,633][23468] Updated weights for policy 0, policy_version 96563 (0.0009) -[2023-10-09 12:09:19,008][23468] Updated weights for policy 0, policy_version 96573 (0.0008) -[2023-10-09 12:09:20,012][23469] Updated weights for policy 1, policy_version 97091 (0.0007) -[2023-10-09 12:09:20,387][23469] Updated weights for policy 1, policy_version 97101 (0.0008) -[2023-10-09 12:09:20,758][23469] Updated weights for policy 1, policy_version 97111 (0.0009) -[2023-10-09 12:09:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 198311936. Throughput: 0: 1798.0, 1: 1798.4. Samples: 49585710. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-09 12:09:21,078][22500] Avg episode reward: [(0, '11.040'), (1, '9.690')] -[2023-10-09 12:09:22,922][23468] Updated weights for policy 0, policy_version 96583 (0.0008) -[2023-10-09 12:09:23,280][23468] Updated weights for policy 0, policy_version 96593 (0.0009) -[2023-10-09 12:09:23,658][23468] Updated weights for policy 0, policy_version 96603 (0.0008) -[2023-10-09 12:09:24,455][23469] Updated weights for policy 1, policy_version 97121 (0.0009) -[2023-10-09 12:09:24,822][23469] Updated weights for policy 1, policy_version 97131 (0.0008) -[2023-10-09 12:09:25,185][23469] Updated weights for policy 1, policy_version 97141 (0.0008) -[2023-10-09 12:09:25,555][23469] Updated weights for policy 1, policy_version 97151 (0.0009) -[2023-10-09 12:09:26,077][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 198410240. Throughput: 0: 1786.9, 1: 1810.0. Samples: 49606856. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 12:09:26,078][22500] Avg episode reward: [(0, '11.110'), (1, '10.090')] -[2023-10-09 12:09:27,570][23468] Updated weights for policy 0, policy_version 96613 (0.0008) -[2023-10-09 12:09:27,931][23468] Updated weights for policy 0, policy_version 96623 (0.0008) -[2023-10-09 12:09:28,305][23468] Updated weights for policy 0, policy_version 96633 (0.0010) -[2023-10-09 12:09:29,174][23469] Updated weights for policy 1, policy_version 97161 (0.0010) -[2023-10-09 12:09:29,535][23469] Updated weights for policy 1, policy_version 97171 (0.0008) -[2023-10-09 12:09:29,913][23469] Updated weights for policy 1, policy_version 97181 (0.0008) -[2023-10-09 12:09:31,078][22500] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 198475776. Throughput: 0: 1785.5, 1: 1796.3. Samples: 49628278. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 12:09:31,078][22500] Avg episode reward: [(0, '10.650'), (1, '9.810')] -[2023-10-09 12:09:31,970][23468] Updated weights for policy 0, policy_version 96643 (0.0010) -[2023-10-09 12:09:32,340][23468] Updated weights for policy 0, policy_version 96653 (0.0010) -[2023-10-09 12:09:32,706][23468] Updated weights for policy 0, policy_version 96663 (0.0008) -[2023-10-09 12:09:33,794][23469] Updated weights for policy 1, policy_version 97191 (0.0010) -[2023-10-09 12:09:34,150][23469] Updated weights for policy 1, policy_version 97201 (0.0010) -[2023-10-09 12:09:34,528][23469] Updated weights for policy 1, policy_version 97211 (0.0010) -[2023-10-09 12:09:36,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 198541312. Throughput: 0: 1784.8, 1: 1807.9. Samples: 49638942. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 12:09:36,078][22500] Avg episode reward: [(0, '10.050'), (1, '9.650')] -[2023-10-09 12:09:36,423][23468] Updated weights for policy 0, policy_version 96673 (0.0010) -[2023-10-09 12:09:36,788][23468] Updated weights for policy 0, policy_version 96683 (0.0011) -[2023-10-09 12:09:37,167][23468] Updated weights for policy 0, policy_version 96693 (0.0010) -[2023-10-09 12:09:37,535][23468] Updated weights for policy 0, policy_version 96703 (0.0008) -[2023-10-09 12:09:38,313][23469] Updated weights for policy 1, policy_version 97221 (0.0011) -[2023-10-09 12:09:38,680][23469] Updated weights for policy 1, policy_version 97231 (0.0012) -[2023-10-09 12:09:39,054][23469] Updated weights for policy 1, policy_version 97241 (0.0011) -[2023-10-09 12:09:41,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 198606848. Throughput: 0: 1783.5, 1: 1798.0. Samples: 49660234. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 12:09:41,078][22500] Avg episode reward: [(0, '11.190'), (1, '10.000')] -[2023-10-09 12:09:41,435][23468] Updated weights for policy 0, policy_version 96713 (0.0009) -[2023-10-09 12:09:41,805][23468] Updated weights for policy 0, policy_version 96723 (0.0009) -[2023-10-09 12:09:42,175][23468] Updated weights for policy 0, policy_version 96733 (0.0008) -[2023-10-09 12:09:42,853][23469] Updated weights for policy 1, policy_version 97251 (0.0009) -[2023-10-09 12:09:43,231][23469] Updated weights for policy 1, policy_version 97261 (0.0009) -[2023-10-09 12:09:43,590][23469] Updated weights for policy 1, policy_version 97271 (0.0007) -[2023-10-09 12:09:45,982][23468] Updated weights for policy 0, policy_version 96743 (0.0008) -[2023-10-09 12:09:46,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 198672384. Throughput: 0: 1792.4, 1: 1791.5. Samples: 49682616. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 12:09:46,078][22500] Avg episode reward: [(0, '10.840'), (1, '9.690')] -[2023-10-09 12:09:46,352][23468] Updated weights for policy 0, policy_version 96753 (0.0008) -[2023-10-09 12:09:46,725][23468] Updated weights for policy 0, policy_version 96763 (0.0009) -[2023-10-09 12:09:47,249][23469] Updated weights for policy 1, policy_version 97281 (0.0008) -[2023-10-09 12:09:47,626][23469] Updated weights for policy 1, policy_version 97291 (0.0008) -[2023-10-09 12:09:48,000][23469] Updated weights for policy 1, policy_version 97301 (0.0008) -[2023-10-09 12:09:48,364][23469] Updated weights for policy 1, policy_version 97311 (0.0010) -[2023-10-09 12:09:50,487][23468] Updated weights for policy 0, policy_version 96773 (0.0008) -[2023-10-09 12:09:50,865][23468] Updated weights for policy 0, policy_version 96783 (0.0009) -[2023-10-09 12:09:51,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 198737920. Throughput: 0: 1782.3, 1: 1796.3. Samples: 49692436. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 12:09:51,078][22500] Avg episode reward: [(0, '10.910'), (1, '9.490')] -[2023-10-09 12:09:51,238][23468] Updated weights for policy 0, policy_version 96793 (0.0009) -[2023-10-09 12:09:52,143][23469] Updated weights for policy 1, policy_version 97321 (0.0010) -[2023-10-09 12:09:52,520][23469] Updated weights for policy 1, policy_version 97331 (0.0010) -[2023-10-09 12:09:52,890][23469] Updated weights for policy 1, policy_version 97341 (0.0008) -[2023-10-09 12:09:54,893][23468] Updated weights for policy 0, policy_version 96803 (0.0008) -[2023-10-09 12:09:55,264][23468] Updated weights for policy 0, policy_version 96813 (0.0007) -[2023-10-09 12:09:55,631][23468] Updated weights for policy 0, policy_version 96823 (0.0008) -[2023-10-09 12:09:56,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 198836224. Throughput: 0: 1793.6, 1: 1799.1. Samples: 49715216. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 12:09:56,078][22500] Avg episode reward: [(0, '11.260'), (1, '10.780')] -[2023-10-09 12:09:56,583][23469] Updated weights for policy 1, policy_version 97351 (0.0007) -[2023-10-09 12:09:56,948][23469] Updated weights for policy 1, policy_version 97361 (0.0008) -[2023-10-09 12:09:57,314][23469] Updated weights for policy 1, policy_version 97371 (0.0007) -[2023-10-09 12:09:59,434][23468] Updated weights for policy 0, policy_version 96833 (0.0008) -[2023-10-09 12:09:59,849][23468] Updated weights for policy 0, policy_version 96843 (0.0007) -[2023-10-09 12:10:00,218][23468] Updated weights for policy 0, policy_version 96853 (0.0008) -[2023-10-09 12:10:00,593][23468] Updated weights for policy 0, policy_version 96863 (0.0007) -[2023-10-09 12:10:00,923][23469] Updated weights for policy 1, policy_version 97381 (0.0011) -[2023-10-09 12:10:01,077][22500] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 198901760. Throughput: 0: 1794.2, 1: 1810.2. Samples: 49736686. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 12:10:01,078][22500] Avg episode reward: [(0, '11.640'), (1, '9.920')] -[2023-10-09 12:10:01,288][23469] Updated weights for policy 1, policy_version 97391 (0.0009) -[2023-10-09 12:10:01,663][23469] Updated weights for policy 1, policy_version 97401 (0.0007) -[2023-10-09 12:10:04,271][23468] Updated weights for policy 0, policy_version 96873 (0.0010) -[2023-10-09 12:10:04,639][23468] Updated weights for policy 0, policy_version 96883 (0.0011) -[2023-10-09 12:10:05,005][23468] Updated weights for policy 0, policy_version 96893 (0.0010) -[2023-10-09 12:10:05,372][23469] Updated weights for policy 1, policy_version 97411 (0.0008) -[2023-10-09 12:10:05,737][23469] Updated weights for policy 1, policy_version 97421 (0.0010) -[2023-10-09 12:10:06,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 198967296. Throughput: 0: 1791.8, 1: 1802.6. Samples: 49747458. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 12:10:06,078][22500] Avg episode reward: [(0, '11.310'), (1, '10.300')] -[2023-10-09 12:10:06,101][23469] Updated weights for policy 1, policy_version 97431 (0.0010) -[2023-10-09 12:10:08,818][23468] Updated weights for policy 0, policy_version 96903 (0.0008) -[2023-10-09 12:10:09,183][23468] Updated weights for policy 0, policy_version 96913 (0.0011) -[2023-10-09 12:10:09,566][23468] Updated weights for policy 0, policy_version 96923 (0.0010) -[2023-10-09 12:10:09,923][23469] Updated weights for policy 1, policy_version 97441 (0.0009) -[2023-10-09 12:10:10,289][23469] Updated weights for policy 1, policy_version 97451 (0.0010) -[2023-10-09 12:10:10,661][23469] Updated weights for policy 1, policy_version 97461 (0.0010) -[2023-10-09 12:10:11,042][23469] Updated weights for policy 1, policy_version 97471 (0.0008) -[2023-10-09 12:10:11,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 199065600. Throughput: 0: 1794.6, 1: 1810.2. Samples: 49769072. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 12:10:11,078][22500] Avg episode reward: [(0, '11.200'), (1, '9.920')] -[2023-10-09 12:10:13,186][23468] Updated weights for policy 0, policy_version 96933 (0.0009) -[2023-10-09 12:10:13,559][23468] Updated weights for policy 0, policy_version 96943 (0.0009) -[2023-10-09 12:10:13,926][23468] Updated weights for policy 0, policy_version 96953 (0.0008) -[2023-10-09 12:10:14,836][23469] Updated weights for policy 1, policy_version 97481 (0.0009) -[2023-10-09 12:10:15,211][23469] Updated weights for policy 1, policy_version 97491 (0.0008) -[2023-10-09 12:10:15,590][23469] Updated weights for policy 1, policy_version 97501 (0.0010) -[2023-10-09 12:10:16,078][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 199131136. Throughput: 0: 1783.1, 1: 1798.8. Samples: 49789462. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 12:10:16,078][22500] Avg episode reward: [(0, '11.000'), (1, '9.580')] -[2023-10-09 12:10:16,092][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000097504_99844096.pth... -[2023-10-09 12:10:16,093][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000096960_99287040.pth... -[2023-10-09 12:10:16,128][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000095296_97583104.pth -[2023-10-09 12:10:16,131][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000095808_98107392.pth -[2023-10-09 12:10:17,625][23468] Updated weights for policy 0, policy_version 96963 (0.0010) -[2023-10-09 12:10:17,996][23468] Updated weights for policy 0, policy_version 96973 (0.0009) -[2023-10-09 12:10:18,363][23468] Updated weights for policy 0, policy_version 96983 (0.0007) -[2023-10-09 12:10:19,343][23469] Updated weights for policy 1, policy_version 97511 (0.0009) -[2023-10-09 12:10:19,721][23469] Updated weights for policy 1, policy_version 97521 (0.0009) -[2023-10-09 12:10:20,094][23469] Updated weights for policy 1, policy_version 97531 (0.0007) -[2023-10-09 12:10:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 199196672. Throughput: 0: 1799.8, 1: 1807.6. Samples: 49801274. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 12:10:21,078][22500] Avg episode reward: [(0, '10.850'), (1, '10.250')] -[2023-10-09 12:10:22,151][23468] Updated weights for policy 0, policy_version 96993 (0.0007) -[2023-10-09 12:10:22,520][23468] Updated weights for policy 0, policy_version 97003 (0.0009) -[2023-10-09 12:10:22,893][23468] Updated weights for policy 0, policy_version 97013 (0.0011) -[2023-10-09 12:10:23,264][23468] Updated weights for policy 0, policy_version 97023 (0.0011) -[2023-10-09 12:10:23,672][23469] Updated weights for policy 1, policy_version 97541 (0.0008) -[2023-10-09 12:10:24,038][23469] Updated weights for policy 1, policy_version 97551 (0.0009) -[2023-10-09 12:10:24,405][23469] Updated weights for policy 1, policy_version 97561 (0.0009) -[2023-10-09 12:10:26,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 199262208. Throughput: 0: 1790.6, 1: 1797.1. Samples: 49821682. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:10:26,079][22500] Avg episode reward: [(0, '10.960'), (1, '9.970')] -[2023-10-09 12:10:27,045][23468] Updated weights for policy 0, policy_version 97033 (0.0008) -[2023-10-09 12:10:27,427][23468] Updated weights for policy 0, policy_version 97043 (0.0007) -[2023-10-09 12:10:27,793][23468] Updated weights for policy 0, policy_version 97053 (0.0007) -[2023-10-09 12:10:28,290][23469] Updated weights for policy 1, policy_version 97571 (0.0010) -[2023-10-09 12:10:28,652][23469] Updated weights for policy 1, policy_version 97581 (0.0008) -[2023-10-09 12:10:29,024][23469] Updated weights for policy 1, policy_version 97591 (0.0009) -[2023-10-09 12:10:31,077][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 199327744. Throughput: 0: 1794.8, 1: 1792.8. Samples: 49844056. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:10:31,078][22500] Avg episode reward: [(0, '10.880'), (1, '10.500')] -[2023-10-09 12:10:31,437][23468] Updated weights for policy 0, policy_version 97063 (0.0008) -[2023-10-09 12:10:31,809][23468] Updated weights for policy 0, policy_version 97073 (0.0007) -[2023-10-09 12:10:32,182][23468] Updated weights for policy 0, policy_version 97083 (0.0008) -[2023-10-09 12:10:32,819][23469] Updated weights for policy 1, policy_version 97601 (0.0009) -[2023-10-09 12:10:33,229][23469] Updated weights for policy 1, policy_version 97611 (0.0007) -[2023-10-09 12:10:33,611][23469] Updated weights for policy 1, policy_version 97621 (0.0007) -[2023-10-09 12:10:33,977][23469] Updated weights for policy 1, policy_version 97631 (0.0008) -[2023-10-09 12:10:36,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 199393280. Throughput: 0: 1793.2, 1: 1798.8. Samples: 49854072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:10:36,078][22500] Avg episode reward: [(0, '11.200'), (1, '9.900')] -[2023-10-09 12:10:36,125][23468] Updated weights for policy 0, policy_version 97093 (0.0007) -[2023-10-09 12:10:36,495][23468] Updated weights for policy 0, policy_version 97103 (0.0007) -[2023-10-09 12:10:36,866][23468] Updated weights for policy 0, policy_version 97113 (0.0007) -[2023-10-09 12:10:37,672][23469] Updated weights for policy 1, policy_version 97641 (0.0008) -[2023-10-09 12:10:38,029][23469] Updated weights for policy 1, policy_version 97651 (0.0011) -[2023-10-09 12:10:38,402][23469] Updated weights for policy 1, policy_version 97661 (0.0009) -[2023-10-09 12:10:40,599][23468] Updated weights for policy 0, policy_version 97123 (0.0008) -[2023-10-09 12:10:40,969][23468] Updated weights for policy 0, policy_version 97133 (0.0008) -[2023-10-09 12:10:41,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 199458816. Throughput: 0: 1782.5, 1: 1789.7. Samples: 49875964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:10:41,078][22500] Avg episode reward: [(0, '10.490'), (1, '10.660')] -[2023-10-09 12:10:41,338][23468] Updated weights for policy 0, policy_version 97143 (0.0007) -[2023-10-09 12:10:42,205][23469] Updated weights for policy 1, policy_version 97671 (0.0009) -[2023-10-09 12:10:42,571][23469] Updated weights for policy 1, policy_version 97681 (0.0008) -[2023-10-09 12:10:42,939][23469] Updated weights for policy 1, policy_version 97691 (0.0007) -[2023-10-09 12:10:45,203][23468] Updated weights for policy 0, policy_version 97153 (0.0008) -[2023-10-09 12:10:45,610][23468] Updated weights for policy 0, policy_version 97163 (0.0008) -[2023-10-09 12:10:45,979][23468] Updated weights for policy 0, policy_version 97173 (0.0008) -[2023-10-09 12:10:46,078][22500] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 199524352. Throughput: 0: 1800.7, 1: 1787.5. Samples: 49898152. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:10:46,079][22500] Avg episode reward: [(0, '10.920'), (1, '10.390')] -[2023-10-09 12:10:46,342][23468] Updated weights for policy 0, policy_version 97183 (0.0007) -[2023-10-09 12:10:46,694][23469] Updated weights for policy 1, policy_version 97701 (0.0008) -[2023-10-09 12:10:47,062][23469] Updated weights for policy 1, policy_version 97711 (0.0009) -[2023-10-09 12:10:47,424][23469] Updated weights for policy 1, policy_version 97721 (0.0008) -[2023-10-09 12:10:50,020][23468] Updated weights for policy 0, policy_version 97193 (0.0007) -[2023-10-09 12:10:50,389][23468] Updated weights for policy 0, policy_version 97203 (0.0009) -[2023-10-09 12:10:50,770][23468] Updated weights for policy 0, policy_version 97213 (0.0009) -[2023-10-09 12:10:51,077][22500] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 199622656. Throughput: 0: 1782.7, 1: 1784.8. Samples: 49907994. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:10:51,079][22500] Avg episode reward: [(0, '10.740'), (1, '9.620')] -[2023-10-09 12:10:51,236][23469] Updated weights for policy 1, policy_version 97731 (0.0007) -[2023-10-09 12:10:51,603][23469] Updated weights for policy 1, policy_version 97741 (0.0007) -[2023-10-09 12:10:51,972][23469] Updated weights for policy 1, policy_version 97751 (0.0008) -[2023-10-09 12:10:54,514][23468] Updated weights for policy 0, policy_version 97223 (0.0009) -[2023-10-09 12:10:54,893][23468] Updated weights for policy 0, policy_version 97233 (0.0009) -[2023-10-09 12:10:55,267][23468] Updated weights for policy 0, policy_version 97243 (0.0010) -[2023-10-09 12:10:55,694][23469] Updated weights for policy 1, policy_version 97761 (0.0008) -[2023-10-09 12:10:56,061][23469] Updated weights for policy 1, policy_version 97771 (0.0007) -[2023-10-09 12:10:56,077][22500] Fps is (10 sec: 16384.4, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 199688192. Throughput: 0: 1800.0, 1: 1786.0. Samples: 49930442. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:10:56,078][22500] Avg episode reward: [(0, '11.130'), (1, '9.430')] -[2023-10-09 12:10:56,432][23469] Updated weights for policy 1, policy_version 97781 (0.0008) -[2023-10-09 12:10:56,800][23469] Updated weights for policy 1, policy_version 97791 (0.0008) -[2023-10-09 12:10:59,072][23468] Updated weights for policy 0, policy_version 97253 (0.0010) -[2023-10-09 12:10:59,446][23468] Updated weights for policy 0, policy_version 97263 (0.0009) -[2023-10-09 12:10:59,831][23468] Updated weights for policy 0, policy_version 97273 (0.0008) -[2023-10-09 12:11:00,430][23469] Updated weights for policy 1, policy_version 97801 (0.0011) -[2023-10-09 12:11:00,805][23469] Updated weights for policy 1, policy_version 97811 (0.0010) -[2023-10-09 12:11:01,078][22500] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 199753728. Throughput: 0: 1777.9, 1: 1803.8. Samples: 49950636. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:11:01,079][22500] Avg episode reward: [(0, '10.880'), (1, '9.040')] -[2023-10-09 12:11:01,170][23469] Updated weights for policy 1, policy_version 97821 (0.0009) -[2023-10-09 12:11:03,550][23468] Updated weights for policy 0, policy_version 97283 (0.0007) -[2023-10-09 12:11:03,923][23468] Updated weights for policy 0, policy_version 97293 (0.0007) -[2023-10-09 12:11:04,297][23468] Updated weights for policy 0, policy_version 97303 (0.0008) -[2023-10-09 12:11:05,031][23469] Updated weights for policy 1, policy_version 97831 (0.0009) -[2023-10-09 12:11:05,407][23469] Updated weights for policy 1, policy_version 97841 (0.0007) -[2023-10-09 12:11:05,771][23469] Updated weights for policy 1, policy_version 97851 (0.0010) -[2023-10-09 12:11:06,077][22500] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 199852032. Throughput: 0: 1801.3, 1: 1785.0. Samples: 49962660. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:11:06,079][22500] Avg episode reward: [(0, '10.190'), (1, '9.310')] -[2023-10-09 12:11:08,035][23468] Updated weights for policy 0, policy_version 97313 (0.0010) -[2023-10-09 12:11:08,413][23468] Updated weights for policy 0, policy_version 97323 (0.0010) -[2023-10-09 12:11:08,796][23468] Updated weights for policy 0, policy_version 97333 (0.0010) -[2023-10-09 12:11:09,175][23468] Updated weights for policy 0, policy_version 97343 (0.0009) -[2023-10-09 12:11:09,473][23469] Updated weights for policy 1, policy_version 97861 (0.0007) -[2023-10-09 12:11:09,852][23469] Updated weights for policy 1, policy_version 97871 (0.0007) -[2023-10-09 12:11:10,218][23469] Updated weights for policy 1, policy_version 97881 (0.0009) -[2023-10-09 12:11:11,077][22500] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 199917568. Throughput: 0: 1776.7, 1: 1808.2. Samples: 49983000. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:11:11,078][22500] Avg episode reward: [(0, '11.140'), (1, '9.180')] -[2023-10-09 12:11:12,901][23468] Updated weights for policy 0, policy_version 97353 (0.0007) -[2023-10-09 12:11:13,273][23468] Updated weights for policy 0, policy_version 97363 (0.0008) -[2023-10-09 12:11:13,648][23468] Updated weights for policy 0, policy_version 97373 (0.0009) -[2023-10-09 12:11:13,827][23469] Updated weights for policy 1, policy_version 97891 (0.0008) -[2023-10-09 12:11:14,192][23469] Updated weights for policy 1, policy_version 97901 (0.0011) -[2023-10-09 12:11:14,565][23469] Updated weights for policy 1, policy_version 97911 (0.0008) -[2023-10-09 12:11:16,077][22500] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 199983104. Throughput: 0: 1776.1, 1: 1799.3. Samples: 50004950. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:11:16,078][22500] Avg episode reward: [(0, '10.110'), (1, '9.840')] -[2023-10-09 12:11:17,436][23468] Updated weights for policy 0, policy_version 97383 (0.0008) -[2023-10-09 12:11:17,807][23468] Updated weights for policy 0, policy_version 97393 (0.0010) -[2023-10-09 12:11:18,180][23468] Updated weights for policy 0, policy_version 97403 (0.0010) -[2023-10-09 12:11:18,420][23469] Updated weights for policy 1, policy_version 97921 (0.0008) -[2023-10-09 12:11:18,828][23469] Updated weights for policy 1, policy_version 97931 (0.0007) -[2023-10-09 12:11:19,189][23469] Updated weights for policy 1, policy_version 97941 (0.0010) -[2023-10-09 12:11:19,564][23469] Updated weights for policy 1, policy_version 97951 (0.0011) -[2023-10-09 12:11:21,077][22500] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 200048640. Throughput: 0: 1779.7, 1: 1814.1. Samples: 50015796. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:11:21,078][22500] Avg episode reward: [(0, '10.840'), (1, '9.900')] -[2023-10-09 12:11:21,826][23468] Updated weights for policy 0, policy_version 97413 (0.0009) -[2023-10-09 12:11:22,192][23468] Updated weights for policy 0, policy_version 97423 (0.0011) -[2023-10-09 12:11:22,568][23468] Updated weights for policy 0, policy_version 97433 (0.0010) -[2023-10-09 12:11:23,388][23469] Updated weights for policy 1, policy_version 97961 (0.0008) -[2023-10-09 12:11:23,762][23469] Updated weights for policy 1, policy_version 97971 (0.0009) -[2023-10-09 12:11:24,127][23469] Updated weights for policy 1, policy_version 97981 (0.0008) -[2023-10-09 12:11:26,077][22500] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 200114176. Throughput: 0: 1782.5, 1: 1793.8. Samples: 50036898. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:11:26,078][22500] Avg episode reward: [(0, '10.820'), (1, '9.890')] -[2023-10-09 12:11:26,419][23468] Updated weights for policy 0, policy_version 97443 (0.0008) -[2023-10-09 12:11:26,792][23468] Updated weights for policy 0, policy_version 97453 (0.0008) -[2023-10-09 12:11:27,163][23468] Updated weights for policy 0, policy_version 97463 (0.0009) -[2023-10-09 12:11:27,852][23469] Updated weights for policy 1, policy_version 97991 (0.0010) -[2023-10-09 12:11:28,224][23469] Updated weights for policy 1, policy_version 98001 (0.0011) -[2023-10-09 12:11:28,591][23469] Updated weights for policy 1, policy_version 98011 (0.0010) -[2023-10-09 12:11:30,864][23468] Updated weights for policy 0, policy_version 97473 (0.0008) -[2023-10-09 12:11:31,077][22500] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 200179712. Throughput: 0: 1791.5, 1: 1796.8. Samples: 50059624. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:11:31,078][22500] Avg episode reward: [(0, '10.640'), (1, '9.380')] -[2023-10-09 12:11:31,260][23468] Updated weights for policy 0, policy_version 97483 (0.0010) -[2023-10-09 12:11:31,635][23468] Updated weights for policy 0, policy_version 97493 (0.0008) -[2023-10-09 12:11:32,005][23468] Updated weights for policy 0, policy_version 97503 (0.0009) -[2023-10-09 12:11:32,266][23469] Updated weights for policy 1, policy_version 98021 (0.0009) -[2023-10-09 12:11:32,633][23469] Updated weights for policy 1, policy_version 98031 (0.0008) -[2023-10-09 12:11:33,001][23469] Updated weights for policy 1, policy_version 98041 (0.0008) -[2023-10-09 12:11:35,694][23468] Updated weights for policy 0, policy_version 97513 (0.0011) -[2023-10-09 12:11:36,067][23468] Updated weights for policy 0, policy_version 97523 (0.0007) -[2023-10-09 12:11:36,077][22500] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 200245248. Throughput: 0: 1784.7, 1: 1802.4. Samples: 50069410. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:11:36,078][22500] Avg episode reward: [(0, '10.910'), (1, '9.290')] -[2023-10-09 12:11:36,440][23468] Updated weights for policy 0, policy_version 97533 (0.0009) -[2023-10-09 12:11:36,667][23469] Updated weights for policy 1, policy_version 98051 (0.0008) -[2023-10-09 12:11:37,037][23469] Updated weights for policy 1, policy_version 98061 (0.0009) -[2023-10-09 12:11:37,399][23469] Updated weights for policy 1, policy_version 98071 (0.0009) -[2023-10-09 12:11:40,154][23468] Updated weights for policy 0, policy_version 97543 (0.0009) -[2023-10-09 12:11:40,524][23468] Updated weights for policy 0, policy_version 97553 (0.0010) -[2023-10-09 12:11:40,891][23468] Updated weights for policy 0, policy_version 97563 (0.0011) -[2023-10-09 12:11:41,077][22500] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 200343552. Throughput: 0: 1792.4, 1: 1797.2. Samples: 50091974. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:11:41,078][22500] Avg episode reward: [(0, '10.740'), (1, '9.490')] -[2023-10-09 12:11:41,187][23469] Updated weights for policy 1, policy_version 98081 (0.0009) -[2023-10-09 12:11:41,546][23469] Updated weights for policy 1, policy_version 98091 (0.0010) -[2023-10-09 12:11:41,919][23469] Updated weights for policy 1, policy_version 98101 (0.0009) -[2023-10-09 12:11:42,292][23469] Updated weights for policy 1, policy_version 98111 (0.0008) -[2023-10-09 12:11:44,629][23468] Updated weights for policy 0, policy_version 97573 (0.0009) -[2023-10-09 12:11:45,014][23468] Updated weights for policy 0, policy_version 97583 (0.0009) -[2023-10-09 12:11:45,380][23468] Updated weights for policy 0, policy_version 97593 (0.0008) -[2023-10-09 12:11:46,072][23469] Updated weights for policy 1, policy_version 98121 (0.0007) -[2023-10-09 12:11:46,077][22500] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 200409088. Throughput: 0: 1806.1, 1: 1814.5. Samples: 50113564. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:11:46,078][22500] Avg episode reward: [(0, '10.900'), (1, '9.910')] -[2023-10-09 12:11:46,452][23469] Updated weights for policy 1, policy_version 98131 (0.0008) -[2023-10-09 12:11:46,811][23469] Updated weights for policy 1, policy_version 98141 (0.0010) -[2023-10-09 12:11:49,137][23468] Updated weights for policy 0, policy_version 97603 (0.0008) -[2023-10-09 12:11:49,514][23468] Updated weights for policy 0, policy_version 97613 (0.0007) -[2023-10-09 12:11:49,886][23468] Updated weights for policy 0, policy_version 97623 (0.0007) -[2023-10-09 12:11:50,495][23469] Updated weights for policy 1, policy_version 98151 (0.0010) -[2023-10-09 12:11:50,856][23469] Updated weights for policy 1, policy_version 98161 (0.0007) -[2023-10-09 12:11:51,077][22500] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 200474624. Throughput: 0: 1790.7, 1: 1800.1. Samples: 50124248. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 12:11:51,078][22500] Avg episode reward: [(0, '10.950'), (1, '10.040')] -[2023-10-09 12:11:51,220][23469] Updated weights for policy 1, policy_version 98171 (0.0007) -[2023-10-09 12:11:53,801][23468] Updated weights for policy 0, policy_version 97633 (0.0009) -[2023-10-09 12:11:54,171][23468] Updated weights for policy 0, policy_version 97643 (0.0009) -[2023-10-09 12:11:54,542][23468] Updated weights for policy 0, policy_version 97653 (0.0008) -[2023-10-09 12:11:54,915][23468] Updated weights for policy 0, policy_version 97663 (0.0007) -[2023-10-09 12:11:55,003][23469] Updated weights for policy 1, policy_version 98181 (0.0008) -[2023-10-09 12:11:55,374][23469] Updated weights for policy 1, policy_version 98191 (0.0009) -[2023-10-09 12:11:55,737][23469] Updated weights for policy 1, policy_version 98201 (0.0008) -[2023-10-09 12:11:55,998][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000098208_100564992.pth... -[2023-10-09 12:11:55,998][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000097664_100007936.pth... -[2023-10-09 12:11:55,999][23532] Stopping RolloutWorker_w10... -[2023-10-09 12:11:55,999][23531] Stopping RolloutWorker_w9... -[2023-10-09 12:11:55,999][23532] Loop rollout_proc10_evt_loop terminating... -[2023-10-09 12:11:55,999][23513] Stopping RolloutWorker_w1... -[2023-10-09 12:11:55,999][23531] Loop rollout_proc9_evt_loop terminating... -[2023-10-09 12:11:55,999][23522] Stopping RolloutWorker_w6... -[2023-10-09 12:11:55,999][23535] Stopping RolloutWorker_w13... -[2023-10-09 12:11:55,999][23514] Stopping RolloutWorker_w0... -[2023-10-09 12:11:56,000][23513] Loop rollout_proc1_evt_loop terminating... -[2023-10-09 12:11:56,000][23522] Loop rollout_proc6_evt_loop terminating... -[2023-10-09 12:11:56,000][23535] Loop rollout_proc13_evt_loop terminating... -[2023-10-09 12:11:56,000][23514] Loop rollout_proc0_evt_loop terminating... -[2023-10-09 12:11:56,000][23517] Stopping RolloutWorker_w3... -[2023-10-09 12:11:56,000][23516] Stopping RolloutWorker_w2... -[2023-10-09 12:11:56,000][24382] Stopping RolloutWorker_w14... -[2023-10-09 12:11:56,000][23516] Loop rollout_proc2_evt_loop terminating... -[2023-10-09 12:11:56,000][23525] Stopping RolloutWorker_w7... -[2023-10-09 12:11:56,000][23517] Loop rollout_proc3_evt_loop terminating... -[2023-10-09 12:11:56,000][24382] Loop rollout_proc14_evt_loop terminating... -[2023-10-09 12:11:56,001][23525] Loop rollout_proc7_evt_loop terminating... -[2023-10-09 12:11:56,001][23523] Stopping RolloutWorker_w4... -[2023-10-09 12:11:56,001][23523] Loop rollout_proc4_evt_loop terminating... -[2023-10-09 12:11:56,004][23530] Stopping RolloutWorker_w8... -[2023-10-09 12:11:56,004][23530] Loop rollout_proc8_evt_loop terminating... -[2023-10-09 12:11:56,004][23534] Stopping RolloutWorker_w12... -[2023-10-09 12:11:56,005][23534] Loop rollout_proc12_evt_loop terminating... -[2023-10-09 12:11:56,005][24383] Stopping RolloutWorker_w15... -[2023-10-09 12:11:56,005][23533] Stopping RolloutWorker_w11... -[2023-10-09 12:11:56,005][24383] Loop rollout_proc15_evt_loop terminating... -[2023-10-09 12:11:56,006][23533] Loop rollout_proc11_evt_loop terminating... -[2023-10-09 12:11:56,009][22500] Component RolloutWorker_w10 stopped! -[2023-10-09 12:11:56,011][22500] Component RolloutWorker_w9 stopped! -[2023-10-09 12:11:56,012][22500] Component RolloutWorker_w1 stopped! -[2023-10-09 12:11:56,013][22500] Component RolloutWorker_w6 stopped! -[2023-10-09 12:11:56,014][22500] Component RolloutWorker_w13 stopped! -[2023-10-09 12:11:56,014][22500] Component RolloutWorker_w0 stopped! -[2023-10-09 12:11:56,015][22500] Component RolloutWorker_w3 stopped! -[2023-10-09 12:11:56,016][22500] Component RolloutWorker_w14 stopped! -[2023-10-09 12:11:56,016][22500] Component RolloutWorker_w2 stopped! -[2023-10-09 12:11:56,017][23468] Weights refcount: 2 0 -[2023-10-09 12:11:56,017][22500] Component RolloutWorker_w7 stopped! -[2023-10-09 12:11:56,017][22500] Component RolloutWorker_w4 stopped! -[2023-10-09 12:11:56,018][22500] Component RolloutWorker_w8 stopped! -[2023-10-09 12:11:56,018][22500] Component RolloutWorker_w12 stopped! -[2023-10-09 12:11:56,018][23468] Stopping InferenceWorker_p0-w0... -[2023-10-09 12:11:56,018][22500] Component Batcher_0 stopped! -[2023-10-09 12:11:56,005][23265] Stopping Batcher_0... -[2023-10-09 12:11:56,018][22500] Component RolloutWorker_w15 stopped! -[2023-10-09 12:11:56,018][23468] Loop inference_proc0-0_evt_loop terminating... -[2023-10-09 12:11:56,019][22500] Component RolloutWorker_w11 stopped! -[2023-10-09 12:11:56,019][22500] Component Batcher_1 stopped! -[2023-10-09 12:11:56,019][22500] Component InferenceWorker_p0-w0 stopped! -[2023-10-09 12:11:56,022][23520] Stopping RolloutWorker_w5... -[2023-10-09 12:11:56,022][22500] Component RolloutWorker_w5 stopped! -[2023-10-09 12:11:56,022][23520] Loop rollout_proc5_evt_loop terminating... -[2023-10-09 12:11:56,011][23343] Stopping Batcher_1... -[2023-10-09 12:11:56,026][23469] Weights refcount: 2 0 -[2023-10-09 12:11:56,028][23469] Stopping InferenceWorker_p1-w0... -[2023-10-09 12:11:56,028][23469] Loop inference_proc1-0_evt_loop terminating... -[2023-10-09 12:11:56,028][22500] Component InferenceWorker_p1-w0 stopped! -[2023-10-09 12:11:56,033][23343] Loop batcher_evt_loop terminating... -[2023-10-09 12:11:56,035][23343] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000096640_98959360.pth -[2023-10-09 12:11:56,039][23343] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p1/checkpoint_000098208_100564992.pth... -[2023-10-09 12:11:56,032][23265] Loop batcher_evt_loop terminating... -[2023-10-09 12:11:56,045][23265] Removing ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000096128_98435072.pth -[2023-10-09 12:11:56,051][23265] Saving ./train_atari/atari_berzerk_APPO/checkpoint_p0/checkpoint_000097664_100007936.pth... -[2023-10-09 12:11:56,078][23343] Stopping LearnerWorker_p1... -[2023-10-09 12:11:56,078][23343] Loop learner_proc1_evt_loop terminating... -[2023-10-09 12:11:56,078][22500] Component LearnerWorker_p1 stopped! -[2023-10-09 12:11:56,107][23265] Stopping LearnerWorker_p0... -[2023-10-09 12:11:56,108][22500] Component LearnerWorker_p0 stopped! -[2023-10-09 12:11:56,108][23265] Loop learner_proc0_evt_loop terminating... -[2023-10-09 12:11:56,108][22500] Waiting for process learner_proc0 to stop... -[2023-10-09 12:11:56,967][22500] Waiting for process learner_proc1 to stop... -[2023-10-09 12:11:56,968][22500] Waiting for process inference_proc0-0 to join... -[2023-10-09 12:11:56,968][22500] Waiting for process inference_proc1-0 to join... -[2023-10-09 12:11:56,998][22500] Waiting for process rollout_proc0 to join... -[2023-10-09 12:11:56,999][22500] Waiting for process rollout_proc1 to join... -[2023-10-09 12:11:57,000][22500] Waiting for process rollout_proc2 to join... -[2023-10-09 12:11:57,001][22500] Waiting for process rollout_proc3 to join... -[2023-10-09 12:11:57,001][22500] Waiting for process rollout_proc4 to join... -[2023-10-09 12:11:57,002][22500] Waiting for process rollout_proc5 to join... -[2023-10-09 12:11:57,003][22500] Waiting for process rollout_proc6 to join... -[2023-10-09 12:11:57,004][22500] Waiting for process rollout_proc7 to join... -[2023-10-09 12:11:57,005][22500] Waiting for process rollout_proc8 to join... -[2023-10-09 12:11:57,005][22500] Waiting for process rollout_proc9 to join... -[2023-10-09 12:11:57,005][22500] Waiting for process rollout_proc10 to join... -[2023-10-09 12:11:57,006][22500] Waiting for process rollout_proc11 to join... -[2023-10-09 12:11:57,006][22500] Waiting for process rollout_proc12 to join... -[2023-10-09 12:11:57,006][22500] Waiting for process rollout_proc13 to join... -[2023-10-09 12:11:57,007][22500] Waiting for process rollout_proc14 to join... -[2023-10-09 12:11:57,007][22500] Waiting for process rollout_proc15 to join... -[2023-10-09 12:11:57,007][22500] Batcher 0 profile tree view: -batching: 172.3734, releasing_batches: 0.0909 -[2023-10-09 12:11:57,008][22500] Batcher 1 profile tree view: -batching: 172.6782, releasing_batches: 0.0922 -[2023-10-09 12:11:57,008][22500] InferenceWorker_p0-w0 profile tree view: -wait_policy: 0.0003 - wait_policy_total: 1937.1248 -update_model: 199.5477 - weight_update: 0.0007 -one_step: 0.0014 - handle_policy_step: 11308.7530 - deserialize: 63.5071, stack: 194.4689, obs_to_device_normalize: 2532.6586, forward: 5098.5448, prepare_outputs: 2472.3535, send_messages: 461.3275 -[2023-10-09 12:11:57,009][22500] InferenceWorker_p1-w0 profile tree view: -wait_policy: 0.0001 - wait_policy_total: 1895.0856 -update_model: 200.5387 - weight_update: 0.0009 -one_step: 0.0026 - handle_policy_step: 11346.7640 - deserialize: 63.7888, stack: 194.9659, obs_to_device_normalize: 2518.0680, forward: 5126.7366, prepare_outputs: 2483.0742, send_messages: 472.9656 -[2023-10-09 12:11:57,009][22500] Learner 0 profile tree view: -misc: 0.0199, prepare_batch: 269.7933 -train: 3656.3245 - epoch_init: 0.1879, minibatch_init: 13.3410, losses_postprocess: 900.5620, kl_divergence: 31.9976, update: 385.9151, after_optimizer: 2136.8858 - calculate_losses: 170.2787 - losses_init: 0.4072, forward_head: 59.7189, bptt_initial: 1.4394, bptt: 1.8427, tail: 38.2372, advantages_returns: 11.0732, losses: 43.7579 -[2023-10-09 12:11:57,009][22500] Learner 1 profile tree view: -misc: 0.0200, prepare_batch: 270.8032 -train: 3648.9891 - epoch_init: 0.1880, minibatch_init: 13.0602, losses_postprocess: 902.7253, kl_divergence: 31.1992, update: 387.3318, after_optimizer: 2127.7065 - calculate_losses: 169.8876 - losses_init: 0.4318, forward_head: 59.7685, bptt_initial: 1.4366, bptt: 1.8731, tail: 38.1529, advantages_returns: 11.0209, losses: 43.5570 -[2023-10-09 12:11:57,010][22500] RolloutWorker_w0 profile tree view: -wait_for_trajectories: 1.2216, enqueue_policy_requests: 404.0989, process_policy_outputs: 194.5348, env_step: 6685.2898, finalize_trajectories: 3.4408, complete_rollouts: 2.9353 -post_env_step: 376.7121 - process_env_step: 84.8643 -[2023-10-09 12:11:57,010][22500] RolloutWorker_w15 profile tree view: -wait_for_trajectories: 1.2104, enqueue_policy_requests: 405.5947, process_policy_outputs: 196.0802, env_step: 6621.2096, finalize_trajectories: 3.5908, complete_rollouts: 2.9149 -post_env_step: 377.6685 - process_env_step: 85.8004 -[2023-10-09 12:11:57,010][22500] Loop Runner_EvtLoop terminating... -[2023-10-09 12:11:57,011][22500] Runner profile tree view: -main_loop: 14136.3197 -[2023-10-09 12:11:57,011][22500] Collected {0: 100007936, 1: 100564992}, FPS: 14188.5 +version https://git-lfs.github.com/spec/v1 +oid sha256:9500d0b43935294f09aca18252fd108e6927ac66390248843fd10485cfb00bd9 +size 48650122