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.1701928702.rhmmedcatt-proliant-ml350-gen10 b/.summary/0/events.out.tfevents.1701928702.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..5763484bdd20db8e1b91d7964b7491d951ea7413 --- /dev/null +++ b/.summary/0/events.out.tfevents.1701928702.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7088c596c3dc18b711e6cef7b429e1bbc990e624ad5a0814be4ebffb7589b1bf +size 83625864 diff --git a/.summary/1/events.out.tfevents.1701928702.rhmmedcatt-proliant-ml350-gen10 b/.summary/1/events.out.tfevents.1701928702.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..4dd481532713833041877fe7200aacc204fc36d5 --- /dev/null +++ b/.summary/1/events.out.tfevents.1701928702.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59c18a79b5425fb0db0c08242bd53ad72b1da06d6daa3cabf9910766d97c7afc +size 43926452 diff --git a/README.md b/README.md index 8f5e809ed5db13a9dcd7039c566d540f57ef964d..a8f27276692c6a4d24d2e7480e2a5c3143203388 100644 --- a/README.md +++ b/README.md @@ -15,35 +15,39 @@ model-index: type: atari_timepilot metrics: - type: mean_reward - value: 15050.00 +/- 1467.82 + value: 148350.00 +/- 100627.70 name: mean_reward verified: false --- -A(n) **APPO** model trained on the **atari_timepilot** 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_timepilot -``` +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_timepilot** 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_timepilot +``` + + ## Using the model To run the model after download, use the `enjoy` script corresponding to this environment: diff --git a/checkpoint_p0/best_001942784_497352704_reward_122.080.pth b/checkpoint_p0/best_001942784_497352704_reward_122.080.pth new file mode 100644 index 0000000000000000000000000000000000000000..9a9b8f6474cbefa183fe4fb83b3e974d2edc952d --- /dev/null +++ b/checkpoint_p0/best_001942784_497352704_reward_122.080.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecbacd52bcdfc27a7ffee884edc32efe3ee1715d4f02dd2503f9d5ed4443d709 +size 20746419 diff --git a/checkpoint_p0/checkpoint_001951968_499703808.pth b/checkpoint_p0/checkpoint_001951968_499703808.pth new file mode 100644 index 0000000000000000000000000000000000000000..4fa9979d568bc8ec4da3227689c4d36146a7aa4b --- /dev/null +++ b/checkpoint_p0/checkpoint_001951968_499703808.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d079ed607345d689ed9ae63d66262c94667985db86b46ffee05b7822c06198b0 +size 20746755 diff --git a/checkpoint_p0/checkpoint_001953120_500006912.pth b/checkpoint_p0/checkpoint_001953120_500006912.pth new file mode 100644 index 0000000000000000000000000000000000000000..6799bfe171c9d94e3e69fff67ed05105ff1d2bfb --- /dev/null +++ b/checkpoint_p0/checkpoint_001953120_500006912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:640abd465b472c8a5943c0b572a59c0034dcf10a44a3fc025b9f50a71379f4b7 +size 20746755 diff --git a/checkpoint_p0/milestones/checkpoint_000013248_3391488.pth b/checkpoint_p0/milestones/checkpoint_000013248_3391488.pth new file mode 100644 index 0000000000000000000000000000000000000000..db5bf0921d019b22ec05af417d9293cb19c2aaae --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000013248_3391488.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5d2eb666346be65fcc32f8e88d0afb412b1eb470823dcd6ad0c1585af6c2f60 +size 20747611 diff --git a/checkpoint_p0/milestones/checkpoint_000026816_6864896.pth b/checkpoint_p0/milestones/checkpoint_000026816_6864896.pth new file mode 100644 index 0000000000000000000000000000000000000000..77405b979c5595149abde91da12206c406fe9e27 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000026816_6864896.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f461d7a1f414a8f1d31ca3930bbabc5bc2ccc722c303a7b0433eebd9162b55c0 +size 20747611 diff --git a/checkpoint_p0/milestones/checkpoint_000040448_10354688.pth b/checkpoint_p0/milestones/checkpoint_000040448_10354688.pth new file mode 100644 index 0000000000000000000000000000000000000000..00792dcb84b905d0292728f27c2845f13a65a6a7 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000040448_10354688.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44cc7872aaa53c552acdacd946b96eab6038b32fcd20a11af3aaf363997feff8 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000054080_13844480.pth b/checkpoint_p0/milestones/checkpoint_000054080_13844480.pth new file mode 100644 index 0000000000000000000000000000000000000000..a4f7b5a38b6e75e45b457ac857952400fd5f5cdb --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000054080_13844480.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60fb3a50e473d8783a540478cc44b5132c7ab86cb243fc4e727f4fe65bfb9791 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000067744_17342464.pth b/checkpoint_p0/milestones/checkpoint_000067744_17342464.pth new file mode 100644 index 0000000000000000000000000000000000000000..bd1b1a127a09ce8a0173ff1946393faf02c11d29 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000067744_17342464.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9eb7f6daba2666160aa2f706b703de78e07d6faf3d5f1819b64057d358dc010a +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000081376_20832256.pth b/checkpoint_p0/milestones/checkpoint_000081376_20832256.pth new file mode 100644 index 0000000000000000000000000000000000000000..9088fec6a7fec11e34b35fadb0ac07172e966ce7 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000081376_20832256.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:782ce348f91d5a2734c540cdd36a1ea4fa5318c642edcc9a44a5369bb221a4ee +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000094912_24297472.pth b/checkpoint_p0/milestones/checkpoint_000094912_24297472.pth new file mode 100644 index 0000000000000000000000000000000000000000..622460b4d555095841ccb56cb51f134215b753ce --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000094912_24297472.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a2c1b6852129956d1143503e2bea1fe1811bfd2d3c6607946457717ffbc4e02 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000108544_27787264.pth b/checkpoint_p0/milestones/checkpoint_000108544_27787264.pth new file mode 100644 index 0000000000000000000000000000000000000000..006033f985ea5ccaa3585e6fa0c7e27bfb64cb63 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000108544_27787264.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1f08e89da3126972bda7f1aab398271541f72e6c9f82da400e5fc76e0a80fe0 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000122208_31285248.pth b/checkpoint_p0/milestones/checkpoint_000122208_31285248.pth new file mode 100644 index 0000000000000000000000000000000000000000..97c3c79ad89127daf772ed24e1ceb485d70eff76 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000122208_31285248.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:372f4ddda3eabe8469b90f9ac0ea6ede3f4a63723fdd9c42e2eba15035c03355 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000135936_34799616.pth b/checkpoint_p0/milestones/checkpoint_000135936_34799616.pth new file mode 100644 index 0000000000000000000000000000000000000000..13ae3b5bed85be27b7f6ffa8afa9dc4a356857a4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000135936_34799616.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f42cf6cc71e55696fe9d5a671f13ca2cf05f560acee2bfff4432bc938844974f +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000149632_38305792.pth b/checkpoint_p0/milestones/checkpoint_000149632_38305792.pth new file mode 100644 index 0000000000000000000000000000000000000000..153254a54014dd69bbb5749f9c75976b6ebbb1dc --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000149632_38305792.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e30f5316a6427180ac5a9e030a198e9aca966f09f0aa07b0de83e3e1c65385d1 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000163360_41820160.pth b/checkpoint_p0/milestones/checkpoint_000163360_41820160.pth new file mode 100644 index 0000000000000000000000000000000000000000..86ce070f6d47fc211b6bd3677b9be3b09ce2bee4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000163360_41820160.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b96eb7f2be564a22c8b3af3f681b52ed3fe45883714ae9cc69d206602b556099 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000177024_45318144.pth b/checkpoint_p0/milestones/checkpoint_000177024_45318144.pth new file mode 100644 index 0000000000000000000000000000000000000000..470c8afd2196c38b33317a20689f2d1b5e3cbfde --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000177024_45318144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ed5a62e862c382359b6073abda5e34d0f076ea669348fc43f3c94c13ac3b194 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000190752_48832512.pth b/checkpoint_p0/milestones/checkpoint_000190752_48832512.pth new file mode 100644 index 0000000000000000000000000000000000000000..22111b0f96a365247fb54dcfb8c22f52483d8109 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000190752_48832512.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8fc7ff5b1b75c27bb59a5288f47b9856ae2b1eca2cf93009e4e9f1378315086 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000204480_52346880.pth b/checkpoint_p0/milestones/checkpoint_000204480_52346880.pth new file mode 100644 index 0000000000000000000000000000000000000000..6e0567ce726e1f4cffe6474fd91773bfcf0e47de --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000204480_52346880.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:705ec016adb3074313e589aa23f17620bb88b991c6c03d90aa637a8108d32503 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000218144_55844864.pth b/checkpoint_p0/milestones/checkpoint_000218144_55844864.pth new file mode 100644 index 0000000000000000000000000000000000000000..60ec5d9a531b6aae3349150d6265036ba106f255 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000218144_55844864.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd1bced19d1ec301ba7c6452fe99d1bd6950c61fc29536be01638319fed88c8b +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000231872_59359232.pth b/checkpoint_p0/milestones/checkpoint_000231872_59359232.pth new file mode 100644 index 0000000000000000000000000000000000000000..d25ef0d61bd334fb8d99c9319ad37c4b124051a8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000231872_59359232.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9923c290f5b1e02a140b2a527a43ac54bbcda25c3712dc380704dd62d55ba9f9 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000245568_62865408.pth b/checkpoint_p0/milestones/checkpoint_000245568_62865408.pth new file mode 100644 index 0000000000000000000000000000000000000000..155a99ffdc3b2864ecc67872ac09369222f59f11 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000245568_62865408.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1911b8e86fd819a0a5fd509b310a46c664d061d6a686c044d213450ec7d5959f +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000259232_66363392.pth b/checkpoint_p0/milestones/checkpoint_000259232_66363392.pth new file mode 100644 index 0000000000000000000000000000000000000000..e38a2cd6b279549550a873b6708f096ac2082db0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000259232_66363392.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f108b922fcf8e4be7f2d21d321a6e82d0359a8f4ba47a589103bc64651e10f00 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000272960_69877760.pth b/checkpoint_p0/milestones/checkpoint_000272960_69877760.pth new file mode 100644 index 0000000000000000000000000000000000000000..c292121b3931c49533e5a7ac1afa9a13762bff03 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000272960_69877760.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:003f6a6aa637257a8492efa028227849ed513518ae87ddefc1caf1b3838cfaa0 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000286624_73375744.pth b/checkpoint_p0/milestones/checkpoint_000286624_73375744.pth new file mode 100644 index 0000000000000000000000000000000000000000..20784b44b1d6cc3910bf06d7d7787b11c19d4d40 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000286624_73375744.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df960dfe7b48aa62b803e246265de55c7eadf84b56d3889af22328e1e57404b0 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000300192_76849152.pth b/checkpoint_p0/milestones/checkpoint_000300192_76849152.pth new file mode 100644 index 0000000000000000000000000000000000000000..162dc2b5d8f88c33cbcf93b369bbfd0e85fe4b9c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000300192_76849152.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ca0ed32727a11556454a50d1c63b0eb7528e90f227bf36e015ca5bc3bd89a44 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000313792_80330752.pth b/checkpoint_p0/milestones/checkpoint_000313792_80330752.pth new file mode 100644 index 0000000000000000000000000000000000000000..3f5dec564db86db70e04594e647d3c3907efa107 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000313792_80330752.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:678469d2842a548f9d0f8070fb8bd058c099e45cf5a3265f72e2ea3ecf293efa +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000327424_83820544.pth b/checkpoint_p0/milestones/checkpoint_000327424_83820544.pth new file mode 100644 index 0000000000000000000000000000000000000000..3fb1e017cbdba784d08df0b29e20360b522944f2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000327424_83820544.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4146b447bf6282db28f7987845c1b940dec9d2ff207d6ce246c18b3d0a320bb +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000341024_87302144.pth b/checkpoint_p0/milestones/checkpoint_000341024_87302144.pth new file mode 100644 index 0000000000000000000000000000000000000000..cace6453d081f62f2f8cd954b19f75d78f8ceb79 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000341024_87302144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc59a59ee177370978618d7e7a7f947d98bbbe2c5d7a3ffe185850513dd7e26c +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000354656_90791936.pth b/checkpoint_p0/milestones/checkpoint_000354656_90791936.pth new file mode 100644 index 0000000000000000000000000000000000000000..430345674cf0e67d61a4a42fd11e3f39f5f835b5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000354656_90791936.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb7fea5cbb1d4736d39f8ab5dd0ccbc306454303f9098f54fdbf2b2c2585b8a2 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000368320_94289920.pth b/checkpoint_p0/milestones/checkpoint_000368320_94289920.pth new file mode 100644 index 0000000000000000000000000000000000000000..73c8eadd28d8f4794f771346d1c9007157932de5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000368320_94289920.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f131a2f8d7b8ea3ef6504bf93d149f15bc2c17b57c870314a8fe0465b19d5ef +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000381952_97779712.pth b/checkpoint_p0/milestones/checkpoint_000381952_97779712.pth new file mode 100644 index 0000000000000000000000000000000000000000..f3fa30fc2eb330d8fd6bdfa3d8c2e07155b294b4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000381952_97779712.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:460979af9d31833728642cf62bdbb44f27052412dc8a22c6e79ac0ff7f26575b +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000395584_101269504.pth b/checkpoint_p0/milestones/checkpoint_000395584_101269504.pth new file mode 100644 index 0000000000000000000000000000000000000000..b28fa593f7605935acefdf2fb2e16d7a569448a3 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000395584_101269504.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eabbd34038c6bb17f586c8bba47f5b16b39437dea4610f8c3078f0921595565 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000409184_104751104.pth b/checkpoint_p0/milestones/checkpoint_000409184_104751104.pth new file mode 100644 index 0000000000000000000000000000000000000000..a6c15813f46622cef79212722a5549e607805761 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000409184_104751104.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5b57ccb611463682624a74b7bfd54d9fd5c47ac9b95293df8b5b1420c2cf7db +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000422816_108240896.pth b/checkpoint_p0/milestones/checkpoint_000422816_108240896.pth new file mode 100644 index 0000000000000000000000000000000000000000..45912f0dc9b5e38c5013865621c7f0a299bff4f7 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000422816_108240896.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99771f8679e6c114fe4b2390afd5f0c2603eaebf144c919569495bcd6ad384e9 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000436384_111714304.pth b/checkpoint_p0/milestones/checkpoint_000436384_111714304.pth new file mode 100644 index 0000000000000000000000000000000000000000..158e4fa5586ee679a5b96637f5e919733c3574ea --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000436384_111714304.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce009464070612d4f132989e66604e043d7afeb9a5b70e8641e3f774827303f3 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000449984_115195904.pth b/checkpoint_p0/milestones/checkpoint_000449984_115195904.pth new file mode 100644 index 0000000000000000000000000000000000000000..c749d80c4dbf542a216e97cb431f23e4be81f5f2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000449984_115195904.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ada65927e4d67510e78145dcd7a63cea2002df297dd7d3dc05fc29a3105e771d +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000463616_118685696.pth b/checkpoint_p0/milestones/checkpoint_000463616_118685696.pth new file mode 100644 index 0000000000000000000000000000000000000000..3b702534a6302ba46eb734ad857abea7b406a069 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000463616_118685696.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9be42b7d4a3e9f034e549b939902effbd25c6dd89f507c70266b1125760188ae +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000477184_122159104.pth b/checkpoint_p0/milestones/checkpoint_000477184_122159104.pth new file mode 100644 index 0000000000000000000000000000000000000000..fe0c1d7dfdcf051b4b468120aa48daa5b77ca83c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000477184_122159104.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9a40bcf285756e1d0e1afa3a3742f8270fd3a1ff7d65261309e42f9ec6e152e +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000490816_125648896.pth b/checkpoint_p0/milestones/checkpoint_000490816_125648896.pth new file mode 100644 index 0000000000000000000000000000000000000000..37c869f635cd9b6038d97c2b14b8e38138a0c5b0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000490816_125648896.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:820d20bd73f975de3ab6e0942d81342b9ff3690fa8d4774c577614e0bdcd63b8 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000504512_129155072.pth b/checkpoint_p0/milestones/checkpoint_000504512_129155072.pth new file mode 100644 index 0000000000000000000000000000000000000000..1ea19db8527890a71f99e517bc4ff0e0334a820e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000504512_129155072.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9d4beca02110855a89fe5d1cc59f60ab5c2ef45eedbebb01b7ca0f204680694 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000518144_132644864.pth b/checkpoint_p0/milestones/checkpoint_000518144_132644864.pth new file mode 100644 index 0000000000000000000000000000000000000000..11fe661573b573286fa778aa50e3c4ca4c6a67c0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000518144_132644864.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8660a9ca204638f21f81ed10b9c7ae3c23fe9a51cdd108a774133a23b69abf9e +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000531776_136134656.pth b/checkpoint_p0/milestones/checkpoint_000531776_136134656.pth new file mode 100644 index 0000000000000000000000000000000000000000..02f27d686999359871529939aa3fa72edfaa88eb --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000531776_136134656.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3716560536799fb54ecf6f9f7d38a88ed145720e52e637e18e3630dbd60d7f9b +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000545504_139649024.pth b/checkpoint_p0/milestones/checkpoint_000545504_139649024.pth new file mode 100644 index 0000000000000000000000000000000000000000..55f234cc97b7d4fb3f4e4949054fef33ae06ab24 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000545504_139649024.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11345418be405240f85d19bd9c32514b3841d5e1c25878354153aa346bec680f +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000559296_143179776.pth b/checkpoint_p0/milestones/checkpoint_000559296_143179776.pth new file mode 100644 index 0000000000000000000000000000000000000000..ae1174fa1776de3cc7dab3e887154cdb3c4c32ec --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000559296_143179776.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce15e90e4f44779652008b1d2f4772ab9bc53197b4b7158faf5e60ab55cc5e72 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000572992_146685952.pth b/checkpoint_p0/milestones/checkpoint_000572992_146685952.pth new file mode 100644 index 0000000000000000000000000000000000000000..d146cee14c3de5120d1b83cab13eef38a975ebc6 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000572992_146685952.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f758e60574aa7afda3793480f52108c59d15fb2c3f34a790be67243d766efc0e +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000586752_150208512.pth b/checkpoint_p0/milestones/checkpoint_000586752_150208512.pth new file mode 100644 index 0000000000000000000000000000000000000000..5f5db160c8a189e6d10e5f4fda3979b5cd785b3a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000586752_150208512.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:258cefb82d5eda2f43c34fdcccf6cd150205eaeac3007b158540fb9d94e92094 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000600448_153714688.pth b/checkpoint_p0/milestones/checkpoint_000600448_153714688.pth new file mode 100644 index 0000000000000000000000000000000000000000..df4e0c1fa742078b4d7d9f6deac3ed8493738312 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000600448_153714688.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53fd4bc6cf9863ccb5706c644c4ed1b7192c1f586c02c45e1afca65e1079db1d +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000614208_157237248.pth b/checkpoint_p0/milestones/checkpoint_000614208_157237248.pth new file mode 100644 index 0000000000000000000000000000000000000000..f6215bdaea614405b23fe0d10a4de7d3534b470a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000614208_157237248.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b011da0ab39fa3025ef77afa5d44492d4883fcea8a805a79134a2324a42b9e17 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000627968_160759808.pth b/checkpoint_p0/milestones/checkpoint_000627968_160759808.pth new file mode 100644 index 0000000000000000000000000000000000000000..cf57a18d69660154ca336ab13eb26056fff070fb --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000627968_160759808.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ef5830e29335650352567032d61178a9abd7f563bc648b53a60265098d8dcc2 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000641760_164290560.pth b/checkpoint_p0/milestones/checkpoint_000641760_164290560.pth new file mode 100644 index 0000000000000000000000000000000000000000..c05f7429b23e9d40910120681efa9f9a140f5602 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000641760_164290560.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07b02e0a56105ca6ac2ab2825cc6c40b616ce347d698505e0792b6cfa033d645 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000655488_167804928.pth b/checkpoint_p0/milestones/checkpoint_000655488_167804928.pth new file mode 100644 index 0000000000000000000000000000000000000000..276d8178fd8c71f204014e5bb9033d6027c5b500 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000655488_167804928.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65def520b7ad6518db9e321c2447cc39caeab76577a1e001e24ee8a473a07d2b +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000669216_171319296.pth b/checkpoint_p0/milestones/checkpoint_000669216_171319296.pth new file mode 100644 index 0000000000000000000000000000000000000000..29d80c372114e5464767946a3d4eda972de77860 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000669216_171319296.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ec88cfe5ad993cee3a037af024f83f3572582f72db9d0d82995d0eae2c5a715 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000682976_174841856.pth b/checkpoint_p0/milestones/checkpoint_000682976_174841856.pth new file mode 100644 index 0000000000000000000000000000000000000000..131944161d0254ca1e1629d4e5b03f80914afcf4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000682976_174841856.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cee5254115a76d68ea6a5a76604b68fb0f439ad90d70fefb48f10f613c040297 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000696704_178356224.pth b/checkpoint_p0/milestones/checkpoint_000696704_178356224.pth new file mode 100644 index 0000000000000000000000000000000000000000..e0b894d6f8e01295494874dfdd2412b32171ebf6 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000696704_178356224.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fe3215db4dc3f8dfa89dfcef73735cdd487bffb8d7a2d05708f82fba2127b88 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000710496_181886976.pth b/checkpoint_p0/milestones/checkpoint_000710496_181886976.pth new file mode 100644 index 0000000000000000000000000000000000000000..f7fe69a58ae03ec323e288c341947ed51a077d98 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000710496_181886976.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:222320991c0d79d04c333d625e0ab8e74cd9229365440de4c362ee84233ebfa5 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000724224_185401344.pth b/checkpoint_p0/milestones/checkpoint_000724224_185401344.pth new file mode 100644 index 0000000000000000000000000000000000000000..fcf1bbd42f41722a9caf63c54f0e445174464e09 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000724224_185401344.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:691d8b1fcfe7719dce2a8dffe1f75bf88224602af69b6bdb9d1ee8ec06493c90 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000738016_188932096.pth b/checkpoint_p0/milestones/checkpoint_000738016_188932096.pth new file mode 100644 index 0000000000000000000000000000000000000000..17f798e13e17fc9b3e46ec4648cda968687c9ed5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000738016_188932096.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c138b87e98c48d52441325c7cda6be6abbd59ff835473e17597c318dd8daead +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000751424_192364544.pth b/checkpoint_p0/milestones/checkpoint_000751424_192364544.pth new file mode 100644 index 0000000000000000000000000000000000000000..f48efb5d753ea3ae339dc13366857a8563c60bca --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000751424_192364544.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cf1eb488313321a0ee3d994347e9b94162253f3f6599682bfa845c65ca13caa +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000764992_195837952.pth b/checkpoint_p0/milestones/checkpoint_000764992_195837952.pth new file mode 100644 index 0000000000000000000000000000000000000000..f59ca5a24fe2bb9fbb9981905dc957eec9eeab1c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000764992_195837952.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3376983a6f15a75d32de7739be7860c8f7d1df3b628b3e1504a27ddfd3bd0a6 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000778752_199360512.pth b/checkpoint_p0/milestones/checkpoint_000778752_199360512.pth new file mode 100644 index 0000000000000000000000000000000000000000..4f532539b505879509fdd751ff10da5a4006de79 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000778752_199360512.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bbeb495f878d556b8e3a4c27206e86630f537d2ffc49d1900fb0c6b17f4ed2a +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000792512_202883072.pth b/checkpoint_p0/milestones/checkpoint_000792512_202883072.pth new file mode 100644 index 0000000000000000000000000000000000000000..2b4d0601966aad68d1f9bfee73c95aa4e45cca4f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000792512_202883072.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30887a8a87f46b5d3881597625474e8046630e5a01ad994b7abd59af041d4014 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000806144_206372864.pth b/checkpoint_p0/milestones/checkpoint_000806144_206372864.pth new file mode 100644 index 0000000000000000000000000000000000000000..d121f2db284136f6bc43e8d8bec814c00bf817c5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000806144_206372864.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46d0b6e480a022d462c1bd2dbf668cf4d496e02afa3e98e6ca30d79c4af3b914 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000819904_209895424.pth b/checkpoint_p0/milestones/checkpoint_000819904_209895424.pth new file mode 100644 index 0000000000000000000000000000000000000000..016b9d8a2dbe5f9491f6cdbd075331ea3fbca655 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000819904_209895424.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4e420d306f101c9f56cd113491b6b2dec0bdd5cb8244b4810088b8407682fd9 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000833664_213417984.pth b/checkpoint_p0/milestones/checkpoint_000833664_213417984.pth new file mode 100644 index 0000000000000000000000000000000000000000..f50a3fb4bc94f4c54da7bf333bcf1d5a17a8d1a7 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000833664_213417984.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57f64f059b82c55d6c35ee149860c4639d009b80d6f7d09b6cc8be1b0fe652c2 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000847424_216940544.pth b/checkpoint_p0/milestones/checkpoint_000847424_216940544.pth new file mode 100644 index 0000000000000000000000000000000000000000..ef24405f2a4a9debee67676ed5c34137186f3c8c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000847424_216940544.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9bc6022f4e7c477ef0bab238ea6db475fb55a1cf38209b333384f4f28e56b90 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000861152_220454912.pth b/checkpoint_p0/milestones/checkpoint_000861152_220454912.pth new file mode 100644 index 0000000000000000000000000000000000000000..ad830d8be44f68a16e0ff6fcb26d1ee8bbb87e8c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000861152_220454912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8eee575f1d137ce2a05b73d1989ef3abaa3530136c5a705a16508bb005f400cd +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000874912_223977472.pth b/checkpoint_p0/milestones/checkpoint_000874912_223977472.pth new file mode 100644 index 0000000000000000000000000000000000000000..0f9c823f0cd4bbe9444f004b6c88d8b948801321 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000874912_223977472.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d489eb5ecb3aad1b9e3a582ce87e814c0b709fdc8946c7043f14887a115ac84 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000888672_227500032.pth b/checkpoint_p0/milestones/checkpoint_000888672_227500032.pth new file mode 100644 index 0000000000000000000000000000000000000000..5a2e4c5ba2e5dd2d8480971d0cc58c3bc346573d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000888672_227500032.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73fff2a3d8b08cf9c6b59512128640c20226495933bf954324cf9f9de19829bc +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000902432_231022592.pth b/checkpoint_p0/milestones/checkpoint_000902432_231022592.pth new file mode 100644 index 0000000000000000000000000000000000000000..aaa658beb441f82d7c05133c6e62a18572800516 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000902432_231022592.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58f7b8959f538409e64c89e903572bccc08235da8d909af9dea633ee2cc1ee50 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000916224_234553344.pth b/checkpoint_p0/milestones/checkpoint_000916224_234553344.pth new file mode 100644 index 0000000000000000000000000000000000000000..0dba21fdcc50793010a89c8140cbaeb55225c4b2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000916224_234553344.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76edb3e4826bffcfa110f9145b9fa3ada964377936111f6d64c3c54a71b8fefd +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000930080_238100480.pth b/checkpoint_p0/milestones/checkpoint_000930080_238100480.pth new file mode 100644 index 0000000000000000000000000000000000000000..f101b7d206113b850e4a154f81d4af62c36e329a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000930080_238100480.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb4a4c2cb9467690414f8ed52127e37b88857212ec89e22059dace386a03bdfb +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000943904_241639424.pth b/checkpoint_p0/milestones/checkpoint_000943904_241639424.pth new file mode 100644 index 0000000000000000000000000000000000000000..a88e96d3e02b5c6051487c5fc8ea810a11d11a8e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000943904_241639424.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:289e22528e114b1f247661664a9d8246443125b2331f258f7d904f8057162275 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000957664_245161984.pth b/checkpoint_p0/milestones/checkpoint_000957664_245161984.pth new file mode 100644 index 0000000000000000000000000000000000000000..74e074d27e34761e57d0b179e6fd59e7c0764466 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000957664_245161984.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9baab490ef230386e3f0f55142ad4d3db013c8f207bc6231c5a0dc33b2aa4b8e +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000971488_248700928.pth b/checkpoint_p0/milestones/checkpoint_000971488_248700928.pth new file mode 100644 index 0000000000000000000000000000000000000000..fe7cdb64fb4de0ad23beb6b0c4602daaa4261e5f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000971488_248700928.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3065751341474657ad2207f9246c5c2776610ce6100b992494e4da399c39e60f +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000985248_252223488.pth b/checkpoint_p0/milestones/checkpoint_000985248_252223488.pth new file mode 100644 index 0000000000000000000000000000000000000000..5823ddaec25e018283063d036d011821578d6455 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000985248_252223488.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb666e1c6f13f80c014af364a00d91727044a0d7ae6276ce0e7a83e4741b086a +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000999040_255754240.pth b/checkpoint_p0/milestones/checkpoint_000999040_255754240.pth new file mode 100644 index 0000000000000000000000000000000000000000..70b243bc5fe4a6aa9099f9afff35c9535bf08886 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000999040_255754240.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2939b8839ec372ef5595ae1b70867beef62d858b1b471ebc346e6b224cc8566e +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001012832_259284992.pth b/checkpoint_p0/milestones/checkpoint_001012832_259284992.pth new file mode 100644 index 0000000000000000000000000000000000000000..ee7ee5c57b6875595f4c21877c5980b8a354c3ad --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001012832_259284992.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f31349620dd6ddd50f0f12b5c082b655a81a41f4b71486f88581ad5af606bf48 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001026592_262807552.pth b/checkpoint_p0/milestones/checkpoint_001026592_262807552.pth new file mode 100644 index 0000000000000000000000000000000000000000..64835be7123976b21332806a6b6d24779e760c2f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001026592_262807552.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1458e943e134308de7ef71e979925aeda2f114ebe2c9fc5d1c2f11329084a30c +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001040384_266338304.pth b/checkpoint_p0/milestones/checkpoint_001040384_266338304.pth new file mode 100644 index 0000000000000000000000000000000000000000..04ed67a03672668b290a42e0353bfb2bdd1d454d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001040384_266338304.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8aafc7aa9649f91af75dca2af660a35715c93eda2fa5bae525ce0faddf92009 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001054112_269852672.pth b/checkpoint_p0/milestones/checkpoint_001054112_269852672.pth new file mode 100644 index 0000000000000000000000000000000000000000..139315b22a86e597ca2ba17f416ccb86c635e575 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001054112_269852672.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15efc0bc63666a8be1875816cfd97ba13fd13670382cb29aea62859f59cd847d +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001067904_273383424.pth b/checkpoint_p0/milestones/checkpoint_001067904_273383424.pth new file mode 100644 index 0000000000000000000000000000000000000000..44b24258d018b38ab6ca6e41c608e877eb130859 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001067904_273383424.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f51e218b495feea2908a60d362c491f23623fccb4e11fbcc8beec1624979b847 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001081664_276905984.pth b/checkpoint_p0/milestones/checkpoint_001081664_276905984.pth new file mode 100644 index 0000000000000000000000000000000000000000..f49491281386c0d2ad533ea4c9c20979e48b56c1 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001081664_276905984.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a49d7485ff403112521861f615438b836d3129a97e40f282114f6bbeb24cca9 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001095456_280436736.pth b/checkpoint_p0/milestones/checkpoint_001095456_280436736.pth new file mode 100644 index 0000000000000000000000000000000000000000..fbe6c7a4d441e6d0945d3d7894da31cb4c101310 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001095456_280436736.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c9207e27dac91c362fbf3870ec830a47e2fcb98d7b4412ea50eafc4532bfd62 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001109216_283959296.pth b/checkpoint_p0/milestones/checkpoint_001109216_283959296.pth new file mode 100644 index 0000000000000000000000000000000000000000..e4c64b3da29d02222bc8b2c83255e5de69464ca4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001109216_283959296.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4af17f063d5893a4c319988051289be82cefb289ee71a85fb6b1a8667f8538ba +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001122784_287432704.pth b/checkpoint_p0/milestones/checkpoint_001122784_287432704.pth new file mode 100644 index 0000000000000000000000000000000000000000..169a427e23b160d784bfbfdca331c9977369c130 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001122784_287432704.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1faf6ef0438a4fd32043856d769c00c5a71721cb006dd8d7869c2072ff77861b +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001136512_290947072.pth b/checkpoint_p0/milestones/checkpoint_001136512_290947072.pth new file mode 100644 index 0000000000000000000000000000000000000000..5ecca2ceda6416b1bfa5e107e2d1d83ba230d7ec --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001136512_290947072.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14619ebad42c3587ee195de6beeac29d1a4edaa324018aebc8a7349d7f89e948 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001150304_294477824.pth b/checkpoint_p0/milestones/checkpoint_001150304_294477824.pth new file mode 100644 index 0000000000000000000000000000000000000000..0a1bedcb40d81f32d2c5b1097b645ad5fa69e642 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001150304_294477824.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5654b5eef364f84ad660995445492508b3c196314658ce04cd5f4bf5dbb585f8 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001164096_298008576.pth b/checkpoint_p0/milestones/checkpoint_001164096_298008576.pth new file mode 100644 index 0000000000000000000000000000000000000000..3cb474156b3a66aa56db4aada57a21e7abdcc96a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001164096_298008576.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a04daeab56788cd439933c23efd7bc5f148561e780cb1aec631fdf83ed1e0ef +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001177856_301531136.pth b/checkpoint_p0/milestones/checkpoint_001177856_301531136.pth new file mode 100644 index 0000000000000000000000000000000000000000..2a8b771c9d1d7d8c4dff75dd7deaf496c7d517d3 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001177856_301531136.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1aadea6a8e3a4073f393f0df7fa860a227869d0e39897679c119398587fa5497 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001191648_305061888.pth b/checkpoint_p0/milestones/checkpoint_001191648_305061888.pth new file mode 100644 index 0000000000000000000000000000000000000000..145773591aa8a0ca84efa3af864a05a5958cf195 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001191648_305061888.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4347952bc43e8b762ce76c1802303a520ed77604ce980bdd782bc0ebbefb1b9c +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001205408_308584448.pth b/checkpoint_p0/milestones/checkpoint_001205408_308584448.pth new file mode 100644 index 0000000000000000000000000000000000000000..41beacdd9c2cff571e20d8b86e46e5f2756e9671 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001205408_308584448.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f6b3f65925e8480ec0b74b5b8bc38e306250dc5bec15588be4707529bd853f1 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001219200_312115200.pth b/checkpoint_p0/milestones/checkpoint_001219200_312115200.pth new file mode 100644 index 0000000000000000000000000000000000000000..5a645925149b2fe828460b1d927743242e0a11ff --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001219200_312115200.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11117fe0782b2d0fbb3f1e54acf728c191b09cbe5825e6d5c092c113eb28b365 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001232928_315629568.pth b/checkpoint_p0/milestones/checkpoint_001232928_315629568.pth new file mode 100644 index 0000000000000000000000000000000000000000..3f16395581630ca0a18167e474434a2e8718deed --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001232928_315629568.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bec20689068f61f7fd2f42cebadc49390db781cd1b33c43bf5bbf54f2b8db20 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001246720_319160320.pth b/checkpoint_p0/milestones/checkpoint_001246720_319160320.pth new file mode 100644 index 0000000000000000000000000000000000000000..3d3dbc1616d0c3557b024832ef98e70c98f7643f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001246720_319160320.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ae4df3196d7e9c231a21ac3d9709a0800f04ba017960d76f68bc4f82e24b339 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001260512_322691072.pth b/checkpoint_p0/milestones/checkpoint_001260512_322691072.pth new file mode 100644 index 0000000000000000000000000000000000000000..e17d9f7dd244c6e057e9b6804f37b0a77e156942 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001260512_322691072.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a6eb5a0cff5518e0dfc8f97d63778daccd0ab739c7bf33b3263a863317149c2 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001274272_326213632.pth b/checkpoint_p0/milestones/checkpoint_001274272_326213632.pth new file mode 100644 index 0000000000000000000000000000000000000000..f01c8642f1d64691453552e8f2a47fbf30e14be5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001274272_326213632.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:116ad0deeab8bd1149bddcbd33a45954c9cc58c39af5849c98ef4d3b64646e04 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001288096_329752576.pth b/checkpoint_p0/milestones/checkpoint_001288096_329752576.pth new file mode 100644 index 0000000000000000000000000000000000000000..c3de340ff5317d95c191999cce431d751784534f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001288096_329752576.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee5fa5b10f4902069bf3a3663098f15e3ca057a5152c693e3d7dabf212eb9814 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001301952_333299712.pth b/checkpoint_p0/milestones/checkpoint_001301952_333299712.pth new file mode 100644 index 0000000000000000000000000000000000000000..d7caa5202e18858cb31374ce2f73623fc64169d9 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001301952_333299712.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bae8a10deca11361746227400d626a54bdca060be2b30c1c805363cabdc1fd5 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001315712_336822272.pth b/checkpoint_p0/milestones/checkpoint_001315712_336822272.pth new file mode 100644 index 0000000000000000000000000000000000000000..600bf39bbb3d63fcb28410bb78373b40df426868 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001315712_336822272.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a939187e33c99164ab08eb8acc086a71f5876dc3e5a663bee1190c8cc76324e0 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001329504_340353024.pth b/checkpoint_p0/milestones/checkpoint_001329504_340353024.pth new file mode 100644 index 0000000000000000000000000000000000000000..72f4473976a790816b9553f4befefb4c65133d03 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001329504_340353024.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a444ebb2ca66978bd9c84d3126b3eae0736fd59dc638d33f73e9ea4154e5556f +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001343360_343900160.pth b/checkpoint_p0/milestones/checkpoint_001343360_343900160.pth new file mode 100644 index 0000000000000000000000000000000000000000..b46e90194e2748744982e028c5821dcaa4d3a72a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001343360_343900160.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edbb1efb4796a42bfa26b43c82ca74e061e9f0cb5213b9e707e09c7220769e60 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001357152_347430912.pth b/checkpoint_p0/milestones/checkpoint_001357152_347430912.pth new file mode 100644 index 0000000000000000000000000000000000000000..b7cd5a32ffea6dd8d387bd90218ff6af97e1ad4a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001357152_347430912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa16445c7dffae0f4a6ab35ccdaddd9c84af87f8c8a7a05bf26bd0b412694732 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001370912_350953472.pth b/checkpoint_p0/milestones/checkpoint_001370912_350953472.pth new file mode 100644 index 0000000000000000000000000000000000000000..342aa77d0ae5851add87251810f7ea9fbed9e0f9 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001370912_350953472.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07f13f97c0c91030313fe3e40b04cf5a808e469ac332d3ad7e04cd13a45ab60d +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001384672_354476032.pth b/checkpoint_p0/milestones/checkpoint_001384672_354476032.pth new file mode 100644 index 0000000000000000000000000000000000000000..f8154dd45f511f265158f10623d9608f62feb8bd --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001384672_354476032.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d07fb98e21ec7b1e81a32e22996d8c04f633102f5a458bc10627e995bfcd1ab0 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001398496_358014976.pth b/checkpoint_p0/milestones/checkpoint_001398496_358014976.pth new file mode 100644 index 0000000000000000000000000000000000000000..8d65bdd7345e5f5b482791908f64d1bec9e3f26e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001398496_358014976.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e6189933f80eaf7299c11b409fd724e57a0275c38082091ebf3401a19bcfe71 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001412320_361553920.pth b/checkpoint_p0/milestones/checkpoint_001412320_361553920.pth new file mode 100644 index 0000000000000000000000000000000000000000..305722bab623a7698ab38f9451cbc5de5e6d0c9d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001412320_361553920.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0746121192e39814a50da4316e0b06ef4ba9ddd80c41b8324419af01890d8129 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001426112_365084672.pth b/checkpoint_p0/milestones/checkpoint_001426112_365084672.pth new file mode 100644 index 0000000000000000000000000000000000000000..42c3229d278b9f35204bc4ae863ec837bf5ff865 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001426112_365084672.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b061f7b1b2222c7126b0d5b686167949afb88197885f77c367651fb9b71c0e8 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001439872_368607232.pth b/checkpoint_p0/milestones/checkpoint_001439872_368607232.pth new file mode 100644 index 0000000000000000000000000000000000000000..3450a09377d9e918f3cfba74e238d9b5eb401b47 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001439872_368607232.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c998a98299fa8d82160d7c9a546bfb8caaebaf6bd05793b83c6a95290a1c01b +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001453696_372146176.pth b/checkpoint_p0/milestones/checkpoint_001453696_372146176.pth new file mode 100644 index 0000000000000000000000000000000000000000..d5d7be1a34f7642ccdaed564c2e53f1a8b445c83 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001453696_372146176.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f447c7267c08780d95b2fcbb40fc9623014021dddd9426e6219366eef2404d4 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001467488_375676928.pth b/checkpoint_p0/milestones/checkpoint_001467488_375676928.pth new file mode 100644 index 0000000000000000000000000000000000000000..cfdc3981c193754169ba7b8e25890f3b6423cc0f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001467488_375676928.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:861f53d63479b1a079d7e67cbbae543a10a43f98c6ca177eddaf424ff9eaa589 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001481280_379207680.pth b/checkpoint_p0/milestones/checkpoint_001481280_379207680.pth new file mode 100644 index 0000000000000000000000000000000000000000..825fcfef605354279e58b604595afe1f25fc630d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001481280_379207680.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8a0f468ee9518bfa1c1aaab10b669d2d0bde90e48aaafaadc0893bd070f6c2b +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001495104_382746624.pth b/checkpoint_p0/milestones/checkpoint_001495104_382746624.pth new file mode 100644 index 0000000000000000000000000000000000000000..eae3e0bb3c3b2891c961793774cf705c0622af78 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001495104_382746624.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb8d1ae7b3ede928faf3dc61e9e4702811b9b13b0a0e9988815d69993bfd2223 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001508960_386293760.pth b/checkpoint_p0/milestones/checkpoint_001508960_386293760.pth new file mode 100644 index 0000000000000000000000000000000000000000..1d26f1392bc3a3aace2fb18c6473246023062be4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001508960_386293760.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2612aec3400bbe7339e731d1272cd92fbf0aa6740457f5ecb99b9bde671b3139 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001522784_389832704.pth b/checkpoint_p0/milestones/checkpoint_001522784_389832704.pth new file mode 100644 index 0000000000000000000000000000000000000000..3a967698799e421835af3f542f51f68349d4fe23 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001522784_389832704.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bfaacff564edd219ae619b74436da899317ddf8a03aa7bad710c53f1dc985ae +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001536640_393379840.pth b/checkpoint_p0/milestones/checkpoint_001536640_393379840.pth new file mode 100644 index 0000000000000000000000000000000000000000..cb744f20971c2516b52fa782fbb0ed93693a5201 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001536640_393379840.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:443f843e8c11c4fb67cc2806d0c24925f7f43ca27337c8b14f8c74e0f42541d7 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001550432_396910592.pth b/checkpoint_p0/milestones/checkpoint_001550432_396910592.pth new file mode 100644 index 0000000000000000000000000000000000000000..5f797b5c9de440a245a79d1d348e57ef351c75d2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001550432_396910592.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6485d9dacc3db7db7647171adac165c21618f0044ee278538d3865aeda026d55 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001564288_400457728.pth b/checkpoint_p0/milestones/checkpoint_001564288_400457728.pth new file mode 100644 index 0000000000000000000000000000000000000000..8bc28f12b1a760a8ef1cb41757531c4fc90a5ddf --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001564288_400457728.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74d1ad7609d0412530e35df8f46c1a6e0f7259e417073455d38e9632ffbca34b +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001578144_404004864.pth b/checkpoint_p0/milestones/checkpoint_001578144_404004864.pth new file mode 100644 index 0000000000000000000000000000000000000000..308cffdbfbad68072b549edc15e3dd41cf002688 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001578144_404004864.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0b33c62906d6c93574e42641efdf43113c4e2415af44f0ca7d43700debdd513 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001591936_407535616.pth b/checkpoint_p0/milestones/checkpoint_001591936_407535616.pth new file mode 100644 index 0000000000000000000000000000000000000000..11e82860dcba932763f2087f91da5f98c93684ff --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001591936_407535616.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc005000f456bae04d116977db39401db0b6eeec71b6e54a927d81b10bf83cbb +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001605760_411074560.pth b/checkpoint_p0/milestones/checkpoint_001605760_411074560.pth new file mode 100644 index 0000000000000000000000000000000000000000..4c2cab1241efdc424bd17f94fb0e31d4d0071b0f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001605760_411074560.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e91354fc8f90c2c1c7f9961fa9d0668576e7042e1ad42798fa454343e690c0a +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001619552_414605312.pth b/checkpoint_p0/milestones/checkpoint_001619552_414605312.pth new file mode 100644 index 0000000000000000000000000000000000000000..451fb6cee09b5f23d8e4949fc2ccdd3761aa92b9 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001619552_414605312.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72a09a5df89a3f37daea0df8f66cd1c8d617a937dcc01d2a1d972049985f6d8c +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001633344_418136064.pth b/checkpoint_p0/milestones/checkpoint_001633344_418136064.pth new file mode 100644 index 0000000000000000000000000000000000000000..3545b85e6c4613155b0049745bbbd2eace76a9c5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001633344_418136064.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:433d9b58914e50a8619921f50bc7330faebcd1903cf6b81a4cb2ed296521c5f1 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001647232_421691392.pth b/checkpoint_p0/milestones/checkpoint_001647232_421691392.pth new file mode 100644 index 0000000000000000000000000000000000000000..888a2ee5c7f54441a0031462526821b7c5c68798 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001647232_421691392.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c649467dc63743e4603bf0aa3b6ea98e407db648417b4f72e5bb5b0ce58995b9 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001661056_425230336.pth b/checkpoint_p0/milestones/checkpoint_001661056_425230336.pth new file mode 100644 index 0000000000000000000000000000000000000000..45921033f14160806a6bbd624c04abadd238d979 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001661056_425230336.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3281cfacf66cb27f193483efc1bde80fa64e101541d522ff854c5f045c31b9d1 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001674880_428769280.pth b/checkpoint_p0/milestones/checkpoint_001674880_428769280.pth new file mode 100644 index 0000000000000000000000000000000000000000..b9cb04b984971480f54a00843ad0f0beea6c489c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001674880_428769280.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0512146b186eba3441ea68caf5d78bc56adb718b0375549feee8045b901592d2 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001688640_432291840.pth b/checkpoint_p0/milestones/checkpoint_001688640_432291840.pth new file mode 100644 index 0000000000000000000000000000000000000000..2e96f1cf57ee621fe1735c14276b5ce20774a1d8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001688640_432291840.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ffdac4f77969d7053e63b8e5ed02965586e5560bc99674f5e295f690848d926 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001702432_435822592.pth b/checkpoint_p0/milestones/checkpoint_001702432_435822592.pth new file mode 100644 index 0000000000000000000000000000000000000000..ca96b76f921f3901d02fd9d16a9c94d5c6deec63 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001702432_435822592.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8a0763fb0979393f89fd64f97705af616fc05af706a00854dc53fdab8284b1b +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001716256_439361536.pth b/checkpoint_p0/milestones/checkpoint_001716256_439361536.pth new file mode 100644 index 0000000000000000000000000000000000000000..abe948a64d98329e21309ca964b3bcc90989daed --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001716256_439361536.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:335edfff0a0858b0cf806b1509b4953540ec9944c62e384e4246dec61b5a020e +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001730080_442900480.pth b/checkpoint_p0/milestones/checkpoint_001730080_442900480.pth new file mode 100644 index 0000000000000000000000000000000000000000..7474a05099ef0750449e72ba7d8e39ab5d4d6937 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001730080_442900480.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4001ff51eb285fa0d05368531f91ec60934ffd28ca92814afec90b1c343c1550 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001743552_446349312.pth b/checkpoint_p0/milestones/checkpoint_001743552_446349312.pth new file mode 100644 index 0000000000000000000000000000000000000000..71d99cc4a10e7378ccf47ae068ee18e959779f29 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001743552_446349312.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34a64358fc15bcc80f7c29a84de98e41921bba45ab9cdf9352c3e95015c33e6d +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001757216_449847296.pth b/checkpoint_p0/milestones/checkpoint_001757216_449847296.pth new file mode 100644 index 0000000000000000000000000000000000000000..2f93743d669fa74f2bb404b9024af161488ec66d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001757216_449847296.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ec7d584ecce13428e803ccec85b4603a2d5939353935d372f5d1e782f068ed9 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001771008_453378048.pth b/checkpoint_p0/milestones/checkpoint_001771008_453378048.pth new file mode 100644 index 0000000000000000000000000000000000000000..a37e3d15c83a700e4b479afdcdceb2354a833ae5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001771008_453378048.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7b6c7a7c24db0cdd1861c82f2c8c861ca455398e1d3ecd7e723a67ca7f41109 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001784832_456916992.pth b/checkpoint_p0/milestones/checkpoint_001784832_456916992.pth new file mode 100644 index 0000000000000000000000000000000000000000..cb7bef83734eb3484c2ae8864cd9b90294987234 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001784832_456916992.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84c0f5744729afd831e0c390d740e4b5f4efd182c65ea0ecdd2b6a16a13b9e86 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001798624_460447744.pth b/checkpoint_p0/milestones/checkpoint_001798624_460447744.pth new file mode 100644 index 0000000000000000000000000000000000000000..04483fc4d834b9710744f95d299c7fa1b45bc88e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001798624_460447744.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffe3d2f8e10dde0e184692b96d712e16f1b87dd13fede4402ad11f07decbe6bd +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001812480_463994880.pth b/checkpoint_p0/milestones/checkpoint_001812480_463994880.pth new file mode 100644 index 0000000000000000000000000000000000000000..17f2667c07f5b10a0b45de9be91b05613dc52563 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001812480_463994880.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dd57b9cd3274b2fe1c29ea57120c6457032c607a76800db234ffa82d58fd7fc +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001826240_467517440.pth b/checkpoint_p0/milestones/checkpoint_001826240_467517440.pth new file mode 100644 index 0000000000000000000000000000000000000000..7b9639df12bfaa92ed356b157aabb1d62055a592 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001826240_467517440.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebc61453b78697da11ebbd1c3631a9f4f2f3d1d2e90c31acf7e587ff07bf0454 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001840128_471072768.pth b/checkpoint_p0/milestones/checkpoint_001840128_471072768.pth new file mode 100644 index 0000000000000000000000000000000000000000..1ae5118faf47d3e61ae975c733fb8c26ca0ac9eb --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001840128_471072768.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:161c3891793555ad7848595dd94ba92985a9310284ad2f4c4b1b52d8f74a3df3 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001854016_474628096.pth b/checkpoint_p0/milestones/checkpoint_001854016_474628096.pth new file mode 100644 index 0000000000000000000000000000000000000000..00a9c6573ae1b091b20fcd2c5fa6c93022252f7f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001854016_474628096.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43cbf4e954ee3c3fa68c9d06fb6fe65626bef4772e8a084170a2ea6d5ab1d5d6 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001867808_478158848.pth b/checkpoint_p0/milestones/checkpoint_001867808_478158848.pth new file mode 100644 index 0000000000000000000000000000000000000000..b58c3681f1f6f9aa2ebd434f771aaf5959d8e52f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001867808_478158848.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5269fded347b76adf6d95c91be86b8bb5ff5f0377058ffe7f851228c921c1fd4 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001881568_481681408.pth b/checkpoint_p0/milestones/checkpoint_001881568_481681408.pth new file mode 100644 index 0000000000000000000000000000000000000000..78839eb2876600e4174a3a2230fb1c84460824f4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001881568_481681408.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b7ca5a71268f080e436d59f313820b9e5e1080603f7bff3dcdc2492d182a63f +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001895392_485220352.pth b/checkpoint_p0/milestones/checkpoint_001895392_485220352.pth new file mode 100644 index 0000000000000000000000000000000000000000..617196a6e25a264280e9104867a9831cfb0e080b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001895392_485220352.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b355cff02177060b7cb28ebb68e1fcdfd52a64845af5fac8c8a36c4e5bd9f998 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001909120_488734720.pth b/checkpoint_p0/milestones/checkpoint_001909120_488734720.pth new file mode 100644 index 0000000000000000000000000000000000000000..6a9bc1a8e77273c2791cb016b3ecaa23bfb748fc --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001909120_488734720.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2fdfe08f54d603a2a27f332c9bef7924dca69ec641fc637c6d69dc06a58bde8 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001922944_492273664.pth b/checkpoint_p0/milestones/checkpoint_001922944_492273664.pth new file mode 100644 index 0000000000000000000000000000000000000000..a8f37221621a436a561f3c738e363ba52f96281d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001922944_492273664.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7ab32352dd7b5585287a672213de39a13fe54803fcdb6c775b7a52f6e9a7e53 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001936768_495812608.pth b/checkpoint_p0/milestones/checkpoint_001936768_495812608.pth new file mode 100644 index 0000000000000000000000000000000000000000..55499367134e07334df7bc14d2701411dc16e075 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001936768_495812608.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed8b61d514980bda136d5a0838d78157cfe481a51831a16db2e2e9e8025a5ada +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001950592_499351552.pth b/checkpoint_p0/milestones/checkpoint_001950592_499351552.pth new file mode 100644 index 0000000000000000000000000000000000000000..07ef8a070c2dcc32a75634661c5ed8f8434ee081 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001950592_499351552.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e35d1742eb54c286835cebad7b75965c87c6ffe45f57b752ddaf4f949966081c +size 20747723 diff --git a/checkpoint_p1/best_001905440_487792640_reward_97.190.pth b/checkpoint_p1/best_001905440_487792640_reward_97.190.pth new file mode 100644 index 0000000000000000000000000000000000000000..baec6dbb5b72a7846a65c91a64e8fc1a51d0c4bc --- /dev/null +++ b/checkpoint_p1/best_001905440_487792640_reward_97.190.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dd003b810e5d9552f31a80081a52ac4c4835805022a3d4752dbfbd3824d0f0e +size 20746419 diff --git a/checkpoint_p1/checkpoint_001957568_502284288.pth b/checkpoint_p1/checkpoint_001957568_502284288.pth new file mode 100644 index 0000000000000000000000000000000000000000..da9e7e9424069f12b3ce81ca7ebc15609750c759 --- /dev/null +++ b/checkpoint_p1/checkpoint_001957568_502284288.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3b4fbca780389c42890675c827aca36ef8a09d2d880dcfee34cdbaf7702fd0f +size 20746755 diff --git a/checkpoint_p1/checkpoint_001958224_502620160.pth b/checkpoint_p1/checkpoint_001958224_502620160.pth new file mode 100644 index 0000000000000000000000000000000000000000..7b6689106e7fd0f4343928f90eec063ff1a557cd --- /dev/null +++ b/checkpoint_p1/checkpoint_001958224_502620160.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32602b8409de1e1db7203a362319a9e5540c4fe5707a5319200b090ad36f253a +size 20746755 diff --git a/checkpoint_p1/milestones/checkpoint_000013376_3424256.pth b/checkpoint_p1/milestones/checkpoint_000013376_3424256.pth new file mode 100644 index 0000000000000000000000000000000000000000..8e9fc5c6f4b246b0fdeab4a27dad84fa6e2baf3a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000013376_3424256.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4206b79a61a4bbc665e2e00641a6356852f7682d8c9ea3b7c4625153f41a3347 +size 20747611 diff --git a/checkpoint_p1/milestones/checkpoint_000027072_6930432.pth b/checkpoint_p1/milestones/checkpoint_000027072_6930432.pth new file mode 100644 index 0000000000000000000000000000000000000000..298d0bb3b233386808e6c7d714e3883118b4932c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000027072_6930432.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14b340b1dbe3ee694ec4fc82781d2fb9e9aa5476989a91aab26a0b9bd500b722 +size 20747611 diff --git a/checkpoint_p1/milestones/checkpoint_000040800_10444800.pth b/checkpoint_p1/milestones/checkpoint_000040800_10444800.pth new file mode 100644 index 0000000000000000000000000000000000000000..1e3135be2d9fbe72fe98be032f10f938e9b651a6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000040800_10444800.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71d9fc94d1e3be16093dc2034218271ba7f5aff1c8b03f47015ac9f47a57b77f +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000054592_13975552.pth b/checkpoint_p1/milestones/checkpoint_000054592_13975552.pth new file mode 100644 index 0000000000000000000000000000000000000000..7913d0cf2a323607eff329c1b8f9a4ce328e6b4b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000054592_13975552.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caff6e0fee45fd25770b1745ef8204e9e9cf0dfa22762f6591f4f7006202ac08 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000068288_17481728.pth b/checkpoint_p1/milestones/checkpoint_000068288_17481728.pth new file mode 100644 index 0000000000000000000000000000000000000000..bc6ed2377e2deaf5ccbb0521b316ee8e02e91217 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000068288_17481728.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4157b9dfe3dcba9a8c3b9c69c6c937733af45e1e1bdc79b3527f9238f77b20f9 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000082016_20996096.pth b/checkpoint_p1/milestones/checkpoint_000082016_20996096.pth new file mode 100644 index 0000000000000000000000000000000000000000..918f02e80de9fcd6d43f212fbb9c8a9e6d0cad44 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000082016_20996096.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cbb99f85f5282b8ccae31de3b63e0f1b8024b298da8ce5fc5117a31fc8c816e +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000095584_24469504.pth b/checkpoint_p1/milestones/checkpoint_000095584_24469504.pth new file mode 100644 index 0000000000000000000000000000000000000000..8644d831c6839260532650af818be1d09da7ca99 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000095584_24469504.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ec8add827ba0a5c006a9178aaa098be094e2e38341bdef319230968d179326d +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000109344_27992064.pth b/checkpoint_p1/milestones/checkpoint_000109344_27992064.pth new file mode 100644 index 0000000000000000000000000000000000000000..66550515b6e7de04b68f1dc1471b72769bdd9ca1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000109344_27992064.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf52366feb68d50503cab011d92f84dad32a19878e55c788573747b58bd20e2c +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000123104_31514624.pth b/checkpoint_p1/milestones/checkpoint_000123104_31514624.pth new file mode 100644 index 0000000000000000000000000000000000000000..be30ae140088ade79b68fb3522ba5fbd5c51f922 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000123104_31514624.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccae67af4ec73f74aacb2122b89636b5d5fb13afa25eef0a4e3bd047e19e48a6 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000136896_35045376.pth b/checkpoint_p1/milestones/checkpoint_000136896_35045376.pth new file mode 100644 index 0000000000000000000000000000000000000000..aea849bc04abc082f0a8e212a81943b46b9035ae --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000136896_35045376.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47dd9476ef1a10a5386d5c476da79623f84e793cd3d7bd5971547a79f0281fbd +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000150560_38543360.pth b/checkpoint_p1/milestones/checkpoint_000150560_38543360.pth new file mode 100644 index 0000000000000000000000000000000000000000..8b1b7beddddf2dc93a35ec6c3a97db5fb64295c0 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000150560_38543360.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dee9dad58f537c2f87d7b91c973bd976d09e61a4d1d36c362577ea24ee68fcaa +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000164288_42057728.pth b/checkpoint_p1/milestones/checkpoint_000164288_42057728.pth new file mode 100644 index 0000000000000000000000000000000000000000..8d00f4b4d486f2377860c25ed81a839be7d70d5a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000164288_42057728.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddbcd58c43a8bfa45d50501c0d3ab3a29ae53d9e064875f58ae3c378ab37d9b7 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000177984_45563904.pth b/checkpoint_p1/milestones/checkpoint_000177984_45563904.pth new file mode 100644 index 0000000000000000000000000000000000000000..9fe19bfd560516a3fc6c1fdf12ef235cfd58250a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000177984_45563904.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f22f58175e0e1349557086a2c579728db83a9f9f2397fbb756977caa28db0624 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000191712_49078272.pth b/checkpoint_p1/milestones/checkpoint_000191712_49078272.pth new file mode 100644 index 0000000000000000000000000000000000000000..986ff275d864bf157a7448abe08edd2f01aea9ce --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000191712_49078272.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41d969199330f194a1bb1d98f31652e2c20ee7d95994d3f8c99b90bb1e10c0d0 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000205504_52609024.pth b/checkpoint_p1/milestones/checkpoint_000205504_52609024.pth new file mode 100644 index 0000000000000000000000000000000000000000..a2f043032d9fb1b4142995463cc1d40501473a4d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000205504_52609024.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:224c23367221c7f3988cc3126bc88e831a8198d7b30688cb5dc6b8e31e7abe06 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000219232_56123392.pth b/checkpoint_p1/milestones/checkpoint_000219232_56123392.pth new file mode 100644 index 0000000000000000000000000000000000000000..709d73b4221a46e42a76f825ae6db3a4dd1a5dcc --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000219232_56123392.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1309eebcbd8e6c438c933d88d6ae32e1df8fc66690130b6c36b220f3ed3b8610 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000232992_59645952.pth b/checkpoint_p1/milestones/checkpoint_000232992_59645952.pth new file mode 100644 index 0000000000000000000000000000000000000000..650121582dd1f197c6792f162d5dc7967f32d803 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000232992_59645952.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe6655db0f0bee9deb42eb09c2524dc3eba08ba94c56caf5125fd04ead6b8507 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000246752_63168512.pth b/checkpoint_p1/milestones/checkpoint_000246752_63168512.pth new file mode 100644 index 0000000000000000000000000000000000000000..e45c4159204757610d20d346e011771685a948b6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000246752_63168512.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f263f66a3ae21e5af6dca498f8a6c9a398f510de090d712b02ac1f814d44d0b +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000260448_66674688.pth b/checkpoint_p1/milestones/checkpoint_000260448_66674688.pth new file mode 100644 index 0000000000000000000000000000000000000000..0a2d44ee604fa44873a151cb34b176063144b6a9 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000260448_66674688.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe41c34fbddc30796b8cd486ef1dc2c1e8a37cc662cde6f9210947d1237421f0 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000274240_70205440.pth b/checkpoint_p1/milestones/checkpoint_000274240_70205440.pth new file mode 100644 index 0000000000000000000000000000000000000000..b9375aa727bab0fd9a6615582bcb8830f6a157bd --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000274240_70205440.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:205edc0f5d4c253ae319cff074d36b9e910a29d6265aae9dad1520f8d9bc401f +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000287968_73719808.pth b/checkpoint_p1/milestones/checkpoint_000287968_73719808.pth new file mode 100644 index 0000000000000000000000000000000000000000..fbe0b426dac06a62c4c80ef832a8da618e4ae09f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000287968_73719808.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24305a1c280f96f0741224935af1c06a18c0fa699f4321fe3596936e2b81c185 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000301504_77185024.pth b/checkpoint_p1/milestones/checkpoint_000301504_77185024.pth new file mode 100644 index 0000000000000000000000000000000000000000..a989f433f7324f36a1917c3deafd2cbb8431ee78 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000301504_77185024.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dc1d03552d44a0a0e9f8b040999f46cec8070a718a3ee50b1c7c708eab5349c +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000315232_80699392.pth b/checkpoint_p1/milestones/checkpoint_000315232_80699392.pth new file mode 100644 index 0000000000000000000000000000000000000000..7e2bf5907abd1708491b5bb10785b11f34872bdd --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000315232_80699392.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d060e0fc7317c012fc0d97cf72f2bda7ccdafe15cdb08ca355900ad8bb09684 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000328864_84189184.pth b/checkpoint_p1/milestones/checkpoint_000328864_84189184.pth new file mode 100644 index 0000000000000000000000000000000000000000..7ae892cc1d1ad708947a730492e45ba1de4fe6cc --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000328864_84189184.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfa9119c706d56e48776f3f619b7865967329d8249313be0332b0bc6f5270fc6 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000342528_87687168.pth b/checkpoint_p1/milestones/checkpoint_000342528_87687168.pth new file mode 100644 index 0000000000000000000000000000000000000000..9b2beb1bcd7c16df8869fd52f44eb2e600c7cb8e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000342528_87687168.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a70596bbdc2fe09da0054ba5d546274cf87a30acdcbcab6e24b1ff9a6728d664 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000356224_91193344.pth b/checkpoint_p1/milestones/checkpoint_000356224_91193344.pth new file mode 100644 index 0000000000000000000000000000000000000000..107eed4f2ffc4065c55e9cb78f0dec027f12e673 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000356224_91193344.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:801dd5ee7849cbbd86f67848ee977efed8f9355b657e695820c6b6aa041f51e2 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000369920_94699520.pth b/checkpoint_p1/milestones/checkpoint_000369920_94699520.pth new file mode 100644 index 0000000000000000000000000000000000000000..553571764da870d570659de4300016c73da2fb0b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000369920_94699520.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fc426b6414a3d03146a7822b621ab96c94205c07035bf0b2e120b96e97f4ea6 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000383648_98213888.pth b/checkpoint_p1/milestones/checkpoint_000383648_98213888.pth new file mode 100644 index 0000000000000000000000000000000000000000..21a0415d6a88d5ac03d712fd7f590503e53f3463 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000383648_98213888.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:766478e89e0c135bc7f0bf7ddc11dd431718dc3f98579843b59c3ac16c747620 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000397344_101720064.pth b/checkpoint_p1/milestones/checkpoint_000397344_101720064.pth new file mode 100644 index 0000000000000000000000000000000000000000..afa24c3018340a63b4eff5edcd51ba7f713ea7cb --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000397344_101720064.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75beb20c348a4d67dcd43026eda43b9aff0e0b0f22e760cb3c4920ae375bc168 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000411040_105226240.pth b/checkpoint_p1/milestones/checkpoint_000411040_105226240.pth new file mode 100644 index 0000000000000000000000000000000000000000..d0908f56546b3dce3e4d55fdd849b729f57fc9b3 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000411040_105226240.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:337329b51bd484d09c8e6f31e55b3615f0b554b9256fb11276a7dbbb0d833b17 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000424704_108724224.pth b/checkpoint_p1/milestones/checkpoint_000424704_108724224.pth new file mode 100644 index 0000000000000000000000000000000000000000..e84080e861b083eb4f2535ba5d4e759ce24097be --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000424704_108724224.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04d991698349b913005d5d68183b589ec652ef5553fe91d713b8ddef691064bc +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000438432_112238592.pth b/checkpoint_p1/milestones/checkpoint_000438432_112238592.pth new file mode 100644 index 0000000000000000000000000000000000000000..8740d624bec6aebc201511294dea62e2e1e12009 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000438432_112238592.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f4a4f581c6d71bee83b3ad85e70225dab4aaf74ad3d2983cca07c45e2c0ba34 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000452128_115744768.pth b/checkpoint_p1/milestones/checkpoint_000452128_115744768.pth new file mode 100644 index 0000000000000000000000000000000000000000..5ad9a6a6b463d77d7a2f2efffb206b4a17372b8c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000452128_115744768.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d42acf271060892449f0f700078be704e8dbff17fe4bdf1054a9b4f518e72710 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000465760_119234560.pth b/checkpoint_p1/milestones/checkpoint_000465760_119234560.pth new file mode 100644 index 0000000000000000000000000000000000000000..f4f4ed6a735a768ca84d40ab4af18b13e5b09229 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000465760_119234560.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d8ecfdad7d6faddeb7a4f22d4d370f6546d142197bad35d96b5c06bf71c9eb9 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000479424_122732544.pth b/checkpoint_p1/milestones/checkpoint_000479424_122732544.pth new file mode 100644 index 0000000000000000000000000000000000000000..487e8eb3df68259f1a1a5214e8f599dd56674ab8 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000479424_122732544.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae40ecd6514d00302cf59296699b0657b6359d5373fe4289089ba17a12ca810a +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000493152_126246912.pth b/checkpoint_p1/milestones/checkpoint_000493152_126246912.pth new file mode 100644 index 0000000000000000000000000000000000000000..d84fba5129a90492943ce305667eaa1f506ef62f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000493152_126246912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c54df7245c2164eeaf26db7caa46c05794e36f976ad1223aac8cae1051eb5f83 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000506848_129753088.pth b/checkpoint_p1/milestones/checkpoint_000506848_129753088.pth new file mode 100644 index 0000000000000000000000000000000000000000..3017d4a015752d4c7397373343bd62344269ad95 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000506848_129753088.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0aacbb583b496b06754e9534d0c9ced47643ce549a205ae7087b9c18332674f +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000520544_133259264.pth b/checkpoint_p1/milestones/checkpoint_000520544_133259264.pth new file mode 100644 index 0000000000000000000000000000000000000000..85bd3b0350c0e7e4a222cba6290b14f6d74b8578 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000520544_133259264.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d8612637d4572e48126d0342dc316e8f091a31d11be77c8866a8775ab2f7d57 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000534208_136757248.pth b/checkpoint_p1/milestones/checkpoint_000534208_136757248.pth new file mode 100644 index 0000000000000000000000000000000000000000..83bac5b15a2a4bb7cf7d80b5115f33db06a64c36 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000534208_136757248.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38199c967e73bfff6c81281b46b3d4d9b0ba11411d9b3ed9df5c143dd15f95b7 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000547968_140279808.pth b/checkpoint_p1/milestones/checkpoint_000547968_140279808.pth new file mode 100644 index 0000000000000000000000000000000000000000..7f0af096fa9e71d5696f62e577667580ae27bfe6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000547968_140279808.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:549493695d099f3ce459cd5a7627c4b323673e594b94d32467e1ddcd93e4bd94 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000561792_143818752.pth b/checkpoint_p1/milestones/checkpoint_000561792_143818752.pth new file mode 100644 index 0000000000000000000000000000000000000000..2f905dfdf03b14e447fffad262b7fcbd389b235c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000561792_143818752.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1818f204692792043f195a0ab4b7d3d56e7c192493092ee74a5d8c5726740641 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000575552_147341312.pth b/checkpoint_p1/milestones/checkpoint_000575552_147341312.pth new file mode 100644 index 0000000000000000000000000000000000000000..d61edfc5badb8bd9cf0ed9c70cf51d28112b37be --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000575552_147341312.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:431cdc15cf6447adc161a5742aa7869b8a7e40d202d32db9498a43944066cbac +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000589408_150888448.pth b/checkpoint_p1/milestones/checkpoint_000589408_150888448.pth new file mode 100644 index 0000000000000000000000000000000000000000..70f23ffee2634c31eb610ac914ec37355194517e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000589408_150888448.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c7d0c74b84f11d67831ba73ee466cc64af23dcb6c4d637819af4f122a3a5fa8 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000603232_154427392.pth b/checkpoint_p1/milestones/checkpoint_000603232_154427392.pth new file mode 100644 index 0000000000000000000000000000000000000000..ff6bb3fa65307f5b86f1581022c04fafaf5c961b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000603232_154427392.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f68b6cb381a4e3027d3e52bd168eec0ffd9132fd5fde7cad24d168b092b1b009 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000617056_157966336.pth b/checkpoint_p1/milestones/checkpoint_000617056_157966336.pth new file mode 100644 index 0000000000000000000000000000000000000000..5c4ee5f0c70113d9e709bfd794591dd7934b1298 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000617056_157966336.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2059d5b6054f5192d4ff5058a5515b7b9602bb7bb7cc50c8f51cd4e9967eded +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000630848_161497088.pth b/checkpoint_p1/milestones/checkpoint_000630848_161497088.pth new file mode 100644 index 0000000000000000000000000000000000000000..4746f290920394b2547dc0c7ea5d9bd648ede427 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000630848_161497088.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f35895ad366b4ab28bf2c7929cc47426caf8810f004abfadd83ef3261bd2332 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000644768_165060608.pth b/checkpoint_p1/milestones/checkpoint_000644768_165060608.pth new file mode 100644 index 0000000000000000000000000000000000000000..096e36ce35e530ff19431bb39f3ecd9b1dc1c5f7 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000644768_165060608.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa75c1896f87cce0f1da04ec5a94caf994a4221955e20c12e7d6e08516263d6e +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000658592_168599552.pth b/checkpoint_p1/milestones/checkpoint_000658592_168599552.pth new file mode 100644 index 0000000000000000000000000000000000000000..85d96a5cdb1e01fe38ca47771c334d3b3b83627c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000658592_168599552.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5350b8e9d8467c639490c23a5c00989ae165ddecc9d81fa8be307cbc00647ec +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000672384_172130304.pth b/checkpoint_p1/milestones/checkpoint_000672384_172130304.pth new file mode 100644 index 0000000000000000000000000000000000000000..134fedc7dc408905b0dfc471d20636adf2733374 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000672384_172130304.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff595c70c7f9dd52225af8adb9246e34cc1e88225a50e59d1fd8743e08fd53bf +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000686176_175661056.pth b/checkpoint_p1/milestones/checkpoint_000686176_175661056.pth new file mode 100644 index 0000000000000000000000000000000000000000..cd4ad649d91f63461b7c0d652fa9f71c8ac0d955 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000686176_175661056.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1eb0c6b172c9ded50490c819d8cf87f473bb3d7aef6b02debe4519ba833e84b0 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000700000_179200000.pth b/checkpoint_p1/milestones/checkpoint_000700000_179200000.pth new file mode 100644 index 0000000000000000000000000000000000000000..ad1b5063f80e80b6d127bc2c00ea5a60587496df --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000700000_179200000.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4da9cc182ba8ba52808d82623d3933742dded41bd4f07e4a956eae1f557bfb25 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000713888_182755328.pth b/checkpoint_p1/milestones/checkpoint_000713888_182755328.pth new file mode 100644 index 0000000000000000000000000000000000000000..8266ba5efe9b745ee362f36156e765987c3da92d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000713888_182755328.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69a5038edb5fb0f916abba0b2a848a2cd35512b6a0ad9dc5111f7d7e87c612fa +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000727744_186302464.pth b/checkpoint_p1/milestones/checkpoint_000727744_186302464.pth new file mode 100644 index 0000000000000000000000000000000000000000..3499f7f94997bf866f235b889a00b0fff9e5d559 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000727744_186302464.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0007ca3a97182af579af0fa937f52b1afabbe90d73c437186f304d257bfcf0ef +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000741568_189841408.pth b/checkpoint_p1/milestones/checkpoint_000741568_189841408.pth new file mode 100644 index 0000000000000000000000000000000000000000..e84d03ceff9e13b5f50c41154f4c4461f1c09501 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000741568_189841408.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23bae5106bb8979df88a8c50acdd0b1e1f480b9228090fdffee23476a5a040dd +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000755040_193290240.pth b/checkpoint_p1/milestones/checkpoint_000755040_193290240.pth new file mode 100644 index 0000000000000000000000000000000000000000..d88d512038e6c81986bc5d0849cd6d9a7ad02897 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000755040_193290240.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aceb0ede2339b5c4ae3a617847e38090803950a34c436fc4cdcfa28f59b62a7a +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000768704_196788224.pth b/checkpoint_p1/milestones/checkpoint_000768704_196788224.pth new file mode 100644 index 0000000000000000000000000000000000000000..85b4ad3665eefb740e8232d5e92f151b025676c7 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000768704_196788224.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42dc81e5414647e7c17b588a4ec1c5105b9b38184309e35cc4d7ad940dd1f03b +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000782528_200327168.pth b/checkpoint_p1/milestones/checkpoint_000782528_200327168.pth new file mode 100644 index 0000000000000000000000000000000000000000..22247796042758c4a927755a81dc91f6e6b6c00b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000782528_200327168.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bddedec2e9f065efc54490d960da1188cae52c1b5473b37217777ffac1a901e +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000796352_203866112.pth b/checkpoint_p1/milestones/checkpoint_000796352_203866112.pth new file mode 100644 index 0000000000000000000000000000000000000000..089b934484ed65470bec2080fb753703a1b93b4f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000796352_203866112.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f856ee5fd2ab6a05439a87d3b719ba71fc4f293f30fb4203cbea253aad60a99 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000810112_207388672.pth b/checkpoint_p1/milestones/checkpoint_000810112_207388672.pth new file mode 100644 index 0000000000000000000000000000000000000000..6c3a8039cf7b428a6a30e0b63e5cece7facd404f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000810112_207388672.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4a4d49087272a81ec95d08d25ebfeec1f26c8e2b3542ddb2633ec809e02075d +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000823968_210935808.pth b/checkpoint_p1/milestones/checkpoint_000823968_210935808.pth new file mode 100644 index 0000000000000000000000000000000000000000..4eace1f8b910fab4c6ca23ece88896fb3e018c5a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000823968_210935808.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3b1dcd8859f9fc12ff5022c4509a4ce887aa582e760e31f65620c2b4ee23b6b +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000837760_214466560.pth b/checkpoint_p1/milestones/checkpoint_000837760_214466560.pth new file mode 100644 index 0000000000000000000000000000000000000000..51fe4a01267dd844ad6c6698fb6a4ca7cbd00934 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000837760_214466560.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76625d542b99b3e3796d20f097d441ec92c28f911394748d51bda959b986d2fd +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000851584_218005504.pth b/checkpoint_p1/milestones/checkpoint_000851584_218005504.pth new file mode 100644 index 0000000000000000000000000000000000000000..29407733924f08f2d458d97aed15ecb12bcd2a98 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000851584_218005504.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7775f88b3fba4c3921741bb8883a07e777208fc72f12b436f8d56a5e8259541 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000865408_221544448.pth b/checkpoint_p1/milestones/checkpoint_000865408_221544448.pth new file mode 100644 index 0000000000000000000000000000000000000000..cb5105b6949132a2437e237069b592fc3719622a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000865408_221544448.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78683024c719234c48ef2a80e35e0cf6fc91e18c4c526f5ac14d67e9a78f54b8 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000879200_225075200.pth b/checkpoint_p1/milestones/checkpoint_000879200_225075200.pth new file mode 100644 index 0000000000000000000000000000000000000000..6bff1014449c8dfaf95ea35554652ca869d8e40b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000879200_225075200.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f22df87ca1b2f2a147c2d3b994c5b11223835c17021f5422a0c818e0b3b6dd77 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000893056_228622336.pth b/checkpoint_p1/milestones/checkpoint_000893056_228622336.pth new file mode 100644 index 0000000000000000000000000000000000000000..e73b219bd37705c024b5e4437ab03854660d2fef --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000893056_228622336.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b73ba503e6085c84fff4fbc01f5f27a88fd982a9987cd890275f8a87895dbba +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000906912_232169472.pth b/checkpoint_p1/milestones/checkpoint_000906912_232169472.pth new file mode 100644 index 0000000000000000000000000000000000000000..a9a1726a1ffbc1d034459bc444c970172e03d2bb --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000906912_232169472.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43ce785839b8a68a8c4b7a142b81000f4d10fb415d916a6629b70b7c1e310c0f +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000920768_235716608.pth b/checkpoint_p1/milestones/checkpoint_000920768_235716608.pth new file mode 100644 index 0000000000000000000000000000000000000000..524a9245c19ac5840687e7b4032fe40b282bb423 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000920768_235716608.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a9a542ad15174cd56adef16a2880ca9405b60068cb465b37061c3d6305cd3df +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000934656_239271936.pth b/checkpoint_p1/milestones/checkpoint_000934656_239271936.pth new file mode 100644 index 0000000000000000000000000000000000000000..578dc30fec0cb73ab2b4820e96bfefdbf376f422 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000934656_239271936.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6095016f3b81400f594fea52e30f1e54d343bff5da3fe0cb005f826c77a80a82 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000948480_242810880.pth b/checkpoint_p1/milestones/checkpoint_000948480_242810880.pth new file mode 100644 index 0000000000000000000000000000000000000000..fbebba16b4c364ad8d9f0d0cf39787a1e2710b13 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000948480_242810880.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfd3e4539aa42f909d405c33b4896788f0c3aa0541a274ab5204b713d90ee409 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000962304_246349824.pth b/checkpoint_p1/milestones/checkpoint_000962304_246349824.pth new file mode 100644 index 0000000000000000000000000000000000000000..07e857940c6c6f5d2d046b5cc42b57a4ce0ae87c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000962304_246349824.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59cd1864fa08648e8b80b61608ba442a1acda03a65cd1f5b3d03d2c5baedfb31 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000976096_249880576.pth b/checkpoint_p1/milestones/checkpoint_000976096_249880576.pth new file mode 100644 index 0000000000000000000000000000000000000000..c2773c68d7013be93eb447eb9bfd2014fb76d296 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000976096_249880576.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf2b5c6360b686f7a4b7e1d14aa352bdc9b954701b18913c570b51ad589a2711 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000989920_253419520.pth b/checkpoint_p1/milestones/checkpoint_000989920_253419520.pth new file mode 100644 index 0000000000000000000000000000000000000000..abd4a22807b4a8dbe17db558efc6e4156b0868e5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000989920_253419520.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:860721dfa6afd9af6a3d70234e2cb10b7cc092327e3e38fff808b480da61631a +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001003776_256966656.pth b/checkpoint_p1/milestones/checkpoint_001003776_256966656.pth new file mode 100644 index 0000000000000000000000000000000000000000..d74462a5aecdd211a17bb0825611d4c70f6590bf --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001003776_256966656.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43f3007cbbc71dc7c64703f783e2954746516ac729520f20763fefdbf05c504f +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001017632_260513792.pth b/checkpoint_p1/milestones/checkpoint_001017632_260513792.pth new file mode 100644 index 0000000000000000000000000000000000000000..cb323ce99b6f6920a997f0fd49cdc7d1eed2fc16 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001017632_260513792.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65cc005d2d9ae959ec40d4615ddbe0f7c4c23123f674a0aee8184d10716a6889 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001031456_264052736.pth b/checkpoint_p1/milestones/checkpoint_001031456_264052736.pth new file mode 100644 index 0000000000000000000000000000000000000000..a1cbc9633307884eb2cda474b20879dee71c13e0 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001031456_264052736.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8eb72a15fdefd2532710433af510abc60087f8488cf2464a63842c4f8baf8ca3 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001045344_267608064.pth b/checkpoint_p1/milestones/checkpoint_001045344_267608064.pth new file mode 100644 index 0000000000000000000000000000000000000000..f05e4ea45635d68a0ed7a1b34c42a3158ab7c80c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001045344_267608064.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52941226f1b1ded2f08d80b9c0133060001ad21f7d33809f9cbbcb4d81df66aa +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001059200_271155200.pth b/checkpoint_p1/milestones/checkpoint_001059200_271155200.pth new file mode 100644 index 0000000000000000000000000000000000000000..4d70ebeef3bdfc09637e3e06845d548d998c5abf --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001059200_271155200.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f18c73e2feb68fac300826ec8ae2390fa499e3bf5baa5e9abc9cbcbc75cb5d1f +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001073024_274694144.pth b/checkpoint_p1/milestones/checkpoint_001073024_274694144.pth new file mode 100644 index 0000000000000000000000000000000000000000..e4a7419cdaed32ad3aaefdf776cda8fe23e3b571 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001073024_274694144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7848cbc50e2b3e1d8fabdbac7023be6d4b07b2d0123be116c72d450c56c10f79 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001086880_278241280.pth b/checkpoint_p1/milestones/checkpoint_001086880_278241280.pth new file mode 100644 index 0000000000000000000000000000000000000000..82f7fbcc0ab713404b11105a3ea337fc81904850 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001086880_278241280.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0a7d3e55ad7301507b4f377474a5f1236136d4d865227e68d929af07690eb0b +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001100736_281788416.pth b/checkpoint_p1/milestones/checkpoint_001100736_281788416.pth new file mode 100644 index 0000000000000000000000000000000000000000..db3024875e98a11a49b386174e2bb90b3efce1f0 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001100736_281788416.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4133c9394e134248b90263d2324ddf0d2eb2022729c9b8aafe77a1c402929954 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001114624_285343744.pth b/checkpoint_p1/milestones/checkpoint_001114624_285343744.pth new file mode 100644 index 0000000000000000000000000000000000000000..9c373bac6a6d8ba27b72acc7368ae56f723cf66b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001114624_285343744.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b89e3c6a49d55195062f56423d1c0ccd6d0e5df1598e248b256829379ce366af +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001128256_288833536.pth b/checkpoint_p1/milestones/checkpoint_001128256_288833536.pth new file mode 100644 index 0000000000000000000000000000000000000000..99e1ed28255e61292c638bf611ea2956bb473aaa --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001128256_288833536.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29a269949f351ea53a52facf74cd8f0c4a8259fdfad0a74d45ba86111ffebb16 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001142048_292364288.pth b/checkpoint_p1/milestones/checkpoint_001142048_292364288.pth new file mode 100644 index 0000000000000000000000000000000000000000..2f9ac547b2d6b4446add49de15ad24e8d121f394 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001142048_292364288.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9a28915912107789d37dad3408fecf097818694c7e7b8844599bac906c03d44 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001155904_295911424.pth b/checkpoint_p1/milestones/checkpoint_001155904_295911424.pth new file mode 100644 index 0000000000000000000000000000000000000000..af25238e8d6bfa40c49ca3cbaab42ba0c4397e9a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001155904_295911424.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77b2b28dcd60614a41ee9039b387bc21178b0be2c56e9aea5a7cf277b7892ce9 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001169760_299458560.pth b/checkpoint_p1/milestones/checkpoint_001169760_299458560.pth new file mode 100644 index 0000000000000000000000000000000000000000..2eae571750d79cf90aa5f5a4e2dc4f1d0dd07664 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001169760_299458560.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac79383f41d98aeb95b60f37a945bfdfe62853d2ce9a8bcc532c62c6979a7f04 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001183616_303005696.pth b/checkpoint_p1/milestones/checkpoint_001183616_303005696.pth new file mode 100644 index 0000000000000000000000000000000000000000..9c631b0db339622bc11975b1b1f2fb49fa7403c2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001183616_303005696.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:063963a581c8cde6fc3a326503731f21448461d0c7f5aa51000db5709afcfe87 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001197504_306561024.pth b/checkpoint_p1/milestones/checkpoint_001197504_306561024.pth new file mode 100644 index 0000000000000000000000000000000000000000..b0b23f6f6d0b803f504c7927509cde71e20d2db0 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001197504_306561024.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48fe9ef587903829db2b93d21ec8e7b2a4f29e7e2df9e55dc96fc1eae24b858d +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001211328_310099968.pth b/checkpoint_p1/milestones/checkpoint_001211328_310099968.pth new file mode 100644 index 0000000000000000000000000000000000000000..0ec0ea473670557cdc5b62bc1c4ed135c34fe20a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001211328_310099968.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcd3cbd6dcd55594663046cb5b81c518fac0decce73cba9a797b4352aa687149 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001225152_313638912.pth b/checkpoint_p1/milestones/checkpoint_001225152_313638912.pth new file mode 100644 index 0000000000000000000000000000000000000000..1014fad12d6431fbdf8ee5c428ab90f69f1fd811 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001225152_313638912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c42ef6b4d5b3469d78ec6d80398d7270bfb42122de77ecf3f02e449dadab9f7f +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001239072_317202432.pth b/checkpoint_p1/milestones/checkpoint_001239072_317202432.pth new file mode 100644 index 0000000000000000000000000000000000000000..c7a792e9d33d546cf23ea2b2a1cb7b99da8a5f6e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001239072_317202432.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b3a0128c4e510913005836b4123c6fb07f182c804c5d4ed374a070f63c05068 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001252896_320741376.pth b/checkpoint_p1/milestones/checkpoint_001252896_320741376.pth new file mode 100644 index 0000000000000000000000000000000000000000..01caa65b227ea9809f47619b02eaede6bba25535 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001252896_320741376.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:756b0a5c4b66a55bdba6d9b74508032aba6fdc2989af836cbc9cf9d181e05cc4 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001266784_324296704.pth b/checkpoint_p1/milestones/checkpoint_001266784_324296704.pth new file mode 100644 index 0000000000000000000000000000000000000000..e7320fbbcd45a05c6975e72f3f87d82952873a90 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001266784_324296704.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:186336cdec7089776bf261bcf8c778ea877781f032ac24421a4051a206554e67 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001280704_327860224.pth b/checkpoint_p1/milestones/checkpoint_001280704_327860224.pth new file mode 100644 index 0000000000000000000000000000000000000000..21a88f266ef000227f9ec5f274d168cec5cbc073 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001280704_327860224.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ceb840eed8197fec9a34e2a4c677f454660d71e9018aea9232fca32fed031a7d +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001294560_331407360.pth b/checkpoint_p1/milestones/checkpoint_001294560_331407360.pth new file mode 100644 index 0000000000000000000000000000000000000000..1d9efdf2560295160939ccb06585f7903715ec91 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001294560_331407360.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7b0f09a8335fe18b220163413e507d8003f5832fa8419db8a6961cca0bb74a7 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001308416_334954496.pth b/checkpoint_p1/milestones/checkpoint_001308416_334954496.pth new file mode 100644 index 0000000000000000000000000000000000000000..3919d6673181dfa2f48678fcce10a788a60bfdd9 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001308416_334954496.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81b014bf034d233d91a23bdd01c1049646b8e740f700c27d50c19fbae5ea1eae +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001322272_338501632.pth b/checkpoint_p1/milestones/checkpoint_001322272_338501632.pth new file mode 100644 index 0000000000000000000000000000000000000000..688eb7c986c26df33d92f2aabce29add781241c3 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001322272_338501632.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ae7072625f5cc737bcbb2a92f6bcc01e5cfe5afd1545cc8c57bb7f614fdaa27 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001336224_342073344.pth b/checkpoint_p1/milestones/checkpoint_001336224_342073344.pth new file mode 100644 index 0000000000000000000000000000000000000000..89b423e87a5a9ed777852a6509195b22e4c54c8c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001336224_342073344.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa927045696a021531319d0daa41321b337f9e64aab3f260deb920ff60bcdab7 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001350112_345628672.pth b/checkpoint_p1/milestones/checkpoint_001350112_345628672.pth new file mode 100644 index 0000000000000000000000000000000000000000..97e8238dab951e5d49b266436112b60363f9e1c7 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001350112_345628672.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2347e425d7466af43cf5677d354647103b56219942a501a3615633077b5d439 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001364000_349184000.pth b/checkpoint_p1/milestones/checkpoint_001364000_349184000.pth new file mode 100644 index 0000000000000000000000000000000000000000..7e8cf4bc875d0e3a4205e6f5ee838811484c4455 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001364000_349184000.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bac217513d5d623d36a25cc3fc69bff87a550de1ec73666347b82897edaa05e +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001377856_352731136.pth b/checkpoint_p1/milestones/checkpoint_001377856_352731136.pth new file mode 100644 index 0000000000000000000000000000000000000000..17fe8da80f142705af1c4d860c90855ac177342e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001377856_352731136.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b4f01c05472b82726fc0aa75678a81dba7efd9efd508fd28308ea8e576c74e6 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001391744_356286464.pth b/checkpoint_p1/milestones/checkpoint_001391744_356286464.pth new file mode 100644 index 0000000000000000000000000000000000000000..cc0f8f2399c860c6c26dc527be9472777a1472e2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001391744_356286464.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97b820551a56da08bc0bfbbfb5d88e94c9345dc3c1c3cac3fcb56f480151f389 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001405568_359825408.pth b/checkpoint_p1/milestones/checkpoint_001405568_359825408.pth new file mode 100644 index 0000000000000000000000000000000000000000..be518a9dd3fb846d1be065c9fca60fce818891ef --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001405568_359825408.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d185a3fd30e1519b6e82fd533057bbe3dccee576ce443d107ef5ab393c4f10f7 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001419456_363380736.pth b/checkpoint_p1/milestones/checkpoint_001419456_363380736.pth new file mode 100644 index 0000000000000000000000000000000000000000..b0604db5adc71bc53a1ffe7bfc7903f6175d0830 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001419456_363380736.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:118f2063b7fd280d46596a52f749348d915938b0d8c2a6a11d6c220850228abb +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001433280_366919680.pth b/checkpoint_p1/milestones/checkpoint_001433280_366919680.pth new file mode 100644 index 0000000000000000000000000000000000000000..62b808405bae2fbde065c15af1475f0bfc78c5e2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001433280_366919680.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0641fab75dc1e361a14b18abc80bac42c467356189f65670a4f468d4f856061 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001447136_370466816.pth b/checkpoint_p1/milestones/checkpoint_001447136_370466816.pth new file mode 100644 index 0000000000000000000000000000000000000000..8045ef199227584a804c7a27804253d486d2b5b6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001447136_370466816.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a50038b498e165b412f94c8254b7a2f9846790fd486d1501e1f23e611962b79 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001460992_374013952.pth b/checkpoint_p1/milestones/checkpoint_001460992_374013952.pth new file mode 100644 index 0000000000000000000000000000000000000000..b6ca0e2544ef1d885419d7b23ca317f396f993ef --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001460992_374013952.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13f3a8fbe145abce6e1488db547e53a4f0913b2e32a713848243514bad5e779c +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001474848_377561088.pth b/checkpoint_p1/milestones/checkpoint_001474848_377561088.pth new file mode 100644 index 0000000000000000000000000000000000000000..e751e5b08d566cadce3f60aeb9b9c40cf9505f46 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001474848_377561088.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49df9fa35d14187843205bd4fc1fde1c79d147f73308c6c564a3c82287c960a8 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001488736_381116416.pth b/checkpoint_p1/milestones/checkpoint_001488736_381116416.pth new file mode 100644 index 0000000000000000000000000000000000000000..fff6560cf9dce1576ae6b53b52a1914ab3d8df6c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001488736_381116416.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7ba2aedd08e33f496a27950c32e6ba2704700ebea128ae590f165f6f30926fe +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001502656_384679936.pth b/checkpoint_p1/milestones/checkpoint_001502656_384679936.pth new file mode 100644 index 0000000000000000000000000000000000000000..abe9634c45f368972b838cccb0a730a1a8d01491 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001502656_384679936.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:015c766a3e757ef51213722b9506392e274394bd6a4aa3d76282ae1f96c1da9c +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001516576_388243456.pth b/checkpoint_p1/milestones/checkpoint_001516576_388243456.pth new file mode 100644 index 0000000000000000000000000000000000000000..1c8855413e8e578185508deabc6ad70a0a67318d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001516576_388243456.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c4a54e94e81051457c7d1845444a270d72afb7882d321274df5a448acfb908b +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001530496_391806976.pth b/checkpoint_p1/milestones/checkpoint_001530496_391806976.pth new file mode 100644 index 0000000000000000000000000000000000000000..02cab032c1f9cf376ead36957ab0c12395b8126a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001530496_391806976.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec8195d282a65843a6a6422668affffec3b36b4c9813eca0a839c0b31e03b456 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001544352_395354112.pth b/checkpoint_p1/milestones/checkpoint_001544352_395354112.pth new file mode 100644 index 0000000000000000000000000000000000000000..186abbe5a8fa134b348a5a5a681ece389fa249a3 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001544352_395354112.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73edd94c77f46198548106234389830ae4b9ccc5c805318fa5756f33045ff1e0 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001558272_398917632.pth b/checkpoint_p1/milestones/checkpoint_001558272_398917632.pth new file mode 100644 index 0000000000000000000000000000000000000000..b8be83f2b54f576f465fe9f1d72878a31c20dd3e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001558272_398917632.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd1fec16f371e314ee0a3ab6b5058f16e522e220265d958c3f030f37875eb070 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001572128_402464768.pth b/checkpoint_p1/milestones/checkpoint_001572128_402464768.pth new file mode 100644 index 0000000000000000000000000000000000000000..d934ff16eb79724f070c9dc44950e83f69fa9977 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001572128_402464768.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37051bf0a2127326071daaaad0732204c545186569d59dcf443bb03b1d77b19f +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001586016_406020096.pth b/checkpoint_p1/milestones/checkpoint_001586016_406020096.pth new file mode 100644 index 0000000000000000000000000000000000000000..9f4cc1765d4c21929bb39f684af9a125e50ecf8b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001586016_406020096.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ca1d195e86183b1d71a10d6596dd77835a2d18e279209b98f2642a39aab3df6 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001599936_409583616.pth b/checkpoint_p1/milestones/checkpoint_001599936_409583616.pth new file mode 100644 index 0000000000000000000000000000000000000000..226a6906a121ffd2b5ed639eabe3272ba3f3edda --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001599936_409583616.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac01b5d7a6fb61b0870690b504c840053b9b094e1d09463d44d121bfa151776e +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001613920_413163520.pth b/checkpoint_p1/milestones/checkpoint_001613920_413163520.pth new file mode 100644 index 0000000000000000000000000000000000000000..6d1a2cff3dc063da34262bd087e9fb64df96f901 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001613920_413163520.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfa9f75c01e45a9d65df055130046dae506e157ac89cf73552112ee675e308fd +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001627840_416727040.pth b/checkpoint_p1/milestones/checkpoint_001627840_416727040.pth new file mode 100644 index 0000000000000000000000000000000000000000..02df6f5ca3d2737e9913e80f4ba12e62fa16a821 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001627840_416727040.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9890265cce6dfdca7d85753dabb8a68b6877fc7fae84a6935f94ca8885717d60 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001641728_420282368.pth b/checkpoint_p1/milestones/checkpoint_001641728_420282368.pth new file mode 100644 index 0000000000000000000000000000000000000000..8401743658daf133373c589f7aa7b8aafd3afcd4 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001641728_420282368.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8086a59a45b33611bc97743090abcab1ab75907b31d5395bd692e1603fec0cf +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001655648_423845888.pth b/checkpoint_p1/milestones/checkpoint_001655648_423845888.pth new file mode 100644 index 0000000000000000000000000000000000000000..75be39d75d72cd02eacee949a4fac07a4a7ea59d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001655648_423845888.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:270f24dd6807dcc867f817395010f655f97514d95f9890cb8e490d44b7be54d7 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001669440_427376640.pth b/checkpoint_p1/milestones/checkpoint_001669440_427376640.pth new file mode 100644 index 0000000000000000000000000000000000000000..e629c3a5f18b5f470a6142af1f58c5aa4681e908 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001669440_427376640.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8da9acf83d7c191762d5d69ff679dffb4ace2fa64e47f8a9cc4847ece2e42459 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001683328_430931968.pth b/checkpoint_p1/milestones/checkpoint_001683328_430931968.pth new file mode 100644 index 0000000000000000000000000000000000000000..63a6ee409916099f814a30c23cbb06faefa08c23 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001683328_430931968.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47f65a837aabe9b019c669f6c89ecc9672dc61b78173948f919645a9ba6d2182 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001697248_434495488.pth b/checkpoint_p1/milestones/checkpoint_001697248_434495488.pth new file mode 100644 index 0000000000000000000000000000000000000000..57a3572aef67aaa8945ae26fd76016df845890bf --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001697248_434495488.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:548ef8d5d6e1959400bb7b3d3c73475914461be8a8e33d5b6872105f136a92a1 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001711136_438050816.pth b/checkpoint_p1/milestones/checkpoint_001711136_438050816.pth new file mode 100644 index 0000000000000000000000000000000000000000..7fe54d1b8f4835a96f0864f8077d0669048a29bf --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001711136_438050816.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2793459b9a111f7b553a9dccbece587e39f2b3f18cf20a35d05f937524cdca4 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001725024_441606144.pth b/checkpoint_p1/milestones/checkpoint_001725024_441606144.pth new file mode 100644 index 0000000000000000000000000000000000000000..079998dd99200feae6304f0d26dd1ae02b580067 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001725024_441606144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01b5650b66d2c0ea9d8e673dbe97e97c6e32d3393fb9b9dd2e7bece97b786e40 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001738912_445161472.pth b/checkpoint_p1/milestones/checkpoint_001738912_445161472.pth new file mode 100644 index 0000000000000000000000000000000000000000..47b88b4977ec7d073d1527ec427b2b95425e1104 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001738912_445161472.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76634130deb81a1ff3f1cd8259dc441c434a456f58135dcb70ef447365c78314 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001752384_448610304.pth b/checkpoint_p1/milestones/checkpoint_001752384_448610304.pth new file mode 100644 index 0000000000000000000000000000000000000000..b0778791eb4d3ed00212a73ba1ba798ff727a564 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001752384_448610304.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b16bf0438c905f74bc85d754314f1ab1d2767d64503460510108373a978dd506 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001766016_452100096.pth b/checkpoint_p1/milestones/checkpoint_001766016_452100096.pth new file mode 100644 index 0000000000000000000000000000000000000000..5a7c1e3953b3b7c83241db375981a0c6b69a355c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001766016_452100096.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28d2af6aa489e2101dd8382dac080b8cd5145742270dd97db3f7474822404267 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001779872_455647232.pth b/checkpoint_p1/milestones/checkpoint_001779872_455647232.pth new file mode 100644 index 0000000000000000000000000000000000000000..2cc77bc2318c73b28306085a9a6781617f5c49a2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001779872_455647232.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:810855a48b364817dca5bd3b3ffcd7ec4b32b0f8863358b20997d50022969365 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001793728_459194368.pth b/checkpoint_p1/milestones/checkpoint_001793728_459194368.pth new file mode 100644 index 0000000000000000000000000000000000000000..feaafda4a9a53401df62dcdad6336ea118237095 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001793728_459194368.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d65319b784c8b8b8cf46e50a663a0fc229c58cb08b44d074dae01261bece23b1 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001807520_462725120.pth b/checkpoint_p1/milestones/checkpoint_001807520_462725120.pth new file mode 100644 index 0000000000000000000000000000000000000000..c1a86b8f810fcbfc29e2a2c7f637f35ea9b15a5f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001807520_462725120.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bf5dd040e2f227b98d08ea9e1aa386c489bd93b1a94b7e0083892b606056212 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001821440_466288640.pth b/checkpoint_p1/milestones/checkpoint_001821440_466288640.pth new file mode 100644 index 0000000000000000000000000000000000000000..c0000aa502e434e34cecae9dae3c66d65899073f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001821440_466288640.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:490f48cacf17b8607b6ee84700b53e9da779c08e2ddd137e938baa8371d80894 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001835264_469827584.pth b/checkpoint_p1/milestones/checkpoint_001835264_469827584.pth new file mode 100644 index 0000000000000000000000000000000000000000..160e45586e589cb085f2c55ecb64e8565a1388cb --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001835264_469827584.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8417f2bbd0ecc211d15342eeaf44abf99049e6d7026f05c209abd5a497c43ccf +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001849184_473391104.pth b/checkpoint_p1/milestones/checkpoint_001849184_473391104.pth new file mode 100644 index 0000000000000000000000000000000000000000..8c115d39132699851a2ba4face9a1a0f3aa02f9f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001849184_473391104.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:899cea030d3eec2bf943eb1d99e99fb2cde9b3fab0842fc5c8d5625ed97a512e +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001863040_476938240.pth b/checkpoint_p1/milestones/checkpoint_001863040_476938240.pth new file mode 100644 index 0000000000000000000000000000000000000000..76b9d3ba808a0032a63275a7b20b12096adbbcba --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001863040_476938240.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c60f8d6b58e67122499cfbc962d7ee67c822cac5a1bb3b48534baf60cd325bd +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001876928_480493568.pth b/checkpoint_p1/milestones/checkpoint_001876928_480493568.pth new file mode 100644 index 0000000000000000000000000000000000000000..03f0a6598ecd70b6620d03e20ebb974ec0717dfb --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001876928_480493568.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4053f1203ea280f43e81bb2d0c3f768d8e2eb75ac424a34230434b665bc55f66 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001890816_484048896.pth b/checkpoint_p1/milestones/checkpoint_001890816_484048896.pth new file mode 100644 index 0000000000000000000000000000000000000000..3250088feb0f40fc6c66222a54266c09baf8a9be --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001890816_484048896.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91e70b974be015a9cab95126193fa4291fb54ebb043d8ecc4694ca06f462a032 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001904704_487604224.pth b/checkpoint_p1/milestones/checkpoint_001904704_487604224.pth new file mode 100644 index 0000000000000000000000000000000000000000..88a1dd2629077ff349eb19dcedc916e6025fbabc --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001904704_487604224.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edb4056f1f3f90d22fea428418727ec3bc96370f445a8577adcda0006b2e1b8a +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001918592_491159552.pth b/checkpoint_p1/milestones/checkpoint_001918592_491159552.pth new file mode 100644 index 0000000000000000000000000000000000000000..0504735616288abc6eab0f45f55d918dfd7198dc --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001918592_491159552.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c30181b44a21eb97e1b21efdaf99869ddfceb32a5a501e3cac7b975c63c978f0 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001932448_494706688.pth b/checkpoint_p1/milestones/checkpoint_001932448_494706688.pth new file mode 100644 index 0000000000000000000000000000000000000000..6a3c166dfa1ce26885ba70db2a61f691c041da6c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001932448_494706688.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20d663237288c79342191497c0074f39508db27b7e109daf84f468d0466217f2 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001946336_498262016.pth b/checkpoint_p1/milestones/checkpoint_001946336_498262016.pth new file mode 100644 index 0000000000000000000000000000000000000000..7f6224a4eccfea35d879be0af8ec6d0d30eddac9 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001946336_498262016.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5811787de0c615192d39f20c1e1acd99c8ba081150ab309b57a29da1a63e95e1 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001956832_501907456.pth b/checkpoint_p1/milestones/checkpoint_001956832_501907456.pth new file mode 100644 index 0000000000000000000000000000000000000000..a5819887106623c776bbc5318b0a5c0101dc7478 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001956832_501907456.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce8d9abcd1560232af8aabd39a2beb2113f6a4de3ed109cfbbe593320b323af0 +size 20747659 diff --git a/config.json b/config.json index 554047fdd11e7bb950085279a31592aa435bd9ff..d0ac6397be88e3b0e0076548a6532e89831817c8 100644 --- a/config.json +++ b/config.json @@ -4,7 +4,7 @@ "env": "atari_timepilot", "experiment": "atari_timepilot_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_timepilot --experiment=atari_timepilot_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_timepilot --wandb_job_type=SF --wandb_tags=atari", + "command_line": "--algo=APPO --env=atari_timepilot --experiment=atari_timepilot_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_timepilot --wandb_job_type=SF --wandb_tags=atari", "cli_args": { "algo": "APPO", "env": "atari_timepilot", "experiment": "atari_timepilot_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_timepilot_APPO_20231016_024534_717006" + "wandb_unique_id": "atari_timepilot_APPO_20231207_055819_692466" } \ 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 b10eaac74fbf2ddf512a628c7beea5f93c861460..c17d346624e36512a4a2ae231e52a43a69346519 100644 --- a/replay.mp4 +++ b/replay.mp4 @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:1e1f760838ec6ca924273e03703fe894bc5b74ea1d1bfebb7a171f10da200770 -size 4076763 +oid sha256:ee2b61b694dba75898b30b1909acf38e67b3626c3497efd1fa8280d132f553c0 +size 22012327 diff --git a/sf_log.txt b/sf_log.txt index ae64521638edca0573704ffd280d9cba880ff61a..ac65db11ba4304f4264c39202e66e18ce2e3a148 100644 --- a/sf_log.txt +++ b/sf_log.txt @@ -1,26126 +1,3 @@ -[2023-10-16 02:45:41,301][03835] Saving configuration to ./train_atari/atari_timepilot_APPO/config.json... -[2023-10-16 02:45:41,618][03835] Rollout worker 0 uses device cpu -[2023-10-16 02:45:41,619][03835] Rollout worker 1 uses device cpu -[2023-10-16 02:45:41,619][03835] Rollout worker 2 uses device cpu -[2023-10-16 02:45:41,620][03835] Rollout worker 3 uses device cpu -[2023-10-16 02:45:41,620][03835] Rollout worker 4 uses device cpu -[2023-10-16 02:45:41,621][03835] Rollout worker 5 uses device cpu -[2023-10-16 02:45:41,621][03835] Rollout worker 6 uses device cpu -[2023-10-16 02:45:41,622][03835] Rollout worker 7 uses device cpu -[2023-10-16 02:45:41,622][03835] Rollout worker 8 uses device cpu -[2023-10-16 02:45:41,623][03835] Rollout worker 9 uses device cpu -[2023-10-16 02:45:41,623][03835] Rollout worker 10 uses device cpu -[2023-10-16 02:45:41,623][03835] Rollout worker 11 uses device cpu -[2023-10-16 02:45:41,624][03835] Rollout worker 12 uses device cpu -[2023-10-16 02:45:41,624][03835] Rollout worker 13 uses device cpu -[2023-10-16 02:45:41,625][03835] Rollout worker 14 uses device cpu -[2023-10-16 02:45:41,625][03835] Rollout worker 15 uses device cpu -[2023-10-16 02:45:41,916][03835] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-16 02:45:41,916][03835] InferenceWorker_p0-w0: min num requests: 2 -[2023-10-16 02:45:41,919][03835] Using GPUs [1] for process 1 (actually maps to GPUs [1]) -[2023-10-16 02:45:41,919][03835] InferenceWorker_p1-w0: min num requests: 2 -[2023-10-16 02:45:41,965][03835] Starting all processes... -[2023-10-16 02:45:41,966][03835] Starting process learner_proc0 -[2023-10-16 02:45:43,634][03835] Starting process learner_proc1 -[2023-10-16 02:45:43,638][04766] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-16 02:45:43,638][04766] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 -[2023-10-16 02:45:43,657][04766] Num visible devices: 1 -[2023-10-16 02:45:43,679][04766] Setting fixed seed 1234 -[2023-10-16 02:45:43,680][04766] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-16 02:45:43,681][04766] Initializing actor-critic model on device cuda:0 -[2023-10-16 02:45:43,681][04766] RunningMeanStd input shape: (4, 84, 84) -[2023-10-16 02:45:43,681][04766] RunningMeanStd input shape: (1,) -[2023-10-16 02:45:43,693][04766] ConvEncoder: input_channels=4 -[2023-10-16 02:45:43,867][04766] Conv encoder output size: 512 -[2023-10-16 02:45:43,870][04766] Created Actor Critic model with architecture: -[2023-10-16 02:45:43,870][04766] ActorCriticSharedWeights( - (obs_normalizer): ObservationNormalizer( - (running_mean_std): RunningMeanStdDictInPlace( - (running_mean_std): ModuleDict( - (obs): RunningMeanStdInPlace() - ) - ) - ) - (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) - (encoder): MultiInputEncoder( - (encoders): ModuleDict( - (obs): ConvEncoder( - (enc): RecursiveScriptModule( - original_name=ConvEncoderImpl - (conv_head): RecursiveScriptModule( - original_name=Sequential - (0): RecursiveScriptModule(original_name=Conv2d) - (1): RecursiveScriptModule(original_name=ReLU) - (2): RecursiveScriptModule(original_name=Conv2d) - (3): RecursiveScriptModule(original_name=ReLU) - (4): RecursiveScriptModule(original_name=Conv2d) - (5): RecursiveScriptModule(original_name=ReLU) - ) - (mlp_layers): RecursiveScriptModule( - original_name=Sequential - (0): RecursiveScriptModule(original_name=Linear) - (1): RecursiveScriptModule(original_name=ReLU) - ) - ) - ) - ) - ) - (core): ModelCoreIdentity() - (decoder): MlpDecoder( - (mlp): Identity() - ) - (critic_linear): Linear(in_features=512, out_features=1, bias=True) - (action_parameterization): ActionParameterizationDefault( - (distribution_linear): Linear(in_features=512, out_features=10, bias=True) - ) -) -[2023-10-16 02:45:44,460][04766] Using optimizer -[2023-10-16 02:45:44,461][04766] No checkpoints found -[2023-10-16 02:45:44,461][04766] Did not load from checkpoint, starting from scratch! -[2023-10-16 02:45:44,461][04766] Initialized policy 0 weights for model version 0 -[2023-10-16 02:45:44,463][04766] LearnerWorker_p0 finished initialization! -[2023-10-16 02:45:44,463][04766] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-16 02:45:45,411][03835] Starting all processes... -[2023-10-16 02:45:45,415][04891] Using GPUs [1] for process 1 (actually maps to GPUs [1]) -[2023-10-16 02:45:45,415][04891] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [1]) for learning process 1 -[2023-10-16 02:45:45,433][04891] Num visible devices: 1 -[2023-10-16 02:45:45,469][04891] Setting fixed seed 1234 -[2023-10-16 02:45:45,469][03835] Starting process inference_proc0-0 -[2023-10-16 02:45:45,469][03835] Starting process inference_proc1-0 -[2023-10-16 02:45:45,470][04891] Using GPUs [0] for process 1 (actually maps to GPUs [1]) -[2023-10-16 02:45:45,471][04891] Initializing actor-critic model on device cuda:0 -[2023-10-16 02:45:45,471][04891] RunningMeanStd input shape: (4, 84, 84) -[2023-10-16 02:45:45,472][04891] RunningMeanStd input shape: (1,) -[2023-10-16 02:45:45,469][03835] Starting process rollout_proc0 -[2023-10-16 02:45:45,469][03835] Starting process rollout_proc1 -[2023-10-16 02:45:45,469][03835] Starting process rollout_proc2 -[2023-10-16 02:45:45,470][03835] Starting process rollout_proc3 -[2023-10-16 02:45:45,483][04891] ConvEncoder: input_channels=4 -[2023-10-16 02:45:45,470][03835] Starting process rollout_proc4 -[2023-10-16 02:45:45,470][03835] Starting process rollout_proc5 -[2023-10-16 02:45:45,473][03835] Starting process rollout_proc6 -[2023-10-16 02:45:45,475][03835] Starting process rollout_proc7 -[2023-10-16 02:45:45,476][03835] Starting process rollout_proc8 -[2023-10-16 02:45:45,476][03835] Starting process rollout_proc9 -[2023-10-16 02:45:45,477][03835] Starting process rollout_proc10 -[2023-10-16 02:45:45,478][03835] Starting process rollout_proc11 -[2023-10-16 02:45:45,479][03835] Starting process rollout_proc12 -[2023-10-16 02:45:45,480][03835] Starting process rollout_proc13 -[2023-10-16 02:45:45,929][04891] Conv encoder output size: 512 -[2023-10-16 02:45:45,932][04891] Created Actor Critic model with architecture: -[2023-10-16 02:45:45,932][04891] ActorCriticSharedWeights( - (obs_normalizer): ObservationNormalizer( - (running_mean_std): RunningMeanStdDictInPlace( - (running_mean_std): ModuleDict( - (obs): RunningMeanStdInPlace() - ) - ) - ) - (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) - (encoder): MultiInputEncoder( - (encoders): ModuleDict( - (obs): ConvEncoder( - (enc): RecursiveScriptModule( - original_name=ConvEncoderImpl - (conv_head): RecursiveScriptModule( - original_name=Sequential - (0): RecursiveScriptModule(original_name=Conv2d) - (1): RecursiveScriptModule(original_name=ReLU) - (2): RecursiveScriptModule(original_name=Conv2d) - (3): RecursiveScriptModule(original_name=ReLU) - (4): RecursiveScriptModule(original_name=Conv2d) - (5): RecursiveScriptModule(original_name=ReLU) - ) - (mlp_layers): RecursiveScriptModule( - original_name=Sequential - (0): RecursiveScriptModule(original_name=Linear) - (1): RecursiveScriptModule(original_name=ReLU) - ) - ) - ) - ) - ) - (core): ModelCoreIdentity() - (decoder): MlpDecoder( - (mlp): Identity() - ) - (critic_linear): Linear(in_features=512, out_features=1, bias=True) - (action_parameterization): ActionParameterizationDefault( - (distribution_linear): Linear(in_features=512, out_features=10, bias=True) - ) -) -[2023-10-16 02:45:46,704][04891] Using optimizer -[2023-10-16 02:45:46,704][04891] No checkpoints found -[2023-10-16 02:45:46,705][04891] Did not load from checkpoint, starting from scratch! -[2023-10-16 02:45:46,705][04891] Initialized policy 1 weights for model version 0 -[2023-10-16 02:45:46,707][04891] LearnerWorker_p1 finished initialization! -[2023-10-16 02:45:46,707][04891] Using GPUs [0] for process 1 (actually maps to GPUs [1]) -[2023-10-16 02:45:47,686][03835] Starting process rollout_proc14 -[2023-10-16 02:45:47,690][03835] Starting process rollout_proc15 -[2023-10-16 02:45:47,691][05230] Worker 10 uses CPU cores [20, 21] -[2023-10-16 02:45:47,694][05231] Worker 11 uses CPU cores [22, 23] -[2023-10-16 02:45:47,714][05223] Worker 3 uses CPU cores [6, 7] -[2023-10-16 02:45:47,718][05225] Worker 5 uses CPU cores [10, 11] -[2023-10-16 02:45:47,845][05224] Worker 4 uses CPU cores [8, 9] -[2023-10-16 02:45:47,917][05228] Worker 8 uses CPU cores [16, 17] -[2023-10-16 02:45:47,946][05232] Worker 12 uses CPU cores [24, 25] -[2023-10-16 02:45:47,980][05220] Worker 0 uses CPU cores [0, 1] -[2023-10-16 02:45:47,994][05233] Worker 13 uses CPU cores [26, 27] -[2023-10-16 02:45:48,065][05221] Worker 1 uses CPU cores [2, 3] -[2023-10-16 02:45:48,101][05226] Worker 6 uses CPU cores [12, 13] -[2023-10-16 02:45:48,221][05222] Worker 2 uses CPU cores [4, 5] -[2023-10-16 02:45:48,261][05219] Using GPUs [1] for process 1 (actually maps to GPUs [1]) -[2023-10-16 02:45:48,261][05219] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [1]) for inference process 1 -[2023-10-16 02:45:48,280][05219] Num visible devices: 1 -[2023-10-16 02:45:48,299][05229] Worker 9 uses CPU cores [18, 19] -[2023-10-16 02:45:48,406][05227] Worker 7 uses CPU cores [14, 15] -[2023-10-16 02:45:48,527][05218] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-16 02:45:48,527][05218] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 -[2023-10-16 02:45:48,547][05218] Num visible devices: 1 -[2023-10-16 02:45:48,927][05219] RunningMeanStd input shape: (4, 84, 84) -[2023-10-16 02:45:48,928][05219] RunningMeanStd input shape: (1,) -[2023-10-16 02:45:48,939][05219] ConvEncoder: input_channels=4 -[2023-10-16 02:45:49,046][05219] Conv encoder output size: 512 -[2023-10-16 02:45:49,145][05218] RunningMeanStd input shape: (4, 84, 84) -[2023-10-16 02:45:49,146][05218] RunningMeanStd input shape: (1,) -[2023-10-16 02:45:49,158][05218] ConvEncoder: input_channels=4 -[2023-10-16 02:45:49,263][05218] Conv encoder output size: 512 -[2023-10-16 02:45:49,590][05969] Worker 14 uses CPU cores [28, 29] -[2023-10-16 02:45:49,709][03835] Inference worker 1-0 is ready! -[2023-10-16 02:45:49,710][03835] Inference worker 0-0 is ready! -[2023-10-16 02:45:49,711][03835] All inference workers are ready! Signal rollout workers to start! -[2023-10-16 02:45:49,711][05970] Worker 15 uses CPU cores [30, 31] -[2023-10-16 02:45:49,712][05226] EnvRunner 6-0 uses policy 0 -[2023-10-16 02:45:49,712][05224] EnvRunner 4-0 uses policy 0 -[2023-10-16 02:45:49,712][05227] EnvRunner 7-0 uses policy 1 -[2023-10-16 02:45:49,712][05220] EnvRunner 0-0 uses policy 0 -[2023-10-16 02:45:49,712][05228] EnvRunner 8-0 uses policy 0 -[2023-10-16 02:45:49,712][05225] EnvRunner 5-0 uses policy 1 -[2023-10-16 02:45:49,713][05221] EnvRunner 1-0 uses policy 1 -[2023-10-16 02:45:49,712][03835] 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) -[2023-10-16 02:45:49,713][05233] EnvRunner 13-0 uses policy 1 -[2023-10-16 02:45:49,713][05223] EnvRunner 3-0 uses policy 1 -[2023-10-16 02:45:49,713][05232] EnvRunner 12-0 uses policy 0 -[2023-10-16 02:45:49,713][05229] EnvRunner 9-0 uses policy 1 -[2023-10-16 02:45:49,713][05222] EnvRunner 2-0 uses policy 0 -[2023-10-16 02:45:49,713][05230] EnvRunner 10-0 uses policy 0 -[2023-10-16 02:45:49,713][05231] EnvRunner 11-0 uses policy 1 -[2023-10-16 02:45:49,799][05969] EnvRunner 14-0 uses policy 0 -[2023-10-16 02:45:49,819][05970] EnvRunner 15-0 uses policy 1 -[2023-10-16 02:45:51,903][03835] Heartbeat connected on Batcher_0 -[2023-10-16 02:45:51,906][03835] Heartbeat connected on LearnerWorker_p0 -[2023-10-16 02:45:51,909][03835] Heartbeat connected on Batcher_1 -[2023-10-16 02:45:51,912][03835] Heartbeat connected on LearnerWorker_p1 -[2023-10-16 02:45:51,919][03835] Heartbeat connected on InferenceWorker_p0-w0 -[2023-10-16 02:45:51,921][03835] Heartbeat connected on InferenceWorker_p1-w0 -[2023-10-16 02:45:51,923][03835] Heartbeat connected on RolloutWorker_w0 -[2023-10-16 02:45:51,927][03835] Heartbeat connected on RolloutWorker_w1 -[2023-10-16 02:45:51,928][03835] Heartbeat connected on RolloutWorker_w2 -[2023-10-16 02:45:51,935][03835] Heartbeat connected on RolloutWorker_w4 -[2023-10-16 02:45:51,936][03835] Heartbeat connected on RolloutWorker_w3 -[2023-10-16 02:45:51,938][03835] Heartbeat connected on RolloutWorker_w6 -[2023-10-16 02:45:51,942][03835] Heartbeat connected on RolloutWorker_w5 -[2023-10-16 02:45:51,942][03835] Heartbeat connected on RolloutWorker_w7 -[2023-10-16 02:45:51,945][03835] Heartbeat connected on RolloutWorker_w8 -[2023-10-16 02:45:51,951][03835] Heartbeat connected on RolloutWorker_w9 -[2023-10-16 02:45:51,953][03835] Heartbeat connected on RolloutWorker_w11 -[2023-10-16 02:45:51,954][03835] Heartbeat connected on RolloutWorker_w10 -[2023-10-16 02:45:51,955][03835] Heartbeat connected on RolloutWorker_w12 -[2023-10-16 02:45:51,958][03835] Heartbeat connected on RolloutWorker_w13 -[2023-10-16 02:45:51,962][03835] Heartbeat connected on RolloutWorker_w14 -[2023-10-16 02:45:51,966][03835] Heartbeat connected on RolloutWorker_w15 -[2023-10-16 02:45:52,350][03835] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 883.3, 1: 704.4. Samples: 4188. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-10-16 02:45:52,351][03835] Avg episode reward: [(0, '1.000'), (1, '1.000')] -[2023-10-16 02:45:57,351][03835] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 1094.3, 1: 1086.4. Samples: 16656. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-10-16 02:45:57,352][03835] Avg episode reward: [(0, '1.774'), (1, '1.659')] -[2023-10-16 02:45:59,577][05218] Updated weights for policy 0, policy_version 10 (0.0009) -[2023-10-16 02:45:59,654][05219] Updated weights for policy 1, policy_version 10 (0.0009) -[2023-10-16 02:45:59,956][05218] Updated weights for policy 0, policy_version 20 (0.0008) -[2023-10-16 02:46:00,021][05219] Updated weights for policy 1, policy_version 20 (0.0007) -[2023-10-16 02:46:00,331][05218] Updated weights for policy 0, policy_version 30 (0.0009) -[2023-10-16 02:46:00,390][05219] Updated weights for policy 1, policy_version 30 (0.0007) -[2023-10-16 02:46:02,350][03835] Fps is (10 sec: 6553.7, 60 sec: 5185.8, 300 sec: 5185.8). Total num frames: 65536. Throughput: 0: 1335.5, 1: 1332.7. Samples: 33720. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-16 02:46:02,351][03835] Avg episode reward: [(0, '2.286'), (1, '1.790')] -[2023-10-16 02:46:02,675][05218] Updated weights for policy 0, policy_version 42 (0.0010) -[2023-10-16 02:46:02,682][05219] Updated weights for policy 1, policy_version 40 (0.0008) -[2023-10-16 02:46:03,040][05219] Updated weights for policy 1, policy_version 50 (0.0007) -[2023-10-16 02:46:03,049][05218] Updated weights for policy 0, policy_version 52 (0.0009) -[2023-10-16 02:46:03,407][05219] Updated weights for policy 1, policy_version 60 (0.0010) -[2023-10-16 02:46:03,420][05218] Updated weights for policy 0, policy_version 62 (0.0008) -[2023-10-16 02:46:06,875][05218] Updated weights for policy 0, policy_version 72 (0.0008) -[2023-10-16 02:46:06,993][05219] Updated weights for policy 1, policy_version 70 (0.0009) -[2023-10-16 02:46:07,250][05218] Updated weights for policy 0, policy_version 82 (0.0009) -[2023-10-16 02:46:07,351][03835] Fps is (10 sec: 13107.2, 60 sec: 7431.2, 300 sec: 7431.2). Total num frames: 131072. Throughput: 0: 1517.1, 1: 1538.3. Samples: 53890. Policy #0 lag: (min: 33.0, avg: 33.0, max: 33.0) -[2023-10-16 02:46:07,352][03835] Avg episode reward: [(0, '2.208'), (1, '1.929')] -[2023-10-16 02:46:07,360][05219] Updated weights for policy 1, policy_version 80 (0.0009) -[2023-10-16 02:46:07,628][05218] Updated weights for policy 0, policy_version 92 (0.0007) -[2023-10-16 02:46:07,724][05219] Updated weights for policy 1, policy_version 90 (0.0008) -[2023-10-16 02:46:10,944][05218] Updated weights for policy 0, policy_version 102 (0.0009) -[2023-10-16 02:46:11,106][05219] Updated weights for policy 1, policy_version 100 (0.0008) -[2023-10-16 02:46:11,308][05218] Updated weights for policy 0, policy_version 112 (0.0007) -[2023-10-16 02:46:11,468][05219] Updated weights for policy 1, policy_version 110 (0.0008) -[2023-10-16 02:46:11,703][05218] Updated weights for policy 0, policy_version 122 (0.0007) -[2023-10-16 02:46:11,841][05219] Updated weights for policy 1, policy_version 120 (0.0009) -[2023-10-16 02:46:12,350][03835] Fps is (10 sec: 19660.6, 60 sec: 11580.0, 300 sec: 11580.0). Total num frames: 262144. Throughput: 0: 1446.6, 1: 1433.5. Samples: 65200. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-16 02:46:12,351][03835] Avg episode reward: [(0, '2.271'), (1, '2.050')] -[2023-10-16 02:46:12,351][04766] Saving new best policy, reward=2.271! -[2023-10-16 02:46:12,352][04891] Saving new best policy, reward=2.050! -[2023-10-16 02:46:15,638][05218] Updated weights for policy 0, policy_version 132 (0.0007) -[2023-10-16 02:46:15,859][05219] Updated weights for policy 1, policy_version 130 (0.0009) -[2023-10-16 02:46:16,019][05218] Updated weights for policy 0, policy_version 142 (0.0010) -[2023-10-16 02:46:16,224][05219] Updated weights for policy 1, policy_version 140 (0.0007) -[2023-10-16 02:46:16,391][05218] Updated weights for policy 0, policy_version 152 (0.0008) -[2023-10-16 02:46:16,581][05219] Updated weights for policy 1, policy_version 150 (0.0009) -[2023-10-16 02:46:16,945][05219] Updated weights for policy 1, policy_version 160 (0.0010) -[2023-10-16 02:46:17,350][03835] Fps is (10 sec: 19661.7, 60 sec: 11856.3, 300 sec: 11856.3). Total num frames: 327680. Throughput: 0: 1545.3, 1: 1544.9. Samples: 85406. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:46:17,351][03835] Avg episode reward: [(0, '2.520'), (1, '2.340')] -[2023-10-16 02:46:17,351][04766] Saving new best policy, reward=2.520! -[2023-10-16 02:46:17,351][04891] Saving new best policy, reward=2.340! -[2023-10-16 02:46:20,079][05218] Updated weights for policy 0, policy_version 162 (0.0008) -[2023-10-16 02:46:20,454][05218] Updated weights for policy 0, policy_version 172 (0.0011) -[2023-10-16 02:46:20,577][05219] Updated weights for policy 1, policy_version 170 (0.0008) -[2023-10-16 02:46:20,832][05218] Updated weights for policy 0, policy_version 182 (0.0011) -[2023-10-16 02:46:20,938][05219] Updated weights for policy 1, policy_version 180 (0.0008) -[2023-10-16 02:46:21,203][05218] Updated weights for policy 0, policy_version 192 (0.0008) -[2023-10-16 02:46:21,292][05219] Updated weights for policy 1, policy_version 190 (0.0009) -[2023-10-16 02:46:22,350][03835] Fps is (10 sec: 13106.9, 60 sec: 12047.8, 300 sec: 12047.8). Total num frames: 393216. Throughput: 0: 1631.7, 1: 1622.4. Samples: 106206. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:46:22,351][03835] Avg episode reward: [(0, '2.510'), (1, '2.670')] -[2023-10-16 02:46:22,360][04891] Saving new best policy, reward=2.670! -[2023-10-16 02:46:25,077][05219] Updated weights for policy 1, policy_version 200 (0.0008) -[2023-10-16 02:46:25,101][05218] Updated weights for policy 0, policy_version 202 (0.0008) -[2023-10-16 02:46:25,428][05219] Updated weights for policy 1, policy_version 210 (0.0007) -[2023-10-16 02:46:25,481][05218] Updated weights for policy 0, policy_version 212 (0.0007) -[2023-10-16 02:46:25,785][05219] Updated weights for policy 1, policy_version 220 (0.0008) -[2023-10-16 02:46:25,860][05218] Updated weights for policy 0, policy_version 222 (0.0008) -[2023-10-16 02:46:27,350][03835] Fps is (10 sec: 13106.9, 60 sec: 12188.6, 300 sec: 12188.6). Total num frames: 458752. Throughput: 0: 1557.4, 1: 1562.2. Samples: 117414. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-16 02:46:27,351][03835] Avg episode reward: [(0, '2.540'), (1, '2.630')] -[2023-10-16 02:46:27,353][04766] Saving new best policy, reward=2.540! -[2023-10-16 02:46:29,583][05218] Updated weights for policy 0, policy_version 232 (0.0008) -[2023-10-16 02:46:29,627][05219] Updated weights for policy 1, policy_version 230 (0.0008) -[2023-10-16 02:46:29,949][05218] Updated weights for policy 0, policy_version 242 (0.0008) -[2023-10-16 02:46:29,984][05219] Updated weights for policy 1, policy_version 240 (0.0007) -[2023-10-16 02:46:30,317][05218] Updated weights for policy 0, policy_version 252 (0.0009) -[2023-10-16 02:46:30,358][05219] Updated weights for policy 1, policy_version 250 (0.0008) -[2023-10-16 02:46:32,350][03835] Fps is (10 sec: 13107.3, 60 sec: 12296.3, 300 sec: 12296.3). Total num frames: 524288. Throughput: 0: 1616.7, 1: 1609.4. Samples: 137556. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-16 02:46:32,351][03835] Avg episode reward: [(0, '2.490'), (1, '2.700')] -[2023-10-16 02:46:32,353][04891] Saving new best policy, reward=2.700! -[2023-10-16 02:46:34,163][05219] Updated weights for policy 1, policy_version 260 (0.0008) -[2023-10-16 02:46:34,272][05218] Updated weights for policy 0, policy_version 262 (0.0008) -[2023-10-16 02:46:34,525][05219] Updated weights for policy 1, policy_version 270 (0.0008) -[2023-10-16 02:46:34,651][05218] Updated weights for policy 0, policy_version 272 (0.0009) -[2023-10-16 02:46:34,884][05219] Updated weights for policy 1, policy_version 280 (0.0009) -[2023-10-16 02:46:35,038][05218] Updated weights for policy 0, policy_version 282 (0.0009) -[2023-10-16 02:46:37,351][03835] Fps is (10 sec: 13106.9, 60 sec: 12381.4, 300 sec: 12381.4). Total num frames: 589824. Throughput: 0: 1725.7, 1: 1728.5. Samples: 159626. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-16 02:46:37,352][03835] Avg episode reward: [(0, '2.380'), (1, '2.130')] -[2023-10-16 02:46:38,848][05219] Updated weights for policy 1, policy_version 290 (0.0008) -[2023-10-16 02:46:38,888][05218] Updated weights for policy 0, policy_version 292 (0.0008) -[2023-10-16 02:46:39,220][05219] Updated weights for policy 1, policy_version 300 (0.0009) -[2023-10-16 02:46:39,252][05218] Updated weights for policy 0, policy_version 302 (0.0007) -[2023-10-16 02:46:39,584][05219] Updated weights for policy 1, policy_version 310 (0.0008) -[2023-10-16 02:46:39,631][05218] Updated weights for policy 0, policy_version 312 (0.0007) -[2023-10-16 02:46:39,957][05219] Updated weights for policy 1, policy_version 320 (0.0007) -[2023-10-16 02:46:42,350][03835] Fps is (10 sec: 13107.5, 60 sec: 12450.4, 300 sec: 12450.4). Total num frames: 655360. Throughput: 0: 1698.1, 1: 1692.3. Samples: 169220. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-16 02:46:42,351][03835] Avg episode reward: [(0, '2.300'), (1, '2.070')] -[2023-10-16 02:46:43,452][05218] Updated weights for policy 0, policy_version 322 (0.0007) -[2023-10-16 02:46:43,820][05219] Updated weights for policy 1, policy_version 330 (0.0009) -[2023-10-16 02:46:43,825][05218] Updated weights for policy 0, policy_version 332 (0.0008) -[2023-10-16 02:46:44,182][05219] Updated weights for policy 1, policy_version 340 (0.0009) -[2023-10-16 02:46:44,204][05218] Updated weights for policy 0, policy_version 342 (0.0008) -[2023-10-16 02:46:44,548][05219] Updated weights for policy 1, policy_version 350 (0.0008) -[2023-10-16 02:46:44,573][05218] Updated weights for policy 0, policy_version 352 (0.0009) -[2023-10-16 02:46:47,350][03835] Fps is (10 sec: 13107.6, 60 sec: 12507.4, 300 sec: 12507.4). Total num frames: 720896. Throughput: 0: 1755.2, 1: 1744.8. Samples: 191216. Policy #0 lag: (min: 26.0, avg: 32.2, max: 58.0) -[2023-10-16 02:46:47,351][03835] Avg episode reward: [(0, '2.350'), (1, '2.320')] -[2023-10-16 02:46:48,382][05219] Updated weights for policy 1, policy_version 360 (0.0007) -[2023-10-16 02:46:48,465][05218] Updated weights for policy 0, policy_version 362 (0.0009) -[2023-10-16 02:46:48,759][05219] Updated weights for policy 1, policy_version 370 (0.0008) -[2023-10-16 02:46:48,839][05218] Updated weights for policy 0, policy_version 372 (0.0009) -[2023-10-16 02:46:49,118][05219] Updated weights for policy 1, policy_version 380 (0.0007) -[2023-10-16 02:46:49,214][05218] Updated weights for policy 0, policy_version 382 (0.0008) -[2023-10-16 02:46:52,350][03835] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 12555.2). Total num frames: 786432. Throughput: 0: 1779.3, 1: 1759.6. Samples: 213142. Policy #0 lag: (min: 31.0, avg: 36.2, max: 63.0) -[2023-10-16 02:46:52,351][03835] Avg episode reward: [(0, '2.440'), (1, '2.350')] -[2023-10-16 02:46:52,937][05218] Updated weights for policy 0, policy_version 392 (0.0007) -[2023-10-16 02:46:52,989][05219] Updated weights for policy 1, policy_version 390 (0.0007) -[2023-10-16 02:46:53,305][05218] Updated weights for policy 0, policy_version 402 (0.0009) -[2023-10-16 02:46:53,349][05219] Updated weights for policy 1, policy_version 400 (0.0008) -[2023-10-16 02:46:53,677][05218] Updated weights for policy 0, policy_version 412 (0.0009) -[2023-10-16 02:46:53,712][05219] Updated weights for policy 1, policy_version 410 (0.0008) -[2023-10-16 02:46:57,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.6, 300 sec: 12596.1). Total num frames: 851968. Throughput: 0: 1753.6, 1: 1746.4. Samples: 222704. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-16 02:46:57,351][03835] Avg episode reward: [(0, '2.420'), (1, '2.450')] -[2023-10-16 02:46:57,481][05218] Updated weights for policy 0, policy_version 422 (0.0008) -[2023-10-16 02:46:57,491][05219] Updated weights for policy 1, policy_version 420 (0.0009) -[2023-10-16 02:46:57,855][05218] Updated weights for policy 0, policy_version 432 (0.0008) -[2023-10-16 02:46:57,862][05219] Updated weights for policy 1, policy_version 430 (0.0007) -[2023-10-16 02:46:58,223][05219] Updated weights for policy 1, policy_version 440 (0.0008) -[2023-10-16 02:46:58,226][05218] Updated weights for policy 0, policy_version 442 (0.0009) -[2023-10-16 02:47:01,870][05219] Updated weights for policy 1, policy_version 450 (0.0007) -[2023-10-16 02:47:02,111][05218] Updated weights for policy 0, policy_version 452 (0.0009) -[2023-10-16 02:47:02,235][05219] Updated weights for policy 1, policy_version 460 (0.0008) -[2023-10-16 02:47:02,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 12631.2). Total num frames: 917504. Throughput: 0: 1781.1, 1: 1768.0. Samples: 245116. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-16 02:47:02,352][03835] Avg episode reward: [(0, '2.580'), (1, '2.510')] -[2023-10-16 02:47:02,490][05218] Updated weights for policy 0, policy_version 462 (0.0009) -[2023-10-16 02:47:02,609][05219] Updated weights for policy 1, policy_version 470 (0.0008) -[2023-10-16 02:47:02,859][05218] Updated weights for policy 0, policy_version 472 (0.0009) -[2023-10-16 02:47:02,967][05219] Updated weights for policy 1, policy_version 480 (0.0008) -[2023-10-16 02:47:03,164][04766] Saving new best policy, reward=2.580! -[2023-10-16 02:47:06,616][05218] Updated weights for policy 0, policy_version 482 (0.0009) -[2023-10-16 02:47:06,967][05219] Updated weights for policy 1, policy_version 490 (0.0009) -[2023-10-16 02:47:06,998][05218] Updated weights for policy 0, policy_version 492 (0.0009) -[2023-10-16 02:47:07,334][05219] Updated weights for policy 1, policy_version 500 (0.0009) -[2023-10-16 02:47:07,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.6, 300 sec: 12661.9). Total num frames: 983040. Throughput: 0: 1775.1, 1: 1768.7. Samples: 265676. Policy #0 lag: (min: 1.0, avg: 6.4, max: 33.0) -[2023-10-16 02:47:07,351][03835] Avg episode reward: [(0, '2.740'), (1, '2.660')] -[2023-10-16 02:47:07,367][05218] Updated weights for policy 0, policy_version 502 (0.0009) -[2023-10-16 02:47:07,701][05219] Updated weights for policy 1, policy_version 510 (0.0007) -[2023-10-16 02:47:07,743][05218] Updated weights for policy 0, policy_version 512 (0.0007) -[2023-10-16 02:47:07,744][04766] Saving new best policy, reward=2.740! -[2023-10-16 02:47:11,472][05219] Updated weights for policy 1, policy_version 520 (0.0008) -[2023-10-16 02:47:11,539][05218] Updated weights for policy 0, policy_version 522 (0.0009) -[2023-10-16 02:47:11,841][05219] Updated weights for policy 1, policy_version 530 (0.0007) -[2023-10-16 02:47:11,921][05218] Updated weights for policy 0, policy_version 532 (0.0009) -[2023-10-16 02:47:12,207][05219] Updated weights for policy 1, policy_version 540 (0.0008) -[2023-10-16 02:47:12,294][05218] Updated weights for policy 0, policy_version 542 (0.0009) -[2023-10-16 02:47:12,350][03835] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12688.8). Total num frames: 1048576. Throughput: 0: 1781.0, 1: 1757.3. Samples: 276638. Policy #0 lag: (min: 26.0, avg: 39.8, max: 58.0) -[2023-10-16 02:47:12,351][03835] Avg episode reward: [(0, '2.710'), (1, '2.680')] -[2023-10-16 02:47:15,993][05219] Updated weights for policy 1, policy_version 550 (0.0008) -[2023-10-16 02:47:16,008][05218] Updated weights for policy 0, policy_version 552 (0.0008) -[2023-10-16 02:47:16,357][05219] Updated weights for policy 1, policy_version 560 (0.0008) -[2023-10-16 02:47:16,372][05218] Updated weights for policy 0, policy_version 562 (0.0007) -[2023-10-16 02:47:16,716][05219] Updated weights for policy 1, policy_version 570 (0.0009) -[2023-10-16 02:47:16,757][05218] Updated weights for policy 0, policy_version 572 (0.0008) -[2023-10-16 02:47:17,350][03835] Fps is (10 sec: 19660.6, 60 sec: 14199.4, 300 sec: 13460.5). Total num frames: 1179648. Throughput: 0: 1785.4, 1: 1777.0. Samples: 297862. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:47:17,351][03835] Avg episode reward: [(0, '2.770'), (1, '2.900')] -[2023-10-16 02:47:17,352][04766] Saving new best policy, reward=2.770! -[2023-10-16 02:47:17,352][04891] Saving new best policy, reward=2.900! -[2023-10-16 02:47:20,360][05218] Updated weights for policy 0, policy_version 582 (0.0008) -[2023-10-16 02:47:20,474][05219] Updated weights for policy 1, policy_version 580 (0.0009) -[2023-10-16 02:47:20,735][05218] Updated weights for policy 0, policy_version 592 (0.0010) -[2023-10-16 02:47:20,845][05219] Updated weights for policy 1, policy_version 590 (0.0007) -[2023-10-16 02:47:21,109][05218] Updated weights for policy 0, policy_version 602 (0.0009) -[2023-10-16 02:47:21,214][05219] Updated weights for policy 1, policy_version 600 (0.0008) -[2023-10-16 02:47:22,350][03835] Fps is (10 sec: 19660.6, 60 sec: 14199.5, 300 sec: 13441.4). Total num frames: 1245184. Throughput: 0: 1776.1, 1: 1755.2. Samples: 318530. Policy #0 lag: (min: 17.0, avg: 24.3, max: 49.0) -[2023-10-16 02:47:22,351][03835] Avg episode reward: [(0, '2.550'), (1, '2.870')] -[2023-10-16 02:47:24,835][05218] Updated weights for policy 0, policy_version 612 (0.0007) -[2023-10-16 02:47:25,151][05219] Updated weights for policy 1, policy_version 610 (0.0008) -[2023-10-16 02:47:25,210][05218] Updated weights for policy 0, policy_version 622 (0.0008) -[2023-10-16 02:47:25,519][05219] Updated weights for policy 1, policy_version 620 (0.0008) -[2023-10-16 02:47:25,595][05218] Updated weights for policy 0, policy_version 632 (0.0007) -[2023-10-16 02:47:25,884][05219] Updated weights for policy 1, policy_version 630 (0.0008) -[2023-10-16 02:47:26,251][05219] Updated weights for policy 1, policy_version 640 (0.0008) -[2023-10-16 02:47:27,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13424.3). Total num frames: 1310720. Throughput: 0: 1795.5, 1: 1781.9. Samples: 330200. Policy #0 lag: (min: 28.0, avg: 29.3, max: 52.0) -[2023-10-16 02:47:27,352][03835] Avg episode reward: [(0, '2.320'), (1, '2.840')] -[2023-10-16 02:47:29,437][05218] Updated weights for policy 0, policy_version 642 (0.0008) -[2023-10-16 02:47:29,831][05218] Updated weights for policy 0, policy_version 652 (0.0010) -[2023-10-16 02:47:30,154][05219] Updated weights for policy 1, policy_version 650 (0.0008) -[2023-10-16 02:47:30,203][05218] Updated weights for policy 0, policy_version 662 (0.0008) -[2023-10-16 02:47:30,532][05219] Updated weights for policy 1, policy_version 660 (0.0008) -[2023-10-16 02:47:30,579][05218] Updated weights for policy 0, policy_version 672 (0.0009) -[2023-10-16 02:47:30,896][05219] Updated weights for policy 1, policy_version 670 (0.0007) -[2023-10-16 02:47:32,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13408.9). Total num frames: 1376256. Throughput: 0: 1778.8, 1: 1752.2. Samples: 350110. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:47:32,351][03835] Avg episode reward: [(0, '2.350'), (1, '2.700')] -[2023-10-16 02:47:34,307][05218] Updated weights for policy 0, policy_version 682 (0.0009) -[2023-10-16 02:47:34,638][05219] Updated weights for policy 1, policy_version 680 (0.0007) -[2023-10-16 02:47:34,691][05218] Updated weights for policy 0, policy_version 692 (0.0009) -[2023-10-16 02:47:35,008][05219] Updated weights for policy 1, policy_version 690 (0.0007) -[2023-10-16 02:47:35,066][05218] Updated weights for policy 0, policy_version 702 (0.0009) -[2023-10-16 02:47:35,375][05219] Updated weights for policy 1, policy_version 700 (0.0008) -[2023-10-16 02:47:37,351][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13394.8). Total num frames: 1441792. Throughput: 0: 1783.2, 1: 1758.3. Samples: 372510. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-16 02:47:37,352][03835] Avg episode reward: [(0, '2.490'), (1, '2.670')] -[2023-10-16 02:47:37,363][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000000704_720896.pth... -[2023-10-16 02:47:37,363][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000000704_720896.pth... -[2023-10-16 02:47:38,848][05218] Updated weights for policy 0, policy_version 712 (0.0008) -[2023-10-16 02:47:39,133][05219] Updated weights for policy 1, policy_version 710 (0.0008) -[2023-10-16 02:47:39,211][05218] Updated weights for policy 0, policy_version 722 (0.0008) -[2023-10-16 02:47:39,502][05219] Updated weights for policy 1, policy_version 720 (0.0009) -[2023-10-16 02:47:39,588][05218] Updated weights for policy 0, policy_version 732 (0.0008) -[2023-10-16 02:47:39,873][05219] Updated weights for policy 1, policy_version 730 (0.0008) -[2023-10-16 02:47:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13382.1). Total num frames: 1507328. Throughput: 0: 1785.1, 1: 1760.9. Samples: 382274. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-16 02:47:42,351][03835] Avg episode reward: [(0, '2.490'), (1, '2.800')] -[2023-10-16 02:47:43,213][05218] Updated weights for policy 0, policy_version 742 (0.0009) -[2023-10-16 02:47:43,595][05218] Updated weights for policy 0, policy_version 752 (0.0008) -[2023-10-16 02:47:43,768][05219] Updated weights for policy 1, policy_version 740 (0.0008) -[2023-10-16 02:47:43,963][05218] Updated weights for policy 0, policy_version 762 (0.0007) -[2023-10-16 02:47:44,139][05219] Updated weights for policy 1, policy_version 750 (0.0007) -[2023-10-16 02:47:44,501][05219] Updated weights for policy 1, policy_version 760 (0.0008) -[2023-10-16 02:47:47,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13370.4). Total num frames: 1572864. Throughput: 0: 1786.0, 1: 1757.2. Samples: 404558. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-16 02:47:47,351][03835] Avg episode reward: [(0, '2.410'), (1, '2.720')] -[2023-10-16 02:47:47,805][05218] Updated weights for policy 0, policy_version 772 (0.0007) -[2023-10-16 02:47:48,183][05218] Updated weights for policy 0, policy_version 782 (0.0010) -[2023-10-16 02:47:48,341][05219] Updated weights for policy 1, policy_version 770 (0.0009) -[2023-10-16 02:47:48,555][05218] Updated weights for policy 0, policy_version 792 (0.0008) -[2023-10-16 02:47:48,707][05219] Updated weights for policy 1, policy_version 780 (0.0009) -[2023-10-16 02:47:49,069][05219] Updated weights for policy 1, policy_version 790 (0.0008) -[2023-10-16 02:47:49,442][05219] Updated weights for policy 1, policy_version 800 (0.0007) -[2023-10-16 02:47:52,299][05218] Updated weights for policy 0, policy_version 802 (0.0008) -[2023-10-16 02:47:52,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13359.7). Total num frames: 1638400. Throughput: 0: 1801.6, 1: 1773.5. Samples: 426558. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-16 02:47:52,351][03835] Avg episode reward: [(0, '2.450'), (1, '2.620')] -[2023-10-16 02:47:52,670][05218] Updated weights for policy 0, policy_version 812 (0.0008) -[2023-10-16 02:47:53,051][05218] Updated weights for policy 0, policy_version 822 (0.0008) -[2023-10-16 02:47:53,362][05219] Updated weights for policy 1, policy_version 810 (0.0008) -[2023-10-16 02:47:53,418][05218] Updated weights for policy 0, policy_version 832 (0.0008) -[2023-10-16 02:47:53,721][05219] Updated weights for policy 1, policy_version 820 (0.0009) -[2023-10-16 02:47:54,088][05219] Updated weights for policy 1, policy_version 830 (0.0007) -[2023-10-16 02:47:57,105][05218] Updated weights for policy 0, policy_version 842 (0.0009) -[2023-10-16 02:47:57,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13349.8). Total num frames: 1703936. Throughput: 0: 1787.9, 1: 1763.8. Samples: 436464. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-16 02:47:57,351][03835] Avg episode reward: [(0, '2.660'), (1, '2.540')] -[2023-10-16 02:47:57,484][05218] Updated weights for policy 0, policy_version 852 (0.0008) -[2023-10-16 02:47:57,847][05218] Updated weights for policy 0, policy_version 862 (0.0007) -[2023-10-16 02:47:57,881][05219] Updated weights for policy 1, policy_version 840 (0.0008) -[2023-10-16 02:47:58,236][05219] Updated weights for policy 1, policy_version 850 (0.0010) -[2023-10-16 02:47:58,613][05219] Updated weights for policy 1, policy_version 860 (0.0009) -[2023-10-16 02:48:01,468][05218] Updated weights for policy 0, policy_version 872 (0.0010) -[2023-10-16 02:48:01,844][05218] Updated weights for policy 0, policy_version 882 (0.0008) -[2023-10-16 02:48:02,222][05218] Updated weights for policy 0, policy_version 892 (0.0007) -[2023-10-16 02:48:02,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13340.6). Total num frames: 1769472. Throughput: 0: 1800.6, 1: 1768.7. Samples: 458484. Policy #0 lag: (min: 23.0, avg: 39.3, max: 40.0) -[2023-10-16 02:48:02,352][03835] Avg episode reward: [(0, '2.620'), (1, '2.300')] -[2023-10-16 02:48:02,416][05219] Updated weights for policy 1, policy_version 870 (0.0009) -[2023-10-16 02:48:02,788][05219] Updated weights for policy 1, policy_version 880 (0.0008) -[2023-10-16 02:48:03,165][05219] Updated weights for policy 1, policy_version 890 (0.0007) -[2023-10-16 02:48:06,028][05218] Updated weights for policy 0, policy_version 902 (0.0008) -[2023-10-16 02:48:06,410][05218] Updated weights for policy 0, policy_version 912 (0.0008) -[2023-10-16 02:48:06,766][05219] Updated weights for policy 1, policy_version 900 (0.0008) -[2023-10-16 02:48:06,781][05218] Updated weights for policy 0, policy_version 922 (0.0007) -[2023-10-16 02:48:07,127][05219] Updated weights for policy 1, policy_version 910 (0.0009) -[2023-10-16 02:48:07,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 13570.2). Total num frames: 1867776. Throughput: 0: 1781.9, 1: 1785.7. Samples: 479072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:48:07,351][03835] Avg episode reward: [(0, '2.600'), (1, '2.360')] -[2023-10-16 02:48:07,492][05219] Updated weights for policy 1, policy_version 920 (0.0010) -[2023-10-16 02:48:10,602][05218] Updated weights for policy 0, policy_version 932 (0.0007) -[2023-10-16 02:48:10,976][05218] Updated weights for policy 0, policy_version 942 (0.0008) -[2023-10-16 02:48:11,178][05219] Updated weights for policy 1, policy_version 930 (0.0007) -[2023-10-16 02:48:11,357][05218] Updated weights for policy 0, policy_version 952 (0.0007) -[2023-10-16 02:48:11,536][05219] Updated weights for policy 1, policy_version 940 (0.0008) -[2023-10-16 02:48:11,902][05219] Updated weights for policy 1, policy_version 950 (0.0007) -[2023-10-16 02:48:12,270][05219] Updated weights for policy 1, policy_version 960 (0.0007) -[2023-10-16 02:48:12,350][03835] Fps is (10 sec: 19661.1, 60 sec: 15291.7, 300 sec: 13783.7). Total num frames: 1966080. Throughput: 0: 1797.1, 1: 1777.2. Samples: 491042. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:48:12,351][03835] Avg episode reward: [(0, '2.590'), (1, '2.370')] -[2023-10-16 02:48:15,231][05218] Updated weights for policy 0, policy_version 962 (0.0007) -[2023-10-16 02:48:15,644][05218] Updated weights for policy 0, policy_version 972 (0.0008) -[2023-10-16 02:48:16,023][05218] Updated weights for policy 0, policy_version 982 (0.0009) -[2023-10-16 02:48:16,148][05219] Updated weights for policy 1, policy_version 970 (0.0010) -[2023-10-16 02:48:16,393][05218] Updated weights for policy 0, policy_version 992 (0.0009) -[2023-10-16 02:48:16,511][05219] Updated weights for policy 1, policy_version 980 (0.0008) -[2023-10-16 02:48:16,877][05219] Updated weights for policy 1, policy_version 990 (0.0010) -[2023-10-16 02:48:17,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13760.8). Total num frames: 2031616. Throughput: 0: 1783.4, 1: 1798.9. Samples: 511314. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-16 02:48:17,351][03835] Avg episode reward: [(0, '2.150'), (1, '2.420')] -[2023-10-16 02:48:20,208][05218] Updated weights for policy 0, policy_version 1002 (0.0008) -[2023-10-16 02:48:20,583][05218] Updated weights for policy 0, policy_version 1012 (0.0009) -[2023-10-16 02:48:20,671][05219] Updated weights for policy 1, policy_version 1000 (0.0008) -[2023-10-16 02:48:20,958][05218] Updated weights for policy 0, policy_version 1022 (0.0008) -[2023-10-16 02:48:21,032][05219] Updated weights for policy 1, policy_version 1010 (0.0007) -[2023-10-16 02:48:21,403][05219] Updated weights for policy 1, policy_version 1020 (0.0008) -[2023-10-16 02:48:22,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13739.4). Total num frames: 2097152. Throughput: 0: 1778.0, 1: 1772.1. Samples: 532264. Policy #0 lag: (min: 13.0, avg: 16.2, max: 45.0) -[2023-10-16 02:48:22,351][03835] Avg episode reward: [(0, '2.370'), (1, '2.430')] -[2023-10-16 02:48:24,722][05218] Updated weights for policy 0, policy_version 1032 (0.0007) -[2023-10-16 02:48:25,102][05218] Updated weights for policy 0, policy_version 1042 (0.0009) -[2023-10-16 02:48:25,148][05219] Updated weights for policy 1, policy_version 1030 (0.0008) -[2023-10-16 02:48:25,476][05218] Updated weights for policy 0, policy_version 1052 (0.0008) -[2023-10-16 02:48:25,515][05219] Updated weights for policy 1, policy_version 1040 (0.0007) -[2023-10-16 02:48:25,869][05219] Updated weights for policy 1, policy_version 1050 (0.0010) -[2023-10-16 02:48:27,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13719.3). Total num frames: 2162688. Throughput: 0: 1783.5, 1: 1800.5. Samples: 543554. Policy #0 lag: (min: 3.0, avg: 3.2, max: 13.0) -[2023-10-16 02:48:27,351][03835] Avg episode reward: [(0, '2.310'), (1, '2.460')] -[2023-10-16 02:48:29,390][05218] Updated weights for policy 0, policy_version 1062 (0.0009) -[2023-10-16 02:48:29,764][05218] Updated weights for policy 0, policy_version 1072 (0.0008) -[2023-10-16 02:48:29,817][05219] Updated weights for policy 1, policy_version 1060 (0.0009) -[2023-10-16 02:48:30,146][05218] Updated weights for policy 0, policy_version 1082 (0.0008) -[2023-10-16 02:48:30,185][05219] Updated weights for policy 1, policy_version 1070 (0.0008) -[2023-10-16 02:48:30,551][05219] Updated weights for policy 1, policy_version 1080 (0.0008) -[2023-10-16 02:48:32,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13700.5). Total num frames: 2228224. Throughput: 0: 1768.3, 1: 1771.0. Samples: 563826. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:48:32,351][03835] Avg episode reward: [(0, '2.400'), (1, '2.410')] -[2023-10-16 02:48:33,879][05218] Updated weights for policy 0, policy_version 1092 (0.0008) -[2023-10-16 02:48:34,251][05218] Updated weights for policy 0, policy_version 1102 (0.0009) -[2023-10-16 02:48:34,359][05219] Updated weights for policy 1, policy_version 1090 (0.0009) -[2023-10-16 02:48:34,625][05218] Updated weights for policy 0, policy_version 1112 (0.0009) -[2023-10-16 02:48:34,715][05219] Updated weights for policy 1, policy_version 1100 (0.0008) -[2023-10-16 02:48:35,084][05219] Updated weights for policy 1, policy_version 1110 (0.0009) -[2023-10-16 02:48:35,444][05219] Updated weights for policy 1, policy_version 1120 (0.0008) -[2023-10-16 02:48:37,351][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13682.8). Total num frames: 2293760. Throughput: 0: 1776.1, 1: 1772.8. Samples: 586262. Policy #0 lag: (min: 6.0, avg: 6.2, max: 16.0) -[2023-10-16 02:48:37,352][03835] Avg episode reward: [(0, '2.330'), (1, '2.560')] -[2023-10-16 02:48:38,305][05218] Updated weights for policy 0, policy_version 1122 (0.0009) -[2023-10-16 02:48:38,671][05218] Updated weights for policy 0, policy_version 1132 (0.0009) -[2023-10-16 02:48:39,052][05218] Updated weights for policy 0, policy_version 1142 (0.0008) -[2023-10-16 02:48:39,173][05219] Updated weights for policy 1, policy_version 1130 (0.0009) -[2023-10-16 02:48:39,425][05218] Updated weights for policy 0, policy_version 1152 (0.0007) -[2023-10-16 02:48:39,544][05219] Updated weights for policy 1, policy_version 1140 (0.0009) -[2023-10-16 02:48:39,911][05219] Updated weights for policy 1, policy_version 1150 (0.0007) -[2023-10-16 02:48:42,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 13666.2). Total num frames: 2359296. Throughput: 0: 1778.7, 1: 1775.3. Samples: 596394. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-16 02:48:42,351][03835] Avg episode reward: [(0, '2.450'), (1, '2.610')] -[2023-10-16 02:48:43,160][05218] Updated weights for policy 0, policy_version 1162 (0.0009) -[2023-10-16 02:48:43,524][05218] Updated weights for policy 0, policy_version 1172 (0.0009) -[2023-10-16 02:48:43,801][05219] Updated weights for policy 1, policy_version 1160 (0.0007) -[2023-10-16 02:48:43,898][05218] Updated weights for policy 0, policy_version 1182 (0.0008) -[2023-10-16 02:48:44,160][05219] Updated weights for policy 1, policy_version 1170 (0.0009) -[2023-10-16 02:48:44,523][05219] Updated weights for policy 1, policy_version 1180 (0.0010) -[2023-10-16 02:48:47,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13650.4). Total num frames: 2424832. Throughput: 0: 1777.9, 1: 1776.5. Samples: 618432. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) -[2023-10-16 02:48:47,351][03835] Avg episode reward: [(0, '2.570'), (1, '2.350')] -[2023-10-16 02:48:47,759][05218] Updated weights for policy 0, policy_version 1192 (0.0009) -[2023-10-16 02:48:48,138][05218] Updated weights for policy 0, policy_version 1202 (0.0010) -[2023-10-16 02:48:48,424][05219] Updated weights for policy 1, policy_version 1190 (0.0009) -[2023-10-16 02:48:48,516][05218] Updated weights for policy 0, policy_version 1212 (0.0009) -[2023-10-16 02:48:48,791][05219] Updated weights for policy 1, policy_version 1200 (0.0010) -[2023-10-16 02:48:49,152][05219] Updated weights for policy 1, policy_version 1210 (0.0007) -[2023-10-16 02:48:52,288][05218] Updated weights for policy 0, policy_version 1222 (0.0009) -[2023-10-16 02:48:52,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13635.5). Total num frames: 2490368. Throughput: 0: 1799.4, 1: 1785.7. Samples: 640400. Policy #0 lag: (min: 31.0, avg: 32.8, max: 59.0) -[2023-10-16 02:48:52,351][03835] Avg episode reward: [(0, '2.860'), (1, '2.410')] -[2023-10-16 02:48:52,666][05218] Updated weights for policy 0, policy_version 1232 (0.0009) -[2023-10-16 02:48:52,867][05219] Updated weights for policy 1, policy_version 1220 (0.0008) -[2023-10-16 02:48:53,033][05218] Updated weights for policy 0, policy_version 1242 (0.0008) -[2023-10-16 02:48:53,230][05219] Updated weights for policy 1, policy_version 1230 (0.0008) -[2023-10-16 02:48:53,261][04766] Saving new best policy, reward=2.860! -[2023-10-16 02:48:53,587][05219] Updated weights for policy 1, policy_version 1240 (0.0008) -[2023-10-16 02:48:56,753][05218] Updated weights for policy 0, policy_version 1252 (0.0008) -[2023-10-16 02:48:57,132][05218] Updated weights for policy 0, policy_version 1262 (0.0010) -[2023-10-16 02:48:57,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13621.5). Total num frames: 2555904. Throughput: 0: 1775.1, 1: 1765.9. Samples: 650386. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:48:57,351][03835] Avg episode reward: [(0, '2.770'), (1, '2.360')] -[2023-10-16 02:48:57,453][05219] Updated weights for policy 1, policy_version 1250 (0.0007) -[2023-10-16 02:48:57,510][05218] Updated weights for policy 0, policy_version 1272 (0.0009) -[2023-10-16 02:48:57,826][05219] Updated weights for policy 1, policy_version 1260 (0.0008) -[2023-10-16 02:48:58,185][05219] Updated weights for policy 1, policy_version 1270 (0.0009) -[2023-10-16 02:48:58,556][05219] Updated weights for policy 1, policy_version 1280 (0.0010) -[2023-10-16 02:49:01,236][05218] Updated weights for policy 0, policy_version 1282 (0.0009) -[2023-10-16 02:49:01,624][05218] Updated weights for policy 0, policy_version 1292 (0.0009) -[2023-10-16 02:49:02,009][05218] Updated weights for policy 0, policy_version 1302 (0.0008) -[2023-10-16 02:49:02,331][05219] Updated weights for policy 1, policy_version 1290 (0.0009) -[2023-10-16 02:49:02,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13608.1). Total num frames: 2621440. Throughput: 0: 1803.1, 1: 1776.6. Samples: 672398. Policy #0 lag: (min: 31.0, avg: 32.8, max: 59.0) -[2023-10-16 02:49:02,351][03835] Avg episode reward: [(0, '2.670'), (1, '2.400')] -[2023-10-16 02:49:02,392][05218] Updated weights for policy 0, policy_version 1312 (0.0008) -[2023-10-16 02:49:02,707][05219] Updated weights for policy 1, policy_version 1300 (0.0007) -[2023-10-16 02:49:03,077][05219] Updated weights for policy 1, policy_version 1310 (0.0009) -[2023-10-16 02:49:05,995][05218] Updated weights for policy 0, policy_version 1322 (0.0008) -[2023-10-16 02:49:06,376][05218] Updated weights for policy 0, policy_version 1332 (0.0009) -[2023-10-16 02:49:06,756][05218] Updated weights for policy 0, policy_version 1342 (0.0007) -[2023-10-16 02:49:07,139][05219] Updated weights for policy 1, policy_version 1320 (0.0010) -[2023-10-16 02:49:07,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13761.3). Total num frames: 2719744. Throughput: 0: 1782.6, 1: 1788.8. Samples: 692980. Policy #0 lag: (min: 28.0, avg: 31.2, max: 60.0) -[2023-10-16 02:49:07,351][03835] Avg episode reward: [(0, '2.440'), (1, '2.340')] -[2023-10-16 02:49:07,512][05219] Updated weights for policy 1, policy_version 1330 (0.0008) -[2023-10-16 02:49:07,875][05219] Updated weights for policy 1, policy_version 1340 (0.0009) -[2023-10-16 02:49:10,514][05218] Updated weights for policy 0, policy_version 1352 (0.0007) -[2023-10-16 02:49:10,900][05218] Updated weights for policy 0, policy_version 1362 (0.0009) -[2023-10-16 02:49:11,268][05218] Updated weights for policy 0, policy_version 1372 (0.0008) -[2023-10-16 02:49:11,543][05219] Updated weights for policy 1, policy_version 1350 (0.0008) -[2023-10-16 02:49:11,912][05219] Updated weights for policy 1, policy_version 1360 (0.0007) -[2023-10-16 02:49:12,278][05219] Updated weights for policy 1, policy_version 1370 (0.0008) -[2023-10-16 02:49:12,350][03835] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13745.1). Total num frames: 2785280. Throughput: 0: 1804.5, 1: 1767.7. Samples: 704302. Policy #0 lag: (min: 10.0, avg: 10.3, max: 22.0) -[2023-10-16 02:49:12,351][03835] Avg episode reward: [(0, '2.230'), (1, '2.390')] -[2023-10-16 02:49:14,942][05218] Updated weights for policy 0, policy_version 1382 (0.0008) -[2023-10-16 02:49:15,320][05218] Updated weights for policy 0, policy_version 1392 (0.0007) -[2023-10-16 02:49:15,699][05218] Updated weights for policy 0, policy_version 1402 (0.0008) -[2023-10-16 02:49:16,021][05219] Updated weights for policy 1, policy_version 1380 (0.0008) -[2023-10-16 02:49:16,396][05219] Updated weights for policy 1, policy_version 1390 (0.0008) -[2023-10-16 02:49:16,755][05219] Updated weights for policy 1, policy_version 1400 (0.0009) -[2023-10-16 02:49:17,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13887.6). Total num frames: 2883584. Throughput: 0: 1794.7, 1: 1793.9. Samples: 725314. Policy #0 lag: (min: 10.0, avg: 10.5, max: 25.0) -[2023-10-16 02:49:17,352][03835] Avg episode reward: [(0, '2.260'), (1, '2.270')] -[2023-10-16 02:49:19,398][05218] Updated weights for policy 0, policy_version 1412 (0.0008) -[2023-10-16 02:49:19,770][05218] Updated weights for policy 0, policy_version 1422 (0.0010) -[2023-10-16 02:49:20,146][05218] Updated weights for policy 0, policy_version 1432 (0.0008) -[2023-10-16 02:49:20,347][05219] Updated weights for policy 1, policy_version 1410 (0.0007) -[2023-10-16 02:49:20,713][05219] Updated weights for policy 1, policy_version 1420 (0.0010) -[2023-10-16 02:49:21,083][05219] Updated weights for policy 1, policy_version 1430 (0.0010) -[2023-10-16 02:49:21,451][05219] Updated weights for policy 1, policy_version 1440 (0.0010) -[2023-10-16 02:49:22,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13869.2). Total num frames: 2949120. Throughput: 0: 1794.7, 1: 1775.5. Samples: 746922. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-16 02:49:22,351][03835] Avg episode reward: [(0, '2.600'), (1, '2.400')] -[2023-10-16 02:49:23,880][05218] Updated weights for policy 0, policy_version 1442 (0.0008) -[2023-10-16 02:49:24,251][05218] Updated weights for policy 0, policy_version 1452 (0.0011) -[2023-10-16 02:49:24,625][05218] Updated weights for policy 0, policy_version 1462 (0.0009) -[2023-10-16 02:49:25,000][05218] Updated weights for policy 0, policy_version 1472 (0.0008) -[2023-10-16 02:49:25,291][05219] Updated weights for policy 1, policy_version 1450 (0.0007) -[2023-10-16 02:49:25,650][05219] Updated weights for policy 1, policy_version 1460 (0.0009) -[2023-10-16 02:49:26,017][05219] Updated weights for policy 1, policy_version 1470 (0.0008) -[2023-10-16 02:49:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13851.7). Total num frames: 3014656. Throughput: 0: 1784.6, 1: 1795.5. Samples: 757500. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:49:27,351][03835] Avg episode reward: [(0, '2.500'), (1, '2.390')] -[2023-10-16 02:49:28,768][05218] Updated weights for policy 0, policy_version 1482 (0.0008) -[2023-10-16 02:49:29,148][05218] Updated weights for policy 0, policy_version 1492 (0.0010) -[2023-10-16 02:49:29,521][05218] Updated weights for policy 0, policy_version 1502 (0.0008) -[2023-10-16 02:49:29,745][05219] Updated weights for policy 1, policy_version 1480 (0.0008) -[2023-10-16 02:49:30,113][05219] Updated weights for policy 1, policy_version 1490 (0.0009) -[2023-10-16 02:49:30,478][05219] Updated weights for policy 1, policy_version 1500 (0.0009) -[2023-10-16 02:49:32,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13835.0). Total num frames: 3080192. Throughput: 0: 1788.2, 1: 1777.8. Samples: 778902. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:49:32,351][03835] Avg episode reward: [(0, '2.450'), (1, '2.390')] -[2023-10-16 02:49:33,163][05218] Updated weights for policy 0, policy_version 1512 (0.0009) -[2023-10-16 02:49:33,525][05218] Updated weights for policy 0, policy_version 1522 (0.0010) -[2023-10-16 02:49:33,900][05218] Updated weights for policy 0, policy_version 1532 (0.0009) -[2023-10-16 02:49:34,125][05219] Updated weights for policy 1, policy_version 1510 (0.0009) -[2023-10-16 02:49:34,498][05219] Updated weights for policy 1, policy_version 1520 (0.0009) -[2023-10-16 02:49:34,865][05219] Updated weights for policy 1, policy_version 1530 (0.0008) -[2023-10-16 02:49:37,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13819.0). Total num frames: 3145728. Throughput: 0: 1797.5, 1: 1777.4. Samples: 801268. Policy #0 lag: (min: 5.0, avg: 5.7, max: 23.0) -[2023-10-16 02:49:37,351][03835] Avg episode reward: [(0, '2.380'), (1, '2.530')] -[2023-10-16 02:49:37,359][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000001536_1572864.pth... -[2023-10-16 02:49:37,559][05218] Updated weights for policy 0, policy_version 1542 (0.0009) -[2023-10-16 02:49:37,940][05218] Updated weights for policy 0, policy_version 1552 (0.0011) -[2023-10-16 02:49:38,323][05218] Updated weights for policy 0, policy_version 1562 (0.0009) -[2023-10-16 02:49:38,547][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000001568_1605632.pth... -[2023-10-16 02:49:38,771][05219] Updated weights for policy 1, policy_version 1540 (0.0008) -[2023-10-16 02:49:39,145][05219] Updated weights for policy 1, policy_version 1550 (0.0008) -[2023-10-16 02:49:39,506][05219] Updated weights for policy 1, policy_version 1560 (0.0008) -[2023-10-16 02:49:42,081][05218] Updated weights for policy 0, policy_version 1572 (0.0009) -[2023-10-16 02:49:42,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13803.7). Total num frames: 3211264. Throughput: 0: 1792.2, 1: 1782.0. Samples: 811226. Policy #0 lag: (min: 17.0, avg: 32.2, max: 49.0) -[2023-10-16 02:49:42,351][03835] Avg episode reward: [(0, '2.400'), (1, '2.470')] -[2023-10-16 02:49:42,461][05218] Updated weights for policy 0, policy_version 1582 (0.0007) -[2023-10-16 02:49:42,830][05218] Updated weights for policy 0, policy_version 1592 (0.0008) -[2023-10-16 02:49:43,312][05219] Updated weights for policy 1, policy_version 1570 (0.0007) -[2023-10-16 02:49:43,681][05219] Updated weights for policy 1, policy_version 1580 (0.0008) -[2023-10-16 02:49:44,060][05219] Updated weights for policy 1, policy_version 1590 (0.0008) -[2023-10-16 02:49:44,430][05219] Updated weights for policy 1, policy_version 1600 (0.0007) -[2023-10-16 02:49:46,853][05218] Updated weights for policy 0, policy_version 1602 (0.0008) -[2023-10-16 02:49:47,255][05218] Updated weights for policy 0, policy_version 1612 (0.0007) -[2023-10-16 02:49:47,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13789.1). Total num frames: 3276800. Throughput: 0: 1788.4, 1: 1785.1. Samples: 833204. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-16 02:49:47,351][03835] Avg episode reward: [(0, '2.580'), (1, '2.430')] -[2023-10-16 02:49:47,633][05218] Updated weights for policy 0, policy_version 1622 (0.0008) -[2023-10-16 02:49:48,006][05218] Updated weights for policy 0, policy_version 1632 (0.0008) -[2023-10-16 02:49:48,142][05219] Updated weights for policy 1, policy_version 1610 (0.0008) -[2023-10-16 02:49:48,505][05219] Updated weights for policy 1, policy_version 1620 (0.0009) -[2023-10-16 02:49:48,868][05219] Updated weights for policy 1, policy_version 1630 (0.0009) -[2023-10-16 02:49:51,903][05218] Updated weights for policy 0, policy_version 1642 (0.0009) -[2023-10-16 02:49:52,282][05218] Updated weights for policy 0, policy_version 1652 (0.0007) -[2023-10-16 02:49:52,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13775.0). Total num frames: 3342336. Throughput: 0: 1788.0, 1: 1795.3. Samples: 854232. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-16 02:49:52,351][03835] Avg episode reward: [(0, '2.580'), (1, '2.240')] -[2023-10-16 02:49:52,576][05219] Updated weights for policy 1, policy_version 1640 (0.0008) -[2023-10-16 02:49:52,665][05218] Updated weights for policy 0, policy_version 1662 (0.0007) -[2023-10-16 02:49:52,942][05219] Updated weights for policy 1, policy_version 1650 (0.0007) -[2023-10-16 02:49:53,315][05219] Updated weights for policy 1, policy_version 1660 (0.0007) -[2023-10-16 02:49:56,407][05218] Updated weights for policy 0, policy_version 1672 (0.0008) -[2023-10-16 02:49:56,793][05218] Updated weights for policy 0, policy_version 1682 (0.0007) -[2023-10-16 02:49:57,021][05219] Updated weights for policy 1, policy_version 1670 (0.0007) -[2023-10-16 02:49:57,159][05218] Updated weights for policy 0, policy_version 1692 (0.0007) -[2023-10-16 02:49:57,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 13893.8). Total num frames: 3440640. Throughput: 0: 1779.9, 1: 1790.0. Samples: 864944. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:49:57,351][03835] Avg episode reward: [(0, '2.470'), (1, '2.350')] -[2023-10-16 02:49:57,393][05219] Updated weights for policy 1, policy_version 1680 (0.0009) -[2023-10-16 02:49:57,743][05219] Updated weights for policy 1, policy_version 1690 (0.0007) -[2023-10-16 02:50:00,875][05218] Updated weights for policy 0, policy_version 1702 (0.0008) -[2023-10-16 02:50:01,256][05218] Updated weights for policy 0, policy_version 1712 (0.0008) -[2023-10-16 02:50:01,562][05219] Updated weights for policy 1, policy_version 1700 (0.0007) -[2023-10-16 02:50:01,631][05218] Updated weights for policy 0, policy_version 1722 (0.0009) -[2023-10-16 02:50:01,921][05219] Updated weights for policy 1, policy_version 1710 (0.0008) -[2023-10-16 02:50:02,296][05219] Updated weights for policy 1, policy_version 1720 (0.0009) -[2023-10-16 02:50:02,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 13878.3). Total num frames: 3506176. Throughput: 0: 1788.5, 1: 1794.5. Samples: 886544. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:50:02,351][03835] Avg episode reward: [(0, '2.410'), (1, '2.260')] -[2023-10-16 02:50:05,408][05218] Updated weights for policy 0, policy_version 1732 (0.0009) -[2023-10-16 02:50:05,788][05218] Updated weights for policy 0, policy_version 1742 (0.0008) -[2023-10-16 02:50:06,136][05219] Updated weights for policy 1, policy_version 1730 (0.0009) -[2023-10-16 02:50:06,168][05218] Updated weights for policy 0, policy_version 1752 (0.0009) -[2023-10-16 02:50:06,504][05219] Updated weights for policy 1, policy_version 1740 (0.0007) -[2023-10-16 02:50:06,869][05219] Updated weights for policy 1, policy_version 1750 (0.0009) -[2023-10-16 02:50:07,239][05219] Updated weights for policy 1, policy_version 1760 (0.0008) -[2023-10-16 02:50:07,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 13990.5). Total num frames: 3604480. Throughput: 0: 1770.4, 1: 1786.0. Samples: 906960. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:50:07,351][03835] Avg episode reward: [(0, '2.570'), (1, '2.220')] -[2023-10-16 02:50:10,010][05218] Updated weights for policy 0, policy_version 1762 (0.0007) -[2023-10-16 02:50:10,405][05218] Updated weights for policy 0, policy_version 1772 (0.0007) -[2023-10-16 02:50:10,776][05218] Updated weights for policy 0, policy_version 1782 (0.0009) -[2023-10-16 02:50:10,898][05219] Updated weights for policy 1, policy_version 1770 (0.0007) -[2023-10-16 02:50:11,153][05218] Updated weights for policy 0, policy_version 1792 (0.0008) -[2023-10-16 02:50:11,257][05219] Updated weights for policy 1, policy_version 1780 (0.0007) -[2023-10-16 02:50:11,631][05219] Updated weights for policy 1, policy_version 1790 (0.0007) -[2023-10-16 02:50:12,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 13973.7). Total num frames: 3670016. Throughput: 0: 1793.2, 1: 1794.9. Samples: 918968. Policy #0 lag: (min: 8.0, avg: 33.9, max: 40.0) -[2023-10-16 02:50:12,352][03835] Avg episode reward: [(0, '2.480'), (1, '1.970')] -[2023-10-16 02:50:14,968][05218] Updated weights for policy 0, policy_version 1802 (0.0008) -[2023-10-16 02:50:15,339][05218] Updated weights for policy 0, policy_version 1812 (0.0008) -[2023-10-16 02:50:15,431][05219] Updated weights for policy 1, policy_version 1800 (0.0008) -[2023-10-16 02:50:15,721][05218] Updated weights for policy 0, policy_version 1822 (0.0009) -[2023-10-16 02:50:15,789][05219] Updated weights for policy 1, policy_version 1810 (0.0008) -[2023-10-16 02:50:16,160][05219] Updated weights for policy 1, policy_version 1820 (0.0010) -[2023-10-16 02:50:17,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13957.5). Total num frames: 3735552. Throughput: 0: 1764.2, 1: 1789.7. Samples: 938826. Policy #0 lag: (min: 31.0, avg: 32.9, max: 62.0) -[2023-10-16 02:50:17,351][03835] Avg episode reward: [(0, '2.410'), (1, '2.300')] -[2023-10-16 02:50:19,602][05218] Updated weights for policy 0, policy_version 1832 (0.0009) -[2023-10-16 02:50:19,922][05219] Updated weights for policy 1, policy_version 1830 (0.0008) -[2023-10-16 02:50:19,984][05218] Updated weights for policy 0, policy_version 1842 (0.0008) -[2023-10-16 02:50:20,297][05219] Updated weights for policy 1, policy_version 1840 (0.0007) -[2023-10-16 02:50:20,366][05218] Updated weights for policy 0, policy_version 1852 (0.0007) -[2023-10-16 02:50:20,661][05219] Updated weights for policy 1, policy_version 1850 (0.0008) -[2023-10-16 02:50:22,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13941.9). Total num frames: 3801088. Throughput: 0: 1764.1, 1: 1782.1. Samples: 960846. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 02:50:22,352][03835] Avg episode reward: [(0, '2.190'), (1, '2.410')] -[2023-10-16 02:50:24,083][05218] Updated weights for policy 0, policy_version 1862 (0.0008) -[2023-10-16 02:50:24,450][05218] Updated weights for policy 0, policy_version 1872 (0.0008) -[2023-10-16 02:50:24,602][05219] Updated weights for policy 1, policy_version 1860 (0.0009) -[2023-10-16 02:50:24,835][05218] Updated weights for policy 0, policy_version 1882 (0.0009) -[2023-10-16 02:50:24,971][05219] Updated weights for policy 1, policy_version 1870 (0.0008) -[2023-10-16 02:50:25,333][05219] Updated weights for policy 1, policy_version 1880 (0.0007) -[2023-10-16 02:50:27,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13926.9). Total num frames: 3866624. Throughput: 0: 1763.2, 1: 1793.3. Samples: 971268. Policy #0 lag: (min: 26.0, avg: 36.7, max: 58.0) -[2023-10-16 02:50:27,351][03835] Avg episode reward: [(0, '2.510'), (1, '2.500')] -[2023-10-16 02:50:28,468][05218] Updated weights for policy 0, policy_version 1892 (0.0011) -[2023-10-16 02:50:28,843][05218] Updated weights for policy 0, policy_version 1902 (0.0011) -[2023-10-16 02:50:29,156][05219] Updated weights for policy 1, policy_version 1890 (0.0010) -[2023-10-16 02:50:29,217][05218] Updated weights for policy 0, policy_version 1912 (0.0009) -[2023-10-16 02:50:29,522][05219] Updated weights for policy 1, policy_version 1900 (0.0009) -[2023-10-16 02:50:29,879][05219] Updated weights for policy 1, policy_version 1910 (0.0009) -[2023-10-16 02:50:30,253][05219] Updated weights for policy 1, policy_version 1920 (0.0008) -[2023-10-16 02:50:32,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13912.4). Total num frames: 3932160. Throughput: 0: 1773.4, 1: 1775.5. Samples: 992904. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-16 02:50:32,351][03835] Avg episode reward: [(0, '2.550'), (1, '2.320')] -[2023-10-16 02:50:32,862][05218] Updated weights for policy 0, policy_version 1922 (0.0007) -[2023-10-16 02:50:33,238][05218] Updated weights for policy 0, policy_version 1932 (0.0008) -[2023-10-16 02:50:33,611][05218] Updated weights for policy 0, policy_version 1942 (0.0009) -[2023-10-16 02:50:33,989][05218] Updated weights for policy 0, policy_version 1952 (0.0009) -[2023-10-16 02:50:34,127][05219] Updated weights for policy 1, policy_version 1930 (0.0009) -[2023-10-16 02:50:34,493][05219] Updated weights for policy 1, policy_version 1940 (0.0008) -[2023-10-16 02:50:34,859][05219] Updated weights for policy 1, policy_version 1950 (0.0008) -[2023-10-16 02:50:37,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13898.4). Total num frames: 3997696. Throughput: 0: 1800.3, 1: 1777.0. Samples: 1015208. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:50:37,352][03835] Avg episode reward: [(0, '2.620'), (1, '2.520')] -[2023-10-16 02:50:37,898][05218] Updated weights for policy 0, policy_version 1962 (0.0008) -[2023-10-16 02:50:38,280][05218] Updated weights for policy 0, policy_version 1972 (0.0007) -[2023-10-16 02:50:38,637][05219] Updated weights for policy 1, policy_version 1960 (0.0007) -[2023-10-16 02:50:38,650][05218] Updated weights for policy 0, policy_version 1982 (0.0008) -[2023-10-16 02:50:39,006][05219] Updated weights for policy 1, policy_version 1970 (0.0008) -[2023-10-16 02:50:39,375][05219] Updated weights for policy 1, policy_version 1980 (0.0008) -[2023-10-16 02:50:42,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.8). Total num frames: 4063232. Throughput: 0: 1778.7, 1: 1775.8. Samples: 1024898. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:50:42,351][03835] Avg episode reward: [(0, '2.750'), (1, '2.400')] -[2023-10-16 02:50:42,405][05218] Updated weights for policy 0, policy_version 1992 (0.0008) -[2023-10-16 02:50:42,779][05218] Updated weights for policy 0, policy_version 2002 (0.0007) -[2023-10-16 02:50:43,164][05218] Updated weights for policy 0, policy_version 2012 (0.0010) -[2023-10-16 02:50:43,189][05219] Updated weights for policy 1, policy_version 1990 (0.0008) -[2023-10-16 02:50:43,556][05219] Updated weights for policy 1, policy_version 2000 (0.0008) -[2023-10-16 02:50:43,926][05219] Updated weights for policy 1, policy_version 2010 (0.0009) -[2023-10-16 02:50:46,997][05218] Updated weights for policy 0, policy_version 2022 (0.0008) -[2023-10-16 02:50:47,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 4128768. Throughput: 0: 1793.9, 1: 1774.2. Samples: 1047108. Policy #0 lag: (min: 1.0, avg: 5.4, max: 33.0) -[2023-10-16 02:50:47,351][03835] Avg episode reward: [(0, '2.470'), (1, '2.500')] -[2023-10-16 02:50:47,375][05218] Updated weights for policy 0, policy_version 2032 (0.0007) -[2023-10-16 02:50:47,706][05219] Updated weights for policy 1, policy_version 2020 (0.0008) -[2023-10-16 02:50:47,754][05218] Updated weights for policy 0, policy_version 2042 (0.0007) -[2023-10-16 02:50:48,075][05219] Updated weights for policy 1, policy_version 2030 (0.0009) -[2023-10-16 02:50:48,445][05219] Updated weights for policy 1, policy_version 2040 (0.0007) -[2023-10-16 02:50:51,390][05218] Updated weights for policy 0, policy_version 2052 (0.0007) -[2023-10-16 02:50:51,765][05218] Updated weights for policy 0, policy_version 2062 (0.0009) -[2023-10-16 02:50:52,145][05218] Updated weights for policy 0, policy_version 2072 (0.0011) -[2023-10-16 02:50:52,251][05219] Updated weights for policy 1, policy_version 2050 (0.0009) -[2023-10-16 02:50:52,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 4194304. Throughput: 0: 1781.4, 1: 1796.2. Samples: 1067952. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-16 02:50:52,351][03835] Avg episode reward: [(0, '2.570'), (1, '2.050')] -[2023-10-16 02:50:52,605][05219] Updated weights for policy 1, policy_version 2060 (0.0009) -[2023-10-16 02:50:52,969][05219] Updated weights for policy 1, policy_version 2070 (0.0007) -[2023-10-16 02:50:53,338][05219] Updated weights for policy 1, policy_version 2080 (0.0008) -[2023-10-16 02:50:55,865][05218] Updated weights for policy 0, policy_version 2082 (0.0009) -[2023-10-16 02:50:56,239][05218] Updated weights for policy 0, policy_version 2092 (0.0008) -[2023-10-16 02:50:56,616][05218] Updated weights for policy 0, policy_version 2102 (0.0008) -[2023-10-16 02:50:56,998][05218] Updated weights for policy 0, policy_version 2112 (0.0010) -[2023-10-16 02:50:57,181][05219] Updated weights for policy 1, policy_version 2090 (0.0010) -[2023-10-16 02:50:57,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 4292608. Throughput: 0: 1793.4, 1: 1761.2. Samples: 1078926. Policy #0 lag: (min: 26.0, avg: 26.5, max: 41.0) -[2023-10-16 02:50:57,351][03835] Avg episode reward: [(0, '2.380'), (1, '2.290')] -[2023-10-16 02:50:57,556][05219] Updated weights for policy 1, policy_version 2100 (0.0010) -[2023-10-16 02:50:57,926][05219] Updated weights for policy 1, policy_version 2110 (0.0008) -[2023-10-16 02:51:00,705][05218] Updated weights for policy 0, policy_version 2122 (0.0009) -[2023-10-16 02:51:01,076][05218] Updated weights for policy 0, policy_version 2132 (0.0007) -[2023-10-16 02:51:01,459][05218] Updated weights for policy 0, policy_version 2142 (0.0007) -[2023-10-16 02:51:01,836][05219] Updated weights for policy 1, policy_version 2120 (0.0008) -[2023-10-16 02:51:02,196][05219] Updated weights for policy 1, policy_version 2130 (0.0009) -[2023-10-16 02:51:02,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 4358144. Throughput: 0: 1796.7, 1: 1785.5. Samples: 1100024. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:51:02,351][03835] Avg episode reward: [(0, '2.350'), (1, '2.320')] -[2023-10-16 02:51:02,563][05219] Updated weights for policy 1, policy_version 2140 (0.0008) -[2023-10-16 02:51:05,051][05218] Updated weights for policy 0, policy_version 2152 (0.0007) -[2023-10-16 02:51:05,433][05218] Updated weights for policy 0, policy_version 2162 (0.0007) -[2023-10-16 02:51:05,812][05218] Updated weights for policy 0, policy_version 2172 (0.0009) -[2023-10-16 02:51:06,422][05219] Updated weights for policy 1, policy_version 2150 (0.0009) -[2023-10-16 02:51:06,786][05219] Updated weights for policy 1, policy_version 2160 (0.0009) -[2023-10-16 02:51:07,169][05219] Updated weights for policy 1, policy_version 2170 (0.0009) -[2023-10-16 02:51:07,350][03835] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 4423680. Throughput: 0: 1795.5, 1: 1765.7. Samples: 1121096. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:51:07,351][03835] Avg episode reward: [(0, '2.440'), (1, '2.400')] -[2023-10-16 02:51:09,671][05218] Updated weights for policy 0, policy_version 2182 (0.0008) -[2023-10-16 02:51:10,050][05218] Updated weights for policy 0, policy_version 2192 (0.0007) -[2023-10-16 02:51:10,424][05218] Updated weights for policy 0, policy_version 2202 (0.0008) -[2023-10-16 02:51:10,922][05219] Updated weights for policy 1, policy_version 2180 (0.0007) -[2023-10-16 02:51:11,287][05219] Updated weights for policy 1, policy_version 2190 (0.0007) -[2023-10-16 02:51:11,660][05219] Updated weights for policy 1, policy_version 2200 (0.0008) -[2023-10-16 02:51:12,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 4521984. Throughput: 0: 1798.6, 1: 1777.9. Samples: 1132208. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:51:12,351][03835] Avg episode reward: [(0, '2.340'), (1, '2.420')] -[2023-10-16 02:51:14,093][05218] Updated weights for policy 0, policy_version 2212 (0.0009) -[2023-10-16 02:51:14,478][05218] Updated weights for policy 0, policy_version 2222 (0.0009) -[2023-10-16 02:51:14,864][05218] Updated weights for policy 0, policy_version 2232 (0.0008) -[2023-10-16 02:51:15,638][05219] Updated weights for policy 1, policy_version 2210 (0.0009) -[2023-10-16 02:51:15,995][05219] Updated weights for policy 1, policy_version 2220 (0.0009) -[2023-10-16 02:51:16,362][05219] Updated weights for policy 1, policy_version 2230 (0.0007) -[2023-10-16 02:51:16,740][05219] Updated weights for policy 1, policy_version 2240 (0.0009) -[2023-10-16 02:51:17,350][03835] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 4587520. Throughput: 0: 1786.7, 1: 1780.0. Samples: 1153404. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:51:17,352][03835] Avg episode reward: [(0, '2.500'), (1, '2.520')] -[2023-10-16 02:51:18,527][05218] Updated weights for policy 0, policy_version 2242 (0.0008) -[2023-10-16 02:51:18,934][05218] Updated weights for policy 0, policy_version 2252 (0.0008) -[2023-10-16 02:51:19,310][05218] Updated weights for policy 0, policy_version 2262 (0.0008) -[2023-10-16 02:51:19,676][05218] Updated weights for policy 0, policy_version 2272 (0.0008) -[2023-10-16 02:51:20,469][05219] Updated weights for policy 1, policy_version 2250 (0.0009) -[2023-10-16 02:51:20,836][05219] Updated weights for policy 1, policy_version 2260 (0.0009) -[2023-10-16 02:51:21,201][05219] Updated weights for policy 1, policy_version 2270 (0.0009) -[2023-10-16 02:51:22,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 4653056. Throughput: 0: 1793.9, 1: 1762.7. Samples: 1175256. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:51:22,351][03835] Avg episode reward: [(0, '2.290'), (1, '2.260')] -[2023-10-16 02:51:23,419][05218] Updated weights for policy 0, policy_version 2282 (0.0008) -[2023-10-16 02:51:23,788][05218] Updated weights for policy 0, policy_version 2292 (0.0008) -[2023-10-16 02:51:24,167][05218] Updated weights for policy 0, policy_version 2302 (0.0009) -[2023-10-16 02:51:24,951][05219] Updated weights for policy 1, policy_version 2280 (0.0009) -[2023-10-16 02:51:25,328][05219] Updated weights for policy 1, policy_version 2290 (0.0009) -[2023-10-16 02:51:25,695][05219] Updated weights for policy 1, policy_version 2300 (0.0010) -[2023-10-16 02:51:27,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 4718592. Throughput: 0: 1795.0, 1: 1778.3. Samples: 1185696. Policy #0 lag: (min: 9.0, avg: 20.5, max: 41.0) -[2023-10-16 02:51:27,352][03835] Avg episode reward: [(0, '2.380'), (1, '2.150')] -[2023-10-16 02:51:27,847][05218] Updated weights for policy 0, policy_version 2312 (0.0007) -[2023-10-16 02:51:28,229][05218] Updated weights for policy 0, policy_version 2322 (0.0007) -[2023-10-16 02:51:28,604][05218] Updated weights for policy 0, policy_version 2332 (0.0008) -[2023-10-16 02:51:29,424][05219] Updated weights for policy 1, policy_version 2310 (0.0009) -[2023-10-16 02:51:29,797][05219] Updated weights for policy 1, policy_version 2320 (0.0009) -[2023-10-16 02:51:30,174][05219] Updated weights for policy 1, policy_version 2330 (0.0009) -[2023-10-16 02:51:32,343][05218] Updated weights for policy 0, policy_version 2342 (0.0008) -[2023-10-16 02:51:32,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 4784128. Throughput: 0: 1794.5, 1: 1760.2. Samples: 1207070. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-16 02:51:32,351][03835] Avg episode reward: [(0, '2.300'), (1, '2.080')] -[2023-10-16 02:51:32,719][05218] Updated weights for policy 0, policy_version 2352 (0.0009) -[2023-10-16 02:51:33,094][05218] Updated weights for policy 0, policy_version 2362 (0.0008) -[2023-10-16 02:51:33,916][05219] Updated weights for policy 1, policy_version 2340 (0.0008) -[2023-10-16 02:51:34,287][05219] Updated weights for policy 1, policy_version 2350 (0.0009) -[2023-10-16 02:51:34,647][05219] Updated weights for policy 1, policy_version 2360 (0.0009) -[2023-10-16 02:51:36,861][05218] Updated weights for policy 0, policy_version 2372 (0.0010) -[2023-10-16 02:51:37,234][05218] Updated weights for policy 0, policy_version 2382 (0.0007) -[2023-10-16 02:51:37,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 4849664. Throughput: 0: 1807.4, 1: 1762.4. Samples: 1228594. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-16 02:51:37,351][03835] Avg episode reward: [(0, '2.520'), (1, '2.130')] -[2023-10-16 02:51:37,361][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000002368_2424832.pth... -[2023-10-16 02:51:37,395][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000000704_720896.pth -[2023-10-16 02:51:37,614][05218] Updated weights for policy 0, policy_version 2392 (0.0007) -[2023-10-16 02:51:37,915][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000002400_2457600.pth... -[2023-10-16 02:51:37,956][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000000704_720896.pth -[2023-10-16 02:51:38,445][05219] Updated weights for policy 1, policy_version 2370 (0.0011) -[2023-10-16 02:51:38,815][05219] Updated weights for policy 1, policy_version 2380 (0.0008) -[2023-10-16 02:51:39,182][05219] Updated weights for policy 1, policy_version 2390 (0.0008) -[2023-10-16 02:51:39,548][05219] Updated weights for policy 1, policy_version 2400 (0.0007) -[2023-10-16 02:51:41,343][05218] Updated weights for policy 0, policy_version 2402 (0.0007) -[2023-10-16 02:51:41,720][05218] Updated weights for policy 0, policy_version 2412 (0.0007) -[2023-10-16 02:51:42,092][05218] Updated weights for policy 0, policy_version 2422 (0.0010) -[2023-10-16 02:51:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 4915200. Throughput: 0: 1794.5, 1: 1766.3. Samples: 1239160. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:51:42,351][03835] Avg episode reward: [(0, '2.410'), (1, '2.240')] -[2023-10-16 02:51:42,475][05218] Updated weights for policy 0, policy_version 2432 (0.0009) -[2023-10-16 02:51:43,284][05219] Updated weights for policy 1, policy_version 2410 (0.0008) -[2023-10-16 02:51:43,646][05219] Updated weights for policy 1, policy_version 2420 (0.0009) -[2023-10-16 02:51:44,013][05219] Updated weights for policy 1, policy_version 2430 (0.0007) -[2023-10-16 02:51:46,204][05218] Updated weights for policy 0, policy_version 2442 (0.0009) -[2023-10-16 02:51:46,578][05218] Updated weights for policy 0, policy_version 2452 (0.0008) -[2023-10-16 02:51:46,955][05218] Updated weights for policy 0, policy_version 2462 (0.0009) -[2023-10-16 02:51:47,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 5013504. Throughput: 0: 1803.9, 1: 1767.6. Samples: 1260744. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 02:51:47,351][03835] Avg episode reward: [(0, '2.490'), (1, '2.330')] -[2023-10-16 02:51:47,855][05219] Updated weights for policy 1, policy_version 2440 (0.0008) -[2023-10-16 02:51:48,229][05219] Updated weights for policy 1, policy_version 2450 (0.0007) -[2023-10-16 02:51:48,587][05219] Updated weights for policy 1, policy_version 2460 (0.0008) -[2023-10-16 02:51:50,641][05218] Updated weights for policy 0, policy_version 2472 (0.0009) -[2023-10-16 02:51:51,014][05218] Updated weights for policy 0, policy_version 2482 (0.0009) -[2023-10-16 02:51:51,404][05218] Updated weights for policy 0, policy_version 2492 (0.0007) -[2023-10-16 02:51:52,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 5079040. Throughput: 0: 1791.5, 1: 1794.8. Samples: 1282480. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 02:51:52,351][03835] Avg episode reward: [(0, '2.200'), (1, '2.460')] -[2023-10-16 02:51:52,367][05219] Updated weights for policy 1, policy_version 2470 (0.0010) -[2023-10-16 02:51:52,726][05219] Updated weights for policy 1, policy_version 2480 (0.0010) -[2023-10-16 02:51:53,097][05219] Updated weights for policy 1, policy_version 2490 (0.0009) -[2023-10-16 02:51:54,981][05218] Updated weights for policy 0, policy_version 2502 (0.0007) -[2023-10-16 02:51:55,359][05218] Updated weights for policy 0, policy_version 2512 (0.0010) -[2023-10-16 02:51:55,731][05218] Updated weights for policy 0, policy_version 2522 (0.0010) -[2023-10-16 02:51:57,078][05219] Updated weights for policy 1, policy_version 2500 (0.0009) -[2023-10-16 02:51:57,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 5144576. Throughput: 0: 1807.0, 1: 1767.0. Samples: 1293036. Policy #0 lag: (min: 18.0, avg: 18.0, max: 22.0) -[2023-10-16 02:51:57,351][03835] Avg episode reward: [(0, '2.620'), (1, '2.240')] -[2023-10-16 02:51:57,436][05219] Updated weights for policy 1, policy_version 2510 (0.0008) -[2023-10-16 02:51:57,810][05219] Updated weights for policy 1, policy_version 2520 (0.0008) -[2023-10-16 02:51:59,516][05218] Updated weights for policy 0, policy_version 2532 (0.0009) -[2023-10-16 02:51:59,896][05218] Updated weights for policy 0, policy_version 2542 (0.0010) -[2023-10-16 02:52:00,271][05218] Updated weights for policy 0, policy_version 2552 (0.0009) -[2023-10-16 02:52:01,475][05219] Updated weights for policy 1, policy_version 2530 (0.0007) -[2023-10-16 02:52:01,836][05219] Updated weights for policy 1, policy_version 2540 (0.0010) -[2023-10-16 02:52:02,204][05219] Updated weights for policy 1, policy_version 2550 (0.0008) -[2023-10-16 02:52:02,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 5210112. Throughput: 0: 1798.9, 1: 1783.9. Samples: 1314630. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:52:02,352][03835] Avg episode reward: [(0, '2.690'), (1, '2.270')] -[2023-10-16 02:52:02,571][05219] Updated weights for policy 1, policy_version 2560 (0.0008) -[2023-10-16 02:52:03,994][05218] Updated weights for policy 0, policy_version 2562 (0.0008) -[2023-10-16 02:52:04,407][05218] Updated weights for policy 0, policy_version 2572 (0.0009) -[2023-10-16 02:52:04,774][05218] Updated weights for policy 0, policy_version 2582 (0.0009) -[2023-10-16 02:52:05,156][05218] Updated weights for policy 0, policy_version 2592 (0.0009) -[2023-10-16 02:52:06,299][05219] Updated weights for policy 1, policy_version 2570 (0.0008) -[2023-10-16 02:52:06,666][05219] Updated weights for policy 1, policy_version 2580 (0.0010) -[2023-10-16 02:52:07,036][05219] Updated weights for policy 1, policy_version 2590 (0.0010) -[2023-10-16 02:52:07,351][03835] Fps is (10 sec: 16383.4, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 5308416. Throughput: 0: 1794.7, 1: 1771.9. Samples: 1335752. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:52:07,352][03835] Avg episode reward: [(0, '2.870'), (1, '2.080')] -[2023-10-16 02:52:07,361][04766] Saving new best policy, reward=2.870! -[2023-10-16 02:52:08,841][05218] Updated weights for policy 0, policy_version 2602 (0.0010) -[2023-10-16 02:52:09,211][05218] Updated weights for policy 0, policy_version 2612 (0.0009) -[2023-10-16 02:52:09,587][05218] Updated weights for policy 0, policy_version 2622 (0.0008) -[2023-10-16 02:52:10,992][05219] Updated weights for policy 1, policy_version 2600 (0.0009) -[2023-10-16 02:52:11,368][05219] Updated weights for policy 1, policy_version 2610 (0.0007) -[2023-10-16 02:52:11,731][05219] Updated weights for policy 1, policy_version 2620 (0.0007) -[2023-10-16 02:52:12,351][03835] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 5373952. Throughput: 0: 1794.3, 1: 1787.5. Samples: 1346878. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 02:52:12,352][03835] Avg episode reward: [(0, '2.570'), (1, '2.090')] -[2023-10-16 02:52:13,339][05218] Updated weights for policy 0, policy_version 2632 (0.0010) -[2023-10-16 02:52:13,716][05218] Updated weights for policy 0, policy_version 2642 (0.0009) -[2023-10-16 02:52:14,096][05218] Updated weights for policy 0, policy_version 2652 (0.0008) -[2023-10-16 02:52:15,520][05219] Updated weights for policy 1, policy_version 2630 (0.0009) -[2023-10-16 02:52:15,891][05219] Updated weights for policy 1, policy_version 2640 (0.0007) -[2023-10-16 02:52:16,249][05219] Updated weights for policy 1, policy_version 2650 (0.0007) -[2023-10-16 02:52:17,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 5439488. Throughput: 0: 1793.5, 1: 1780.9. Samples: 1367914. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 02:52:17,351][03835] Avg episode reward: [(0, '2.300'), (1, '2.260')] -[2023-10-16 02:52:17,979][05218] Updated weights for policy 0, policy_version 2662 (0.0009) -[2023-10-16 02:52:18,358][05218] Updated weights for policy 0, policy_version 2672 (0.0008) -[2023-10-16 02:52:18,743][05218] Updated weights for policy 0, policy_version 2682 (0.0008) -[2023-10-16 02:52:20,022][05219] Updated weights for policy 1, policy_version 2660 (0.0008) -[2023-10-16 02:52:20,395][05219] Updated weights for policy 1, policy_version 2670 (0.0007) -[2023-10-16 02:52:20,764][05219] Updated weights for policy 1, policy_version 2680 (0.0008) -[2023-10-16 02:52:22,350][03835] Fps is (10 sec: 13107.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 5505024. Throughput: 0: 1801.5, 1: 1774.4. Samples: 1389508. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:52:22,351][03835] Avg episode reward: [(0, '2.090'), (1, '2.430')] -[2023-10-16 02:52:22,583][05218] Updated weights for policy 0, policy_version 2692 (0.0008) -[2023-10-16 02:52:22,960][05218] Updated weights for policy 0, policy_version 2702 (0.0008) -[2023-10-16 02:52:23,334][05218] Updated weights for policy 0, policy_version 2712 (0.0011) -[2023-10-16 02:52:24,496][05219] Updated weights for policy 1, policy_version 2690 (0.0008) -[2023-10-16 02:52:24,871][05219] Updated weights for policy 1, policy_version 2700 (0.0008) -[2023-10-16 02:52:25,245][05219] Updated weights for policy 1, policy_version 2710 (0.0008) -[2023-10-16 02:52:25,611][05219] Updated weights for policy 1, policy_version 2720 (0.0008) -[2023-10-16 02:52:27,078][05218] Updated weights for policy 0, policy_version 2722 (0.0008) -[2023-10-16 02:52:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 5570560. Throughput: 0: 1781.5, 1: 1786.2. Samples: 1399706. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:52:27,351][03835] Avg episode reward: [(0, '2.250'), (1, '2.330')] -[2023-10-16 02:52:27,461][05218] Updated weights for policy 0, policy_version 2732 (0.0010) -[2023-10-16 02:52:27,851][05218] Updated weights for policy 0, policy_version 2742 (0.0007) -[2023-10-16 02:52:28,235][05218] Updated weights for policy 0, policy_version 2752 (0.0008) -[2023-10-16 02:52:29,384][05219] Updated weights for policy 1, policy_version 2730 (0.0010) -[2023-10-16 02:52:29,752][05219] Updated weights for policy 1, policy_version 2740 (0.0009) -[2023-10-16 02:52:30,123][05219] Updated weights for policy 1, policy_version 2750 (0.0009) -[2023-10-16 02:52:31,891][05218] Updated weights for policy 0, policy_version 2762 (0.0007) -[2023-10-16 02:52:32,264][05218] Updated weights for policy 0, policy_version 2772 (0.0009) -[2023-10-16 02:52:32,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 5636096. Throughput: 0: 1801.2, 1: 1773.0. Samples: 1421584. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-16 02:52:32,351][03835] Avg episode reward: [(0, '2.500'), (1, '2.200')] -[2023-10-16 02:52:32,642][05218] Updated weights for policy 0, policy_version 2782 (0.0009) -[2023-10-16 02:52:33,949][05219] Updated weights for policy 1, policy_version 2760 (0.0009) -[2023-10-16 02:52:34,315][05219] Updated weights for policy 1, policy_version 2770 (0.0007) -[2023-10-16 02:52:34,683][05219] Updated weights for policy 1, policy_version 2780 (0.0007) -[2023-10-16 02:52:36,504][05218] Updated weights for policy 0, policy_version 2792 (0.0008) -[2023-10-16 02:52:36,887][05218] Updated weights for policy 0, policy_version 2802 (0.0008) -[2023-10-16 02:52:37,274][05218] Updated weights for policy 0, policy_version 2812 (0.0008) -[2023-10-16 02:52:37,351][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 5701632. Throughput: 0: 1779.9, 1: 1776.8. Samples: 1442532. Policy #0 lag: (min: 25.0, avg: 33.1, max: 57.0) -[2023-10-16 02:52:37,351][03835] Avg episode reward: [(0, '2.550'), (1, '2.330')] -[2023-10-16 02:52:38,398][05219] Updated weights for policy 1, policy_version 2790 (0.0008) -[2023-10-16 02:52:38,764][05219] Updated weights for policy 1, policy_version 2800 (0.0007) -[2023-10-16 02:52:39,129][05219] Updated weights for policy 1, policy_version 2810 (0.0009) -[2023-10-16 02:52:40,924][05218] Updated weights for policy 0, policy_version 2822 (0.0008) -[2023-10-16 02:52:41,303][05218] Updated weights for policy 0, policy_version 2832 (0.0008) -[2023-10-16 02:52:41,679][05218] Updated weights for policy 0, policy_version 2842 (0.0008) -[2023-10-16 02:52:42,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 5799936. Throughput: 0: 1791.8, 1: 1780.1. Samples: 1453770. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:52:42,351][03835] Avg episode reward: [(0, '2.170'), (1, '2.360')] -[2023-10-16 02:52:42,855][05219] Updated weights for policy 1, policy_version 2820 (0.0008) -[2023-10-16 02:52:43,224][05219] Updated weights for policy 1, policy_version 2830 (0.0007) -[2023-10-16 02:52:43,588][05219] Updated weights for policy 1, policy_version 2840 (0.0008) -[2023-10-16 02:52:45,488][05218] Updated weights for policy 0, policy_version 2852 (0.0009) -[2023-10-16 02:52:45,870][05218] Updated weights for policy 0, policy_version 2862 (0.0008) -[2023-10-16 02:52:46,250][05218] Updated weights for policy 0, policy_version 2872 (0.0009) -[2023-10-16 02:52:47,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 5865472. Throughput: 0: 1779.1, 1: 1779.2. Samples: 1474754. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:52:47,351][03835] Avg episode reward: [(0, '2.090'), (1, '2.200')] -[2023-10-16 02:52:47,405][05219] Updated weights for policy 1, policy_version 2850 (0.0007) -[2023-10-16 02:52:47,774][05219] Updated weights for policy 1, policy_version 2860 (0.0008) -[2023-10-16 02:52:48,148][05219] Updated weights for policy 1, policy_version 2870 (0.0009) -[2023-10-16 02:52:48,513][05219] Updated weights for policy 1, policy_version 2880 (0.0008) -[2023-10-16 02:52:50,095][05218] Updated weights for policy 0, policy_version 2882 (0.0009) -[2023-10-16 02:52:50,486][05218] Updated weights for policy 0, policy_version 2892 (0.0009) -[2023-10-16 02:52:50,867][05218] Updated weights for policy 0, policy_version 2902 (0.0009) -[2023-10-16 02:52:51,243][05218] Updated weights for policy 0, policy_version 2912 (0.0007) -[2023-10-16 02:52:52,337][05219] Updated weights for policy 1, policy_version 2890 (0.0010) -[2023-10-16 02:52:52,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 5931008. Throughput: 0: 1763.3, 1: 1804.5. Samples: 1496302. Policy #0 lag: (min: 15.0, avg: 22.8, max: 47.0) -[2023-10-16 02:52:52,351][03835] Avg episode reward: [(0, '2.110'), (1, '2.140')] -[2023-10-16 02:52:52,714][05219] Updated weights for policy 1, policy_version 2900 (0.0007) -[2023-10-16 02:52:53,081][05219] Updated weights for policy 1, policy_version 2910 (0.0007) -[2023-10-16 02:52:55,016][05218] Updated weights for policy 0, policy_version 2922 (0.0008) -[2023-10-16 02:52:55,390][05218] Updated weights for policy 0, policy_version 2932 (0.0007) -[2023-10-16 02:52:55,765][05218] Updated weights for policy 0, policy_version 2942 (0.0011) -[2023-10-16 02:52:56,896][05219] Updated weights for policy 1, policy_version 2920 (0.0009) -[2023-10-16 02:52:57,254][05219] Updated weights for policy 1, policy_version 2930 (0.0009) -[2023-10-16 02:52:57,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 5996544. Throughput: 0: 1776.6, 1: 1775.6. Samples: 1506722. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-16 02:52:57,351][03835] Avg episode reward: [(0, '2.060'), (1, '2.110')] -[2023-10-16 02:52:57,620][05219] Updated weights for policy 1, policy_version 2940 (0.0009) -[2023-10-16 02:52:59,476][05218] Updated weights for policy 0, policy_version 2952 (0.0007) -[2023-10-16 02:52:59,850][05218] Updated weights for policy 0, policy_version 2962 (0.0007) -[2023-10-16 02:53:00,221][05218] Updated weights for policy 0, policy_version 2972 (0.0007) -[2023-10-16 02:53:01,254][05219] Updated weights for policy 1, policy_version 2950 (0.0010) -[2023-10-16 02:53:01,629][05219] Updated weights for policy 1, policy_version 2960 (0.0009) -[2023-10-16 02:53:02,003][05219] Updated weights for policy 1, policy_version 2970 (0.0008) -[2023-10-16 02:53:02,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 6094848. Throughput: 0: 1763.6, 1: 1803.3. Samples: 1528426. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:53:02,351][03835] Avg episode reward: [(0, '2.140'), (1, '2.240')] -[2023-10-16 02:53:03,979][05218] Updated weights for policy 0, policy_version 2982 (0.0008) -[2023-10-16 02:53:04,340][05218] Updated weights for policy 0, policy_version 2992 (0.0008) -[2023-10-16 02:53:04,719][05218] Updated weights for policy 0, policy_version 3002 (0.0008) -[2023-10-16 02:53:05,730][05219] Updated weights for policy 1, policy_version 2980 (0.0008) -[2023-10-16 02:53:06,095][05219] Updated weights for policy 1, policy_version 2990 (0.0009) -[2023-10-16 02:53:06,458][05219] Updated weights for policy 1, policy_version 3000 (0.0008) -[2023-10-16 02:53:07,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 6160384. Throughput: 0: 1774.1, 1: 1786.2. Samples: 1549722. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:53:07,351][03835] Avg episode reward: [(0, '2.180'), (1, '2.150')] -[2023-10-16 02:53:08,529][05218] Updated weights for policy 0, policy_version 3012 (0.0009) -[2023-10-16 02:53:08,907][05218] Updated weights for policy 0, policy_version 3022 (0.0010) -[2023-10-16 02:53:09,275][05218] Updated weights for policy 0, policy_version 3032 (0.0008) -[2023-10-16 02:53:10,149][05219] Updated weights for policy 1, policy_version 3010 (0.0009) -[2023-10-16 02:53:10,514][05219] Updated weights for policy 1, policy_version 3020 (0.0007) -[2023-10-16 02:53:10,879][05219] Updated weights for policy 1, policy_version 3030 (0.0010) -[2023-10-16 02:53:11,246][05219] Updated weights for policy 1, policy_version 3040 (0.0009) -[2023-10-16 02:53:12,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.6, 300 sec: 14218.0). Total num frames: 6225920. Throughput: 0: 1776.4, 1: 1805.9. Samples: 1560906. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) -[2023-10-16 02:53:12,351][03835] Avg episode reward: [(0, '2.360'), (1, '2.250')] -[2023-10-16 02:53:12,862][05218] Updated weights for policy 0, policy_version 3042 (0.0007) -[2023-10-16 02:53:13,247][05218] Updated weights for policy 0, policy_version 3052 (0.0007) -[2023-10-16 02:53:13,635][05218] Updated weights for policy 0, policy_version 3062 (0.0007) -[2023-10-16 02:53:14,011][05218] Updated weights for policy 0, policy_version 3072 (0.0010) -[2023-10-16 02:53:15,115][05219] Updated weights for policy 1, policy_version 3050 (0.0010) -[2023-10-16 02:53:15,475][05219] Updated weights for policy 1, policy_version 3060 (0.0008) -[2023-10-16 02:53:15,853][05219] Updated weights for policy 1, policy_version 3070 (0.0008) -[2023-10-16 02:53:17,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 6291456. Throughput: 0: 1775.0, 1: 1788.4. Samples: 1581938. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) -[2023-10-16 02:53:17,351][03835] Avg episode reward: [(0, '2.370'), (1, '2.450')] -[2023-10-16 02:53:17,886][05218] Updated weights for policy 0, policy_version 3082 (0.0008) -[2023-10-16 02:53:18,273][05218] Updated weights for policy 0, policy_version 3092 (0.0007) -[2023-10-16 02:53:18,643][05218] Updated weights for policy 0, policy_version 3102 (0.0007) -[2023-10-16 02:53:19,626][05219] Updated weights for policy 1, policy_version 3080 (0.0007) -[2023-10-16 02:53:19,983][05219] Updated weights for policy 1, policy_version 3090 (0.0007) -[2023-10-16 02:53:20,349][05219] Updated weights for policy 1, policy_version 3100 (0.0007) -[2023-10-16 02:53:22,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 6356992. Throughput: 0: 1808.6, 1: 1788.5. Samples: 1604404. Policy #0 lag: (min: 3.0, avg: 3.0, max: 4.0) -[2023-10-16 02:53:22,351][03835] Avg episode reward: [(0, '2.130'), (1, '2.400')] -[2023-10-16 02:53:22,388][05218] Updated weights for policy 0, policy_version 3112 (0.0008) -[2023-10-16 02:53:22,778][05218] Updated weights for policy 0, policy_version 3122 (0.0008) -[2023-10-16 02:53:23,159][05218] Updated weights for policy 0, policy_version 3132 (0.0008) -[2023-10-16 02:53:24,011][05219] Updated weights for policy 1, policy_version 3110 (0.0008) -[2023-10-16 02:53:24,387][05219] Updated weights for policy 1, policy_version 3120 (0.0009) -[2023-10-16 02:53:24,758][05219] Updated weights for policy 1, policy_version 3130 (0.0007) -[2023-10-16 02:53:26,818][05218] Updated weights for policy 0, policy_version 3142 (0.0009) -[2023-10-16 02:53:27,203][05218] Updated weights for policy 0, policy_version 3152 (0.0010) -[2023-10-16 02:53:27,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 6422528. Throughput: 0: 1784.4, 1: 1789.7. Samples: 1614604. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-16 02:53:27,351][03835] Avg episode reward: [(0, '2.300'), (1, '2.300')] -[2023-10-16 02:53:27,583][05218] Updated weights for policy 0, policy_version 3162 (0.0009) -[2023-10-16 02:53:28,579][05219] Updated weights for policy 1, policy_version 3140 (0.0007) -[2023-10-16 02:53:28,950][05219] Updated weights for policy 1, policy_version 3150 (0.0009) -[2023-10-16 02:53:29,321][05219] Updated weights for policy 1, policy_version 3160 (0.0007) -[2023-10-16 02:53:31,302][05218] Updated weights for policy 0, policy_version 3172 (0.0008) -[2023-10-16 02:53:31,690][05218] Updated weights for policy 0, policy_version 3182 (0.0010) -[2023-10-16 02:53:32,064][05218] Updated weights for policy 0, policy_version 3192 (0.0008) -[2023-10-16 02:53:32,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 6488064. Throughput: 0: 1808.3, 1: 1786.0. Samples: 1636494. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-16 02:53:32,351][03835] Avg episode reward: [(0, '2.250'), (1, '2.100')] -[2023-10-16 02:53:33,172][05219] Updated weights for policy 1, policy_version 3170 (0.0008) -[2023-10-16 02:53:33,552][05219] Updated weights for policy 1, policy_version 3180 (0.0009) -[2023-10-16 02:53:33,917][05219] Updated weights for policy 1, policy_version 3190 (0.0007) -[2023-10-16 02:53:34,278][05219] Updated weights for policy 1, policy_version 3200 (0.0010) -[2023-10-16 02:53:35,860][05218] Updated weights for policy 0, policy_version 3202 (0.0010) -[2023-10-16 02:53:36,239][05218] Updated weights for policy 0, policy_version 3212 (0.0009) -[2023-10-16 02:53:36,619][05218] Updated weights for policy 0, policy_version 3222 (0.0007) -[2023-10-16 02:53:36,992][05218] Updated weights for policy 0, policy_version 3232 (0.0009) -[2023-10-16 02:53:37,351][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 6586368. Throughput: 0: 1789.8, 1: 1789.8. Samples: 1657382. Policy #0 lag: (min: 29.0, avg: 35.1, max: 61.0) -[2023-10-16 02:53:37,352][03835] Avg episode reward: [(0, '2.210'), (1, '2.140')] -[2023-10-16 02:53:37,363][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000003200_3276800.pth... -[2023-10-16 02:53:37,363][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000003232_3309568.pth... -[2023-10-16 02:53:37,402][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000001568_1605632.pth -[2023-10-16 02:53:37,403][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000001536_1572864.pth -[2023-10-16 02:53:38,162][05219] Updated weights for policy 1, policy_version 3210 (0.0009) -[2023-10-16 02:53:38,530][05219] Updated weights for policy 1, policy_version 3220 (0.0007) -[2023-10-16 02:53:38,895][05219] Updated weights for policy 1, policy_version 3230 (0.0007) -[2023-10-16 02:53:40,624][05218] Updated weights for policy 0, policy_version 3242 (0.0009) -[2023-10-16 02:53:41,001][05218] Updated weights for policy 0, policy_version 3252 (0.0010) -[2023-10-16 02:53:41,387][05218] Updated weights for policy 0, policy_version 3262 (0.0011) -[2023-10-16 02:53:42,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 6651904. Throughput: 0: 1812.8, 1: 1785.1. Samples: 1668624. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-16 02:53:42,351][03835] Avg episode reward: [(0, '2.260'), (1, '2.090')] -[2023-10-16 02:53:42,723][05219] Updated weights for policy 1, policy_version 3240 (0.0008) -[2023-10-16 02:53:43,089][05219] Updated weights for policy 1, policy_version 3250 (0.0007) -[2023-10-16 02:53:43,466][05219] Updated weights for policy 1, policy_version 3260 (0.0010) -[2023-10-16 02:53:45,349][05218] Updated weights for policy 0, policy_version 3272 (0.0009) -[2023-10-16 02:53:45,726][05218] Updated weights for policy 0, policy_version 3282 (0.0009) -[2023-10-16 02:53:46,101][05218] Updated weights for policy 0, policy_version 3292 (0.0008) -[2023-10-16 02:53:47,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 6717440. Throughput: 0: 1792.2, 1: 1780.4. Samples: 1689196. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:53:47,351][03835] Avg episode reward: [(0, '2.160'), (1, '2.340')] -[2023-10-16 02:53:47,432][05219] Updated weights for policy 1, policy_version 3270 (0.0009) -[2023-10-16 02:53:47,804][05219] Updated weights for policy 1, policy_version 3280 (0.0010) -[2023-10-16 02:53:48,170][05219] Updated weights for policy 1, policy_version 3290 (0.0010) -[2023-10-16 02:53:49,983][05218] Updated weights for policy 0, policy_version 3302 (0.0008) -[2023-10-16 02:53:50,358][05218] Updated weights for policy 0, policy_version 3312 (0.0010) -[2023-10-16 02:53:50,733][05218] Updated weights for policy 0, policy_version 3322 (0.0009) -[2023-10-16 02:53:51,984][05219] Updated weights for policy 1, policy_version 3300 (0.0007) -[2023-10-16 02:53:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 6782976. Throughput: 0: 1780.9, 1: 1799.3. Samples: 1710832. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:53:52,351][05219] Updated weights for policy 1, policy_version 3310 (0.0007) -[2023-10-16 02:53:52,351][03835] Avg episode reward: [(0, '2.190'), (1, '2.540')] -[2023-10-16 02:53:52,712][05219] Updated weights for policy 1, policy_version 3320 (0.0008) -[2023-10-16 02:53:54,526][05218] Updated weights for policy 0, policy_version 3332 (0.0008) -[2023-10-16 02:53:54,905][05218] Updated weights for policy 0, policy_version 3342 (0.0007) -[2023-10-16 02:53:55,283][05218] Updated weights for policy 0, policy_version 3352 (0.0008) -[2023-10-16 02:53:56,413][05219] Updated weights for policy 1, policy_version 3330 (0.0007) -[2023-10-16 02:53:56,780][05219] Updated weights for policy 1, policy_version 3340 (0.0010) -[2023-10-16 02:53:57,153][05219] Updated weights for policy 1, policy_version 3350 (0.0009) -[2023-10-16 02:53:57,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 6848512. Throughput: 0: 1787.5, 1: 1776.8. Samples: 1721300. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:53:57,351][03835] Avg episode reward: [(0, '2.420'), (1, '2.650')] -[2023-10-16 02:53:57,524][05219] Updated weights for policy 1, policy_version 3360 (0.0010) -[2023-10-16 02:53:59,100][05218] Updated weights for policy 0, policy_version 3362 (0.0008) -[2023-10-16 02:53:59,478][05218] Updated weights for policy 0, policy_version 3372 (0.0008) -[2023-10-16 02:53:59,855][05218] Updated weights for policy 0, policy_version 3382 (0.0008) -[2023-10-16 02:54:00,231][05218] Updated weights for policy 0, policy_version 3392 (0.0007) -[2023-10-16 02:54:01,281][05219] Updated weights for policy 1, policy_version 3370 (0.0008) -[2023-10-16 02:54:01,657][05219] Updated weights for policy 1, policy_version 3380 (0.0009) -[2023-10-16 02:54:02,017][05219] Updated weights for policy 1, policy_version 3390 (0.0009) -[2023-10-16 02:54:02,351][03835] Fps is (10 sec: 16383.4, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 6946816. Throughput: 0: 1777.9, 1: 1804.5. Samples: 1743148. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:54:02,352][03835] Avg episode reward: [(0, '2.350'), (1, '2.460')] -[2023-10-16 02:54:03,889][05218] Updated weights for policy 0, policy_version 3402 (0.0007) -[2023-10-16 02:54:04,270][05218] Updated weights for policy 0, policy_version 3412 (0.0007) -[2023-10-16 02:54:04,638][05218] Updated weights for policy 0, policy_version 3422 (0.0007) -[2023-10-16 02:54:05,687][05219] Updated weights for policy 1, policy_version 3400 (0.0009) -[2023-10-16 02:54:06,047][05219] Updated weights for policy 1, policy_version 3410 (0.0009) -[2023-10-16 02:54:06,415][05219] Updated weights for policy 1, policy_version 3420 (0.0009) -[2023-10-16 02:54:07,351][03835] Fps is (10 sec: 16383.4, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 7012352. Throughput: 0: 1786.6, 1: 1772.0. Samples: 1764544. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:54:07,352][03835] Avg episode reward: [(0, '2.660'), (1, '2.210')] -[2023-10-16 02:54:08,134][05218] Updated weights for policy 0, policy_version 3432 (0.0008) -[2023-10-16 02:54:08,516][05218] Updated weights for policy 0, policy_version 3442 (0.0007) -[2023-10-16 02:54:08,889][05218] Updated weights for policy 0, policy_version 3452 (0.0007) -[2023-10-16 02:54:10,177][05219] Updated weights for policy 1, policy_version 3430 (0.0008) -[2023-10-16 02:54:10,529][05219] Updated weights for policy 1, policy_version 3440 (0.0010) -[2023-10-16 02:54:10,905][05219] Updated weights for policy 1, policy_version 3450 (0.0008) -[2023-10-16 02:54:12,350][03835] Fps is (10 sec: 13107.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 7077888. Throughput: 0: 1781.1, 1: 1796.5. Samples: 1775594. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:54:12,351][03835] Avg episode reward: [(0, '2.600'), (1, '2.150')] -[2023-10-16 02:54:12,620][05218] Updated weights for policy 0, policy_version 3462 (0.0008) -[2023-10-16 02:54:13,003][05218] Updated weights for policy 0, policy_version 3472 (0.0009) -[2023-10-16 02:54:13,377][05218] Updated weights for policy 0, policy_version 3482 (0.0008) -[2023-10-16 02:54:14,652][05219] Updated weights for policy 1, policy_version 3460 (0.0008) -[2023-10-16 02:54:15,021][05219] Updated weights for policy 1, policy_version 3470 (0.0007) -[2023-10-16 02:54:15,381][05219] Updated weights for policy 1, policy_version 3480 (0.0012) -[2023-10-16 02:54:17,151][05218] Updated weights for policy 0, policy_version 3492 (0.0009) -[2023-10-16 02:54:17,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 7143424. Throughput: 0: 1786.6, 1: 1771.5. Samples: 1796608. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-16 02:54:17,351][03835] Avg episode reward: [(0, '2.730'), (1, '2.260')] -[2023-10-16 02:54:17,527][05218] Updated weights for policy 0, policy_version 3502 (0.0009) -[2023-10-16 02:54:17,904][05218] Updated weights for policy 0, policy_version 3512 (0.0009) -[2023-10-16 02:54:19,107][05219] Updated weights for policy 1, policy_version 3490 (0.0010) -[2023-10-16 02:54:19,478][05219] Updated weights for policy 1, policy_version 3500 (0.0007) -[2023-10-16 02:54:19,847][05219] Updated weights for policy 1, policy_version 3510 (0.0007) -[2023-10-16 02:54:20,213][05219] Updated weights for policy 1, policy_version 3520 (0.0008) -[2023-10-16 02:54:21,595][05218] Updated weights for policy 0, policy_version 3522 (0.0009) -[2023-10-16 02:54:22,013][05218] Updated weights for policy 0, policy_version 3532 (0.0007) -[2023-10-16 02:54:22,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 7208960. Throughput: 0: 1794.2, 1: 1777.1. Samples: 1818090. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-16 02:54:22,352][03835] Avg episode reward: [(0, '2.370'), (1, '2.200')] -[2023-10-16 02:54:22,381][05218] Updated weights for policy 0, policy_version 3542 (0.0007) -[2023-10-16 02:54:22,754][05218] Updated weights for policy 0, policy_version 3552 (0.0008) -[2023-10-16 02:54:23,922][05219] Updated weights for policy 1, policy_version 3530 (0.0008) -[2023-10-16 02:54:24,284][05219] Updated weights for policy 1, policy_version 3540 (0.0008) -[2023-10-16 02:54:24,645][05219] Updated weights for policy 1, policy_version 3550 (0.0008) -[2023-10-16 02:54:26,575][05218] Updated weights for policy 0, policy_version 3562 (0.0007) -[2023-10-16 02:54:26,951][05218] Updated weights for policy 0, policy_version 3572 (0.0009) -[2023-10-16 02:54:27,338][05218] Updated weights for policy 0, policy_version 3582 (0.0010) -[2023-10-16 02:54:27,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 7274496. Throughput: 0: 1778.1, 1: 1779.0. Samples: 1828696. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-16 02:54:27,351][03835] Avg episode reward: [(0, '2.290'), (1, '2.030')] -[2023-10-16 02:54:28,404][05219] Updated weights for policy 1, policy_version 3560 (0.0009) -[2023-10-16 02:54:28,784][05219] Updated weights for policy 1, policy_version 3570 (0.0007) -[2023-10-16 02:54:29,142][05219] Updated weights for policy 1, policy_version 3580 (0.0007) -[2023-10-16 02:54:31,174][05218] Updated weights for policy 0, policy_version 3592 (0.0008) -[2023-10-16 02:54:31,543][05218] Updated weights for policy 0, policy_version 3602 (0.0011) -[2023-10-16 02:54:31,923][05218] Updated weights for policy 0, policy_version 3612 (0.0009) -[2023-10-16 02:54:32,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 7372800. Throughput: 0: 1798.5, 1: 1784.7. Samples: 1850440. Policy #0 lag: (min: 31.0, avg: 31.3, max: 42.0) -[2023-10-16 02:54:32,351][03835] Avg episode reward: [(0, '2.190'), (1, '2.040')] -[2023-10-16 02:54:32,741][05219] Updated weights for policy 1, policy_version 3590 (0.0007) -[2023-10-16 02:54:33,104][05219] Updated weights for policy 1, policy_version 3600 (0.0010) -[2023-10-16 02:54:33,468][05219] Updated weights for policy 1, policy_version 3610 (0.0007) -[2023-10-16 02:54:35,689][05218] Updated weights for policy 0, policy_version 3622 (0.0010) -[2023-10-16 02:54:36,079][05218] Updated weights for policy 0, policy_version 3632 (0.0010) -[2023-10-16 02:54:36,446][05218] Updated weights for policy 0, policy_version 3642 (0.0007) -[2023-10-16 02:54:37,251][05219] Updated weights for policy 1, policy_version 3620 (0.0008) -[2023-10-16 02:54:37,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 7438336. Throughput: 0: 1781.6, 1: 1799.1. Samples: 1871960. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:54:37,351][03835] Avg episode reward: [(0, '2.000'), (1, '2.290')] -[2023-10-16 02:54:37,619][05219] Updated weights for policy 1, policy_version 3630 (0.0007) -[2023-10-16 02:54:37,976][05219] Updated weights for policy 1, policy_version 3640 (0.0008) -[2023-10-16 02:54:40,267][05218] Updated weights for policy 0, policy_version 3652 (0.0008) -[2023-10-16 02:54:40,643][05218] Updated weights for policy 0, policy_version 3662 (0.0008) -[2023-10-16 02:54:41,021][05218] Updated weights for policy 0, policy_version 3672 (0.0010) -[2023-10-16 02:54:41,899][05219] Updated weights for policy 1, policy_version 3650 (0.0008) -[2023-10-16 02:54:42,271][05219] Updated weights for policy 1, policy_version 3660 (0.0008) -[2023-10-16 02:54:42,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 7503872. Throughput: 0: 1802.3, 1: 1787.6. Samples: 1882844. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:54:42,351][03835] Avg episode reward: [(0, '2.030'), (1, '2.090')] -[2023-10-16 02:54:42,633][05219] Updated weights for policy 1, policy_version 3670 (0.0010) -[2023-10-16 02:54:43,002][05219] Updated weights for policy 1, policy_version 3680 (0.0009) -[2023-10-16 02:54:44,766][05218] Updated weights for policy 0, policy_version 3682 (0.0008) -[2023-10-16 02:54:45,139][05218] Updated weights for policy 0, policy_version 3692 (0.0010) -[2023-10-16 02:54:45,514][05218] Updated weights for policy 0, policy_version 3702 (0.0008) -[2023-10-16 02:54:45,886][05218] Updated weights for policy 0, policy_version 3712 (0.0009) -[2023-10-16 02:54:46,879][05219] Updated weights for policy 1, policy_version 3690 (0.0008) -[2023-10-16 02:54:47,248][05219] Updated weights for policy 1, policy_version 3700 (0.0007) -[2023-10-16 02:54:47,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 7569408. Throughput: 0: 1783.2, 1: 1790.0. Samples: 1903938. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:54:47,351][03835] Avg episode reward: [(0, '2.400'), (1, '2.170')] -[2023-10-16 02:54:47,623][05219] Updated weights for policy 1, policy_version 3710 (0.0007) -[2023-10-16 02:54:49,567][05218] Updated weights for policy 0, policy_version 3722 (0.0010) -[2023-10-16 02:54:49,948][05218] Updated weights for policy 0, policy_version 3732 (0.0007) -[2023-10-16 02:54:50,323][05218] Updated weights for policy 0, policy_version 3742 (0.0008) -[2023-10-16 02:54:51,526][05219] Updated weights for policy 1, policy_version 3720 (0.0008) -[2023-10-16 02:54:51,898][05219] Updated weights for policy 1, policy_version 3730 (0.0007) -[2023-10-16 02:54:52,276][05219] Updated weights for policy 1, policy_version 3740 (0.0009) -[2023-10-16 02:54:52,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 7634944. Throughput: 0: 1777.1, 1: 1791.2. Samples: 1925118. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:54:52,351][03835] Avg episode reward: [(0, '2.700'), (1, '2.200')] -[2023-10-16 02:54:54,128][05218] Updated weights for policy 0, policy_version 3752 (0.0009) -[2023-10-16 02:54:54,510][05218] Updated weights for policy 0, policy_version 3762 (0.0009) -[2023-10-16 02:54:54,889][05218] Updated weights for policy 0, policy_version 3772 (0.0009) -[2023-10-16 02:54:55,888][05219] Updated weights for policy 1, policy_version 3750 (0.0008) -[2023-10-16 02:54:56,256][05219] Updated weights for policy 1, policy_version 3760 (0.0011) -[2023-10-16 02:54:56,630][05219] Updated weights for policy 1, policy_version 3770 (0.0007) -[2023-10-16 02:54:57,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 7733248. Throughput: 0: 1773.5, 1: 1789.4. Samples: 1935922. Policy #0 lag: (min: 16.0, avg: 42.5, max: 48.0) -[2023-10-16 02:54:57,351][03835] Avg episode reward: [(0, '2.750'), (1, '2.180')] -[2023-10-16 02:54:58,603][05218] Updated weights for policy 0, policy_version 3782 (0.0008) -[2023-10-16 02:54:58,982][05218] Updated weights for policy 0, policy_version 3792 (0.0009) -[2023-10-16 02:54:59,358][05218] Updated weights for policy 0, policy_version 3802 (0.0009) -[2023-10-16 02:55:00,465][05219] Updated weights for policy 1, policy_version 3780 (0.0009) -[2023-10-16 02:55:00,820][05219] Updated weights for policy 1, policy_version 3790 (0.0010) -[2023-10-16 02:55:01,188][05219] Updated weights for policy 1, policy_version 3800 (0.0007) -[2023-10-16 02:55:02,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14199.6, 300 sec: 14218.0). Total num frames: 7798784. Throughput: 0: 1778.2, 1: 1795.1. Samples: 1957408. Policy #0 lag: (min: 16.0, avg: 42.5, max: 48.0) -[2023-10-16 02:55:02,351][03835] Avg episode reward: [(0, '2.660'), (1, '2.170')] -[2023-10-16 02:55:03,047][05218] Updated weights for policy 0, policy_version 3812 (0.0009) -[2023-10-16 02:55:03,418][05218] Updated weights for policy 0, policy_version 3822 (0.0009) -[2023-10-16 02:55:03,797][05218] Updated weights for policy 0, policy_version 3832 (0.0010) -[2023-10-16 02:55:04,809][05219] Updated weights for policy 1, policy_version 3810 (0.0008) -[2023-10-16 02:55:05,169][05219] Updated weights for policy 1, policy_version 3820 (0.0008) -[2023-10-16 02:55:05,540][05219] Updated weights for policy 1, policy_version 3830 (0.0010) -[2023-10-16 02:55:05,893][05219] Updated weights for policy 1, policy_version 3840 (0.0009) -[2023-10-16 02:55:07,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 7864320. Throughput: 0: 1805.0, 1: 1779.2. Samples: 1979378. Policy #0 lag: (min: 29.0, avg: 35.7, max: 61.0) -[2023-10-16 02:55:07,352][03835] Avg episode reward: [(0, '2.430'), (1, '2.280')] -[2023-10-16 02:55:07,567][05218] Updated weights for policy 0, policy_version 3842 (0.0010) -[2023-10-16 02:55:07,959][05218] Updated weights for policy 0, policy_version 3852 (0.0007) -[2023-10-16 02:55:08,331][05218] Updated weights for policy 0, policy_version 3862 (0.0009) -[2023-10-16 02:55:08,708][05218] Updated weights for policy 0, policy_version 3872 (0.0008) -[2023-10-16 02:55:09,782][05219] Updated weights for policy 1, policy_version 3850 (0.0007) -[2023-10-16 02:55:10,150][05219] Updated weights for policy 1, policy_version 3860 (0.0007) -[2023-10-16 02:55:10,513][05219] Updated weights for policy 1, policy_version 3870 (0.0009) -[2023-10-16 02:55:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 7929856. Throughput: 0: 1785.2, 1: 1791.8. Samples: 1989660. Policy #0 lag: (min: 29.0, avg: 35.7, max: 61.0) -[2023-10-16 02:55:12,351][03835] Avg episode reward: [(0, '2.540'), (1, '2.260')] -[2023-10-16 02:55:12,527][05218] Updated weights for policy 0, policy_version 3882 (0.0010) -[2023-10-16 02:55:12,905][05218] Updated weights for policy 0, policy_version 3892 (0.0010) -[2023-10-16 02:55:13,289][05218] Updated weights for policy 0, policy_version 3902 (0.0011) -[2023-10-16 02:55:14,244][05219] Updated weights for policy 1, policy_version 3880 (0.0008) -[2023-10-16 02:55:14,603][05219] Updated weights for policy 1, policy_version 3890 (0.0007) -[2023-10-16 02:55:14,968][05219] Updated weights for policy 1, policy_version 3900 (0.0009) -[2023-10-16 02:55:16,921][05218] Updated weights for policy 0, policy_version 3912 (0.0008) -[2023-10-16 02:55:17,296][05218] Updated weights for policy 0, policy_version 3922 (0.0008) -[2023-10-16 02:55:17,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 7995392. Throughput: 0: 1798.8, 1: 1772.8. Samples: 2011162. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:55:17,351][03835] Avg episode reward: [(0, '2.600'), (1, '2.210')] -[2023-10-16 02:55:17,660][05218] Updated weights for policy 0, policy_version 3932 (0.0007) -[2023-10-16 02:55:18,957][05219] Updated weights for policy 1, policy_version 3910 (0.0008) -[2023-10-16 02:55:19,329][05219] Updated weights for policy 1, policy_version 3920 (0.0009) -[2023-10-16 02:55:19,706][05219] Updated weights for policy 1, policy_version 3930 (0.0008) -[2023-10-16 02:55:21,378][05218] Updated weights for policy 0, policy_version 3942 (0.0009) -[2023-10-16 02:55:21,753][05218] Updated weights for policy 0, policy_version 3952 (0.0009) -[2023-10-16 02:55:22,127][05218] Updated weights for policy 0, policy_version 3962 (0.0008) -[2023-10-16 02:55:22,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 8060928. Throughput: 0: 1795.7, 1: 1762.4. Samples: 2032076. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:55:22,351][03835] Avg episode reward: [(0, '2.620'), (1, '2.410')] -[2023-10-16 02:55:23,497][05219] Updated weights for policy 1, policy_version 3940 (0.0008) -[2023-10-16 02:55:23,866][05219] Updated weights for policy 1, policy_version 3950 (0.0008) -[2023-10-16 02:55:24,233][05219] Updated weights for policy 1, policy_version 3960 (0.0010) -[2023-10-16 02:55:25,803][05218] Updated weights for policy 0, policy_version 3972 (0.0009) -[2023-10-16 02:55:26,183][05218] Updated weights for policy 0, policy_version 3982 (0.0009) -[2023-10-16 02:55:26,563][05218] Updated weights for policy 0, policy_version 3992 (0.0009) -[2023-10-16 02:55:27,351][03835] Fps is (10 sec: 16383.5, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 8159232. Throughput: 0: 1800.7, 1: 1763.1. Samples: 2043218. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:55:27,352][03835] Avg episode reward: [(0, '2.370'), (1, '2.410')] -[2023-10-16 02:55:28,136][05219] Updated weights for policy 1, policy_version 3970 (0.0008) -[2023-10-16 02:55:28,503][05219] Updated weights for policy 1, policy_version 3980 (0.0009) -[2023-10-16 02:55:28,860][05219] Updated weights for policy 1, policy_version 3990 (0.0008) -[2023-10-16 02:55:29,223][05219] Updated weights for policy 1, policy_version 4000 (0.0009) -[2023-10-16 02:55:30,332][05218] Updated weights for policy 0, policy_version 4002 (0.0009) -[2023-10-16 02:55:30,699][05218] Updated weights for policy 0, policy_version 4012 (0.0010) -[2023-10-16 02:55:31,080][05218] Updated weights for policy 0, policy_version 4022 (0.0009) -[2023-10-16 02:55:31,462][05218] Updated weights for policy 0, policy_version 4032 (0.0009) -[2023-10-16 02:55:32,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 8224768. Throughput: 0: 1794.6, 1: 1759.3. Samples: 2063864. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:55:32,352][03835] Avg episode reward: [(0, '2.180'), (1, '2.350')] -[2023-10-16 02:55:33,058][05219] Updated weights for policy 1, policy_version 4010 (0.0011) -[2023-10-16 02:55:33,430][05219] Updated weights for policy 1, policy_version 4020 (0.0008) -[2023-10-16 02:55:33,788][05219] Updated weights for policy 1, policy_version 4030 (0.0007) -[2023-10-16 02:55:35,165][05218] Updated weights for policy 0, policy_version 4042 (0.0007) -[2023-10-16 02:55:35,542][05218] Updated weights for policy 0, policy_version 4052 (0.0009) -[2023-10-16 02:55:35,912][05218] Updated weights for policy 0, policy_version 4062 (0.0010) -[2023-10-16 02:55:37,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 8290304. Throughput: 0: 1791.4, 1: 1783.4. Samples: 2085982. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:55:37,352][03835] Avg episode reward: [(0, '2.080'), (1, '2.190')] -[2023-10-16 02:55:37,363][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000004064_4161536.pth... -[2023-10-16 02:55:37,363][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000004032_4128768.pth... -[2023-10-16 02:55:37,400][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000002400_2457600.pth -[2023-10-16 02:55:37,400][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000002368_2424832.pth -[2023-10-16 02:55:37,795][05219] Updated weights for policy 1, policy_version 4040 (0.0008) -[2023-10-16 02:55:38,163][05219] Updated weights for policy 1, policy_version 4050 (0.0007) -[2023-10-16 02:55:38,533][05219] Updated weights for policy 1, policy_version 4060 (0.0009) -[2023-10-16 02:55:39,587][05218] Updated weights for policy 0, policy_version 4072 (0.0009) -[2023-10-16 02:55:39,964][05218] Updated weights for policy 0, policy_version 4082 (0.0007) -[2023-10-16 02:55:40,343][05218] Updated weights for policy 0, policy_version 4092 (0.0008) -[2023-10-16 02:55:42,146][05219] Updated weights for policy 1, policy_version 4070 (0.0009) -[2023-10-16 02:55:42,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 8355840. Throughput: 0: 1801.4, 1: 1758.5. Samples: 2096118. Policy #0 lag: (min: 2.0, avg: 9.3, max: 34.0) -[2023-10-16 02:55:42,351][03835] Avg episode reward: [(0, '2.080'), (1, '2.090')] -[2023-10-16 02:55:42,525][05219] Updated weights for policy 1, policy_version 4080 (0.0008) -[2023-10-16 02:55:42,891][05219] Updated weights for policy 1, policy_version 4090 (0.0009) -[2023-10-16 02:55:44,217][05218] Updated weights for policy 0, policy_version 4102 (0.0008) -[2023-10-16 02:55:44,596][05218] Updated weights for policy 0, policy_version 4112 (0.0009) -[2023-10-16 02:55:44,974][05218] Updated weights for policy 0, policy_version 4122 (0.0009) -[2023-10-16 02:55:46,719][05219] Updated weights for policy 1, policy_version 4100 (0.0009) -[2023-10-16 02:55:47,085][05219] Updated weights for policy 1, policy_version 4110 (0.0009) -[2023-10-16 02:55:47,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 8421376. Throughput: 0: 1788.3, 1: 1777.7. Samples: 2117882. Policy #0 lag: (min: 7.0, avg: 20.3, max: 39.0) -[2023-10-16 02:55:47,351][03835] Avg episode reward: [(0, '2.100'), (1, '2.110')] -[2023-10-16 02:55:47,454][05219] Updated weights for policy 1, policy_version 4120 (0.0010) -[2023-10-16 02:55:48,716][05218] Updated weights for policy 0, policy_version 4132 (0.0010) -[2023-10-16 02:55:49,089][05218] Updated weights for policy 0, policy_version 4142 (0.0008) -[2023-10-16 02:55:49,475][05218] Updated weights for policy 0, policy_version 4152 (0.0008) -[2023-10-16 02:55:51,261][05219] Updated weights for policy 1, policy_version 4130 (0.0009) -[2023-10-16 02:55:51,636][05219] Updated weights for policy 1, policy_version 4140 (0.0011) -[2023-10-16 02:55:52,001][05219] Updated weights for policy 1, policy_version 4150 (0.0010) -[2023-10-16 02:55:52,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 8486912. Throughput: 0: 1788.7, 1: 1761.8. Samples: 2139150. Policy #0 lag: (min: 7.0, avg: 20.3, max: 39.0) -[2023-10-16 02:55:52,351][03835] Avg episode reward: [(0, '2.150'), (1, '2.350')] -[2023-10-16 02:55:52,363][05219] Updated weights for policy 1, policy_version 4160 (0.0011) -[2023-10-16 02:55:53,126][05218] Updated weights for policy 0, policy_version 4162 (0.0009) -[2023-10-16 02:55:53,517][05218] Updated weights for policy 0, policy_version 4172 (0.0009) -[2023-10-16 02:55:53,899][05218] Updated weights for policy 0, policy_version 4182 (0.0008) -[2023-10-16 02:55:54,260][05218] Updated weights for policy 0, policy_version 4192 (0.0007) -[2023-10-16 02:55:56,083][05219] Updated weights for policy 1, policy_version 4170 (0.0007) -[2023-10-16 02:55:56,446][05219] Updated weights for policy 1, policy_version 4180 (0.0007) -[2023-10-16 02:55:56,811][05219] Updated weights for policy 1, policy_version 4190 (0.0010) -[2023-10-16 02:55:57,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 8585216. Throughput: 0: 1787.5, 1: 1774.8. Samples: 2149968. Policy #0 lag: (min: 21.0, avg: 29.0, max: 53.0) -[2023-10-16 02:55:57,351][03835] Avg episode reward: [(0, '2.220'), (1, '2.050')] -[2023-10-16 02:55:58,089][05218] Updated weights for policy 0, policy_version 4202 (0.0009) -[2023-10-16 02:55:58,468][05218] Updated weights for policy 0, policy_version 4212 (0.0009) -[2023-10-16 02:55:58,851][05218] Updated weights for policy 0, policy_version 4222 (0.0008) -[2023-10-16 02:56:00,701][05219] Updated weights for policy 1, policy_version 4200 (0.0010) -[2023-10-16 02:56:01,074][05219] Updated weights for policy 1, policy_version 4210 (0.0009) -[2023-10-16 02:56:01,431][05219] Updated weights for policy 1, policy_version 4220 (0.0008) -[2023-10-16 02:56:02,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 8650752. Throughput: 0: 1787.2, 1: 1772.4. Samples: 2171342. Policy #0 lag: (min: 21.0, avg: 29.0, max: 53.0) -[2023-10-16 02:56:02,351][03835] Avg episode reward: [(0, '2.170'), (1, '2.180')] -[2023-10-16 02:56:02,659][05218] Updated weights for policy 0, policy_version 4232 (0.0007) -[2023-10-16 02:56:03,038][05218] Updated weights for policy 0, policy_version 4242 (0.0011) -[2023-10-16 02:56:03,412][05218] Updated weights for policy 0, policy_version 4252 (0.0012) -[2023-10-16 02:56:05,292][05219] Updated weights for policy 1, policy_version 4230 (0.0008) -[2023-10-16 02:56:05,671][05219] Updated weights for policy 1, policy_version 4240 (0.0007) -[2023-10-16 02:56:06,029][05219] Updated weights for policy 1, policy_version 4250 (0.0009) -[2023-10-16 02:56:07,129][05218] Updated weights for policy 0, policy_version 4262 (0.0008) -[2023-10-16 02:56:07,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 8716288. Throughput: 0: 1805.6, 1: 1757.3. Samples: 2192406. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:56:07,352][03835] Avg episode reward: [(0, '2.200'), (1, '2.250')] -[2023-10-16 02:56:07,513][05218] Updated weights for policy 0, policy_version 4272 (0.0007) -[2023-10-16 02:56:07,891][05218] Updated weights for policy 0, policy_version 4282 (0.0008) -[2023-10-16 02:56:09,805][05219] Updated weights for policy 1, policy_version 4260 (0.0008) -[2023-10-16 02:56:10,167][05219] Updated weights for policy 1, policy_version 4270 (0.0007) -[2023-10-16 02:56:10,536][05219] Updated weights for policy 1, policy_version 4280 (0.0010) -[2023-10-16 02:56:11,552][05218] Updated weights for policy 0, policy_version 4292 (0.0008) -[2023-10-16 02:56:11,919][05218] Updated weights for policy 0, policy_version 4302 (0.0009) -[2023-10-16 02:56:12,295][05218] Updated weights for policy 0, policy_version 4312 (0.0007) -[2023-10-16 02:56:12,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 8781824. Throughput: 0: 1786.0, 1: 1780.8. Samples: 2203726. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:56:12,352][03835] Avg episode reward: [(0, '2.340'), (1, '2.090')] -[2023-10-16 02:56:14,378][05219] Updated weights for policy 1, policy_version 4290 (0.0010) -[2023-10-16 02:56:14,734][05219] Updated weights for policy 1, policy_version 4300 (0.0009) -[2023-10-16 02:56:15,104][05219] Updated weights for policy 1, policy_version 4310 (0.0008) -[2023-10-16 02:56:15,467][05219] Updated weights for policy 1, policy_version 4320 (0.0009) -[2023-10-16 02:56:15,977][05218] Updated weights for policy 0, policy_version 4322 (0.0007) -[2023-10-16 02:56:16,351][05218] Updated weights for policy 0, policy_version 4332 (0.0009) -[2023-10-16 02:56:16,726][05218] Updated weights for policy 0, policy_version 4342 (0.0009) -[2023-10-16 02:56:17,100][05218] Updated weights for policy 0, policy_version 4352 (0.0008) -[2023-10-16 02:56:17,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 8880128. Throughput: 0: 1810.2, 1: 1764.5. Samples: 2224726. Policy #0 lag: (min: 0.0, avg: 22.3, max: 32.0) -[2023-10-16 02:56:17,351][03835] Avg episode reward: [(0, '2.580'), (1, '1.990')] -[2023-10-16 02:56:19,319][05219] Updated weights for policy 1, policy_version 4330 (0.0009) -[2023-10-16 02:56:19,687][05219] Updated weights for policy 1, policy_version 4340 (0.0007) -[2023-10-16 02:56:20,054][05219] Updated weights for policy 1, policy_version 4350 (0.0009) -[2023-10-16 02:56:20,814][05218] Updated weights for policy 0, policy_version 4362 (0.0009) -[2023-10-16 02:56:21,193][05218] Updated weights for policy 0, policy_version 4372 (0.0009) -[2023-10-16 02:56:21,571][05218] Updated weights for policy 0, policy_version 4382 (0.0008) -[2023-10-16 02:56:22,351][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 8945664. Throughput: 0: 1791.8, 1: 1767.9. Samples: 2246168. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:56:22,352][03835] Avg episode reward: [(0, '2.610'), (1, '2.200')] -[2023-10-16 02:56:23,935][05219] Updated weights for policy 1, policy_version 4360 (0.0008) -[2023-10-16 02:56:24,294][05219] Updated weights for policy 1, policy_version 4370 (0.0007) -[2023-10-16 02:56:24,652][05219] Updated weights for policy 1, policy_version 4380 (0.0007) -[2023-10-16 02:56:25,273][05218] Updated weights for policy 0, policy_version 4392 (0.0008) -[2023-10-16 02:56:25,647][05218] Updated weights for policy 0, policy_version 4402 (0.0009) -[2023-10-16 02:56:26,034][05218] Updated weights for policy 0, policy_version 4412 (0.0007) -[2023-10-16 02:56:27,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 9011200. Throughput: 0: 1810.1, 1: 1768.1. Samples: 2257138. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:56:27,351][03835] Avg episode reward: [(0, '2.570'), (1, '2.370')] -[2023-10-16 02:56:28,482][05219] Updated weights for policy 1, policy_version 4390 (0.0008) -[2023-10-16 02:56:28,845][05219] Updated weights for policy 1, policy_version 4400 (0.0010) -[2023-10-16 02:56:29,213][05219] Updated weights for policy 1, policy_version 4410 (0.0008) -[2023-10-16 02:56:29,806][05218] Updated weights for policy 0, policy_version 4422 (0.0008) -[2023-10-16 02:56:30,181][05218] Updated weights for policy 0, policy_version 4432 (0.0009) -[2023-10-16 02:56:30,559][05218] Updated weights for policy 0, policy_version 4442 (0.0009) -[2023-10-16 02:56:32,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 9076736. Throughput: 0: 1794.8, 1: 1770.8. Samples: 2278336. Policy #0 lag: (min: 31.0, avg: 32.9, max: 60.0) -[2023-10-16 02:56:32,352][03835] Avg episode reward: [(0, '2.520'), (1, '2.190')] -[2023-10-16 02:56:33,062][05219] Updated weights for policy 1, policy_version 4420 (0.0009) -[2023-10-16 02:56:33,428][05219] Updated weights for policy 1, policy_version 4430 (0.0008) -[2023-10-16 02:56:33,800][05219] Updated weights for policy 1, policy_version 4440 (0.0007) -[2023-10-16 02:56:34,193][05218] Updated weights for policy 0, policy_version 4452 (0.0008) -[2023-10-16 02:56:34,570][05218] Updated weights for policy 0, policy_version 4462 (0.0008) -[2023-10-16 02:56:34,937][05218] Updated weights for policy 0, policy_version 4472 (0.0009) -[2023-10-16 02:56:37,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 9142272. Throughput: 0: 1789.1, 1: 1795.1. Samples: 2300438. Policy #0 lag: (min: 31.0, avg: 32.9, max: 60.0) -[2023-10-16 02:56:37,351][03835] Avg episode reward: [(0, '2.600'), (1, '1.940')] -[2023-10-16 02:56:37,506][05219] Updated weights for policy 1, policy_version 4450 (0.0008) -[2023-10-16 02:56:37,875][05219] Updated weights for policy 1, policy_version 4460 (0.0009) -[2023-10-16 02:56:38,246][05219] Updated weights for policy 1, policy_version 4470 (0.0007) -[2023-10-16 02:56:38,619][05219] Updated weights for policy 1, policy_version 4480 (0.0008) -[2023-10-16 02:56:38,772][05218] Updated weights for policy 0, policy_version 4482 (0.0009) -[2023-10-16 02:56:39,170][05218] Updated weights for policy 0, policy_version 4492 (0.0009) -[2023-10-16 02:56:39,553][05218] Updated weights for policy 0, policy_version 4502 (0.0007) -[2023-10-16 02:56:39,937][05218] Updated weights for policy 0, policy_version 4512 (0.0008) -[2023-10-16 02:56:42,341][05219] Updated weights for policy 1, policy_version 4490 (0.0010) -[2023-10-16 02:56:42,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 9207808. Throughput: 0: 1791.0, 1: 1769.3. Samples: 2310184. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-16 02:56:42,351][03835] Avg episode reward: [(0, '2.520'), (1, '2.360')] -[2023-10-16 02:56:42,708][05219] Updated weights for policy 1, policy_version 4500 (0.0007) -[2023-10-16 02:56:43,084][05219] Updated weights for policy 1, policy_version 4510 (0.0009) -[2023-10-16 02:56:43,564][05218] Updated weights for policy 0, policy_version 4522 (0.0009) -[2023-10-16 02:56:43,944][05218] Updated weights for policy 0, policy_version 4532 (0.0009) -[2023-10-16 02:56:44,321][05218] Updated weights for policy 0, policy_version 4542 (0.0009) -[2023-10-16 02:56:46,853][05219] Updated weights for policy 1, policy_version 4520 (0.0009) -[2023-10-16 02:56:47,216][05219] Updated weights for policy 1, policy_version 4530 (0.0007) -[2023-10-16 02:56:47,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 9273344. Throughput: 0: 1794.8, 1: 1789.3. Samples: 2332628. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-16 02:56:47,351][03835] Avg episode reward: [(0, '2.530'), (1, '2.390')] -[2023-10-16 02:56:47,593][05219] Updated weights for policy 1, policy_version 4540 (0.0008) -[2023-10-16 02:56:47,975][05218] Updated weights for policy 0, policy_version 4552 (0.0009) -[2023-10-16 02:56:48,357][05218] Updated weights for policy 0, policy_version 4562 (0.0007) -[2023-10-16 02:56:48,728][05218] Updated weights for policy 0, policy_version 4572 (0.0009) -[2023-10-16 02:56:51,507][05219] Updated weights for policy 1, policy_version 4550 (0.0008) -[2023-10-16 02:56:51,886][05219] Updated weights for policy 1, policy_version 4560 (0.0007) -[2023-10-16 02:56:52,252][05219] Updated weights for policy 1, policy_version 4570 (0.0010) -[2023-10-16 02:56:52,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 9338880. Throughput: 0: 1802.4, 1: 1780.3. Samples: 2353626. Policy #0 lag: (min: 20.0, avg: 24.6, max: 52.0) -[2023-10-16 02:56:52,351][03835] Avg episode reward: [(0, '2.310'), (1, '2.470')] -[2023-10-16 02:56:52,514][05218] Updated weights for policy 0, policy_version 4582 (0.0010) -[2023-10-16 02:56:52,897][05218] Updated weights for policy 0, policy_version 4592 (0.0010) -[2023-10-16 02:56:53,271][05218] Updated weights for policy 0, policy_version 4602 (0.0010) -[2023-10-16 02:56:55,966][05219] Updated weights for policy 1, policy_version 4580 (0.0009) -[2023-10-16 02:56:56,329][05219] Updated weights for policy 1, policy_version 4590 (0.0007) -[2023-10-16 02:56:56,689][05219] Updated weights for policy 1, policy_version 4600 (0.0008) -[2023-10-16 02:56:57,048][05218] Updated weights for policy 0, policy_version 4612 (0.0010) -[2023-10-16 02:56:57,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 9437184. Throughput: 0: 1791.3, 1: 1779.2. Samples: 2364396. Policy #0 lag: (min: 20.0, avg: 24.6, max: 52.0) -[2023-10-16 02:56:57,351][03835] Avg episode reward: [(0, '2.270'), (1, '2.370')] -[2023-10-16 02:56:57,420][05218] Updated weights for policy 0, policy_version 4622 (0.0008) -[2023-10-16 02:56:57,792][05218] Updated weights for policy 0, policy_version 4632 (0.0008) -[2023-10-16 02:57:00,370][05219] Updated weights for policy 1, policy_version 4610 (0.0007) -[2023-10-16 02:57:00,737][05219] Updated weights for policy 1, policy_version 4620 (0.0009) -[2023-10-16 02:57:01,102][05219] Updated weights for policy 1, policy_version 4630 (0.0008) -[2023-10-16 02:57:01,471][05219] Updated weights for policy 1, policy_version 4640 (0.0007) -[2023-10-16 02:57:01,508][05218] Updated weights for policy 0, policy_version 4642 (0.0007) -[2023-10-16 02:57:01,882][05218] Updated weights for policy 0, policy_version 4652 (0.0009) -[2023-10-16 02:57:02,258][05218] Updated weights for policy 0, policy_version 4662 (0.0007) -[2023-10-16 02:57:02,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 9502720. Throughput: 0: 1803.0, 1: 1781.9. Samples: 2386046. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-16 02:57:02,351][03835] Avg episode reward: [(0, '2.510'), (1, '2.390')] -[2023-10-16 02:57:02,636][05218] Updated weights for policy 0, policy_version 4672 (0.0007) -[2023-10-16 02:57:05,251][05219] Updated weights for policy 1, policy_version 4650 (0.0009) -[2023-10-16 02:57:05,612][05219] Updated weights for policy 1, policy_version 4660 (0.0011) -[2023-10-16 02:57:05,976][05219] Updated weights for policy 1, policy_version 4670 (0.0007) -[2023-10-16 02:57:06,304][05218] Updated weights for policy 0, policy_version 4682 (0.0012) -[2023-10-16 02:57:06,678][05218] Updated weights for policy 0, policy_version 4692 (0.0009) -[2023-10-16 02:57:07,048][05218] Updated weights for policy 0, policy_version 4702 (0.0010) -[2023-10-16 02:57:07,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 9601024. Throughput: 0: 1789.6, 1: 1770.4. Samples: 2406366. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 02:57:07,351][03835] Avg episode reward: [(0, '2.600'), (1, '2.380')] -[2023-10-16 02:57:09,863][05219] Updated weights for policy 1, policy_version 4680 (0.0010) -[2023-10-16 02:57:10,236][05219] Updated weights for policy 1, policy_version 4690 (0.0009) -[2023-10-16 02:57:10,599][05219] Updated weights for policy 1, policy_version 4700 (0.0008) -[2023-10-16 02:57:10,802][05218] Updated weights for policy 0, policy_version 4712 (0.0009) -[2023-10-16 02:57:11,175][05218] Updated weights for policy 0, policy_version 4722 (0.0008) -[2023-10-16 02:57:11,557][05218] Updated weights for policy 0, policy_version 4732 (0.0008) -[2023-10-16 02:57:12,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 9666560. Throughput: 0: 1794.9, 1: 1789.7. Samples: 2418444. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 02:57:12,351][03835] Avg episode reward: [(0, '2.390'), (1, '2.100')] -[2023-10-16 02:57:14,365][05219] Updated weights for policy 1, policy_version 4710 (0.0009) -[2023-10-16 02:57:14,738][05219] Updated weights for policy 1, policy_version 4720 (0.0008) -[2023-10-16 02:57:15,110][05219] Updated weights for policy 1, policy_version 4730 (0.0007) -[2023-10-16 02:57:15,379][05218] Updated weights for policy 0, policy_version 4742 (0.0008) -[2023-10-16 02:57:15,754][05218] Updated weights for policy 0, policy_version 4752 (0.0010) -[2023-10-16 02:57:16,133][05218] Updated weights for policy 0, policy_version 4762 (0.0009) -[2023-10-16 02:57:17,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 9732096. Throughput: 0: 1787.6, 1: 1777.1. Samples: 2438748. Policy #0 lag: (min: 0.0, avg: 22.8, max: 32.0) -[2023-10-16 02:57:17,352][03835] Avg episode reward: [(0, '2.190'), (1, '2.160')] -[2023-10-16 02:57:18,890][05219] Updated weights for policy 1, policy_version 4740 (0.0008) -[2023-10-16 02:57:19,247][05219] Updated weights for policy 1, policy_version 4750 (0.0008) -[2023-10-16 02:57:19,616][05219] Updated weights for policy 1, policy_version 4760 (0.0007) -[2023-10-16 02:57:19,935][05218] Updated weights for policy 0, policy_version 4772 (0.0008) -[2023-10-16 02:57:20,301][05218] Updated weights for policy 0, policy_version 4782 (0.0008) -[2023-10-16 02:57:20,677][05218] Updated weights for policy 0, policy_version 4792 (0.0008) -[2023-10-16 02:57:22,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 9797632. Throughput: 0: 1788.0, 1: 1777.0. Samples: 2460860. Policy #0 lag: (min: 0.0, avg: 22.8, max: 32.0) -[2023-10-16 02:57:22,351][03835] Avg episode reward: [(0, '2.610'), (1, '2.290')] -[2023-10-16 02:57:23,554][05219] Updated weights for policy 1, policy_version 4770 (0.0008) -[2023-10-16 02:57:23,922][05219] Updated weights for policy 1, policy_version 4780 (0.0009) -[2023-10-16 02:57:24,289][05219] Updated weights for policy 1, policy_version 4790 (0.0010) -[2023-10-16 02:57:24,428][05218] Updated weights for policy 0, policy_version 4802 (0.0011) -[2023-10-16 02:57:24,649][05219] Updated weights for policy 1, policy_version 4800 (0.0007) -[2023-10-16 02:57:24,845][05218] Updated weights for policy 0, policy_version 4812 (0.0008) -[2023-10-16 02:57:25,214][05218] Updated weights for policy 0, policy_version 4822 (0.0008) -[2023-10-16 02:57:25,593][05218] Updated weights for policy 0, policy_version 4832 (0.0008) -[2023-10-16 02:57:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 9863168. Throughput: 0: 1793.0, 1: 1775.5. Samples: 2470766. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-16 02:57:27,351][03835] Avg episode reward: [(0, '2.620'), (1, '2.200')] -[2023-10-16 02:57:28,385][05219] Updated weights for policy 1, policy_version 4810 (0.0009) -[2023-10-16 02:57:28,752][05219] Updated weights for policy 1, policy_version 4820 (0.0009) -[2023-10-16 02:57:29,123][05219] Updated weights for policy 1, policy_version 4830 (0.0007) -[2023-10-16 02:57:29,394][05218] Updated weights for policy 0, policy_version 4842 (0.0010) -[2023-10-16 02:57:29,775][05218] Updated weights for policy 0, policy_version 4852 (0.0010) -[2023-10-16 02:57:30,159][05218] Updated weights for policy 0, policy_version 4862 (0.0009) -[2023-10-16 02:57:32,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 9928704. Throughput: 0: 1781.2, 1: 1779.2. Samples: 2492842. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-16 02:57:32,351][03835] Avg episode reward: [(0, '2.430'), (1, '2.250')] -[2023-10-16 02:57:32,896][05219] Updated weights for policy 1, policy_version 4840 (0.0008) -[2023-10-16 02:57:33,264][05219] Updated weights for policy 1, policy_version 4850 (0.0008) -[2023-10-16 02:57:33,624][05219] Updated weights for policy 1, policy_version 4860 (0.0007) -[2023-10-16 02:57:34,003][05218] Updated weights for policy 0, policy_version 4872 (0.0009) -[2023-10-16 02:57:34,380][05218] Updated weights for policy 0, policy_version 4882 (0.0009) -[2023-10-16 02:57:34,762][05218] Updated weights for policy 0, policy_version 4892 (0.0007) -[2023-10-16 02:57:37,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 9994240. Throughput: 0: 1784.2, 1: 1804.6. Samples: 2515122. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-16 02:57:37,351][03835] Avg episode reward: [(0, '2.390'), (1, '2.310')] -[2023-10-16 02:57:37,358][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000004896_5013504.pth... -[2023-10-16 02:57:37,388][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000003232_3309568.pth -[2023-10-16 02:57:37,539][05219] Updated weights for policy 1, policy_version 4870 (0.0009) -[2023-10-16 02:57:37,921][05219] Updated weights for policy 1, policy_version 4880 (0.0008) -[2023-10-16 02:57:38,283][05219] Updated weights for policy 1, policy_version 4890 (0.0007) -[2023-10-16 02:57:38,404][05218] Updated weights for policy 0, policy_version 4902 (0.0008) -[2023-10-16 02:57:38,492][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000004896_5013504.pth... -[2023-10-16 02:57:38,534][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000003200_3276800.pth -[2023-10-16 02:57:38,776][05218] Updated weights for policy 0, policy_version 4912 (0.0009) -[2023-10-16 02:57:39,160][05218] Updated weights for policy 0, policy_version 4922 (0.0007) -[2023-10-16 02:57:42,128][05219] Updated weights for policy 1, policy_version 4900 (0.0008) -[2023-10-16 02:57:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 10059776. Throughput: 0: 1783.2, 1: 1780.2. Samples: 2524746. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-16 02:57:42,351][03835] Avg episode reward: [(0, '2.500'), (1, '2.180')] -[2023-10-16 02:57:42,501][05219] Updated weights for policy 1, policy_version 4910 (0.0009) -[2023-10-16 02:57:42,872][05219] Updated weights for policy 1, policy_version 4920 (0.0009) -[2023-10-16 02:57:42,931][05218] Updated weights for policy 0, policy_version 4932 (0.0007) -[2023-10-16 02:57:43,312][05218] Updated weights for policy 0, policy_version 4942 (0.0008) -[2023-10-16 02:57:43,691][05218] Updated weights for policy 0, policy_version 4952 (0.0007) -[2023-10-16 02:57:46,627][05219] Updated weights for policy 1, policy_version 4930 (0.0008) -[2023-10-16 02:57:46,998][05219] Updated weights for policy 1, policy_version 4940 (0.0008) -[2023-10-16 02:57:47,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 10125312. Throughput: 0: 1776.0, 1: 1793.5. Samples: 2546674. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-16 02:57:47,351][03835] Avg episode reward: [(0, '2.720'), (1, '2.260')] -[2023-10-16 02:57:47,367][05219] Updated weights for policy 1, policy_version 4950 (0.0009) -[2023-10-16 02:57:47,493][05218] Updated weights for policy 0, policy_version 4962 (0.0009) -[2023-10-16 02:57:47,731][05219] Updated weights for policy 1, policy_version 4960 (0.0007) -[2023-10-16 02:57:47,865][05218] Updated weights for policy 0, policy_version 4972 (0.0007) -[2023-10-16 02:57:48,235][05218] Updated weights for policy 0, policy_version 4982 (0.0007) -[2023-10-16 02:57:48,608][05218] Updated weights for policy 0, policy_version 4992 (0.0009) -[2023-10-16 02:57:51,617][05219] Updated weights for policy 1, policy_version 4970 (0.0009) -[2023-10-16 02:57:51,987][05219] Updated weights for policy 1, policy_version 4980 (0.0010) -[2023-10-16 02:57:52,300][05218] Updated weights for policy 0, policy_version 5002 (0.0007) -[2023-10-16 02:57:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 10190848. Throughput: 0: 1798.9, 1: 1774.7. Samples: 2567178. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-16 02:57:52,351][03835] Avg episode reward: [(0, '2.490'), (1, '2.490')] -[2023-10-16 02:57:52,361][05219] Updated weights for policy 1, policy_version 4990 (0.0008) -[2023-10-16 02:57:52,683][05218] Updated weights for policy 0, policy_version 5012 (0.0008) -[2023-10-16 02:57:53,072][05218] Updated weights for policy 0, policy_version 5022 (0.0009) -[2023-10-16 02:57:56,209][05219] Updated weights for policy 1, policy_version 5000 (0.0008) -[2023-10-16 02:57:56,561][05219] Updated weights for policy 1, policy_version 5010 (0.0008) -[2023-10-16 02:57:56,930][05219] Updated weights for policy 1, policy_version 5020 (0.0008) -[2023-10-16 02:57:56,940][05218] Updated weights for policy 0, policy_version 5032 (0.0008) -[2023-10-16 02:57:57,318][05218] Updated weights for policy 0, policy_version 5042 (0.0007) -[2023-10-16 02:57:57,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 10289152. Throughput: 0: 1775.7, 1: 1779.5. Samples: 2578428. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-16 02:57:57,351][03835] Avg episode reward: [(0, '2.370'), (1, '2.460')] -[2023-10-16 02:57:57,695][05218] Updated weights for policy 0, policy_version 5052 (0.0009) -[2023-10-16 02:58:00,736][05219] Updated weights for policy 1, policy_version 5030 (0.0009) -[2023-10-16 02:58:01,101][05219] Updated weights for policy 1, policy_version 5040 (0.0010) -[2023-10-16 02:58:01,468][05219] Updated weights for policy 1, policy_version 5050 (0.0008) -[2023-10-16 02:58:01,516][05218] Updated weights for policy 0, policy_version 5062 (0.0007) -[2023-10-16 02:58:01,896][05218] Updated weights for policy 0, policy_version 5072 (0.0008) -[2023-10-16 02:58:02,273][05218] Updated weights for policy 0, policy_version 5082 (0.0007) -[2023-10-16 02:58:02,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 10354688. Throughput: 0: 1803.7, 1: 1771.8. Samples: 2599644. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-16 02:58:02,351][03835] Avg episode reward: [(0, '2.430'), (1, '2.220')] -[2023-10-16 02:58:05,228][05219] Updated weights for policy 1, policy_version 5060 (0.0007) -[2023-10-16 02:58:05,593][05219] Updated weights for policy 1, policy_version 5070 (0.0008) -[2023-10-16 02:58:05,965][05219] Updated weights for policy 1, policy_version 5080 (0.0009) -[2023-10-16 02:58:06,158][05218] Updated weights for policy 0, policy_version 5092 (0.0008) -[2023-10-16 02:58:06,537][05218] Updated weights for policy 0, policy_version 5102 (0.0008) -[2023-10-16 02:58:06,907][05218] Updated weights for policy 0, policy_version 5112 (0.0009) -[2023-10-16 02:58:07,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 10452992. Throughput: 0: 1769.9, 1: 1753.6. Samples: 2619420. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:58:07,352][03835] Avg episode reward: [(0, '2.550'), (1, '2.170')] -[2023-10-16 02:58:09,760][05219] Updated weights for policy 1, policy_version 5090 (0.0007) -[2023-10-16 02:58:10,128][05219] Updated weights for policy 1, policy_version 5100 (0.0009) -[2023-10-16 02:58:10,500][05219] Updated weights for policy 1, policy_version 5110 (0.0008) -[2023-10-16 02:58:10,662][05218] Updated weights for policy 0, policy_version 5122 (0.0010) -[2023-10-16 02:58:10,861][05219] Updated weights for policy 1, policy_version 5120 (0.0009) -[2023-10-16 02:58:11,065][05218] Updated weights for policy 0, policy_version 5132 (0.0009) -[2023-10-16 02:58:11,454][05218] Updated weights for policy 0, policy_version 5142 (0.0009) -[2023-10-16 02:58:11,815][05218] Updated weights for policy 0, policy_version 5152 (0.0009) -[2023-10-16 02:58:12,350][03835] Fps is (10 sec: 16383.4, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 10518528. Throughput: 0: 1798.7, 1: 1776.6. Samples: 2631654. Policy #0 lag: (min: 4.0, avg: 30.3, max: 32.0) -[2023-10-16 02:58:12,352][03835] Avg episode reward: [(0, '2.530'), (1, '2.240')] -[2023-10-16 02:58:14,713][05219] Updated weights for policy 1, policy_version 5130 (0.0011) -[2023-10-16 02:58:15,076][05219] Updated weights for policy 1, policy_version 5140 (0.0009) -[2023-10-16 02:58:15,445][05219] Updated weights for policy 1, policy_version 5150 (0.0008) -[2023-10-16 02:58:15,524][05218] Updated weights for policy 0, policy_version 5162 (0.0007) -[2023-10-16 02:58:15,901][05218] Updated weights for policy 0, policy_version 5172 (0.0008) -[2023-10-16 02:58:16,289][05218] Updated weights for policy 0, policy_version 5182 (0.0007) -[2023-10-16 02:58:17,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 10584064. Throughput: 0: 1774.2, 1: 1751.8. Samples: 2651514. Policy #0 lag: (min: 4.0, avg: 30.3, max: 32.0) -[2023-10-16 02:58:17,351][03835] Avg episode reward: [(0, '2.390'), (1, '2.500')] -[2023-10-16 02:58:19,190][05219] Updated weights for policy 1, policy_version 5160 (0.0009) -[2023-10-16 02:58:19,557][05219] Updated weights for policy 1, policy_version 5170 (0.0009) -[2023-10-16 02:58:19,917][05219] Updated weights for policy 1, policy_version 5180 (0.0007) -[2023-10-16 02:58:19,936][05218] Updated weights for policy 0, policy_version 5192 (0.0008) -[2023-10-16 02:58:20,304][05218] Updated weights for policy 0, policy_version 5202 (0.0008) -[2023-10-16 02:58:20,677][05218] Updated weights for policy 0, policy_version 5212 (0.0011) -[2023-10-16 02:58:22,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 10649600. Throughput: 0: 1768.0, 1: 1757.9. Samples: 2673786. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-16 02:58:22,351][03835] Avg episode reward: [(0, '2.370'), (1, '2.520')] -[2023-10-16 02:58:23,815][05219] Updated weights for policy 1, policy_version 5190 (0.0008) -[2023-10-16 02:58:24,188][05219] Updated weights for policy 1, policy_version 5200 (0.0009) -[2023-10-16 02:58:24,552][05218] Updated weights for policy 0, policy_version 5222 (0.0008) -[2023-10-16 02:58:24,553][05219] Updated weights for policy 1, policy_version 5210 (0.0008) -[2023-10-16 02:58:24,928][05218] Updated weights for policy 0, policy_version 5232 (0.0008) -[2023-10-16 02:58:25,305][05218] Updated weights for policy 0, policy_version 5242 (0.0008) -[2023-10-16 02:58:27,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 10715136. Throughput: 0: 1773.8, 1: 1755.2. Samples: 2683554. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-16 02:58:27,351][03835] Avg episode reward: [(0, '2.310'), (1, '2.380')] -[2023-10-16 02:58:28,404][05219] Updated weights for policy 1, policy_version 5220 (0.0009) -[2023-10-16 02:58:28,772][05219] Updated weights for policy 1, policy_version 5230 (0.0008) -[2023-10-16 02:58:28,976][05218] Updated weights for policy 0, policy_version 5252 (0.0009) -[2023-10-16 02:58:29,135][05219] Updated weights for policy 1, policy_version 5240 (0.0008) -[2023-10-16 02:58:29,347][05218] Updated weights for policy 0, policy_version 5262 (0.0008) -[2023-10-16 02:58:29,725][05218] Updated weights for policy 0, policy_version 5272 (0.0008) -[2023-10-16 02:58:32,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 10780672. Throughput: 0: 1772.2, 1: 1764.3. Samples: 2705818. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-16 02:58:32,352][03835] Avg episode reward: [(0, '2.190'), (1, '2.260')] -[2023-10-16 02:58:32,873][05219] Updated weights for policy 1, policy_version 5250 (0.0009) -[2023-10-16 02:58:33,240][05219] Updated weights for policy 1, policy_version 5260 (0.0008) -[2023-10-16 02:58:33,605][05218] Updated weights for policy 0, policy_version 5282 (0.0009) -[2023-10-16 02:58:33,616][05219] Updated weights for policy 1, policy_version 5270 (0.0007) -[2023-10-16 02:58:33,977][05219] Updated weights for policy 1, policy_version 5280 (0.0007) -[2023-10-16 02:58:33,982][05218] Updated weights for policy 0, policy_version 5292 (0.0008) -[2023-10-16 02:58:34,355][05218] Updated weights for policy 0, policy_version 5302 (0.0008) -[2023-10-16 02:58:34,733][05218] Updated weights for policy 0, policy_version 5312 (0.0008) -[2023-10-16 02:58:37,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 10846208. Throughput: 0: 1776.2, 1: 1795.3. Samples: 2727894. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-16 02:58:37,351][03835] Avg episode reward: [(0, '2.430'), (1, '2.200')] -[2023-10-16 02:58:37,627][05219] Updated weights for policy 1, policy_version 5290 (0.0007) -[2023-10-16 02:58:37,994][05219] Updated weights for policy 1, policy_version 5300 (0.0009) -[2023-10-16 02:58:38,364][05219] Updated weights for policy 1, policy_version 5310 (0.0008) -[2023-10-16 02:58:38,426][05218] Updated weights for policy 0, policy_version 5322 (0.0009) -[2023-10-16 02:58:38,811][05218] Updated weights for policy 0, policy_version 5332 (0.0009) -[2023-10-16 02:58:39,186][05218] Updated weights for policy 0, policy_version 5342 (0.0007) -[2023-10-16 02:58:42,255][05219] Updated weights for policy 1, policy_version 5320 (0.0007) -[2023-10-16 02:58:42,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 10911744. Throughput: 0: 1762.7, 1: 1773.7. Samples: 2737568. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) -[2023-10-16 02:58:42,351][03835] Avg episode reward: [(0, '2.530'), (1, '2.240')] -[2023-10-16 02:58:42,626][05219] Updated weights for policy 1, policy_version 5330 (0.0008) -[2023-10-16 02:58:42,920][05218] Updated weights for policy 0, policy_version 5352 (0.0007) -[2023-10-16 02:58:42,980][05219] Updated weights for policy 1, policy_version 5340 (0.0008) -[2023-10-16 02:58:43,293][05218] Updated weights for policy 0, policy_version 5362 (0.0007) -[2023-10-16 02:58:43,668][05218] Updated weights for policy 0, policy_version 5372 (0.0009) -[2023-10-16 02:58:46,849][05219] Updated weights for policy 1, policy_version 5350 (0.0008) -[2023-10-16 02:58:47,219][05219] Updated weights for policy 1, policy_version 5360 (0.0007) -[2023-10-16 02:58:47,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 10977280. Throughput: 0: 1767.2, 1: 1792.0. Samples: 2759808. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) -[2023-10-16 02:58:47,351][03835] Avg episode reward: [(0, '2.380'), (1, '2.400')] -[2023-10-16 02:58:47,494][05218] Updated weights for policy 0, policy_version 5382 (0.0008) -[2023-10-16 02:58:47,584][05219] Updated weights for policy 1, policy_version 5370 (0.0007) -[2023-10-16 02:58:47,874][05218] Updated weights for policy 0, policy_version 5392 (0.0008) -[2023-10-16 02:58:48,244][05218] Updated weights for policy 0, policy_version 5402 (0.0010) -[2023-10-16 02:58:51,372][05219] Updated weights for policy 1, policy_version 5380 (0.0008) -[2023-10-16 02:58:51,722][05219] Updated weights for policy 1, policy_version 5390 (0.0010) -[2023-10-16 02:58:52,006][05218] Updated weights for policy 0, policy_version 5412 (0.0009) -[2023-10-16 02:58:52,094][05219] Updated weights for policy 1, policy_version 5400 (0.0008) -[2023-10-16 02:58:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 11042816. Throughput: 0: 1791.8, 1: 1784.3. Samples: 2780346. Policy #0 lag: (min: 3.0, avg: 10.4, max: 35.0) -[2023-10-16 02:58:52,351][03835] Avg episode reward: [(0, '2.570'), (1, '2.570')] -[2023-10-16 02:58:52,386][05218] Updated weights for policy 0, policy_version 5422 (0.0007) -[2023-10-16 02:58:52,759][05218] Updated weights for policy 0, policy_version 5432 (0.0009) -[2023-10-16 02:58:55,806][05219] Updated weights for policy 1, policy_version 5410 (0.0007) -[2023-10-16 02:58:56,164][05219] Updated weights for policy 1, policy_version 5420 (0.0009) -[2023-10-16 02:58:56,534][05219] Updated weights for policy 1, policy_version 5430 (0.0007) -[2023-10-16 02:58:56,606][05218] Updated weights for policy 0, policy_version 5442 (0.0010) -[2023-10-16 02:58:56,894][05219] Updated weights for policy 1, policy_version 5440 (0.0008) -[2023-10-16 02:58:57,001][05218] Updated weights for policy 0, policy_version 5452 (0.0010) -[2023-10-16 02:58:57,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 11141120. Throughput: 0: 1767.9, 1: 1785.5. Samples: 2791558. Policy #0 lag: (min: 3.0, avg: 10.4, max: 35.0) -[2023-10-16 02:58:57,351][03835] Avg episode reward: [(0, '2.400'), (1, '2.400')] -[2023-10-16 02:58:57,379][05218] Updated weights for policy 0, policy_version 5462 (0.0008) -[2023-10-16 02:58:57,763][05218] Updated weights for policy 0, policy_version 5472 (0.0009) -[2023-10-16 02:59:00,709][05219] Updated weights for policy 1, policy_version 5450 (0.0010) -[2023-10-16 02:59:01,076][05219] Updated weights for policy 1, policy_version 5460 (0.0010) -[2023-10-16 02:59:01,380][05218] Updated weights for policy 0, policy_version 5482 (0.0008) -[2023-10-16 02:59:01,442][05219] Updated weights for policy 1, policy_version 5470 (0.0007) -[2023-10-16 02:59:01,761][05218] Updated weights for policy 0, policy_version 5492 (0.0007) -[2023-10-16 02:59:02,137][05218] Updated weights for policy 0, policy_version 5502 (0.0008) -[2023-10-16 02:59:02,350][03835] Fps is (10 sec: 19660.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 11239424. Throughput: 0: 1791.4, 1: 1783.0. Samples: 2812364. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-16 02:59:02,351][03835] Avg episode reward: [(0, '2.230'), (1, '2.530')] -[2023-10-16 02:59:05,181][05219] Updated weights for policy 1, policy_version 5480 (0.0009) -[2023-10-16 02:59:05,548][05219] Updated weights for policy 1, policy_version 5490 (0.0010) -[2023-10-16 02:59:05,909][05219] Updated weights for policy 1, policy_version 5500 (0.0008) -[2023-10-16 02:59:05,911][05218] Updated weights for policy 0, policy_version 5512 (0.0009) -[2023-10-16 02:59:06,293][05218] Updated weights for policy 0, policy_version 5522 (0.0010) -[2023-10-16 02:59:06,667][05218] Updated weights for policy 0, policy_version 5532 (0.0010) -[2023-10-16 02:59:07,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 11304960. Throughput: 0: 1769.2, 1: 1765.1. Samples: 2832830. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:59:07,351][03835] Avg episode reward: [(0, '2.270'), (1, '2.470')] -[2023-10-16 02:59:09,768][05219] Updated weights for policy 1, policy_version 5510 (0.0008) -[2023-10-16 02:59:10,161][05219] Updated weights for policy 1, policy_version 5520 (0.0007) -[2023-10-16 02:59:10,513][05218] Updated weights for policy 0, policy_version 5542 (0.0009) -[2023-10-16 02:59:10,517][05219] Updated weights for policy 1, policy_version 5530 (0.0009) -[2023-10-16 02:59:10,886][05218] Updated weights for policy 0, policy_version 5552 (0.0011) -[2023-10-16 02:59:11,268][05218] Updated weights for policy 0, policy_version 5562 (0.0011) -[2023-10-16 02:59:12,351][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 11370496. Throughput: 0: 1799.9, 1: 1785.1. Samples: 2844882. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:59:12,352][03835] Avg episode reward: [(0, '2.250'), (1, '2.660')] -[2023-10-16 02:59:14,246][05219] Updated weights for policy 1, policy_version 5540 (0.0009) -[2023-10-16 02:59:14,608][05219] Updated weights for policy 1, policy_version 5550 (0.0008) -[2023-10-16 02:59:14,980][05219] Updated weights for policy 1, policy_version 5560 (0.0007) -[2023-10-16 02:59:15,094][05218] Updated weights for policy 0, policy_version 5572 (0.0009) -[2023-10-16 02:59:15,466][05218] Updated weights for policy 0, policy_version 5582 (0.0008) -[2023-10-16 02:59:15,839][05218] Updated weights for policy 0, policy_version 5592 (0.0010) -[2023-10-16 02:59:17,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 11436032. Throughput: 0: 1774.1, 1: 1773.1. Samples: 2865442. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:59:17,351][03835] Avg episode reward: [(0, '2.470'), (1, '2.540')] -[2023-10-16 02:59:18,709][05219] Updated weights for policy 1, policy_version 5570 (0.0007) -[2023-10-16 02:59:19,076][05219] Updated weights for policy 1, policy_version 5580 (0.0009) -[2023-10-16 02:59:19,441][05219] Updated weights for policy 1, policy_version 5590 (0.0008) -[2023-10-16 02:59:19,533][05218] Updated weights for policy 0, policy_version 5602 (0.0010) -[2023-10-16 02:59:19,805][05219] Updated weights for policy 1, policy_version 5600 (0.0008) -[2023-10-16 02:59:19,902][05218] Updated weights for policy 0, policy_version 5612 (0.0009) -[2023-10-16 02:59:20,280][05218] Updated weights for policy 0, policy_version 5622 (0.0012) -[2023-10-16 02:59:20,655][05218] Updated weights for policy 0, policy_version 5632 (0.0009) -[2023-10-16 02:59:22,351][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 11501568. Throughput: 0: 1781.2, 1: 1771.5. Samples: 2887768. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 02:59:22,352][03835] Avg episode reward: [(0, '2.520'), (1, '2.360')] -[2023-10-16 02:59:23,622][05219] Updated weights for policy 1, policy_version 5610 (0.0008) -[2023-10-16 02:59:23,978][05219] Updated weights for policy 1, policy_version 5620 (0.0007) -[2023-10-16 02:59:24,341][05219] Updated weights for policy 1, policy_version 5630 (0.0007) -[2023-10-16 02:59:24,409][05218] Updated weights for policy 0, policy_version 5642 (0.0008) -[2023-10-16 02:59:24,790][05218] Updated weights for policy 0, policy_version 5652 (0.0009) -[2023-10-16 02:59:25,173][05218] Updated weights for policy 0, policy_version 5662 (0.0009) -[2023-10-16 02:59:27,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 11567104. Throughput: 0: 1787.7, 1: 1769.3. Samples: 2897632. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-10-16 02:59:27,351][03835] Avg episode reward: [(0, '2.590'), (1, '2.270')] -[2023-10-16 02:59:28,200][05219] Updated weights for policy 1, policy_version 5640 (0.0008) -[2023-10-16 02:59:28,566][05219] Updated weights for policy 1, policy_version 5650 (0.0008) -[2023-10-16 02:59:28,928][05219] Updated weights for policy 1, policy_version 5660 (0.0007) -[2023-10-16 02:59:28,990][05218] Updated weights for policy 0, policy_version 5672 (0.0008) -[2023-10-16 02:59:29,354][05218] Updated weights for policy 0, policy_version 5682 (0.0011) -[2023-10-16 02:59:29,730][05218] Updated weights for policy 0, policy_version 5692 (0.0011) -[2023-10-16 02:59:32,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 11632640. Throughput: 0: 1783.8, 1: 1769.6. Samples: 2919714. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-10-16 02:59:32,351][03835] Avg episode reward: [(0, '2.270'), (1, '2.520')] -[2023-10-16 02:59:32,623][05219] Updated weights for policy 1, policy_version 5670 (0.0010) -[2023-10-16 02:59:32,990][05219] Updated weights for policy 1, policy_version 5680 (0.0010) -[2023-10-16 02:59:33,358][05219] Updated weights for policy 1, policy_version 5690 (0.0008) -[2023-10-16 02:59:33,398][05218] Updated weights for policy 0, policy_version 5702 (0.0010) -[2023-10-16 02:59:33,784][05218] Updated weights for policy 0, policy_version 5712 (0.0010) -[2023-10-16 02:59:34,148][05218] Updated weights for policy 0, policy_version 5722 (0.0009) -[2023-10-16 02:59:37,168][05219] Updated weights for policy 1, policy_version 5700 (0.0007) -[2023-10-16 02:59:37,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 11698176. Throughput: 0: 1795.8, 1: 1798.3. Samples: 2942084. Policy #0 lag: (min: 1.0, avg: 12.5, max: 33.0) -[2023-10-16 02:59:37,351][03835] Avg episode reward: [(0, '2.390'), (1, '2.330')] -[2023-10-16 02:59:37,361][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000005728_5865472.pth... -[2023-10-16 02:59:37,402][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000004064_4161536.pth -[2023-10-16 02:59:37,536][05219] Updated weights for policy 1, policy_version 5710 (0.0008) -[2023-10-16 02:59:37,893][05219] Updated weights for policy 1, policy_version 5720 (0.0007) -[2023-10-16 02:59:37,997][05218] Updated weights for policy 0, policy_version 5732 (0.0008) -[2023-10-16 02:59:38,185][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000005728_5865472.pth... -[2023-10-16 02:59:38,213][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000004032_4128768.pth -[2023-10-16 02:59:38,376][05218] Updated weights for policy 0, policy_version 5742 (0.0009) -[2023-10-16 02:59:38,750][05218] Updated weights for policy 0, policy_version 5752 (0.0007) -[2023-10-16 02:59:41,598][05219] Updated weights for policy 1, policy_version 5730 (0.0007) -[2023-10-16 02:59:41,963][05219] Updated weights for policy 1, policy_version 5740 (0.0007) -[2023-10-16 02:59:42,332][05219] Updated weights for policy 1, policy_version 5750 (0.0010) -[2023-10-16 02:59:42,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 11763712. Throughput: 0: 1784.8, 1: 1780.5. Samples: 2951998. Policy #0 lag: (min: 1.0, avg: 12.5, max: 33.0) -[2023-10-16 02:59:42,351][03835] Avg episode reward: [(0, '2.600'), (1, '2.420')] -[2023-10-16 02:59:42,462][05218] Updated weights for policy 0, policy_version 5762 (0.0008) -[2023-10-16 02:59:42,704][05219] Updated weights for policy 1, policy_version 5760 (0.0008) -[2023-10-16 02:59:42,835][05218] Updated weights for policy 0, policy_version 5772 (0.0007) -[2023-10-16 02:59:43,213][05218] Updated weights for policy 0, policy_version 5782 (0.0009) -[2023-10-16 02:59:43,588][05218] Updated weights for policy 0, policy_version 5792 (0.0010) -[2023-10-16 02:59:46,643][05219] Updated weights for policy 1, policy_version 5770 (0.0007) -[2023-10-16 02:59:47,007][05219] Updated weights for policy 1, policy_version 5780 (0.0008) -[2023-10-16 02:59:47,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 11829248. Throughput: 0: 1790.8, 1: 1801.5. Samples: 2974020. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-16 02:59:47,351][03835] Avg episode reward: [(0, '2.520'), (1, '2.450')] -[2023-10-16 02:59:47,381][05219] Updated weights for policy 1, policy_version 5790 (0.0008) -[2023-10-16 02:59:47,456][05218] Updated weights for policy 0, policy_version 5802 (0.0009) -[2023-10-16 02:59:47,829][05218] Updated weights for policy 0, policy_version 5812 (0.0008) -[2023-10-16 02:59:48,196][05218] Updated weights for policy 0, policy_version 5822 (0.0008) -[2023-10-16 02:59:51,331][05219] Updated weights for policy 1, policy_version 5800 (0.0007) -[2023-10-16 02:59:51,695][05219] Updated weights for policy 1, policy_version 5810 (0.0009) -[2023-10-16 02:59:52,065][05219] Updated weights for policy 1, policy_version 5820 (0.0010) -[2023-10-16 02:59:52,075][05218] Updated weights for policy 0, policy_version 5832 (0.0009) -[2023-10-16 02:59:52,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 11927552. Throughput: 0: 1800.8, 1: 1784.7. Samples: 2994176. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-16 02:59:52,351][03835] Avg episode reward: [(0, '2.400'), (1, '2.610')] -[2023-10-16 02:59:52,446][05218] Updated weights for policy 0, policy_version 5842 (0.0011) -[2023-10-16 02:59:52,819][05218] Updated weights for policy 0, policy_version 5852 (0.0008) -[2023-10-16 02:59:55,753][05219] Updated weights for policy 1, policy_version 5830 (0.0009) -[2023-10-16 02:59:56,124][05219] Updated weights for policy 1, policy_version 5840 (0.0009) -[2023-10-16 02:59:56,490][05219] Updated weights for policy 1, policy_version 5850 (0.0007) -[2023-10-16 02:59:56,587][05218] Updated weights for policy 0, policy_version 5862 (0.0008) -[2023-10-16 02:59:56,968][05218] Updated weights for policy 0, policy_version 5872 (0.0008) -[2023-10-16 02:59:57,337][05218] Updated weights for policy 0, policy_version 5882 (0.0010) -[2023-10-16 02:59:57,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 11993088. Throughput: 0: 1773.2, 1: 1802.0. Samples: 3005766. Policy #0 lag: (min: 17.0, avg: 20.9, max: 49.0) -[2023-10-16 02:59:57,351][03835] Avg episode reward: [(0, '2.410'), (1, '2.610')] -[2023-10-16 03:00:00,353][05219] Updated weights for policy 1, policy_version 5860 (0.0007) -[2023-10-16 03:00:00,724][05219] Updated weights for policy 1, policy_version 5870 (0.0010) -[2023-10-16 03:00:01,076][05218] Updated weights for policy 0, policy_version 5892 (0.0007) -[2023-10-16 03:00:01,077][05219] Updated weights for policy 1, policy_version 5880 (0.0008) -[2023-10-16 03:00:01,453][05218] Updated weights for policy 0, policy_version 5902 (0.0007) -[2023-10-16 03:00:01,826][05218] Updated weights for policy 0, policy_version 5912 (0.0009) -[2023-10-16 03:00:02,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 12091392. Throughput: 0: 1792.3, 1: 1782.1. Samples: 3026288. Policy #0 lag: (min: 7.0, avg: 14.2, max: 39.0) -[2023-10-16 03:00:02,351][03835] Avg episode reward: [(0, '2.550'), (1, '2.480')] -[2023-10-16 03:00:04,714][05219] Updated weights for policy 1, policy_version 5890 (0.0008) -[2023-10-16 03:00:05,083][05219] Updated weights for policy 1, policy_version 5900 (0.0007) -[2023-10-16 03:00:05,455][05219] Updated weights for policy 1, policy_version 5910 (0.0009) -[2023-10-16 03:00:05,661][05218] Updated weights for policy 0, policy_version 5922 (0.0008) -[2023-10-16 03:00:05,822][05219] Updated weights for policy 1, policy_version 5920 (0.0008) -[2023-10-16 03:00:06,039][05218] Updated weights for policy 0, policy_version 5932 (0.0008) -[2023-10-16 03:00:06,421][05218] Updated weights for policy 0, policy_version 5942 (0.0008) -[2023-10-16 03:00:06,803][05218] Updated weights for policy 0, policy_version 5952 (0.0007) -[2023-10-16 03:00:07,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 12156928. Throughput: 0: 1768.2, 1: 1777.1. Samples: 3047306. Policy #0 lag: (min: 7.0, avg: 14.2, max: 39.0) -[2023-10-16 03:00:07,351][03835] Avg episode reward: [(0, '2.450'), (1, '2.320')] -[2023-10-16 03:00:09,687][05219] Updated weights for policy 1, policy_version 5930 (0.0007) -[2023-10-16 03:00:10,051][05219] Updated weights for policy 1, policy_version 5940 (0.0008) -[2023-10-16 03:00:10,422][05219] Updated weights for policy 1, policy_version 5950 (0.0009) -[2023-10-16 03:00:10,624][05218] Updated weights for policy 0, policy_version 5962 (0.0010) -[2023-10-16 03:00:11,009][05218] Updated weights for policy 0, policy_version 5972 (0.0011) -[2023-10-16 03:00:11,389][05218] Updated weights for policy 0, policy_version 5982 (0.0010) -[2023-10-16 03:00:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.6, 300 sec: 14329.1). Total num frames: 12222464. Throughput: 0: 1797.6, 1: 1787.5. Samples: 3058960. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:00:12,351][03835] Avg episode reward: [(0, '2.330'), (1, '2.220')] -[2023-10-16 03:00:14,313][05219] Updated weights for policy 1, policy_version 5960 (0.0009) -[2023-10-16 03:00:14,686][05219] Updated weights for policy 1, policy_version 5970 (0.0008) -[2023-10-16 03:00:15,010][05218] Updated weights for policy 0, policy_version 5992 (0.0009) -[2023-10-16 03:00:15,049][05219] Updated weights for policy 1, policy_version 5980 (0.0011) -[2023-10-16 03:00:15,392][05218] Updated weights for policy 0, policy_version 6002 (0.0008) -[2023-10-16 03:00:15,766][05218] Updated weights for policy 0, policy_version 6012 (0.0008) -[2023-10-16 03:00:17,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 12288000. Throughput: 0: 1772.4, 1: 1774.0. Samples: 3079300. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:00:17,352][03835] Avg episode reward: [(0, '2.320'), (1, '2.300')] -[2023-10-16 03:00:18,815][05219] Updated weights for policy 1, policy_version 5990 (0.0008) -[2023-10-16 03:00:19,189][05219] Updated weights for policy 1, policy_version 6000 (0.0008) -[2023-10-16 03:00:19,519][05218] Updated weights for policy 0, policy_version 6022 (0.0008) -[2023-10-16 03:00:19,553][05219] Updated weights for policy 1, policy_version 6010 (0.0009) -[2023-10-16 03:00:19,897][05218] Updated weights for policy 0, policy_version 6032 (0.0010) -[2023-10-16 03:00:20,270][05218] Updated weights for policy 0, policy_version 6042 (0.0008) -[2023-10-16 03:00:22,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 12353536. Throughput: 0: 1765.7, 1: 1776.0. Samples: 3101458. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:00:22,351][03835] Avg episode reward: [(0, '2.270'), (1, '2.220')] -[2023-10-16 03:00:23,202][05219] Updated weights for policy 1, policy_version 6020 (0.0009) -[2023-10-16 03:00:23,572][05219] Updated weights for policy 1, policy_version 6030 (0.0010) -[2023-10-16 03:00:23,935][05219] Updated weights for policy 1, policy_version 6040 (0.0010) -[2023-10-16 03:00:24,046][05218] Updated weights for policy 0, policy_version 6052 (0.0009) -[2023-10-16 03:00:24,413][05218] Updated weights for policy 0, policy_version 6062 (0.0008) -[2023-10-16 03:00:24,790][05218] Updated weights for policy 0, policy_version 6072 (0.0008) -[2023-10-16 03:00:27,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 12419072. Throughput: 0: 1767.0, 1: 1774.5. Samples: 3111366. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:00:27,351][03835] Avg episode reward: [(0, '2.090'), (1, '2.390')] -[2023-10-16 03:00:27,526][05219] Updated weights for policy 1, policy_version 6050 (0.0008) -[2023-10-16 03:00:27,892][05219] Updated weights for policy 1, policy_version 6060 (0.0007) -[2023-10-16 03:00:28,266][05219] Updated weights for policy 1, policy_version 6070 (0.0007) -[2023-10-16 03:00:28,594][05218] Updated weights for policy 0, policy_version 6082 (0.0009) -[2023-10-16 03:00:28,638][05219] Updated weights for policy 1, policy_version 6080 (0.0009) -[2023-10-16 03:00:29,005][05218] Updated weights for policy 0, policy_version 6092 (0.0010) -[2023-10-16 03:00:29,372][05218] Updated weights for policy 0, policy_version 6102 (0.0008) -[2023-10-16 03:00:29,753][05218] Updated weights for policy 0, policy_version 6112 (0.0008) -[2023-10-16 03:00:32,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 12484608. Throughput: 0: 1767.5, 1: 1782.5. Samples: 3133768. Policy #0 lag: (min: 24.0, avg: 49.7, max: 56.0) -[2023-10-16 03:00:32,351][03835] Avg episode reward: [(0, '2.300'), (1, '2.830')] -[2023-10-16 03:00:32,468][05219] Updated weights for policy 1, policy_version 6090 (0.0009) -[2023-10-16 03:00:32,827][05219] Updated weights for policy 1, policy_version 6100 (0.0009) -[2023-10-16 03:00:33,200][05219] Updated weights for policy 1, policy_version 6110 (0.0009) -[2023-10-16 03:00:33,402][05218] Updated weights for policy 0, policy_version 6122 (0.0009) -[2023-10-16 03:00:33,775][05218] Updated weights for policy 0, policy_version 6132 (0.0007) -[2023-10-16 03:00:34,150][05218] Updated weights for policy 0, policy_version 6142 (0.0009) -[2023-10-16 03:00:36,991][05219] Updated weights for policy 1, policy_version 6120 (0.0009) -[2023-10-16 03:00:37,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 12550144. Throughput: 0: 1786.2, 1: 1798.3. Samples: 3155480. Policy #0 lag: (min: 24.0, avg: 49.7, max: 56.0) -[2023-10-16 03:00:37,351][03835] Avg episode reward: [(0, '2.360'), (1, '3.020')] -[2023-10-16 03:00:37,354][05219] Updated weights for policy 1, policy_version 6130 (0.0008) -[2023-10-16 03:00:37,721][05219] Updated weights for policy 1, policy_version 6140 (0.0009) -[2023-10-16 03:00:37,864][04891] Saving new best policy, reward=3.020! -[2023-10-16 03:00:37,954][05218] Updated weights for policy 0, policy_version 6152 (0.0010) -[2023-10-16 03:00:38,330][05218] Updated weights for policy 0, policy_version 6162 (0.0009) -[2023-10-16 03:00:38,697][05218] Updated weights for policy 0, policy_version 6172 (0.0008) -[2023-10-16 03:00:41,622][05219] Updated weights for policy 1, policy_version 6150 (0.0009) -[2023-10-16 03:00:42,004][05219] Updated weights for policy 1, policy_version 6160 (0.0008) -[2023-10-16 03:00:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 12615680. Throughput: 0: 1774.0, 1: 1778.0. Samples: 3165604. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:00:42,351][03835] Avg episode reward: [(0, '2.500'), (1, '2.710')] -[2023-10-16 03:00:42,368][05219] Updated weights for policy 1, policy_version 6170 (0.0009) -[2023-10-16 03:00:42,576][05218] Updated weights for policy 0, policy_version 6182 (0.0008) -[2023-10-16 03:00:42,961][05218] Updated weights for policy 0, policy_version 6192 (0.0007) -[2023-10-16 03:00:43,328][05218] Updated weights for policy 0, policy_version 6202 (0.0007) -[2023-10-16 03:00:46,070][05219] Updated weights for policy 1, policy_version 6180 (0.0010) -[2023-10-16 03:00:46,446][05219] Updated weights for policy 1, policy_version 6190 (0.0011) -[2023-10-16 03:00:46,814][05219] Updated weights for policy 1, policy_version 6200 (0.0009) -[2023-10-16 03:00:47,002][05218] Updated weights for policy 0, policy_version 6212 (0.0009) -[2023-10-16 03:00:47,350][03835] Fps is (10 sec: 16384.6, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 12713984. Throughput: 0: 1787.6, 1: 1797.3. Samples: 3187610. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:00:47,351][03835] Avg episode reward: [(0, '2.370'), (1, '2.570')] -[2023-10-16 03:00:47,380][05218] Updated weights for policy 0, policy_version 6222 (0.0007) -[2023-10-16 03:00:47,766][05218] Updated weights for policy 0, policy_version 6232 (0.0007) -[2023-10-16 03:00:50,792][05219] Updated weights for policy 1, policy_version 6210 (0.0008) -[2023-10-16 03:00:51,155][05219] Updated weights for policy 1, policy_version 6220 (0.0008) -[2023-10-16 03:00:51,383][05218] Updated weights for policy 0, policy_version 6242 (0.0008) -[2023-10-16 03:00:51,520][05219] Updated weights for policy 1, policy_version 6230 (0.0008) -[2023-10-16 03:00:51,746][05218] Updated weights for policy 0, policy_version 6252 (0.0007) -[2023-10-16 03:00:51,884][05219] Updated weights for policy 1, policy_version 6240 (0.0008) -[2023-10-16 03:00:52,115][05218] Updated weights for policy 0, policy_version 6262 (0.0007) -[2023-10-16 03:00:52,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 12779520. Throughput: 0: 1788.1, 1: 1776.6. Samples: 3207718. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:00:52,351][03835] Avg episode reward: [(0, '2.300'), (1, '2.640')] -[2023-10-16 03:00:52,492][05218] Updated weights for policy 0, policy_version 6272 (0.0007) -[2023-10-16 03:00:55,617][05219] Updated weights for policy 1, policy_version 6250 (0.0007) -[2023-10-16 03:00:55,984][05219] Updated weights for policy 1, policy_version 6260 (0.0009) -[2023-10-16 03:00:56,352][05219] Updated weights for policy 1, policy_version 6270 (0.0010) -[2023-10-16 03:00:56,398][05218] Updated weights for policy 0, policy_version 6282 (0.0008) -[2023-10-16 03:00:56,786][05218] Updated weights for policy 0, policy_version 6292 (0.0010) -[2023-10-16 03:00:57,149][05218] Updated weights for policy 0, policy_version 6302 (0.0010) -[2023-10-16 03:00:57,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 12877824. Throughput: 0: 1779.5, 1: 1796.9. Samples: 3219898. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:00:57,351][03835] Avg episode reward: [(0, '2.320'), (1, '2.870')] -[2023-10-16 03:01:00,106][05219] Updated weights for policy 1, policy_version 6280 (0.0009) -[2023-10-16 03:01:00,469][05219] Updated weights for policy 1, policy_version 6290 (0.0010) -[2023-10-16 03:01:00,768][05218] Updated weights for policy 0, policy_version 6312 (0.0007) -[2023-10-16 03:01:00,826][05219] Updated weights for policy 1, policy_version 6300 (0.0008) -[2023-10-16 03:01:01,147][05218] Updated weights for policy 0, policy_version 6322 (0.0009) -[2023-10-16 03:01:01,526][05218] Updated weights for policy 0, policy_version 6332 (0.0008) -[2023-10-16 03:01:02,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 12943360. Throughput: 0: 1785.8, 1: 1780.7. Samples: 3239790. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:01:02,351][03835] Avg episode reward: [(0, '2.450'), (1, '2.610')] -[2023-10-16 03:01:04,509][05219] Updated weights for policy 1, policy_version 6310 (0.0007) -[2023-10-16 03:01:04,877][05219] Updated weights for policy 1, policy_version 6320 (0.0007) -[2023-10-16 03:01:05,236][05219] Updated weights for policy 1, policy_version 6330 (0.0008) -[2023-10-16 03:01:05,394][05218] Updated weights for policy 0, policy_version 6342 (0.0009) -[2023-10-16 03:01:05,768][05218] Updated weights for policy 0, policy_version 6352 (0.0010) -[2023-10-16 03:01:06,133][05218] Updated weights for policy 0, policy_version 6362 (0.0011) -[2023-10-16 03:01:07,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 13008896. Throughput: 0: 1775.6, 1: 1778.5. Samples: 3261392. Policy #0 lag: (min: 6.0, avg: 13.8, max: 38.0) -[2023-10-16 03:01:07,351][03835] Avg episode reward: [(0, '2.450'), (1, '2.690')] -[2023-10-16 03:01:09,067][05219] Updated weights for policy 1, policy_version 6340 (0.0008) -[2023-10-16 03:01:09,434][05219] Updated weights for policy 1, policy_version 6350 (0.0010) -[2023-10-16 03:01:09,809][05219] Updated weights for policy 1, policy_version 6360 (0.0009) -[2023-10-16 03:01:09,949][05218] Updated weights for policy 0, policy_version 6372 (0.0009) -[2023-10-16 03:01:10,318][05218] Updated weights for policy 0, policy_version 6382 (0.0009) -[2023-10-16 03:01:10,700][05218] Updated weights for policy 0, policy_version 6392 (0.0011) -[2023-10-16 03:01:12,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 13074432. Throughput: 0: 1793.0, 1: 1776.7. Samples: 3272004. Policy #0 lag: (min: 6.0, avg: 13.8, max: 38.0) -[2023-10-16 03:01:12,351][03835] Avg episode reward: [(0, '2.370'), (1, '2.730')] -[2023-10-16 03:01:13,687][05219] Updated weights for policy 1, policy_version 6370 (0.0007) -[2023-10-16 03:01:14,043][05219] Updated weights for policy 1, policy_version 6380 (0.0008) -[2023-10-16 03:01:14,419][05219] Updated weights for policy 1, policy_version 6390 (0.0008) -[2023-10-16 03:01:14,628][05218] Updated weights for policy 0, policy_version 6402 (0.0011) -[2023-10-16 03:01:14,784][05219] Updated weights for policy 1, policy_version 6400 (0.0007) -[2023-10-16 03:01:15,016][05218] Updated weights for policy 0, policy_version 6412 (0.0010) -[2023-10-16 03:01:15,396][05218] Updated weights for policy 0, policy_version 6422 (0.0010) -[2023-10-16 03:01:15,770][05218] Updated weights for policy 0, policy_version 6432 (0.0009) -[2023-10-16 03:01:17,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 13139968. Throughput: 0: 1772.8, 1: 1764.3. Samples: 3292938. Policy #0 lag: (min: 31.0, avg: 43.3, max: 63.0) -[2023-10-16 03:01:17,351][03835] Avg episode reward: [(0, '2.350'), (1, '2.720')] -[2023-10-16 03:01:18,693][05219] Updated weights for policy 1, policy_version 6410 (0.0007) -[2023-10-16 03:01:19,062][05219] Updated weights for policy 1, policy_version 6420 (0.0008) -[2023-10-16 03:01:19,430][05219] Updated weights for policy 1, policy_version 6430 (0.0008) -[2023-10-16 03:01:19,520][05218] Updated weights for policy 0, policy_version 6442 (0.0008) -[2023-10-16 03:01:19,895][05218] Updated weights for policy 0, policy_version 6452 (0.0007) -[2023-10-16 03:01:20,270][05218] Updated weights for policy 0, policy_version 6462 (0.0008) -[2023-10-16 03:01:22,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 13205504. Throughput: 0: 1764.9, 1: 1773.2. Samples: 3314692. Policy #0 lag: (min: 31.0, avg: 43.3, max: 63.0) -[2023-10-16 03:01:22,351][03835] Avg episode reward: [(0, '2.370'), (1, '2.850')] -[2023-10-16 03:01:23,423][05219] Updated weights for policy 1, policy_version 6440 (0.0009) -[2023-10-16 03:01:23,801][05219] Updated weights for policy 1, policy_version 6450 (0.0008) -[2023-10-16 03:01:24,164][05219] Updated weights for policy 1, policy_version 6460 (0.0008) -[2023-10-16 03:01:24,175][05218] Updated weights for policy 0, policy_version 6472 (0.0008) -[2023-10-16 03:01:24,550][05218] Updated weights for policy 0, policy_version 6482 (0.0008) -[2023-10-16 03:01:24,930][05218] Updated weights for policy 0, policy_version 6492 (0.0010) -[2023-10-16 03:01:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 13271040. Throughput: 0: 1765.6, 1: 1761.6. Samples: 3324330. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:01:27,351][03835] Avg episode reward: [(0, '2.550'), (1, '2.660')] -[2023-10-16 03:01:27,970][05219] Updated weights for policy 1, policy_version 6470 (0.0008) -[2023-10-16 03:01:28,357][05219] Updated weights for policy 1, policy_version 6480 (0.0008) -[2023-10-16 03:01:28,710][05218] Updated weights for policy 0, policy_version 6502 (0.0009) -[2023-10-16 03:01:28,722][05219] Updated weights for policy 1, policy_version 6490 (0.0008) -[2023-10-16 03:01:29,083][05218] Updated weights for policy 0, policy_version 6512 (0.0007) -[2023-10-16 03:01:29,463][05218] Updated weights for policy 0, policy_version 6522 (0.0007) -[2023-10-16 03:01:32,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 13336576. Throughput: 0: 1763.8, 1: 1768.3. Samples: 3346554. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:01:32,351][03835] Avg episode reward: [(0, '2.570'), (1, '2.730')] -[2023-10-16 03:01:32,545][05219] Updated weights for policy 1, policy_version 6500 (0.0007) -[2023-10-16 03:01:32,904][05219] Updated weights for policy 1, policy_version 6510 (0.0008) -[2023-10-16 03:01:33,196][05218] Updated weights for policy 0, policy_version 6532 (0.0010) -[2023-10-16 03:01:33,277][05219] Updated weights for policy 1, policy_version 6520 (0.0008) -[2023-10-16 03:01:33,568][05218] Updated weights for policy 0, policy_version 6542 (0.0010) -[2023-10-16 03:01:33,936][05218] Updated weights for policy 0, policy_version 6552 (0.0008) -[2023-10-16 03:01:36,992][05219] Updated weights for policy 1, policy_version 6530 (0.0008) -[2023-10-16 03:01:37,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 13402112. Throughput: 0: 1785.1, 1: 1786.2. Samples: 3368424. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:01:37,351][03835] Avg episode reward: [(0, '2.390'), (1, '2.520')] -[2023-10-16 03:01:37,359][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000006560_6717440.pth... -[2023-10-16 03:01:37,362][05219] Updated weights for policy 1, policy_version 6540 (0.0008) -[2023-10-16 03:01:37,397][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000004896_5013504.pth -[2023-10-16 03:01:37,732][05219] Updated weights for policy 1, policy_version 6550 (0.0010) -[2023-10-16 03:01:37,738][05218] Updated weights for policy 0, policy_version 6562 (0.0009) -[2023-10-16 03:01:38,098][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000006560_6717440.pth... -[2023-10-16 03:01:38,098][05219] Updated weights for policy 1, policy_version 6560 (0.0007) -[2023-10-16 03:01:38,120][05218] Updated weights for policy 0, policy_version 6572 (0.0009) -[2023-10-16 03:01:38,127][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000004896_5013504.pth -[2023-10-16 03:01:38,494][05218] Updated weights for policy 0, policy_version 6582 (0.0010) -[2023-10-16 03:01:38,870][05218] Updated weights for policy 0, policy_version 6592 (0.0009) -[2023-10-16 03:01:41,918][05219] Updated weights for policy 1, policy_version 6570 (0.0007) -[2023-10-16 03:01:42,273][05219] Updated weights for policy 1, policy_version 6580 (0.0007) -[2023-10-16 03:01:42,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 13467648. Throughput: 0: 1761.9, 1: 1761.5. Samples: 3378450. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:01:42,351][03835] Avg episode reward: [(0, '2.560'), (1, '2.640')] -[2023-10-16 03:01:42,644][05218] Updated weights for policy 0, policy_version 6602 (0.0007) -[2023-10-16 03:01:42,648][05219] Updated weights for policy 1, policy_version 6590 (0.0008) -[2023-10-16 03:01:43,024][05218] Updated weights for policy 0, policy_version 6612 (0.0009) -[2023-10-16 03:01:43,407][05218] Updated weights for policy 0, policy_version 6622 (0.0009) -[2023-10-16 03:01:46,405][05219] Updated weights for policy 1, policy_version 6600 (0.0007) -[2023-10-16 03:01:46,774][05219] Updated weights for policy 1, policy_version 6610 (0.0008) -[2023-10-16 03:01:47,139][05219] Updated weights for policy 1, policy_version 6620 (0.0009) -[2023-10-16 03:01:47,230][05218] Updated weights for policy 0, policy_version 6632 (0.0007) -[2023-10-16 03:01:47,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 13565952. Throughput: 0: 1782.5, 1: 1793.0. Samples: 3400690. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-16 03:01:47,351][03835] Avg episode reward: [(0, '2.700'), (1, '2.840')] -[2023-10-16 03:01:47,600][05218] Updated weights for policy 0, policy_version 6642 (0.0007) -[2023-10-16 03:01:47,975][05218] Updated weights for policy 0, policy_version 6652 (0.0009) -[2023-10-16 03:01:51,014][05219] Updated weights for policy 1, policy_version 6630 (0.0008) -[2023-10-16 03:01:51,382][05219] Updated weights for policy 1, policy_version 6640 (0.0010) -[2023-10-16 03:01:51,734][05218] Updated weights for policy 0, policy_version 6662 (0.0009) -[2023-10-16 03:01:51,749][05219] Updated weights for policy 1, policy_version 6650 (0.0007) -[2023-10-16 03:01:52,108][05218] Updated weights for policy 0, policy_version 6672 (0.0009) -[2023-10-16 03:01:52,351][03835] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 13631488. Throughput: 0: 1779.3, 1: 1758.4. Samples: 3420588. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-16 03:01:52,352][03835] Avg episode reward: [(0, '2.500'), (1, '2.800')] -[2023-10-16 03:01:52,491][05218] Updated weights for policy 0, policy_version 6682 (0.0007) -[2023-10-16 03:01:55,501][05219] Updated weights for policy 1, policy_version 6660 (0.0009) -[2023-10-16 03:01:55,864][05219] Updated weights for policy 1, policy_version 6670 (0.0008) -[2023-10-16 03:01:56,228][05219] Updated weights for policy 1, policy_version 6680 (0.0008) -[2023-10-16 03:01:56,254][05218] Updated weights for policy 0, policy_version 6692 (0.0008) -[2023-10-16 03:01:56,631][05218] Updated weights for policy 0, policy_version 6702 (0.0007) -[2023-10-16 03:01:57,008][05218] Updated weights for policy 0, policy_version 6712 (0.0008) -[2023-10-16 03:01:57,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 13729792. Throughput: 0: 1780.2, 1: 1790.8. Samples: 3432702. Policy #0 lag: (min: 21.0, avg: 31.2, max: 53.0) -[2023-10-16 03:01:57,351][03835] Avg episode reward: [(0, '2.320'), (1, '2.590')] -[2023-10-16 03:01:59,871][05219] Updated weights for policy 1, policy_version 6690 (0.0009) -[2023-10-16 03:02:00,232][05219] Updated weights for policy 1, policy_version 6700 (0.0009) -[2023-10-16 03:02:00,604][05219] Updated weights for policy 1, policy_version 6710 (0.0008) -[2023-10-16 03:02:00,699][05218] Updated weights for policy 0, policy_version 6722 (0.0007) -[2023-10-16 03:02:00,971][05219] Updated weights for policy 1, policy_version 6720 (0.0007) -[2023-10-16 03:02:01,065][05218] Updated weights for policy 0, policy_version 6732 (0.0007) -[2023-10-16 03:02:01,445][05218] Updated weights for policy 0, policy_version 6742 (0.0007) -[2023-10-16 03:02:01,813][05218] Updated weights for policy 0, policy_version 6752 (0.0007) -[2023-10-16 03:02:02,350][03835] Fps is (10 sec: 16384.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 13795328. Throughput: 0: 1788.5, 1: 1772.4. Samples: 3453180. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-16 03:02:02,351][03835] Avg episode reward: [(0, '2.480'), (1, '2.410')] -[2023-10-16 03:02:04,596][05219] Updated weights for policy 1, policy_version 6730 (0.0008) -[2023-10-16 03:02:04,971][05219] Updated weights for policy 1, policy_version 6740 (0.0008) -[2023-10-16 03:02:05,336][05219] Updated weights for policy 1, policy_version 6750 (0.0008) -[2023-10-16 03:02:05,618][05218] Updated weights for policy 0, policy_version 6762 (0.0008) -[2023-10-16 03:02:05,996][05218] Updated weights for policy 0, policy_version 6772 (0.0009) -[2023-10-16 03:02:06,380][05218] Updated weights for policy 0, policy_version 6782 (0.0010) -[2023-10-16 03:02:07,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 13860864. Throughput: 0: 1780.4, 1: 1781.9. Samples: 3474996. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-16 03:02:07,352][03835] Avg episode reward: [(0, '2.300'), (1, '2.420')] -[2023-10-16 03:02:09,215][05219] Updated weights for policy 1, policy_version 6760 (0.0008) -[2023-10-16 03:02:09,586][05219] Updated weights for policy 1, policy_version 6770 (0.0007) -[2023-10-16 03:02:09,955][05219] Updated weights for policy 1, policy_version 6780 (0.0007) -[2023-10-16 03:02:09,974][05218] Updated weights for policy 0, policy_version 6792 (0.0008) -[2023-10-16 03:02:10,353][05218] Updated weights for policy 0, policy_version 6802 (0.0009) -[2023-10-16 03:02:10,726][05218] Updated weights for policy 0, policy_version 6812 (0.0009) -[2023-10-16 03:02:12,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 13926400. Throughput: 0: 1800.2, 1: 1783.3. Samples: 3485588. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-16 03:02:12,351][03835] Avg episode reward: [(0, '2.190'), (1, '2.680')] -[2023-10-16 03:02:13,674][05219] Updated weights for policy 1, policy_version 6790 (0.0007) -[2023-10-16 03:02:14,044][05219] Updated weights for policy 1, policy_version 6800 (0.0007) -[2023-10-16 03:02:14,420][05219] Updated weights for policy 1, policy_version 6810 (0.0009) -[2023-10-16 03:02:14,543][05218] Updated weights for policy 0, policy_version 6822 (0.0008) -[2023-10-16 03:02:14,914][05218] Updated weights for policy 0, policy_version 6832 (0.0007) -[2023-10-16 03:02:15,299][05218] Updated weights for policy 0, policy_version 6842 (0.0007) -[2023-10-16 03:02:17,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 13991936. Throughput: 0: 1781.1, 1: 1781.1. Samples: 3506856. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-16 03:02:17,351][03835] Avg episode reward: [(0, '2.480'), (1, '2.670')] -[2023-10-16 03:02:18,089][05219] Updated weights for policy 1, policy_version 6820 (0.0010) -[2023-10-16 03:02:18,478][05219] Updated weights for policy 1, policy_version 6830 (0.0009) -[2023-10-16 03:02:18,838][05219] Updated weights for policy 1, policy_version 6840 (0.0010) -[2023-10-16 03:02:19,155][05218] Updated weights for policy 0, policy_version 6852 (0.0009) -[2023-10-16 03:02:19,532][05218] Updated weights for policy 0, policy_version 6862 (0.0008) -[2023-10-16 03:02:19,914][05218] Updated weights for policy 0, policy_version 6872 (0.0011) -[2023-10-16 03:02:22,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 14057472. Throughput: 0: 1781.8, 1: 1784.9. Samples: 3528926. Policy #0 lag: (min: 23.0, avg: 38.4, max: 40.0) -[2023-10-16 03:02:22,351][03835] Avg episode reward: [(0, '2.540'), (1, '2.490')] -[2023-10-16 03:02:22,819][05219] Updated weights for policy 1, policy_version 6850 (0.0009) -[2023-10-16 03:02:23,191][05219] Updated weights for policy 1, policy_version 6860 (0.0010) -[2023-10-16 03:02:23,524][05218] Updated weights for policy 0, policy_version 6882 (0.0008) -[2023-10-16 03:02:23,552][05219] Updated weights for policy 1, policy_version 6870 (0.0010) -[2023-10-16 03:02:23,887][05218] Updated weights for policy 0, policy_version 6892 (0.0009) -[2023-10-16 03:02:23,909][05219] Updated weights for policy 1, policy_version 6880 (0.0007) -[2023-10-16 03:02:24,272][05218] Updated weights for policy 0, policy_version 6902 (0.0011) -[2023-10-16 03:02:24,639][05218] Updated weights for policy 0, policy_version 6912 (0.0009) -[2023-10-16 03:02:27,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 14123008. Throughput: 0: 1780.1, 1: 1776.8. Samples: 3538514. Policy #0 lag: (min: 23.0, avg: 38.4, max: 40.0) -[2023-10-16 03:02:27,351][03835] Avg episode reward: [(0, '2.810'), (1, '2.830')] -[2023-10-16 03:02:27,714][05219] Updated weights for policy 1, policy_version 6890 (0.0008) -[2023-10-16 03:02:28,083][05219] Updated weights for policy 1, policy_version 6900 (0.0008) -[2023-10-16 03:02:28,379][05218] Updated weights for policy 0, policy_version 6922 (0.0007) -[2023-10-16 03:02:28,457][05219] Updated weights for policy 1, policy_version 6910 (0.0008) -[2023-10-16 03:02:28,764][05218] Updated weights for policy 0, policy_version 6932 (0.0009) -[2023-10-16 03:02:29,147][05218] Updated weights for policy 0, policy_version 6942 (0.0009) -[2023-10-16 03:02:32,253][05219] Updated weights for policy 1, policy_version 6920 (0.0007) -[2023-10-16 03:02:32,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 14188544. Throughput: 0: 1782.8, 1: 1778.4. Samples: 3560948. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-16 03:02:32,351][03835] Avg episode reward: [(0, '2.760'), (1, '2.680')] -[2023-10-16 03:02:32,610][05219] Updated weights for policy 1, policy_version 6930 (0.0008) -[2023-10-16 03:02:32,908][05218] Updated weights for policy 0, policy_version 6952 (0.0008) -[2023-10-16 03:02:32,977][05219] Updated weights for policy 1, policy_version 6940 (0.0009) -[2023-10-16 03:02:33,285][05218] Updated weights for policy 0, policy_version 6962 (0.0007) -[2023-10-16 03:02:33,668][05218] Updated weights for policy 0, policy_version 6972 (0.0007) -[2023-10-16 03:02:36,901][05219] Updated weights for policy 1, policy_version 6950 (0.0009) -[2023-10-16 03:02:37,273][05219] Updated weights for policy 1, policy_version 6960 (0.0009) -[2023-10-16 03:02:37,297][05218] Updated weights for policy 0, policy_version 6982 (0.0007) -[2023-10-16 03:02:37,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 14254080. Throughput: 0: 1799.0, 1: 1797.7. Samples: 3582438. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-16 03:02:37,351][03835] Avg episode reward: [(0, '2.870'), (1, '2.720')] -[2023-10-16 03:02:37,646][05219] Updated weights for policy 1, policy_version 6970 (0.0009) -[2023-10-16 03:02:37,678][05218] Updated weights for policy 0, policy_version 6992 (0.0009) -[2023-10-16 03:02:38,063][05218] Updated weights for policy 0, policy_version 7002 (0.0009) -[2023-10-16 03:02:41,360][05219] Updated weights for policy 1, policy_version 6980 (0.0008) -[2023-10-16 03:02:41,729][05219] Updated weights for policy 1, policy_version 6990 (0.0008) -[2023-10-16 03:02:42,041][05218] Updated weights for policy 0, policy_version 7012 (0.0010) -[2023-10-16 03:02:42,095][05219] Updated weights for policy 1, policy_version 7000 (0.0008) -[2023-10-16 03:02:42,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 14319616. Throughput: 0: 1782.7, 1: 1774.5. Samples: 3592776. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-16 03:02:42,351][03835] Avg episode reward: [(0, '2.740'), (1, '2.580')] -[2023-10-16 03:02:42,414][05218] Updated weights for policy 0, policy_version 7022 (0.0010) -[2023-10-16 03:02:42,792][05218] Updated weights for policy 0, policy_version 7032 (0.0009) -[2023-10-16 03:02:45,974][05219] Updated weights for policy 1, policy_version 7010 (0.0007) -[2023-10-16 03:02:46,349][05219] Updated weights for policy 1, policy_version 7020 (0.0009) -[2023-10-16 03:02:46,664][05218] Updated weights for policy 0, policy_version 7042 (0.0008) -[2023-10-16 03:02:46,728][05219] Updated weights for policy 1, policy_version 7030 (0.0009) -[2023-10-16 03:02:47,045][05218] Updated weights for policy 0, policy_version 7052 (0.0007) -[2023-10-16 03:02:47,091][05219] Updated weights for policy 1, policy_version 7040 (0.0008) -[2023-10-16 03:02:47,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 14417920. Throughput: 0: 1794.7, 1: 1790.8. Samples: 3614528. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-16 03:02:47,351][03835] Avg episode reward: [(0, '2.730'), (1, '2.670')] -[2023-10-16 03:02:47,414][05218] Updated weights for policy 0, policy_version 7062 (0.0009) -[2023-10-16 03:02:47,793][05218] Updated weights for policy 0, policy_version 7072 (0.0011) -[2023-10-16 03:02:51,000][05219] Updated weights for policy 1, policy_version 7050 (0.0010) -[2023-10-16 03:02:51,371][05219] Updated weights for policy 1, policy_version 7060 (0.0009) -[2023-10-16 03:02:51,728][05219] Updated weights for policy 1, policy_version 7070 (0.0008) -[2023-10-16 03:02:51,779][05218] Updated weights for policy 0, policy_version 7082 (0.0007) -[2023-10-16 03:02:52,159][05218] Updated weights for policy 0, policy_version 7092 (0.0009) -[2023-10-16 03:02:52,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 14483456. Throughput: 0: 1777.1, 1: 1760.6. Samples: 3634192. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) -[2023-10-16 03:02:52,351][03835] Avg episode reward: [(0, '2.600'), (1, '2.660')] -[2023-10-16 03:02:52,536][05218] Updated weights for policy 0, policy_version 7102 (0.0007) -[2023-10-16 03:02:55,387][05219] Updated weights for policy 1, policy_version 7080 (0.0008) -[2023-10-16 03:02:55,758][05219] Updated weights for policy 1, policy_version 7090 (0.0010) -[2023-10-16 03:02:56,112][05219] Updated weights for policy 1, policy_version 7100 (0.0008) -[2023-10-16 03:02:56,182][05218] Updated weights for policy 0, policy_version 7112 (0.0009) -[2023-10-16 03:02:56,553][05218] Updated weights for policy 0, policy_version 7122 (0.0009) -[2023-10-16 03:02:56,935][05218] Updated weights for policy 0, policy_version 7132 (0.0010) -[2023-10-16 03:02:57,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 14581760. Throughput: 0: 1785.1, 1: 1789.9. Samples: 3646468. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-16 03:02:57,351][03835] Avg episode reward: [(0, '2.730'), (1, '2.530')] -[2023-10-16 03:03:00,116][05219] Updated weights for policy 1, policy_version 7110 (0.0011) -[2023-10-16 03:03:00,477][05219] Updated weights for policy 1, policy_version 7120 (0.0011) -[2023-10-16 03:03:00,734][05218] Updated weights for policy 0, policy_version 7142 (0.0007) -[2023-10-16 03:03:00,845][05219] Updated weights for policy 1, policy_version 7130 (0.0009) -[2023-10-16 03:03:01,116][05218] Updated weights for policy 0, policy_version 7152 (0.0009) -[2023-10-16 03:03:01,494][05218] Updated weights for policy 0, policy_version 7162 (0.0008) -[2023-10-16 03:03:02,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 14647296. Throughput: 0: 1782.2, 1: 1760.0. Samples: 3666254. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-16 03:03:02,351][03835] Avg episode reward: [(0, '2.650'), (1, '2.730')] -[2023-10-16 03:03:04,619][05219] Updated weights for policy 1, policy_version 7140 (0.0008) -[2023-10-16 03:03:04,970][05218] Updated weights for policy 0, policy_version 7172 (0.0008) -[2023-10-16 03:03:05,008][05219] Updated weights for policy 1, policy_version 7150 (0.0009) -[2023-10-16 03:03:05,342][05218] Updated weights for policy 0, policy_version 7182 (0.0009) -[2023-10-16 03:03:05,369][05219] Updated weights for policy 1, policy_version 7160 (0.0008) -[2023-10-16 03:03:05,713][05218] Updated weights for policy 0, policy_version 7192 (0.0009) -[2023-10-16 03:03:07,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 14712832. Throughput: 0: 1777.5, 1: 1760.3. Samples: 3688128. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:03:07,351][03835] Avg episode reward: [(0, '2.690'), (1, '3.050')] -[2023-10-16 03:03:07,360][04891] Saving new best policy, reward=3.050! -[2023-10-16 03:03:09,110][05219] Updated weights for policy 1, policy_version 7170 (0.0009) -[2023-10-16 03:03:09,421][05218] Updated weights for policy 0, policy_version 7202 (0.0009) -[2023-10-16 03:03:09,479][05219] Updated weights for policy 1, policy_version 7180 (0.0008) -[2023-10-16 03:03:09,790][05218] Updated weights for policy 0, policy_version 7212 (0.0009) -[2023-10-16 03:03:09,853][05219] Updated weights for policy 1, policy_version 7190 (0.0007) -[2023-10-16 03:03:10,167][05218] Updated weights for policy 0, policy_version 7222 (0.0008) -[2023-10-16 03:03:10,218][05219] Updated weights for policy 1, policy_version 7200 (0.0008) -[2023-10-16 03:03:10,540][05218] Updated weights for policy 0, policy_version 7232 (0.0009) -[2023-10-16 03:03:12,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 14778368. Throughput: 0: 1786.3, 1: 1764.5. Samples: 3698304. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:03:12,351][03835] Avg episode reward: [(0, '2.940'), (1, '3.090')] -[2023-10-16 03:03:12,353][04766] Saving new best policy, reward=2.940! -[2023-10-16 03:03:12,353][04891] Saving new best policy, reward=3.090! -[2023-10-16 03:03:14,036][05219] Updated weights for policy 1, policy_version 7210 (0.0008) -[2023-10-16 03:03:14,243][05218] Updated weights for policy 0, policy_version 7242 (0.0009) -[2023-10-16 03:03:14,402][05219] Updated weights for policy 1, policy_version 7220 (0.0009) -[2023-10-16 03:03:14,604][05218] Updated weights for policy 0, policy_version 7252 (0.0009) -[2023-10-16 03:03:14,768][05219] Updated weights for policy 1, policy_version 7230 (0.0007) -[2023-10-16 03:03:14,990][05218] Updated weights for policy 0, policy_version 7262 (0.0008) -[2023-10-16 03:03:17,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 14843904. Throughput: 0: 1782.4, 1: 1751.7. Samples: 3719982. Policy #0 lag: (min: 9.0, avg: 9.7, max: 21.0) -[2023-10-16 03:03:17,351][03835] Avg episode reward: [(0, '3.090'), (1, '3.310')] -[2023-10-16 03:03:17,352][04766] Saving new best policy, reward=3.090! -[2023-10-16 03:03:17,352][04891] Saving new best policy, reward=3.310! -[2023-10-16 03:03:18,671][05219] Updated weights for policy 1, policy_version 7240 (0.0007) -[2023-10-16 03:03:18,702][05218] Updated weights for policy 0, policy_version 7272 (0.0007) -[2023-10-16 03:03:19,033][05219] Updated weights for policy 1, policy_version 7250 (0.0008) -[2023-10-16 03:03:19,065][05218] Updated weights for policy 0, policy_version 7282 (0.0009) -[2023-10-16 03:03:19,401][05219] Updated weights for policy 1, policy_version 7260 (0.0008) -[2023-10-16 03:03:19,436][05218] Updated weights for policy 0, policy_version 7292 (0.0009) -[2023-10-16 03:03:22,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 14909440. Throughput: 0: 1787.3, 1: 1761.0. Samples: 3742114. Policy #0 lag: (min: 9.0, avg: 9.7, max: 21.0) -[2023-10-16 03:03:22,351][03835] Avg episode reward: [(0, '3.000'), (1, '3.130')] -[2023-10-16 03:03:23,192][05219] Updated weights for policy 1, policy_version 7270 (0.0008) -[2023-10-16 03:03:23,218][05218] Updated weights for policy 0, policy_version 7302 (0.0008) -[2023-10-16 03:03:23,560][05219] Updated weights for policy 1, policy_version 7280 (0.0009) -[2023-10-16 03:03:23,596][05218] Updated weights for policy 0, policy_version 7312 (0.0008) -[2023-10-16 03:03:23,917][05219] Updated weights for policy 1, policy_version 7290 (0.0010) -[2023-10-16 03:03:23,972][05218] Updated weights for policy 0, policy_version 7322 (0.0008) -[2023-10-16 03:03:27,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 14974976. Throughput: 0: 1786.0, 1: 1749.7. Samples: 3751886. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:03:27,352][03835] Avg episode reward: [(0, '2.350'), (1, '2.870')] -[2023-10-16 03:03:27,688][05218] Updated weights for policy 0, policy_version 7332 (0.0008) -[2023-10-16 03:03:27,874][05219] Updated weights for policy 1, policy_version 7300 (0.0008) -[2023-10-16 03:03:28,061][05218] Updated weights for policy 0, policy_version 7342 (0.0009) -[2023-10-16 03:03:28,242][05219] Updated weights for policy 1, policy_version 7310 (0.0009) -[2023-10-16 03:03:28,445][05218] Updated weights for policy 0, policy_version 7352 (0.0007) -[2023-10-16 03:03:28,602][05219] Updated weights for policy 1, policy_version 7320 (0.0007) -[2023-10-16 03:03:32,223][05218] Updated weights for policy 0, policy_version 7362 (0.0008) -[2023-10-16 03:03:32,319][05219] Updated weights for policy 1, policy_version 7330 (0.0008) -[2023-10-16 03:03:32,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 15040512. Throughput: 0: 1787.2, 1: 1758.6. Samples: 3774090. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:03:32,351][03835] Avg episode reward: [(0, '2.540'), (1, '2.840')] -[2023-10-16 03:03:32,607][05218] Updated weights for policy 0, policy_version 7372 (0.0008) -[2023-10-16 03:03:32,678][05219] Updated weights for policy 1, policy_version 7340 (0.0007) -[2023-10-16 03:03:32,975][05218] Updated weights for policy 0, policy_version 7382 (0.0007) -[2023-10-16 03:03:33,056][05219] Updated weights for policy 1, policy_version 7350 (0.0008) -[2023-10-16 03:03:33,359][05218] Updated weights for policy 0, policy_version 7392 (0.0008) -[2023-10-16 03:03:33,427][05219] Updated weights for policy 1, policy_version 7360 (0.0007) -[2023-10-16 03:03:37,296][05219] Updated weights for policy 1, policy_version 7370 (0.0008) -[2023-10-16 03:03:37,343][05218] Updated weights for policy 0, policy_version 7402 (0.0007) -[2023-10-16 03:03:37,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 15106048. Throughput: 0: 1805.6, 1: 1778.5. Samples: 3795478. Policy #0 lag: (min: 28.0, avg: 35.9, max: 60.0) -[2023-10-16 03:03:37,351][03835] Avg episode reward: [(0, '2.780'), (1, '2.970')] -[2023-10-16 03:03:37,664][05219] Updated weights for policy 1, policy_version 7380 (0.0009) -[2023-10-16 03:03:37,705][05218] Updated weights for policy 0, policy_version 7412 (0.0008) -[2023-10-16 03:03:38,039][05219] Updated weights for policy 1, policy_version 7390 (0.0008) -[2023-10-16 03:03:38,085][05218] Updated weights for policy 0, policy_version 7422 (0.0009) -[2023-10-16 03:03:38,106][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000007392_7569408.pth... -[2023-10-16 03:03:38,136][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000005728_5865472.pth -[2023-10-16 03:03:38,160][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000007424_7602176.pth... -[2023-10-16 03:03:38,198][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000005728_5865472.pth -[2023-10-16 03:03:41,872][05218] Updated weights for policy 0, policy_version 7432 (0.0009) -[2023-10-16 03:03:41,914][05219] Updated weights for policy 1, policy_version 7400 (0.0008) -[2023-10-16 03:03:42,238][05218] Updated weights for policy 0, policy_version 7442 (0.0009) -[2023-10-16 03:03:42,285][05219] Updated weights for policy 1, policy_version 7410 (0.0007) -[2023-10-16 03:03:42,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 15171584. Throughput: 0: 1789.7, 1: 1750.2. Samples: 3805764. Policy #0 lag: (min: 28.0, avg: 35.9, max: 60.0) -[2023-10-16 03:03:42,351][03835] Avg episode reward: [(0, '2.870'), (1, '2.780')] -[2023-10-16 03:03:42,610][05218] Updated weights for policy 0, policy_version 7452 (0.0009) -[2023-10-16 03:03:42,652][05219] Updated weights for policy 1, policy_version 7420 (0.0007) -[2023-10-16 03:03:46,432][05218] Updated weights for policy 0, policy_version 7462 (0.0008) -[2023-10-16 03:03:46,537][05219] Updated weights for policy 1, policy_version 7430 (0.0008) -[2023-10-16 03:03:46,810][05218] Updated weights for policy 0, policy_version 7472 (0.0007) -[2023-10-16 03:03:46,914][05219] Updated weights for policy 1, policy_version 7440 (0.0008) -[2023-10-16 03:03:47,183][05218] Updated weights for policy 0, policy_version 7482 (0.0010) -[2023-10-16 03:03:47,280][05219] Updated weights for policy 1, policy_version 7450 (0.0007) -[2023-10-16 03:03:47,350][03835] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 14218.0). Total num frames: 15237120. Throughput: 0: 1803.9, 1: 1777.3. Samples: 3827408. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:03:47,351][03835] Avg episode reward: [(0, '2.750'), (1, '2.930')] -[2023-10-16 03:03:50,848][05218] Updated weights for policy 0, policy_version 7492 (0.0007) -[2023-10-16 03:03:51,131][05219] Updated weights for policy 1, policy_version 7460 (0.0007) -[2023-10-16 03:03:51,220][05218] Updated weights for policy 0, policy_version 7502 (0.0007) -[2023-10-16 03:03:51,513][05219] Updated weights for policy 1, policy_version 7470 (0.0008) -[2023-10-16 03:03:51,600][05218] Updated weights for policy 0, policy_version 7512 (0.0008) -[2023-10-16 03:03:51,882][05219] Updated weights for policy 1, policy_version 7480 (0.0008) -[2023-10-16 03:03:52,350][03835] Fps is (10 sec: 19660.3, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 15368192. Throughput: 0: 1784.6, 1: 1748.7. Samples: 3847126. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:03:52,351][03835] Avg episode reward: [(0, '2.600'), (1, '2.820')] -[2023-10-16 03:03:55,407][05218] Updated weights for policy 0, policy_version 7522 (0.0008) -[2023-10-16 03:03:55,747][05219] Updated weights for policy 1, policy_version 7490 (0.0007) -[2023-10-16 03:03:55,780][05218] Updated weights for policy 0, policy_version 7532 (0.0008) -[2023-10-16 03:03:56,116][05219] Updated weights for policy 1, policy_version 7500 (0.0009) -[2023-10-16 03:03:56,165][05218] Updated weights for policy 0, policy_version 7542 (0.0011) -[2023-10-16 03:03:56,485][05219] Updated weights for policy 1, policy_version 7510 (0.0008) -[2023-10-16 03:03:56,534][05218] Updated weights for policy 0, policy_version 7552 (0.0009) -[2023-10-16 03:03:56,848][05219] Updated weights for policy 1, policy_version 7520 (0.0008) -[2023-10-16 03:03:57,351][03835] Fps is (10 sec: 19660.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 15433728. Throughput: 0: 1811.4, 1: 1770.2. Samples: 3859474. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:03:57,352][03835] Avg episode reward: [(0, '2.610'), (1, '2.730')] -[2023-10-16 03:04:00,220][05218] Updated weights for policy 0, policy_version 7562 (0.0008) -[2023-10-16 03:04:00,600][05218] Updated weights for policy 0, policy_version 7572 (0.0007) -[2023-10-16 03:04:00,608][05219] Updated weights for policy 1, policy_version 7530 (0.0007) -[2023-10-16 03:04:00,969][05219] Updated weights for policy 1, policy_version 7540 (0.0009) -[2023-10-16 03:04:00,970][05218] Updated weights for policy 0, policy_version 7582 (0.0008) -[2023-10-16 03:04:01,337][05219] Updated weights for policy 1, policy_version 7550 (0.0008) -[2023-10-16 03:04:02,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 15499264. Throughput: 0: 1785.5, 1: 1760.5. Samples: 3879550. Policy #0 lag: (min: 31.0, avg: 31.9, max: 51.0) -[2023-10-16 03:04:02,351][03835] Avg episode reward: [(0, '2.470'), (1, '2.730')] -[2023-10-16 03:04:04,726][05218] Updated weights for policy 0, policy_version 7592 (0.0009) -[2023-10-16 03:04:05,097][05218] Updated weights for policy 0, policy_version 7602 (0.0007) -[2023-10-16 03:04:05,123][05219] Updated weights for policy 1, policy_version 7560 (0.0009) -[2023-10-16 03:04:05,470][05218] Updated weights for policy 0, policy_version 7612 (0.0008) -[2023-10-16 03:04:05,484][05219] Updated weights for policy 1, policy_version 7570 (0.0008) -[2023-10-16 03:04:05,846][05219] Updated weights for policy 1, policy_version 7580 (0.0010) -[2023-10-16 03:04:07,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 15564800. Throughput: 0: 1783.7, 1: 1758.1. Samples: 3901498. Policy #0 lag: (min: 31.0, avg: 31.9, max: 51.0) -[2023-10-16 03:04:07,352][03835] Avg episode reward: [(0, '2.470'), (1, '2.780')] -[2023-10-16 03:04:09,331][05218] Updated weights for policy 0, policy_version 7622 (0.0007) -[2023-10-16 03:04:09,707][05218] Updated weights for policy 0, policy_version 7632 (0.0007) -[2023-10-16 03:04:09,728][05219] Updated weights for policy 1, policy_version 7590 (0.0010) -[2023-10-16 03:04:10,086][05218] Updated weights for policy 0, policy_version 7642 (0.0007) -[2023-10-16 03:04:10,094][05219] Updated weights for policy 1, policy_version 7600 (0.0008) -[2023-10-16 03:04:10,443][05219] Updated weights for policy 1, policy_version 7610 (0.0009) -[2023-10-16 03:04:12,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 15630336. Throughput: 0: 1779.9, 1: 1773.9. Samples: 3911806. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:04:12,351][03835] Avg episode reward: [(0, '2.780'), (1, '2.790')] -[2023-10-16 03:04:13,860][05218] Updated weights for policy 0, policy_version 7652 (0.0007) -[2023-10-16 03:04:14,241][05218] Updated weights for policy 0, policy_version 7662 (0.0009) -[2023-10-16 03:04:14,270][05219] Updated weights for policy 1, policy_version 7620 (0.0010) -[2023-10-16 03:04:14,615][05218] Updated weights for policy 0, policy_version 7672 (0.0009) -[2023-10-16 03:04:14,633][05219] Updated weights for policy 1, policy_version 7630 (0.0008) -[2023-10-16 03:04:15,003][05219] Updated weights for policy 1, policy_version 7640 (0.0008) -[2023-10-16 03:04:17,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 15695872. Throughput: 0: 1779.2, 1: 1755.3. Samples: 3933142. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:04:17,351][03835] Avg episode reward: [(0, '2.850'), (1, '2.750')] -[2023-10-16 03:04:18,401][05218] Updated weights for policy 0, policy_version 7682 (0.0010) -[2023-10-16 03:04:18,784][05218] Updated weights for policy 0, policy_version 7692 (0.0007) -[2023-10-16 03:04:18,871][05219] Updated weights for policy 1, policy_version 7650 (0.0007) -[2023-10-16 03:04:19,153][05218] Updated weights for policy 0, policy_version 7702 (0.0009) -[2023-10-16 03:04:19,238][05219] Updated weights for policy 1, policy_version 7660 (0.0007) -[2023-10-16 03:04:19,524][05218] Updated weights for policy 0, policy_version 7712 (0.0008) -[2023-10-16 03:04:19,611][05219] Updated weights for policy 1, policy_version 7670 (0.0008) -[2023-10-16 03:04:19,971][05219] Updated weights for policy 1, policy_version 7680 (0.0010) -[2023-10-16 03:04:22,351][03835] Fps is (10 sec: 13106.6, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 15761408. Throughput: 0: 1794.3, 1: 1766.7. Samples: 3955726. Policy #0 lag: (min: 14.0, avg: 15.8, max: 42.0) -[2023-10-16 03:04:22,352][03835] Avg episode reward: [(0, '2.640'), (1, '2.670')] -[2023-10-16 03:04:23,151][05218] Updated weights for policy 0, policy_version 7722 (0.0009) -[2023-10-16 03:04:23,534][05218] Updated weights for policy 0, policy_version 7732 (0.0009) -[2023-10-16 03:04:23,830][05219] Updated weights for policy 1, policy_version 7690 (0.0007) -[2023-10-16 03:04:23,908][05218] Updated weights for policy 0, policy_version 7742 (0.0008) -[2023-10-16 03:04:24,202][05219] Updated weights for policy 1, policy_version 7700 (0.0007) -[2023-10-16 03:04:24,568][05219] Updated weights for policy 1, policy_version 7710 (0.0008) -[2023-10-16 03:04:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 15826944. Throughput: 0: 1782.7, 1: 1763.5. Samples: 3965344. Policy #0 lag: (min: 14.0, avg: 15.8, max: 42.0) -[2023-10-16 03:04:27,351][03835] Avg episode reward: [(0, '2.640'), (1, '2.820')] -[2023-10-16 03:04:27,641][05218] Updated weights for policy 0, policy_version 7752 (0.0011) -[2023-10-16 03:04:28,024][05218] Updated weights for policy 0, policy_version 7762 (0.0010) -[2023-10-16 03:04:28,364][05219] Updated weights for policy 1, policy_version 7720 (0.0008) -[2023-10-16 03:04:28,391][05218] Updated weights for policy 0, policy_version 7772 (0.0008) -[2023-10-16 03:04:28,735][05219] Updated weights for policy 1, policy_version 7730 (0.0009) -[2023-10-16 03:04:29,099][05219] Updated weights for policy 1, policy_version 7740 (0.0008) -[2023-10-16 03:04:32,145][05218] Updated weights for policy 0, policy_version 7782 (0.0009) -[2023-10-16 03:04:32,350][03835] Fps is (10 sec: 13107.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 15892480. Throughput: 0: 1790.0, 1: 1770.8. Samples: 3987644. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:04:32,351][03835] Avg episode reward: [(0, '2.660'), (1, '2.980')] -[2023-10-16 03:04:32,524][05218] Updated weights for policy 0, policy_version 7792 (0.0009) -[2023-10-16 03:04:32,855][05219] Updated weights for policy 1, policy_version 7750 (0.0007) -[2023-10-16 03:04:32,902][05218] Updated weights for policy 0, policy_version 7802 (0.0008) -[2023-10-16 03:04:33,228][05219] Updated weights for policy 1, policy_version 7760 (0.0008) -[2023-10-16 03:04:33,584][05219] Updated weights for policy 1, policy_version 7770 (0.0008) -[2023-10-16 03:04:36,743][05218] Updated weights for policy 0, policy_version 7812 (0.0007) -[2023-10-16 03:04:37,133][05218] Updated weights for policy 0, policy_version 7822 (0.0012) -[2023-10-16 03:04:37,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 15958016. Throughput: 0: 1790.5, 1: 1798.1. Samples: 4008612. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:04:37,351][03835] Avg episode reward: [(0, '2.930'), (1, '3.120')] -[2023-10-16 03:04:37,511][05218] Updated weights for policy 0, policy_version 7832 (0.0009) -[2023-10-16 03:04:37,566][05219] Updated weights for policy 1, policy_version 7780 (0.0008) -[2023-10-16 03:04:37,957][05219] Updated weights for policy 1, policy_version 7790 (0.0007) -[2023-10-16 03:04:38,332][05219] Updated weights for policy 1, policy_version 7800 (0.0011) -[2023-10-16 03:04:41,256][05218] Updated weights for policy 0, policy_version 7842 (0.0009) -[2023-10-16 03:04:41,623][05218] Updated weights for policy 0, policy_version 7852 (0.0010) -[2023-10-16 03:04:42,001][05218] Updated weights for policy 0, policy_version 7862 (0.0009) -[2023-10-16 03:04:42,035][05219] Updated weights for policy 1, policy_version 7810 (0.0008) -[2023-10-16 03:04:42,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 16023552. Throughput: 0: 1779.4, 1: 1772.4. Samples: 4019304. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-16 03:04:42,351][03835] Avg episode reward: [(0, '3.020'), (1, '2.960')] -[2023-10-16 03:04:42,380][05218] Updated weights for policy 0, policy_version 7872 (0.0010) -[2023-10-16 03:04:42,402][05219] Updated weights for policy 1, policy_version 7820 (0.0007) -[2023-10-16 03:04:42,763][05219] Updated weights for policy 1, policy_version 7830 (0.0010) -[2023-10-16 03:04:43,133][05219] Updated weights for policy 1, policy_version 7840 (0.0007) -[2023-10-16 03:04:46,170][05218] Updated weights for policy 0, policy_version 7882 (0.0009) -[2023-10-16 03:04:46,547][05218] Updated weights for policy 0, policy_version 7892 (0.0007) -[2023-10-16 03:04:46,831][05219] Updated weights for policy 1, policy_version 7850 (0.0007) -[2023-10-16 03:04:46,926][05218] Updated weights for policy 0, policy_version 7902 (0.0007) -[2023-10-16 03:04:47,195][05219] Updated weights for policy 1, policy_version 7860 (0.0010) -[2023-10-16 03:04:47,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 16121856. Throughput: 0: 1791.3, 1: 1794.1. Samples: 4040894. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:04:47,351][03835] Avg episode reward: [(0, '2.890'), (1, '2.720')] -[2023-10-16 03:04:47,552][05219] Updated weights for policy 1, policy_version 7870 (0.0011) -[2023-10-16 03:04:50,667][05218] Updated weights for policy 0, policy_version 7912 (0.0008) -[2023-10-16 03:04:51,051][05218] Updated weights for policy 0, policy_version 7922 (0.0007) -[2023-10-16 03:04:51,425][05218] Updated weights for policy 0, policy_version 7932 (0.0008) -[2023-10-16 03:04:51,425][05219] Updated weights for policy 1, policy_version 7880 (0.0007) -[2023-10-16 03:04:51,793][05219] Updated weights for policy 1, policy_version 7890 (0.0010) -[2023-10-16 03:04:52,171][05219] Updated weights for policy 1, policy_version 7900 (0.0008) -[2023-10-16 03:04:52,350][03835] Fps is (10 sec: 19661.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 16220160. Throughput: 0: 1776.0, 1: 1775.1. Samples: 4061296. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:04:52,351][03835] Avg episode reward: [(0, '2.650'), (1, '2.870')] -[2023-10-16 03:04:55,158][05218] Updated weights for policy 0, policy_version 7942 (0.0007) -[2023-10-16 03:04:55,527][05218] Updated weights for policy 0, policy_version 7952 (0.0009) -[2023-10-16 03:04:55,903][05218] Updated weights for policy 0, policy_version 7962 (0.0008) -[2023-10-16 03:04:55,943][05219] Updated weights for policy 1, policy_version 7910 (0.0008) -[2023-10-16 03:04:56,308][05219] Updated weights for policy 1, policy_version 7920 (0.0009) -[2023-10-16 03:04:56,671][05219] Updated weights for policy 1, policy_version 7930 (0.0007) -[2023-10-16 03:04:57,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 16285696. Throughput: 0: 1799.6, 1: 1783.5. Samples: 4073048. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-16 03:04:57,351][03835] Avg episode reward: [(0, '2.530'), (1, '2.980')] -[2023-10-16 03:04:59,708][05218] Updated weights for policy 0, policy_version 7972 (0.0008) -[2023-10-16 03:05:00,077][05218] Updated weights for policy 0, policy_version 7982 (0.0009) -[2023-10-16 03:05:00,460][05218] Updated weights for policy 0, policy_version 7992 (0.0008) -[2023-10-16 03:05:00,465][05219] Updated weights for policy 1, policy_version 7940 (0.0008) -[2023-10-16 03:05:00,829][05219] Updated weights for policy 1, policy_version 7950 (0.0008) -[2023-10-16 03:05:01,198][05219] Updated weights for policy 1, policy_version 7960 (0.0008) -[2023-10-16 03:05:02,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 16351232. Throughput: 0: 1781.0, 1: 1782.4. Samples: 4093494. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-16 03:05:02,352][03835] Avg episode reward: [(0, '2.620'), (1, '2.720')] -[2023-10-16 03:05:04,068][05218] Updated weights for policy 0, policy_version 8002 (0.0009) -[2023-10-16 03:05:04,440][05218] Updated weights for policy 0, policy_version 8012 (0.0008) -[2023-10-16 03:05:04,826][05218] Updated weights for policy 0, policy_version 8022 (0.0010) -[2023-10-16 03:05:05,041][05219] Updated weights for policy 1, policy_version 7970 (0.0010) -[2023-10-16 03:05:05,201][05218] Updated weights for policy 0, policy_version 8032 (0.0009) -[2023-10-16 03:05:05,406][05219] Updated weights for policy 1, policy_version 7980 (0.0008) -[2023-10-16 03:05:05,769][05219] Updated weights for policy 1, policy_version 7990 (0.0010) -[2023-10-16 03:05:06,141][05219] Updated weights for policy 1, policy_version 8000 (0.0007) -[2023-10-16 03:05:07,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 16416768. Throughput: 0: 1780.0, 1: 1765.6. Samples: 4115278. Policy #0 lag: (min: 27.0, avg: 27.8, max: 47.0) -[2023-10-16 03:05:07,352][03835] Avg episode reward: [(0, '2.750'), (1, '2.790')] -[2023-10-16 03:05:09,021][05218] Updated weights for policy 0, policy_version 8042 (0.0008) -[2023-10-16 03:05:09,395][05218] Updated weights for policy 0, policy_version 8052 (0.0007) -[2023-10-16 03:05:09,772][05218] Updated weights for policy 0, policy_version 8062 (0.0007) -[2023-10-16 03:05:09,832][05219] Updated weights for policy 1, policy_version 8010 (0.0007) -[2023-10-16 03:05:10,199][05219] Updated weights for policy 1, policy_version 8020 (0.0007) -[2023-10-16 03:05:10,558][05219] Updated weights for policy 1, policy_version 8030 (0.0009) -[2023-10-16 03:05:12,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 16482304. Throughput: 0: 1781.6, 1: 1781.1. Samples: 4125664. Policy #0 lag: (min: 27.0, avg: 27.8, max: 47.0) -[2023-10-16 03:05:12,352][03835] Avg episode reward: [(0, '2.870'), (1, '2.900')] -[2023-10-16 03:05:13,249][05218] Updated weights for policy 0, policy_version 8072 (0.0009) -[2023-10-16 03:05:13,627][05218] Updated weights for policy 0, policy_version 8082 (0.0010) -[2023-10-16 03:05:13,995][05218] Updated weights for policy 0, policy_version 8092 (0.0010) -[2023-10-16 03:05:14,405][05219] Updated weights for policy 1, policy_version 8040 (0.0010) -[2023-10-16 03:05:14,772][05219] Updated weights for policy 1, policy_version 8050 (0.0008) -[2023-10-16 03:05:15,138][05219] Updated weights for policy 1, policy_version 8060 (0.0007) -[2023-10-16 03:05:17,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 16547840. Throughput: 0: 1783.5, 1: 1765.2. Samples: 4147338. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:05:17,352][03835] Avg episode reward: [(0, '2.820'), (1, '2.900')] -[2023-10-16 03:05:17,865][05218] Updated weights for policy 0, policy_version 8102 (0.0009) -[2023-10-16 03:05:18,241][05218] Updated weights for policy 0, policy_version 8112 (0.0009) -[2023-10-16 03:05:18,625][05218] Updated weights for policy 0, policy_version 8122 (0.0008) -[2023-10-16 03:05:18,946][05219] Updated weights for policy 1, policy_version 8070 (0.0008) -[2023-10-16 03:05:19,319][05219] Updated weights for policy 1, policy_version 8080 (0.0009) -[2023-10-16 03:05:19,687][05219] Updated weights for policy 1, policy_version 8090 (0.0008) -[2023-10-16 03:05:22,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 16613376. Throughput: 0: 1808.7, 1: 1773.1. Samples: 4169798. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:05:22,351][03835] Avg episode reward: [(0, '2.820'), (1, '2.970')] -[2023-10-16 03:05:22,386][05218] Updated weights for policy 0, policy_version 8132 (0.0009) -[2023-10-16 03:05:22,767][05218] Updated weights for policy 0, policy_version 8142 (0.0007) -[2023-10-16 03:05:23,133][05218] Updated weights for policy 0, policy_version 8152 (0.0008) -[2023-10-16 03:05:23,379][05219] Updated weights for policy 1, policy_version 8100 (0.0011) -[2023-10-16 03:05:23,770][05219] Updated weights for policy 1, policy_version 8110 (0.0008) -[2023-10-16 03:05:24,129][05219] Updated weights for policy 1, policy_version 8120 (0.0009) -[2023-10-16 03:05:26,855][05218] Updated weights for policy 0, policy_version 8162 (0.0008) -[2023-10-16 03:05:27,227][05218] Updated weights for policy 0, policy_version 8172 (0.0010) -[2023-10-16 03:05:27,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 16678912. Throughput: 0: 1789.9, 1: 1773.1. Samples: 4179640. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) -[2023-10-16 03:05:27,351][03835] Avg episode reward: [(0, '2.860'), (1, '2.800')] -[2023-10-16 03:05:27,600][05218] Updated weights for policy 0, policy_version 8182 (0.0007) -[2023-10-16 03:05:27,833][05219] Updated weights for policy 1, policy_version 8130 (0.0009) -[2023-10-16 03:05:27,979][05218] Updated weights for policy 0, policy_version 8192 (0.0007) -[2023-10-16 03:05:28,205][05219] Updated weights for policy 1, policy_version 8140 (0.0009) -[2023-10-16 03:05:28,584][05219] Updated weights for policy 1, policy_version 8150 (0.0012) -[2023-10-16 03:05:28,950][05219] Updated weights for policy 1, policy_version 8160 (0.0010) -[2023-10-16 03:05:31,639][05218] Updated weights for policy 0, policy_version 8202 (0.0010) -[2023-10-16 03:05:32,011][05218] Updated weights for policy 0, policy_version 8212 (0.0010) -[2023-10-16 03:05:32,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 16744448. Throughput: 0: 1803.0, 1: 1769.8. Samples: 4201670. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) -[2023-10-16 03:05:32,351][03835] Avg episode reward: [(0, '2.820'), (1, '2.890')] -[2023-10-16 03:05:32,381][05218] Updated weights for policy 0, policy_version 8222 (0.0010) -[2023-10-16 03:05:32,832][05219] Updated weights for policy 1, policy_version 8170 (0.0008) -[2023-10-16 03:05:33,194][05219] Updated weights for policy 1, policy_version 8180 (0.0009) -[2023-10-16 03:05:33,560][05219] Updated weights for policy 1, policy_version 8190 (0.0008) -[2023-10-16 03:05:36,052][05218] Updated weights for policy 0, policy_version 8232 (0.0008) -[2023-10-16 03:05:36,422][05218] Updated weights for policy 0, policy_version 8242 (0.0009) -[2023-10-16 03:05:36,798][05218] Updated weights for policy 0, policy_version 8252 (0.0010) -[2023-10-16 03:05:37,312][05219] Updated weights for policy 1, policy_version 8200 (0.0010) -[2023-10-16 03:05:37,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 16842752. Throughput: 0: 1789.5, 1: 1800.8. Samples: 4222856. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:05:37,351][03835] Avg episode reward: [(0, '2.900'), (1, '3.140')] -[2023-10-16 03:05:37,358][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000008256_8454144.pth... -[2023-10-16 03:05:37,397][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000006560_6717440.pth -[2023-10-16 03:05:37,402][04766] Saving a milestone ./train_atari/atari_timepilot_APPO/checkpoint_p0/milestones/checkpoint_000008256_8454144.pth -[2023-10-16 03:05:37,678][05219] Updated weights for policy 1, policy_version 8210 (0.0010) -[2023-10-16 03:05:38,038][05219] Updated weights for policy 1, policy_version 8220 (0.0008) -[2023-10-16 03:05:38,182][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000008224_8421376.pth... -[2023-10-16 03:05:38,210][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000006560_6717440.pth -[2023-10-16 03:05:38,214][04891] Saving a milestone ./train_atari/atari_timepilot_APPO/checkpoint_p1/milestones/checkpoint_000008224_8421376.pth -[2023-10-16 03:05:40,609][05218] Updated weights for policy 0, policy_version 8262 (0.0010) -[2023-10-16 03:05:40,988][05218] Updated weights for policy 0, policy_version 8272 (0.0008) -[2023-10-16 03:05:41,366][05218] Updated weights for policy 0, policy_version 8282 (0.0009) -[2023-10-16 03:05:41,806][05219] Updated weights for policy 1, policy_version 8230 (0.0010) -[2023-10-16 03:05:42,165][05219] Updated weights for policy 1, policy_version 8240 (0.0010) -[2023-10-16 03:05:42,351][03835] Fps is (10 sec: 16383.5, 60 sec: 14745.5, 300 sec: 14218.0). Total num frames: 16908288. Throughput: 0: 1800.1, 1: 1776.6. Samples: 4234002. Policy #0 lag: (min: 8.0, avg: 32.2, max: 40.0) -[2023-10-16 03:05:42,352][03835] Avg episode reward: [(0, '2.810'), (1, '3.040')] -[2023-10-16 03:05:42,521][05219] Updated weights for policy 1, policy_version 8250 (0.0010) -[2023-10-16 03:05:45,227][05218] Updated weights for policy 0, policy_version 8292 (0.0008) -[2023-10-16 03:05:45,602][05218] Updated weights for policy 0, policy_version 8302 (0.0009) -[2023-10-16 03:05:45,982][05218] Updated weights for policy 0, policy_version 8312 (0.0009) -[2023-10-16 03:05:46,345][05219] Updated weights for policy 1, policy_version 8260 (0.0009) -[2023-10-16 03:05:46,708][05219] Updated weights for policy 1, policy_version 8270 (0.0009) -[2023-10-16 03:05:47,081][05219] Updated weights for policy 1, policy_version 8280 (0.0011) -[2023-10-16 03:05:47,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 16973824. Throughput: 0: 1787.9, 1: 1797.0. Samples: 4254812. Policy #0 lag: (min: 8.0, avg: 32.2, max: 40.0) -[2023-10-16 03:05:47,351][03835] Avg episode reward: [(0, '3.000'), (1, '3.110')] -[2023-10-16 03:05:49,643][05218] Updated weights for policy 0, policy_version 8322 (0.0007) -[2023-10-16 03:05:50,019][05218] Updated weights for policy 0, policy_version 8332 (0.0007) -[2023-10-16 03:05:50,395][05218] Updated weights for policy 0, policy_version 8342 (0.0007) -[2023-10-16 03:05:50,759][05219] Updated weights for policy 1, policy_version 8290 (0.0008) -[2023-10-16 03:05:50,781][05218] Updated weights for policy 0, policy_version 8352 (0.0009) -[2023-10-16 03:05:51,124][05219] Updated weights for policy 1, policy_version 8300 (0.0008) -[2023-10-16 03:05:51,482][05219] Updated weights for policy 1, policy_version 8310 (0.0009) -[2023-10-16 03:05:51,857][05219] Updated weights for policy 1, policy_version 8320 (0.0007) -[2023-10-16 03:05:52,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 17072128. Throughput: 0: 1787.1, 1: 1778.1. Samples: 4275712. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:05:52,351][03835] Avg episode reward: [(0, '2.850'), (1, '3.040')] -[2023-10-16 03:05:54,621][05218] Updated weights for policy 0, policy_version 8362 (0.0008) -[2023-10-16 03:05:55,001][05218] Updated weights for policy 0, policy_version 8372 (0.0009) -[2023-10-16 03:05:55,376][05218] Updated weights for policy 0, policy_version 8382 (0.0009) -[2023-10-16 03:05:55,610][05219] Updated weights for policy 1, policy_version 8330 (0.0008) -[2023-10-16 03:05:55,976][05219] Updated weights for policy 1, policy_version 8340 (0.0008) -[2023-10-16 03:05:56,353][05219] Updated weights for policy 1, policy_version 8350 (0.0008) -[2023-10-16 03:05:57,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 17137664. Throughput: 0: 1792.3, 1: 1798.1. Samples: 4287232. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:05:57,351][03835] Avg episode reward: [(0, '3.070'), (1, '3.220')] -[2023-10-16 03:05:59,208][05218] Updated weights for policy 0, policy_version 8392 (0.0008) -[2023-10-16 03:05:59,580][05218] Updated weights for policy 0, policy_version 8402 (0.0008) -[2023-10-16 03:05:59,954][05218] Updated weights for policy 0, policy_version 8412 (0.0008) -[2023-10-16 03:06:00,111][05219] Updated weights for policy 1, policy_version 8360 (0.0010) -[2023-10-16 03:06:00,480][05219] Updated weights for policy 1, policy_version 8370 (0.0008) -[2023-10-16 03:06:00,853][05219] Updated weights for policy 1, policy_version 8380 (0.0008) -[2023-10-16 03:06:02,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 17203200. Throughput: 0: 1788.2, 1: 1785.1. Samples: 4308136. Policy #0 lag: (min: 0.0, avg: 29.0, max: 32.0) -[2023-10-16 03:06:02,351][03835] Avg episode reward: [(0, '2.980'), (1, '3.210')] -[2023-10-16 03:06:03,462][05218] Updated weights for policy 0, policy_version 8422 (0.0010) -[2023-10-16 03:06:03,826][05218] Updated weights for policy 0, policy_version 8432 (0.0010) -[2023-10-16 03:06:04,204][05218] Updated weights for policy 0, policy_version 8442 (0.0009) -[2023-10-16 03:06:04,582][05219] Updated weights for policy 1, policy_version 8390 (0.0008) -[2023-10-16 03:06:04,953][05219] Updated weights for policy 1, policy_version 8400 (0.0008) -[2023-10-16 03:06:05,314][05219] Updated weights for policy 1, policy_version 8410 (0.0008) -[2023-10-16 03:06:07,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 17268736. Throughput: 0: 1790.9, 1: 1781.7. Samples: 4330560. Policy #0 lag: (min: 0.0, avg: 29.0, max: 32.0) -[2023-10-16 03:06:07,351][03835] Avg episode reward: [(0, '2.850'), (1, '3.090')] -[2023-10-16 03:06:07,917][05218] Updated weights for policy 0, policy_version 8452 (0.0008) -[2023-10-16 03:06:08,296][05218] Updated weights for policy 0, policy_version 8462 (0.0008) -[2023-10-16 03:06:08,682][05218] Updated weights for policy 0, policy_version 8472 (0.0008) -[2023-10-16 03:06:09,172][05219] Updated weights for policy 1, policy_version 8420 (0.0008) -[2023-10-16 03:06:09,551][05219] Updated weights for policy 1, policy_version 8430 (0.0007) -[2023-10-16 03:06:09,928][05219] Updated weights for policy 1, policy_version 8440 (0.0009) -[2023-10-16 03:06:12,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 17334272. Throughput: 0: 1785.0, 1: 1788.0. Samples: 4340424. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:06:12,351][03835] Avg episode reward: [(0, '2.900'), (1, '3.240')] -[2023-10-16 03:06:12,559][05218] Updated weights for policy 0, policy_version 8482 (0.0010) -[2023-10-16 03:06:12,942][05218] Updated weights for policy 0, policy_version 8492 (0.0011) -[2023-10-16 03:06:13,325][05218] Updated weights for policy 0, policy_version 8502 (0.0008) -[2023-10-16 03:06:13,600][05219] Updated weights for policy 1, policy_version 8450 (0.0008) -[2023-10-16 03:06:13,707][05218] Updated weights for policy 0, policy_version 8512 (0.0008) -[2023-10-16 03:06:13,965][05219] Updated weights for policy 1, policy_version 8460 (0.0009) -[2023-10-16 03:06:14,332][05219] Updated weights for policy 1, policy_version 8470 (0.0009) -[2023-10-16 03:06:14,705][05219] Updated weights for policy 1, policy_version 8480 (0.0007) -[2023-10-16 03:06:17,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 17399808. Throughput: 0: 1785.6, 1: 1786.0. Samples: 4362394. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:06:17,351][03835] Avg episode reward: [(0, '3.070'), (1, '2.990')] -[2023-10-16 03:06:17,435][05218] Updated weights for policy 0, policy_version 8522 (0.0010) -[2023-10-16 03:06:17,799][05218] Updated weights for policy 0, policy_version 8532 (0.0009) -[2023-10-16 03:06:18,173][05218] Updated weights for policy 0, policy_version 8542 (0.0008) -[2023-10-16 03:06:18,434][05219] Updated weights for policy 1, policy_version 8490 (0.0007) -[2023-10-16 03:06:18,804][05219] Updated weights for policy 1, policy_version 8500 (0.0008) -[2023-10-16 03:06:19,169][05219] Updated weights for policy 1, policy_version 8510 (0.0008) -[2023-10-16 03:06:21,952][05218] Updated weights for policy 0, policy_version 8552 (0.0010) -[2023-10-16 03:06:22,326][05218] Updated weights for policy 0, policy_version 8562 (0.0010) -[2023-10-16 03:06:22,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 17465344. Throughput: 0: 1795.3, 1: 1782.2. Samples: 4383844. Policy #0 lag: (min: 6.0, avg: 10.1, max: 38.0) -[2023-10-16 03:06:22,351][03835] Avg episode reward: [(0, '3.150'), (1, '3.040')] -[2023-10-16 03:06:22,700][05218] Updated weights for policy 0, policy_version 8572 (0.0010) -[2023-10-16 03:06:22,847][04766] Saving new best policy, reward=3.150! -[2023-10-16 03:06:23,012][05219] Updated weights for policy 1, policy_version 8520 (0.0008) -[2023-10-16 03:06:23,378][05219] Updated weights for policy 1, policy_version 8530 (0.0009) -[2023-10-16 03:06:23,750][05219] Updated weights for policy 1, policy_version 8540 (0.0010) -[2023-10-16 03:06:26,449][05218] Updated weights for policy 0, policy_version 8582 (0.0007) -[2023-10-16 03:06:26,829][05218] Updated weights for policy 0, policy_version 8592 (0.0007) -[2023-10-16 03:06:27,209][05218] Updated weights for policy 0, policy_version 8602 (0.0008) -[2023-10-16 03:06:27,332][05219] Updated weights for policy 1, policy_version 8550 (0.0009) -[2023-10-16 03:06:27,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 17530880. Throughput: 0: 1781.6, 1: 1784.9. Samples: 4394490. Policy #0 lag: (min: 6.0, avg: 10.1, max: 38.0) -[2023-10-16 03:06:27,351][03835] Avg episode reward: [(0, '3.310'), (1, '3.120')] -[2023-10-16 03:06:27,433][04766] Saving new best policy, reward=3.310! -[2023-10-16 03:06:27,692][05219] Updated weights for policy 1, policy_version 8560 (0.0008) -[2023-10-16 03:06:28,057][05219] Updated weights for policy 1, policy_version 8570 (0.0007) -[2023-10-16 03:06:31,020][05218] Updated weights for policy 0, policy_version 8612 (0.0009) -[2023-10-16 03:06:31,402][05218] Updated weights for policy 0, policy_version 8622 (0.0009) -[2023-10-16 03:06:31,752][05219] Updated weights for policy 1, policy_version 8580 (0.0007) -[2023-10-16 03:06:31,786][05218] Updated weights for policy 0, policy_version 8632 (0.0008) -[2023-10-16 03:06:32,113][05219] Updated weights for policy 1, policy_version 8590 (0.0008) -[2023-10-16 03:06:32,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 17629184. Throughput: 0: 1801.1, 1: 1788.1. Samples: 4416324. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:06:32,352][03835] Avg episode reward: [(0, '3.320'), (1, '3.100')] -[2023-10-16 03:06:32,353][04766] Saving new best policy, reward=3.320! -[2023-10-16 03:06:32,485][05219] Updated weights for policy 1, policy_version 8600 (0.0007) -[2023-10-16 03:06:35,591][05218] Updated weights for policy 0, policy_version 8642 (0.0008) -[2023-10-16 03:06:35,970][05218] Updated weights for policy 0, policy_version 8652 (0.0010) -[2023-10-16 03:06:36,313][05219] Updated weights for policy 1, policy_version 8610 (0.0008) -[2023-10-16 03:06:36,336][05218] Updated weights for policy 0, policy_version 8662 (0.0010) -[2023-10-16 03:06:36,671][05219] Updated weights for policy 1, policy_version 8620 (0.0009) -[2023-10-16 03:06:36,711][05218] Updated weights for policy 0, policy_version 8672 (0.0009) -[2023-10-16 03:06:37,048][05219] Updated weights for policy 1, policy_version 8630 (0.0009) -[2023-10-16 03:06:37,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 17694720. Throughput: 0: 1782.1, 1: 1797.3. Samples: 4436782. Policy #0 lag: (min: 15.0, avg: 19.3, max: 47.0) -[2023-10-16 03:06:37,351][03835] Avg episode reward: [(0, '3.390'), (1, '3.030')] -[2023-10-16 03:06:37,358][04766] Saving new best policy, reward=3.390! -[2023-10-16 03:06:37,410][05219] Updated weights for policy 1, policy_version 8640 (0.0008) -[2023-10-16 03:06:40,355][05218] Updated weights for policy 0, policy_version 8682 (0.0010) -[2023-10-16 03:06:40,727][05218] Updated weights for policy 0, policy_version 8692 (0.0008) -[2023-10-16 03:06:41,091][05218] Updated weights for policy 0, policy_version 8702 (0.0007) -[2023-10-16 03:06:41,324][05219] Updated weights for policy 1, policy_version 8650 (0.0007) -[2023-10-16 03:06:41,687][05219] Updated weights for policy 1, policy_version 8660 (0.0007) -[2023-10-16 03:06:42,062][05219] Updated weights for policy 1, policy_version 8670 (0.0008) -[2023-10-16 03:06:42,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 17793024. Throughput: 0: 1803.9, 1: 1781.8. Samples: 4448588. Policy #0 lag: (min: 15.0, avg: 19.3, max: 47.0) -[2023-10-16 03:06:42,351][03835] Avg episode reward: [(0, '3.240'), (1, '2.890')] -[2023-10-16 03:06:44,781][05218] Updated weights for policy 0, policy_version 8712 (0.0008) -[2023-10-16 03:06:45,163][05218] Updated weights for policy 0, policy_version 8722 (0.0008) -[2023-10-16 03:06:45,535][05218] Updated weights for policy 0, policy_version 8732 (0.0009) -[2023-10-16 03:06:45,969][05219] Updated weights for policy 1, policy_version 8680 (0.0008) -[2023-10-16 03:06:46,337][05219] Updated weights for policy 1, policy_version 8690 (0.0009) -[2023-10-16 03:06:46,707][05219] Updated weights for policy 1, policy_version 8700 (0.0008) -[2023-10-16 03:06:47,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 17858560. Throughput: 0: 1786.8, 1: 1799.8. Samples: 4469536. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:06:47,352][03835] Avg episode reward: [(0, '3.370'), (1, '2.780')] -[2023-10-16 03:06:49,365][05218] Updated weights for policy 0, policy_version 8742 (0.0008) -[2023-10-16 03:06:49,739][05218] Updated weights for policy 0, policy_version 8752 (0.0008) -[2023-10-16 03:06:50,117][05218] Updated weights for policy 0, policy_version 8762 (0.0008) -[2023-10-16 03:06:50,463][05219] Updated weights for policy 1, policy_version 8710 (0.0008) -[2023-10-16 03:06:50,827][05219] Updated weights for policy 1, policy_version 8720 (0.0007) -[2023-10-16 03:06:51,193][05219] Updated weights for policy 1, policy_version 8730 (0.0007) -[2023-10-16 03:06:52,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 17924096. Throughput: 0: 1780.8, 1: 1777.6. Samples: 4490690. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:06:52,351][03835] Avg episode reward: [(0, '3.430'), (1, '3.020')] -[2023-10-16 03:06:52,358][04766] Saving new best policy, reward=3.430! -[2023-10-16 03:06:54,001][05218] Updated weights for policy 0, policy_version 8772 (0.0008) -[2023-10-16 03:06:54,381][05218] Updated weights for policy 0, policy_version 8782 (0.0009) -[2023-10-16 03:06:54,764][05218] Updated weights for policy 0, policy_version 8792 (0.0007) -[2023-10-16 03:06:55,041][05219] Updated weights for policy 1, policy_version 8740 (0.0008) -[2023-10-16 03:06:55,432][05219] Updated weights for policy 1, policy_version 8750 (0.0009) -[2023-10-16 03:06:55,799][05219] Updated weights for policy 1, policy_version 8760 (0.0007) -[2023-10-16 03:06:57,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 17989632. Throughput: 0: 1779.0, 1: 1799.9. Samples: 4501476. Policy #0 lag: (min: 10.0, avg: 12.0, max: 40.0) -[2023-10-16 03:06:57,351][03835] Avg episode reward: [(0, '3.330'), (1, '3.000')] -[2023-10-16 03:06:58,483][05218] Updated weights for policy 0, policy_version 8802 (0.0007) -[2023-10-16 03:06:58,848][05218] Updated weights for policy 0, policy_version 8812 (0.0008) -[2023-10-16 03:06:59,224][05218] Updated weights for policy 0, policy_version 8822 (0.0009) -[2023-10-16 03:06:59,488][05219] Updated weights for policy 1, policy_version 8770 (0.0007) -[2023-10-16 03:06:59,602][05218] Updated weights for policy 0, policy_version 8832 (0.0007) -[2023-10-16 03:06:59,851][05219] Updated weights for policy 1, policy_version 8780 (0.0008) -[2023-10-16 03:07:00,222][05219] Updated weights for policy 1, policy_version 8790 (0.0009) -[2023-10-16 03:07:00,582][05219] Updated weights for policy 1, policy_version 8800 (0.0008) -[2023-10-16 03:07:02,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 18055168. Throughput: 0: 1781.1, 1: 1780.0. Samples: 4522642. Policy #0 lag: (min: 10.0, avg: 12.0, max: 40.0) -[2023-10-16 03:07:02,351][03835] Avg episode reward: [(0, '3.190'), (1, '2.830')] -[2023-10-16 03:07:03,478][05218] Updated weights for policy 0, policy_version 8842 (0.0008) -[2023-10-16 03:07:03,862][05218] Updated weights for policy 0, policy_version 8852 (0.0007) -[2023-10-16 03:07:04,237][05218] Updated weights for policy 0, policy_version 8862 (0.0007) -[2023-10-16 03:07:04,264][05219] Updated weights for policy 1, policy_version 8810 (0.0009) -[2023-10-16 03:07:04,635][05219] Updated weights for policy 1, policy_version 8820 (0.0010) -[2023-10-16 03:07:05,003][05219] Updated weights for policy 1, policy_version 8830 (0.0010) -[2023-10-16 03:07:07,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 18120704. Throughput: 0: 1798.0, 1: 1779.6. Samples: 4544836. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:07:07,351][03835] Avg episode reward: [(0, '3.070'), (1, '2.740')] -[2023-10-16 03:07:07,945][05218] Updated weights for policy 0, policy_version 8872 (0.0010) -[2023-10-16 03:07:08,319][05218] Updated weights for policy 0, policy_version 8882 (0.0010) -[2023-10-16 03:07:08,688][05218] Updated weights for policy 0, policy_version 8892 (0.0008) -[2023-10-16 03:07:08,826][05219] Updated weights for policy 1, policy_version 8840 (0.0009) -[2023-10-16 03:07:09,188][05219] Updated weights for policy 1, policy_version 8850 (0.0009) -[2023-10-16 03:07:09,553][05219] Updated weights for policy 1, policy_version 8860 (0.0008) -[2023-10-16 03:07:12,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 18186240. Throughput: 0: 1777.6, 1: 1776.7. Samples: 4554438. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:07:12,352][03835] Avg episode reward: [(0, '2.930'), (1, '2.740')] -[2023-10-16 03:07:12,515][05218] Updated weights for policy 0, policy_version 8902 (0.0010) -[2023-10-16 03:07:12,891][05218] Updated weights for policy 0, policy_version 8912 (0.0007) -[2023-10-16 03:07:13,265][05218] Updated weights for policy 0, policy_version 8922 (0.0010) -[2023-10-16 03:07:13,398][05219] Updated weights for policy 1, policy_version 8870 (0.0007) -[2023-10-16 03:07:13,778][05219] Updated weights for policy 1, policy_version 8880 (0.0008) -[2023-10-16 03:07:14,153][05219] Updated weights for policy 1, policy_version 8890 (0.0009) -[2023-10-16 03:07:17,100][05218] Updated weights for policy 0, policy_version 8932 (0.0009) -[2023-10-16 03:07:17,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 18251776. Throughput: 0: 1788.4, 1: 1773.6. Samples: 4576612. Policy #0 lag: (min: 31.0, avg: 32.1, max: 55.0) -[2023-10-16 03:07:17,351][03835] Avg episode reward: [(0, '2.880'), (1, '3.100')] -[2023-10-16 03:07:17,476][05218] Updated weights for policy 0, policy_version 8942 (0.0009) -[2023-10-16 03:07:17,860][05218] Updated weights for policy 0, policy_version 8952 (0.0008) -[2023-10-16 03:07:18,061][05219] Updated weights for policy 1, policy_version 8900 (0.0009) -[2023-10-16 03:07:18,434][05219] Updated weights for policy 1, policy_version 8910 (0.0010) -[2023-10-16 03:07:18,800][05219] Updated weights for policy 1, policy_version 8920 (0.0009) -[2023-10-16 03:07:21,538][05218] Updated weights for policy 0, policy_version 8962 (0.0008) -[2023-10-16 03:07:21,919][05218] Updated weights for policy 0, policy_version 8972 (0.0007) -[2023-10-16 03:07:22,293][05218] Updated weights for policy 0, policy_version 8982 (0.0010) -[2023-10-16 03:07:22,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 18317312. Throughput: 0: 1791.2, 1: 1797.8. Samples: 4598288. Policy #0 lag: (min: 31.0, avg: 32.1, max: 55.0) -[2023-10-16 03:07:22,351][03835] Avg episode reward: [(0, '2.890'), (1, '3.230')] -[2023-10-16 03:07:22,630][05219] Updated weights for policy 1, policy_version 8930 (0.0008) -[2023-10-16 03:07:22,663][05218] Updated weights for policy 0, policy_version 8992 (0.0009) -[2023-10-16 03:07:22,999][05219] Updated weights for policy 1, policy_version 8940 (0.0009) -[2023-10-16 03:07:23,369][05219] Updated weights for policy 1, policy_version 8950 (0.0008) -[2023-10-16 03:07:23,740][05219] Updated weights for policy 1, policy_version 8960 (0.0008) -[2023-10-16 03:07:26,516][05218] Updated weights for policy 0, policy_version 9002 (0.0009) -[2023-10-16 03:07:26,897][05218] Updated weights for policy 0, policy_version 9012 (0.0007) -[2023-10-16 03:07:27,264][05218] Updated weights for policy 0, policy_version 9022 (0.0007) -[2023-10-16 03:07:27,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 18415616. Throughput: 0: 1789.4, 1: 1775.9. Samples: 4609028. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-16 03:07:27,351][03835] Avg episode reward: [(0, '3.130'), (1, '3.400')] -[2023-10-16 03:07:27,544][05219] Updated weights for policy 1, policy_version 8970 (0.0007) -[2023-10-16 03:07:27,903][05219] Updated weights for policy 1, policy_version 8980 (0.0008) -[2023-10-16 03:07:28,274][05219] Updated weights for policy 1, policy_version 8990 (0.0009) -[2023-10-16 03:07:28,347][04891] Saving new best policy, reward=3.400! -[2023-10-16 03:07:31,012][05218] Updated weights for policy 0, policy_version 9032 (0.0010) -[2023-10-16 03:07:31,387][05218] Updated weights for policy 0, policy_version 9042 (0.0010) -[2023-10-16 03:07:31,764][05218] Updated weights for policy 0, policy_version 9052 (0.0008) -[2023-10-16 03:07:31,981][05219] Updated weights for policy 1, policy_version 9000 (0.0008) -[2023-10-16 03:07:32,346][05219] Updated weights for policy 1, policy_version 9010 (0.0008) -[2023-10-16 03:07:32,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 18481152. Throughput: 0: 1783.2, 1: 1788.4. Samples: 4630256. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-16 03:07:32,351][03835] Avg episode reward: [(0, '3.160'), (1, '3.350')] -[2023-10-16 03:07:32,710][05219] Updated weights for policy 1, policy_version 9020 (0.0007) -[2023-10-16 03:07:35,472][05218] Updated weights for policy 0, policy_version 9062 (0.0010) -[2023-10-16 03:07:35,839][05218] Updated weights for policy 0, policy_version 9072 (0.0008) -[2023-10-16 03:07:36,221][05218] Updated weights for policy 0, policy_version 9082 (0.0008) -[2023-10-16 03:07:36,411][05219] Updated weights for policy 1, policy_version 9030 (0.0007) -[2023-10-16 03:07:36,777][05219] Updated weights for policy 1, policy_version 9040 (0.0009) -[2023-10-16 03:07:37,137][05219] Updated weights for policy 1, policy_version 9050 (0.0008) -[2023-10-16 03:07:37,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 18546688. Throughput: 0: 1775.2, 1: 1786.1. Samples: 4650950. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-16 03:07:37,351][03835] Avg episode reward: [(0, '3.470'), (1, '3.270')] -[2023-10-16 03:07:37,362][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000009088_9306112.pth... -[2023-10-16 03:07:37,362][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000009056_9273344.pth... -[2023-10-16 03:07:37,392][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000007424_7602176.pth -[2023-10-16 03:07:37,393][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000007392_7569408.pth -[2023-10-16 03:07:37,396][04766] Saving new best policy, reward=3.470! -[2023-10-16 03:07:40,029][05218] Updated weights for policy 0, policy_version 9092 (0.0007) -[2023-10-16 03:07:40,401][05218] Updated weights for policy 0, policy_version 9102 (0.0008) -[2023-10-16 03:07:40,778][05218] Updated weights for policy 0, policy_version 9112 (0.0007) -[2023-10-16 03:07:40,986][05219] Updated weights for policy 1, policy_version 9060 (0.0007) -[2023-10-16 03:07:41,371][05219] Updated weights for policy 1, policy_version 9070 (0.0007) -[2023-10-16 03:07:41,737][05219] Updated weights for policy 1, policy_version 9080 (0.0008) -[2023-10-16 03:07:42,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 18644992. Throughput: 0: 1797.4, 1: 1783.6. Samples: 4662624. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:07:42,352][03835] Avg episode reward: [(0, '3.370'), (1, '2.780')] -[2023-10-16 03:07:44,331][05218] Updated weights for policy 0, policy_version 9122 (0.0008) -[2023-10-16 03:07:44,706][05218] Updated weights for policy 0, policy_version 9132 (0.0009) -[2023-10-16 03:07:45,080][05218] Updated weights for policy 0, policy_version 9142 (0.0008) -[2023-10-16 03:07:45,455][05218] Updated weights for policy 0, policy_version 9152 (0.0009) -[2023-10-16 03:07:45,480][05219] Updated weights for policy 1, policy_version 9090 (0.0009) -[2023-10-16 03:07:45,852][05219] Updated weights for policy 1, policy_version 9100 (0.0007) -[2023-10-16 03:07:46,219][05219] Updated weights for policy 1, policy_version 9110 (0.0009) -[2023-10-16 03:07:46,592][05219] Updated weights for policy 1, policy_version 9120 (0.0009) -[2023-10-16 03:07:47,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14199.6, 300 sec: 14329.1). Total num frames: 18710528. Throughput: 0: 1784.2, 1: 1790.2. Samples: 4683490. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:07:47,351][03835] Avg episode reward: [(0, '3.220'), (1, '2.780')] -[2023-10-16 03:07:49,298][05218] Updated weights for policy 0, policy_version 9162 (0.0009) -[2023-10-16 03:07:49,675][05218] Updated weights for policy 0, policy_version 9172 (0.0008) -[2023-10-16 03:07:50,058][05218] Updated weights for policy 0, policy_version 9182 (0.0008) -[2023-10-16 03:07:50,261][05219] Updated weights for policy 1, policy_version 9130 (0.0007) -[2023-10-16 03:07:50,632][05219] Updated weights for policy 1, policy_version 9140 (0.0010) -[2023-10-16 03:07:50,993][05219] Updated weights for policy 1, policy_version 9150 (0.0009) -[2023-10-16 03:07:52,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 18776064. Throughput: 0: 1788.6, 1: 1778.2. Samples: 4705342. Policy #0 lag: (min: 17.0, avg: 26.3, max: 49.0) -[2023-10-16 03:07:52,351][03835] Avg episode reward: [(0, '3.220'), (1, '2.750')] -[2023-10-16 03:07:53,631][05218] Updated weights for policy 0, policy_version 9192 (0.0009) -[2023-10-16 03:07:54,018][05218] Updated weights for policy 0, policy_version 9202 (0.0010) -[2023-10-16 03:07:54,392][05218] Updated weights for policy 0, policy_version 9212 (0.0011) -[2023-10-16 03:07:54,863][05219] Updated weights for policy 1, policy_version 9160 (0.0008) -[2023-10-16 03:07:55,233][05219] Updated weights for policy 1, policy_version 9170 (0.0008) -[2023-10-16 03:07:55,603][05219] Updated weights for policy 1, policy_version 9180 (0.0010) -[2023-10-16 03:07:57,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 18841600. Throughput: 0: 1791.3, 1: 1795.0. Samples: 4715818. Policy #0 lag: (min: 17.0, avg: 26.3, max: 49.0) -[2023-10-16 03:07:57,351][03835] Avg episode reward: [(0, '3.100'), (1, '2.750')] -[2023-10-16 03:07:58,066][05218] Updated weights for policy 0, policy_version 9222 (0.0009) -[2023-10-16 03:07:58,459][05218] Updated weights for policy 0, policy_version 9232 (0.0008) -[2023-10-16 03:07:58,833][05218] Updated weights for policy 0, policy_version 9242 (0.0010) -[2023-10-16 03:07:59,366][05219] Updated weights for policy 1, policy_version 9190 (0.0010) -[2023-10-16 03:07:59,734][05219] Updated weights for policy 1, policy_version 9200 (0.0009) -[2023-10-16 03:08:00,108][05219] Updated weights for policy 1, policy_version 9210 (0.0008) -[2023-10-16 03:08:02,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 18907136. Throughput: 0: 1793.1, 1: 1778.0. Samples: 4737314. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:08:02,351][03835] Avg episode reward: [(0, '3.030'), (1, '2.840')] -[2023-10-16 03:08:02,552][05218] Updated weights for policy 0, policy_version 9252 (0.0010) -[2023-10-16 03:08:02,936][05218] Updated weights for policy 0, policy_version 9262 (0.0008) -[2023-10-16 03:08:03,319][05218] Updated weights for policy 0, policy_version 9272 (0.0009) -[2023-10-16 03:08:03,966][05219] Updated weights for policy 1, policy_version 9220 (0.0009) -[2023-10-16 03:08:04,337][05219] Updated weights for policy 1, policy_version 9230 (0.0010) -[2023-10-16 03:08:04,703][05219] Updated weights for policy 1, policy_version 9240 (0.0009) -[2023-10-16 03:08:06,985][05218] Updated weights for policy 0, policy_version 9282 (0.0009) -[2023-10-16 03:08:07,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 18972672. Throughput: 0: 1799.9, 1: 1774.2. Samples: 4759122. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:08:07,351][03835] Avg episode reward: [(0, '3.020'), (1, '3.120')] -[2023-10-16 03:08:07,377][05218] Updated weights for policy 0, policy_version 9292 (0.0009) -[2023-10-16 03:08:07,745][05218] Updated weights for policy 0, policy_version 9302 (0.0010) -[2023-10-16 03:08:08,119][05218] Updated weights for policy 0, policy_version 9312 (0.0008) -[2023-10-16 03:08:08,459][05219] Updated weights for policy 1, policy_version 9250 (0.0008) -[2023-10-16 03:08:08,824][05219] Updated weights for policy 1, policy_version 9260 (0.0009) -[2023-10-16 03:08:09,182][05219] Updated weights for policy 1, policy_version 9270 (0.0009) -[2023-10-16 03:08:09,553][05219] Updated weights for policy 1, policy_version 9280 (0.0008) -[2023-10-16 03:08:11,897][05218] Updated weights for policy 0, policy_version 9322 (0.0009) -[2023-10-16 03:08:12,264][05218] Updated weights for policy 0, policy_version 9332 (0.0008) -[2023-10-16 03:08:12,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 19038208. Throughput: 0: 1787.3, 1: 1777.3. Samples: 4769436. Policy #0 lag: (min: 11.0, avg: 26.2, max: 43.0) -[2023-10-16 03:08:12,351][03835] Avg episode reward: [(0, '3.080'), (1, '3.110')] -[2023-10-16 03:08:12,651][05218] Updated weights for policy 0, policy_version 9342 (0.0007) -[2023-10-16 03:08:13,437][05219] Updated weights for policy 1, policy_version 9290 (0.0008) -[2023-10-16 03:08:13,811][05219] Updated weights for policy 1, policy_version 9300 (0.0009) -[2023-10-16 03:08:14,174][05219] Updated weights for policy 1, policy_version 9310 (0.0007) -[2023-10-16 03:08:16,355][05218] Updated weights for policy 0, policy_version 9352 (0.0007) -[2023-10-16 03:08:16,735][05218] Updated weights for policy 0, policy_version 9362 (0.0010) -[2023-10-16 03:08:17,106][05218] Updated weights for policy 0, policy_version 9372 (0.0009) -[2023-10-16 03:08:17,351][03835] Fps is (10 sec: 16383.3, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 19136512. Throughput: 0: 1806.1, 1: 1775.3. Samples: 4791418. Policy #0 lag: (min: 31.0, avg: 32.0, max: 52.0) -[2023-10-16 03:08:17,352][03835] Avg episode reward: [(0, '3.040'), (1, '3.020')] -[2023-10-16 03:08:17,719][05219] Updated weights for policy 1, policy_version 9320 (0.0008) -[2023-10-16 03:08:18,086][05219] Updated weights for policy 1, policy_version 9330 (0.0010) -[2023-10-16 03:08:18,447][05219] Updated weights for policy 1, policy_version 9340 (0.0010) -[2023-10-16 03:08:20,771][05218] Updated weights for policy 0, policy_version 9382 (0.0008) -[2023-10-16 03:08:21,144][05218] Updated weights for policy 0, policy_version 9392 (0.0008) -[2023-10-16 03:08:21,525][05218] Updated weights for policy 0, policy_version 9402 (0.0007) -[2023-10-16 03:08:22,309][05219] Updated weights for policy 1, policy_version 9350 (0.0010) -[2023-10-16 03:08:22,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 19202048. Throughput: 0: 1794.5, 1: 1800.2. Samples: 4812712. Policy #0 lag: (min: 31.0, avg: 32.0, max: 52.0) -[2023-10-16 03:08:22,351][03835] Avg episode reward: [(0, '3.040'), (1, '3.100')] -[2023-10-16 03:08:22,677][05219] Updated weights for policy 1, policy_version 9360 (0.0007) -[2023-10-16 03:08:23,046][05219] Updated weights for policy 1, policy_version 9370 (0.0007) -[2023-10-16 03:08:25,345][05218] Updated weights for policy 0, policy_version 9412 (0.0007) -[2023-10-16 03:08:25,721][05218] Updated weights for policy 0, policy_version 9422 (0.0009) -[2023-10-16 03:08:26,087][05218] Updated weights for policy 0, policy_version 9432 (0.0009) -[2023-10-16 03:08:26,915][05219] Updated weights for policy 1, policy_version 9380 (0.0008) -[2023-10-16 03:08:27,302][05219] Updated weights for policy 1, policy_version 9390 (0.0010) -[2023-10-16 03:08:27,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 19267584. Throughput: 0: 1801.3, 1: 1773.6. Samples: 4823490. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:08:27,351][03835] Avg episode reward: [(0, '2.960'), (1, '3.080')] -[2023-10-16 03:08:27,666][05219] Updated weights for policy 1, policy_version 9400 (0.0008) -[2023-10-16 03:08:29,943][05218] Updated weights for policy 0, policy_version 9442 (0.0009) -[2023-10-16 03:08:30,329][05218] Updated weights for policy 0, policy_version 9452 (0.0007) -[2023-10-16 03:08:30,712][05218] Updated weights for policy 0, policy_version 9462 (0.0008) -[2023-10-16 03:08:31,084][05218] Updated weights for policy 0, policy_version 9472 (0.0009) -[2023-10-16 03:08:31,480][05219] Updated weights for policy 1, policy_version 9410 (0.0009) -[2023-10-16 03:08:31,846][05219] Updated weights for policy 1, policy_version 9420 (0.0009) -[2023-10-16 03:08:32,212][05219] Updated weights for policy 1, policy_version 9430 (0.0009) -[2023-10-16 03:08:32,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 19333120. Throughput: 0: 1783.3, 1: 1784.7. Samples: 4844048. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:08:32,351][03835] Avg episode reward: [(0, '2.970'), (1, '3.080')] -[2023-10-16 03:08:32,578][05219] Updated weights for policy 1, policy_version 9440 (0.0009) -[2023-10-16 03:08:34,884][05218] Updated weights for policy 0, policy_version 9482 (0.0009) -[2023-10-16 03:08:35,255][05218] Updated weights for policy 0, policy_version 9492 (0.0008) -[2023-10-16 03:08:35,640][05218] Updated weights for policy 0, policy_version 9502 (0.0010) -[2023-10-16 03:08:36,367][05219] Updated weights for policy 1, policy_version 9450 (0.0009) -[2023-10-16 03:08:36,733][05219] Updated weights for policy 1, policy_version 9460 (0.0009) -[2023-10-16 03:08:37,099][05219] Updated weights for policy 1, policy_version 9470 (0.0011) -[2023-10-16 03:08:37,350][03835] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 19431424. Throughput: 0: 1778.9, 1: 1770.4. Samples: 4865062. Policy #0 lag: (min: 21.0, avg: 21.3, max: 31.0) -[2023-10-16 03:08:37,351][03835] Avg episode reward: [(0, '3.170'), (1, '2.960')] -[2023-10-16 03:08:39,315][05218] Updated weights for policy 0, policy_version 9512 (0.0008) -[2023-10-16 03:08:39,697][05218] Updated weights for policy 0, policy_version 9522 (0.0008) -[2023-10-16 03:08:40,073][05218] Updated weights for policy 0, policy_version 9532 (0.0008) -[2023-10-16 03:08:40,962][05219] Updated weights for policy 1, policy_version 9480 (0.0009) -[2023-10-16 03:08:41,328][05219] Updated weights for policy 1, policy_version 9490 (0.0009) -[2023-10-16 03:08:41,689][05219] Updated weights for policy 1, policy_version 9500 (0.0007) -[2023-10-16 03:08:42,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 19496960. Throughput: 0: 1778.1, 1: 1779.4. Samples: 4875908. Policy #0 lag: (min: 21.0, avg: 21.3, max: 31.0) -[2023-10-16 03:08:42,351][03835] Avg episode reward: [(0, '3.400'), (1, '2.860')] -[2023-10-16 03:08:43,714][05218] Updated weights for policy 0, policy_version 9542 (0.0008) -[2023-10-16 03:08:44,085][05218] Updated weights for policy 0, policy_version 9552 (0.0008) -[2023-10-16 03:08:44,459][05218] Updated weights for policy 0, policy_version 9562 (0.0009) -[2023-10-16 03:08:45,504][05219] Updated weights for policy 1, policy_version 9510 (0.0009) -[2023-10-16 03:08:45,869][05219] Updated weights for policy 1, policy_version 9520 (0.0008) -[2023-10-16 03:08:46,233][05219] Updated weights for policy 1, policy_version 9530 (0.0009) -[2023-10-16 03:08:47,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 19562496. Throughput: 0: 1781.5, 1: 1774.0. Samples: 4897314. Policy #0 lag: (min: 18.0, avg: 25.8, max: 50.0) -[2023-10-16 03:08:47,351][03835] Avg episode reward: [(0, '3.430'), (1, '2.900')] -[2023-10-16 03:08:48,316][05218] Updated weights for policy 0, policy_version 9572 (0.0007) -[2023-10-16 03:08:48,691][05218] Updated weights for policy 0, policy_version 9582 (0.0009) -[2023-10-16 03:08:49,065][05218] Updated weights for policy 0, policy_version 9592 (0.0009) -[2023-10-16 03:08:50,011][05219] Updated weights for policy 1, policy_version 9540 (0.0008) -[2023-10-16 03:08:50,385][05219] Updated weights for policy 1, policy_version 9550 (0.0010) -[2023-10-16 03:08:50,749][05219] Updated weights for policy 1, policy_version 9560 (0.0010) -[2023-10-16 03:08:52,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 19628032. Throughput: 0: 1792.0, 1: 1767.1. Samples: 4919280. Policy #0 lag: (min: 18.0, avg: 25.8, max: 50.0) -[2023-10-16 03:08:52,351][03835] Avg episode reward: [(0, '3.450'), (1, '2.790')] -[2023-10-16 03:08:52,927][05218] Updated weights for policy 0, policy_version 9602 (0.0007) -[2023-10-16 03:08:53,304][05218] Updated weights for policy 0, policy_version 9612 (0.0008) -[2023-10-16 03:08:53,683][05218] Updated weights for policy 0, policy_version 9622 (0.0009) -[2023-10-16 03:08:54,053][05218] Updated weights for policy 0, policy_version 9632 (0.0009) -[2023-10-16 03:08:54,411][05219] Updated weights for policy 1, policy_version 9570 (0.0011) -[2023-10-16 03:08:54,777][05219] Updated weights for policy 1, policy_version 9580 (0.0009) -[2023-10-16 03:08:55,147][05219] Updated weights for policy 1, policy_version 9590 (0.0008) -[2023-10-16 03:08:55,507][05219] Updated weights for policy 1, policy_version 9600 (0.0008) -[2023-10-16 03:08:57,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 19693568. Throughput: 0: 1780.4, 1: 1781.4. Samples: 4929714. Policy #0 lag: (min: 14.0, avg: 16.9, max: 46.0) -[2023-10-16 03:08:57,351][03835] Avg episode reward: [(0, '3.530'), (1, '2.870')] -[2023-10-16 03:08:57,762][05218] Updated weights for policy 0, policy_version 9642 (0.0008) -[2023-10-16 03:08:58,139][05218] Updated weights for policy 0, policy_version 9652 (0.0008) -[2023-10-16 03:08:58,508][05218] Updated weights for policy 0, policy_version 9662 (0.0010) -[2023-10-16 03:08:58,580][04766] Saving new best policy, reward=3.530! -[2023-10-16 03:08:59,318][05219] Updated weights for policy 1, policy_version 9610 (0.0008) -[2023-10-16 03:08:59,678][05219] Updated weights for policy 1, policy_version 9620 (0.0008) -[2023-10-16 03:09:00,054][05219] Updated weights for policy 1, policy_version 9630 (0.0009) -[2023-10-16 03:09:02,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 19759104. Throughput: 0: 1784.5, 1: 1775.4. Samples: 4951616. Policy #0 lag: (min: 14.0, avg: 16.9, max: 46.0) -[2023-10-16 03:09:02,351][03835] Avg episode reward: [(0, '3.420'), (1, '3.090')] -[2023-10-16 03:09:02,359][05218] Updated weights for policy 0, policy_version 9672 (0.0009) -[2023-10-16 03:09:02,744][05218] Updated weights for policy 0, policy_version 9682 (0.0009) -[2023-10-16 03:09:03,123][05218] Updated weights for policy 0, policy_version 9692 (0.0008) -[2023-10-16 03:09:03,808][05219] Updated weights for policy 1, policy_version 9640 (0.0011) -[2023-10-16 03:09:04,170][05219] Updated weights for policy 1, policy_version 9650 (0.0008) -[2023-10-16 03:09:04,540][05219] Updated weights for policy 1, policy_version 9660 (0.0010) -[2023-10-16 03:09:06,857][05218] Updated weights for policy 0, policy_version 9702 (0.0008) -[2023-10-16 03:09:07,230][05218] Updated weights for policy 0, policy_version 9712 (0.0008) -[2023-10-16 03:09:07,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 19824640. Throughput: 0: 1789.1, 1: 1777.3. Samples: 4973200. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:09:07,351][03835] Avg episode reward: [(0, '3.370'), (1, '3.300')] -[2023-10-16 03:09:07,597][05218] Updated weights for policy 0, policy_version 9722 (0.0009) -[2023-10-16 03:09:08,303][05219] Updated weights for policy 1, policy_version 9670 (0.0009) -[2023-10-16 03:09:08,676][05219] Updated weights for policy 1, policy_version 9680 (0.0007) -[2023-10-16 03:09:09,042][05219] Updated weights for policy 1, policy_version 9690 (0.0007) -[2023-10-16 03:09:11,364][05218] Updated weights for policy 0, policy_version 9732 (0.0009) -[2023-10-16 03:09:11,736][05218] Updated weights for policy 0, policy_version 9742 (0.0008) -[2023-10-16 03:09:12,113][05218] Updated weights for policy 0, policy_version 9752 (0.0008) -[2023-10-16 03:09:12,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 19890176. Throughput: 0: 1782.7, 1: 1780.0. Samples: 4983810. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:09:12,351][03835] Avg episode reward: [(0, '3.430'), (1, '3.140')] -[2023-10-16 03:09:12,885][05219] Updated weights for policy 1, policy_version 9700 (0.0009) -[2023-10-16 03:09:13,257][05219] Updated weights for policy 1, policy_version 9710 (0.0007) -[2023-10-16 03:09:13,623][05219] Updated weights for policy 1, policy_version 9720 (0.0010) -[2023-10-16 03:09:15,933][05218] Updated weights for policy 0, policy_version 9762 (0.0007) -[2023-10-16 03:09:16,309][05218] Updated weights for policy 0, policy_version 9772 (0.0010) -[2023-10-16 03:09:16,684][05218] Updated weights for policy 0, policy_version 9782 (0.0009) -[2023-10-16 03:09:17,050][05218] Updated weights for policy 0, policy_version 9792 (0.0008) -[2023-10-16 03:09:17,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 19988480. Throughput: 0: 1797.1, 1: 1786.4. Samples: 5005306. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-16 03:09:17,351][05219] Updated weights for policy 1, policy_version 9730 (0.0008) -[2023-10-16 03:09:17,351][03835] Avg episode reward: [(0, '3.420'), (1, '3.040')] -[2023-10-16 03:09:17,716][05219] Updated weights for policy 1, policy_version 9740 (0.0009) -[2023-10-16 03:09:18,077][05219] Updated weights for policy 1, policy_version 9750 (0.0008) -[2023-10-16 03:09:18,452][05219] Updated weights for policy 1, policy_version 9760 (0.0009) -[2023-10-16 03:09:20,830][05218] Updated weights for policy 0, policy_version 9802 (0.0008) -[2023-10-16 03:09:21,201][05218] Updated weights for policy 0, policy_version 9812 (0.0009) -[2023-10-16 03:09:21,591][05218] Updated weights for policy 0, policy_version 9822 (0.0009) -[2023-10-16 03:09:22,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 20054016. Throughput: 0: 1781.4, 1: 1807.1. Samples: 5026542. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-16 03:09:22,351][03835] Avg episode reward: [(0, '3.600'), (1, '2.990')] -[2023-10-16 03:09:22,361][04766] Saving new best policy, reward=3.600! -[2023-10-16 03:09:22,440][05219] Updated weights for policy 1, policy_version 9770 (0.0009) -[2023-10-16 03:09:22,811][05219] Updated weights for policy 1, policy_version 9780 (0.0011) -[2023-10-16 03:09:23,169][05219] Updated weights for policy 1, policy_version 9790 (0.0010) -[2023-10-16 03:09:25,389][05218] Updated weights for policy 0, policy_version 9832 (0.0010) -[2023-10-16 03:09:25,771][05218] Updated weights for policy 0, policy_version 9842 (0.0009) -[2023-10-16 03:09:26,146][05218] Updated weights for policy 0, policy_version 9852 (0.0008) -[2023-10-16 03:09:26,902][05219] Updated weights for policy 1, policy_version 9800 (0.0008) -[2023-10-16 03:09:27,271][05219] Updated weights for policy 1, policy_version 9810 (0.0007) -[2023-10-16 03:09:27,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 20119552. Throughput: 0: 1804.7, 1: 1784.4. Samples: 5037414. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-16 03:09:27,351][03835] Avg episode reward: [(0, '3.670'), (1, '3.130')] -[2023-10-16 03:09:27,351][04766] Saving new best policy, reward=3.670! -[2023-10-16 03:09:27,645][05219] Updated weights for policy 1, policy_version 9820 (0.0007) -[2023-10-16 03:09:29,870][05218] Updated weights for policy 0, policy_version 9862 (0.0008) -[2023-10-16 03:09:30,242][05218] Updated weights for policy 0, policy_version 9872 (0.0007) -[2023-10-16 03:09:30,627][05218] Updated weights for policy 0, policy_version 9882 (0.0007) -[2023-10-16 03:09:31,463][05219] Updated weights for policy 1, policy_version 9830 (0.0008) -[2023-10-16 03:09:31,826][05219] Updated weights for policy 1, policy_version 9840 (0.0007) -[2023-10-16 03:09:32,198][05219] Updated weights for policy 1, policy_version 9850 (0.0007) -[2023-10-16 03:09:32,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 20185088. Throughput: 0: 1780.1, 1: 1806.3. Samples: 5058706. Policy #0 lag: (min: 26.0, avg: 33.9, max: 58.0) -[2023-10-16 03:09:32,352][03835] Avg episode reward: [(0, '3.400'), (1, '3.070')] -[2023-10-16 03:09:34,320][05218] Updated weights for policy 0, policy_version 9892 (0.0009) -[2023-10-16 03:09:34,696][05218] Updated weights for policy 0, policy_version 9902 (0.0008) -[2023-10-16 03:09:35,073][05218] Updated weights for policy 0, policy_version 9912 (0.0009) -[2023-10-16 03:09:35,927][05219] Updated weights for policy 1, policy_version 9860 (0.0008) -[2023-10-16 03:09:36,293][05219] Updated weights for policy 1, policy_version 9870 (0.0010) -[2023-10-16 03:09:36,660][05219] Updated weights for policy 1, policy_version 9880 (0.0010) -[2023-10-16 03:09:37,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 20283392. Throughput: 0: 1782.6, 1: 1786.8. Samples: 5079906. Policy #0 lag: (min: 26.0, avg: 33.9, max: 58.0) -[2023-10-16 03:09:37,351][03835] Avg episode reward: [(0, '3.550'), (1, '3.040')] -[2023-10-16 03:09:37,362][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000009888_10125312.pth... -[2023-10-16 03:09:37,363][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000009920_10158080.pth... -[2023-10-16 03:09:37,392][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000008224_8421376.pth -[2023-10-16 03:09:37,400][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000008256_8454144.pth -[2023-10-16 03:09:38,792][05218] Updated weights for policy 0, policy_version 9922 (0.0010) -[2023-10-16 03:09:39,172][05218] Updated weights for policy 0, policy_version 9932 (0.0010) -[2023-10-16 03:09:39,536][05218] Updated weights for policy 0, policy_version 9942 (0.0008) -[2023-10-16 03:09:39,920][05218] Updated weights for policy 0, policy_version 9952 (0.0007) -[2023-10-16 03:09:40,422][05219] Updated weights for policy 1, policy_version 9890 (0.0010) -[2023-10-16 03:09:40,784][05219] Updated weights for policy 1, policy_version 9900 (0.0007) -[2023-10-16 03:09:41,163][05219] Updated weights for policy 1, policy_version 9910 (0.0007) -[2023-10-16 03:09:41,521][05219] Updated weights for policy 1, policy_version 9920 (0.0008) -[2023-10-16 03:09:42,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 20348928. Throughput: 0: 1780.3, 1: 1803.6. Samples: 5090988. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:09:42,351][03835] Avg episode reward: [(0, '3.370'), (1, '2.990')] -[2023-10-16 03:09:43,685][05218] Updated weights for policy 0, policy_version 9962 (0.0007) -[2023-10-16 03:09:44,066][05218] Updated weights for policy 0, policy_version 9972 (0.0008) -[2023-10-16 03:09:44,445][05218] Updated weights for policy 0, policy_version 9982 (0.0007) -[2023-10-16 03:09:45,208][05219] Updated weights for policy 1, policy_version 9930 (0.0010) -[2023-10-16 03:09:45,580][05219] Updated weights for policy 1, policy_version 9940 (0.0010) -[2023-10-16 03:09:45,935][05219] Updated weights for policy 1, policy_version 9950 (0.0010) -[2023-10-16 03:09:47,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 20414464. Throughput: 0: 1784.1, 1: 1780.9. Samples: 5112042. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:09:47,351][03835] Avg episode reward: [(0, '3.500'), (1, '2.930')] -[2023-10-16 03:09:48,382][05218] Updated weights for policy 0, policy_version 9992 (0.0011) -[2023-10-16 03:09:48,757][05218] Updated weights for policy 0, policy_version 10002 (0.0008) -[2023-10-16 03:09:49,129][05218] Updated weights for policy 0, policy_version 10012 (0.0009) -[2023-10-16 03:09:49,699][05219] Updated weights for policy 1, policy_version 9960 (0.0010) -[2023-10-16 03:09:50,070][05219] Updated weights for policy 1, policy_version 9970 (0.0010) -[2023-10-16 03:09:50,438][05219] Updated weights for policy 1, policy_version 9980 (0.0010) -[2023-10-16 03:09:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 20480000. Throughput: 0: 1800.3, 1: 1774.6. Samples: 5134070. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-16 03:09:52,351][03835] Avg episode reward: [(0, '3.090'), (1, '2.820')] -[2023-10-16 03:09:52,811][05218] Updated weights for policy 0, policy_version 10022 (0.0008) -[2023-10-16 03:09:53,181][05218] Updated weights for policy 0, policy_version 10032 (0.0009) -[2023-10-16 03:09:53,552][05218] Updated weights for policy 0, policy_version 10042 (0.0007) -[2023-10-16 03:09:54,133][05219] Updated weights for policy 1, policy_version 9990 (0.0010) -[2023-10-16 03:09:54,507][05219] Updated weights for policy 1, policy_version 10000 (0.0010) -[2023-10-16 03:09:54,877][05219] Updated weights for policy 1, policy_version 10010 (0.0008) -[2023-10-16 03:09:57,277][05218] Updated weights for policy 0, policy_version 10052 (0.0009) -[2023-10-16 03:09:57,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 20545536. Throughput: 0: 1783.8, 1: 1776.7. Samples: 5144032. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-16 03:09:57,351][03835] Avg episode reward: [(0, '3.100'), (1, '3.160')] -[2023-10-16 03:09:57,657][05218] Updated weights for policy 0, policy_version 10062 (0.0008) -[2023-10-16 03:09:58,030][05218] Updated weights for policy 0, policy_version 10072 (0.0009) -[2023-10-16 03:09:58,872][05219] Updated weights for policy 1, policy_version 10020 (0.0008) -[2023-10-16 03:09:59,249][05219] Updated weights for policy 1, policy_version 10030 (0.0010) -[2023-10-16 03:09:59,621][05219] Updated weights for policy 1, policy_version 10040 (0.0009) -[2023-10-16 03:10:01,777][05218] Updated weights for policy 0, policy_version 10082 (0.0008) -[2023-10-16 03:10:02,158][05218] Updated weights for policy 0, policy_version 10092 (0.0007) -[2023-10-16 03:10:02,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 20611072. Throughput: 0: 1800.5, 1: 1768.7. Samples: 5165916. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-16 03:10:02,351][03835] Avg episode reward: [(0, '2.980'), (1, '3.000')] -[2023-10-16 03:10:02,525][05218] Updated weights for policy 0, policy_version 10102 (0.0008) -[2023-10-16 03:10:02,899][05218] Updated weights for policy 0, policy_version 10112 (0.0010) -[2023-10-16 03:10:03,384][05219] Updated weights for policy 1, policy_version 10050 (0.0011) -[2023-10-16 03:10:03,752][05219] Updated weights for policy 1, policy_version 10060 (0.0008) -[2023-10-16 03:10:04,123][05219] Updated weights for policy 1, policy_version 10070 (0.0011) -[2023-10-16 03:10:04,494][05219] Updated weights for policy 1, policy_version 10080 (0.0009) -[2023-10-16 03:10:06,656][05218] Updated weights for policy 0, policy_version 10122 (0.0008) -[2023-10-16 03:10:07,030][05218] Updated weights for policy 0, policy_version 10132 (0.0009) -[2023-10-16 03:10:07,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 20676608. Throughput: 0: 1791.0, 1: 1780.0. Samples: 5187240. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-16 03:10:07,351][03835] Avg episode reward: [(0, '3.140'), (1, '3.110')] -[2023-10-16 03:10:07,404][05218] Updated weights for policy 0, policy_version 10142 (0.0008) -[2023-10-16 03:10:08,175][05219] Updated weights for policy 1, policy_version 10090 (0.0008) -[2023-10-16 03:10:08,536][05219] Updated weights for policy 1, policy_version 10100 (0.0007) -[2023-10-16 03:10:08,903][05219] Updated weights for policy 1, policy_version 10110 (0.0008) -[2023-10-16 03:10:11,149][05218] Updated weights for policy 0, policy_version 10152 (0.0010) -[2023-10-16 03:10:11,513][05218] Updated weights for policy 0, policy_version 10162 (0.0008) -[2023-10-16 03:10:11,891][05218] Updated weights for policy 0, policy_version 10172 (0.0007) -[2023-10-16 03:10:12,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 20774912. Throughput: 0: 1795.7, 1: 1780.0. Samples: 5198318. Policy #0 lag: (min: 9.0, avg: 19.7, max: 41.0) -[2023-10-16 03:10:12,351][03835] Avg episode reward: [(0, '3.210'), (1, '2.990')] -[2023-10-16 03:10:12,607][05219] Updated weights for policy 1, policy_version 10120 (0.0008) -[2023-10-16 03:10:12,977][05219] Updated weights for policy 1, policy_version 10130 (0.0010) -[2023-10-16 03:10:13,338][05219] Updated weights for policy 1, policy_version 10140 (0.0008) -[2023-10-16 03:10:15,672][05218] Updated weights for policy 0, policy_version 10182 (0.0008) -[2023-10-16 03:10:16,056][05218] Updated weights for policy 0, policy_version 10192 (0.0009) -[2023-10-16 03:10:16,412][05218] Updated weights for policy 0, policy_version 10202 (0.0010) -[2023-10-16 03:10:17,228][05219] Updated weights for policy 1, policy_version 10150 (0.0010) -[2023-10-16 03:10:17,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 20840448. Throughput: 0: 1794.2, 1: 1783.7. Samples: 5219710. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:10:17,351][03835] Avg episode reward: [(0, '3.410'), (1, '3.160')] -[2023-10-16 03:10:17,592][05219] Updated weights for policy 1, policy_version 10160 (0.0009) -[2023-10-16 03:10:17,962][05219] Updated weights for policy 1, policy_version 10170 (0.0010) -[2023-10-16 03:10:20,068][05218] Updated weights for policy 0, policy_version 10212 (0.0008) -[2023-10-16 03:10:20,441][05218] Updated weights for policy 0, policy_version 10222 (0.0008) -[2023-10-16 03:10:20,817][05218] Updated weights for policy 0, policy_version 10232 (0.0008) -[2023-10-16 03:10:21,812][05219] Updated weights for policy 1, policy_version 10180 (0.0010) -[2023-10-16 03:10:22,181][05219] Updated weights for policy 1, policy_version 10190 (0.0008) -[2023-10-16 03:10:22,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 20905984. Throughput: 0: 1784.3, 1: 1799.4. Samples: 5241176. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:10:22,351][03835] Avg episode reward: [(0, '3.200'), (1, '3.330')] -[2023-10-16 03:10:22,545][05219] Updated weights for policy 1, policy_version 10200 (0.0009) -[2023-10-16 03:10:24,507][05218] Updated weights for policy 0, policy_version 10242 (0.0009) -[2023-10-16 03:10:24,874][05218] Updated weights for policy 0, policy_version 10252 (0.0008) -[2023-10-16 03:10:25,254][05218] Updated weights for policy 0, policy_version 10262 (0.0007) -[2023-10-16 03:10:25,632][05218] Updated weights for policy 0, policy_version 10272 (0.0007) -[2023-10-16 03:10:26,313][05219] Updated weights for policy 1, policy_version 10210 (0.0008) -[2023-10-16 03:10:26,686][05219] Updated weights for policy 1, policy_version 10220 (0.0008) -[2023-10-16 03:10:27,053][05219] Updated weights for policy 1, policy_version 10230 (0.0009) -[2023-10-16 03:10:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 20971520. Throughput: 0: 1796.9, 1: 1776.5. Samples: 5251792. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:10:27,351][03835] Avg episode reward: [(0, '3.080'), (1, '3.450')] -[2023-10-16 03:10:27,407][04891] Saving new best policy, reward=3.450! -[2023-10-16 03:10:27,408][05219] Updated weights for policy 1, policy_version 10240 (0.0010) -[2023-10-16 03:10:29,312][05218] Updated weights for policy 0, policy_version 10282 (0.0007) -[2023-10-16 03:10:29,693][05218] Updated weights for policy 0, policy_version 10292 (0.0009) -[2023-10-16 03:10:30,073][05218] Updated weights for policy 0, policy_version 10302 (0.0008) -[2023-10-16 03:10:31,025][05219] Updated weights for policy 1, policy_version 10250 (0.0008) -[2023-10-16 03:10:31,397][05219] Updated weights for policy 1, policy_version 10260 (0.0007) -[2023-10-16 03:10:31,765][05219] Updated weights for policy 1, policy_version 10270 (0.0008) -[2023-10-16 03:10:32,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 21069824. Throughput: 0: 1793.2, 1: 1792.4. Samples: 5273392. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) -[2023-10-16 03:10:32,351][03835] Avg episode reward: [(0, '2.960'), (1, '3.180')] -[2023-10-16 03:10:33,898][05218] Updated weights for policy 0, policy_version 10312 (0.0008) -[2023-10-16 03:10:34,278][05218] Updated weights for policy 0, policy_version 10322 (0.0010) -[2023-10-16 03:10:34,654][05218] Updated weights for policy 0, policy_version 10332 (0.0008) -[2023-10-16 03:10:35,619][05219] Updated weights for policy 1, policy_version 10280 (0.0010) -[2023-10-16 03:10:35,985][05219] Updated weights for policy 1, policy_version 10290 (0.0010) -[2023-10-16 03:10:36,351][05219] Updated weights for policy 1, policy_version 10300 (0.0009) -[2023-10-16 03:10:37,350][03835] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 21135360. Throughput: 0: 1791.4, 1: 1778.7. Samples: 5294722. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) -[2023-10-16 03:10:37,351][03835] Avg episode reward: [(0, '2.970'), (1, '3.070')] -[2023-10-16 03:10:38,313][05218] Updated weights for policy 0, policy_version 10342 (0.0007) -[2023-10-16 03:10:38,685][05218] Updated weights for policy 0, policy_version 10352 (0.0007) -[2023-10-16 03:10:39,065][05218] Updated weights for policy 0, policy_version 10362 (0.0008) -[2023-10-16 03:10:40,254][05219] Updated weights for policy 1, policy_version 10310 (0.0008) -[2023-10-16 03:10:40,623][05219] Updated weights for policy 1, policy_version 10320 (0.0008) -[2023-10-16 03:10:40,985][05219] Updated weights for policy 1, policy_version 10330 (0.0010) -[2023-10-16 03:10:42,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 21200896. Throughput: 0: 1791.3, 1: 1811.0. Samples: 5306136. Policy #0 lag: (min: 22.0, avg: 29.9, max: 54.0) -[2023-10-16 03:10:42,351][03835] Avg episode reward: [(0, '3.200'), (1, '2.910')] -[2023-10-16 03:10:42,756][05218] Updated weights for policy 0, policy_version 10372 (0.0008) -[2023-10-16 03:10:43,132][05218] Updated weights for policy 0, policy_version 10382 (0.0009) -[2023-10-16 03:10:43,499][05218] Updated weights for policy 0, policy_version 10392 (0.0010) -[2023-10-16 03:10:44,852][05219] Updated weights for policy 1, policy_version 10340 (0.0009) -[2023-10-16 03:10:45,212][05219] Updated weights for policy 1, policy_version 10350 (0.0008) -[2023-10-16 03:10:45,568][05219] Updated weights for policy 1, policy_version 10360 (0.0009) -[2023-10-16 03:10:47,274][05218] Updated weights for policy 0, policy_version 10402 (0.0009) -[2023-10-16 03:10:47,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 21266432. Throughput: 0: 1791.5, 1: 1786.5. Samples: 5326926. Policy #0 lag: (min: 22.0, avg: 29.9, max: 54.0) -[2023-10-16 03:10:47,351][03835] Avg episode reward: [(0, '3.420'), (1, '3.310')] -[2023-10-16 03:10:47,651][05218] Updated weights for policy 0, policy_version 10412 (0.0009) -[2023-10-16 03:10:48,023][05218] Updated weights for policy 0, policy_version 10422 (0.0007) -[2023-10-16 03:10:48,409][05218] Updated weights for policy 0, policy_version 10432 (0.0007) -[2023-10-16 03:10:49,279][05219] Updated weights for policy 1, policy_version 10370 (0.0011) -[2023-10-16 03:10:49,678][05219] Updated weights for policy 1, policy_version 10380 (0.0008) -[2023-10-16 03:10:50,045][05219] Updated weights for policy 1, policy_version 10390 (0.0008) -[2023-10-16 03:10:50,401][05219] Updated weights for policy 1, policy_version 10400 (0.0008) -[2023-10-16 03:10:52,154][05218] Updated weights for policy 0, policy_version 10442 (0.0010) -[2023-10-16 03:10:52,351][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 21331968. Throughput: 0: 1804.7, 1: 1780.7. Samples: 5348584. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:10:52,352][03835] Avg episode reward: [(0, '3.630'), (1, '3.380')] -[2023-10-16 03:10:52,531][05218] Updated weights for policy 0, policy_version 10452 (0.0010) -[2023-10-16 03:10:52,914][05218] Updated weights for policy 0, policy_version 10462 (0.0008) -[2023-10-16 03:10:53,962][05219] Updated weights for policy 1, policy_version 10410 (0.0010) -[2023-10-16 03:10:54,337][05219] Updated weights for policy 1, policy_version 10420 (0.0008) -[2023-10-16 03:10:54,706][05219] Updated weights for policy 1, policy_version 10430 (0.0009) -[2023-10-16 03:10:56,784][05218] Updated weights for policy 0, policy_version 10472 (0.0008) -[2023-10-16 03:10:57,160][05218] Updated weights for policy 0, policy_version 10482 (0.0009) -[2023-10-16 03:10:57,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 21397504. Throughput: 0: 1789.5, 1: 1777.7. Samples: 5358844. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:10:57,352][03835] Avg episode reward: [(0, '3.640'), (1, '3.520')] -[2023-10-16 03:10:57,353][04891] Saving new best policy, reward=3.520! -[2023-10-16 03:10:57,548][05218] Updated weights for policy 0, policy_version 10492 (0.0009) -[2023-10-16 03:10:58,570][05219] Updated weights for policy 1, policy_version 10440 (0.0009) -[2023-10-16 03:10:58,939][05219] Updated weights for policy 1, policy_version 10450 (0.0009) -[2023-10-16 03:10:59,304][05219] Updated weights for policy 1, policy_version 10460 (0.0008) -[2023-10-16 03:11:01,225][05218] Updated weights for policy 0, policy_version 10502 (0.0009) -[2023-10-16 03:11:01,597][05218] Updated weights for policy 0, policy_version 10512 (0.0010) -[2023-10-16 03:11:01,978][05218] Updated weights for policy 0, policy_version 10522 (0.0010) -[2023-10-16 03:11:02,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 21495808. Throughput: 0: 1808.7, 1: 1773.5. Samples: 5380910. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-16 03:11:02,352][03835] Avg episode reward: [(0, '3.350'), (1, '3.240')] -[2023-10-16 03:11:02,987][05219] Updated weights for policy 1, policy_version 10470 (0.0010) -[2023-10-16 03:11:03,360][05219] Updated weights for policy 1, policy_version 10480 (0.0010) -[2023-10-16 03:11:03,726][05219] Updated weights for policy 1, policy_version 10490 (0.0008) -[2023-10-16 03:11:05,689][05218] Updated weights for policy 0, policy_version 10532 (0.0008) -[2023-10-16 03:11:06,070][05218] Updated weights for policy 0, policy_version 10542 (0.0008) -[2023-10-16 03:11:06,433][05218] Updated weights for policy 0, policy_version 10552 (0.0008) -[2023-10-16 03:11:07,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 21561344. Throughput: 0: 1788.7, 1: 1792.2. Samples: 5402318. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-16 03:11:07,351][03835] Avg episode reward: [(0, '3.390'), (1, '3.390')] -[2023-10-16 03:11:07,453][05219] Updated weights for policy 1, policy_version 10500 (0.0008) -[2023-10-16 03:11:07,831][05219] Updated weights for policy 1, policy_version 10510 (0.0008) -[2023-10-16 03:11:08,193][05219] Updated weights for policy 1, policy_version 10520 (0.0007) -[2023-10-16 03:11:10,125][05218] Updated weights for policy 0, policy_version 10562 (0.0009) -[2023-10-16 03:11:10,497][05218] Updated weights for policy 0, policy_version 10572 (0.0007) -[2023-10-16 03:11:10,872][05218] Updated weights for policy 0, policy_version 10582 (0.0009) -[2023-10-16 03:11:11,250][05218] Updated weights for policy 0, policy_version 10592 (0.0010) -[2023-10-16 03:11:11,940][05219] Updated weights for policy 1, policy_version 10530 (0.0008) -[2023-10-16 03:11:12,303][05219] Updated weights for policy 1, policy_version 10540 (0.0008) -[2023-10-16 03:11:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 21626880. Throughput: 0: 1808.2, 1: 1783.9. Samples: 5413436. Policy #0 lag: (min: 25.0, avg: 35.9, max: 57.0) -[2023-10-16 03:11:12,351][03835] Avg episode reward: [(0, '3.040'), (1, '3.370')] -[2023-10-16 03:11:12,676][05219] Updated weights for policy 1, policy_version 10550 (0.0008) -[2023-10-16 03:11:13,038][05219] Updated weights for policy 1, policy_version 10560 (0.0008) -[2023-10-16 03:11:14,952][05218] Updated weights for policy 0, policy_version 10602 (0.0009) -[2023-10-16 03:11:15,331][05218] Updated weights for policy 0, policy_version 10612 (0.0009) -[2023-10-16 03:11:15,704][05218] Updated weights for policy 0, policy_version 10622 (0.0008) -[2023-10-16 03:11:16,962][05219] Updated weights for policy 1, policy_version 10570 (0.0008) -[2023-10-16 03:11:17,327][05219] Updated weights for policy 1, policy_version 10580 (0.0008) -[2023-10-16 03:11:17,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 21692416. Throughput: 0: 1782.8, 1: 1797.3. Samples: 5434498. Policy #0 lag: (min: 25.0, avg: 35.9, max: 57.0) -[2023-10-16 03:11:17,351][03835] Avg episode reward: [(0, '3.010'), (1, '3.240')] -[2023-10-16 03:11:17,700][05219] Updated weights for policy 1, policy_version 10590 (0.0007) -[2023-10-16 03:11:19,694][05218] Updated weights for policy 0, policy_version 10632 (0.0009) -[2023-10-16 03:11:20,067][05218] Updated weights for policy 0, policy_version 10642 (0.0008) -[2023-10-16 03:11:20,444][05218] Updated weights for policy 0, policy_version 10652 (0.0009) -[2023-10-16 03:11:21,533][05219] Updated weights for policy 1, policy_version 10600 (0.0007) -[2023-10-16 03:11:21,897][05219] Updated weights for policy 1, policy_version 10610 (0.0008) -[2023-10-16 03:11:22,265][05219] Updated weights for policy 1, policy_version 10620 (0.0008) -[2023-10-16 03:11:22,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 21757952. Throughput: 0: 1784.7, 1: 1794.9. Samples: 5455806. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-16 03:11:22,352][03835] Avg episode reward: [(0, '2.940'), (1, '3.380')] -[2023-10-16 03:11:24,131][05218] Updated weights for policy 0, policy_version 10662 (0.0008) -[2023-10-16 03:11:24,511][05218] Updated weights for policy 0, policy_version 10672 (0.0007) -[2023-10-16 03:11:24,878][05218] Updated weights for policy 0, policy_version 10682 (0.0007) -[2023-10-16 03:11:26,079][05219] Updated weights for policy 1, policy_version 10630 (0.0010) -[2023-10-16 03:11:26,448][05219] Updated weights for policy 1, policy_version 10640 (0.0009) -[2023-10-16 03:11:26,823][05219] Updated weights for policy 1, policy_version 10650 (0.0009) -[2023-10-16 03:11:27,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 21856256. Throughput: 0: 1779.7, 1: 1781.9. Samples: 5466408. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-16 03:11:27,351][03835] Avg episode reward: [(0, '3.210'), (1, '3.080')] -[2023-10-16 03:11:28,513][05218] Updated weights for policy 0, policy_version 10692 (0.0008) -[2023-10-16 03:11:28,879][05218] Updated weights for policy 0, policy_version 10702 (0.0009) -[2023-10-16 03:11:29,260][05218] Updated weights for policy 0, policy_version 10712 (0.0009) -[2023-10-16 03:11:30,440][05219] Updated weights for policy 1, policy_version 10660 (0.0010) -[2023-10-16 03:11:30,797][05219] Updated weights for policy 1, policy_version 10670 (0.0008) -[2023-10-16 03:11:31,162][05219] Updated weights for policy 1, policy_version 10680 (0.0008) -[2023-10-16 03:11:32,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 21921792. Throughput: 0: 1789.2, 1: 1795.6. Samples: 5488242. Policy #0 lag: (min: 18.0, avg: 42.6, max: 48.0) -[2023-10-16 03:11:32,351][03835] Avg episode reward: [(0, '3.420'), (1, '2.960')] -[2023-10-16 03:11:32,935][05218] Updated weights for policy 0, policy_version 10722 (0.0008) -[2023-10-16 03:11:33,312][05218] Updated weights for policy 0, policy_version 10732 (0.0008) -[2023-10-16 03:11:33,699][05218] Updated weights for policy 0, policy_version 10742 (0.0008) -[2023-10-16 03:11:34,071][05218] Updated weights for policy 0, policy_version 10752 (0.0008) -[2023-10-16 03:11:35,113][05219] Updated weights for policy 1, policy_version 10690 (0.0008) -[2023-10-16 03:11:35,528][05219] Updated weights for policy 1, policy_version 10700 (0.0009) -[2023-10-16 03:11:35,891][05219] Updated weights for policy 1, policy_version 10710 (0.0008) -[2023-10-16 03:11:36,251][05219] Updated weights for policy 1, policy_version 10720 (0.0009) -[2023-10-16 03:11:37,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 21987328. Throughput: 0: 1807.9, 1: 1782.6. Samples: 5510154. Policy #0 lag: (min: 18.0, avg: 42.6, max: 48.0) -[2023-10-16 03:11:37,352][03835] Avg episode reward: [(0, '3.510'), (1, '3.080')] -[2023-10-16 03:11:37,365][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000010752_11010048.pth... -[2023-10-16 03:11:37,365][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000010720_10977280.pth... -[2023-10-16 03:11:37,394][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000009088_9306112.pth -[2023-10-16 03:11:37,403][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000009056_9273344.pth -[2023-10-16 03:11:37,873][05218] Updated weights for policy 0, policy_version 10762 (0.0009) -[2023-10-16 03:11:38,252][05218] Updated weights for policy 0, policy_version 10772 (0.0009) -[2023-10-16 03:11:38,632][05218] Updated weights for policy 0, policy_version 10782 (0.0009) -[2023-10-16 03:11:40,105][05219] Updated weights for policy 1, policy_version 10730 (0.0009) -[2023-10-16 03:11:40,475][05219] Updated weights for policy 1, policy_version 10740 (0.0009) -[2023-10-16 03:11:40,841][05219] Updated weights for policy 1, policy_version 10750 (0.0010) -[2023-10-16 03:11:42,227][05218] Updated weights for policy 0, policy_version 10792 (0.0010) -[2023-10-16 03:11:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 22052864. Throughput: 0: 1796.1, 1: 1804.6. Samples: 5520874. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-16 03:11:42,351][03835] Avg episode reward: [(0, '3.420'), (1, '3.150')] -[2023-10-16 03:11:42,613][05218] Updated weights for policy 0, policy_version 10802 (0.0007) -[2023-10-16 03:11:42,989][05218] Updated weights for policy 0, policy_version 10812 (0.0010) -[2023-10-16 03:11:44,546][05219] Updated weights for policy 1, policy_version 10760 (0.0008) -[2023-10-16 03:11:44,919][05219] Updated weights for policy 1, policy_version 10770 (0.0007) -[2023-10-16 03:11:45,292][05219] Updated weights for policy 1, policy_version 10780 (0.0008) -[2023-10-16 03:11:46,830][05218] Updated weights for policy 0, policy_version 10822 (0.0010) -[2023-10-16 03:11:47,216][05218] Updated weights for policy 0, policy_version 10832 (0.0010) -[2023-10-16 03:11:47,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 22118400. Throughput: 0: 1801.0, 1: 1780.5. Samples: 5542076. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-16 03:11:47,352][03835] Avg episode reward: [(0, '3.450'), (1, '3.360')] -[2023-10-16 03:11:47,601][05218] Updated weights for policy 0, policy_version 10842 (0.0007) -[2023-10-16 03:11:49,062][05219] Updated weights for policy 1, policy_version 10790 (0.0009) -[2023-10-16 03:11:49,446][05219] Updated weights for policy 1, policy_version 10800 (0.0009) -[2023-10-16 03:11:49,810][05219] Updated weights for policy 1, policy_version 10810 (0.0007) -[2023-10-16 03:11:51,371][05218] Updated weights for policy 0, policy_version 10852 (0.0008) -[2023-10-16 03:11:51,734][05218] Updated weights for policy 0, policy_version 10862 (0.0008) -[2023-10-16 03:11:52,110][05218] Updated weights for policy 0, policy_version 10872 (0.0008) -[2023-10-16 03:11:52,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.6, 300 sec: 14218.0). Total num frames: 22183936. Throughput: 0: 1796.1, 1: 1773.1. Samples: 5562934. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:11:52,351][03835] Avg episode reward: [(0, '3.670'), (1, '3.190')] -[2023-10-16 03:11:53,540][05219] Updated weights for policy 1, policy_version 10820 (0.0008) -[2023-10-16 03:11:53,903][05219] Updated weights for policy 1, policy_version 10830 (0.0009) -[2023-10-16 03:11:54,272][05219] Updated weights for policy 1, policy_version 10840 (0.0008) -[2023-10-16 03:11:55,622][05218] Updated weights for policy 0, policy_version 10882 (0.0008) -[2023-10-16 03:11:55,987][05218] Updated weights for policy 0, policy_version 10892 (0.0008) -[2023-10-16 03:11:56,365][05218] Updated weights for policy 0, policy_version 10902 (0.0010) -[2023-10-16 03:11:56,735][05218] Updated weights for policy 0, policy_version 10912 (0.0007) -[2023-10-16 03:11:57,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 22282240. Throughput: 0: 1796.7, 1: 1771.2. Samples: 5573992. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:11:57,352][03835] Avg episode reward: [(0, '3.750'), (1, '3.210')] -[2023-10-16 03:11:57,353][04766] Saving new best policy, reward=3.750! -[2023-10-16 03:11:58,019][05219] Updated weights for policy 1, policy_version 10850 (0.0010) -[2023-10-16 03:11:58,393][05219] Updated weights for policy 1, policy_version 10860 (0.0007) -[2023-10-16 03:11:58,754][05219] Updated weights for policy 1, policy_version 10870 (0.0009) -[2023-10-16 03:11:59,124][05219] Updated weights for policy 1, policy_version 10880 (0.0008) -[2023-10-16 03:12:00,437][05218] Updated weights for policy 0, policy_version 10922 (0.0008) -[2023-10-16 03:12:00,809][05218] Updated weights for policy 0, policy_version 10932 (0.0009) -[2023-10-16 03:12:01,191][05218] Updated weights for policy 0, policy_version 10942 (0.0008) -[2023-10-16 03:12:02,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 22347776. Throughput: 0: 1793.1, 1: 1768.8. Samples: 5594786. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:12:02,351][03835] Avg episode reward: [(0, '3.610'), (1, '3.390')] -[2023-10-16 03:12:02,986][05219] Updated weights for policy 1, policy_version 10890 (0.0007) -[2023-10-16 03:12:03,344][05219] Updated weights for policy 1, policy_version 10900 (0.0010) -[2023-10-16 03:12:03,713][05219] Updated weights for policy 1, policy_version 10910 (0.0008) -[2023-10-16 03:12:04,889][05218] Updated weights for policy 0, policy_version 10952 (0.0008) -[2023-10-16 03:12:05,275][05218] Updated weights for policy 0, policy_version 10962 (0.0008) -[2023-10-16 03:12:05,638][05218] Updated weights for policy 0, policy_version 10972 (0.0009) -[2023-10-16 03:12:07,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 22413312. Throughput: 0: 1795.5, 1: 1792.5. Samples: 5617264. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:12:07,351][03835] Avg episode reward: [(0, '3.400'), (1, '3.230')] -[2023-10-16 03:12:07,401][05219] Updated weights for policy 1, policy_version 10920 (0.0008) -[2023-10-16 03:12:07,773][05219] Updated weights for policy 1, policy_version 10930 (0.0008) -[2023-10-16 03:12:08,139][05219] Updated weights for policy 1, policy_version 10940 (0.0008) -[2023-10-16 03:12:09,361][05218] Updated weights for policy 0, policy_version 10982 (0.0009) -[2023-10-16 03:12:09,738][05218] Updated weights for policy 0, policy_version 10992 (0.0008) -[2023-10-16 03:12:10,117][05218] Updated weights for policy 0, policy_version 11002 (0.0007) -[2023-10-16 03:12:11,915][05219] Updated weights for policy 1, policy_version 10950 (0.0007) -[2023-10-16 03:12:12,289][05219] Updated weights for policy 1, policy_version 10960 (0.0008) -[2023-10-16 03:12:12,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 22478848. Throughput: 0: 1802.0, 1: 1770.4. Samples: 5627168. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:12:12,351][03835] Avg episode reward: [(0, '3.850'), (1, '3.590')] -[2023-10-16 03:12:12,352][04766] Saving new best policy, reward=3.850! -[2023-10-16 03:12:12,655][05219] Updated weights for policy 1, policy_version 10970 (0.0008) -[2023-10-16 03:12:12,876][04891] Saving new best policy, reward=3.590! -[2023-10-16 03:12:13,948][05218] Updated weights for policy 0, policy_version 11012 (0.0009) -[2023-10-16 03:12:14,316][05218] Updated weights for policy 0, policy_version 11022 (0.0008) -[2023-10-16 03:12:14,697][05218] Updated weights for policy 0, policy_version 11032 (0.0007) -[2023-10-16 03:12:16,546][05219] Updated weights for policy 1, policy_version 10980 (0.0008) -[2023-10-16 03:12:16,918][05219] Updated weights for policy 1, policy_version 10990 (0.0007) -[2023-10-16 03:12:17,284][05219] Updated weights for policy 1, policy_version 11000 (0.0007) -[2023-10-16 03:12:17,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 22544384. Throughput: 0: 1789.4, 1: 1788.9. Samples: 5649264. Policy #0 lag: (min: 26.0, avg: 29.4, max: 58.0) -[2023-10-16 03:12:17,351][03835] Avg episode reward: [(0, '4.000'), (1, '3.360')] -[2023-10-16 03:12:17,352][04766] Saving new best policy, reward=4.000! -[2023-10-16 03:12:18,437][05218] Updated weights for policy 0, policy_version 11042 (0.0008) -[2023-10-16 03:12:18,800][05218] Updated weights for policy 0, policy_version 11052 (0.0011) -[2023-10-16 03:12:19,171][05218] Updated weights for policy 0, policy_version 11062 (0.0011) -[2023-10-16 03:12:19,547][05218] Updated weights for policy 0, policy_version 11072 (0.0009) -[2023-10-16 03:12:21,082][05219] Updated weights for policy 1, policy_version 11010 (0.0007) -[2023-10-16 03:12:21,476][05219] Updated weights for policy 1, policy_version 11020 (0.0007) -[2023-10-16 03:12:21,834][05219] Updated weights for policy 1, policy_version 11030 (0.0007) -[2023-10-16 03:12:22,200][05219] Updated weights for policy 1, policy_version 11040 (0.0010) -[2023-10-16 03:12:22,350][03835] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 22642688. Throughput: 0: 1787.8, 1: 1773.5. Samples: 5670414. Policy #0 lag: (min: 26.0, avg: 29.4, max: 58.0) -[2023-10-16 03:12:22,352][03835] Avg episode reward: [(0, '4.040'), (1, '3.520')] -[2023-10-16 03:12:22,360][04766] Saving new best policy, reward=4.040! -[2023-10-16 03:12:23,267][05218] Updated weights for policy 0, policy_version 11082 (0.0008) -[2023-10-16 03:12:23,640][05218] Updated weights for policy 0, policy_version 11092 (0.0010) -[2023-10-16 03:12:24,028][05218] Updated weights for policy 0, policy_version 11102 (0.0008) -[2023-10-16 03:12:25,748][05219] Updated weights for policy 1, policy_version 11050 (0.0008) -[2023-10-16 03:12:26,115][05219] Updated weights for policy 1, policy_version 11060 (0.0009) -[2023-10-16 03:12:26,490][05219] Updated weights for policy 1, policy_version 11070 (0.0008) -[2023-10-16 03:12:27,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 22708224. Throughput: 0: 1784.9, 1: 1783.1. Samples: 5681432. Policy #0 lag: (min: 26.0, avg: 29.4, max: 58.0) -[2023-10-16 03:12:27,351][03835] Avg episode reward: [(0, '3.490'), (1, '3.450')] -[2023-10-16 03:12:27,922][05218] Updated weights for policy 0, policy_version 11112 (0.0007) -[2023-10-16 03:12:28,302][05218] Updated weights for policy 0, policy_version 11122 (0.0008) -[2023-10-16 03:12:28,679][05218] Updated weights for policy 0, policy_version 11132 (0.0010) -[2023-10-16 03:12:30,395][05219] Updated weights for policy 1, policy_version 11080 (0.0008) -[2023-10-16 03:12:30,756][05219] Updated weights for policy 1, policy_version 11090 (0.0010) -[2023-10-16 03:12:31,128][05219] Updated weights for policy 1, policy_version 11100 (0.0009) -[2023-10-16 03:12:32,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 22773760. Throughput: 0: 1781.9, 1: 1780.2. Samples: 5702372. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-16 03:12:32,351][03835] Avg episode reward: [(0, '3.370'), (1, '3.350')] -[2023-10-16 03:12:32,437][05218] Updated weights for policy 0, policy_version 11142 (0.0007) -[2023-10-16 03:12:32,817][05218] Updated weights for policy 0, policy_version 11152 (0.0007) -[2023-10-16 03:12:33,198][05218] Updated weights for policy 0, policy_version 11162 (0.0007) -[2023-10-16 03:12:34,934][05219] Updated weights for policy 1, policy_version 11110 (0.0010) -[2023-10-16 03:12:35,297][05219] Updated weights for policy 1, policy_version 11120 (0.0007) -[2023-10-16 03:12:35,661][05219] Updated weights for policy 1, policy_version 11130 (0.0008) -[2023-10-16 03:12:36,988][05218] Updated weights for policy 0, policy_version 11172 (0.0010) -[2023-10-16 03:12:37,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 22839296. Throughput: 0: 1800.2, 1: 1773.6. Samples: 5723752. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-16 03:12:37,351][03835] Avg episode reward: [(0, '3.580'), (1, '3.180')] -[2023-10-16 03:12:37,354][05218] Updated weights for policy 0, policy_version 11182 (0.0008) -[2023-10-16 03:12:37,733][05218] Updated weights for policy 0, policy_version 11192 (0.0008) -[2023-10-16 03:12:39,518][05219] Updated weights for policy 1, policy_version 11140 (0.0008) -[2023-10-16 03:12:39,886][05219] Updated weights for policy 1, policy_version 11150 (0.0007) -[2023-10-16 03:12:40,254][05219] Updated weights for policy 1, policy_version 11160 (0.0007) -[2023-10-16 03:12:41,448][05218] Updated weights for policy 0, policy_version 11202 (0.0008) -[2023-10-16 03:12:41,839][05218] Updated weights for policy 0, policy_version 11212 (0.0009) -[2023-10-16 03:12:42,206][05218] Updated weights for policy 0, policy_version 11222 (0.0011) -[2023-10-16 03:12:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 22904832. Throughput: 0: 1784.5, 1: 1788.0. Samples: 5734754. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-16 03:12:42,351][03835] Avg episode reward: [(0, '3.480'), (1, '3.340')] -[2023-10-16 03:12:42,580][05218] Updated weights for policy 0, policy_version 11232 (0.0008) -[2023-10-16 03:12:44,073][05219] Updated weights for policy 1, policy_version 11170 (0.0008) -[2023-10-16 03:12:44,436][05219] Updated weights for policy 1, policy_version 11180 (0.0009) -[2023-10-16 03:12:44,806][05219] Updated weights for policy 1, policy_version 11190 (0.0007) -[2023-10-16 03:12:45,161][05219] Updated weights for policy 1, policy_version 11200 (0.0009) -[2023-10-16 03:12:46,388][05218] Updated weights for policy 0, policy_version 11242 (0.0009) -[2023-10-16 03:12:46,762][05218] Updated weights for policy 0, policy_version 11252 (0.0007) -[2023-10-16 03:12:47,127][05218] Updated weights for policy 0, policy_version 11262 (0.0010) -[2023-10-16 03:12:47,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 23003136. Throughput: 0: 1808.3, 1: 1776.4. Samples: 5756094. Policy #0 lag: (min: 17.0, avg: 27.0, max: 49.0) -[2023-10-16 03:12:47,351][03835] Avg episode reward: [(0, '3.550'), (1, '3.190')] -[2023-10-16 03:12:49,092][05219] Updated weights for policy 1, policy_version 11210 (0.0011) -[2023-10-16 03:12:49,459][05219] Updated weights for policy 1, policy_version 11220 (0.0010) -[2023-10-16 03:12:49,828][05219] Updated weights for policy 1, policy_version 11230 (0.0009) -[2023-10-16 03:12:50,948][05218] Updated weights for policy 0, policy_version 11272 (0.0011) -[2023-10-16 03:12:51,315][05218] Updated weights for policy 0, policy_version 11282 (0.0010) -[2023-10-16 03:12:51,695][05218] Updated weights for policy 0, policy_version 11292 (0.0008) -[2023-10-16 03:12:52,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 23068672. Throughput: 0: 1782.3, 1: 1771.6. Samples: 5777192. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) -[2023-10-16 03:12:52,351][03835] Avg episode reward: [(0, '3.420'), (1, '3.440')] -[2023-10-16 03:12:53,691][05219] Updated weights for policy 1, policy_version 11240 (0.0007) -[2023-10-16 03:12:54,054][05219] Updated weights for policy 1, policy_version 11250 (0.0008) -[2023-10-16 03:12:54,426][05219] Updated weights for policy 1, policy_version 11260 (0.0010) -[2023-10-16 03:12:55,564][05218] Updated weights for policy 0, policy_version 11302 (0.0008) -[2023-10-16 03:12:55,939][05218] Updated weights for policy 0, policy_version 11312 (0.0009) -[2023-10-16 03:12:56,320][05218] Updated weights for policy 0, policy_version 11322 (0.0011) -[2023-10-16 03:12:57,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 23134208. Throughput: 0: 1807.4, 1: 1769.3. Samples: 5788120. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) -[2023-10-16 03:12:57,351][03835] Avg episode reward: [(0, '3.520'), (1, '3.320')] -[2023-10-16 03:12:58,198][05219] Updated weights for policy 1, policy_version 11270 (0.0010) -[2023-10-16 03:12:58,560][05219] Updated weights for policy 1, policy_version 11280 (0.0008) -[2023-10-16 03:12:58,919][05219] Updated weights for policy 1, policy_version 11290 (0.0007) -[2023-10-16 03:12:59,889][05218] Updated weights for policy 0, policy_version 11332 (0.0009) -[2023-10-16 03:13:00,260][05218] Updated weights for policy 0, policy_version 11342 (0.0011) -[2023-10-16 03:13:00,641][05218] Updated weights for policy 0, policy_version 11352 (0.0009) -[2023-10-16 03:13:02,351][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 23199744. Throughput: 0: 1781.0, 1: 1772.2. Samples: 5809158. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) -[2023-10-16 03:13:02,352][03835] Avg episode reward: [(0, '3.540'), (1, '3.190')] -[2023-10-16 03:13:02,746][05219] Updated weights for policy 1, policy_version 11300 (0.0008) -[2023-10-16 03:13:03,125][05219] Updated weights for policy 1, policy_version 11310 (0.0010) -[2023-10-16 03:13:03,493][05219] Updated weights for policy 1, policy_version 11320 (0.0008) -[2023-10-16 03:13:04,371][05218] Updated weights for policy 0, policy_version 11362 (0.0008) -[2023-10-16 03:13:04,734][05218] Updated weights for policy 0, policy_version 11372 (0.0010) -[2023-10-16 03:13:05,107][05218] Updated weights for policy 0, policy_version 11382 (0.0011) -[2023-10-16 03:13:05,481][05218] Updated weights for policy 0, policy_version 11392 (0.0008) -[2023-10-16 03:13:07,223][05219] Updated weights for policy 1, policy_version 11330 (0.0011) -[2023-10-16 03:13:07,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 23265280. Throughput: 0: 1779.1, 1: 1802.0. Samples: 5831562. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-16 03:13:07,351][03835] Avg episode reward: [(0, '3.390'), (1, '3.180')] -[2023-10-16 03:13:07,635][05219] Updated weights for policy 1, policy_version 11340 (0.0009) -[2023-10-16 03:13:08,009][05219] Updated weights for policy 1, policy_version 11350 (0.0009) -[2023-10-16 03:13:08,368][05219] Updated weights for policy 1, policy_version 11360 (0.0007) -[2023-10-16 03:13:09,270][05218] Updated weights for policy 0, policy_version 11402 (0.0007) -[2023-10-16 03:13:09,658][05218] Updated weights for policy 0, policy_version 11412 (0.0009) -[2023-10-16 03:13:10,024][05218] Updated weights for policy 0, policy_version 11422 (0.0007) -[2023-10-16 03:13:12,077][05219] Updated weights for policy 1, policy_version 11370 (0.0007) -[2023-10-16 03:13:12,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 23330816. Throughput: 0: 1781.8, 1: 1772.7. Samples: 5841382. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-16 03:13:12,351][03835] Avg episode reward: [(0, '3.410'), (1, '3.080')] -[2023-10-16 03:13:12,451][05219] Updated weights for policy 1, policy_version 11380 (0.0007) -[2023-10-16 03:13:12,814][05219] Updated weights for policy 1, policy_version 11390 (0.0008) -[2023-10-16 03:13:13,856][05218] Updated weights for policy 0, policy_version 11432 (0.0009) -[2023-10-16 03:13:14,233][05218] Updated weights for policy 0, policy_version 11442 (0.0010) -[2023-10-16 03:13:14,617][05218] Updated weights for policy 0, policy_version 11452 (0.0011) -[2023-10-16 03:13:16,686][05219] Updated weights for policy 1, policy_version 11400 (0.0008) -[2023-10-16 03:13:17,054][05219] Updated weights for policy 1, policy_version 11410 (0.0007) -[2023-10-16 03:13:17,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 23396352. Throughput: 0: 1782.8, 1: 1792.9. Samples: 5863282. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-16 03:13:17,351][03835] Avg episode reward: [(0, '3.600'), (1, '3.240')] -[2023-10-16 03:13:17,422][05219] Updated weights for policy 1, policy_version 11420 (0.0007) -[2023-10-16 03:13:18,319][05218] Updated weights for policy 0, policy_version 11462 (0.0009) -[2023-10-16 03:13:18,691][05218] Updated weights for policy 0, policy_version 11472 (0.0009) -[2023-10-16 03:13:19,072][05218] Updated weights for policy 0, policy_version 11482 (0.0008) -[2023-10-16 03:13:21,081][05219] Updated weights for policy 1, policy_version 11430 (0.0007) -[2023-10-16 03:13:21,445][05219] Updated weights for policy 1, policy_version 11440 (0.0008) -[2023-10-16 03:13:21,812][05219] Updated weights for policy 1, policy_version 11450 (0.0009) -[2023-10-16 03:13:22,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 23494656. Throughput: 0: 1800.5, 1: 1769.4. Samples: 5884398. Policy #0 lag: (min: 31.0, avg: 47.8, max: 63.0) -[2023-10-16 03:13:22,351][03835] Avg episode reward: [(0, '3.750'), (1, '3.440')] -[2023-10-16 03:13:22,690][05218] Updated weights for policy 0, policy_version 11492 (0.0008) -[2023-10-16 03:13:23,059][05218] Updated weights for policy 0, policy_version 11502 (0.0008) -[2023-10-16 03:13:23,418][05218] Updated weights for policy 0, policy_version 11512 (0.0009) -[2023-10-16 03:13:25,628][05219] Updated weights for policy 1, policy_version 11460 (0.0008) -[2023-10-16 03:13:25,993][05219] Updated weights for policy 1, policy_version 11470 (0.0009) -[2023-10-16 03:13:26,364][05219] Updated weights for policy 1, policy_version 11480 (0.0008) -[2023-10-16 03:13:27,309][05218] Updated weights for policy 0, policy_version 11522 (0.0009) -[2023-10-16 03:13:27,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 23560192. Throughput: 0: 1782.8, 1: 1791.3. Samples: 5895584. Policy #0 lag: (min: 31.0, avg: 47.8, max: 63.0) -[2023-10-16 03:13:27,351][03835] Avg episode reward: [(0, '3.750'), (1, '3.420')] -[2023-10-16 03:13:27,684][05218] Updated weights for policy 0, policy_version 11532 (0.0009) -[2023-10-16 03:13:28,058][05218] Updated weights for policy 0, policy_version 11542 (0.0009) -[2023-10-16 03:13:28,431][05218] Updated weights for policy 0, policy_version 11552 (0.0008) -[2023-10-16 03:13:30,226][05219] Updated weights for policy 1, policy_version 11490 (0.0007) -[2023-10-16 03:13:30,604][05219] Updated weights for policy 1, policy_version 11500 (0.0009) -[2023-10-16 03:13:30,966][05219] Updated weights for policy 1, policy_version 11510 (0.0009) -[2023-10-16 03:13:31,346][05219] Updated weights for policy 1, policy_version 11520 (0.0011) -[2023-10-16 03:13:32,119][05218] Updated weights for policy 0, policy_version 11562 (0.0009) -[2023-10-16 03:13:32,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 23625728. Throughput: 0: 1790.1, 1: 1780.6. Samples: 5916774. Policy #0 lag: (min: 31.0, avg: 47.8, max: 63.0) -[2023-10-16 03:13:32,351][03835] Avg episode reward: [(0, '3.560'), (1, '3.590')] -[2023-10-16 03:13:32,501][05218] Updated weights for policy 0, policy_version 11572 (0.0010) -[2023-10-16 03:13:32,882][05218] Updated weights for policy 0, policy_version 11582 (0.0008) -[2023-10-16 03:13:35,096][05219] Updated weights for policy 1, policy_version 11530 (0.0007) -[2023-10-16 03:13:35,458][05219] Updated weights for policy 1, policy_version 11540 (0.0007) -[2023-10-16 03:13:35,827][05219] Updated weights for policy 1, policy_version 11550 (0.0008) -[2023-10-16 03:13:36,588][05218] Updated weights for policy 0, policy_version 11592 (0.0010) -[2023-10-16 03:13:36,965][05218] Updated weights for policy 0, policy_version 11602 (0.0008) -[2023-10-16 03:13:37,340][05218] Updated weights for policy 0, policy_version 11612 (0.0007) -[2023-10-16 03:13:37,351][03835] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 23691264. Throughput: 0: 1788.9, 1: 1776.9. Samples: 5937654. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:13:37,352][03835] Avg episode reward: [(0, '3.420'), (1, '3.480')] -[2023-10-16 03:13:37,361][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000011552_11829248.pth... -[2023-10-16 03:13:37,395][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000009888_10125312.pth -[2023-10-16 03:13:37,491][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000011616_11894784.pth... -[2023-10-16 03:13:37,520][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000009920_10158080.pth -[2023-10-16 03:13:39,649][05219] Updated weights for policy 1, policy_version 11560 (0.0007) -[2023-10-16 03:13:40,011][05219] Updated weights for policy 1, policy_version 11570 (0.0007) -[2023-10-16 03:13:40,364][05219] Updated weights for policy 1, policy_version 11580 (0.0008) -[2023-10-16 03:13:41,161][05218] Updated weights for policy 0, policy_version 11622 (0.0009) -[2023-10-16 03:13:41,541][05218] Updated weights for policy 0, policy_version 11632 (0.0007) -[2023-10-16 03:13:41,915][05218] Updated weights for policy 0, policy_version 11642 (0.0010) -[2023-10-16 03:13:42,350][03835] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 23789568. Throughput: 0: 1787.2, 1: 1789.0. Samples: 5949050. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:13:42,351][03835] Avg episode reward: [(0, '3.170'), (1, '3.320')] -[2023-10-16 03:13:44,079][05219] Updated weights for policy 1, policy_version 11590 (0.0009) -[2023-10-16 03:13:44,449][05219] Updated weights for policy 1, policy_version 11600 (0.0009) -[2023-10-16 03:13:44,817][05219] Updated weights for policy 1, policy_version 11610 (0.0008) -[2023-10-16 03:13:45,713][05218] Updated weights for policy 0, policy_version 11652 (0.0010) -[2023-10-16 03:13:46,091][05218] Updated weights for policy 0, policy_version 11662 (0.0010) -[2023-10-16 03:13:46,460][05218] Updated weights for policy 0, policy_version 11672 (0.0009) -[2023-10-16 03:13:47,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 23855104. Throughput: 0: 1797.6, 1: 1771.5. Samples: 5969766. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-16 03:13:47,351][03835] Avg episode reward: [(0, '3.220'), (1, '3.460')] -[2023-10-16 03:13:48,720][05219] Updated weights for policy 1, policy_version 11620 (0.0008) -[2023-10-16 03:13:49,085][05219] Updated weights for policy 1, policy_version 11630 (0.0009) -[2023-10-16 03:13:49,459][05219] Updated weights for policy 1, policy_version 11640 (0.0009) -[2023-10-16 03:13:50,281][05218] Updated weights for policy 0, policy_version 11682 (0.0008) -[2023-10-16 03:13:50,654][05218] Updated weights for policy 0, policy_version 11692 (0.0009) -[2023-10-16 03:13:51,028][05218] Updated weights for policy 0, policy_version 11702 (0.0008) -[2023-10-16 03:13:51,405][05218] Updated weights for policy 0, policy_version 11712 (0.0008) -[2023-10-16 03:13:52,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 23920640. Throughput: 0: 1779.0, 1: 1768.9. Samples: 5991216. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-16 03:13:52,351][03835] Avg episode reward: [(0, '3.220'), (1, '3.700')] -[2023-10-16 03:13:52,359][04891] Saving new best policy, reward=3.700! -[2023-10-16 03:13:53,365][05219] Updated weights for policy 1, policy_version 11650 (0.0009) -[2023-10-16 03:13:53,760][05219] Updated weights for policy 1, policy_version 11660 (0.0008) -[2023-10-16 03:13:54,123][05219] Updated weights for policy 1, policy_version 11670 (0.0008) -[2023-10-16 03:13:54,489][05219] Updated weights for policy 1, policy_version 11680 (0.0010) -[2023-10-16 03:13:55,224][05218] Updated weights for policy 0, policy_version 11722 (0.0010) -[2023-10-16 03:13:55,594][05218] Updated weights for policy 0, policy_version 11732 (0.0009) -[2023-10-16 03:13:55,968][05218] Updated weights for policy 0, policy_version 11742 (0.0010) -[2023-10-16 03:13:57,351][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 23986176. Throughput: 0: 1796.8, 1: 1765.7. Samples: 6001696. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-16 03:13:57,352][03835] Avg episode reward: [(0, '3.010'), (1, '3.840')] -[2023-10-16 03:13:57,353][04891] Saving new best policy, reward=3.840! -[2023-10-16 03:13:58,289][05219] Updated weights for policy 1, policy_version 11690 (0.0008) -[2023-10-16 03:13:58,659][05219] Updated weights for policy 1, policy_version 11700 (0.0009) -[2023-10-16 03:13:59,026][05219] Updated weights for policy 1, policy_version 11710 (0.0010) -[2023-10-16 03:13:59,737][05218] Updated weights for policy 0, policy_version 11752 (0.0010) -[2023-10-16 03:14:00,107][05218] Updated weights for policy 0, policy_version 11762 (0.0008) -[2023-10-16 03:14:00,486][05218] Updated weights for policy 0, policy_version 11772 (0.0009) -[2023-10-16 03:14:02,351][03835] Fps is (10 sec: 13106.7, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 24051712. Throughput: 0: 1778.3, 1: 1774.0. Samples: 6023138. Policy #0 lag: (min: 9.0, avg: 24.4, max: 41.0) -[2023-10-16 03:14:02,352][03835] Avg episode reward: [(0, '3.110'), (1, '3.620')] -[2023-10-16 03:14:02,827][05219] Updated weights for policy 1, policy_version 11720 (0.0008) -[2023-10-16 03:14:03,189][05219] Updated weights for policy 1, policy_version 11730 (0.0009) -[2023-10-16 03:14:03,559][05219] Updated weights for policy 1, policy_version 11740 (0.0010) -[2023-10-16 03:14:04,294][05218] Updated weights for policy 0, policy_version 11782 (0.0009) -[2023-10-16 03:14:04,668][05218] Updated weights for policy 0, policy_version 11792 (0.0009) -[2023-10-16 03:14:05,053][05218] Updated weights for policy 0, policy_version 11802 (0.0010) -[2023-10-16 03:14:07,287][05219] Updated weights for policy 1, policy_version 11750 (0.0007) -[2023-10-16 03:14:07,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 24117248. Throughput: 0: 1773.6, 1: 1801.7. Samples: 6045286. Policy #0 lag: (min: 9.0, avg: 24.4, max: 41.0) -[2023-10-16 03:14:07,352][03835] Avg episode reward: [(0, '3.410'), (1, '3.650')] -[2023-10-16 03:14:07,653][05219] Updated weights for policy 1, policy_version 11760 (0.0007) -[2023-10-16 03:14:08,012][05219] Updated weights for policy 1, policy_version 11770 (0.0010) -[2023-10-16 03:14:08,692][05218] Updated weights for policy 0, policy_version 11812 (0.0010) -[2023-10-16 03:14:09,063][05218] Updated weights for policy 0, policy_version 11822 (0.0009) -[2023-10-16 03:14:09,439][05218] Updated weights for policy 0, policy_version 11832 (0.0007) -[2023-10-16 03:14:11,731][05219] Updated weights for policy 1, policy_version 11780 (0.0010) -[2023-10-16 03:14:12,088][05219] Updated weights for policy 1, policy_version 11790 (0.0011) -[2023-10-16 03:14:12,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 24182784. Throughput: 0: 1777.4, 1: 1770.1. Samples: 6055222. Policy #0 lag: (min: 9.0, avg: 24.4, max: 41.0) -[2023-10-16 03:14:12,351][03835] Avg episode reward: [(0, '3.390'), (1, '3.430')] -[2023-10-16 03:14:12,448][05219] Updated weights for policy 1, policy_version 11800 (0.0008) -[2023-10-16 03:14:13,197][05218] Updated weights for policy 0, policy_version 11842 (0.0007) -[2023-10-16 03:14:13,563][05218] Updated weights for policy 0, policy_version 11852 (0.0011) -[2023-10-16 03:14:13,937][05218] Updated weights for policy 0, policy_version 11862 (0.0009) -[2023-10-16 03:14:14,320][05218] Updated weights for policy 0, policy_version 11872 (0.0010) -[2023-10-16 03:14:16,122][05219] Updated weights for policy 1, policy_version 11810 (0.0008) -[2023-10-16 03:14:16,484][05219] Updated weights for policy 1, policy_version 11820 (0.0008) -[2023-10-16 03:14:16,853][05219] Updated weights for policy 1, policy_version 11830 (0.0008) -[2023-10-16 03:14:17,213][05219] Updated weights for policy 1, policy_version 11840 (0.0009) -[2023-10-16 03:14:17,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 24281088. Throughput: 0: 1779.2, 1: 1790.1. Samples: 6077392. Policy #0 lag: (min: 26.0, avg: 41.8, max: 58.0) -[2023-10-16 03:14:17,352][03835] Avg episode reward: [(0, '3.370'), (1, '3.570')] -[2023-10-16 03:14:18,043][05218] Updated weights for policy 0, policy_version 11882 (0.0011) -[2023-10-16 03:14:18,431][05218] Updated weights for policy 0, policy_version 11892 (0.0009) -[2023-10-16 03:14:18,809][05218] Updated weights for policy 0, policy_version 11902 (0.0008) -[2023-10-16 03:14:21,023][05219] Updated weights for policy 1, policy_version 11850 (0.0007) -[2023-10-16 03:14:21,395][05219] Updated weights for policy 1, policy_version 11860 (0.0008) -[2023-10-16 03:14:21,769][05219] Updated weights for policy 1, policy_version 11870 (0.0011) -[2023-10-16 03:14:22,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 24346624. Throughput: 0: 1808.7, 1: 1770.0. Samples: 6098692. Policy #0 lag: (min: 26.0, avg: 41.8, max: 58.0) -[2023-10-16 03:14:22,351][03835] Avg episode reward: [(0, '3.230'), (1, '3.400')] -[2023-10-16 03:14:22,668][05218] Updated weights for policy 0, policy_version 11912 (0.0009) -[2023-10-16 03:14:23,050][05218] Updated weights for policy 0, policy_version 11922 (0.0009) -[2023-10-16 03:14:23,416][05218] Updated weights for policy 0, policy_version 11932 (0.0010) -[2023-10-16 03:14:25,657][05219] Updated weights for policy 1, policy_version 11880 (0.0010) -[2023-10-16 03:14:26,023][05219] Updated weights for policy 1, policy_version 11890 (0.0010) -[2023-10-16 03:14:26,391][05219] Updated weights for policy 1, policy_version 11900 (0.0009) -[2023-10-16 03:14:27,117][05218] Updated weights for policy 0, policy_version 11942 (0.0010) -[2023-10-16 03:14:27,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 24412160. Throughput: 0: 1779.1, 1: 1793.9. Samples: 6109834. Policy #0 lag: (min: 26.0, avg: 41.8, max: 58.0) -[2023-10-16 03:14:27,351][03835] Avg episode reward: [(0, '3.240'), (1, '3.640')] -[2023-10-16 03:14:27,489][05218] Updated weights for policy 0, policy_version 11952 (0.0009) -[2023-10-16 03:14:27,870][05218] Updated weights for policy 0, policy_version 11962 (0.0009) -[2023-10-16 03:14:30,324][05219] Updated weights for policy 1, policy_version 11910 (0.0008) -[2023-10-16 03:14:30,698][05219] Updated weights for policy 1, policy_version 11920 (0.0008) -[2023-10-16 03:14:31,060][05219] Updated weights for policy 1, policy_version 11930 (0.0008) -[2023-10-16 03:14:31,602][05218] Updated weights for policy 0, policy_version 11972 (0.0008) -[2023-10-16 03:14:31,977][05218] Updated weights for policy 0, policy_version 11982 (0.0008) -[2023-10-16 03:14:32,342][05218] Updated weights for policy 0, policy_version 11992 (0.0007) -[2023-10-16 03:14:32,351][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 24477696. Throughput: 0: 1800.5, 1: 1779.7. Samples: 6130878. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-16 03:14:32,352][03835] Avg episode reward: [(0, '3.460'), (1, '3.810')] -[2023-10-16 03:14:34,804][05219] Updated weights for policy 1, policy_version 11940 (0.0009) -[2023-10-16 03:14:35,173][05219] Updated weights for policy 1, policy_version 11950 (0.0007) -[2023-10-16 03:14:35,532][05219] Updated weights for policy 1, policy_version 11960 (0.0008) -[2023-10-16 03:14:36,072][05218] Updated weights for policy 0, policy_version 12002 (0.0008) -[2023-10-16 03:14:36,443][05218] Updated weights for policy 0, policy_version 12012 (0.0008) -[2023-10-16 03:14:36,825][05218] Updated weights for policy 0, policy_version 12022 (0.0008) -[2023-10-16 03:14:37,195][05218] Updated weights for policy 0, policy_version 12032 (0.0011) -[2023-10-16 03:14:37,350][03835] Fps is (10 sec: 16383.4, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 24576000. Throughput: 0: 1782.0, 1: 1777.1. Samples: 6151374. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-16 03:14:37,352][03835] Avg episode reward: [(0, '3.570'), (1, '3.870')] -[2023-10-16 03:14:37,364][04891] Saving new best policy, reward=3.870! -[2023-10-16 03:14:39,234][05219] Updated weights for policy 1, policy_version 11970 (0.0007) -[2023-10-16 03:14:39,634][05219] Updated weights for policy 1, policy_version 11980 (0.0007) -[2023-10-16 03:14:40,002][05219] Updated weights for policy 1, policy_version 11990 (0.0007) -[2023-10-16 03:14:40,375][05219] Updated weights for policy 1, policy_version 12000 (0.0009) -[2023-10-16 03:14:40,928][05218] Updated weights for policy 0, policy_version 12042 (0.0010) -[2023-10-16 03:14:41,306][05218] Updated weights for policy 0, policy_version 12052 (0.0010) -[2023-10-16 03:14:41,672][05218] Updated weights for policy 0, policy_version 12062 (0.0010) -[2023-10-16 03:14:42,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 24641536. Throughput: 0: 1799.9, 1: 1786.3. Samples: 6163074. Policy #0 lag: (min: 13.0, avg: 20.6, max: 45.0) -[2023-10-16 03:14:42,351][03835] Avg episode reward: [(0, '3.450'), (1, '3.650')] -[2023-10-16 03:14:44,075][05219] Updated weights for policy 1, policy_version 12010 (0.0007) -[2023-10-16 03:14:44,442][05219] Updated weights for policy 1, policy_version 12020 (0.0007) -[2023-10-16 03:14:44,805][05219] Updated weights for policy 1, policy_version 12030 (0.0007) -[2023-10-16 03:14:45,514][05218] Updated weights for policy 0, policy_version 12072 (0.0010) -[2023-10-16 03:14:45,892][05218] Updated weights for policy 0, policy_version 12082 (0.0007) -[2023-10-16 03:14:46,274][05218] Updated weights for policy 0, policy_version 12092 (0.0008) -[2023-10-16 03:14:47,351][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 24707072. Throughput: 0: 1788.8, 1: 1783.3. Samples: 6183882. Policy #0 lag: (min: 13.0, avg: 20.6, max: 45.0) -[2023-10-16 03:14:47,352][03835] Avg episode reward: [(0, '3.210'), (1, '3.250')] -[2023-10-16 03:14:48,488][05219] Updated weights for policy 1, policy_version 12040 (0.0008) -[2023-10-16 03:14:48,855][05219] Updated weights for policy 1, policy_version 12050 (0.0010) -[2023-10-16 03:14:49,212][05219] Updated weights for policy 1, policy_version 12060 (0.0007) -[2023-10-16 03:14:50,068][05218] Updated weights for policy 0, policy_version 12102 (0.0007) -[2023-10-16 03:14:50,434][05218] Updated weights for policy 0, policy_version 12112 (0.0008) -[2023-10-16 03:14:50,815][05218] Updated weights for policy 0, policy_version 12122 (0.0009) -[2023-10-16 03:14:52,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 24772608. Throughput: 0: 1785.1, 1: 1795.6. Samples: 6206418. Policy #0 lag: (min: 13.0, avg: 20.6, max: 45.0) -[2023-10-16 03:14:52,351][03835] Avg episode reward: [(0, '3.360'), (1, '3.290')] -[2023-10-16 03:14:52,880][05219] Updated weights for policy 1, policy_version 12070 (0.0007) -[2023-10-16 03:14:53,249][05219] Updated weights for policy 1, policy_version 12080 (0.0009) -[2023-10-16 03:14:53,624][05219] Updated weights for policy 1, policy_version 12090 (0.0009) -[2023-10-16 03:14:54,558][05218] Updated weights for policy 0, policy_version 12132 (0.0009) -[2023-10-16 03:14:54,935][05218] Updated weights for policy 0, policy_version 12142 (0.0009) -[2023-10-16 03:14:55,319][05218] Updated weights for policy 0, policy_version 12152 (0.0008) -[2023-10-16 03:14:57,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.6, 300 sec: 14329.1). Total num frames: 24838144. Throughput: 0: 1791.5, 1: 1793.8. Samples: 6216560. Policy #0 lag: (min: 22.0, avg: 22.0, max: 23.0) -[2023-10-16 03:14:57,351][03835] Avg episode reward: [(0, '3.540'), (1, '3.160')] -[2023-10-16 03:14:57,356][05219] Updated weights for policy 1, policy_version 12100 (0.0008) -[2023-10-16 03:14:57,720][05219] Updated weights for policy 1, policy_version 12110 (0.0009) -[2023-10-16 03:14:58,091][05219] Updated weights for policy 1, policy_version 12120 (0.0010) -[2023-10-16 03:14:58,972][05218] Updated weights for policy 0, policy_version 12162 (0.0009) -[2023-10-16 03:14:59,345][05218] Updated weights for policy 0, policy_version 12172 (0.0009) -[2023-10-16 03:14:59,726][05218] Updated weights for policy 0, policy_version 12182 (0.0009) -[2023-10-16 03:15:00,093][05218] Updated weights for policy 0, policy_version 12192 (0.0008) -[2023-10-16 03:15:01,605][05219] Updated weights for policy 1, policy_version 12130 (0.0008) -[2023-10-16 03:15:01,974][05219] Updated weights for policy 1, policy_version 12140 (0.0009) -[2023-10-16 03:15:02,334][05219] Updated weights for policy 1, policy_version 12150 (0.0007) -[2023-10-16 03:15:02,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 24903680. Throughput: 0: 1784.0, 1: 1802.4. Samples: 6238782. Policy #0 lag: (min: 22.0, avg: 22.0, max: 23.0) -[2023-10-16 03:15:02,351][03835] Avg episode reward: [(0, '3.490'), (1, '3.150')] -[2023-10-16 03:15:02,697][05219] Updated weights for policy 1, policy_version 12160 (0.0007) -[2023-10-16 03:15:03,812][05218] Updated weights for policy 0, policy_version 12202 (0.0007) -[2023-10-16 03:15:04,191][05218] Updated weights for policy 0, policy_version 12212 (0.0009) -[2023-10-16 03:15:04,569][05218] Updated weights for policy 0, policy_version 12222 (0.0007) -[2023-10-16 03:15:06,524][05219] Updated weights for policy 1, policy_version 12170 (0.0010) -[2023-10-16 03:15:06,879][05219] Updated weights for policy 1, policy_version 12180 (0.0009) -[2023-10-16 03:15:07,242][05219] Updated weights for policy 1, policy_version 12190 (0.0008) -[2023-10-16 03:15:07,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 25001984. Throughput: 0: 1783.5, 1: 1805.7. Samples: 6260206. Policy #0 lag: (min: 22.0, avg: 22.0, max: 23.0) -[2023-10-16 03:15:07,351][03835] Avg episode reward: [(0, '3.350'), (1, '3.140')] -[2023-10-16 03:15:08,394][05218] Updated weights for policy 0, policy_version 12232 (0.0009) -[2023-10-16 03:15:08,779][05218] Updated weights for policy 0, policy_version 12242 (0.0007) -[2023-10-16 03:15:09,157][05218] Updated weights for policy 0, policy_version 12252 (0.0009) -[2023-10-16 03:15:11,069][05219] Updated weights for policy 1, policy_version 12200 (0.0009) -[2023-10-16 03:15:11,442][05219] Updated weights for policy 1, policy_version 12210 (0.0011) -[2023-10-16 03:15:11,803][05219] Updated weights for policy 1, policy_version 12220 (0.0007) -[2023-10-16 03:15:12,351][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 25067520. Throughput: 0: 1781.3, 1: 1797.8. Samples: 6270898. Policy #0 lag: (min: 13.0, avg: 38.0, max: 40.0) -[2023-10-16 03:15:12,352][03835] Avg episode reward: [(0, '3.320'), (1, '3.370')] -[2023-10-16 03:15:12,980][05218] Updated weights for policy 0, policy_version 12262 (0.0008) -[2023-10-16 03:15:13,359][05218] Updated weights for policy 0, policy_version 12272 (0.0009) -[2023-10-16 03:15:13,745][05218] Updated weights for policy 0, policy_version 12282 (0.0010) -[2023-10-16 03:15:15,425][05219] Updated weights for policy 1, policy_version 12230 (0.0007) -[2023-10-16 03:15:15,798][05219] Updated weights for policy 1, policy_version 12240 (0.0011) -[2023-10-16 03:15:16,168][05219] Updated weights for policy 1, policy_version 12250 (0.0011) -[2023-10-16 03:15:17,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 25133056. Throughput: 0: 1775.9, 1: 1803.0. Samples: 6291928. Policy #0 lag: (min: 13.0, avg: 38.0, max: 40.0) -[2023-10-16 03:15:17,351][03835] Avg episode reward: [(0, '3.280'), (1, '3.300')] -[2023-10-16 03:15:17,574][05218] Updated weights for policy 0, policy_version 12292 (0.0008) -[2023-10-16 03:15:17,952][05218] Updated weights for policy 0, policy_version 12302 (0.0007) -[2023-10-16 03:15:18,327][05218] Updated weights for policy 0, policy_version 12312 (0.0007) -[2023-10-16 03:15:20,003][05219] Updated weights for policy 1, policy_version 12260 (0.0009) -[2023-10-16 03:15:20,359][05219] Updated weights for policy 1, policy_version 12270 (0.0009) -[2023-10-16 03:15:20,721][05219] Updated weights for policy 1, policy_version 12280 (0.0009) -[2023-10-16 03:15:21,985][05218] Updated weights for policy 0, policy_version 12322 (0.0007) -[2023-10-16 03:15:22,350][03835] Fps is (10 sec: 13107.8, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 25198592. Throughput: 0: 1801.1, 1: 1799.3. Samples: 6313390. Policy #0 lag: (min: 13.0, avg: 38.0, max: 40.0) -[2023-10-16 03:15:22,351][03835] Avg episode reward: [(0, '3.300'), (1, '3.280')] -[2023-10-16 03:15:22,351][05218] Updated weights for policy 0, policy_version 12332 (0.0008) -[2023-10-16 03:15:22,726][05218] Updated weights for policy 0, policy_version 12342 (0.0007) -[2023-10-16 03:15:23,103][05218] Updated weights for policy 0, policy_version 12352 (0.0007) -[2023-10-16 03:15:24,681][05219] Updated weights for policy 1, policy_version 12290 (0.0009) -[2023-10-16 03:15:25,089][05219] Updated weights for policy 1, policy_version 12300 (0.0008) -[2023-10-16 03:15:25,454][05219] Updated weights for policy 1, policy_version 12310 (0.0008) -[2023-10-16 03:15:25,814][05219] Updated weights for policy 1, policy_version 12320 (0.0008) -[2023-10-16 03:15:26,748][05218] Updated weights for policy 0, policy_version 12362 (0.0008) -[2023-10-16 03:15:27,129][05218] Updated weights for policy 0, policy_version 12372 (0.0008) -[2023-10-16 03:15:27,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 25264128. Throughput: 0: 1779.6, 1: 1810.7. Samples: 6324634. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:15:27,351][03835] Avg episode reward: [(0, '3.390'), (1, '3.430')] -[2023-10-16 03:15:27,495][05218] Updated weights for policy 0, policy_version 12382 (0.0007) -[2023-10-16 03:15:29,485][05219] Updated weights for policy 1, policy_version 12330 (0.0009) -[2023-10-16 03:15:29,845][05219] Updated weights for policy 1, policy_version 12340 (0.0009) -[2023-10-16 03:15:30,209][05219] Updated weights for policy 1, policy_version 12350 (0.0009) -[2023-10-16 03:15:31,202][05218] Updated weights for policy 0, policy_version 12392 (0.0009) -[2023-10-16 03:15:31,587][05218] Updated weights for policy 0, policy_version 12402 (0.0008) -[2023-10-16 03:15:31,959][05218] Updated weights for policy 0, policy_version 12412 (0.0007) -[2023-10-16 03:15:32,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 25362432. Throughput: 0: 1803.4, 1: 1793.2. Samples: 6345728. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:15:32,351][03835] Avg episode reward: [(0, '3.320'), (1, '3.630')] -[2023-10-16 03:15:33,867][05219] Updated weights for policy 1, policy_version 12360 (0.0008) -[2023-10-16 03:15:34,235][05219] Updated weights for policy 1, policy_version 12370 (0.0008) -[2023-10-16 03:15:34,606][05219] Updated weights for policy 1, policy_version 12380 (0.0008) -[2023-10-16 03:15:35,567][05218] Updated weights for policy 0, policy_version 12422 (0.0008) -[2023-10-16 03:15:35,943][05218] Updated weights for policy 0, policy_version 12432 (0.0010) -[2023-10-16 03:15:36,312][05218] Updated weights for policy 0, policy_version 12442 (0.0007) -[2023-10-16 03:15:37,351][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 25427968. Throughput: 0: 1789.3, 1: 1790.2. Samples: 6367494. Policy #0 lag: (min: 8.0, avg: 29.1, max: 40.0) -[2023-10-16 03:15:37,352][03835] Avg episode reward: [(0, '3.170'), (1, '3.680')] -[2023-10-16 03:15:37,364][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000012384_12681216.pth... -[2023-10-16 03:15:37,364][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000012448_12746752.pth... -[2023-10-16 03:15:37,394][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000010720_10977280.pth -[2023-10-16 03:15:37,405][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000010752_11010048.pth -[2023-10-16 03:15:38,221][05219] Updated weights for policy 1, policy_version 12390 (0.0009) -[2023-10-16 03:15:38,587][05219] Updated weights for policy 1, policy_version 12400 (0.0009) -[2023-10-16 03:15:38,957][05219] Updated weights for policy 1, policy_version 12410 (0.0008) -[2023-10-16 03:15:40,200][05218] Updated weights for policy 0, policy_version 12452 (0.0007) -[2023-10-16 03:15:40,574][05218] Updated weights for policy 0, policy_version 12462 (0.0008) -[2023-10-16 03:15:40,944][05218] Updated weights for policy 0, policy_version 12472 (0.0009) -[2023-10-16 03:15:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 25493504. Throughput: 0: 1805.1, 1: 1788.3. Samples: 6378266. Policy #0 lag: (min: 8.0, avg: 29.1, max: 40.0) -[2023-10-16 03:15:42,351][03835] Avg episode reward: [(0, '3.070'), (1, '3.710')] -[2023-10-16 03:15:42,853][05219] Updated weights for policy 1, policy_version 12420 (0.0008) -[2023-10-16 03:15:43,214][05219] Updated weights for policy 1, policy_version 12430 (0.0008) -[2023-10-16 03:15:43,581][05219] Updated weights for policy 1, policy_version 12440 (0.0009) -[2023-10-16 03:15:44,761][05218] Updated weights for policy 0, policy_version 12482 (0.0008) -[2023-10-16 03:15:45,141][05218] Updated weights for policy 0, policy_version 12492 (0.0007) -[2023-10-16 03:15:45,516][05218] Updated weights for policy 0, policy_version 12502 (0.0008) -[2023-10-16 03:15:45,892][05218] Updated weights for policy 0, policy_version 12512 (0.0008) -[2023-10-16 03:15:47,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 25559040. Throughput: 0: 1787.2, 1: 1782.3. Samples: 6399406. Policy #0 lag: (min: 8.0, avg: 29.1, max: 40.0) -[2023-10-16 03:15:47,351][03835] Avg episode reward: [(0, '3.090'), (1, '3.480')] -[2023-10-16 03:15:47,398][05219] Updated weights for policy 1, policy_version 12450 (0.0010) -[2023-10-16 03:15:47,758][05219] Updated weights for policy 1, policy_version 12460 (0.0009) -[2023-10-16 03:15:48,122][05219] Updated weights for policy 1, policy_version 12470 (0.0009) -[2023-10-16 03:15:48,495][05219] Updated weights for policy 1, policy_version 12480 (0.0009) -[2023-10-16 03:15:49,552][05218] Updated weights for policy 0, policy_version 12522 (0.0008) -[2023-10-16 03:15:49,920][05218] Updated weights for policy 0, policy_version 12532 (0.0008) -[2023-10-16 03:15:50,294][05218] Updated weights for policy 0, policy_version 12542 (0.0010) -[2023-10-16 03:15:52,252][05219] Updated weights for policy 1, policy_version 12490 (0.0007) -[2023-10-16 03:15:52,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 25624576. Throughput: 0: 1786.1, 1: 1798.0. Samples: 6421490. Policy #0 lag: (min: 17.0, avg: 37.9, max: 49.0) -[2023-10-16 03:15:52,351][03835] Avg episode reward: [(0, '3.170'), (1, '3.440')] -[2023-10-16 03:15:52,618][05219] Updated weights for policy 1, policy_version 12500 (0.0007) -[2023-10-16 03:15:52,974][05219] Updated weights for policy 1, policy_version 12510 (0.0007) -[2023-10-16 03:15:54,102][05218] Updated weights for policy 0, policy_version 12552 (0.0010) -[2023-10-16 03:15:54,483][05218] Updated weights for policy 0, policy_version 12562 (0.0010) -[2023-10-16 03:15:54,860][05218] Updated weights for policy 0, policy_version 12572 (0.0008) -[2023-10-16 03:15:56,996][05219] Updated weights for policy 1, policy_version 12520 (0.0008) -[2023-10-16 03:15:57,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 25690112. Throughput: 0: 1789.3, 1: 1778.1. Samples: 6431430. Policy #0 lag: (min: 17.0, avg: 37.9, max: 49.0) -[2023-10-16 03:15:57,351][03835] Avg episode reward: [(0, '3.420'), (1, '3.380')] -[2023-10-16 03:15:57,365][05219] Updated weights for policy 1, policy_version 12530 (0.0009) -[2023-10-16 03:15:57,739][05219] Updated weights for policy 1, policy_version 12540 (0.0011) -[2023-10-16 03:15:58,554][05218] Updated weights for policy 0, policy_version 12582 (0.0011) -[2023-10-16 03:15:58,931][05218] Updated weights for policy 0, policy_version 12592 (0.0008) -[2023-10-16 03:15:59,299][05218] Updated weights for policy 0, policy_version 12602 (0.0010) -[2023-10-16 03:16:01,672][05219] Updated weights for policy 1, policy_version 12550 (0.0009) -[2023-10-16 03:16:02,037][05219] Updated weights for policy 1, policy_version 12560 (0.0008) -[2023-10-16 03:16:02,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 25755648. Throughput: 0: 1792.7, 1: 1798.5. Samples: 6453534. Policy #0 lag: (min: 17.0, avg: 37.9, max: 49.0) -[2023-10-16 03:16:02,351][03835] Avg episode reward: [(0, '3.580'), (1, '3.600')] -[2023-10-16 03:16:02,402][05219] Updated weights for policy 1, policy_version 12570 (0.0007) -[2023-10-16 03:16:03,019][05218] Updated weights for policy 0, policy_version 12612 (0.0010) -[2023-10-16 03:16:03,393][05218] Updated weights for policy 0, policy_version 12622 (0.0009) -[2023-10-16 03:16:03,770][05218] Updated weights for policy 0, policy_version 12632 (0.0009) -[2023-10-16 03:16:06,092][05219] Updated weights for policy 1, policy_version 12580 (0.0007) -[2023-10-16 03:16:06,462][05219] Updated weights for policy 1, policy_version 12590 (0.0009) -[2023-10-16 03:16:06,835][05219] Updated weights for policy 1, policy_version 12600 (0.0008) -[2023-10-16 03:16:07,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 25853952. Throughput: 0: 1802.8, 1: 1777.5. Samples: 6474506. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) -[2023-10-16 03:16:07,351][03835] Avg episode reward: [(0, '3.560'), (1, '3.560')] -[2023-10-16 03:16:07,625][05218] Updated weights for policy 0, policy_version 12642 (0.0010) -[2023-10-16 03:16:08,002][05218] Updated weights for policy 0, policy_version 12652 (0.0010) -[2023-10-16 03:16:08,373][05218] Updated weights for policy 0, policy_version 12662 (0.0009) -[2023-10-16 03:16:08,758][05218] Updated weights for policy 0, policy_version 12672 (0.0010) -[2023-10-16 03:16:10,704][05219] Updated weights for policy 1, policy_version 12610 (0.0008) -[2023-10-16 03:16:11,113][05219] Updated weights for policy 1, policy_version 12620 (0.0008) -[2023-10-16 03:16:11,490][05219] Updated weights for policy 1, policy_version 12630 (0.0007) -[2023-10-16 03:16:11,849][05219] Updated weights for policy 1, policy_version 12640 (0.0010) -[2023-10-16 03:16:12,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 25919488. Throughput: 0: 1786.8, 1: 1791.1. Samples: 6485642. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) -[2023-10-16 03:16:12,351][03835] Avg episode reward: [(0, '3.450'), (1, '3.400')] -[2023-10-16 03:16:12,479][05218] Updated weights for policy 0, policy_version 12682 (0.0009) -[2023-10-16 03:16:12,857][05218] Updated weights for policy 0, policy_version 12692 (0.0009) -[2023-10-16 03:16:13,223][05218] Updated weights for policy 0, policy_version 12702 (0.0008) -[2023-10-16 03:16:15,617][05219] Updated weights for policy 1, policy_version 12650 (0.0007) -[2023-10-16 03:16:15,979][05219] Updated weights for policy 1, policy_version 12660 (0.0008) -[2023-10-16 03:16:16,355][05219] Updated weights for policy 1, policy_version 12670 (0.0007) -[2023-10-16 03:16:16,961][05218] Updated weights for policy 0, policy_version 12712 (0.0009) -[2023-10-16 03:16:17,337][05218] Updated weights for policy 0, policy_version 12722 (0.0009) -[2023-10-16 03:16:17,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 25985024. Throughput: 0: 1795.2, 1: 1779.6. Samples: 6506592. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) -[2023-10-16 03:16:17,351][03835] Avg episode reward: [(0, '3.630'), (1, '3.260')] -[2023-10-16 03:16:17,722][05218] Updated weights for policy 0, policy_version 12732 (0.0007) -[2023-10-16 03:16:20,244][05219] Updated weights for policy 1, policy_version 12680 (0.0007) -[2023-10-16 03:16:20,604][05219] Updated weights for policy 1, policy_version 12690 (0.0007) -[2023-10-16 03:16:20,973][05219] Updated weights for policy 1, policy_version 12700 (0.0010) -[2023-10-16 03:16:21,481][05218] Updated weights for policy 0, policy_version 12742 (0.0009) -[2023-10-16 03:16:21,858][05218] Updated weights for policy 0, policy_version 12752 (0.0008) -[2023-10-16 03:16:22,243][05218] Updated weights for policy 0, policy_version 12762 (0.0011) -[2023-10-16 03:16:22,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 26050560. Throughput: 0: 1787.4, 1: 1764.9. Samples: 6527350. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-10-16 03:16:22,351][03835] Avg episode reward: [(0, '3.650'), (1, '3.260')] -[2023-10-16 03:16:24,701][05219] Updated weights for policy 1, policy_version 12710 (0.0008) -[2023-10-16 03:16:25,065][05219] Updated weights for policy 1, policy_version 12720 (0.0009) -[2023-10-16 03:16:25,437][05219] Updated weights for policy 1, policy_version 12730 (0.0007) -[2023-10-16 03:16:25,944][05218] Updated weights for policy 0, policy_version 12772 (0.0010) -[2023-10-16 03:16:26,319][05218] Updated weights for policy 0, policy_version 12782 (0.0009) -[2023-10-16 03:16:26,703][05218] Updated weights for policy 0, policy_version 12792 (0.0009) -[2023-10-16 03:16:27,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 26148864. Throughput: 0: 1794.3, 1: 1783.6. Samples: 6539268. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-10-16 03:16:27,352][03835] Avg episode reward: [(0, '3.570'), (1, '3.360')] -[2023-10-16 03:16:29,272][05219] Updated weights for policy 1, policy_version 12740 (0.0007) -[2023-10-16 03:16:29,639][05219] Updated weights for policy 1, policy_version 12750 (0.0008) -[2023-10-16 03:16:30,002][05219] Updated weights for policy 1, policy_version 12760 (0.0008) -[2023-10-16 03:16:30,319][05218] Updated weights for policy 0, policy_version 12802 (0.0009) -[2023-10-16 03:16:30,687][05218] Updated weights for policy 0, policy_version 12812 (0.0009) -[2023-10-16 03:16:31,066][05218] Updated weights for policy 0, policy_version 12822 (0.0009) -[2023-10-16 03:16:31,443][05218] Updated weights for policy 0, policy_version 12832 (0.0010) -[2023-10-16 03:16:32,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 26214400. Throughput: 0: 1794.5, 1: 1771.6. Samples: 6559876. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:16:32,351][03835] Avg episode reward: [(0, '3.640'), (1, '3.450')] -[2023-10-16 03:16:33,682][05219] Updated weights for policy 1, policy_version 12770 (0.0008) -[2023-10-16 03:16:34,047][05219] Updated weights for policy 1, policy_version 12780 (0.0009) -[2023-10-16 03:16:34,406][05219] Updated weights for policy 1, policy_version 12790 (0.0009) -[2023-10-16 03:16:34,773][05219] Updated weights for policy 1, policy_version 12800 (0.0009) -[2023-10-16 03:16:35,098][05218] Updated weights for policy 0, policy_version 12842 (0.0010) -[2023-10-16 03:16:35,460][05218] Updated weights for policy 0, policy_version 12852 (0.0009) -[2023-10-16 03:16:35,838][05218] Updated weights for policy 0, policy_version 12862 (0.0010) -[2023-10-16 03:16:37,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 26279936. Throughput: 0: 1785.5, 1: 1781.9. Samples: 6582022. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:16:37,351][03835] Avg episode reward: [(0, '3.670'), (1, '3.400')] -[2023-10-16 03:16:38,443][05219] Updated weights for policy 1, policy_version 12810 (0.0010) -[2023-10-16 03:16:38,807][05219] Updated weights for policy 1, policy_version 12820 (0.0010) -[2023-10-16 03:16:39,179][05219] Updated weights for policy 1, policy_version 12830 (0.0010) -[2023-10-16 03:16:39,731][05218] Updated weights for policy 0, policy_version 12872 (0.0010) -[2023-10-16 03:16:40,100][05218] Updated weights for policy 0, policy_version 12882 (0.0009) -[2023-10-16 03:16:40,475][05218] Updated weights for policy 0, policy_version 12892 (0.0007) -[2023-10-16 03:16:42,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 26345472. Throughput: 0: 1793.9, 1: 1780.1. Samples: 6592258. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:16:42,351][03835] Avg episode reward: [(0, '3.770'), (1, '3.420')] -[2023-10-16 03:16:42,940][05219] Updated weights for policy 1, policy_version 12840 (0.0008) -[2023-10-16 03:16:43,300][05219] Updated weights for policy 1, policy_version 12850 (0.0008) -[2023-10-16 03:16:43,665][05219] Updated weights for policy 1, policy_version 12860 (0.0007) -[2023-10-16 03:16:44,251][05218] Updated weights for policy 0, policy_version 12902 (0.0009) -[2023-10-16 03:16:44,630][05218] Updated weights for policy 0, policy_version 12912 (0.0007) -[2023-10-16 03:16:45,015][05218] Updated weights for policy 0, policy_version 12922 (0.0009) -[2023-10-16 03:16:47,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 26411008. Throughput: 0: 1786.0, 1: 1782.8. Samples: 6614132. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:16:47,351][03835] Avg episode reward: [(0, '3.660'), (1, '3.690')] -[2023-10-16 03:16:47,448][05219] Updated weights for policy 1, policy_version 12870 (0.0007) -[2023-10-16 03:16:47,825][05219] Updated weights for policy 1, policy_version 12880 (0.0009) -[2023-10-16 03:16:48,184][05219] Updated weights for policy 1, policy_version 12890 (0.0008) -[2023-10-16 03:16:48,771][05218] Updated weights for policy 0, policy_version 12932 (0.0009) -[2023-10-16 03:16:49,141][05218] Updated weights for policy 0, policy_version 12942 (0.0010) -[2023-10-16 03:16:49,517][05218] Updated weights for policy 0, policy_version 12952 (0.0008) -[2023-10-16 03:16:52,011][05219] Updated weights for policy 1, policy_version 12900 (0.0009) -[2023-10-16 03:16:52,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 26476544. Throughput: 0: 1782.4, 1: 1798.9. Samples: 6635660. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:16:52,351][03835] Avg episode reward: [(0, '3.650'), (1, '3.720')] -[2023-10-16 03:16:52,376][05219] Updated weights for policy 1, policy_version 12910 (0.0010) -[2023-10-16 03:16:52,736][05219] Updated weights for policy 1, policy_version 12920 (0.0007) -[2023-10-16 03:16:53,209][05218] Updated weights for policy 0, policy_version 12962 (0.0009) -[2023-10-16 03:16:53,583][05218] Updated weights for policy 0, policy_version 12972 (0.0007) -[2023-10-16 03:16:53,959][05218] Updated weights for policy 0, policy_version 12982 (0.0007) -[2023-10-16 03:16:54,333][05218] Updated weights for policy 0, policy_version 12992 (0.0008) -[2023-10-16 03:16:56,556][05219] Updated weights for policy 1, policy_version 12930 (0.0008) -[2023-10-16 03:16:56,973][05219] Updated weights for policy 1, policy_version 12940 (0.0007) -[2023-10-16 03:16:57,335][05219] Updated weights for policy 1, policy_version 12950 (0.0008) -[2023-10-16 03:16:57,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 26542080. Throughput: 0: 1783.6, 1: 1776.5. Samples: 6645848. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:16:57,351][03835] Avg episode reward: [(0, '3.690'), (1, '3.610')] -[2023-10-16 03:16:57,706][05219] Updated weights for policy 1, policy_version 12960 (0.0007) -[2023-10-16 03:16:58,203][05218] Updated weights for policy 0, policy_version 13002 (0.0007) -[2023-10-16 03:16:58,579][05218] Updated weights for policy 0, policy_version 13012 (0.0008) -[2023-10-16 03:16:58,945][05218] Updated weights for policy 0, policy_version 13022 (0.0009) -[2023-10-16 03:17:01,349][05219] Updated weights for policy 1, policy_version 12970 (0.0008) -[2023-10-16 03:17:01,724][05219] Updated weights for policy 1, policy_version 12980 (0.0007) -[2023-10-16 03:17:02,090][05219] Updated weights for policy 1, policy_version 12990 (0.0007) -[2023-10-16 03:17:02,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 26640384. Throughput: 0: 1779.1, 1: 1800.4. Samples: 6667670. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-16 03:17:02,351][03835] Avg episode reward: [(0, '3.840'), (1, '3.630')] -[2023-10-16 03:17:02,771][05218] Updated weights for policy 0, policy_version 13032 (0.0009) -[2023-10-16 03:17:03,144][05218] Updated weights for policy 0, policy_version 13042 (0.0009) -[2023-10-16 03:17:03,519][05218] Updated weights for policy 0, policy_version 13052 (0.0008) -[2023-10-16 03:17:05,883][05219] Updated weights for policy 1, policy_version 13000 (0.0009) -[2023-10-16 03:17:06,248][05219] Updated weights for policy 1, policy_version 13010 (0.0009) -[2023-10-16 03:17:06,618][05219] Updated weights for policy 1, policy_version 13020 (0.0008) -[2023-10-16 03:17:07,228][05218] Updated weights for policy 0, policy_version 13062 (0.0009) -[2023-10-16 03:17:07,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 26705920. Throughput: 0: 1798.2, 1: 1788.8. Samples: 6688762. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-16 03:17:07,351][03835] Avg episode reward: [(0, '3.750'), (1, '3.410')] -[2023-10-16 03:17:07,610][05218] Updated weights for policy 0, policy_version 13072 (0.0009) -[2023-10-16 03:17:07,989][05218] Updated weights for policy 0, policy_version 13082 (0.0008) -[2023-10-16 03:17:10,201][05219] Updated weights for policy 1, policy_version 13030 (0.0008) -[2023-10-16 03:17:10,573][05219] Updated weights for policy 1, policy_version 13040 (0.0010) -[2023-10-16 03:17:10,936][05219] Updated weights for policy 1, policy_version 13050 (0.0008) -[2023-10-16 03:17:11,719][05218] Updated weights for policy 0, policy_version 13092 (0.0009) -[2023-10-16 03:17:12,089][05218] Updated weights for policy 0, policy_version 13102 (0.0010) -[2023-10-16 03:17:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 26771456. Throughput: 0: 1777.6, 1: 1802.4. Samples: 6700364. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-16 03:17:12,351][03835] Avg episode reward: [(0, '3.340'), (1, '3.670')] -[2023-10-16 03:17:12,469][05218] Updated weights for policy 0, policy_version 13112 (0.0011) -[2023-10-16 03:17:14,837][05219] Updated weights for policy 1, policy_version 13060 (0.0008) -[2023-10-16 03:17:15,204][05219] Updated weights for policy 1, policy_version 13070 (0.0008) -[2023-10-16 03:17:15,570][05219] Updated weights for policy 1, policy_version 13080 (0.0008) -[2023-10-16 03:17:16,026][05218] Updated weights for policy 0, policy_version 13122 (0.0009) -[2023-10-16 03:17:16,404][05218] Updated weights for policy 0, policy_version 13132 (0.0009) -[2023-10-16 03:17:16,786][05218] Updated weights for policy 0, policy_version 13142 (0.0008) -[2023-10-16 03:17:17,157][05218] Updated weights for policy 0, policy_version 13152 (0.0010) -[2023-10-16 03:17:17,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 26869760. Throughput: 0: 1797.1, 1: 1785.4. Samples: 6721088. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-16 03:17:17,351][03835] Avg episode reward: [(0, '3.380'), (1, '3.600')] -[2023-10-16 03:17:19,393][05219] Updated weights for policy 1, policy_version 13090 (0.0008) -[2023-10-16 03:17:19,754][05219] Updated weights for policy 1, policy_version 13100 (0.0007) -[2023-10-16 03:17:20,123][05219] Updated weights for policy 1, policy_version 13110 (0.0007) -[2023-10-16 03:17:20,487][05219] Updated weights for policy 1, policy_version 13120 (0.0007) -[2023-10-16 03:17:20,823][05218] Updated weights for policy 0, policy_version 13162 (0.0009) -[2023-10-16 03:17:21,196][05218] Updated weights for policy 0, policy_version 13172 (0.0008) -[2023-10-16 03:17:21,587][05218] Updated weights for policy 0, policy_version 13182 (0.0009) -[2023-10-16 03:17:22,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 26935296. Throughput: 0: 1788.2, 1: 1783.4. Samples: 6742742. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-16 03:17:22,352][03835] Avg episode reward: [(0, '3.740'), (1, '3.610')] -[2023-10-16 03:17:24,136][05219] Updated weights for policy 1, policy_version 13130 (0.0008) -[2023-10-16 03:17:24,505][05219] Updated weights for policy 1, policy_version 13140 (0.0009) -[2023-10-16 03:17:24,878][05219] Updated weights for policy 1, policy_version 13150 (0.0008) -[2023-10-16 03:17:25,258][05218] Updated weights for policy 0, policy_version 13192 (0.0007) -[2023-10-16 03:17:25,646][05218] Updated weights for policy 0, policy_version 13202 (0.0010) -[2023-10-16 03:17:26,014][05218] Updated weights for policy 0, policy_version 13212 (0.0009) -[2023-10-16 03:17:27,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 27000832. Throughput: 0: 1804.7, 1: 1777.4. Samples: 6753454. Policy #0 lag: (min: 11.0, avg: 16.5, max: 43.0) -[2023-10-16 03:17:27,351][03835] Avg episode reward: [(0, '3.830'), (1, '3.980')] -[2023-10-16 03:17:27,352][04891] Saving new best policy, reward=3.980! -[2023-10-16 03:17:28,498][05219] Updated weights for policy 1, policy_version 13160 (0.0008) -[2023-10-16 03:17:28,869][05219] Updated weights for policy 1, policy_version 13170 (0.0007) -[2023-10-16 03:17:29,239][05219] Updated weights for policy 1, policy_version 13180 (0.0008) -[2023-10-16 03:17:29,774][05218] Updated weights for policy 0, policy_version 13222 (0.0008) -[2023-10-16 03:17:30,142][05218] Updated weights for policy 0, policy_version 13232 (0.0010) -[2023-10-16 03:17:30,523][05218] Updated weights for policy 0, policy_version 13242 (0.0007) -[2023-10-16 03:17:32,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 27066368. Throughput: 0: 1794.4, 1: 1786.6. Samples: 6775276. Policy #0 lag: (min: 11.0, avg: 16.5, max: 43.0) -[2023-10-16 03:17:32,351][03835] Avg episode reward: [(0, '3.850'), (1, '3.680')] -[2023-10-16 03:17:33,123][05219] Updated weights for policy 1, policy_version 13190 (0.0008) -[2023-10-16 03:17:33,497][05219] Updated weights for policy 1, policy_version 13200 (0.0009) -[2023-10-16 03:17:33,854][05219] Updated weights for policy 1, policy_version 13210 (0.0008) -[2023-10-16 03:17:34,308][05218] Updated weights for policy 0, policy_version 13252 (0.0008) -[2023-10-16 03:17:34,686][05218] Updated weights for policy 0, policy_version 13262 (0.0010) -[2023-10-16 03:17:35,064][05218] Updated weights for policy 0, policy_version 13272 (0.0007) -[2023-10-16 03:17:37,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 27131904. Throughput: 0: 1800.7, 1: 1797.8. Samples: 6797592. Policy #0 lag: (min: 11.0, avg: 16.5, max: 43.0) -[2023-10-16 03:17:37,351][03835] Avg episode reward: [(0, '3.930'), (1, '3.650')] -[2023-10-16 03:17:37,361][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000013280_13598720.pth... -[2023-10-16 03:17:37,361][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000013216_13533184.pth... -[2023-10-16 03:17:37,390][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000011616_11894784.pth -[2023-10-16 03:17:37,398][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000011552_11829248.pth -[2023-10-16 03:17:37,680][05219] Updated weights for policy 1, policy_version 13220 (0.0009) -[2023-10-16 03:17:38,046][05219] Updated weights for policy 1, policy_version 13230 (0.0008) -[2023-10-16 03:17:38,413][05219] Updated weights for policy 1, policy_version 13240 (0.0009) -[2023-10-16 03:17:38,842][05218] Updated weights for policy 0, policy_version 13282 (0.0010) -[2023-10-16 03:17:39,215][05218] Updated weights for policy 0, policy_version 13292 (0.0008) -[2023-10-16 03:17:39,586][05218] Updated weights for policy 0, policy_version 13302 (0.0007) -[2023-10-16 03:17:39,960][05218] Updated weights for policy 0, policy_version 13312 (0.0007) -[2023-10-16 03:17:42,239][05219] Updated weights for policy 1, policy_version 13250 (0.0010) -[2023-10-16 03:17:42,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 27197440. Throughput: 0: 1802.1, 1: 1789.3. Samples: 6807462. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-16 03:17:42,351][03835] Avg episode reward: [(0, '4.060'), (1, '3.270')] -[2023-10-16 03:17:42,353][04766] Saving new best policy, reward=4.060! -[2023-10-16 03:17:42,620][05219] Updated weights for policy 1, policy_version 13260 (0.0008) -[2023-10-16 03:17:42,991][05219] Updated weights for policy 1, policy_version 13270 (0.0008) -[2023-10-16 03:17:43,357][05219] Updated weights for policy 1, policy_version 13280 (0.0008) -[2023-10-16 03:17:43,671][05218] Updated weights for policy 0, policy_version 13322 (0.0007) -[2023-10-16 03:17:44,052][05218] Updated weights for policy 0, policy_version 13332 (0.0007) -[2023-10-16 03:17:44,423][05218] Updated weights for policy 0, policy_version 13342 (0.0008) -[2023-10-16 03:17:47,212][05219] Updated weights for policy 1, policy_version 13290 (0.0008) -[2023-10-16 03:17:47,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 27262976. Throughput: 0: 1806.8, 1: 1790.7. Samples: 6829558. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-16 03:17:47,351][03835] Avg episode reward: [(0, '3.890'), (1, '3.650')] -[2023-10-16 03:17:47,585][05219] Updated weights for policy 1, policy_version 13300 (0.0009) -[2023-10-16 03:17:47,943][05219] Updated weights for policy 1, policy_version 13310 (0.0007) -[2023-10-16 03:17:48,034][05218] Updated weights for policy 0, policy_version 13352 (0.0010) -[2023-10-16 03:17:48,409][05218] Updated weights for policy 0, policy_version 13362 (0.0007) -[2023-10-16 03:17:48,783][05218] Updated weights for policy 0, policy_version 13372 (0.0010) -[2023-10-16 03:17:51,822][05219] Updated weights for policy 1, policy_version 13320 (0.0009) -[2023-10-16 03:17:52,191][05219] Updated weights for policy 1, policy_version 13330 (0.0007) -[2023-10-16 03:17:52,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 27328512. Throughput: 0: 1806.7, 1: 1791.9. Samples: 6850700. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-16 03:17:52,351][03835] Avg episode reward: [(0, '3.860'), (1, '3.680')] -[2023-10-16 03:17:52,448][05218] Updated weights for policy 0, policy_version 13382 (0.0007) -[2023-10-16 03:17:52,550][05219] Updated weights for policy 1, policy_version 13340 (0.0009) -[2023-10-16 03:17:52,814][05218] Updated weights for policy 0, policy_version 13392 (0.0007) -[2023-10-16 03:17:53,200][05218] Updated weights for policy 0, policy_version 13402 (0.0007) -[2023-10-16 03:17:56,223][05219] Updated weights for policy 1, policy_version 13350 (0.0008) -[2023-10-16 03:17:56,583][05219] Updated weights for policy 1, policy_version 13360 (0.0008) -[2023-10-16 03:17:56,946][05219] Updated weights for policy 1, policy_version 13370 (0.0008) -[2023-10-16 03:17:57,032][05218] Updated weights for policy 0, policy_version 13412 (0.0008) -[2023-10-16 03:17:57,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 27426816. Throughput: 0: 1797.2, 1: 1779.5. Samples: 6861314. Policy #0 lag: (min: 20.0, avg: 20.6, max: 37.0) -[2023-10-16 03:17:57,351][03835] Avg episode reward: [(0, '3.690'), (1, '3.750')] -[2023-10-16 03:17:57,403][05218] Updated weights for policy 0, policy_version 13422 (0.0008) -[2023-10-16 03:17:57,771][05218] Updated weights for policy 0, policy_version 13432 (0.0009) -[2023-10-16 03:18:00,498][05219] Updated weights for policy 1, policy_version 13380 (0.0007) -[2023-10-16 03:18:00,865][05219] Updated weights for policy 1, policy_version 13390 (0.0007) -[2023-10-16 03:18:01,239][05219] Updated weights for policy 1, policy_version 13400 (0.0008) -[2023-10-16 03:18:01,536][05218] Updated weights for policy 0, policy_version 13442 (0.0008) -[2023-10-16 03:18:01,912][05218] Updated weights for policy 0, policy_version 13452 (0.0008) -[2023-10-16 03:18:02,284][05218] Updated weights for policy 0, policy_version 13462 (0.0008) -[2023-10-16 03:18:02,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 27492352. Throughput: 0: 1801.0, 1: 1792.6. Samples: 6882798. Policy #0 lag: (min: 20.0, avg: 20.6, max: 37.0) -[2023-10-16 03:18:02,351][03835] Avg episode reward: [(0, '3.930'), (1, '3.590')] -[2023-10-16 03:18:02,666][05218] Updated weights for policy 0, policy_version 13472 (0.0008) -[2023-10-16 03:18:05,197][05219] Updated weights for policy 1, policy_version 13410 (0.0009) -[2023-10-16 03:18:05,557][05219] Updated weights for policy 1, policy_version 13420 (0.0008) -[2023-10-16 03:18:05,922][05219] Updated weights for policy 1, policy_version 13430 (0.0010) -[2023-10-16 03:18:06,277][05219] Updated weights for policy 1, policy_version 13440 (0.0010) -[2023-10-16 03:18:06,474][05218] Updated weights for policy 0, policy_version 13482 (0.0008) -[2023-10-16 03:18:06,844][05218] Updated weights for policy 0, policy_version 13492 (0.0009) -[2023-10-16 03:18:07,216][05218] Updated weights for policy 0, policy_version 13502 (0.0009) -[2023-10-16 03:18:07,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 27590656. Throughput: 0: 1785.6, 1: 1777.7. Samples: 6903090. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:18:07,352][03835] Avg episode reward: [(0, '3.680'), (1, '3.830')] -[2023-10-16 03:18:10,100][05219] Updated weights for policy 1, policy_version 13450 (0.0008) -[2023-10-16 03:18:10,473][05219] Updated weights for policy 1, policy_version 13460 (0.0008) -[2023-10-16 03:18:10,838][05219] Updated weights for policy 1, policy_version 13470 (0.0009) -[2023-10-16 03:18:11,188][05218] Updated weights for policy 0, policy_version 13512 (0.0009) -[2023-10-16 03:18:11,562][05218] Updated weights for policy 0, policy_version 13522 (0.0008) -[2023-10-16 03:18:11,949][05218] Updated weights for policy 0, policy_version 13532 (0.0008) -[2023-10-16 03:18:12,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 27656192. Throughput: 0: 1794.9, 1: 1801.8. Samples: 6915308. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:18:12,351][03835] Avg episode reward: [(0, '3.880'), (1, '3.730')] -[2023-10-16 03:18:14,571][05219] Updated weights for policy 1, policy_version 13480 (0.0008) -[2023-10-16 03:18:14,943][05219] Updated weights for policy 1, policy_version 13490 (0.0008) -[2023-10-16 03:18:15,318][05219] Updated weights for policy 1, policy_version 13500 (0.0008) -[2023-10-16 03:18:15,860][05218] Updated weights for policy 0, policy_version 13542 (0.0010) -[2023-10-16 03:18:16,234][05218] Updated weights for policy 0, policy_version 13552 (0.0009) -[2023-10-16 03:18:16,604][05218] Updated weights for policy 0, policy_version 13562 (0.0008) -[2023-10-16 03:18:17,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 27721728. Throughput: 0: 1787.6, 1: 1772.3. Samples: 6935472. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:18:17,352][03835] Avg episode reward: [(0, '3.790'), (1, '3.680')] -[2023-10-16 03:18:19,149][05219] Updated weights for policy 1, policy_version 13510 (0.0010) -[2023-10-16 03:18:19,511][05219] Updated weights for policy 1, policy_version 13520 (0.0011) -[2023-10-16 03:18:19,877][05219] Updated weights for policy 1, policy_version 13530 (0.0011) -[2023-10-16 03:18:20,154][05218] Updated weights for policy 0, policy_version 13572 (0.0009) -[2023-10-16 03:18:20,533][05218] Updated weights for policy 0, policy_version 13582 (0.0011) -[2023-10-16 03:18:20,905][05218] Updated weights for policy 0, policy_version 13592 (0.0010) -[2023-10-16 03:18:22,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 27787264. Throughput: 0: 1773.5, 1: 1775.3. Samples: 6957286. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-16 03:18:22,352][03835] Avg episode reward: [(0, '3.820'), (1, '3.440')] -[2023-10-16 03:18:23,746][05219] Updated weights for policy 1, policy_version 13540 (0.0009) -[2023-10-16 03:18:24,112][05219] Updated weights for policy 1, policy_version 13550 (0.0007) -[2023-10-16 03:18:24,475][05219] Updated weights for policy 1, policy_version 13560 (0.0007) -[2023-10-16 03:18:24,731][05218] Updated weights for policy 0, policy_version 13602 (0.0010) -[2023-10-16 03:18:25,109][05218] Updated weights for policy 0, policy_version 13612 (0.0011) -[2023-10-16 03:18:25,473][05218] Updated weights for policy 0, policy_version 13622 (0.0010) -[2023-10-16 03:18:25,848][05218] Updated weights for policy 0, policy_version 13632 (0.0010) -[2023-10-16 03:18:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 27852800. Throughput: 0: 1786.5, 1: 1771.5. Samples: 6967574. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-16 03:18:27,351][03835] Avg episode reward: [(0, '3.830'), (1, '3.460')] -[2023-10-16 03:18:28,407][05219] Updated weights for policy 1, policy_version 13570 (0.0008) -[2023-10-16 03:18:28,796][05219] Updated weights for policy 1, policy_version 13580 (0.0008) -[2023-10-16 03:18:29,159][05219] Updated weights for policy 1, policy_version 13590 (0.0009) -[2023-10-16 03:18:29,530][05219] Updated weights for policy 1, policy_version 13600 (0.0010) -[2023-10-16 03:18:29,677][05218] Updated weights for policy 0, policy_version 13642 (0.0007) -[2023-10-16 03:18:30,054][05218] Updated weights for policy 0, policy_version 13652 (0.0008) -[2023-10-16 03:18:30,431][05218] Updated weights for policy 0, policy_version 13662 (0.0008) -[2023-10-16 03:18:32,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 27918336. Throughput: 0: 1773.5, 1: 1771.6. Samples: 6989086. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-16 03:18:32,351][03835] Avg episode reward: [(0, '3.400'), (1, '3.490')] -[2023-10-16 03:18:33,454][05219] Updated weights for policy 1, policy_version 13610 (0.0009) -[2023-10-16 03:18:33,819][05219] Updated weights for policy 1, policy_version 13620 (0.0010) -[2023-10-16 03:18:34,177][05219] Updated weights for policy 1, policy_version 13630 (0.0008) -[2023-10-16 03:18:34,220][05218] Updated weights for policy 0, policy_version 13672 (0.0007) -[2023-10-16 03:18:34,592][05218] Updated weights for policy 0, policy_version 13682 (0.0008) -[2023-10-16 03:18:34,966][05218] Updated weights for policy 0, policy_version 13692 (0.0008) -[2023-10-16 03:18:37,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 27983872. Throughput: 0: 1781.5, 1: 1790.1. Samples: 7011420. Policy #0 lag: (min: 21.0, avg: 27.6, max: 53.0) -[2023-10-16 03:18:37,352][03835] Avg episode reward: [(0, '3.700'), (1, '3.720')] -[2023-10-16 03:18:37,896][05219] Updated weights for policy 1, policy_version 13640 (0.0008) -[2023-10-16 03:18:38,255][05219] Updated weights for policy 1, policy_version 13650 (0.0007) -[2023-10-16 03:18:38,622][05219] Updated weights for policy 1, policy_version 13660 (0.0007) -[2023-10-16 03:18:38,684][05218] Updated weights for policy 0, policy_version 13702 (0.0009) -[2023-10-16 03:18:39,060][05218] Updated weights for policy 0, policy_version 13712 (0.0010) -[2023-10-16 03:18:39,437][05218] Updated weights for policy 0, policy_version 13722 (0.0010) -[2023-10-16 03:18:42,323][05219] Updated weights for policy 1, policy_version 13670 (0.0007) -[2023-10-16 03:18:42,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 28049408. Throughput: 0: 1780.4, 1: 1775.4. Samples: 7021324. Policy #0 lag: (min: 21.0, avg: 27.6, max: 53.0) -[2023-10-16 03:18:42,351][03835] Avg episode reward: [(0, '3.570'), (1, '3.410')] -[2023-10-16 03:18:42,699][05219] Updated weights for policy 1, policy_version 13680 (0.0009) -[2023-10-16 03:18:43,066][05219] Updated weights for policy 1, policy_version 13690 (0.0007) -[2023-10-16 03:18:43,211][05218] Updated weights for policy 0, policy_version 13732 (0.0007) -[2023-10-16 03:18:43,585][05218] Updated weights for policy 0, policy_version 13742 (0.0010) -[2023-10-16 03:18:43,966][05218] Updated weights for policy 0, policy_version 13752 (0.0009) -[2023-10-16 03:18:46,835][05219] Updated weights for policy 1, policy_version 13700 (0.0009) -[2023-10-16 03:18:47,198][05219] Updated weights for policy 1, policy_version 13710 (0.0010) -[2023-10-16 03:18:47,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 28114944. Throughput: 0: 1781.0, 1: 1790.9. Samples: 7043534. Policy #0 lag: (min: 21.0, avg: 27.6, max: 53.0) -[2023-10-16 03:18:47,351][03835] Avg episode reward: [(0, '3.650'), (1, '3.800')] -[2023-10-16 03:18:47,548][05219] Updated weights for policy 1, policy_version 13720 (0.0009) -[2023-10-16 03:18:47,712][05218] Updated weights for policy 0, policy_version 13762 (0.0008) -[2023-10-16 03:18:48,085][05218] Updated weights for policy 0, policy_version 13772 (0.0010) -[2023-10-16 03:18:48,453][05218] Updated weights for policy 0, policy_version 13782 (0.0008) -[2023-10-16 03:18:48,830][05218] Updated weights for policy 0, policy_version 13792 (0.0009) -[2023-10-16 03:18:51,372][05219] Updated weights for policy 1, policy_version 13730 (0.0009) -[2023-10-16 03:18:51,740][05219] Updated weights for policy 1, policy_version 13740 (0.0010) -[2023-10-16 03:18:52,100][05219] Updated weights for policy 1, policy_version 13750 (0.0008) -[2023-10-16 03:18:52,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 28180480. Throughput: 0: 1808.9, 1: 1778.9. Samples: 7064542. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:18:52,351][03835] Avg episode reward: [(0, '3.630'), (1, '3.740')] -[2023-10-16 03:18:52,354][05218] Updated weights for policy 0, policy_version 13802 (0.0008) -[2023-10-16 03:18:52,465][05219] Updated weights for policy 1, policy_version 13760 (0.0007) -[2023-10-16 03:18:52,727][05218] Updated weights for policy 0, policy_version 13812 (0.0007) -[2023-10-16 03:18:53,114][05218] Updated weights for policy 0, policy_version 13822 (0.0007) -[2023-10-16 03:18:56,386][05219] Updated weights for policy 1, policy_version 13770 (0.0009) -[2023-10-16 03:18:56,751][05219] Updated weights for policy 1, policy_version 13780 (0.0009) -[2023-10-16 03:18:56,820][05218] Updated weights for policy 0, policy_version 13832 (0.0010) -[2023-10-16 03:18:57,118][05219] Updated weights for policy 1, policy_version 13790 (0.0007) -[2023-10-16 03:18:57,183][05218] Updated weights for policy 0, policy_version 13842 (0.0007) -[2023-10-16 03:18:57,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 28278784. Throughput: 0: 1788.1, 1: 1778.5. Samples: 7075806. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:18:57,351][03835] Avg episode reward: [(0, '3.730'), (1, '3.870')] -[2023-10-16 03:18:57,557][05218] Updated weights for policy 0, policy_version 13852 (0.0008) -[2023-10-16 03:19:00,927][05219] Updated weights for policy 1, policy_version 13800 (0.0011) -[2023-10-16 03:19:01,170][05218] Updated weights for policy 0, policy_version 13862 (0.0009) -[2023-10-16 03:19:01,288][05219] Updated weights for policy 1, policy_version 13810 (0.0007) -[2023-10-16 03:19:01,549][05218] Updated weights for policy 0, policy_version 13872 (0.0007) -[2023-10-16 03:19:01,657][05219] Updated weights for policy 1, policy_version 13820 (0.0009) -[2023-10-16 03:19:01,917][05218] Updated weights for policy 0, policy_version 13882 (0.0008) -[2023-10-16 03:19:02,350][03835] Fps is (10 sec: 19660.3, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 28377088. Throughput: 0: 1807.9, 1: 1784.7. Samples: 7097138. Policy #0 lag: (min: 18.0, avg: 26.0, max: 50.0) -[2023-10-16 03:19:02,351][03835] Avg episode reward: [(0, '3.870'), (1, '3.910')] -[2023-10-16 03:19:05,449][05219] Updated weights for policy 1, policy_version 13830 (0.0008) -[2023-10-16 03:19:05,751][05218] Updated weights for policy 0, policy_version 13892 (0.0008) -[2023-10-16 03:19:05,809][05219] Updated weights for policy 1, policy_version 13840 (0.0007) -[2023-10-16 03:19:06,120][05218] Updated weights for policy 0, policy_version 13902 (0.0007) -[2023-10-16 03:19:06,181][05219] Updated weights for policy 1, policy_version 13850 (0.0008) -[2023-10-16 03:19:06,497][05218] Updated weights for policy 0, policy_version 13912 (0.0008) -[2023-10-16 03:19:07,351][03835] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 28442624. Throughput: 0: 1793.0, 1: 1766.6. Samples: 7117468. Policy #0 lag: (min: 18.0, avg: 26.0, max: 50.0) -[2023-10-16 03:19:07,352][03835] Avg episode reward: [(0, '3.800'), (1, '3.950')] -[2023-10-16 03:19:09,923][05219] Updated weights for policy 1, policy_version 13860 (0.0008) -[2023-10-16 03:19:10,298][05219] Updated weights for policy 1, policy_version 13870 (0.0007) -[2023-10-16 03:19:10,344][05218] Updated weights for policy 0, policy_version 13922 (0.0009) -[2023-10-16 03:19:10,666][05219] Updated weights for policy 1, policy_version 13880 (0.0008) -[2023-10-16 03:19:10,726][05218] Updated weights for policy 0, policy_version 13932 (0.0008) -[2023-10-16 03:19:11,086][05218] Updated weights for policy 0, policy_version 13942 (0.0009) -[2023-10-16 03:19:11,456][05218] Updated weights for policy 0, policy_version 13952 (0.0009) -[2023-10-16 03:19:12,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 28508160. Throughput: 0: 1806.3, 1: 1792.3. Samples: 7129510. Policy #0 lag: (min: 18.0, avg: 26.0, max: 50.0) -[2023-10-16 03:19:12,351][03835] Avg episode reward: [(0, '3.610'), (1, '3.740')] -[2023-10-16 03:19:14,460][05219] Updated weights for policy 1, policy_version 13890 (0.0009) -[2023-10-16 03:19:14,813][05219] Updated weights for policy 1, policy_version 13900 (0.0009) -[2023-10-16 03:19:15,154][05218] Updated weights for policy 0, policy_version 13962 (0.0009) -[2023-10-16 03:19:15,180][05219] Updated weights for policy 1, policy_version 13910 (0.0007) -[2023-10-16 03:19:15,531][05218] Updated weights for policy 0, policy_version 13972 (0.0007) -[2023-10-16 03:19:15,537][05219] Updated weights for policy 1, policy_version 13920 (0.0007) -[2023-10-16 03:19:15,908][05218] Updated weights for policy 0, policy_version 13982 (0.0010) -[2023-10-16 03:19:17,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 28573696. Throughput: 0: 1790.1, 1: 1771.9. Samples: 7149380. Policy #0 lag: (min: 24.0, avg: 46.7, max: 56.0) -[2023-10-16 03:19:17,352][03835] Avg episode reward: [(0, '3.820'), (1, '3.890')] -[2023-10-16 03:19:19,294][05219] Updated weights for policy 1, policy_version 13930 (0.0009) -[2023-10-16 03:19:19,558][05218] Updated weights for policy 0, policy_version 13992 (0.0009) -[2023-10-16 03:19:19,658][05219] Updated weights for policy 1, policy_version 13940 (0.0007) -[2023-10-16 03:19:19,929][05218] Updated weights for policy 0, policy_version 14002 (0.0007) -[2023-10-16 03:19:20,026][05219] Updated weights for policy 1, policy_version 13950 (0.0008) -[2023-10-16 03:19:20,317][05218] Updated weights for policy 0, policy_version 14012 (0.0009) -[2023-10-16 03:19:22,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 28639232. Throughput: 0: 1791.6, 1: 1768.3. Samples: 7171612. Policy #0 lag: (min: 24.0, avg: 46.7, max: 56.0) -[2023-10-16 03:19:22,351][03835] Avg episode reward: [(0, '3.860'), (1, '3.550')] -[2023-10-16 03:19:23,881][05219] Updated weights for policy 1, policy_version 13960 (0.0009) -[2023-10-16 03:19:24,112][05218] Updated weights for policy 0, policy_version 14022 (0.0009) -[2023-10-16 03:19:24,243][05219] Updated weights for policy 1, policy_version 13970 (0.0008) -[2023-10-16 03:19:24,483][05218] Updated weights for policy 0, policy_version 14032 (0.0008) -[2023-10-16 03:19:24,609][05219] Updated weights for policy 1, policy_version 13980 (0.0009) -[2023-10-16 03:19:24,855][05218] Updated weights for policy 0, policy_version 14042 (0.0008) -[2023-10-16 03:19:27,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 28704768. Throughput: 0: 1788.7, 1: 1762.0. Samples: 7181102. Policy #0 lag: (min: 24.0, avg: 46.7, max: 56.0) -[2023-10-16 03:19:27,351][03835] Avg episode reward: [(0, '3.980'), (1, '3.630')] -[2023-10-16 03:19:28,576][05219] Updated weights for policy 1, policy_version 13990 (0.0009) -[2023-10-16 03:19:28,785][05218] Updated weights for policy 0, policy_version 14052 (0.0009) -[2023-10-16 03:19:28,934][05219] Updated weights for policy 1, policy_version 14000 (0.0009) -[2023-10-16 03:19:29,159][05218] Updated weights for policy 0, policy_version 14062 (0.0009) -[2023-10-16 03:19:29,300][05219] Updated weights for policy 1, policy_version 14010 (0.0008) -[2023-10-16 03:19:29,539][05218] Updated weights for policy 0, policy_version 14072 (0.0008) -[2023-10-16 03:19:32,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 28770304. Throughput: 0: 1781.7, 1: 1753.3. Samples: 7202610. Policy #0 lag: (min: 3.0, avg: 8.4, max: 35.0) -[2023-10-16 03:19:32,352][03835] Avg episode reward: [(0, '3.640'), (1, '3.830')] -[2023-10-16 03:19:33,065][05219] Updated weights for policy 1, policy_version 14020 (0.0008) -[2023-10-16 03:19:33,318][05218] Updated weights for policy 0, policy_version 14082 (0.0007) -[2023-10-16 03:19:33,428][05219] Updated weights for policy 1, policy_version 14030 (0.0008) -[2023-10-16 03:19:33,693][05218] Updated weights for policy 0, policy_version 14092 (0.0007) -[2023-10-16 03:19:33,799][05219] Updated weights for policy 1, policy_version 14040 (0.0007) -[2023-10-16 03:19:34,072][05218] Updated weights for policy 0, policy_version 14102 (0.0007) -[2023-10-16 03:19:34,436][05218] Updated weights for policy 0, policy_version 14112 (0.0009) -[2023-10-16 03:19:37,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 28835840. Throughput: 0: 1783.9, 1: 1778.1. Samples: 7224836. Policy #0 lag: (min: 3.0, avg: 8.4, max: 35.0) -[2023-10-16 03:19:37,351][03835] Avg episode reward: [(0, '4.040'), (1, '3.620')] -[2023-10-16 03:19:37,362][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000014112_14450688.pth... -[2023-10-16 03:19:37,362][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000014048_14385152.pth... -[2023-10-16 03:19:37,414][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000012384_12681216.pth -[2023-10-16 03:19:37,414][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000012448_12746752.pth -[2023-10-16 03:19:37,647][05219] Updated weights for policy 1, policy_version 14050 (0.0007) -[2023-10-16 03:19:38,018][05219] Updated weights for policy 1, policy_version 14060 (0.0007) -[2023-10-16 03:19:38,232][05218] Updated weights for policy 0, policy_version 14122 (0.0009) -[2023-10-16 03:19:38,387][05219] Updated weights for policy 1, policy_version 14070 (0.0007) -[2023-10-16 03:19:38,606][05218] Updated weights for policy 0, policy_version 14132 (0.0009) -[2023-10-16 03:19:38,741][05219] Updated weights for policy 1, policy_version 14080 (0.0008) -[2023-10-16 03:19:38,979][05218] Updated weights for policy 0, policy_version 14142 (0.0009) -[2023-10-16 03:19:42,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 28901376. Throughput: 0: 1772.0, 1: 1757.0. Samples: 7234610. Policy #0 lag: (min: 3.0, avg: 8.4, max: 35.0) -[2023-10-16 03:19:42,351][03835] Avg episode reward: [(0, '4.200'), (1, '3.860')] -[2023-10-16 03:19:42,352][04766] Saving new best policy, reward=4.200! -[2023-10-16 03:19:42,584][05219] Updated weights for policy 1, policy_version 14090 (0.0007) -[2023-10-16 03:19:42,832][05218] Updated weights for policy 0, policy_version 14152 (0.0008) -[2023-10-16 03:19:42,945][05219] Updated weights for policy 1, policy_version 14100 (0.0008) -[2023-10-16 03:19:43,209][05218] Updated weights for policy 0, policy_version 14162 (0.0009) -[2023-10-16 03:19:43,308][05219] Updated weights for policy 1, policy_version 14110 (0.0007) -[2023-10-16 03:19:43,581][05218] Updated weights for policy 0, policy_version 14172 (0.0009) -[2023-10-16 03:19:47,071][05219] Updated weights for policy 1, policy_version 14120 (0.0008) -[2023-10-16 03:19:47,264][05218] Updated weights for policy 0, policy_version 14182 (0.0007) -[2023-10-16 03:19:47,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 28966912. Throughput: 0: 1779.0, 1: 1771.7. Samples: 7256918. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-16 03:19:47,351][03835] Avg episode reward: [(0, '4.250'), (1, '3.740')] -[2023-10-16 03:19:47,430][05219] Updated weights for policy 1, policy_version 14130 (0.0007) -[2023-10-16 03:19:47,640][05218] Updated weights for policy 0, policy_version 14192 (0.0007) -[2023-10-16 03:19:47,801][05219] Updated weights for policy 1, policy_version 14140 (0.0008) -[2023-10-16 03:19:48,001][05218] Updated weights for policy 0, policy_version 14202 (0.0008) -[2023-10-16 03:19:48,227][04766] Saving new best policy, reward=4.250! -[2023-10-16 03:19:51,572][05219] Updated weights for policy 1, policy_version 14150 (0.0009) -[2023-10-16 03:19:51,804][05218] Updated weights for policy 0, policy_version 14212 (0.0009) -[2023-10-16 03:19:51,944][05219] Updated weights for policy 1, policy_version 14160 (0.0007) -[2023-10-16 03:19:52,179][05218] Updated weights for policy 0, policy_version 14222 (0.0007) -[2023-10-16 03:19:52,301][05219] Updated weights for policy 1, policy_version 14170 (0.0007) -[2023-10-16 03:19:52,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 29032448. Throughput: 0: 1785.4, 1: 1769.7. Samples: 7277448. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-16 03:19:52,351][03835] Avg episode reward: [(0, '4.490'), (1, '3.620')] -[2023-10-16 03:19:52,548][05218] Updated weights for policy 0, policy_version 14232 (0.0008) -[2023-10-16 03:19:52,841][04766] Saving new best policy, reward=4.490! -[2023-10-16 03:19:56,100][05219] Updated weights for policy 1, policy_version 14180 (0.0008) -[2023-10-16 03:19:56,403][05218] Updated weights for policy 0, policy_version 14242 (0.0008) -[2023-10-16 03:19:56,470][05219] Updated weights for policy 1, policy_version 14190 (0.0008) -[2023-10-16 03:19:56,768][05218] Updated weights for policy 0, policy_version 14252 (0.0008) -[2023-10-16 03:19:56,828][05219] Updated weights for policy 1, policy_version 14200 (0.0008) -[2023-10-16 03:19:57,141][05218] Updated weights for policy 0, policy_version 14262 (0.0010) -[2023-10-16 03:19:57,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 29130752. Throughput: 0: 1773.8, 1: 1766.7. Samples: 7288832. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-16 03:19:57,351][03835] Avg episode reward: [(0, '4.040'), (1, '3.800')] -[2023-10-16 03:19:57,523][05218] Updated weights for policy 0, policy_version 14272 (0.0007) -[2023-10-16 03:20:00,850][05219] Updated weights for policy 1, policy_version 14210 (0.0009) -[2023-10-16 03:20:01,246][05219] Updated weights for policy 1, policy_version 14220 (0.0008) -[2023-10-16 03:20:01,307][05218] Updated weights for policy 0, policy_version 14282 (0.0008) -[2023-10-16 03:20:01,615][05219] Updated weights for policy 1, policy_version 14230 (0.0009) -[2023-10-16 03:20:01,688][05218] Updated weights for policy 0, policy_version 14292 (0.0008) -[2023-10-16 03:20:01,974][05219] Updated weights for policy 1, policy_version 14240 (0.0008) -[2023-10-16 03:20:02,060][05218] Updated weights for policy 0, policy_version 14302 (0.0008) -[2023-10-16 03:20:02,350][03835] Fps is (10 sec: 19660.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 29229056. Throughput: 0: 1791.2, 1: 1776.0. Samples: 7309902. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-16 03:20:02,351][03835] Avg episode reward: [(0, '3.700'), (1, '3.900')] -[2023-10-16 03:20:05,779][05219] Updated weights for policy 1, policy_version 14250 (0.0010) -[2023-10-16 03:20:05,879][05218] Updated weights for policy 0, policy_version 14312 (0.0008) -[2023-10-16 03:20:06,139][05219] Updated weights for policy 1, policy_version 14260 (0.0009) -[2023-10-16 03:20:06,249][05218] Updated weights for policy 0, policy_version 14322 (0.0008) -[2023-10-16 03:20:06,510][05219] Updated weights for policy 1, policy_version 14270 (0.0008) -[2023-10-16 03:20:06,621][05218] Updated weights for policy 0, policy_version 14332 (0.0008) -[2023-10-16 03:20:07,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.6, 300 sec: 14329.1). Total num frames: 29294592. Throughput: 0: 1766.2, 1: 1758.6. Samples: 7330226. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-16 03:20:07,351][03835] Avg episode reward: [(0, '3.770'), (1, '4.140')] -[2023-10-16 03:20:07,362][04891] Saving new best policy, reward=4.140! -[2023-10-16 03:20:10,390][05219] Updated weights for policy 1, policy_version 14280 (0.0007) -[2023-10-16 03:20:10,394][05218] Updated weights for policy 0, policy_version 14342 (0.0010) -[2023-10-16 03:20:10,755][05219] Updated weights for policy 1, policy_version 14290 (0.0007) -[2023-10-16 03:20:10,777][05218] Updated weights for policy 0, policy_version 14352 (0.0008) -[2023-10-16 03:20:11,112][05219] Updated weights for policy 1, policy_version 14300 (0.0009) -[2023-10-16 03:20:11,141][05218] Updated weights for policy 0, policy_version 14362 (0.0008) -[2023-10-16 03:20:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 29360128. Throughput: 0: 1800.1, 1: 1790.0. Samples: 7342652. Policy #0 lag: (min: 27.0, avg: 31.7, max: 59.0) -[2023-10-16 03:20:12,351][03835] Avg episode reward: [(0, '3.710'), (1, '3.880')] -[2023-10-16 03:20:14,973][05219] Updated weights for policy 1, policy_version 14310 (0.0008) -[2023-10-16 03:20:14,981][05218] Updated weights for policy 0, policy_version 14372 (0.0010) -[2023-10-16 03:20:15,339][05219] Updated weights for policy 1, policy_version 14320 (0.0009) -[2023-10-16 03:20:15,364][05218] Updated weights for policy 0, policy_version 14382 (0.0009) -[2023-10-16 03:20:15,710][05219] Updated weights for policy 1, policy_version 14330 (0.0007) -[2023-10-16 03:20:15,736][05218] Updated weights for policy 0, policy_version 14392 (0.0008) -[2023-10-16 03:20:17,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.6, 300 sec: 14329.1). Total num frames: 29425664. Throughput: 0: 1776.0, 1: 1767.7. Samples: 7362076. Policy #0 lag: (min: 27.0, avg: 31.7, max: 59.0) -[2023-10-16 03:20:17,351][03835] Avg episode reward: [(0, '4.040'), (1, '4.060')] -[2023-10-16 03:20:19,543][05219] Updated weights for policy 1, policy_version 14340 (0.0008) -[2023-10-16 03:20:19,615][05218] Updated weights for policy 0, policy_version 14402 (0.0008) -[2023-10-16 03:20:19,911][05219] Updated weights for policy 1, policy_version 14350 (0.0008) -[2023-10-16 03:20:19,991][05218] Updated weights for policy 0, policy_version 14412 (0.0007) -[2023-10-16 03:20:20,268][05219] Updated weights for policy 1, policy_version 14360 (0.0007) -[2023-10-16 03:20:20,365][05218] Updated weights for policy 0, policy_version 14422 (0.0008) -[2023-10-16 03:20:20,745][05218] Updated weights for policy 0, policy_version 14432 (0.0009) -[2023-10-16 03:20:22,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 29491200. Throughput: 0: 1773.2, 1: 1769.3. Samples: 7384248. Policy #0 lag: (min: 27.0, avg: 31.7, max: 59.0) -[2023-10-16 03:20:22,351][03835] Avg episode reward: [(0, '4.130'), (1, '3.770')] -[2023-10-16 03:20:23,909][05219] Updated weights for policy 1, policy_version 14370 (0.0008) -[2023-10-16 03:20:24,266][05219] Updated weights for policy 1, policy_version 14380 (0.0009) -[2023-10-16 03:20:24,531][05218] Updated weights for policy 0, policy_version 14442 (0.0009) -[2023-10-16 03:20:24,646][05219] Updated weights for policy 1, policy_version 14390 (0.0009) -[2023-10-16 03:20:24,900][05218] Updated weights for policy 0, policy_version 14452 (0.0009) -[2023-10-16 03:20:25,008][05219] Updated weights for policy 1, policy_version 14400 (0.0009) -[2023-10-16 03:20:25,274][05218] Updated weights for policy 0, policy_version 14462 (0.0009) -[2023-10-16 03:20:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 29556736. Throughput: 0: 1770.1, 1: 1770.4. Samples: 7393934. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-16 03:20:27,351][03835] Avg episode reward: [(0, '3.910'), (1, '4.050')] -[2023-10-16 03:20:28,663][05219] Updated weights for policy 1, policy_version 14410 (0.0010) -[2023-10-16 03:20:29,026][05219] Updated weights for policy 1, policy_version 14420 (0.0008) -[2023-10-16 03:20:29,143][05218] Updated weights for policy 0, policy_version 14472 (0.0008) -[2023-10-16 03:20:29,393][05219] Updated weights for policy 1, policy_version 14430 (0.0007) -[2023-10-16 03:20:29,527][05218] Updated weights for policy 0, policy_version 14482 (0.0008) -[2023-10-16 03:20:29,900][05218] Updated weights for policy 0, policy_version 14492 (0.0009) -[2023-10-16 03:20:32,351][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 29622272. Throughput: 0: 1762.7, 1: 1771.1. Samples: 7415940. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-16 03:20:32,352][03835] Avg episode reward: [(0, '4.300'), (1, '4.160')] -[2023-10-16 03:20:32,353][04891] Saving new best policy, reward=4.160! -[2023-10-16 03:20:33,253][05219] Updated weights for policy 1, policy_version 14440 (0.0007) -[2023-10-16 03:20:33,617][05219] Updated weights for policy 1, policy_version 14450 (0.0009) -[2023-10-16 03:20:33,633][05218] Updated weights for policy 0, policy_version 14502 (0.0008) -[2023-10-16 03:20:33,975][05219] Updated weights for policy 1, policy_version 14460 (0.0008) -[2023-10-16 03:20:34,006][05218] Updated weights for policy 0, policy_version 14512 (0.0007) -[2023-10-16 03:20:34,376][05218] Updated weights for policy 0, policy_version 14522 (0.0009) -[2023-10-16 03:20:37,350][03835] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 29687808. Throughput: 0: 1782.5, 1: 1787.1. Samples: 7438080. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-16 03:20:37,352][03835] Avg episode reward: [(0, '4.090'), (1, '4.290')] -[2023-10-16 03:20:37,365][04891] Saving new best policy, reward=4.290! -[2023-10-16 03:20:37,767][05219] Updated weights for policy 1, policy_version 14470 (0.0007) -[2023-10-16 03:20:38,085][05218] Updated weights for policy 0, policy_version 14532 (0.0008) -[2023-10-16 03:20:38,143][05219] Updated weights for policy 1, policy_version 14480 (0.0008) -[2023-10-16 03:20:38,456][05218] Updated weights for policy 0, policy_version 14542 (0.0008) -[2023-10-16 03:20:38,497][05219] Updated weights for policy 1, policy_version 14490 (0.0007) -[2023-10-16 03:20:38,829][05218] Updated weights for policy 0, policy_version 14552 (0.0010) -[2023-10-16 03:20:42,117][05219] Updated weights for policy 1, policy_version 14500 (0.0008) -[2023-10-16 03:20:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 29753344. Throughput: 0: 1765.6, 1: 1769.9. Samples: 7447928. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:20:42,351][03835] Avg episode reward: [(0, '4.550'), (1, '4.210')] -[2023-10-16 03:20:42,352][04766] Saving new best policy, reward=4.550! -[2023-10-16 03:20:42,478][05219] Updated weights for policy 1, policy_version 14510 (0.0009) -[2023-10-16 03:20:42,692][05218] Updated weights for policy 0, policy_version 14562 (0.0008) -[2023-10-16 03:20:42,838][05219] Updated weights for policy 1, policy_version 14520 (0.0008) -[2023-10-16 03:20:43,054][05218] Updated weights for policy 0, policy_version 14572 (0.0008) -[2023-10-16 03:20:43,429][05218] Updated weights for policy 0, policy_version 14582 (0.0009) -[2023-10-16 03:20:43,801][05218] Updated weights for policy 0, policy_version 14592 (0.0008) -[2023-10-16 03:20:46,688][05219] Updated weights for policy 1, policy_version 14530 (0.0009) -[2023-10-16 03:20:47,103][05219] Updated weights for policy 1, policy_version 14540 (0.0009) -[2023-10-16 03:20:47,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 29818880. Throughput: 0: 1772.6, 1: 1789.2. Samples: 7470184. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:20:47,351][03835] Avg episode reward: [(0, '4.100'), (1, '4.160')] -[2023-10-16 03:20:47,464][05219] Updated weights for policy 1, policy_version 14550 (0.0008) -[2023-10-16 03:20:47,579][05218] Updated weights for policy 0, policy_version 14602 (0.0008) -[2023-10-16 03:20:47,822][05219] Updated weights for policy 1, policy_version 14560 (0.0008) -[2023-10-16 03:20:47,953][05218] Updated weights for policy 0, policy_version 14612 (0.0008) -[2023-10-16 03:20:48,328][05218] Updated weights for policy 0, policy_version 14622 (0.0012) -[2023-10-16 03:20:51,601][05219] Updated weights for policy 1, policy_version 14570 (0.0008) -[2023-10-16 03:20:51,960][05219] Updated weights for policy 1, policy_version 14580 (0.0007) -[2023-10-16 03:20:52,186][05218] Updated weights for policy 0, policy_version 14632 (0.0008) -[2023-10-16 03:20:52,327][05219] Updated weights for policy 1, policy_version 14590 (0.0009) -[2023-10-16 03:20:52,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 29884416. Throughput: 0: 1781.1, 1: 1783.2. Samples: 7490618. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:20:52,351][03835] Avg episode reward: [(0, '4.170'), (1, '4.120')] -[2023-10-16 03:20:52,564][05218] Updated weights for policy 0, policy_version 14642 (0.0007) -[2023-10-16 03:20:52,937][05218] Updated weights for policy 0, policy_version 14652 (0.0007) -[2023-10-16 03:20:56,022][05219] Updated weights for policy 1, policy_version 14600 (0.0009) -[2023-10-16 03:20:56,390][05219] Updated weights for policy 1, policy_version 14610 (0.0010) -[2023-10-16 03:20:56,656][05218] Updated weights for policy 0, policy_version 14662 (0.0007) -[2023-10-16 03:20:56,751][05219] Updated weights for policy 1, policy_version 14620 (0.0008) -[2023-10-16 03:20:57,036][05218] Updated weights for policy 0, policy_version 14672 (0.0009) -[2023-10-16 03:20:57,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 29982720. Throughput: 0: 1763.3, 1: 1779.0. Samples: 7502056. Policy #0 lag: (min: 31.0, avg: 32.1, max: 53.0) -[2023-10-16 03:20:57,351][03835] Avg episode reward: [(0, '4.160'), (1, '4.010')] -[2023-10-16 03:20:57,409][05218] Updated weights for policy 0, policy_version 14682 (0.0007) -[2023-10-16 03:21:00,563][05219] Updated weights for policy 1, policy_version 14630 (0.0008) -[2023-10-16 03:21:00,921][05219] Updated weights for policy 1, policy_version 14640 (0.0010) -[2023-10-16 03:21:01,095][05218] Updated weights for policy 0, policy_version 14692 (0.0008) -[2023-10-16 03:21:01,293][05219] Updated weights for policy 1, policy_version 14650 (0.0009) -[2023-10-16 03:21:01,469][05218] Updated weights for policy 0, policy_version 14702 (0.0009) -[2023-10-16 03:21:01,842][05218] Updated weights for policy 0, policy_version 14712 (0.0009) -[2023-10-16 03:21:02,350][03835] Fps is (10 sec: 19661.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 30081024. Throughput: 0: 1783.6, 1: 1793.5. Samples: 7523044. Policy #0 lag: (min: 31.0, avg: 32.1, max: 53.0) -[2023-10-16 03:21:02,351][03835] Avg episode reward: [(0, '4.240'), (1, '3.900')] -[2023-10-16 03:21:05,025][05219] Updated weights for policy 1, policy_version 14660 (0.0008) -[2023-10-16 03:21:05,392][05219] Updated weights for policy 1, policy_version 14670 (0.0008) -[2023-10-16 03:21:05,550][05218] Updated weights for policy 0, policy_version 14722 (0.0008) -[2023-10-16 03:21:05,748][05219] Updated weights for policy 1, policy_version 14680 (0.0008) -[2023-10-16 03:21:05,914][05218] Updated weights for policy 0, policy_version 14732 (0.0010) -[2023-10-16 03:21:06,295][05218] Updated weights for policy 0, policy_version 14742 (0.0007) -[2023-10-16 03:21:06,664][05218] Updated weights for policy 0, policy_version 14752 (0.0008) -[2023-10-16 03:21:07,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 30146560. Throughput: 0: 1771.6, 1: 1780.3. Samples: 7544080. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-16 03:21:07,351][03835] Avg episode reward: [(0, '4.190'), (1, '3.880')] -[2023-10-16 03:21:09,619][05219] Updated weights for policy 1, policy_version 14690 (0.0008) -[2023-10-16 03:21:09,981][05219] Updated weights for policy 1, policy_version 14700 (0.0008) -[2023-10-16 03:21:10,356][05219] Updated weights for policy 1, policy_version 14710 (0.0007) -[2023-10-16 03:21:10,582][05218] Updated weights for policy 0, policy_version 14762 (0.0008) -[2023-10-16 03:21:10,718][05219] Updated weights for policy 1, policy_version 14720 (0.0010) -[2023-10-16 03:21:10,953][05218] Updated weights for policy 0, policy_version 14772 (0.0010) -[2023-10-16 03:21:11,334][05218] Updated weights for policy 0, policy_version 14782 (0.0010) -[2023-10-16 03:21:12,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 30212096. Throughput: 0: 1801.6, 1: 1796.9. Samples: 7555870. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-16 03:21:12,351][03835] Avg episode reward: [(0, '4.240'), (1, '4.130')] -[2023-10-16 03:21:14,457][05219] Updated weights for policy 1, policy_version 14730 (0.0007) -[2023-10-16 03:21:14,827][05219] Updated weights for policy 1, policy_version 14740 (0.0007) -[2023-10-16 03:21:15,108][05218] Updated weights for policy 0, policy_version 14792 (0.0009) -[2023-10-16 03:21:15,192][05219] Updated weights for policy 1, policy_version 14750 (0.0008) -[2023-10-16 03:21:15,480][05218] Updated weights for policy 0, policy_version 14802 (0.0008) -[2023-10-16 03:21:15,860][05218] Updated weights for policy 0, policy_version 14812 (0.0008) -[2023-10-16 03:21:17,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 30277632. Throughput: 0: 1778.1, 1: 1778.7. Samples: 7575994. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-16 03:21:17,351][03835] Avg episode reward: [(0, '4.110'), (1, '3.850')] -[2023-10-16 03:21:19,080][05219] Updated weights for policy 1, policy_version 14760 (0.0009) -[2023-10-16 03:21:19,433][05219] Updated weights for policy 1, policy_version 14770 (0.0008) -[2023-10-16 03:21:19,576][05218] Updated weights for policy 0, policy_version 14822 (0.0007) -[2023-10-16 03:21:19,800][05219] Updated weights for policy 1, policy_version 14780 (0.0007) -[2023-10-16 03:21:19,955][05218] Updated weights for policy 0, policy_version 14832 (0.0007) -[2023-10-16 03:21:20,321][05218] Updated weights for policy 0, policy_version 14842 (0.0008) -[2023-10-16 03:21:22,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 30343168. Throughput: 0: 1776.0, 1: 1784.2. Samples: 7598286. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:21:22,352][03835] Avg episode reward: [(0, '4.430'), (1, '4.020')] -[2023-10-16 03:21:23,493][05219] Updated weights for policy 1, policy_version 14790 (0.0008) -[2023-10-16 03:21:23,868][05219] Updated weights for policy 1, policy_version 14800 (0.0009) -[2023-10-16 03:21:24,133][05218] Updated weights for policy 0, policy_version 14852 (0.0008) -[2023-10-16 03:21:24,231][05219] Updated weights for policy 1, policy_version 14810 (0.0008) -[2023-10-16 03:21:24,501][05218] Updated weights for policy 0, policy_version 14862 (0.0008) -[2023-10-16 03:21:24,871][05218] Updated weights for policy 0, policy_version 14872 (0.0007) -[2023-10-16 03:21:27,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 30408704. Throughput: 0: 1777.0, 1: 1779.7. Samples: 7607976. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:21:27,351][03835] Avg episode reward: [(0, '4.430'), (1, '3.900')] -[2023-10-16 03:21:28,039][05219] Updated weights for policy 1, policy_version 14820 (0.0007) -[2023-10-16 03:21:28,408][05219] Updated weights for policy 1, policy_version 14830 (0.0007) -[2023-10-16 03:21:28,574][05218] Updated weights for policy 0, policy_version 14882 (0.0009) -[2023-10-16 03:21:28,763][05219] Updated weights for policy 1, policy_version 14840 (0.0007) -[2023-10-16 03:21:28,964][05218] Updated weights for policy 0, policy_version 14892 (0.0010) -[2023-10-16 03:21:29,328][05218] Updated weights for policy 0, policy_version 14902 (0.0010) -[2023-10-16 03:21:29,711][05218] Updated weights for policy 0, policy_version 14912 (0.0008) -[2023-10-16 03:21:32,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.6, 300 sec: 14218.0). Total num frames: 30474240. Throughput: 0: 1782.9, 1: 1780.1. Samples: 7630520. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:21:32,351][03835] Avg episode reward: [(0, '4.410'), (1, '4.180')] -[2023-10-16 03:21:32,581][05219] Updated weights for policy 1, policy_version 14850 (0.0008) -[2023-10-16 03:21:32,988][05219] Updated weights for policy 1, policy_version 14860 (0.0007) -[2023-10-16 03:21:33,339][05219] Updated weights for policy 1, policy_version 14870 (0.0008) -[2023-10-16 03:21:33,392][05218] Updated weights for policy 0, policy_version 14922 (0.0008) -[2023-10-16 03:21:33,702][05219] Updated weights for policy 1, policy_version 14880 (0.0007) -[2023-10-16 03:21:33,775][05218] Updated weights for policy 0, policy_version 14932 (0.0007) -[2023-10-16 03:21:34,154][05218] Updated weights for policy 0, policy_version 14942 (0.0011) -[2023-10-16 03:21:37,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 30539776. Throughput: 0: 1802.0, 1: 1806.2. Samples: 7652986. Policy #0 lag: (min: 5.0, avg: 8.2, max: 37.0) -[2023-10-16 03:21:37,351][03835] Avg episode reward: [(0, '4.360'), (1, '4.360')] -[2023-10-16 03:21:37,364][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000014944_15302656.pth... -[2023-10-16 03:21:37,397][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000013280_13598720.pth -[2023-10-16 03:21:37,565][05219] Updated weights for policy 1, policy_version 14890 (0.0008) -[2023-10-16 03:21:37,837][05218] Updated weights for policy 0, policy_version 14952 (0.0009) -[2023-10-16 03:21:37,928][05219] Updated weights for policy 1, policy_version 14900 (0.0007) -[2023-10-16 03:21:38,209][05218] Updated weights for policy 0, policy_version 14962 (0.0010) -[2023-10-16 03:21:38,286][05219] Updated weights for policy 1, policy_version 14910 (0.0008) -[2023-10-16 03:21:38,356][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000014912_15269888.pth... -[2023-10-16 03:21:38,393][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000013216_13533184.pth -[2023-10-16 03:21:38,399][04891] Saving new best policy, reward=4.360! -[2023-10-16 03:21:38,582][05218] Updated weights for policy 0, policy_version 14972 (0.0009) -[2023-10-16 03:21:42,020][05219] Updated weights for policy 1, policy_version 14920 (0.0010) -[2023-10-16 03:21:42,319][05218] Updated weights for policy 0, policy_version 14982 (0.0009) -[2023-10-16 03:21:42,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 30605312. Throughput: 0: 1788.0, 1: 1780.8. Samples: 7662654. Policy #0 lag: (min: 5.0, avg: 8.2, max: 37.0) -[2023-10-16 03:21:42,351][03835] Avg episode reward: [(0, '4.450'), (1, '4.490')] -[2023-10-16 03:21:42,391][05219] Updated weights for policy 1, policy_version 14930 (0.0008) -[2023-10-16 03:21:42,689][05218] Updated weights for policy 0, policy_version 14992 (0.0007) -[2023-10-16 03:21:42,756][05219] Updated weights for policy 1, policy_version 14940 (0.0009) -[2023-10-16 03:21:42,901][04891] Saving new best policy, reward=4.490! -[2023-10-16 03:21:43,062][05218] Updated weights for policy 0, policy_version 15002 (0.0008) -[2023-10-16 03:21:46,720][05219] Updated weights for policy 1, policy_version 14950 (0.0008) -[2023-10-16 03:21:46,902][05218] Updated weights for policy 0, policy_version 15012 (0.0009) -[2023-10-16 03:21:47,088][05219] Updated weights for policy 1, policy_version 14960 (0.0008) -[2023-10-16 03:21:47,282][05218] Updated weights for policy 0, policy_version 15022 (0.0008) -[2023-10-16 03:21:47,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 30670848. Throughput: 0: 1794.8, 1: 1793.5. Samples: 7684516. Policy #0 lag: (min: 5.0, avg: 8.2, max: 37.0) -[2023-10-16 03:21:47,351][03835] Avg episode reward: [(0, '4.410'), (1, '4.650')] -[2023-10-16 03:21:47,450][05219] Updated weights for policy 1, policy_version 14970 (0.0007) -[2023-10-16 03:21:47,650][05218] Updated weights for policy 0, policy_version 15032 (0.0008) -[2023-10-16 03:21:47,666][04891] Saving new best policy, reward=4.650! -[2023-10-16 03:21:51,133][05219] Updated weights for policy 1, policy_version 14980 (0.0007) -[2023-10-16 03:21:51,339][05218] Updated weights for policy 0, policy_version 15042 (0.0009) -[2023-10-16 03:21:51,499][05219] Updated weights for policy 1, policy_version 14990 (0.0007) -[2023-10-16 03:21:51,717][05218] Updated weights for policy 0, policy_version 15052 (0.0007) -[2023-10-16 03:21:51,854][05219] Updated weights for policy 1, policy_version 15000 (0.0008) -[2023-10-16 03:21:52,088][05218] Updated weights for policy 0, policy_version 15062 (0.0007) -[2023-10-16 03:21:52,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 30769152. Throughput: 0: 1788.1, 1: 1776.8. Samples: 7704502. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:21:52,351][03835] Avg episode reward: [(0, '4.290'), (1, '4.070')] -[2023-10-16 03:21:52,462][05218] Updated weights for policy 0, policy_version 15072 (0.0008) -[2023-10-16 03:21:55,597][05219] Updated weights for policy 1, policy_version 15010 (0.0008) -[2023-10-16 03:21:55,969][05219] Updated weights for policy 1, policy_version 15020 (0.0007) -[2023-10-16 03:21:56,003][05218] Updated weights for policy 0, policy_version 15082 (0.0008) -[2023-10-16 03:21:56,326][05219] Updated weights for policy 1, policy_version 15030 (0.0009) -[2023-10-16 03:21:56,385][05218] Updated weights for policy 0, policy_version 15092 (0.0009) -[2023-10-16 03:21:56,688][05219] Updated weights for policy 1, policy_version 15040 (0.0008) -[2023-10-16 03:21:56,755][05218] Updated weights for policy 0, policy_version 15102 (0.0007) -[2023-10-16 03:21:57,350][03835] Fps is (10 sec: 19660.2, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 30867456. Throughput: 0: 1794.8, 1: 1787.9. Samples: 7717096. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:21:57,351][03835] Avg episode reward: [(0, '4.440'), (1, '4.090')] -[2023-10-16 03:22:00,500][05219] Updated weights for policy 1, policy_version 15050 (0.0007) -[2023-10-16 03:22:00,626][05218] Updated weights for policy 0, policy_version 15112 (0.0009) -[2023-10-16 03:22:00,860][05219] Updated weights for policy 1, policy_version 15060 (0.0007) -[2023-10-16 03:22:00,992][05218] Updated weights for policy 0, policy_version 15122 (0.0008) -[2023-10-16 03:22:01,224][05219] Updated weights for policy 1, policy_version 15070 (0.0008) -[2023-10-16 03:22:01,367][05218] Updated weights for policy 0, policy_version 15132 (0.0007) -[2023-10-16 03:22:02,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 30932992. Throughput: 0: 1796.7, 1: 1778.1. Samples: 7736860. Policy #0 lag: (min: 24.0, avg: 47.0, max: 56.0) -[2023-10-16 03:22:02,352][03835] Avg episode reward: [(0, '4.380'), (1, '3.830')] -[2023-10-16 03:22:05,045][05219] Updated weights for policy 1, policy_version 15080 (0.0007) -[2023-10-16 03:22:05,152][05218] Updated weights for policy 0, policy_version 15142 (0.0007) -[2023-10-16 03:22:05,404][05219] Updated weights for policy 1, policy_version 15090 (0.0009) -[2023-10-16 03:22:05,529][05218] Updated weights for policy 0, policy_version 15152 (0.0009) -[2023-10-16 03:22:05,770][05219] Updated weights for policy 1, policy_version 15100 (0.0009) -[2023-10-16 03:22:05,914][05218] Updated weights for policy 0, policy_version 15162 (0.0008) -[2023-10-16 03:22:07,351][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 30998528. Throughput: 0: 1791.7, 1: 1766.1. Samples: 7758386. Policy #0 lag: (min: 24.0, avg: 47.0, max: 56.0) -[2023-10-16 03:22:07,352][03835] Avg episode reward: [(0, '4.380'), (1, '4.250')] -[2023-10-16 03:22:09,696][05219] Updated weights for policy 1, policy_version 15110 (0.0008) -[2023-10-16 03:22:09,768][05218] Updated weights for policy 0, policy_version 15172 (0.0008) -[2023-10-16 03:22:10,050][05219] Updated weights for policy 1, policy_version 15120 (0.0007) -[2023-10-16 03:22:10,145][05218] Updated weights for policy 0, policy_version 15182 (0.0008) -[2023-10-16 03:22:10,419][05219] Updated weights for policy 1, policy_version 15130 (0.0007) -[2023-10-16 03:22:10,524][05218] Updated weights for policy 0, policy_version 15192 (0.0008) -[2023-10-16 03:22:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 31064064. Throughput: 0: 1801.9, 1: 1780.9. Samples: 7769206. Policy #0 lag: (min: 24.0, avg: 47.0, max: 56.0) -[2023-10-16 03:22:12,351][03835] Avg episode reward: [(0, '3.900'), (1, '4.550')] -[2023-10-16 03:22:14,257][05219] Updated weights for policy 1, policy_version 15140 (0.0008) -[2023-10-16 03:22:14,401][05218] Updated weights for policy 0, policy_version 15202 (0.0009) -[2023-10-16 03:22:14,628][05219] Updated weights for policy 1, policy_version 15150 (0.0009) -[2023-10-16 03:22:14,776][05218] Updated weights for policy 0, policy_version 15212 (0.0007) -[2023-10-16 03:22:14,991][05219] Updated weights for policy 1, policy_version 15160 (0.0008) -[2023-10-16 03:22:15,154][05218] Updated weights for policy 0, policy_version 15222 (0.0008) -[2023-10-16 03:22:15,525][05218] Updated weights for policy 0, policy_version 15232 (0.0010) -[2023-10-16 03:22:17,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 31129600. Throughput: 0: 1782.9, 1: 1757.1. Samples: 7789820. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-16 03:22:17,351][03835] Avg episode reward: [(0, '3.950'), (1, '4.310')] -[2023-10-16 03:22:18,951][05219] Updated weights for policy 1, policy_version 15170 (0.0009) -[2023-10-16 03:22:19,140][05218] Updated weights for policy 0, policy_version 15242 (0.0007) -[2023-10-16 03:22:19,352][05219] Updated weights for policy 1, policy_version 15180 (0.0007) -[2023-10-16 03:22:19,505][05218] Updated weights for policy 0, policy_version 15252 (0.0008) -[2023-10-16 03:22:19,715][05219] Updated weights for policy 1, policy_version 15190 (0.0008) -[2023-10-16 03:22:19,882][05218] Updated weights for policy 0, policy_version 15262 (0.0008) -[2023-10-16 03:22:20,084][05219] Updated weights for policy 1, policy_version 15200 (0.0008) -[2023-10-16 03:22:22,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 31195136. Throughput: 0: 1774.0, 1: 1754.3. Samples: 7811762. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-16 03:22:22,352][03835] Avg episode reward: [(0, '4.320'), (1, '3.910')] -[2023-10-16 03:22:23,772][05218] Updated weights for policy 0, policy_version 15272 (0.0009) -[2023-10-16 03:22:23,931][05219] Updated weights for policy 1, policy_version 15210 (0.0009) -[2023-10-16 03:22:24,142][05218] Updated weights for policy 0, policy_version 15282 (0.0008) -[2023-10-16 03:22:24,300][05219] Updated weights for policy 1, policy_version 15220 (0.0008) -[2023-10-16 03:22:24,517][05218] Updated weights for policy 0, policy_version 15292 (0.0008) -[2023-10-16 03:22:24,674][05219] Updated weights for policy 1, policy_version 15230 (0.0008) -[2023-10-16 03:22:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 31260672. Throughput: 0: 1773.9, 1: 1755.0. Samples: 7821456. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-16 03:22:27,351][03835] Avg episode reward: [(0, '4.710'), (1, '3.770')] -[2023-10-16 03:22:27,352][04766] Saving new best policy, reward=4.710! -[2023-10-16 03:22:28,220][05218] Updated weights for policy 0, policy_version 15302 (0.0008) -[2023-10-16 03:22:28,529][05219] Updated weights for policy 1, policy_version 15240 (0.0008) -[2023-10-16 03:22:28,589][05218] Updated weights for policy 0, policy_version 15312 (0.0007) -[2023-10-16 03:22:28,893][05219] Updated weights for policy 1, policy_version 15250 (0.0008) -[2023-10-16 03:22:28,963][05218] Updated weights for policy 0, policy_version 15322 (0.0007) -[2023-10-16 03:22:29,253][05219] Updated weights for policy 1, policy_version 15260 (0.0009) -[2023-10-16 03:22:32,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 31326208. Throughput: 0: 1778.8, 1: 1760.2. Samples: 7843772. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:22:32,351][03835] Avg episode reward: [(0, '4.680'), (1, '4.020')] -[2023-10-16 03:22:32,754][05218] Updated weights for policy 0, policy_version 15332 (0.0007) -[2023-10-16 03:22:32,963][05219] Updated weights for policy 1, policy_version 15270 (0.0008) -[2023-10-16 03:22:33,133][05218] Updated weights for policy 0, policy_version 15342 (0.0008) -[2023-10-16 03:22:33,337][05219] Updated weights for policy 1, policy_version 15280 (0.0008) -[2023-10-16 03:22:33,496][05218] Updated weights for policy 0, policy_version 15352 (0.0008) -[2023-10-16 03:22:33,689][05219] Updated weights for policy 1, policy_version 15290 (0.0009) -[2023-10-16 03:22:37,325][05218] Updated weights for policy 0, policy_version 15362 (0.0007) -[2023-10-16 03:22:37,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 31391744. Throughput: 0: 1795.4, 1: 1785.6. Samples: 7865648. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:22:37,352][03835] Avg episode reward: [(0, '4.740'), (1, '4.340')] -[2023-10-16 03:22:37,554][05219] Updated weights for policy 1, policy_version 15300 (0.0007) -[2023-10-16 03:22:37,695][05218] Updated weights for policy 0, policy_version 15372 (0.0009) -[2023-10-16 03:22:37,913][05219] Updated weights for policy 1, policy_version 15310 (0.0008) -[2023-10-16 03:22:38,082][05218] Updated weights for policy 0, policy_version 15382 (0.0009) -[2023-10-16 03:22:38,270][05219] Updated weights for policy 1, policy_version 15320 (0.0007) -[2023-10-16 03:22:38,446][04766] Saving new best policy, reward=4.740! -[2023-10-16 03:22:38,451][05218] Updated weights for policy 0, policy_version 15392 (0.0008) -[2023-10-16 03:22:42,186][05219] Updated weights for policy 1, policy_version 15330 (0.0009) -[2023-10-16 03:22:42,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 31457280. Throughput: 0: 1758.5, 1: 1751.4. Samples: 7875044. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:22:42,350][05218] Updated weights for policy 0, policy_version 15402 (0.0009) -[2023-10-16 03:22:42,351][03835] Avg episode reward: [(0, '4.350'), (1, '4.370')] -[2023-10-16 03:22:42,550][05219] Updated weights for policy 1, policy_version 15340 (0.0009) -[2023-10-16 03:22:42,729][05218] Updated weights for policy 0, policy_version 15412 (0.0008) -[2023-10-16 03:22:42,918][05219] Updated weights for policy 1, policy_version 15350 (0.0007) -[2023-10-16 03:22:43,109][05218] Updated weights for policy 0, policy_version 15422 (0.0007) -[2023-10-16 03:22:43,279][05219] Updated weights for policy 1, policy_version 15360 (0.0007) -[2023-10-16 03:22:47,028][05219] Updated weights for policy 1, policy_version 15370 (0.0009) -[2023-10-16 03:22:47,079][05218] Updated weights for policy 0, policy_version 15432 (0.0009) -[2023-10-16 03:22:47,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 31522816. Throughput: 0: 1783.2, 1: 1778.1. Samples: 7897120. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:22:47,351][03835] Avg episode reward: [(0, '4.100'), (1, '4.390')] -[2023-10-16 03:22:47,396][05219] Updated weights for policy 1, policy_version 15380 (0.0009) -[2023-10-16 03:22:47,453][05218] Updated weights for policy 0, policy_version 15442 (0.0009) -[2023-10-16 03:22:47,758][05219] Updated weights for policy 1, policy_version 15390 (0.0009) -[2023-10-16 03:22:47,826][05218] Updated weights for policy 0, policy_version 15452 (0.0009) -[2023-10-16 03:22:51,583][05219] Updated weights for policy 1, policy_version 15400 (0.0009) -[2023-10-16 03:22:51,591][05218] Updated weights for policy 0, policy_version 15462 (0.0009) -[2023-10-16 03:22:51,942][05219] Updated weights for policy 1, policy_version 15410 (0.0009) -[2023-10-16 03:22:51,966][05218] Updated weights for policy 0, policy_version 15472 (0.0007) -[2023-10-16 03:22:52,313][05219] Updated weights for policy 1, policy_version 15420 (0.0008) -[2023-10-16 03:22:52,348][05218] Updated weights for policy 0, policy_version 15482 (0.0008) -[2023-10-16 03:22:52,350][03835] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 31588352. Throughput: 0: 1759.1, 1: 1763.4. Samples: 7916898. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:22:52,351][03835] Avg episode reward: [(0, '4.110'), (1, '4.400')] -[2023-10-16 03:22:56,102][05218] Updated weights for policy 0, policy_version 15492 (0.0011) -[2023-10-16 03:22:56,160][05219] Updated weights for policy 1, policy_version 15430 (0.0008) -[2023-10-16 03:22:56,481][05218] Updated weights for policy 0, policy_version 15502 (0.0008) -[2023-10-16 03:22:56,525][05219] Updated weights for policy 1, policy_version 15440 (0.0008) -[2023-10-16 03:22:56,869][05218] Updated weights for policy 0, policy_version 15512 (0.0008) -[2023-10-16 03:22:56,894][05219] Updated weights for policy 1, policy_version 15450 (0.0008) -[2023-10-16 03:22:57,351][03835] Fps is (10 sec: 19660.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 31719424. Throughput: 0: 1769.4, 1: 1770.0. Samples: 7928478. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:22:57,352][03835] Avg episode reward: [(0, '4.250'), (1, '4.120')] -[2023-10-16 03:23:00,638][05218] Updated weights for policy 0, policy_version 15522 (0.0009) -[2023-10-16 03:23:00,709][05219] Updated weights for policy 1, policy_version 15460 (0.0007) -[2023-10-16 03:23:01,015][05218] Updated weights for policy 0, policy_version 15532 (0.0010) -[2023-10-16 03:23:01,069][05219] Updated weights for policy 1, policy_version 15470 (0.0007) -[2023-10-16 03:23:01,385][05218] Updated weights for policy 0, policy_version 15542 (0.0009) -[2023-10-16 03:23:01,430][05219] Updated weights for policy 1, policy_version 15480 (0.0008) -[2023-10-16 03:23:01,761][05218] Updated weights for policy 0, policy_version 15552 (0.0009) -[2023-10-16 03:23:02,350][03835] Fps is (10 sec: 19661.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 31784960. Throughput: 0: 1763.6, 1: 1776.1. Samples: 7949110. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:23:02,351][03835] Avg episode reward: [(0, '4.550'), (1, '3.920')] -[2023-10-16 03:23:05,486][05219] Updated weights for policy 1, policy_version 15490 (0.0008) -[2023-10-16 03:23:05,708][05218] Updated weights for policy 0, policy_version 15562 (0.0009) -[2023-10-16 03:23:05,854][05219] Updated weights for policy 1, policy_version 15500 (0.0007) -[2023-10-16 03:23:06,074][05218] Updated weights for policy 0, policy_version 15572 (0.0009) -[2023-10-16 03:23:06,209][05219] Updated weights for policy 1, policy_version 15510 (0.0008) -[2023-10-16 03:23:06,455][05218] Updated weights for policy 0, policy_version 15582 (0.0007) -[2023-10-16 03:23:06,576][05219] Updated weights for policy 1, policy_version 15520 (0.0007) -[2023-10-16 03:23:07,351][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 31850496. Throughput: 0: 1749.5, 1: 1760.6. Samples: 7969716. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:23:07,352][03835] Avg episode reward: [(0, '4.250'), (1, '4.060')] -[2023-10-16 03:23:10,191][05218] Updated weights for policy 0, policy_version 15592 (0.0009) -[2023-10-16 03:23:10,327][05219] Updated weights for policy 1, policy_version 15530 (0.0007) -[2023-10-16 03:23:10,571][05218] Updated weights for policy 0, policy_version 15602 (0.0010) -[2023-10-16 03:23:10,692][05219] Updated weights for policy 1, policy_version 15540 (0.0008) -[2023-10-16 03:23:10,945][05218] Updated weights for policy 0, policy_version 15612 (0.0008) -[2023-10-16 03:23:11,057][05219] Updated weights for policy 1, policy_version 15550 (0.0008) -[2023-10-16 03:23:12,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 31916032. Throughput: 0: 1774.4, 1: 1789.7. Samples: 7981844. Policy #0 lag: (min: 21.0, avg: 22.4, max: 46.0) -[2023-10-16 03:23:12,352][03835] Avg episode reward: [(0, '4.380'), (1, '4.450')] -[2023-10-16 03:23:14,800][05219] Updated weights for policy 1, policy_version 15560 (0.0010) -[2023-10-16 03:23:14,978][05218] Updated weights for policy 0, policy_version 15622 (0.0008) -[2023-10-16 03:23:15,174][05219] Updated weights for policy 1, policy_version 15570 (0.0008) -[2023-10-16 03:23:15,352][05218] Updated weights for policy 0, policy_version 15632 (0.0008) -[2023-10-16 03:23:15,536][05219] Updated weights for policy 1, policy_version 15580 (0.0007) -[2023-10-16 03:23:15,725][05218] Updated weights for policy 0, policy_version 15642 (0.0009) -[2023-10-16 03:23:17,350][03835] Fps is (10 sec: 13107.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 31981568. Throughput: 0: 1744.8, 1: 1761.0. Samples: 8001532. Policy #0 lag: (min: 21.0, avg: 22.4, max: 46.0) -[2023-10-16 03:23:17,351][03835] Avg episode reward: [(0, '4.250'), (1, '4.540')] -[2023-10-16 03:23:19,314][05218] Updated weights for policy 0, policy_version 15652 (0.0010) -[2023-10-16 03:23:19,365][05219] Updated weights for policy 1, policy_version 15590 (0.0010) -[2023-10-16 03:23:19,689][05218] Updated weights for policy 0, policy_version 15662 (0.0008) -[2023-10-16 03:23:19,741][05219] Updated weights for policy 1, policy_version 15600 (0.0008) -[2023-10-16 03:23:20,070][05218] Updated weights for policy 0, policy_version 15672 (0.0008) -[2023-10-16 03:23:20,112][05219] Updated weights for policy 1, policy_version 15610 (0.0007) -[2023-10-16 03:23:22,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 32047104. Throughput: 0: 1757.0, 1: 1755.0. Samples: 8023686. Policy #0 lag: (min: 21.0, avg: 22.4, max: 46.0) -[2023-10-16 03:23:22,351][03835] Avg episode reward: [(0, '4.670'), (1, '4.260')] -[2023-10-16 03:23:23,752][05218] Updated weights for policy 0, policy_version 15682 (0.0010) -[2023-10-16 03:23:24,003][05219] Updated weights for policy 1, policy_version 15620 (0.0009) -[2023-10-16 03:23:24,121][05218] Updated weights for policy 0, policy_version 15692 (0.0008) -[2023-10-16 03:23:24,368][05219] Updated weights for policy 1, policy_version 15630 (0.0009) -[2023-10-16 03:23:24,484][05218] Updated weights for policy 0, policy_version 15702 (0.0010) -[2023-10-16 03:23:24,724][05219] Updated weights for policy 1, policy_version 15640 (0.0007) -[2023-10-16 03:23:24,856][05218] Updated weights for policy 0, policy_version 15712 (0.0008) -[2023-10-16 03:23:27,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 32112640. Throughput: 0: 1761.6, 1: 1758.3. Samples: 8033442. Policy #0 lag: (min: 1.0, avg: 10.3, max: 33.0) -[2023-10-16 03:23:27,351][03835] Avg episode reward: [(0, '4.970'), (1, '4.450')] -[2023-10-16 03:23:27,353][04766] Saving new best policy, reward=4.970! -[2023-10-16 03:23:28,564][05219] Updated weights for policy 1, policy_version 15650 (0.0007) -[2023-10-16 03:23:28,628][05218] Updated weights for policy 0, policy_version 15722 (0.0008) -[2023-10-16 03:23:28,923][05219] Updated weights for policy 1, policy_version 15660 (0.0009) -[2023-10-16 03:23:28,996][05218] Updated weights for policy 0, policy_version 15732 (0.0008) -[2023-10-16 03:23:29,285][05219] Updated weights for policy 1, policy_version 15670 (0.0007) -[2023-10-16 03:23:29,375][05218] Updated weights for policy 0, policy_version 15742 (0.0010) -[2023-10-16 03:23:29,658][05219] Updated weights for policy 1, policy_version 15680 (0.0009) -[2023-10-16 03:23:32,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 32178176. Throughput: 0: 1766.4, 1: 1760.3. Samples: 8055824. Policy #0 lag: (min: 1.0, avg: 10.3, max: 33.0) -[2023-10-16 03:23:32,351][03835] Avg episode reward: [(0, '4.650'), (1, '4.250')] -[2023-10-16 03:23:33,341][05218] Updated weights for policy 0, policy_version 15752 (0.0009) -[2023-10-16 03:23:33,372][05219] Updated weights for policy 1, policy_version 15690 (0.0007) -[2023-10-16 03:23:33,714][05218] Updated weights for policy 0, policy_version 15762 (0.0008) -[2023-10-16 03:23:33,744][05219] Updated weights for policy 1, policy_version 15700 (0.0007) -[2023-10-16 03:23:34,084][05218] Updated weights for policy 0, policy_version 15772 (0.0009) -[2023-10-16 03:23:34,100][05219] Updated weights for policy 1, policy_version 15710 (0.0008) -[2023-10-16 03:23:37,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 32243712. Throughput: 0: 1794.4, 1: 1785.2. Samples: 8077980. Policy #0 lag: (min: 1.0, avg: 10.3, max: 33.0) -[2023-10-16 03:23:37,351][03835] Avg episode reward: [(0, '4.420'), (1, '4.200')] -[2023-10-16 03:23:37,364][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000015776_16154624.pth... -[2023-10-16 03:23:37,364][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000015712_16089088.pth... -[2023-10-16 03:23:37,393][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000014112_14450688.pth -[2023-10-16 03:23:37,403][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000014048_14385152.pth -[2023-10-16 03:23:37,788][05219] Updated weights for policy 1, policy_version 15720 (0.0007) -[2023-10-16 03:23:37,864][05218] Updated weights for policy 0, policy_version 15782 (0.0009) -[2023-10-16 03:23:38,154][05219] Updated weights for policy 1, policy_version 15730 (0.0008) -[2023-10-16 03:23:38,234][05218] Updated weights for policy 0, policy_version 15792 (0.0007) -[2023-10-16 03:23:38,520][05219] Updated weights for policy 1, policy_version 15740 (0.0008) -[2023-10-16 03:23:38,606][05218] Updated weights for policy 0, policy_version 15802 (0.0007) -[2023-10-16 03:23:42,318][05219] Updated weights for policy 1, policy_version 15750 (0.0010) -[2023-10-16 03:23:42,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 32309248. Throughput: 0: 1771.7, 1: 1762.5. Samples: 8087516. Policy #0 lag: (min: 2.0, avg: 2.6, max: 19.0) -[2023-10-16 03:23:42,351][03835] Avg episode reward: [(0, '4.250'), (1, '4.550')] -[2023-10-16 03:23:42,370][05218] Updated weights for policy 0, policy_version 15812 (0.0007) -[2023-10-16 03:23:42,677][05219] Updated weights for policy 1, policy_version 15760 (0.0008) -[2023-10-16 03:23:42,737][05218] Updated weights for policy 0, policy_version 15822 (0.0009) -[2023-10-16 03:23:43,039][05219] Updated weights for policy 1, policy_version 15770 (0.0007) -[2023-10-16 03:23:43,115][05218] Updated weights for policy 0, policy_version 15832 (0.0009) -[2023-10-16 03:23:46,935][05218] Updated weights for policy 0, policy_version 15842 (0.0010) -[2023-10-16 03:23:46,964][05219] Updated weights for policy 1, policy_version 15780 (0.0008) -[2023-10-16 03:23:47,316][05218] Updated weights for policy 0, policy_version 15852 (0.0009) -[2023-10-16 03:23:47,323][05219] Updated weights for policy 1, policy_version 15790 (0.0007) -[2023-10-16 03:23:47,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 32374784. Throughput: 0: 1794.4, 1: 1775.6. Samples: 8109760. Policy #0 lag: (min: 2.0, avg: 2.6, max: 19.0) -[2023-10-16 03:23:47,351][03835] Avg episode reward: [(0, '4.630'), (1, '4.930')] -[2023-10-16 03:23:47,684][05219] Updated weights for policy 1, policy_version 15800 (0.0009) -[2023-10-16 03:23:47,691][05218] Updated weights for policy 0, policy_version 15862 (0.0009) -[2023-10-16 03:23:47,977][04891] Saving new best policy, reward=4.930! -[2023-10-16 03:23:48,070][05218] Updated weights for policy 0, policy_version 15872 (0.0010) -[2023-10-16 03:23:51,712][05219] Updated weights for policy 1, policy_version 15810 (0.0009) -[2023-10-16 03:23:51,818][05218] Updated weights for policy 0, policy_version 15882 (0.0008) -[2023-10-16 03:23:52,092][05219] Updated weights for policy 1, policy_version 15820 (0.0008) -[2023-10-16 03:23:52,186][05218] Updated weights for policy 0, policy_version 15892 (0.0009) -[2023-10-16 03:23:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 32440320. Throughput: 0: 1783.7, 1: 1779.3. Samples: 8130046. Policy #0 lag: (min: 2.0, avg: 2.6, max: 19.0) -[2023-10-16 03:23:52,351][03835] Avg episode reward: [(0, '4.660'), (1, '4.600')] -[2023-10-16 03:23:52,456][05219] Updated weights for policy 1, policy_version 15830 (0.0008) -[2023-10-16 03:23:52,556][05218] Updated weights for policy 0, policy_version 15902 (0.0008) -[2023-10-16 03:23:52,820][05219] Updated weights for policy 1, policy_version 15840 (0.0007) -[2023-10-16 03:23:56,283][05218] Updated weights for policy 0, policy_version 15912 (0.0008) -[2023-10-16 03:23:56,529][05219] Updated weights for policy 1, policy_version 15850 (0.0007) -[2023-10-16 03:23:56,664][05218] Updated weights for policy 0, policy_version 15922 (0.0009) -[2023-10-16 03:23:56,891][05219] Updated weights for policy 1, policy_version 15860 (0.0007) -[2023-10-16 03:23:57,032][05218] Updated weights for policy 0, policy_version 15932 (0.0007) -[2023-10-16 03:23:57,263][05219] Updated weights for policy 1, policy_version 15870 (0.0008) -[2023-10-16 03:23:57,350][03835] Fps is (10 sec: 19661.0, 60 sec: 14199.6, 300 sec: 14218.0). Total num frames: 32571392. Throughput: 0: 1786.2, 1: 1762.0. Samples: 8141512. Policy #0 lag: (min: 0.0, avg: 28.4, max: 32.0) -[2023-10-16 03:23:57,351][03835] Avg episode reward: [(0, '4.410'), (1, '4.730')] -[2023-10-16 03:24:00,642][05218] Updated weights for policy 0, policy_version 15942 (0.0008) -[2023-10-16 03:24:01,011][05218] Updated weights for policy 0, policy_version 15952 (0.0008) -[2023-10-16 03:24:01,016][05219] Updated weights for policy 1, policy_version 15880 (0.0007) -[2023-10-16 03:24:01,384][05219] Updated weights for policy 1, policy_version 15890 (0.0008) -[2023-10-16 03:24:01,389][05218] Updated weights for policy 0, policy_version 15962 (0.0007) -[2023-10-16 03:24:01,754][05219] Updated weights for policy 1, policy_version 15900 (0.0008) -[2023-10-16 03:24:02,350][03835] Fps is (10 sec: 19660.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 32636928. Throughput: 0: 1795.9, 1: 1782.3. Samples: 8162552. Policy #0 lag: (min: 0.0, avg: 28.4, max: 32.0) -[2023-10-16 03:24:02,351][03835] Avg episode reward: [(0, '4.860'), (1, '4.410')] -[2023-10-16 03:24:05,344][05218] Updated weights for policy 0, policy_version 15972 (0.0009) -[2023-10-16 03:24:05,528][05219] Updated weights for policy 1, policy_version 15910 (0.0008) -[2023-10-16 03:24:05,722][05218] Updated weights for policy 0, policy_version 15982 (0.0008) -[2023-10-16 03:24:05,891][05219] Updated weights for policy 1, policy_version 15920 (0.0007) -[2023-10-16 03:24:06,095][05218] Updated weights for policy 0, policy_version 15992 (0.0007) -[2023-10-16 03:24:06,262][05219] Updated weights for policy 1, policy_version 15930 (0.0008) -[2023-10-16 03:24:07,351][03835] Fps is (10 sec: 13106.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 32702464. Throughput: 0: 1777.4, 1: 1766.5. Samples: 8183162. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:24:07,352][03835] Avg episode reward: [(0, '4.420'), (1, '4.100')] -[2023-10-16 03:24:10,007][05218] Updated weights for policy 0, policy_version 16002 (0.0008) -[2023-10-16 03:24:10,063][05219] Updated weights for policy 1, policy_version 15940 (0.0007) -[2023-10-16 03:24:10,377][05218] Updated weights for policy 0, policy_version 16012 (0.0007) -[2023-10-16 03:24:10,424][05219] Updated weights for policy 1, policy_version 15950 (0.0009) -[2023-10-16 03:24:10,756][05218] Updated weights for policy 0, policy_version 16022 (0.0008) -[2023-10-16 03:24:10,787][05219] Updated weights for policy 1, policy_version 15960 (0.0010) -[2023-10-16 03:24:11,128][05218] Updated weights for policy 0, policy_version 16032 (0.0009) -[2023-10-16 03:24:12,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 32768000. Throughput: 0: 1791.1, 1: 1792.8. Samples: 8194718. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:24:12,351][03835] Avg episode reward: [(0, '4.660'), (1, '4.170')] -[2023-10-16 03:24:14,573][05219] Updated weights for policy 1, policy_version 15970 (0.0007) -[2023-10-16 03:24:14,829][05218] Updated weights for policy 0, policy_version 16042 (0.0007) -[2023-10-16 03:24:14,942][05219] Updated weights for policy 1, policy_version 15980 (0.0008) -[2023-10-16 03:24:15,206][05218] Updated weights for policy 0, policy_version 16052 (0.0008) -[2023-10-16 03:24:15,314][05219] Updated weights for policy 1, policy_version 15990 (0.0008) -[2023-10-16 03:24:15,582][05218] Updated weights for policy 0, policy_version 16062 (0.0007) -[2023-10-16 03:24:15,676][05219] Updated weights for policy 1, policy_version 16000 (0.0010) -[2023-10-16 03:24:17,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 32833536. Throughput: 0: 1768.0, 1: 1764.9. Samples: 8214806. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:24:17,352][03835] Avg episode reward: [(0, '4.870'), (1, '4.190')] -[2023-10-16 03:24:19,395][05218] Updated weights for policy 0, policy_version 16072 (0.0009) -[2023-10-16 03:24:19,489][05219] Updated weights for policy 1, policy_version 16010 (0.0007) -[2023-10-16 03:24:19,758][05218] Updated weights for policy 0, policy_version 16082 (0.0008) -[2023-10-16 03:24:19,849][05219] Updated weights for policy 1, policy_version 16020 (0.0007) -[2023-10-16 03:24:20,129][05218] Updated weights for policy 0, policy_version 16092 (0.0008) -[2023-10-16 03:24:20,221][05219] Updated weights for policy 1, policy_version 16030 (0.0009) -[2023-10-16 03:24:22,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 32899072. Throughput: 0: 1774.1, 1: 1761.2. Samples: 8237066. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:24:22,352][03835] Avg episode reward: [(0, '4.910'), (1, '4.520')] -[2023-10-16 03:24:23,884][05218] Updated weights for policy 0, policy_version 16102 (0.0008) -[2023-10-16 03:24:24,090][05219] Updated weights for policy 1, policy_version 16040 (0.0008) -[2023-10-16 03:24:24,260][05218] Updated weights for policy 0, policy_version 16112 (0.0008) -[2023-10-16 03:24:24,448][05219] Updated weights for policy 1, policy_version 16050 (0.0009) -[2023-10-16 03:24:24,622][05218] Updated weights for policy 0, policy_version 16122 (0.0008) -[2023-10-16 03:24:24,812][05219] Updated weights for policy 1, policy_version 16060 (0.0008) -[2023-10-16 03:24:27,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 32964608. Throughput: 0: 1774.3, 1: 1760.5. Samples: 8246580. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:24:27,351][03835] Avg episode reward: [(0, '4.970'), (1, '4.420')] -[2023-10-16 03:24:28,506][05218] Updated weights for policy 0, policy_version 16132 (0.0009) -[2023-10-16 03:24:28,577][05219] Updated weights for policy 1, policy_version 16070 (0.0007) -[2023-10-16 03:24:28,887][05218] Updated weights for policy 0, policy_version 16142 (0.0009) -[2023-10-16 03:24:28,931][05219] Updated weights for policy 1, policy_version 16080 (0.0007) -[2023-10-16 03:24:29,271][05218] Updated weights for policy 0, policy_version 16152 (0.0009) -[2023-10-16 03:24:29,295][05219] Updated weights for policy 1, policy_version 16090 (0.0009) -[2023-10-16 03:24:32,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 33030144. Throughput: 0: 1766.1, 1: 1764.3. Samples: 8268628. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:24:32,351][03835] Avg episode reward: [(0, '4.910'), (1, '4.670')] -[2023-10-16 03:24:33,099][05218] Updated weights for policy 0, policy_version 16162 (0.0008) -[2023-10-16 03:24:33,192][05219] Updated weights for policy 1, policy_version 16100 (0.0009) -[2023-10-16 03:24:33,478][05218] Updated weights for policy 0, policy_version 16172 (0.0008) -[2023-10-16 03:24:33,559][05219] Updated weights for policy 1, policy_version 16110 (0.0009) -[2023-10-16 03:24:33,846][05218] Updated weights for policy 0, policy_version 16182 (0.0009) -[2023-10-16 03:24:33,933][05219] Updated weights for policy 1, policy_version 16120 (0.0009) -[2023-10-16 03:24:34,223][05218] Updated weights for policy 0, policy_version 16192 (0.0008) -[2023-10-16 03:24:37,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 33095680. Throughput: 0: 1798.3, 1: 1780.0. Samples: 8291074. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:24:37,352][03835] Avg episode reward: [(0, '4.970'), (1, '4.690')] -[2023-10-16 03:24:37,743][05219] Updated weights for policy 1, policy_version 16130 (0.0008) -[2023-10-16 03:24:37,870][05218] Updated weights for policy 0, policy_version 16202 (0.0009) -[2023-10-16 03:24:38,122][05219] Updated weights for policy 1, policy_version 16140 (0.0007) -[2023-10-16 03:24:38,250][05218] Updated weights for policy 0, policy_version 16212 (0.0010) -[2023-10-16 03:24:38,487][05219] Updated weights for policy 1, policy_version 16150 (0.0007) -[2023-10-16 03:24:38,618][05218] Updated weights for policy 0, policy_version 16222 (0.0009) -[2023-10-16 03:24:38,850][05219] Updated weights for policy 1, policy_version 16160 (0.0007) -[2023-10-16 03:24:42,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 33161216. Throughput: 0: 1773.1, 1: 1764.4. Samples: 8300702. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:24:42,351][03835] Avg episode reward: [(0, '4.280'), (1, '4.950')] -[2023-10-16 03:24:42,412][05218] Updated weights for policy 0, policy_version 16232 (0.0010) -[2023-10-16 03:24:42,692][05219] Updated weights for policy 1, policy_version 16170 (0.0007) -[2023-10-16 03:24:42,778][05218] Updated weights for policy 0, policy_version 16242 (0.0009) -[2023-10-16 03:24:43,045][05219] Updated weights for policy 1, policy_version 16180 (0.0009) -[2023-10-16 03:24:43,155][05218] Updated weights for policy 0, policy_version 16252 (0.0008) -[2023-10-16 03:24:43,412][05219] Updated weights for policy 1, policy_version 16190 (0.0010) -[2023-10-16 03:24:43,487][04891] Saving new best policy, reward=4.950! -[2023-10-16 03:24:46,915][05218] Updated weights for policy 0, policy_version 16262 (0.0010) -[2023-10-16 03:24:47,167][05219] Updated weights for policy 1, policy_version 16200 (0.0008) -[2023-10-16 03:24:47,293][05218] Updated weights for policy 0, policy_version 16272 (0.0010) -[2023-10-16 03:24:47,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 33226752. Throughput: 0: 1787.8, 1: 1771.3. Samples: 8322712. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:24:47,351][03835] Avg episode reward: [(0, '4.180'), (1, '4.840')] -[2023-10-16 03:24:47,530][05219] Updated weights for policy 1, policy_version 16210 (0.0007) -[2023-10-16 03:24:47,658][05218] Updated weights for policy 0, policy_version 16282 (0.0007) -[2023-10-16 03:24:47,896][05219] Updated weights for policy 1, policy_version 16220 (0.0008) -[2023-10-16 03:24:51,513][05218] Updated weights for policy 0, policy_version 16292 (0.0008) -[2023-10-16 03:24:51,799][05219] Updated weights for policy 1, policy_version 16230 (0.0008) -[2023-10-16 03:24:51,887][05218] Updated weights for policy 0, policy_version 16302 (0.0007) -[2023-10-16 03:24:52,170][05219] Updated weights for policy 1, policy_version 16240 (0.0007) -[2023-10-16 03:24:52,270][05218] Updated weights for policy 0, policy_version 16312 (0.0007) -[2023-10-16 03:24:52,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 33292288. Throughput: 0: 1771.8, 1: 1777.3. Samples: 8342870. Policy #0 lag: (min: 27.0, avg: 30.7, max: 59.0) -[2023-10-16 03:24:52,351][03835] Avg episode reward: [(0, '4.260'), (1, '4.620')] -[2023-10-16 03:24:52,532][05219] Updated weights for policy 1, policy_version 16250 (0.0009) -[2023-10-16 03:24:56,097][05218] Updated weights for policy 0, policy_version 16322 (0.0007) -[2023-10-16 03:24:56,309][05219] Updated weights for policy 1, policy_version 16260 (0.0009) -[2023-10-16 03:24:56,472][05218] Updated weights for policy 0, policy_version 16332 (0.0007) -[2023-10-16 03:24:56,668][05219] Updated weights for policy 1, policy_version 16270 (0.0007) -[2023-10-16 03:24:56,851][05218] Updated weights for policy 0, policy_version 16342 (0.0007) -[2023-10-16 03:24:57,033][05219] Updated weights for policy 1, policy_version 16280 (0.0007) -[2023-10-16 03:24:57,227][05218] Updated weights for policy 0, policy_version 16352 (0.0007) -[2023-10-16 03:24:57,350][03835] Fps is (10 sec: 19660.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 33423360. Throughput: 0: 1780.5, 1: 1763.5. Samples: 8354200. Policy #0 lag: (min: 27.0, avg: 30.7, max: 59.0) -[2023-10-16 03:24:57,351][03835] Avg episode reward: [(0, '4.670'), (1, '5.170')] -[2023-10-16 03:24:57,353][04891] Saving new best policy, reward=5.170! -[2023-10-16 03:25:00,859][05219] Updated weights for policy 1, policy_version 16290 (0.0008) -[2023-10-16 03:25:00,881][05218] Updated weights for policy 0, policy_version 16362 (0.0008) -[2023-10-16 03:25:01,231][05219] Updated weights for policy 1, policy_version 16300 (0.0008) -[2023-10-16 03:25:01,268][05218] Updated weights for policy 0, policy_version 16372 (0.0009) -[2023-10-16 03:25:01,586][05219] Updated weights for policy 1, policy_version 16310 (0.0007) -[2023-10-16 03:25:01,645][05218] Updated weights for policy 0, policy_version 16382 (0.0009) -[2023-10-16 03:25:01,951][05219] Updated weights for policy 1, policy_version 16320 (0.0007) -[2023-10-16 03:25:02,350][03835] Fps is (10 sec: 19660.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 33488896. Throughput: 0: 1782.8, 1: 1779.7. Samples: 8375118. Policy #0 lag: (min: 11.0, avg: 37.6, max: 40.0) -[2023-10-16 03:25:02,351][03835] Avg episode reward: [(0, '4.790'), (1, '4.730')] -[2023-10-16 03:25:05,381][05218] Updated weights for policy 0, policy_version 16392 (0.0008) -[2023-10-16 03:25:05,652][05219] Updated weights for policy 1, policy_version 16330 (0.0007) -[2023-10-16 03:25:05,753][05218] Updated weights for policy 0, policy_version 16402 (0.0008) -[2023-10-16 03:25:06,017][05219] Updated weights for policy 1, policy_version 16340 (0.0008) -[2023-10-16 03:25:06,135][05218] Updated weights for policy 0, policy_version 16412 (0.0009) -[2023-10-16 03:25:06,389][05219] Updated weights for policy 1, policy_version 16350 (0.0007) -[2023-10-16 03:25:07,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 33554432. Throughput: 0: 1767.1, 1: 1764.5. Samples: 8395988. Policy #0 lag: (min: 11.0, avg: 37.6, max: 40.0) -[2023-10-16 03:25:07,351][03835] Avg episode reward: [(0, '5.020'), (1, '4.990')] -[2023-10-16 03:25:07,365][04766] Saving new best policy, reward=5.020! -[2023-10-16 03:25:09,893][05218] Updated weights for policy 0, policy_version 16422 (0.0009) -[2023-10-16 03:25:10,149][05219] Updated weights for policy 1, policy_version 16360 (0.0008) -[2023-10-16 03:25:10,256][05218] Updated weights for policy 0, policy_version 16432 (0.0010) -[2023-10-16 03:25:10,507][05219] Updated weights for policy 1, policy_version 16370 (0.0007) -[2023-10-16 03:25:10,634][05218] Updated weights for policy 0, policy_version 16442 (0.0010) -[2023-10-16 03:25:10,872][05219] Updated weights for policy 1, policy_version 16380 (0.0008) -[2023-10-16 03:25:12,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 33619968. Throughput: 0: 1782.9, 1: 1792.4. Samples: 8407470. Policy #0 lag: (min: 11.0, avg: 37.6, max: 40.0) -[2023-10-16 03:25:12,351][03835] Avg episode reward: [(0, '4.770'), (1, '4.710')] -[2023-10-16 03:25:14,332][05218] Updated weights for policy 0, policy_version 16452 (0.0008) -[2023-10-16 03:25:14,710][05218] Updated weights for policy 0, policy_version 16462 (0.0007) -[2023-10-16 03:25:14,768][05219] Updated weights for policy 1, policy_version 16390 (0.0008) -[2023-10-16 03:25:15,081][05218] Updated weights for policy 0, policy_version 16472 (0.0008) -[2023-10-16 03:25:15,132][05219] Updated weights for policy 1, policy_version 16400 (0.0009) -[2023-10-16 03:25:15,498][05219] Updated weights for policy 1, policy_version 16410 (0.0007) -[2023-10-16 03:25:17,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 33685504. Throughput: 0: 1777.9, 1: 1763.3. Samples: 8427984. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) -[2023-10-16 03:25:17,351][03835] Avg episode reward: [(0, '4.410'), (1, '4.150')] -[2023-10-16 03:25:18,912][05218] Updated weights for policy 0, policy_version 16482 (0.0008) -[2023-10-16 03:25:19,294][05218] Updated weights for policy 0, policy_version 16492 (0.0010) -[2023-10-16 03:25:19,322][05219] Updated weights for policy 1, policy_version 16420 (0.0007) -[2023-10-16 03:25:19,665][05218] Updated weights for policy 0, policy_version 16502 (0.0009) -[2023-10-16 03:25:19,683][05219] Updated weights for policy 1, policy_version 16430 (0.0007) -[2023-10-16 03:25:20,040][05218] Updated weights for policy 0, policy_version 16512 (0.0008) -[2023-10-16 03:25:20,057][05219] Updated weights for policy 1, policy_version 16440 (0.0009) -[2023-10-16 03:25:22,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 33751040. Throughput: 0: 1773.9, 1: 1760.9. Samples: 8450140. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) -[2023-10-16 03:25:22,352][03835] Avg episode reward: [(0, '4.440'), (1, '4.620')] -[2023-10-16 03:25:23,727][05218] Updated weights for policy 0, policy_version 16522 (0.0007) -[2023-10-16 03:25:23,884][05219] Updated weights for policy 1, policy_version 16450 (0.0009) -[2023-10-16 03:25:24,104][05218] Updated weights for policy 0, policy_version 16532 (0.0007) -[2023-10-16 03:25:24,286][05219] Updated weights for policy 1, policy_version 16460 (0.0009) -[2023-10-16 03:25:24,479][05218] Updated weights for policy 0, policy_version 16542 (0.0007) -[2023-10-16 03:25:24,657][05219] Updated weights for policy 1, policy_version 16470 (0.0008) -[2023-10-16 03:25:25,016][05219] Updated weights for policy 1, policy_version 16480 (0.0009) -[2023-10-16 03:25:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 33816576. Throughput: 0: 1771.8, 1: 1762.6. Samples: 8459750. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) -[2023-10-16 03:25:27,351][03835] Avg episode reward: [(0, '4.750'), (1, '4.600')] -[2023-10-16 03:25:28,320][05218] Updated weights for policy 0, policy_version 16552 (0.0009) -[2023-10-16 03:25:28,697][05218] Updated weights for policy 0, policy_version 16562 (0.0008) -[2023-10-16 03:25:28,938][05219] Updated weights for policy 1, policy_version 16490 (0.0008) -[2023-10-16 03:25:29,083][05218] Updated weights for policy 0, policy_version 16572 (0.0008) -[2023-10-16 03:25:29,302][05219] Updated weights for policy 1, policy_version 16500 (0.0010) -[2023-10-16 03:25:29,671][05219] Updated weights for policy 1, policy_version 16510 (0.0008) -[2023-10-16 03:25:32,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 33882112. Throughput: 0: 1776.9, 1: 1759.1. Samples: 8481832. Policy #0 lag: (min: 9.0, avg: 11.9, max: 41.0) -[2023-10-16 03:25:32,352][03835] Avg episode reward: [(0, '4.940'), (1, '4.780')] -[2023-10-16 03:25:32,892][05218] Updated weights for policy 0, policy_version 16582 (0.0010) -[2023-10-16 03:25:33,270][05218] Updated weights for policy 0, policy_version 16592 (0.0009) -[2023-10-16 03:25:33,541][05219] Updated weights for policy 1, policy_version 16520 (0.0008) -[2023-10-16 03:25:33,641][05218] Updated weights for policy 0, policy_version 16602 (0.0009) -[2023-10-16 03:25:33,905][05219] Updated weights for policy 1, policy_version 16530 (0.0008) -[2023-10-16 03:25:34,277][05219] Updated weights for policy 1, policy_version 16540 (0.0010) -[2023-10-16 03:25:37,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 33947648. Throughput: 0: 1799.8, 1: 1778.4. Samples: 8503892. Policy #0 lag: (min: 9.0, avg: 11.9, max: 41.0) -[2023-10-16 03:25:37,351][03835] Avg episode reward: [(0, '4.620'), (1, '5.210')] -[2023-10-16 03:25:37,364][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000016544_16941056.pth... -[2023-10-16 03:25:37,372][05218] Updated weights for policy 0, policy_version 16612 (0.0008) -[2023-10-16 03:25:37,403][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000014912_15269888.pth -[2023-10-16 03:25:37,409][04891] Saving new best policy, reward=5.210! -[2023-10-16 03:25:37,450][04891] Saving a milestone ./train_atari/atari_timepilot_APPO/checkpoint_p1/milestones/checkpoint_000016544_16941056.pth -[2023-10-16 03:25:37,748][05218] Updated weights for policy 0, policy_version 16622 (0.0007) -[2023-10-16 03:25:37,966][05219] Updated weights for policy 1, policy_version 16550 (0.0008) -[2023-10-16 03:25:38,129][05218] Updated weights for policy 0, policy_version 16632 (0.0007) -[2023-10-16 03:25:38,338][05219] Updated weights for policy 1, policy_version 16560 (0.0008) -[2023-10-16 03:25:38,422][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000016640_17039360.pth... -[2023-10-16 03:25:38,451][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000014944_15302656.pth -[2023-10-16 03:25:38,455][04766] Saving a milestone ./train_atari/atari_timepilot_APPO/checkpoint_p0/milestones/checkpoint_000016640_17039360.pth -[2023-10-16 03:25:38,709][05219] Updated weights for policy 1, policy_version 16570 (0.0007) -[2023-10-16 03:25:41,976][05218] Updated weights for policy 0, policy_version 16642 (0.0008) -[2023-10-16 03:25:42,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 34013184. Throughput: 0: 1780.8, 1: 1766.3. Samples: 8513816. Policy #0 lag: (min: 9.0, avg: 11.9, max: 41.0) -[2023-10-16 03:25:42,351][03835] Avg episode reward: [(0, '5.050'), (1, '4.970')] -[2023-10-16 03:25:42,356][05218] Updated weights for policy 0, policy_version 16652 (0.0010) -[2023-10-16 03:25:42,731][05218] Updated weights for policy 0, policy_version 16662 (0.0008) -[2023-10-16 03:25:42,737][05219] Updated weights for policy 1, policy_version 16580 (0.0007) -[2023-10-16 03:25:43,103][04766] Saving new best policy, reward=5.050! -[2023-10-16 03:25:43,107][05218] Updated weights for policy 0, policy_version 16672 (0.0007) -[2023-10-16 03:25:43,108][05219] Updated weights for policy 1, policy_version 16590 (0.0007) -[2023-10-16 03:25:43,480][05219] Updated weights for policy 1, policy_version 16600 (0.0010) -[2023-10-16 03:25:46,840][05218] Updated weights for policy 0, policy_version 16682 (0.0008) -[2023-10-16 03:25:47,215][05218] Updated weights for policy 0, policy_version 16692 (0.0008) -[2023-10-16 03:25:47,348][05219] Updated weights for policy 1, policy_version 16610 (0.0009) -[2023-10-16 03:25:47,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 34078720. Throughput: 0: 1794.3, 1: 1775.4. Samples: 8535754. Policy #0 lag: (min: 23.0, avg: 27.3, max: 55.0) -[2023-10-16 03:25:47,351][03835] Avg episode reward: [(0, '4.860'), (1, '4.930')] -[2023-10-16 03:25:47,579][05218] Updated weights for policy 0, policy_version 16702 (0.0009) -[2023-10-16 03:25:47,722][05219] Updated weights for policy 1, policy_version 16620 (0.0009) -[2023-10-16 03:25:48,079][05219] Updated weights for policy 1, policy_version 16630 (0.0009) -[2023-10-16 03:25:48,447][05219] Updated weights for policy 1, policy_version 16640 (0.0009) -[2023-10-16 03:25:51,377][05218] Updated weights for policy 0, policy_version 16712 (0.0010) -[2023-10-16 03:25:51,763][05218] Updated weights for policy 0, policy_version 16722 (0.0007) -[2023-10-16 03:25:52,131][05218] Updated weights for policy 0, policy_version 16732 (0.0010) -[2023-10-16 03:25:52,311][05219] Updated weights for policy 1, policy_version 16650 (0.0009) -[2023-10-16 03:25:52,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 34177024. Throughput: 0: 1772.6, 1: 1785.9. Samples: 8556120. Policy #0 lag: (min: 23.0, avg: 27.3, max: 55.0) -[2023-10-16 03:25:52,351][03835] Avg episode reward: [(0, '4.610'), (1, '5.380')] -[2023-10-16 03:25:52,670][05219] Updated weights for policy 1, policy_version 16660 (0.0007) -[2023-10-16 03:25:53,049][05219] Updated weights for policy 1, policy_version 16670 (0.0008) -[2023-10-16 03:25:53,115][04891] Saving new best policy, reward=5.380! -[2023-10-16 03:25:55,816][05218] Updated weights for policy 0, policy_version 16742 (0.0007) -[2023-10-16 03:25:56,195][05218] Updated weights for policy 0, policy_version 16752 (0.0011) -[2023-10-16 03:25:56,580][05218] Updated weights for policy 0, policy_version 16762 (0.0008) -[2023-10-16 03:25:56,787][05219] Updated weights for policy 1, policy_version 16680 (0.0007) -[2023-10-16 03:25:57,153][05219] Updated weights for policy 1, policy_version 16690 (0.0008) -[2023-10-16 03:25:57,350][03835] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 34242560. Throughput: 0: 1792.0, 1: 1767.8. Samples: 8567658. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:25:57,351][03835] Avg episode reward: [(0, '4.470'), (1, '4.210')] -[2023-10-16 03:25:57,516][05219] Updated weights for policy 1, policy_version 16700 (0.0007) -[2023-10-16 03:26:00,383][05218] Updated weights for policy 0, policy_version 16772 (0.0008) -[2023-10-16 03:26:00,753][05218] Updated weights for policy 0, policy_version 16782 (0.0008) -[2023-10-16 03:26:01,129][05218] Updated weights for policy 0, policy_version 16792 (0.0009) -[2023-10-16 03:26:01,187][05219] Updated weights for policy 1, policy_version 16710 (0.0008) -[2023-10-16 03:26:01,547][05219] Updated weights for policy 1, policy_version 16720 (0.0008) -[2023-10-16 03:26:01,915][05219] Updated weights for policy 1, policy_version 16730 (0.0007) -[2023-10-16 03:26:02,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 34340864. Throughput: 0: 1777.3, 1: 1795.6. Samples: 8588766. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:26:02,351][03835] Avg episode reward: [(0, '4.300'), (1, '5.320')] -[2023-10-16 03:26:04,879][05218] Updated weights for policy 0, policy_version 16802 (0.0009) -[2023-10-16 03:26:05,250][05218] Updated weights for policy 0, policy_version 16812 (0.0008) -[2023-10-16 03:26:05,634][05218] Updated weights for policy 0, policy_version 16822 (0.0009) -[2023-10-16 03:26:05,727][05219] Updated weights for policy 1, policy_version 16740 (0.0007) -[2023-10-16 03:26:05,997][05218] Updated weights for policy 0, policy_version 16832 (0.0007) -[2023-10-16 03:26:06,091][05219] Updated weights for policy 1, policy_version 16750 (0.0008) -[2023-10-16 03:26:06,456][05219] Updated weights for policy 1, policy_version 16760 (0.0009) -[2023-10-16 03:26:07,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 34406400. Throughput: 0: 1776.7, 1: 1768.9. Samples: 8609694. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:26:07,351][03835] Avg episode reward: [(0, '4.810'), (1, '5.190')] -[2023-10-16 03:26:09,710][05218] Updated weights for policy 0, policy_version 16842 (0.0010) -[2023-10-16 03:26:10,084][05218] Updated weights for policy 0, policy_version 16852 (0.0009) -[2023-10-16 03:26:10,165][05219] Updated weights for policy 1, policy_version 16770 (0.0008) -[2023-10-16 03:26:10,467][05218] Updated weights for policy 0, policy_version 16862 (0.0008) -[2023-10-16 03:26:10,540][05219] Updated weights for policy 1, policy_version 16780 (0.0007) -[2023-10-16 03:26:10,903][05219] Updated weights for policy 1, policy_version 16790 (0.0008) -[2023-10-16 03:26:11,277][05219] Updated weights for policy 1, policy_version 16800 (0.0008) -[2023-10-16 03:26:12,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 34471936. Throughput: 0: 1784.9, 1: 1800.2. Samples: 8621080. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:26:12,351][03835] Avg episode reward: [(0, '4.790'), (1, '4.990')] -[2023-10-16 03:26:14,216][05218] Updated weights for policy 0, policy_version 16872 (0.0009) -[2023-10-16 03:26:14,589][05218] Updated weights for policy 0, policy_version 16882 (0.0010) -[2023-10-16 03:26:14,960][05218] Updated weights for policy 0, policy_version 16892 (0.0007) -[2023-10-16 03:26:15,077][05219] Updated weights for policy 1, policy_version 16810 (0.0007) -[2023-10-16 03:26:15,441][05219] Updated weights for policy 1, policy_version 16820 (0.0007) -[2023-10-16 03:26:15,806][05219] Updated weights for policy 1, policy_version 16830 (0.0009) -[2023-10-16 03:26:17,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 34537472. Throughput: 0: 1781.6, 1: 1775.9. Samples: 8641920. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:26:17,351][03835] Avg episode reward: [(0, '4.460'), (1, '5.800')] -[2023-10-16 03:26:17,353][04891] Saving new best policy, reward=5.800! -[2023-10-16 03:26:18,624][05218] Updated weights for policy 0, policy_version 16902 (0.0007) -[2023-10-16 03:26:18,994][05218] Updated weights for policy 0, policy_version 16912 (0.0008) -[2023-10-16 03:26:19,365][05218] Updated weights for policy 0, policy_version 16922 (0.0009) -[2023-10-16 03:26:19,581][05219] Updated weights for policy 1, policy_version 16840 (0.0009) -[2023-10-16 03:26:19,932][05219] Updated weights for policy 1, policy_version 16850 (0.0011) -[2023-10-16 03:26:20,297][05219] Updated weights for policy 1, policy_version 16860 (0.0007) -[2023-10-16 03:26:22,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 34603008. Throughput: 0: 1791.9, 1: 1775.3. Samples: 8664416. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:26:22,351][03835] Avg episode reward: [(0, '4.400'), (1, '5.090')] -[2023-10-16 03:26:23,057][05218] Updated weights for policy 0, policy_version 16932 (0.0009) -[2023-10-16 03:26:23,437][05218] Updated weights for policy 0, policy_version 16942 (0.0011) -[2023-10-16 03:26:23,814][05218] Updated weights for policy 0, policy_version 16952 (0.0010) -[2023-10-16 03:26:24,103][05219] Updated weights for policy 1, policy_version 16870 (0.0009) -[2023-10-16 03:26:24,470][05219] Updated weights for policy 1, policy_version 16880 (0.0007) -[2023-10-16 03:26:24,826][05219] Updated weights for policy 1, policy_version 16890 (0.0007) -[2023-10-16 03:26:27,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 34668544. Throughput: 0: 1786.2, 1: 1775.2. Samples: 8674080. Policy #0 lag: (min: 12.0, avg: 13.3, max: 36.0) -[2023-10-16 03:26:27,351][03835] Avg episode reward: [(0, '4.900'), (1, '4.730')] -[2023-10-16 03:26:27,633][05218] Updated weights for policy 0, policy_version 16962 (0.0008) -[2023-10-16 03:26:28,010][05218] Updated weights for policy 0, policy_version 16972 (0.0010) -[2023-10-16 03:26:28,381][05218] Updated weights for policy 0, policy_version 16982 (0.0008) -[2023-10-16 03:26:28,599][05219] Updated weights for policy 1, policy_version 16900 (0.0009) -[2023-10-16 03:26:28,757][05218] Updated weights for policy 0, policy_version 16992 (0.0007) -[2023-10-16 03:26:28,973][05219] Updated weights for policy 1, policy_version 16910 (0.0008) -[2023-10-16 03:26:29,337][05219] Updated weights for policy 1, policy_version 16920 (0.0009) -[2023-10-16 03:26:32,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 34734080. Throughput: 0: 1800.5, 1: 1773.5. Samples: 8696584. Policy #0 lag: (min: 12.0, avg: 13.3, max: 36.0) -[2023-10-16 03:26:32,351][03835] Avg episode reward: [(0, '5.130'), (1, '4.870')] -[2023-10-16 03:26:32,405][05218] Updated weights for policy 0, policy_version 17002 (0.0010) -[2023-10-16 03:26:32,786][05218] Updated weights for policy 0, policy_version 17012 (0.0011) -[2023-10-16 03:26:33,161][05218] Updated weights for policy 0, policy_version 17022 (0.0008) -[2023-10-16 03:26:33,176][05219] Updated weights for policy 1, policy_version 16930 (0.0011) -[2023-10-16 03:26:33,235][04766] Saving new best policy, reward=5.130! -[2023-10-16 03:26:33,541][05219] Updated weights for policy 1, policy_version 16940 (0.0008) -[2023-10-16 03:26:33,909][05219] Updated weights for policy 1, policy_version 16950 (0.0009) -[2023-10-16 03:26:34,282][05219] Updated weights for policy 1, policy_version 16960 (0.0011) -[2023-10-16 03:26:36,972][05218] Updated weights for policy 0, policy_version 17032 (0.0008) -[2023-10-16 03:26:37,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 34799616. Throughput: 0: 1815.2, 1: 1782.8. Samples: 8718034. Policy #0 lag: (min: 12.0, avg: 13.3, max: 36.0) -[2023-10-16 03:26:37,352][03835] Avg episode reward: [(0, '5.030'), (1, '4.650')] -[2023-10-16 03:26:37,354][05218] Updated weights for policy 0, policy_version 17042 (0.0009) -[2023-10-16 03:26:37,731][05218] Updated weights for policy 0, policy_version 17052 (0.0009) -[2023-10-16 03:26:38,117][05219] Updated weights for policy 1, policy_version 16970 (0.0011) -[2023-10-16 03:26:38,474][05219] Updated weights for policy 1, policy_version 16980 (0.0011) -[2023-10-16 03:26:38,848][05219] Updated weights for policy 1, policy_version 16990 (0.0007) -[2023-10-16 03:26:41,485][05218] Updated weights for policy 0, policy_version 17062 (0.0008) -[2023-10-16 03:26:41,854][05218] Updated weights for policy 0, policy_version 17072 (0.0009) -[2023-10-16 03:26:42,235][05218] Updated weights for policy 0, policy_version 17082 (0.0008) -[2023-10-16 03:26:42,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 34865152. Throughput: 0: 1802.2, 1: 1775.8. Samples: 8728670. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-16 03:26:42,351][03835] Avg episode reward: [(0, '4.610'), (1, '4.880')] -[2023-10-16 03:26:42,664][05219] Updated weights for policy 1, policy_version 17000 (0.0007) -[2023-10-16 03:26:43,030][05219] Updated weights for policy 1, policy_version 17010 (0.0008) -[2023-10-16 03:26:43,392][05219] Updated weights for policy 1, policy_version 17020 (0.0008) -[2023-10-16 03:26:45,891][05218] Updated weights for policy 0, policy_version 17092 (0.0008) -[2023-10-16 03:26:46,267][05218] Updated weights for policy 0, policy_version 17102 (0.0008) -[2023-10-16 03:26:46,651][05218] Updated weights for policy 0, policy_version 17112 (0.0010) -[2023-10-16 03:26:47,143][05219] Updated weights for policy 1, policy_version 17030 (0.0008) -[2023-10-16 03:26:47,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 34963456. Throughput: 0: 1816.7, 1: 1771.5. Samples: 8750232. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-16 03:26:47,351][03835] Avg episode reward: [(0, '4.900'), (1, '4.550')] -[2023-10-16 03:26:47,514][05219] Updated weights for policy 1, policy_version 17040 (0.0009) -[2023-10-16 03:26:47,892][05219] Updated weights for policy 1, policy_version 17050 (0.0009) -[2023-10-16 03:26:50,365][05218] Updated weights for policy 0, policy_version 17122 (0.0010) -[2023-10-16 03:26:50,735][05218] Updated weights for policy 0, policy_version 17132 (0.0010) -[2023-10-16 03:26:51,111][05218] Updated weights for policy 0, policy_version 17142 (0.0008) -[2023-10-16 03:26:51,483][05218] Updated weights for policy 0, policy_version 17152 (0.0008) -[2023-10-16 03:26:51,652][05219] Updated weights for policy 1, policy_version 17060 (0.0008) -[2023-10-16 03:26:52,015][05219] Updated weights for policy 1, policy_version 17070 (0.0007) -[2023-10-16 03:26:52,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 35028992. Throughput: 0: 1801.1, 1: 1786.1. Samples: 8771120. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-16 03:26:52,351][03835] Avg episode reward: [(0, '4.750'), (1, '4.970')] -[2023-10-16 03:26:52,384][05219] Updated weights for policy 1, policy_version 17080 (0.0007) -[2023-10-16 03:26:55,188][05218] Updated weights for policy 0, policy_version 17162 (0.0008) -[2023-10-16 03:26:55,573][05218] Updated weights for policy 0, policy_version 17172 (0.0010) -[2023-10-16 03:26:55,940][05218] Updated weights for policy 0, policy_version 17182 (0.0008) -[2023-10-16 03:26:56,070][05219] Updated weights for policy 1, policy_version 17090 (0.0007) -[2023-10-16 03:26:56,492][05219] Updated weights for policy 1, policy_version 17100 (0.0007) -[2023-10-16 03:26:56,848][05219] Updated weights for policy 1, policy_version 17110 (0.0010) -[2023-10-16 03:26:57,216][05219] Updated weights for policy 1, policy_version 17120 (0.0010) -[2023-10-16 03:26:57,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 35127296. Throughput: 0: 1816.1, 1: 1773.6. Samples: 8782618. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-16 03:26:57,351][03835] Avg episode reward: [(0, '4.510'), (1, '4.860')] -[2023-10-16 03:26:59,804][05218] Updated weights for policy 0, policy_version 17192 (0.0010) -[2023-10-16 03:27:00,181][05218] Updated weights for policy 0, policy_version 17202 (0.0010) -[2023-10-16 03:27:00,556][05218] Updated weights for policy 0, policy_version 17212 (0.0010) -[2023-10-16 03:27:01,044][05219] Updated weights for policy 1, policy_version 17130 (0.0007) -[2023-10-16 03:27:01,408][05219] Updated weights for policy 1, policy_version 17140 (0.0010) -[2023-10-16 03:27:01,774][05219] Updated weights for policy 1, policy_version 17150 (0.0007) -[2023-10-16 03:27:02,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 35192832. Throughput: 0: 1796.2, 1: 1794.1. Samples: 8803482. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-16 03:27:02,351][03835] Avg episode reward: [(0, '4.850'), (1, '4.640')] -[2023-10-16 03:27:04,278][05218] Updated weights for policy 0, policy_version 17222 (0.0009) -[2023-10-16 03:27:04,648][05218] Updated weights for policy 0, policy_version 17232 (0.0009) -[2023-10-16 03:27:05,028][05218] Updated weights for policy 0, policy_version 17242 (0.0007) -[2023-10-16 03:27:05,464][05219] Updated weights for policy 1, policy_version 17160 (0.0008) -[2023-10-16 03:27:05,824][05219] Updated weights for policy 1, policy_version 17170 (0.0007) -[2023-10-16 03:27:06,186][05219] Updated weights for policy 1, policy_version 17180 (0.0007) -[2023-10-16 03:27:07,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 35258368. Throughput: 0: 1790.0, 1: 1777.2. Samples: 8824942. Policy #0 lag: (min: 26.0, avg: 35.0, max: 58.0) -[2023-10-16 03:27:07,351][03835] Avg episode reward: [(0, '4.490'), (1, '4.840')] -[2023-10-16 03:27:08,777][05218] Updated weights for policy 0, policy_version 17252 (0.0007) -[2023-10-16 03:27:09,146][05218] Updated weights for policy 0, policy_version 17262 (0.0008) -[2023-10-16 03:27:09,515][05218] Updated weights for policy 0, policy_version 17272 (0.0011) -[2023-10-16 03:27:10,020][05219] Updated weights for policy 1, policy_version 17190 (0.0011) -[2023-10-16 03:27:10,391][05219] Updated weights for policy 1, policy_version 17200 (0.0009) -[2023-10-16 03:27:10,760][05219] Updated weights for policy 1, policy_version 17210 (0.0010) -[2023-10-16 03:27:12,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 35323904. Throughput: 0: 1788.7, 1: 1802.0. Samples: 8835662. Policy #0 lag: (min: 26.0, avg: 35.0, max: 58.0) -[2023-10-16 03:27:12,351][03835] Avg episode reward: [(0, '4.790'), (1, '4.970')] -[2023-10-16 03:27:13,106][05218] Updated weights for policy 0, policy_version 17282 (0.0011) -[2023-10-16 03:27:13,480][05218] Updated weights for policy 0, policy_version 17292 (0.0008) -[2023-10-16 03:27:13,855][05218] Updated weights for policy 0, policy_version 17302 (0.0009) -[2023-10-16 03:27:14,225][05218] Updated weights for policy 0, policy_version 17312 (0.0008) -[2023-10-16 03:27:14,594][05219] Updated weights for policy 1, policy_version 17220 (0.0008) -[2023-10-16 03:27:14,962][05219] Updated weights for policy 1, policy_version 17230 (0.0010) -[2023-10-16 03:27:15,329][05219] Updated weights for policy 1, policy_version 17240 (0.0009) -[2023-10-16 03:27:17,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 35389440. Throughput: 0: 1784.0, 1: 1782.0. Samples: 8857054. Policy #0 lag: (min: 26.0, avg: 35.0, max: 58.0) -[2023-10-16 03:27:17,351][03835] Avg episode reward: [(0, '5.100'), (1, '4.920')] -[2023-10-16 03:27:18,102][05218] Updated weights for policy 0, policy_version 17322 (0.0008) -[2023-10-16 03:27:18,483][05218] Updated weights for policy 0, policy_version 17332 (0.0009) -[2023-10-16 03:27:18,852][05218] Updated weights for policy 0, policy_version 17342 (0.0007) -[2023-10-16 03:27:18,991][05219] Updated weights for policy 1, policy_version 17250 (0.0010) -[2023-10-16 03:27:19,359][05219] Updated weights for policy 1, policy_version 17260 (0.0008) -[2023-10-16 03:27:19,721][05219] Updated weights for policy 1, policy_version 17270 (0.0010) -[2023-10-16 03:27:20,078][05219] Updated weights for policy 1, policy_version 17280 (0.0007) -[2023-10-16 03:27:22,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 35454976. Throughput: 0: 1800.5, 1: 1778.1. Samples: 8879070. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-16 03:27:22,351][03835] Avg episode reward: [(0, '4.850'), (1, '5.230')] -[2023-10-16 03:27:22,659][05218] Updated weights for policy 0, policy_version 17352 (0.0009) -[2023-10-16 03:27:23,048][05218] Updated weights for policy 0, policy_version 17362 (0.0008) -[2023-10-16 03:27:23,417][05218] Updated weights for policy 0, policy_version 17372 (0.0009) -[2023-10-16 03:27:23,864][05219] Updated weights for policy 1, policy_version 17290 (0.0009) -[2023-10-16 03:27:24,226][05219] Updated weights for policy 1, policy_version 17300 (0.0009) -[2023-10-16 03:27:24,602][05219] Updated weights for policy 1, policy_version 17310 (0.0009) -[2023-10-16 03:27:27,108][05218] Updated weights for policy 0, policy_version 17382 (0.0009) -[2023-10-16 03:27:27,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 35520512. Throughput: 0: 1778.2, 1: 1781.5. Samples: 8888856. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-16 03:27:27,351][03835] Avg episode reward: [(0, '5.110'), (1, '5.030')] -[2023-10-16 03:27:27,489][05218] Updated weights for policy 0, policy_version 17392 (0.0008) -[2023-10-16 03:27:27,858][05218] Updated weights for policy 0, policy_version 17402 (0.0008) -[2023-10-16 03:27:28,370][05219] Updated weights for policy 1, policy_version 17320 (0.0008) -[2023-10-16 03:27:28,734][05219] Updated weights for policy 1, policy_version 17330 (0.0010) -[2023-10-16 03:27:29,107][05219] Updated weights for policy 1, policy_version 17340 (0.0011) -[2023-10-16 03:27:31,534][05218] Updated weights for policy 0, policy_version 17412 (0.0009) -[2023-10-16 03:27:31,913][05218] Updated weights for policy 0, policy_version 17422 (0.0009) -[2023-10-16 03:27:32,286][05218] Updated weights for policy 0, policy_version 17432 (0.0009) -[2023-10-16 03:27:32,351][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 35586048. Throughput: 0: 1795.9, 1: 1785.3. Samples: 8911384. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-16 03:27:32,352][03835] Avg episode reward: [(0, '4.700'), (1, '4.870')] -[2023-10-16 03:27:32,992][05219] Updated weights for policy 1, policy_version 17350 (0.0009) -[2023-10-16 03:27:33,357][05219] Updated weights for policy 1, policy_version 17360 (0.0010) -[2023-10-16 03:27:33,724][05219] Updated weights for policy 1, policy_version 17370 (0.0010) -[2023-10-16 03:27:36,151][05218] Updated weights for policy 0, policy_version 17442 (0.0008) -[2023-10-16 03:27:36,524][05218] Updated weights for policy 0, policy_version 17452 (0.0010) -[2023-10-16 03:27:36,899][05218] Updated weights for policy 0, policy_version 17462 (0.0011) -[2023-10-16 03:27:37,274][05218] Updated weights for policy 0, policy_version 17472 (0.0010) -[2023-10-16 03:27:37,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 35684352. Throughput: 0: 1776.4, 1: 1805.0. Samples: 8932282. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:27:37,351][03835] Avg episode reward: [(0, '4.680'), (1, '4.830')] -[2023-10-16 03:27:37,359][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000017472_17891328.pth... -[2023-10-16 03:27:37,398][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000015776_16154624.pth -[2023-10-16 03:27:37,435][05219] Updated weights for policy 1, policy_version 17380 (0.0010) -[2023-10-16 03:27:37,796][05219] Updated weights for policy 1, policy_version 17390 (0.0009) -[2023-10-16 03:27:38,164][05219] Updated weights for policy 1, policy_version 17400 (0.0009) -[2023-10-16 03:27:38,456][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000017408_17825792.pth... -[2023-10-16 03:27:38,493][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000015712_16089088.pth -[2023-10-16 03:27:40,859][05218] Updated weights for policy 0, policy_version 17482 (0.0010) -[2023-10-16 03:27:41,237][05218] Updated weights for policy 0, policy_version 17492 (0.0010) -[2023-10-16 03:27:41,608][05218] Updated weights for policy 0, policy_version 17502 (0.0009) -[2023-10-16 03:27:41,919][05219] Updated weights for policy 1, policy_version 17410 (0.0011) -[2023-10-16 03:27:42,301][05219] Updated weights for policy 1, policy_version 17420 (0.0010) -[2023-10-16 03:27:42,350][03835] Fps is (10 sec: 16384.6, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 35749888. Throughput: 0: 1792.8, 1: 1787.8. Samples: 8943748. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:27:42,351][03835] Avg episode reward: [(0, '5.180'), (1, '4.410')] -[2023-10-16 03:27:42,352][04766] Saving new best policy, reward=5.180! -[2023-10-16 03:27:42,658][05219] Updated weights for policy 1, policy_version 17430 (0.0011) -[2023-10-16 03:27:43,029][05219] Updated weights for policy 1, policy_version 17440 (0.0011) -[2023-10-16 03:27:45,340][05218] Updated weights for policy 0, policy_version 17512 (0.0009) -[2023-10-16 03:27:45,717][05218] Updated weights for policy 0, policy_version 17522 (0.0008) -[2023-10-16 03:27:46,099][05218] Updated weights for policy 0, policy_version 17532 (0.0010) -[2023-10-16 03:27:46,625][05219] Updated weights for policy 1, policy_version 17450 (0.0007) -[2023-10-16 03:27:46,984][05219] Updated weights for policy 1, policy_version 17460 (0.0007) -[2023-10-16 03:27:47,350][05219] Updated weights for policy 1, policy_version 17470 (0.0009) -[2023-10-16 03:27:47,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 35815424. Throughput: 0: 1784.5, 1: 1799.2. Samples: 8964746. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:27:47,351][03835] Avg episode reward: [(0, '5.360'), (1, '4.860')] -[2023-10-16 03:27:47,351][04766] Saving new best policy, reward=5.360! -[2023-10-16 03:27:49,858][05218] Updated weights for policy 0, policy_version 17542 (0.0009) -[2023-10-16 03:27:50,233][05218] Updated weights for policy 0, policy_version 17552 (0.0009) -[2023-10-16 03:27:50,606][05218] Updated weights for policy 0, policy_version 17562 (0.0009) -[2023-10-16 03:27:51,065][05219] Updated weights for policy 1, policy_version 17480 (0.0008) -[2023-10-16 03:27:51,433][05219] Updated weights for policy 1, policy_version 17490 (0.0008) -[2023-10-16 03:27:51,799][05219] Updated weights for policy 1, policy_version 17500 (0.0007) -[2023-10-16 03:27:52,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 35913728. Throughput: 0: 1792.7, 1: 1782.3. Samples: 8985818. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:27:52,351][03835] Avg episode reward: [(0, '5.210'), (1, '4.550')] -[2023-10-16 03:27:54,256][05218] Updated weights for policy 0, policy_version 17572 (0.0008) -[2023-10-16 03:27:54,635][05218] Updated weights for policy 0, policy_version 17582 (0.0007) -[2023-10-16 03:27:55,006][05218] Updated weights for policy 0, policy_version 17592 (0.0010) -[2023-10-16 03:27:55,620][05219] Updated weights for policy 1, policy_version 17510 (0.0008) -[2023-10-16 03:27:55,986][05219] Updated weights for policy 1, policy_version 17520 (0.0008) -[2023-10-16 03:27:56,352][05219] Updated weights for policy 1, policy_version 17530 (0.0008) -[2023-10-16 03:27:57,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 35979264. Throughput: 0: 1792.4, 1: 1793.0. Samples: 8997008. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:27:57,351][03835] Avg episode reward: [(0, '5.570'), (1, '4.740')] -[2023-10-16 03:27:57,352][04766] Saving new best policy, reward=5.570! -[2023-10-16 03:27:58,718][05218] Updated weights for policy 0, policy_version 17602 (0.0009) -[2023-10-16 03:27:59,099][05218] Updated weights for policy 0, policy_version 17612 (0.0009) -[2023-10-16 03:27:59,465][05218] Updated weights for policy 0, policy_version 17622 (0.0008) -[2023-10-16 03:27:59,840][05218] Updated weights for policy 0, policy_version 17632 (0.0009) -[2023-10-16 03:28:00,128][05219] Updated weights for policy 1, policy_version 17540 (0.0007) -[2023-10-16 03:28:00,490][05219] Updated weights for policy 1, policy_version 17550 (0.0008) -[2023-10-16 03:28:00,853][05219] Updated weights for policy 1, policy_version 17560 (0.0007) -[2023-10-16 03:28:02,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 36044800. Throughput: 0: 1791.8, 1: 1787.6. Samples: 9018124. Policy #0 lag: (min: 24.0, avg: 47.1, max: 56.0) -[2023-10-16 03:28:02,351][03835] Avg episode reward: [(0, '4.730'), (1, '4.410')] -[2023-10-16 03:28:03,643][05218] Updated weights for policy 0, policy_version 17642 (0.0010) -[2023-10-16 03:28:04,032][05218] Updated weights for policy 0, policy_version 17652 (0.0011) -[2023-10-16 03:28:04,403][05218] Updated weights for policy 0, policy_version 17662 (0.0010) -[2023-10-16 03:28:04,709][05219] Updated weights for policy 1, policy_version 17570 (0.0007) -[2023-10-16 03:28:05,086][05219] Updated weights for policy 1, policy_version 17580 (0.0008) -[2023-10-16 03:28:05,446][05219] Updated weights for policy 1, policy_version 17590 (0.0008) -[2023-10-16 03:28:05,814][05219] Updated weights for policy 1, policy_version 17600 (0.0009) -[2023-10-16 03:28:07,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 36110336. Throughput: 0: 1795.2, 1: 1788.9. Samples: 9040356. Policy #0 lag: (min: 24.0, avg: 47.1, max: 56.0) -[2023-10-16 03:28:07,352][03835] Avg episode reward: [(0, '4.710'), (1, '4.680')] -[2023-10-16 03:28:08,219][05218] Updated weights for policy 0, policy_version 17672 (0.0008) -[2023-10-16 03:28:08,595][05218] Updated weights for policy 0, policy_version 17682 (0.0007) -[2023-10-16 03:28:08,976][05218] Updated weights for policy 0, policy_version 17692 (0.0008) -[2023-10-16 03:28:09,698][05219] Updated weights for policy 1, policy_version 17610 (0.0007) -[2023-10-16 03:28:10,053][05219] Updated weights for policy 1, policy_version 17620 (0.0010) -[2023-10-16 03:28:10,430][05219] Updated weights for policy 1, policy_version 17630 (0.0009) -[2023-10-16 03:28:12,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 36175872. Throughput: 0: 1796.7, 1: 1797.8. Samples: 9050612. Policy #0 lag: (min: 24.0, avg: 47.1, max: 56.0) -[2023-10-16 03:28:12,351][03835] Avg episode reward: [(0, '4.590'), (1, '4.870')] -[2023-10-16 03:28:12,779][05218] Updated weights for policy 0, policy_version 17702 (0.0008) -[2023-10-16 03:28:13,154][05218] Updated weights for policy 0, policy_version 17712 (0.0009) -[2023-10-16 03:28:13,531][05218] Updated weights for policy 0, policy_version 17722 (0.0008) -[2023-10-16 03:28:14,179][05219] Updated weights for policy 1, policy_version 17640 (0.0007) -[2023-10-16 03:28:14,539][05219] Updated weights for policy 1, policy_version 17650 (0.0009) -[2023-10-16 03:28:14,908][05219] Updated weights for policy 1, policy_version 17660 (0.0008) -[2023-10-16 03:28:17,351][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 36241408. Throughput: 0: 1790.5, 1: 1783.2. Samples: 9072204. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:28:17,352][03835] Avg episode reward: [(0, '4.840'), (1, '4.840')] -[2023-10-16 03:28:17,389][05218] Updated weights for policy 0, policy_version 17732 (0.0008) -[2023-10-16 03:28:17,769][05218] Updated weights for policy 0, policy_version 17742 (0.0011) -[2023-10-16 03:28:18,135][05218] Updated weights for policy 0, policy_version 17752 (0.0011) -[2023-10-16 03:28:18,789][05219] Updated weights for policy 1, policy_version 17670 (0.0008) -[2023-10-16 03:28:19,155][05219] Updated weights for policy 1, policy_version 17680 (0.0009) -[2023-10-16 03:28:19,516][05219] Updated weights for policy 1, policy_version 17690 (0.0009) -[2023-10-16 03:28:22,042][05218] Updated weights for policy 0, policy_version 17762 (0.0009) -[2023-10-16 03:28:22,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 36306944. Throughput: 0: 1814.0, 1: 1779.0. Samples: 9093968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:28:22,351][03835] Avg episode reward: [(0, '4.660'), (1, '4.530')] -[2023-10-16 03:28:22,427][05218] Updated weights for policy 0, policy_version 17772 (0.0007) -[2023-10-16 03:28:22,798][05218] Updated weights for policy 0, policy_version 17782 (0.0010) -[2023-10-16 03:28:23,170][05218] Updated weights for policy 0, policy_version 17792 (0.0008) -[2023-10-16 03:28:23,220][05219] Updated weights for policy 1, policy_version 17700 (0.0008) -[2023-10-16 03:28:23,594][05219] Updated weights for policy 1, policy_version 17710 (0.0008) -[2023-10-16 03:28:23,956][05219] Updated weights for policy 1, policy_version 17720 (0.0008) -[2023-10-16 03:28:26,865][05218] Updated weights for policy 0, policy_version 17802 (0.0008) -[2023-10-16 03:28:27,247][05218] Updated weights for policy 0, policy_version 17812 (0.0009) -[2023-10-16 03:28:27,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 36372480. Throughput: 0: 1787.2, 1: 1777.3. Samples: 9104154. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:28:27,351][03835] Avg episode reward: [(0, '5.070'), (1, '4.570')] -[2023-10-16 03:28:27,634][05218] Updated weights for policy 0, policy_version 17822 (0.0008) -[2023-10-16 03:28:27,849][05219] Updated weights for policy 1, policy_version 17730 (0.0007) -[2023-10-16 03:28:28,257][05219] Updated weights for policy 1, policy_version 17740 (0.0008) -[2023-10-16 03:28:28,618][05219] Updated weights for policy 1, policy_version 17750 (0.0007) -[2023-10-16 03:28:28,979][05219] Updated weights for policy 1, policy_version 17760 (0.0008) -[2023-10-16 03:28:31,333][05218] Updated weights for policy 0, policy_version 17832 (0.0010) -[2023-10-16 03:28:31,712][05218] Updated weights for policy 0, policy_version 17842 (0.0010) -[2023-10-16 03:28:32,085][05218] Updated weights for policy 0, policy_version 17852 (0.0008) -[2023-10-16 03:28:32,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 36470784. Throughput: 0: 1810.4, 1: 1773.6. Samples: 9126030. Policy #0 lag: (min: 18.0, avg: 27.0, max: 50.0) -[2023-10-16 03:28:32,351][03835] Avg episode reward: [(0, '5.030'), (1, '4.760')] -[2023-10-16 03:28:32,690][05219] Updated weights for policy 1, policy_version 17770 (0.0010) -[2023-10-16 03:28:33,055][05219] Updated weights for policy 1, policy_version 17780 (0.0010) -[2023-10-16 03:28:33,420][05219] Updated weights for policy 1, policy_version 17790 (0.0008) -[2023-10-16 03:28:35,766][05218] Updated weights for policy 0, policy_version 17862 (0.0008) -[2023-10-16 03:28:36,139][05218] Updated weights for policy 0, policy_version 17872 (0.0010) -[2023-10-16 03:28:36,514][05218] Updated weights for policy 0, policy_version 17882 (0.0007) -[2023-10-16 03:28:37,161][05219] Updated weights for policy 1, policy_version 17800 (0.0011) -[2023-10-16 03:28:37,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 36536320. Throughput: 0: 1780.6, 1: 1804.3. Samples: 9147138. Policy #0 lag: (min: 18.0, avg: 27.0, max: 50.0) -[2023-10-16 03:28:37,351][03835] Avg episode reward: [(0, '5.130'), (1, '4.280')] -[2023-10-16 03:28:37,514][05219] Updated weights for policy 1, policy_version 17810 (0.0010) -[2023-10-16 03:28:37,887][05219] Updated weights for policy 1, policy_version 17820 (0.0008) -[2023-10-16 03:28:40,224][05218] Updated weights for policy 0, policy_version 17892 (0.0010) -[2023-10-16 03:28:40,596][05218] Updated weights for policy 0, policy_version 17902 (0.0008) -[2023-10-16 03:28:40,981][05218] Updated weights for policy 0, policy_version 17912 (0.0008) -[2023-10-16 03:28:41,439][05219] Updated weights for policy 1, policy_version 17830 (0.0009) -[2023-10-16 03:28:41,806][05219] Updated weights for policy 1, policy_version 17840 (0.0009) -[2023-10-16 03:28:42,174][05219] Updated weights for policy 1, policy_version 17850 (0.0010) -[2023-10-16 03:28:42,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 36601856. Throughput: 0: 1811.4, 1: 1779.9. Samples: 9158616. Policy #0 lag: (min: 22.0, avg: 31.2, max: 54.0) -[2023-10-16 03:28:42,352][03835] Avg episode reward: [(0, '4.930'), (1, '4.860')] -[2023-10-16 03:28:44,711][05218] Updated weights for policy 0, policy_version 17922 (0.0009) -[2023-10-16 03:28:45,085][05218] Updated weights for policy 0, policy_version 17932 (0.0008) -[2023-10-16 03:28:45,455][05218] Updated weights for policy 0, policy_version 17942 (0.0008) -[2023-10-16 03:28:45,840][05218] Updated weights for policy 0, policy_version 17952 (0.0008) -[2023-10-16 03:28:45,985][05219] Updated weights for policy 1, policy_version 17860 (0.0008) -[2023-10-16 03:28:46,356][05219] Updated weights for policy 1, policy_version 17870 (0.0008) -[2023-10-16 03:28:46,723][05219] Updated weights for policy 1, policy_version 17880 (0.0007) -[2023-10-16 03:28:47,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 36700160. Throughput: 0: 1783.2, 1: 1798.3. Samples: 9179294. Policy #0 lag: (min: 22.0, avg: 31.2, max: 54.0) -[2023-10-16 03:28:47,351][03835] Avg episode reward: [(0, '4.280'), (1, '4.760')] -[2023-10-16 03:28:49,564][05218] Updated weights for policy 0, policy_version 17962 (0.0010) -[2023-10-16 03:28:49,935][05218] Updated weights for policy 0, policy_version 17972 (0.0008) -[2023-10-16 03:28:50,308][05218] Updated weights for policy 0, policy_version 17982 (0.0007) -[2023-10-16 03:28:50,519][05219] Updated weights for policy 1, policy_version 17890 (0.0009) -[2023-10-16 03:28:50,887][05219] Updated weights for policy 1, policy_version 17900 (0.0007) -[2023-10-16 03:28:51,264][05219] Updated weights for policy 1, policy_version 17910 (0.0008) -[2023-10-16 03:28:51,627][05219] Updated weights for policy 1, policy_version 17920 (0.0009) -[2023-10-16 03:28:52,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 36765696. Throughput: 0: 1786.0, 1: 1775.8. Samples: 9200636. Policy #0 lag: (min: 22.0, avg: 31.2, max: 54.0) -[2023-10-16 03:28:52,351][03835] Avg episode reward: [(0, '4.560'), (1, '4.650')] -[2023-10-16 03:28:54,010][05218] Updated weights for policy 0, policy_version 17992 (0.0009) -[2023-10-16 03:28:54,381][05218] Updated weights for policy 0, policy_version 18002 (0.0009) -[2023-10-16 03:28:54,757][05218] Updated weights for policy 0, policy_version 18012 (0.0009) -[2023-10-16 03:28:55,506][05219] Updated weights for policy 1, policy_version 17930 (0.0008) -[2023-10-16 03:28:55,867][05219] Updated weights for policy 1, policy_version 17940 (0.0009) -[2023-10-16 03:28:56,228][05219] Updated weights for policy 1, policy_version 17950 (0.0007) -[2023-10-16 03:28:57,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 36831232. Throughput: 0: 1782.0, 1: 1797.9. Samples: 9211704. Policy #0 lag: (min: 38.0, avg: 54.6, max: 56.0) -[2023-10-16 03:28:57,351][03835] Avg episode reward: [(0, '4.830'), (1, '5.090')] -[2023-10-16 03:28:58,533][05218] Updated weights for policy 0, policy_version 18022 (0.0008) -[2023-10-16 03:28:58,902][05218] Updated weights for policy 0, policy_version 18032 (0.0008) -[2023-10-16 03:28:59,278][05218] Updated weights for policy 0, policy_version 18042 (0.0009) -[2023-10-16 03:28:59,928][05219] Updated weights for policy 1, policy_version 17960 (0.0008) -[2023-10-16 03:29:00,292][05219] Updated weights for policy 1, policy_version 17970 (0.0007) -[2023-10-16 03:29:00,660][05219] Updated weights for policy 1, policy_version 17980 (0.0008) -[2023-10-16 03:29:02,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 36896768. Throughput: 0: 1786.0, 1: 1783.1. Samples: 9232814. Policy #0 lag: (min: 38.0, avg: 54.6, max: 56.0) -[2023-10-16 03:29:02,351][03835] Avg episode reward: [(0, '4.880'), (1, '4.590')] -[2023-10-16 03:29:03,078][05218] Updated weights for policy 0, policy_version 18052 (0.0009) -[2023-10-16 03:29:03,444][05218] Updated weights for policy 0, policy_version 18062 (0.0007) -[2023-10-16 03:29:03,817][05218] Updated weights for policy 0, policy_version 18072 (0.0009) -[2023-10-16 03:29:04,432][05219] Updated weights for policy 1, policy_version 17990 (0.0009) -[2023-10-16 03:29:04,794][05219] Updated weights for policy 1, policy_version 18000 (0.0007) -[2023-10-16 03:29:05,164][05219] Updated weights for policy 1, policy_version 18010 (0.0008) -[2023-10-16 03:29:07,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.6, 300 sec: 14218.0). Total num frames: 36962304. Throughput: 0: 1799.6, 1: 1786.1. Samples: 9255328. Policy #0 lag: (min: 38.0, avg: 54.6, max: 56.0) -[2023-10-16 03:29:07,351][03835] Avg episode reward: [(0, '5.330'), (1, '5.010')] -[2023-10-16 03:29:07,494][05218] Updated weights for policy 0, policy_version 18082 (0.0011) -[2023-10-16 03:29:07,870][05218] Updated weights for policy 0, policy_version 18092 (0.0008) -[2023-10-16 03:29:08,245][05218] Updated weights for policy 0, policy_version 18102 (0.0010) -[2023-10-16 03:29:08,628][05218] Updated weights for policy 0, policy_version 18112 (0.0009) -[2023-10-16 03:29:08,807][05219] Updated weights for policy 1, policy_version 18020 (0.0008) -[2023-10-16 03:29:09,180][05219] Updated weights for policy 1, policy_version 18030 (0.0008) -[2023-10-16 03:29:09,536][05219] Updated weights for policy 1, policy_version 18040 (0.0008) -[2023-10-16 03:29:12,345][05218] Updated weights for policy 0, policy_version 18122 (0.0007) -[2023-10-16 03:29:12,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 37027840. Throughput: 0: 1786.5, 1: 1791.5. Samples: 9265166. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-16 03:29:12,351][03835] Avg episode reward: [(0, '5.040'), (1, '4.920')] -[2023-10-16 03:29:12,714][05218] Updated weights for policy 0, policy_version 18132 (0.0007) -[2023-10-16 03:29:13,092][05218] Updated weights for policy 0, policy_version 18142 (0.0007) -[2023-10-16 03:29:13,311][05219] Updated weights for policy 1, policy_version 18050 (0.0009) -[2023-10-16 03:29:13,677][05219] Updated weights for policy 1, policy_version 18060 (0.0010) -[2023-10-16 03:29:14,040][05219] Updated weights for policy 1, policy_version 18070 (0.0009) -[2023-10-16 03:29:14,402][05219] Updated weights for policy 1, policy_version 18080 (0.0007) -[2023-10-16 03:29:16,680][05218] Updated weights for policy 0, policy_version 18152 (0.0009) -[2023-10-16 03:29:17,049][05218] Updated weights for policy 0, policy_version 18162 (0.0009) -[2023-10-16 03:29:17,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.6, 300 sec: 14218.0). Total num frames: 37093376. Throughput: 0: 1798.9, 1: 1795.0. Samples: 9287758. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-16 03:29:17,351][03835] Avg episode reward: [(0, '4.580'), (1, '4.830')] -[2023-10-16 03:29:17,428][05218] Updated weights for policy 0, policy_version 18172 (0.0009) -[2023-10-16 03:29:18,272][05219] Updated weights for policy 1, policy_version 18090 (0.0009) -[2023-10-16 03:29:18,640][05219] Updated weights for policy 1, policy_version 18100 (0.0010) -[2023-10-16 03:29:19,017][05219] Updated weights for policy 1, policy_version 18110 (0.0009) -[2023-10-16 03:29:21,224][05218] Updated weights for policy 0, policy_version 18182 (0.0009) -[2023-10-16 03:29:21,598][05218] Updated weights for policy 0, policy_version 18192 (0.0009) -[2023-10-16 03:29:21,983][05218] Updated weights for policy 0, policy_version 18202 (0.0009) -[2023-10-16 03:29:22,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 37191680. Throughput: 0: 1788.4, 1: 1796.8. Samples: 9308470. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-16 03:29:22,352][03835] Avg episode reward: [(0, '4.300'), (1, '4.560')] -[2023-10-16 03:29:22,785][05219] Updated weights for policy 1, policy_version 18120 (0.0008) -[2023-10-16 03:29:23,151][05219] Updated weights for policy 1, policy_version 18130 (0.0007) -[2023-10-16 03:29:23,521][05219] Updated weights for policy 1, policy_version 18140 (0.0008) -[2023-10-16 03:29:25,697][05218] Updated weights for policy 0, policy_version 18212 (0.0007) -[2023-10-16 03:29:26,077][05218] Updated weights for policy 0, policy_version 18222 (0.0011) -[2023-10-16 03:29:26,446][05218] Updated weights for policy 0, policy_version 18232 (0.0008) -[2023-10-16 03:29:27,274][05219] Updated weights for policy 1, policy_version 18150 (0.0009) -[2023-10-16 03:29:27,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 37257216. Throughput: 0: 1794.0, 1: 1786.5. Samples: 9319736. Policy #0 lag: (min: 0.0, avg: 25.8, max: 32.0) -[2023-10-16 03:29:27,351][03835] Avg episode reward: [(0, '4.370'), (1, '4.610')] -[2023-10-16 03:29:27,641][05219] Updated weights for policy 1, policy_version 18160 (0.0009) -[2023-10-16 03:29:28,009][05219] Updated weights for policy 1, policy_version 18170 (0.0008) -[2023-10-16 03:29:30,277][05218] Updated weights for policy 0, policy_version 18242 (0.0007) -[2023-10-16 03:29:30,658][05218] Updated weights for policy 0, policy_version 18252 (0.0007) -[2023-10-16 03:29:31,033][05218] Updated weights for policy 0, policy_version 18262 (0.0008) -[2023-10-16 03:29:31,413][05218] Updated weights for policy 0, policy_version 18272 (0.0009) -[2023-10-16 03:29:31,721][05219] Updated weights for policy 1, policy_version 18180 (0.0007) -[2023-10-16 03:29:32,087][05219] Updated weights for policy 1, policy_version 18190 (0.0009) -[2023-10-16 03:29:32,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 37322752. Throughput: 0: 1790.4, 1: 1801.1. Samples: 9340914. Policy #0 lag: (min: 0.0, avg: 25.8, max: 32.0) -[2023-10-16 03:29:32,351][03835] Avg episode reward: [(0, '3.970'), (1, '4.780')] -[2023-10-16 03:29:32,442][05219] Updated weights for policy 1, policy_version 18200 (0.0008) -[2023-10-16 03:29:35,154][05218] Updated weights for policy 0, policy_version 18282 (0.0009) -[2023-10-16 03:29:35,527][05218] Updated weights for policy 0, policy_version 18292 (0.0011) -[2023-10-16 03:29:35,898][05218] Updated weights for policy 0, policy_version 18302 (0.0011) -[2023-10-16 03:29:36,368][05219] Updated weights for policy 1, policy_version 18210 (0.0007) -[2023-10-16 03:29:36,739][05219] Updated weights for policy 1, policy_version 18220 (0.0010) -[2023-10-16 03:29:37,095][05219] Updated weights for policy 1, policy_version 18230 (0.0009) -[2023-10-16 03:29:37,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 37388288. Throughput: 0: 1786.0, 1: 1800.8. Samples: 9362044. Policy #0 lag: (min: 0.0, avg: 25.8, max: 32.0) -[2023-10-16 03:29:37,351][03835] Avg episode reward: [(0, '4.030'), (1, '4.540')] -[2023-10-16 03:29:37,361][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000018304_18743296.pth... -[2023-10-16 03:29:37,399][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000016640_17039360.pth -[2023-10-16 03:29:37,466][05219] Updated weights for policy 1, policy_version 18240 (0.0007) -[2023-10-16 03:29:37,467][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000018240_18677760.pth... -[2023-10-16 03:29:37,506][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000016544_16941056.pth -[2023-10-16 03:29:39,695][05218] Updated weights for policy 0, policy_version 18312 (0.0009) -[2023-10-16 03:29:40,077][05218] Updated weights for policy 0, policy_version 18322 (0.0010) -[2023-10-16 03:29:40,442][05218] Updated weights for policy 0, policy_version 18332 (0.0010) -[2023-10-16 03:29:41,271][05219] Updated weights for policy 1, policy_version 18250 (0.0009) -[2023-10-16 03:29:41,632][05219] Updated weights for policy 1, policy_version 18260 (0.0010) -[2023-10-16 03:29:41,997][05219] Updated weights for policy 1, policy_version 18270 (0.0007) -[2023-10-16 03:29:42,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 37486592. Throughput: 0: 1796.8, 1: 1787.1. Samples: 9372980. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-16 03:29:42,351][03835] Avg episode reward: [(0, '3.730'), (1, '5.120')] -[2023-10-16 03:29:44,132][05218] Updated weights for policy 0, policy_version 18342 (0.0008) -[2023-10-16 03:29:44,506][05218] Updated weights for policy 0, policy_version 18352 (0.0008) -[2023-10-16 03:29:44,871][05218] Updated weights for policy 0, policy_version 18362 (0.0009) -[2023-10-16 03:29:45,809][05219] Updated weights for policy 1, policy_version 18280 (0.0008) -[2023-10-16 03:29:46,176][05219] Updated weights for policy 1, policy_version 18290 (0.0010) -[2023-10-16 03:29:46,533][05219] Updated weights for policy 1, policy_version 18300 (0.0007) -[2023-10-16 03:29:47,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 37552128. Throughput: 0: 1786.5, 1: 1798.5. Samples: 9394142. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-16 03:29:47,351][03835] Avg episode reward: [(0, '3.900'), (1, '4.980')] -[2023-10-16 03:29:48,737][05218] Updated weights for policy 0, policy_version 18372 (0.0009) -[2023-10-16 03:29:49,104][05218] Updated weights for policy 0, policy_version 18382 (0.0009) -[2023-10-16 03:29:49,485][05218] Updated weights for policy 0, policy_version 18392 (0.0007) -[2023-10-16 03:29:50,295][05219] Updated weights for policy 1, policy_version 18310 (0.0007) -[2023-10-16 03:29:50,657][05219] Updated weights for policy 1, policy_version 18320 (0.0010) -[2023-10-16 03:29:51,016][05219] Updated weights for policy 1, policy_version 18330 (0.0010) -[2023-10-16 03:29:52,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 37617664. Throughput: 0: 1782.1, 1: 1779.0. Samples: 9415576. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-16 03:29:52,351][03835] Avg episode reward: [(0, '4.280'), (1, '5.180')] -[2023-10-16 03:29:53,213][05218] Updated weights for policy 0, policy_version 18402 (0.0008) -[2023-10-16 03:29:53,588][05218] Updated weights for policy 0, policy_version 18412 (0.0008) -[2023-10-16 03:29:53,962][05218] Updated weights for policy 0, policy_version 18422 (0.0011) -[2023-10-16 03:29:54,335][05218] Updated weights for policy 0, policy_version 18432 (0.0008) -[2023-10-16 03:29:54,816][05219] Updated weights for policy 1, policy_version 18340 (0.0008) -[2023-10-16 03:29:55,175][05219] Updated weights for policy 1, policy_version 18350 (0.0007) -[2023-10-16 03:29:55,539][05219] Updated weights for policy 1, policy_version 18360 (0.0007) -[2023-10-16 03:29:57,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 37683200. Throughput: 0: 1785.3, 1: 1795.7. Samples: 9426310. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-16 03:29:57,351][03835] Avg episode reward: [(0, '4.200'), (1, '5.280')] -[2023-10-16 03:29:58,130][05218] Updated weights for policy 0, policy_version 18442 (0.0009) -[2023-10-16 03:29:58,510][05218] Updated weights for policy 0, policy_version 18452 (0.0008) -[2023-10-16 03:29:58,880][05218] Updated weights for policy 0, policy_version 18462 (0.0011) -[2023-10-16 03:29:59,325][05219] Updated weights for policy 1, policy_version 18370 (0.0009) -[2023-10-16 03:29:59,690][05219] Updated weights for policy 1, policy_version 18380 (0.0010) -[2023-10-16 03:30:00,053][05219] Updated weights for policy 1, policy_version 18390 (0.0009) -[2023-10-16 03:30:00,418][05219] Updated weights for policy 1, policy_version 18400 (0.0009) -[2023-10-16 03:30:02,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 37748736. Throughput: 0: 1778.0, 1: 1774.0. Samples: 9447600. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:30:02,351][03835] Avg episode reward: [(0, '4.900'), (1, '4.940')] -[2023-10-16 03:30:02,631][05218] Updated weights for policy 0, policy_version 18472 (0.0008) -[2023-10-16 03:30:03,021][05218] Updated weights for policy 0, policy_version 18482 (0.0007) -[2023-10-16 03:30:03,396][05218] Updated weights for policy 0, policy_version 18492 (0.0010) -[2023-10-16 03:30:04,287][05219] Updated weights for policy 1, policy_version 18410 (0.0009) -[2023-10-16 03:30:04,641][05219] Updated weights for policy 1, policy_version 18420 (0.0009) -[2023-10-16 03:30:05,001][05219] Updated weights for policy 1, policy_version 18430 (0.0008) -[2023-10-16 03:30:07,208][05218] Updated weights for policy 0, policy_version 18502 (0.0008) -[2023-10-16 03:30:07,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 37814272. Throughput: 0: 1799.4, 1: 1774.1. Samples: 9469278. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:30:07,351][03835] Avg episode reward: [(0, '4.690'), (1, '4.870')] -[2023-10-16 03:30:07,588][05218] Updated weights for policy 0, policy_version 18512 (0.0009) -[2023-10-16 03:30:07,966][05218] Updated weights for policy 0, policy_version 18522 (0.0010) -[2023-10-16 03:30:08,623][05219] Updated weights for policy 1, policy_version 18440 (0.0007) -[2023-10-16 03:30:08,987][05219] Updated weights for policy 1, policy_version 18450 (0.0008) -[2023-10-16 03:30:09,358][05219] Updated weights for policy 1, policy_version 18460 (0.0008) -[2023-10-16 03:30:11,879][05218] Updated weights for policy 0, policy_version 18532 (0.0008) -[2023-10-16 03:30:12,263][05218] Updated weights for policy 0, policy_version 18542 (0.0008) -[2023-10-16 03:30:12,351][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 37879808. Throughput: 0: 1774.6, 1: 1781.7. Samples: 9479772. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:30:12,352][03835] Avg episode reward: [(0, '4.980'), (1, '4.560')] -[2023-10-16 03:30:12,638][05218] Updated weights for policy 0, policy_version 18552 (0.0009) -[2023-10-16 03:30:13,000][05219] Updated weights for policy 1, policy_version 18470 (0.0009) -[2023-10-16 03:30:13,363][05219] Updated weights for policy 1, policy_version 18480 (0.0009) -[2023-10-16 03:30:13,729][05219] Updated weights for policy 1, policy_version 18490 (0.0007) -[2023-10-16 03:30:16,329][05218] Updated weights for policy 0, policy_version 18562 (0.0009) -[2023-10-16 03:30:16,701][05218] Updated weights for policy 0, policy_version 18572 (0.0009) -[2023-10-16 03:30:17,076][05218] Updated weights for policy 0, policy_version 18582 (0.0009) -[2023-10-16 03:30:17,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 37945344. Throughput: 0: 1800.4, 1: 1777.9. Samples: 9501936. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:30:17,351][03835] Avg episode reward: [(0, '4.950'), (1, '4.900')] -[2023-10-16 03:30:17,450][05218] Updated weights for policy 0, policy_version 18592 (0.0007) -[2023-10-16 03:30:17,501][05219] Updated weights for policy 1, policy_version 18500 (0.0010) -[2023-10-16 03:30:17,873][05219] Updated weights for policy 1, policy_version 18510 (0.0011) -[2023-10-16 03:30:18,239][05219] Updated weights for policy 1, policy_version 18520 (0.0009) -[2023-10-16 03:30:21,250][05218] Updated weights for policy 0, policy_version 18602 (0.0010) -[2023-10-16 03:30:21,619][05218] Updated weights for policy 0, policy_version 18612 (0.0010) -[2023-10-16 03:30:21,994][05218] Updated weights for policy 0, policy_version 18622 (0.0010) -[2023-10-16 03:30:22,059][05219] Updated weights for policy 1, policy_version 18530 (0.0008) -[2023-10-16 03:30:22,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 38043648. Throughput: 0: 1771.1, 1: 1798.1. Samples: 9522656. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:30:22,352][03835] Avg episode reward: [(0, '5.180'), (1, '5.240')] -[2023-10-16 03:30:22,424][05219] Updated weights for policy 1, policy_version 18540 (0.0009) -[2023-10-16 03:30:22,787][05219] Updated weights for policy 1, policy_version 18550 (0.0009) -[2023-10-16 03:30:23,154][05219] Updated weights for policy 1, policy_version 18560 (0.0008) -[2023-10-16 03:30:25,791][05218] Updated weights for policy 0, policy_version 18632 (0.0008) -[2023-10-16 03:30:26,173][05218] Updated weights for policy 0, policy_version 18642 (0.0009) -[2023-10-16 03:30:26,547][05218] Updated weights for policy 0, policy_version 18652 (0.0009) -[2023-10-16 03:30:26,948][05219] Updated weights for policy 1, policy_version 18570 (0.0007) -[2023-10-16 03:30:27,314][05219] Updated weights for policy 1, policy_version 18580 (0.0008) -[2023-10-16 03:30:27,350][03835] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 38109184. Throughput: 0: 1801.5, 1: 1780.5. Samples: 9534172. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:30:27,351][03835] Avg episode reward: [(0, '5.070'), (1, '4.830')] -[2023-10-16 03:30:27,673][05219] Updated weights for policy 1, policy_version 18590 (0.0009) -[2023-10-16 03:30:30,253][05218] Updated weights for policy 0, policy_version 18662 (0.0008) -[2023-10-16 03:30:30,634][05218] Updated weights for policy 0, policy_version 18672 (0.0008) -[2023-10-16 03:30:31,007][05218] Updated weights for policy 0, policy_version 18682 (0.0008) -[2023-10-16 03:30:31,370][05219] Updated weights for policy 1, policy_version 18600 (0.0007) -[2023-10-16 03:30:31,730][05219] Updated weights for policy 1, policy_version 18610 (0.0009) -[2023-10-16 03:30:32,096][05219] Updated weights for policy 1, policy_version 18620 (0.0008) -[2023-10-16 03:30:32,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 38207488. Throughput: 0: 1774.3, 1: 1806.4. Samples: 9555270. Policy #0 lag: (min: 11.0, avg: 12.0, max: 32.0) -[2023-10-16 03:30:32,351][03835] Avg episode reward: [(0, '4.980'), (1, '5.530')] -[2023-10-16 03:30:34,685][05218] Updated weights for policy 0, policy_version 18692 (0.0007) -[2023-10-16 03:30:35,060][05218] Updated weights for policy 0, policy_version 18702 (0.0010) -[2023-10-16 03:30:35,435][05218] Updated weights for policy 0, policy_version 18712 (0.0011) -[2023-10-16 03:30:35,869][05219] Updated weights for policy 1, policy_version 18630 (0.0009) -[2023-10-16 03:30:36,241][05219] Updated weights for policy 1, policy_version 18640 (0.0008) -[2023-10-16 03:30:36,606][05219] Updated weights for policy 1, policy_version 18650 (0.0009) -[2023-10-16 03:30:37,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 38273024. Throughput: 0: 1777.8, 1: 1792.8. Samples: 9576256. Policy #0 lag: (min: 11.0, avg: 12.0, max: 32.0) -[2023-10-16 03:30:37,352][03835] Avg episode reward: [(0, '5.030'), (1, '4.820')] -[2023-10-16 03:30:39,193][05218] Updated weights for policy 0, policy_version 18722 (0.0008) -[2023-10-16 03:30:39,571][05218] Updated weights for policy 0, policy_version 18732 (0.0008) -[2023-10-16 03:30:39,943][05218] Updated weights for policy 0, policy_version 18742 (0.0010) -[2023-10-16 03:30:40,325][05218] Updated weights for policy 0, policy_version 18752 (0.0007) -[2023-10-16 03:30:40,409][05219] Updated weights for policy 1, policy_version 18660 (0.0008) -[2023-10-16 03:30:40,767][05219] Updated weights for policy 1, policy_version 18670 (0.0009) -[2023-10-16 03:30:41,131][05219] Updated weights for policy 1, policy_version 18680 (0.0010) -[2023-10-16 03:30:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 38338560. Throughput: 0: 1778.2, 1: 1807.1. Samples: 9587648. Policy #0 lag: (min: 11.0, avg: 12.0, max: 32.0) -[2023-10-16 03:30:42,351][03835] Avg episode reward: [(0, '4.420'), (1, '4.910')] -[2023-10-16 03:30:43,992][05218] Updated weights for policy 0, policy_version 18762 (0.0009) -[2023-10-16 03:30:44,376][05218] Updated weights for policy 0, policy_version 18772 (0.0011) -[2023-10-16 03:30:44,757][05218] Updated weights for policy 0, policy_version 18782 (0.0011) -[2023-10-16 03:30:44,899][05219] Updated weights for policy 1, policy_version 18690 (0.0009) -[2023-10-16 03:30:45,272][05219] Updated weights for policy 1, policy_version 18700 (0.0010) -[2023-10-16 03:30:45,635][05219] Updated weights for policy 1, policy_version 18710 (0.0008) -[2023-10-16 03:30:46,004][05219] Updated weights for policy 1, policy_version 18720 (0.0010) -[2023-10-16 03:30:47,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 38404096. Throughput: 0: 1779.4, 1: 1795.6. Samples: 9608478. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:30:47,352][03835] Avg episode reward: [(0, '5.280'), (1, '5.050')] -[2023-10-16 03:30:48,571][05218] Updated weights for policy 0, policy_version 18792 (0.0009) -[2023-10-16 03:30:48,936][05218] Updated weights for policy 0, policy_version 18802 (0.0010) -[2023-10-16 03:30:49,311][05218] Updated weights for policy 0, policy_version 18812 (0.0007) -[2023-10-16 03:30:49,889][05219] Updated weights for policy 1, policy_version 18730 (0.0011) -[2023-10-16 03:30:50,253][05219] Updated weights for policy 1, policy_version 18740 (0.0010) -[2023-10-16 03:30:50,610][05219] Updated weights for policy 1, policy_version 18750 (0.0010) -[2023-10-16 03:30:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 38469632. Throughput: 0: 1796.3, 1: 1792.8. Samples: 9630784. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:30:52,351][03835] Avg episode reward: [(0, '4.600'), (1, '4.930')] -[2023-10-16 03:30:53,093][05218] Updated weights for policy 0, policy_version 18822 (0.0008) -[2023-10-16 03:30:53,464][05218] Updated weights for policy 0, policy_version 18832 (0.0009) -[2023-10-16 03:30:53,848][05218] Updated weights for policy 0, policy_version 18842 (0.0011) -[2023-10-16 03:30:54,452][05219] Updated weights for policy 1, policy_version 18760 (0.0008) -[2023-10-16 03:30:54,814][05219] Updated weights for policy 1, policy_version 18770 (0.0008) -[2023-10-16 03:30:55,184][05219] Updated weights for policy 1, policy_version 18780 (0.0007) -[2023-10-16 03:30:57,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 38535168. Throughput: 0: 1787.1, 1: 1795.2. Samples: 9640974. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:30:57,351][03835] Avg episode reward: [(0, '4.910'), (1, '4.980')] -[2023-10-16 03:30:57,468][05218] Updated weights for policy 0, policy_version 18852 (0.0009) -[2023-10-16 03:30:57,834][05218] Updated weights for policy 0, policy_version 18862 (0.0008) -[2023-10-16 03:30:58,215][05218] Updated weights for policy 0, policy_version 18872 (0.0008) -[2023-10-16 03:30:58,868][05219] Updated weights for policy 1, policy_version 18790 (0.0008) -[2023-10-16 03:30:59,230][05219] Updated weights for policy 1, policy_version 18800 (0.0008) -[2023-10-16 03:30:59,594][05219] Updated weights for policy 1, policy_version 18810 (0.0009) -[2023-10-16 03:31:01,894][05218] Updated weights for policy 0, policy_version 18882 (0.0007) -[2023-10-16 03:31:02,273][05218] Updated weights for policy 0, policy_version 18892 (0.0007) -[2023-10-16 03:31:02,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 38600704. Throughput: 0: 1790.2, 1: 1787.1. Samples: 9662914. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:31:02,351][03835] Avg episode reward: [(0, '4.940'), (1, '5.300')] -[2023-10-16 03:31:02,656][05218] Updated weights for policy 0, policy_version 18902 (0.0009) -[2023-10-16 03:31:03,037][05218] Updated weights for policy 0, policy_version 18912 (0.0009) -[2023-10-16 03:31:03,417][05219] Updated weights for policy 1, policy_version 18820 (0.0011) -[2023-10-16 03:31:03,785][05219] Updated weights for policy 1, policy_version 18830 (0.0007) -[2023-10-16 03:31:04,144][05219] Updated weights for policy 1, policy_version 18840 (0.0007) -[2023-10-16 03:31:06,716][05218] Updated weights for policy 0, policy_version 18922 (0.0009) -[2023-10-16 03:31:07,095][05218] Updated weights for policy 0, policy_version 18932 (0.0008) -[2023-10-16 03:31:07,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 38666240. Throughput: 0: 1800.9, 1: 1794.8. Samples: 9684460. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:31:07,351][03835] Avg episode reward: [(0, '5.020'), (1, '4.600')] -[2023-10-16 03:31:07,462][05218] Updated weights for policy 0, policy_version 18942 (0.0007) -[2023-10-16 03:31:07,774][05219] Updated weights for policy 1, policy_version 18850 (0.0008) -[2023-10-16 03:31:08,148][05219] Updated weights for policy 1, policy_version 18860 (0.0010) -[2023-10-16 03:31:08,510][05219] Updated weights for policy 1, policy_version 18870 (0.0008) -[2023-10-16 03:31:08,883][05219] Updated weights for policy 1, policy_version 18880 (0.0009) -[2023-10-16 03:31:11,351][05218] Updated weights for policy 0, policy_version 18952 (0.0007) -[2023-10-16 03:31:11,720][05218] Updated weights for policy 0, policy_version 18962 (0.0009) -[2023-10-16 03:31:12,099][05218] Updated weights for policy 0, policy_version 18972 (0.0009) -[2023-10-16 03:31:12,351][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 38764544. Throughput: 0: 1793.7, 1: 1790.0. Samples: 9695442. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:31:12,352][03835] Avg episode reward: [(0, '5.040'), (1, '5.450')] -[2023-10-16 03:31:12,594][05219] Updated weights for policy 1, policy_version 18890 (0.0008) -[2023-10-16 03:31:12,967][05219] Updated weights for policy 1, policy_version 18900 (0.0007) -[2023-10-16 03:31:13,332][05219] Updated weights for policy 1, policy_version 18910 (0.0008) -[2023-10-16 03:31:15,876][05218] Updated weights for policy 0, policy_version 18982 (0.0008) -[2023-10-16 03:31:16,252][05218] Updated weights for policy 0, policy_version 18992 (0.0008) -[2023-10-16 03:31:16,627][05218] Updated weights for policy 0, policy_version 19002 (0.0008) -[2023-10-16 03:31:17,123][05219] Updated weights for policy 1, policy_version 18920 (0.0009) -[2023-10-16 03:31:17,350][03835] Fps is (10 sec: 16383.5, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 38830080. Throughput: 0: 1804.7, 1: 1789.3. Samples: 9717002. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:31:17,352][03835] Avg episode reward: [(0, '5.690'), (1, '4.610')] -[2023-10-16 03:31:17,353][04766] Saving new best policy, reward=5.690! -[2023-10-16 03:31:17,485][05219] Updated weights for policy 1, policy_version 18930 (0.0009) -[2023-10-16 03:31:17,846][05219] Updated weights for policy 1, policy_version 18940 (0.0008) -[2023-10-16 03:31:20,434][05218] Updated weights for policy 0, policy_version 19012 (0.0009) -[2023-10-16 03:31:20,797][05218] Updated weights for policy 0, policy_version 19022 (0.0010) -[2023-10-16 03:31:21,171][05218] Updated weights for policy 0, policy_version 19032 (0.0008) -[2023-10-16 03:31:21,626][05219] Updated weights for policy 1, policy_version 18950 (0.0007) -[2023-10-16 03:31:21,991][05219] Updated weights for policy 1, policy_version 18960 (0.0009) -[2023-10-16 03:31:22,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 38895616. Throughput: 0: 1791.2, 1: 1800.6. Samples: 9737884. Policy #0 lag: (min: 31.0, avg: 32.7, max: 59.0) -[2023-10-16 03:31:22,351][03835] Avg episode reward: [(0, '4.970'), (1, '5.150')] -[2023-10-16 03:31:22,367][05219] Updated weights for policy 1, policy_version 18970 (0.0008) -[2023-10-16 03:31:24,841][05218] Updated weights for policy 0, policy_version 19042 (0.0008) -[2023-10-16 03:31:25,211][05218] Updated weights for policy 0, policy_version 19052 (0.0008) -[2023-10-16 03:31:25,590][05218] Updated weights for policy 0, policy_version 19062 (0.0007) -[2023-10-16 03:31:25,959][05218] Updated weights for policy 0, policy_version 19072 (0.0008) -[2023-10-16 03:31:26,223][05219] Updated weights for policy 1, policy_version 18980 (0.0009) -[2023-10-16 03:31:26,585][05219] Updated weights for policy 1, policy_version 18990 (0.0010) -[2023-10-16 03:31:26,951][05219] Updated weights for policy 1, policy_version 19000 (0.0010) -[2023-10-16 03:31:27,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 38993920. Throughput: 0: 1808.4, 1: 1780.8. Samples: 9749164. Policy #0 lag: (min: 31.0, avg: 32.7, max: 59.0) -[2023-10-16 03:31:27,351][03835] Avg episode reward: [(0, '4.830'), (1, '4.750')] -[2023-10-16 03:31:29,497][05218] Updated weights for policy 0, policy_version 19082 (0.0007) -[2023-10-16 03:31:29,876][05218] Updated weights for policy 0, policy_version 19092 (0.0008) -[2023-10-16 03:31:30,256][05218] Updated weights for policy 0, policy_version 19102 (0.0008) -[2023-10-16 03:31:30,766][05219] Updated weights for policy 1, policy_version 19010 (0.0010) -[2023-10-16 03:31:31,133][05219] Updated weights for policy 1, policy_version 19020 (0.0008) -[2023-10-16 03:31:31,500][05219] Updated weights for policy 1, policy_version 19030 (0.0007) -[2023-10-16 03:31:31,867][05219] Updated weights for policy 1, policy_version 19040 (0.0008) -[2023-10-16 03:31:32,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 39059456. Throughput: 0: 1798.1, 1: 1803.0. Samples: 9770526. Policy #0 lag: (min: 31.0, avg: 32.7, max: 59.0) -[2023-10-16 03:31:32,352][03835] Avg episode reward: [(0, '4.290'), (1, '4.500')] -[2023-10-16 03:31:34,076][05218] Updated weights for policy 0, policy_version 19112 (0.0008) -[2023-10-16 03:31:34,438][05218] Updated weights for policy 0, policy_version 19122 (0.0009) -[2023-10-16 03:31:34,809][05218] Updated weights for policy 0, policy_version 19132 (0.0009) -[2023-10-16 03:31:35,710][05219] Updated weights for policy 1, policy_version 19050 (0.0010) -[2023-10-16 03:31:36,072][05219] Updated weights for policy 1, policy_version 19060 (0.0011) -[2023-10-16 03:31:36,436][05219] Updated weights for policy 1, policy_version 19070 (0.0007) -[2023-10-16 03:31:37,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 39124992. Throughput: 0: 1796.4, 1: 1782.8. Samples: 9791844. Policy #0 lag: (min: 31.0, avg: 32.7, max: 59.0) -[2023-10-16 03:31:37,351][03835] Avg episode reward: [(0, '4.920'), (1, '4.780')] -[2023-10-16 03:31:37,359][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000019072_19529728.pth... -[2023-10-16 03:31:37,359][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000019136_19595264.pth... -[2023-10-16 03:31:37,396][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000017472_17891328.pth -[2023-10-16 03:31:37,399][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000017408_17825792.pth -[2023-10-16 03:31:38,558][05218] Updated weights for policy 0, policy_version 19142 (0.0009) -[2023-10-16 03:31:38,929][05218] Updated weights for policy 0, policy_version 19152 (0.0009) -[2023-10-16 03:31:39,311][05218] Updated weights for policy 0, policy_version 19162 (0.0009) -[2023-10-16 03:31:40,098][05219] Updated weights for policy 1, policy_version 19080 (0.0007) -[2023-10-16 03:31:40,475][05219] Updated weights for policy 1, policy_version 19090 (0.0007) -[2023-10-16 03:31:40,837][05219] Updated weights for policy 1, policy_version 19100 (0.0008) -[2023-10-16 03:31:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 39190528. Throughput: 0: 1797.3, 1: 1799.1. Samples: 9802814. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:31:42,351][03835] Avg episode reward: [(0, '5.290'), (1, '4.830')] -[2023-10-16 03:31:43,052][05218] Updated weights for policy 0, policy_version 19172 (0.0010) -[2023-10-16 03:31:43,425][05218] Updated weights for policy 0, policy_version 19182 (0.0009) -[2023-10-16 03:31:43,800][05218] Updated weights for policy 0, policy_version 19192 (0.0008) -[2023-10-16 03:31:44,596][05219] Updated weights for policy 1, policy_version 19110 (0.0009) -[2023-10-16 03:31:44,960][05219] Updated weights for policy 1, policy_version 19120 (0.0008) -[2023-10-16 03:31:45,325][05219] Updated weights for policy 1, policy_version 19130 (0.0007) -[2023-10-16 03:31:47,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 39256064. Throughput: 0: 1795.9, 1: 1787.9. Samples: 9824182. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:31:47,351][03835] Avg episode reward: [(0, '5.150'), (1, '5.180')] -[2023-10-16 03:31:47,585][05218] Updated weights for policy 0, policy_version 19202 (0.0009) -[2023-10-16 03:31:47,964][05218] Updated weights for policy 0, policy_version 19212 (0.0009) -[2023-10-16 03:31:48,335][05218] Updated weights for policy 0, policy_version 19222 (0.0008) -[2023-10-16 03:31:48,713][05218] Updated weights for policy 0, policy_version 19232 (0.0011) -[2023-10-16 03:31:48,989][05219] Updated weights for policy 1, policy_version 19140 (0.0007) -[2023-10-16 03:31:49,359][05219] Updated weights for policy 1, policy_version 19150 (0.0009) -[2023-10-16 03:31:49,718][05219] Updated weights for policy 1, policy_version 19160 (0.0008) -[2023-10-16 03:31:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 39321600. Throughput: 0: 1812.3, 1: 1790.2. Samples: 9846570. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:31:52,351][03835] Avg episode reward: [(0, '5.230'), (1, '4.940')] -[2023-10-16 03:31:52,422][05218] Updated weights for policy 0, policy_version 19242 (0.0009) -[2023-10-16 03:31:52,807][05218] Updated weights for policy 0, policy_version 19252 (0.0007) -[2023-10-16 03:31:53,180][05218] Updated weights for policy 0, policy_version 19262 (0.0007) -[2023-10-16 03:31:53,393][05219] Updated weights for policy 1, policy_version 19170 (0.0008) -[2023-10-16 03:31:53,752][05219] Updated weights for policy 1, policy_version 19180 (0.0009) -[2023-10-16 03:31:54,114][05219] Updated weights for policy 1, policy_version 19190 (0.0010) -[2023-10-16 03:31:54,486][05219] Updated weights for policy 1, policy_version 19200 (0.0011) -[2023-10-16 03:31:56,980][05218] Updated weights for policy 0, policy_version 19272 (0.0010) -[2023-10-16 03:31:57,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 39387136. Throughput: 0: 1791.0, 1: 1794.0. Samples: 9856764. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:31:57,351][03835] Avg episode reward: [(0, '5.310'), (1, '4.700')] -[2023-10-16 03:31:57,371][05218] Updated weights for policy 0, policy_version 19282 (0.0008) -[2023-10-16 03:31:57,748][05218] Updated weights for policy 0, policy_version 19292 (0.0008) -[2023-10-16 03:31:58,364][05219] Updated weights for policy 1, policy_version 19210 (0.0010) -[2023-10-16 03:31:58,737][05219] Updated weights for policy 1, policy_version 19220 (0.0009) -[2023-10-16 03:31:59,101][05219] Updated weights for policy 1, policy_version 19230 (0.0011) -[2023-10-16 03:32:01,335][05218] Updated weights for policy 0, policy_version 19302 (0.0008) -[2023-10-16 03:32:01,716][05218] Updated weights for policy 0, policy_version 19312 (0.0008) -[2023-10-16 03:32:02,089][05218] Updated weights for policy 0, policy_version 19322 (0.0007) -[2023-10-16 03:32:02,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 39485440. Throughput: 0: 1809.1, 1: 1783.8. Samples: 9878682. Policy #0 lag: (min: 31.0, avg: 44.7, max: 63.0) -[2023-10-16 03:32:02,351][03835] Avg episode reward: [(0, '5.040'), (1, '4.750')] -[2023-10-16 03:32:02,990][05219] Updated weights for policy 1, policy_version 19240 (0.0010) -[2023-10-16 03:32:03,362][05219] Updated weights for policy 1, policy_version 19250 (0.0008) -[2023-10-16 03:32:03,715][05219] Updated weights for policy 1, policy_version 19260 (0.0008) -[2023-10-16 03:32:05,920][05218] Updated weights for policy 0, policy_version 19332 (0.0008) -[2023-10-16 03:32:06,295][05218] Updated weights for policy 0, policy_version 19342 (0.0009) -[2023-10-16 03:32:06,677][05218] Updated weights for policy 0, policy_version 19352 (0.0009) -[2023-10-16 03:32:07,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 39550976. Throughput: 0: 1797.9, 1: 1808.2. Samples: 9900158. Policy #0 lag: (min: 31.0, avg: 44.7, max: 63.0) -[2023-10-16 03:32:07,351][03835] Avg episode reward: [(0, '4.980'), (1, '4.650')] -[2023-10-16 03:32:07,404][05219] Updated weights for policy 1, policy_version 19270 (0.0008) -[2023-10-16 03:32:07,767][05219] Updated weights for policy 1, policy_version 19280 (0.0009) -[2023-10-16 03:32:08,125][05219] Updated weights for policy 1, policy_version 19290 (0.0009) -[2023-10-16 03:32:10,322][05218] Updated weights for policy 0, policy_version 19362 (0.0008) -[2023-10-16 03:32:10,704][05218] Updated weights for policy 0, policy_version 19372 (0.0008) -[2023-10-16 03:32:11,087][05218] Updated weights for policy 0, policy_version 19382 (0.0008) -[2023-10-16 03:32:11,465][05218] Updated weights for policy 0, policy_version 19392 (0.0008) -[2023-10-16 03:32:11,915][05219] Updated weights for policy 1, policy_version 19300 (0.0007) -[2023-10-16 03:32:12,281][05219] Updated weights for policy 1, policy_version 19310 (0.0007) -[2023-10-16 03:32:12,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.6, 300 sec: 14329.1). Total num frames: 39616512. Throughput: 0: 1811.4, 1: 1792.1. Samples: 9911324. Policy #0 lag: (min: 31.0, avg: 44.7, max: 63.0) -[2023-10-16 03:32:12,351][03835] Avg episode reward: [(0, '5.370'), (1, '5.000')] -[2023-10-16 03:32:12,635][05219] Updated weights for policy 1, policy_version 19320 (0.0007) -[2023-10-16 03:32:14,978][05218] Updated weights for policy 0, policy_version 19402 (0.0011) -[2023-10-16 03:32:15,353][05218] Updated weights for policy 0, policy_version 19412 (0.0011) -[2023-10-16 03:32:15,732][05218] Updated weights for policy 0, policy_version 19422 (0.0009) -[2023-10-16 03:32:16,467][05219] Updated weights for policy 1, policy_version 19330 (0.0007) -[2023-10-16 03:32:16,828][05219] Updated weights for policy 1, policy_version 19340 (0.0008) -[2023-10-16 03:32:17,201][05219] Updated weights for policy 1, policy_version 19350 (0.0007) -[2023-10-16 03:32:17,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 39682048. Throughput: 0: 1794.2, 1: 1803.3. Samples: 9932410. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-16 03:32:17,351][03835] Avg episode reward: [(0, '5.080'), (1, '4.520')] -[2023-10-16 03:32:17,571][05219] Updated weights for policy 1, policy_version 19360 (0.0007) -[2023-10-16 03:32:19,533][05218] Updated weights for policy 0, policy_version 19432 (0.0009) -[2023-10-16 03:32:19,910][05218] Updated weights for policy 0, policy_version 19442 (0.0007) -[2023-10-16 03:32:20,286][05218] Updated weights for policy 0, policy_version 19452 (0.0007) -[2023-10-16 03:32:21,420][05219] Updated weights for policy 1, policy_version 19370 (0.0007) -[2023-10-16 03:32:21,789][05219] Updated weights for policy 1, policy_version 19380 (0.0008) -[2023-10-16 03:32:22,164][05219] Updated weights for policy 1, policy_version 19390 (0.0007) -[2023-10-16 03:32:22,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 39780352. Throughput: 0: 1794.6, 1: 1800.1. Samples: 9953604. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-16 03:32:22,351][03835] Avg episode reward: [(0, '5.160'), (1, '4.770')] -[2023-10-16 03:32:24,084][05218] Updated weights for policy 0, policy_version 19462 (0.0008) -[2023-10-16 03:32:24,451][05218] Updated weights for policy 0, policy_version 19472 (0.0009) -[2023-10-16 03:32:24,822][05218] Updated weights for policy 0, policy_version 19482 (0.0008) -[2023-10-16 03:32:25,850][05219] Updated weights for policy 1, policy_version 19400 (0.0008) -[2023-10-16 03:32:26,209][05219] Updated weights for policy 1, policy_version 19410 (0.0009) -[2023-10-16 03:32:26,573][05219] Updated weights for policy 1, policy_version 19420 (0.0010) -[2023-10-16 03:32:27,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14440.2). Total num frames: 39845888. Throughput: 0: 1790.1, 1: 1802.9. Samples: 9964500. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-16 03:32:27,351][03835] Avg episode reward: [(0, '5.460'), (1, '3.980')] -[2023-10-16 03:32:28,599][05218] Updated weights for policy 0, policy_version 19492 (0.0008) -[2023-10-16 03:32:28,984][05218] Updated weights for policy 0, policy_version 19502 (0.0009) -[2023-10-16 03:32:29,347][05218] Updated weights for policy 0, policy_version 19512 (0.0007) -[2023-10-16 03:32:30,213][05219] Updated weights for policy 1, policy_version 19430 (0.0009) -[2023-10-16 03:32:30,574][05219] Updated weights for policy 1, policy_version 19440 (0.0008) -[2023-10-16 03:32:30,943][05219] Updated weights for policy 1, policy_version 19450 (0.0010) -[2023-10-16 03:32:32,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 39911424. Throughput: 0: 1799.4, 1: 1799.2. Samples: 9986120. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-16 03:32:32,351][03835] Avg episode reward: [(0, '5.040'), (1, '4.650')] -[2023-10-16 03:32:33,049][05218] Updated weights for policy 0, policy_version 19522 (0.0009) -[2023-10-16 03:32:33,420][05218] Updated weights for policy 0, policy_version 19532 (0.0008) -[2023-10-16 03:32:33,801][05218] Updated weights for policy 0, policy_version 19542 (0.0007) -[2023-10-16 03:32:34,172][05218] Updated weights for policy 0, policy_version 19552 (0.0009) -[2023-10-16 03:32:34,643][05219] Updated weights for policy 1, policy_version 19460 (0.0008) -[2023-10-16 03:32:35,015][05219] Updated weights for policy 1, policy_version 19470 (0.0007) -[2023-10-16 03:32:35,385][05219] Updated weights for policy 1, policy_version 19480 (0.0007) -[2023-10-16 03:32:37,351][03835] Fps is (10 sec: 13106.6, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 39976960. Throughput: 0: 1809.6, 1: 1793.1. Samples: 10008692. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:32:37,352][03835] Avg episode reward: [(0, '4.710'), (1, '4.340')] -[2023-10-16 03:32:37,834][05218] Updated weights for policy 0, policy_version 19562 (0.0011) -[2023-10-16 03:32:38,218][05218] Updated weights for policy 0, policy_version 19572 (0.0008) -[2023-10-16 03:32:38,598][05218] Updated weights for policy 0, policy_version 19582 (0.0008) -[2023-10-16 03:32:39,053][05219] Updated weights for policy 1, policy_version 19490 (0.0011) -[2023-10-16 03:32:39,425][05219] Updated weights for policy 1, policy_version 19500 (0.0009) -[2023-10-16 03:32:39,791][05219] Updated weights for policy 1, policy_version 19510 (0.0008) -[2023-10-16 03:32:40,154][05219] Updated weights for policy 1, policy_version 19520 (0.0007) -[2023-10-16 03:32:42,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 40042496. Throughput: 0: 1803.1, 1: 1797.3. Samples: 10018782. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:32:42,351][03835] Avg episode reward: [(0, '4.650'), (1, '4.440')] -[2023-10-16 03:32:42,413][05218] Updated weights for policy 0, policy_version 19592 (0.0007) -[2023-10-16 03:32:42,789][05218] Updated weights for policy 0, policy_version 19602 (0.0008) -[2023-10-16 03:32:43,170][05218] Updated weights for policy 0, policy_version 19612 (0.0008) -[2023-10-16 03:32:43,992][05219] Updated weights for policy 1, policy_version 19530 (0.0009) -[2023-10-16 03:32:44,356][05219] Updated weights for policy 1, policy_version 19540 (0.0010) -[2023-10-16 03:32:44,737][05219] Updated weights for policy 1, policy_version 19550 (0.0010) -[2023-10-16 03:32:46,805][05218] Updated weights for policy 0, policy_version 19622 (0.0009) -[2023-10-16 03:32:47,177][05218] Updated weights for policy 0, policy_version 19632 (0.0008) -[2023-10-16 03:32:47,350][03835] Fps is (10 sec: 13107.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 40108032. Throughput: 0: 1807.2, 1: 1794.6. Samples: 10040766. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:32:47,351][03835] Avg episode reward: [(0, '4.830'), (1, '4.650')] -[2023-10-16 03:32:47,549][05218] Updated weights for policy 0, policy_version 19642 (0.0010) -[2023-10-16 03:32:48,521][05219] Updated weights for policy 1, policy_version 19560 (0.0009) -[2023-10-16 03:32:48,887][05219] Updated weights for policy 1, policy_version 19570 (0.0009) -[2023-10-16 03:32:49,267][05219] Updated weights for policy 1, policy_version 19580 (0.0009) -[2023-10-16 03:32:51,363][05218] Updated weights for policy 0, policy_version 19652 (0.0011) -[2023-10-16 03:32:51,734][05218] Updated weights for policy 0, policy_version 19662 (0.0010) -[2023-10-16 03:32:52,109][05218] Updated weights for policy 0, policy_version 19672 (0.0011) -[2023-10-16 03:32:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 40173568. Throughput: 0: 1797.7, 1: 1790.2. Samples: 10061614. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:32:52,351][03835] Avg episode reward: [(0, '5.130'), (1, '4.330')] -[2023-10-16 03:32:53,048][05219] Updated weights for policy 1, policy_version 19590 (0.0008) -[2023-10-16 03:32:53,417][05219] Updated weights for policy 1, policy_version 19600 (0.0010) -[2023-10-16 03:32:53,791][05219] Updated weights for policy 1, policy_version 19610 (0.0009) -[2023-10-16 03:32:55,928][05218] Updated weights for policy 0, policy_version 19682 (0.0010) -[2023-10-16 03:32:56,313][05218] Updated weights for policy 0, policy_version 19692 (0.0009) -[2023-10-16 03:32:56,686][05218] Updated weights for policy 0, policy_version 19702 (0.0009) -[2023-10-16 03:32:57,066][05218] Updated weights for policy 0, policy_version 19712 (0.0007) -[2023-10-16 03:32:57,350][03835] Fps is (10 sec: 16383.5, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 40271872. Throughput: 0: 1791.1, 1: 1791.5. Samples: 10072542. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 03:32:57,352][03835] Avg episode reward: [(0, '4.840'), (1, '4.940')] -[2023-10-16 03:32:57,532][05219] Updated weights for policy 1, policy_version 19620 (0.0007) -[2023-10-16 03:32:57,890][05219] Updated weights for policy 1, policy_version 19630 (0.0007) -[2023-10-16 03:32:58,257][05219] Updated weights for policy 1, policy_version 19640 (0.0008) -[2023-10-16 03:33:00,637][05218] Updated weights for policy 0, policy_version 19722 (0.0008) -[2023-10-16 03:33:01,017][05218] Updated weights for policy 0, policy_version 19732 (0.0008) -[2023-10-16 03:33:01,387][05218] Updated weights for policy 0, policy_version 19742 (0.0009) -[2023-10-16 03:33:02,022][05219] Updated weights for policy 1, policy_version 19650 (0.0008) -[2023-10-16 03:33:02,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 40337408. Throughput: 0: 1795.2, 1: 1791.6. Samples: 10093818. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 03:33:02,351][03835] Avg episode reward: [(0, '4.880'), (1, '4.890')] -[2023-10-16 03:33:02,383][05219] Updated weights for policy 1, policy_version 19660 (0.0008) -[2023-10-16 03:33:02,751][05219] Updated weights for policy 1, policy_version 19670 (0.0007) -[2023-10-16 03:33:03,110][05219] Updated weights for policy 1, policy_version 19680 (0.0007) -[2023-10-16 03:33:05,239][05218] Updated weights for policy 0, policy_version 19752 (0.0009) -[2023-10-16 03:33:05,617][05218] Updated weights for policy 0, policy_version 19762 (0.0009) -[2023-10-16 03:33:05,982][05218] Updated weights for policy 0, policy_version 19772 (0.0009) -[2023-10-16 03:33:06,925][05219] Updated weights for policy 1, policy_version 19690 (0.0007) -[2023-10-16 03:33:07,295][05219] Updated weights for policy 1, policy_version 19700 (0.0007) -[2023-10-16 03:33:07,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 40402944. Throughput: 0: 1790.9, 1: 1802.8. Samples: 10115322. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 03:33:07,351][03835] Avg episode reward: [(0, '4.860'), (1, '5.110')] -[2023-10-16 03:33:07,656][05219] Updated weights for policy 1, policy_version 19710 (0.0007) -[2023-10-16 03:33:09,602][05218] Updated weights for policy 0, policy_version 19782 (0.0010) -[2023-10-16 03:33:09,981][05218] Updated weights for policy 0, policy_version 19792 (0.0007) -[2023-10-16 03:33:10,361][05218] Updated weights for policy 0, policy_version 19802 (0.0008) -[2023-10-16 03:33:11,411][05219] Updated weights for policy 1, policy_version 19720 (0.0009) -[2023-10-16 03:33:11,772][05219] Updated weights for policy 1, policy_version 19730 (0.0008) -[2023-10-16 03:33:12,125][05219] Updated weights for policy 1, policy_version 19740 (0.0008) -[2023-10-16 03:33:12,350][03835] Fps is (10 sec: 16383.5, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 40501248. Throughput: 0: 1804.5, 1: 1787.7. Samples: 10126150. Policy #0 lag: (min: 29.0, avg: 29.5, max: 43.0) -[2023-10-16 03:33:12,352][03835] Avg episode reward: [(0, '5.130'), (1, '5.460')] -[2023-10-16 03:33:14,137][05218] Updated weights for policy 0, policy_version 19812 (0.0011) -[2023-10-16 03:33:14,509][05218] Updated weights for policy 0, policy_version 19822 (0.0010) -[2023-10-16 03:33:14,875][05218] Updated weights for policy 0, policy_version 19832 (0.0009) -[2023-10-16 03:33:15,904][05219] Updated weights for policy 1, policy_version 19750 (0.0008) -[2023-10-16 03:33:16,266][05219] Updated weights for policy 1, policy_version 19760 (0.0008) -[2023-10-16 03:33:16,628][05219] Updated weights for policy 1, policy_version 19770 (0.0010) -[2023-10-16 03:33:17,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 40566784. Throughput: 0: 1787.6, 1: 1797.0. Samples: 10147424. Policy #0 lag: (min: 29.0, avg: 29.5, max: 43.0) -[2023-10-16 03:33:17,351][03835] Avg episode reward: [(0, '5.450'), (1, '5.130')] -[2023-10-16 03:33:18,650][05218] Updated weights for policy 0, policy_version 19842 (0.0011) -[2023-10-16 03:33:19,011][05218] Updated weights for policy 0, policy_version 19852 (0.0010) -[2023-10-16 03:33:19,384][05218] Updated weights for policy 0, policy_version 19862 (0.0007) -[2023-10-16 03:33:19,763][05218] Updated weights for policy 0, policy_version 19872 (0.0009) -[2023-10-16 03:33:20,472][05219] Updated weights for policy 1, policy_version 19780 (0.0009) -[2023-10-16 03:33:20,834][05219] Updated weights for policy 1, policy_version 19790 (0.0008) -[2023-10-16 03:33:21,192][05219] Updated weights for policy 1, policy_version 19800 (0.0008) -[2023-10-16 03:33:22,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 40632320. Throughput: 0: 1781.6, 1: 1776.1. Samples: 10168788. Policy #0 lag: (min: 29.0, avg: 29.5, max: 43.0) -[2023-10-16 03:33:22,351][03835] Avg episode reward: [(0, '5.010'), (1, '5.070')] -[2023-10-16 03:33:23,502][05218] Updated weights for policy 0, policy_version 19882 (0.0007) -[2023-10-16 03:33:23,876][05218] Updated weights for policy 0, policy_version 19892 (0.0008) -[2023-10-16 03:33:24,256][05218] Updated weights for policy 0, policy_version 19902 (0.0009) -[2023-10-16 03:33:25,147][05219] Updated weights for policy 1, policy_version 19810 (0.0009) -[2023-10-16 03:33:25,509][05219] Updated weights for policy 1, policy_version 19820 (0.0008) -[2023-10-16 03:33:25,867][05219] Updated weights for policy 1, policy_version 19830 (0.0009) -[2023-10-16 03:33:26,232][05219] Updated weights for policy 1, policy_version 19840 (0.0008) -[2023-10-16 03:33:27,351][03835] Fps is (10 sec: 13106.6, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 40697856. Throughput: 0: 1778.2, 1: 1800.2. Samples: 10179810. Policy #0 lag: (min: 29.0, avg: 29.5, max: 43.0) -[2023-10-16 03:33:27,352][03835] Avg episode reward: [(0, '5.110'), (1, '4.810')] -[2023-10-16 03:33:28,042][05218] Updated weights for policy 0, policy_version 19912 (0.0007) -[2023-10-16 03:33:28,428][05218] Updated weights for policy 0, policy_version 19922 (0.0007) -[2023-10-16 03:33:28,801][05218] Updated weights for policy 0, policy_version 19932 (0.0010) -[2023-10-16 03:33:30,032][05219] Updated weights for policy 1, policy_version 19850 (0.0008) -[2023-10-16 03:33:30,393][05219] Updated weights for policy 1, policy_version 19860 (0.0007) -[2023-10-16 03:33:30,763][05219] Updated weights for policy 1, policy_version 19870 (0.0009) -[2023-10-16 03:33:32,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 40763392. Throughput: 0: 1775.8, 1: 1772.1. Samples: 10200420. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:33:32,351][03835] Avg episode reward: [(0, '4.530'), (1, '4.630')] -[2023-10-16 03:33:32,520][05218] Updated weights for policy 0, policy_version 19942 (0.0009) -[2023-10-16 03:33:32,892][05218] Updated weights for policy 0, policy_version 19952 (0.0009) -[2023-10-16 03:33:33,265][05218] Updated weights for policy 0, policy_version 19962 (0.0009) -[2023-10-16 03:33:34,474][05219] Updated weights for policy 1, policy_version 19880 (0.0007) -[2023-10-16 03:33:34,841][05219] Updated weights for policy 1, policy_version 19890 (0.0008) -[2023-10-16 03:33:35,200][05219] Updated weights for policy 1, policy_version 19900 (0.0008) -[2023-10-16 03:33:36,957][05218] Updated weights for policy 0, policy_version 19972 (0.0009) -[2023-10-16 03:33:37,332][05218] Updated weights for policy 0, policy_version 19982 (0.0010) -[2023-10-16 03:33:37,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 40828928. Throughput: 0: 1797.3, 1: 1777.7. Samples: 10222488. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:33:37,351][03835] Avg episode reward: [(0, '5.130'), (1, '5.350')] -[2023-10-16 03:33:37,359][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000019904_20381696.pth... -[2023-10-16 03:33:37,396][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000018240_18677760.pth -[2023-10-16 03:33:37,708][05218] Updated weights for policy 0, policy_version 19992 (0.0009) -[2023-10-16 03:33:38,013][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000020000_20480000.pth... -[2023-10-16 03:33:38,052][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000018304_18743296.pth -[2023-10-16 03:33:38,891][05219] Updated weights for policy 1, policy_version 19910 (0.0009) -[2023-10-16 03:33:39,265][05219] Updated weights for policy 1, policy_version 19920 (0.0011) -[2023-10-16 03:33:39,634][05219] Updated weights for policy 1, policy_version 19930 (0.0011) -[2023-10-16 03:33:41,525][05218] Updated weights for policy 0, policy_version 20002 (0.0010) -[2023-10-16 03:33:41,894][05218] Updated weights for policy 0, policy_version 20012 (0.0010) -[2023-10-16 03:33:42,269][05218] Updated weights for policy 0, policy_version 20022 (0.0010) -[2023-10-16 03:33:42,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 40894464. Throughput: 0: 1785.4, 1: 1777.7. Samples: 10232882. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:33:42,351][03835] Avg episode reward: [(0, '5.210'), (1, '5.300')] -[2023-10-16 03:33:42,644][05218] Updated weights for policy 0, policy_version 20032 (0.0010) -[2023-10-16 03:33:43,364][05219] Updated weights for policy 1, policy_version 19940 (0.0008) -[2023-10-16 03:33:43,727][05219] Updated weights for policy 1, policy_version 19950 (0.0008) -[2023-10-16 03:33:44,092][05219] Updated weights for policy 1, policy_version 19960 (0.0007) -[2023-10-16 03:33:46,391][05218] Updated weights for policy 0, policy_version 20042 (0.0008) -[2023-10-16 03:33:46,758][05218] Updated weights for policy 0, policy_version 20052 (0.0010) -[2023-10-16 03:33:47,130][05218] Updated weights for policy 0, policy_version 20062 (0.0007) -[2023-10-16 03:33:47,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 40992768. Throughput: 0: 1802.7, 1: 1773.2. Samples: 10254734. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:33:47,351][03835] Avg episode reward: [(0, '5.470'), (1, '5.620')] -[2023-10-16 03:33:47,804][05219] Updated weights for policy 1, policy_version 19970 (0.0008) -[2023-10-16 03:33:48,164][05219] Updated weights for policy 1, policy_version 19980 (0.0008) -[2023-10-16 03:33:48,527][05219] Updated weights for policy 1, policy_version 19990 (0.0008) -[2023-10-16 03:33:48,890][05219] Updated weights for policy 1, policy_version 20000 (0.0008) -[2023-10-16 03:33:50,755][05218] Updated weights for policy 0, policy_version 20072 (0.0010) -[2023-10-16 03:33:51,127][05218] Updated weights for policy 0, policy_version 20082 (0.0007) -[2023-10-16 03:33:51,503][05218] Updated weights for policy 0, policy_version 20092 (0.0007) -[2023-10-16 03:33:52,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 41058304. Throughput: 0: 1783.0, 1: 1795.4. Samples: 10276350. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:33:52,351][03835] Avg episode reward: [(0, '5.590'), (1, '5.710')] -[2023-10-16 03:33:52,848][05219] Updated weights for policy 1, policy_version 20010 (0.0007) -[2023-10-16 03:33:53,215][05219] Updated weights for policy 1, policy_version 20020 (0.0008) -[2023-10-16 03:33:53,571][05219] Updated weights for policy 1, policy_version 20030 (0.0008) -[2023-10-16 03:33:55,227][05218] Updated weights for policy 0, policy_version 20102 (0.0008) -[2023-10-16 03:33:55,609][05218] Updated weights for policy 0, policy_version 20112 (0.0010) -[2023-10-16 03:33:55,988][05218] Updated weights for policy 0, policy_version 20122 (0.0008) -[2023-10-16 03:33:57,242][05219] Updated weights for policy 1, policy_version 20040 (0.0010) -[2023-10-16 03:33:57,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 41123840. Throughput: 0: 1801.8, 1: 1779.4. Samples: 10287302. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:33:57,351][03835] Avg episode reward: [(0, '4.900'), (1, '5.360')] -[2023-10-16 03:33:57,609][05219] Updated weights for policy 1, policy_version 20050 (0.0007) -[2023-10-16 03:33:57,972][05219] Updated weights for policy 1, policy_version 20060 (0.0008) -[2023-10-16 03:33:59,643][05218] Updated weights for policy 0, policy_version 20132 (0.0009) -[2023-10-16 03:34:00,023][05218] Updated weights for policy 0, policy_version 20142 (0.0007) -[2023-10-16 03:34:00,399][05218] Updated weights for policy 0, policy_version 20152 (0.0007) -[2023-10-16 03:34:01,737][05219] Updated weights for policy 1, policy_version 20070 (0.0007) -[2023-10-16 03:34:02,096][05219] Updated weights for policy 1, policy_version 20080 (0.0010) -[2023-10-16 03:34:02,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 41189376. Throughput: 0: 1792.8, 1: 1797.1. Samples: 10308968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:34:02,351][03835] Avg episode reward: [(0, '5.340'), (1, '5.480')] -[2023-10-16 03:34:02,466][05219] Updated weights for policy 1, policy_version 20090 (0.0008) -[2023-10-16 03:34:04,200][05218] Updated weights for policy 0, policy_version 20162 (0.0008) -[2023-10-16 03:34:04,574][05218] Updated weights for policy 0, policy_version 20172 (0.0008) -[2023-10-16 03:34:04,958][05218] Updated weights for policy 0, policy_version 20182 (0.0008) -[2023-10-16 03:34:05,329][05218] Updated weights for policy 0, policy_version 20192 (0.0009) -[2023-10-16 03:34:06,312][05219] Updated weights for policy 1, policy_version 20100 (0.0009) -[2023-10-16 03:34:06,676][05219] Updated weights for policy 1, policy_version 20110 (0.0008) -[2023-10-16 03:34:07,043][05219] Updated weights for policy 1, policy_version 20120 (0.0009) -[2023-10-16 03:34:07,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 41287680. Throughput: 0: 1795.5, 1: 1794.3. Samples: 10330328. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-16 03:34:07,351][03835] Avg episode reward: [(0, '4.680'), (1, '4.900')] -[2023-10-16 03:34:09,078][05218] Updated weights for policy 0, policy_version 20202 (0.0011) -[2023-10-16 03:34:09,442][05218] Updated weights for policy 0, policy_version 20212 (0.0009) -[2023-10-16 03:34:09,829][05218] Updated weights for policy 0, policy_version 20222 (0.0007) -[2023-10-16 03:34:10,679][05219] Updated weights for policy 1, policy_version 20130 (0.0008) -[2023-10-16 03:34:11,033][05219] Updated weights for policy 1, policy_version 20140 (0.0007) -[2023-10-16 03:34:11,408][05219] Updated weights for policy 1, policy_version 20150 (0.0008) -[2023-10-16 03:34:11,771][05219] Updated weights for policy 1, policy_version 20160 (0.0007) -[2023-10-16 03:34:12,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 41353216. Throughput: 0: 1798.6, 1: 1795.2. Samples: 10341532. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-16 03:34:12,351][03835] Avg episode reward: [(0, '5.290'), (1, '5.290')] -[2023-10-16 03:34:13,349][05218] Updated weights for policy 0, policy_version 20232 (0.0009) -[2023-10-16 03:34:13,725][05218] Updated weights for policy 0, policy_version 20242 (0.0008) -[2023-10-16 03:34:14,101][05218] Updated weights for policy 0, policy_version 20252 (0.0007) -[2023-10-16 03:34:15,501][05219] Updated weights for policy 1, policy_version 20170 (0.0009) -[2023-10-16 03:34:15,875][05219] Updated weights for policy 1, policy_version 20180 (0.0009) -[2023-10-16 03:34:16,236][05219] Updated weights for policy 1, policy_version 20190 (0.0009) -[2023-10-16 03:34:17,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 41418752. Throughput: 0: 1815.7, 1: 1802.3. Samples: 10363230. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-16 03:34:17,351][03835] Avg episode reward: [(0, '4.980'), (1, '5.180')] -[2023-10-16 03:34:17,917][05218] Updated weights for policy 0, policy_version 20262 (0.0007) -[2023-10-16 03:34:18,297][05218] Updated weights for policy 0, policy_version 20272 (0.0009) -[2023-10-16 03:34:18,671][05218] Updated weights for policy 0, policy_version 20282 (0.0008) -[2023-10-16 03:34:19,992][05219] Updated weights for policy 1, policy_version 20200 (0.0007) -[2023-10-16 03:34:20,368][05219] Updated weights for policy 1, policy_version 20210 (0.0010) -[2023-10-16 03:34:20,732][05219] Updated weights for policy 1, policy_version 20220 (0.0010) -[2023-10-16 03:34:22,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 41484288. Throughput: 0: 1822.6, 1: 1790.2. Samples: 10385064. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-16 03:34:22,351][03835] Avg episode reward: [(0, '4.750'), (1, '5.020')] -[2023-10-16 03:34:22,449][05218] Updated weights for policy 0, policy_version 20292 (0.0007) -[2023-10-16 03:34:22,826][05218] Updated weights for policy 0, policy_version 20302 (0.0007) -[2023-10-16 03:34:23,201][05218] Updated weights for policy 0, policy_version 20312 (0.0008) -[2023-10-16 03:34:24,601][05219] Updated weights for policy 1, policy_version 20230 (0.0010) -[2023-10-16 03:34:24,963][05219] Updated weights for policy 1, policy_version 20240 (0.0008) -[2023-10-16 03:34:25,333][05219] Updated weights for policy 1, policy_version 20250 (0.0007) -[2023-10-16 03:34:26,992][05218] Updated weights for policy 0, policy_version 20322 (0.0009) -[2023-10-16 03:34:27,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 41549824. Throughput: 0: 1805.1, 1: 1804.4. Samples: 10395310. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-16 03:34:27,351][03835] Avg episode reward: [(0, '5.850'), (1, '5.190')] -[2023-10-16 03:34:27,372][05218] Updated weights for policy 0, policy_version 20332 (0.0007) -[2023-10-16 03:34:27,738][05218] Updated weights for policy 0, policy_version 20342 (0.0011) -[2023-10-16 03:34:28,113][04766] Saving new best policy, reward=5.850! -[2023-10-16 03:34:28,116][05218] Updated weights for policy 0, policy_version 20352 (0.0012) -[2023-10-16 03:34:29,058][05219] Updated weights for policy 1, policy_version 20260 (0.0008) -[2023-10-16 03:34:29,423][05219] Updated weights for policy 1, policy_version 20270 (0.0007) -[2023-10-16 03:34:29,776][05219] Updated weights for policy 1, policy_version 20280 (0.0007) -[2023-10-16 03:34:31,903][05218] Updated weights for policy 0, policy_version 20362 (0.0009) -[2023-10-16 03:34:32,271][05218] Updated weights for policy 0, policy_version 20372 (0.0009) -[2023-10-16 03:34:32,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 41615360. Throughput: 0: 1810.4, 1: 1796.7. Samples: 10417054. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-16 03:34:32,351][03835] Avg episode reward: [(0, '4.530'), (1, '4.700')] -[2023-10-16 03:34:32,637][05218] Updated weights for policy 0, policy_version 20382 (0.0009) -[2023-10-16 03:34:33,418][05219] Updated weights for policy 1, policy_version 20290 (0.0007) -[2023-10-16 03:34:33,780][05219] Updated weights for policy 1, policy_version 20300 (0.0008) -[2023-10-16 03:34:34,145][05219] Updated weights for policy 1, policy_version 20310 (0.0008) -[2023-10-16 03:34:34,510][05219] Updated weights for policy 1, policy_version 20320 (0.0009) -[2023-10-16 03:34:36,322][05218] Updated weights for policy 0, policy_version 20392 (0.0009) -[2023-10-16 03:34:36,708][05218] Updated weights for policy 0, policy_version 20402 (0.0009) -[2023-10-16 03:34:37,085][05218] Updated weights for policy 0, policy_version 20412 (0.0009) -[2023-10-16 03:34:37,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 41713664. Throughput: 0: 1800.0, 1: 1797.3. Samples: 10438230. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-16 03:34:37,351][03835] Avg episode reward: [(0, '5.120'), (1, '5.290')] -[2023-10-16 03:34:38,332][05219] Updated weights for policy 1, policy_version 20330 (0.0010) -[2023-10-16 03:34:38,703][05219] Updated weights for policy 1, policy_version 20340 (0.0008) -[2023-10-16 03:34:39,061][05219] Updated weights for policy 1, policy_version 20350 (0.0008) -[2023-10-16 03:34:40,873][05218] Updated weights for policy 0, policy_version 20422 (0.0010) -[2023-10-16 03:34:41,241][05218] Updated weights for policy 0, policy_version 20432 (0.0010) -[2023-10-16 03:34:41,615][05218] Updated weights for policy 0, policy_version 20442 (0.0007) -[2023-10-16 03:34:42,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 41779200. Throughput: 0: 1804.3, 1: 1799.7. Samples: 10449482. Policy #0 lag: (min: 0.0, avg: 26.2, max: 32.0) -[2023-10-16 03:34:42,352][03835] Avg episode reward: [(0, '4.570'), (1, '4.810')] -[2023-10-16 03:34:42,786][05219] Updated weights for policy 1, policy_version 20360 (0.0008) -[2023-10-16 03:34:43,160][05219] Updated weights for policy 1, policy_version 20370 (0.0010) -[2023-10-16 03:34:43,526][05219] Updated weights for policy 1, policy_version 20380 (0.0008) -[2023-10-16 03:34:45,368][05218] Updated weights for policy 0, policy_version 20452 (0.0008) -[2023-10-16 03:34:45,744][05218] Updated weights for policy 0, policy_version 20462 (0.0008) -[2023-10-16 03:34:46,119][05218] Updated weights for policy 0, policy_version 20472 (0.0008) -[2023-10-16 03:34:46,993][05219] Updated weights for policy 1, policy_version 20390 (0.0009) -[2023-10-16 03:34:47,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 41844736. Throughput: 0: 1791.6, 1: 1799.6. Samples: 10470574. Policy #0 lag: (min: 0.0, avg: 26.2, max: 32.0) -[2023-10-16 03:34:47,351][03835] Avg episode reward: [(0, '4.790'), (1, '4.860')] -[2023-10-16 03:34:47,356][05219] Updated weights for policy 1, policy_version 20400 (0.0011) -[2023-10-16 03:34:47,726][05219] Updated weights for policy 1, policy_version 20410 (0.0008) -[2023-10-16 03:34:49,751][05218] Updated weights for policy 0, policy_version 20482 (0.0008) -[2023-10-16 03:34:50,128][05218] Updated weights for policy 0, policy_version 20492 (0.0011) -[2023-10-16 03:34:50,502][05218] Updated weights for policy 0, policy_version 20502 (0.0009) -[2023-10-16 03:34:50,875][05218] Updated weights for policy 0, policy_version 20512 (0.0009) -[2023-10-16 03:34:51,564][05219] Updated weights for policy 1, policy_version 20420 (0.0008) -[2023-10-16 03:34:51,942][05219] Updated weights for policy 1, policy_version 20430 (0.0007) -[2023-10-16 03:34:52,301][05219] Updated weights for policy 1, policy_version 20440 (0.0010) -[2023-10-16 03:34:52,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 41910272. Throughput: 0: 1787.0, 1: 1808.2. Samples: 10492110. Policy #0 lag: (min: 0.0, avg: 26.2, max: 32.0) -[2023-10-16 03:34:52,351][03835] Avg episode reward: [(0, '5.170'), (1, '5.120')] -[2023-10-16 03:34:54,714][05218] Updated weights for policy 0, policy_version 20522 (0.0009) -[2023-10-16 03:34:55,091][05218] Updated weights for policy 0, policy_version 20532 (0.0008) -[2023-10-16 03:34:55,471][05218] Updated weights for policy 0, policy_version 20542 (0.0009) -[2023-10-16 03:34:56,119][05219] Updated weights for policy 1, policy_version 20450 (0.0009) -[2023-10-16 03:34:56,493][05219] Updated weights for policy 1, policy_version 20460 (0.0007) -[2023-10-16 03:34:56,851][05219] Updated weights for policy 1, policy_version 20470 (0.0008) -[2023-10-16 03:34:57,219][05219] Updated weights for policy 1, policy_version 20480 (0.0008) -[2023-10-16 03:34:57,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 42008576. Throughput: 0: 1790.2, 1: 1795.5. Samples: 10502892. Policy #0 lag: (min: 0.0, avg: 26.2, max: 32.0) -[2023-10-16 03:34:57,351][03835] Avg episode reward: [(0, '4.970'), (1, '4.790')] -[2023-10-16 03:34:59,256][05218] Updated weights for policy 0, policy_version 20552 (0.0010) -[2023-10-16 03:34:59,633][05218] Updated weights for policy 0, policy_version 20562 (0.0009) -[2023-10-16 03:35:00,010][05218] Updated weights for policy 0, policy_version 20572 (0.0011) -[2023-10-16 03:35:00,899][05219] Updated weights for policy 1, policy_version 20490 (0.0007) -[2023-10-16 03:35:01,266][05219] Updated weights for policy 1, policy_version 20500 (0.0009) -[2023-10-16 03:35:01,625][05219] Updated weights for policy 1, policy_version 20510 (0.0007) -[2023-10-16 03:35:02,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 42074112. Throughput: 0: 1775.9, 1: 1810.3. Samples: 10524606. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:35:02,351][03835] Avg episode reward: [(0, '5.490'), (1, '5.060')] -[2023-10-16 03:35:03,930][05218] Updated weights for policy 0, policy_version 20582 (0.0009) -[2023-10-16 03:35:04,310][05218] Updated weights for policy 0, policy_version 20592 (0.0008) -[2023-10-16 03:35:04,691][05218] Updated weights for policy 0, policy_version 20602 (0.0007) -[2023-10-16 03:35:05,467][05219] Updated weights for policy 1, policy_version 20520 (0.0007) -[2023-10-16 03:35:05,846][05219] Updated weights for policy 1, policy_version 20530 (0.0008) -[2023-10-16 03:35:06,198][05219] Updated weights for policy 1, policy_version 20540 (0.0009) -[2023-10-16 03:35:07,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 42139648. Throughput: 0: 1783.3, 1: 1801.2. Samples: 10546370. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:35:07,352][03835] Avg episode reward: [(0, '5.150'), (1, '5.370')] -[2023-10-16 03:35:08,293][05218] Updated weights for policy 0, policy_version 20612 (0.0008) -[2023-10-16 03:35:08,665][05218] Updated weights for policy 0, policy_version 20622 (0.0009) -[2023-10-16 03:35:09,046][05218] Updated weights for policy 0, policy_version 20632 (0.0009) -[2023-10-16 03:35:09,719][05219] Updated weights for policy 1, policy_version 20550 (0.0009) -[2023-10-16 03:35:10,077][05219] Updated weights for policy 1, policy_version 20560 (0.0008) -[2023-10-16 03:35:10,447][05219] Updated weights for policy 1, policy_version 20570 (0.0009) -[2023-10-16 03:35:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 42205184. Throughput: 0: 1785.2, 1: 1807.1. Samples: 10556962. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:35:12,351][03835] Avg episode reward: [(0, '4.910'), (1, '4.840')] -[2023-10-16 03:35:12,774][05218] Updated weights for policy 0, policy_version 20642 (0.0008) -[2023-10-16 03:35:13,150][05218] Updated weights for policy 0, policy_version 20652 (0.0009) -[2023-10-16 03:35:13,531][05218] Updated weights for policy 0, policy_version 20662 (0.0007) -[2023-10-16 03:35:13,898][05218] Updated weights for policy 0, policy_version 20672 (0.0008) -[2023-10-16 03:35:14,038][05219] Updated weights for policy 1, policy_version 20580 (0.0008) -[2023-10-16 03:35:14,404][05219] Updated weights for policy 1, policy_version 20590 (0.0010) -[2023-10-16 03:35:14,778][05219] Updated weights for policy 1, policy_version 20600 (0.0008) -[2023-10-16 03:35:17,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 42270720. Throughput: 0: 1790.3, 1: 1807.0. Samples: 10578934. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:35:17,351][03835] Avg episode reward: [(0, '4.920'), (1, '5.070')] -[2023-10-16 03:35:17,599][05218] Updated weights for policy 0, policy_version 20682 (0.0008) -[2023-10-16 03:35:17,978][05218] Updated weights for policy 0, policy_version 20692 (0.0010) -[2023-10-16 03:35:18,360][05218] Updated weights for policy 0, policy_version 20702 (0.0008) -[2023-10-16 03:35:18,601][05219] Updated weights for policy 1, policy_version 20610 (0.0007) -[2023-10-16 03:35:18,969][05219] Updated weights for policy 1, policy_version 20620 (0.0008) -[2023-10-16 03:35:19,339][05219] Updated weights for policy 1, policy_version 20630 (0.0007) -[2023-10-16 03:35:19,708][05219] Updated weights for policy 1, policy_version 20640 (0.0009) -[2023-10-16 03:35:21,977][05218] Updated weights for policy 0, policy_version 20712 (0.0010) -[2023-10-16 03:35:22,346][05218] Updated weights for policy 0, policy_version 20722 (0.0010) -[2023-10-16 03:35:22,351][03835] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 42336256. Throughput: 0: 1809.4, 1: 1801.5. Samples: 10600722. Policy #0 lag: (min: 19.0, avg: 19.4, max: 32.0) -[2023-10-16 03:35:22,352][03835] Avg episode reward: [(0, '4.620'), (1, '4.630')] -[2023-10-16 03:35:22,727][05218] Updated weights for policy 0, policy_version 20732 (0.0009) -[2023-10-16 03:35:23,544][05219] Updated weights for policy 1, policy_version 20650 (0.0009) -[2023-10-16 03:35:23,918][05219] Updated weights for policy 1, policy_version 20660 (0.0007) -[2023-10-16 03:35:24,278][05219] Updated weights for policy 1, policy_version 20670 (0.0008) -[2023-10-16 03:35:26,506][05218] Updated weights for policy 0, policy_version 20742 (0.0009) -[2023-10-16 03:35:26,878][05218] Updated weights for policy 0, policy_version 20752 (0.0008) -[2023-10-16 03:35:27,251][05218] Updated weights for policy 0, policy_version 20762 (0.0010) -[2023-10-16 03:35:27,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 42401792. Throughput: 0: 1795.0, 1: 1800.3. Samples: 10611270. Policy #0 lag: (min: 19.0, avg: 19.4, max: 32.0) -[2023-10-16 03:35:27,351][03835] Avg episode reward: [(0, '4.560'), (1, '5.210')] -[2023-10-16 03:35:28,037][05219] Updated weights for policy 1, policy_version 20680 (0.0009) -[2023-10-16 03:35:28,401][05219] Updated weights for policy 1, policy_version 20690 (0.0007) -[2023-10-16 03:35:28,774][05219] Updated weights for policy 1, policy_version 20700 (0.0007) -[2023-10-16 03:35:31,180][05218] Updated weights for policy 0, policy_version 20772 (0.0008) -[2023-10-16 03:35:31,554][05218] Updated weights for policy 0, policy_version 20782 (0.0009) -[2023-10-16 03:35:31,933][05218] Updated weights for policy 0, policy_version 20792 (0.0010) -[2023-10-16 03:35:32,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 42500096. Throughput: 0: 1812.9, 1: 1799.4. Samples: 10633128. Policy #0 lag: (min: 19.0, avg: 19.4, max: 32.0) -[2023-10-16 03:35:32,351][03835] Avg episode reward: [(0, '4.780'), (1, '4.950')] -[2023-10-16 03:35:32,633][05219] Updated weights for policy 1, policy_version 20710 (0.0008) -[2023-10-16 03:35:33,001][05219] Updated weights for policy 1, policy_version 20720 (0.0007) -[2023-10-16 03:35:33,356][05219] Updated weights for policy 1, policy_version 20730 (0.0010) -[2023-10-16 03:35:35,532][05218] Updated weights for policy 0, policy_version 20802 (0.0011) -[2023-10-16 03:35:35,916][05218] Updated weights for policy 0, policy_version 20812 (0.0010) -[2023-10-16 03:35:36,282][05218] Updated weights for policy 0, policy_version 20822 (0.0010) -[2023-10-16 03:35:36,660][05218] Updated weights for policy 0, policy_version 20832 (0.0010) -[2023-10-16 03:35:37,253][05219] Updated weights for policy 1, policy_version 20740 (0.0008) -[2023-10-16 03:35:37,351][03835] Fps is (10 sec: 16383.3, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 42565632. Throughput: 0: 1795.9, 1: 1810.9. Samples: 10654414. Policy #0 lag: (min: 20.0, avg: 27.2, max: 52.0) -[2023-10-16 03:35:37,352][03835] Avg episode reward: [(0, '5.150'), (1, '5.160')] -[2023-10-16 03:35:37,362][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000020832_21331968.pth... -[2023-10-16 03:35:37,400][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000019136_19595264.pth -[2023-10-16 03:35:37,623][05219] Updated weights for policy 1, policy_version 20750 (0.0008) -[2023-10-16 03:35:37,990][05219] Updated weights for policy 1, policy_version 20760 (0.0008) -[2023-10-16 03:35:38,288][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000020768_21266432.pth... -[2023-10-16 03:35:38,317][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000019072_19529728.pth -[2023-10-16 03:35:40,429][05218] Updated weights for policy 0, policy_version 20842 (0.0010) -[2023-10-16 03:35:40,811][05218] Updated weights for policy 0, policy_version 20852 (0.0010) -[2023-10-16 03:35:41,181][05218] Updated weights for policy 0, policy_version 20862 (0.0010) -[2023-10-16 03:35:41,827][05219] Updated weights for policy 1, policy_version 20770 (0.0009) -[2023-10-16 03:35:42,191][05219] Updated weights for policy 1, policy_version 20780 (0.0007) -[2023-10-16 03:35:42,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 42631168. Throughput: 0: 1820.2, 1: 1791.6. Samples: 10665420. Policy #0 lag: (min: 20.0, avg: 27.2, max: 52.0) -[2023-10-16 03:35:42,351][03835] Avg episode reward: [(0, '5.240'), (1, '5.740')] -[2023-10-16 03:35:42,560][05219] Updated weights for policy 1, policy_version 20790 (0.0008) -[2023-10-16 03:35:42,936][05219] Updated weights for policy 1, policy_version 20800 (0.0008) -[2023-10-16 03:35:44,898][05218] Updated weights for policy 0, policy_version 20872 (0.0010) -[2023-10-16 03:35:45,270][05218] Updated weights for policy 0, policy_version 20882 (0.0008) -[2023-10-16 03:35:45,637][05218] Updated weights for policy 0, policy_version 20892 (0.0007) -[2023-10-16 03:35:46,695][05219] Updated weights for policy 1, policy_version 20810 (0.0008) -[2023-10-16 03:35:47,060][05219] Updated weights for policy 1, policy_version 20820 (0.0008) -[2023-10-16 03:35:47,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 42696704. Throughput: 0: 1798.8, 1: 1804.5. Samples: 10686754. Policy #0 lag: (min: 20.0, avg: 27.2, max: 52.0) -[2023-10-16 03:35:47,351][03835] Avg episode reward: [(0, '5.680'), (1, '5.170')] -[2023-10-16 03:35:47,432][05219] Updated weights for policy 1, policy_version 20830 (0.0008) -[2023-10-16 03:35:49,424][05218] Updated weights for policy 0, policy_version 20902 (0.0008) -[2023-10-16 03:35:49,810][05218] Updated weights for policy 0, policy_version 20912 (0.0007) -[2023-10-16 03:35:50,184][05218] Updated weights for policy 0, policy_version 20922 (0.0008) -[2023-10-16 03:35:51,265][05219] Updated weights for policy 1, policy_version 20840 (0.0008) -[2023-10-16 03:35:51,630][05219] Updated weights for policy 1, policy_version 20850 (0.0008) -[2023-10-16 03:35:51,993][05219] Updated weights for policy 1, policy_version 20860 (0.0009) -[2023-10-16 03:35:52,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 42795008. Throughput: 0: 1791.7, 1: 1785.5. Samples: 10707342. Policy #0 lag: (min: 20.0, avg: 27.2, max: 52.0) -[2023-10-16 03:35:52,351][03835] Avg episode reward: [(0, '5.630'), (1, '5.030')] -[2023-10-16 03:35:53,967][05218] Updated weights for policy 0, policy_version 20932 (0.0010) -[2023-10-16 03:35:54,343][05218] Updated weights for policy 0, policy_version 20942 (0.0008) -[2023-10-16 03:35:54,718][05218] Updated weights for policy 0, policy_version 20952 (0.0007) -[2023-10-16 03:35:55,786][05219] Updated weights for policy 1, policy_version 20870 (0.0009) -[2023-10-16 03:35:56,147][05219] Updated weights for policy 1, policy_version 20880 (0.0011) -[2023-10-16 03:35:56,521][05219] Updated weights for policy 1, policy_version 20890 (0.0009) -[2023-10-16 03:35:57,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 42860544. Throughput: 0: 1790.8, 1: 1794.9. Samples: 10718318. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-16 03:35:57,351][03835] Avg episode reward: [(0, '4.990'), (1, '5.540')] -[2023-10-16 03:35:58,461][05218] Updated weights for policy 0, policy_version 20962 (0.0008) -[2023-10-16 03:35:58,842][05218] Updated weights for policy 0, policy_version 20972 (0.0008) -[2023-10-16 03:35:59,210][05218] Updated weights for policy 0, policy_version 20982 (0.0007) -[2023-10-16 03:35:59,591][05218] Updated weights for policy 0, policy_version 20992 (0.0008) -[2023-10-16 03:36:00,241][05219] Updated weights for policy 1, policy_version 20900 (0.0008) -[2023-10-16 03:36:00,618][05219] Updated weights for policy 1, policy_version 20910 (0.0009) -[2023-10-16 03:36:00,984][05219] Updated weights for policy 1, policy_version 20920 (0.0009) -[2023-10-16 03:36:02,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 42926080. Throughput: 0: 1788.0, 1: 1779.1. Samples: 10739456. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-16 03:36:02,352][03835] Avg episode reward: [(0, '5.540'), (1, '4.880')] -[2023-10-16 03:36:03,350][05218] Updated weights for policy 0, policy_version 21002 (0.0009) -[2023-10-16 03:36:03,720][05218] Updated weights for policy 0, policy_version 21012 (0.0008) -[2023-10-16 03:36:04,090][05218] Updated weights for policy 0, policy_version 21022 (0.0010) -[2023-10-16 03:36:04,724][05219] Updated weights for policy 1, policy_version 20930 (0.0008) -[2023-10-16 03:36:05,085][05219] Updated weights for policy 1, policy_version 20940 (0.0008) -[2023-10-16 03:36:05,448][05219] Updated weights for policy 1, policy_version 20950 (0.0007) -[2023-10-16 03:36:05,801][05219] Updated weights for policy 1, policy_version 20960 (0.0007) -[2023-10-16 03:36:07,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 42991616. Throughput: 0: 1797.7, 1: 1774.3. Samples: 10761462. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-16 03:36:07,351][03835] Avg episode reward: [(0, '5.060'), (1, '5.170')] -[2023-10-16 03:36:07,929][05218] Updated weights for policy 0, policy_version 21032 (0.0009) -[2023-10-16 03:36:08,312][05218] Updated weights for policy 0, policy_version 21042 (0.0009) -[2023-10-16 03:36:08,692][05218] Updated weights for policy 0, policy_version 21052 (0.0008) -[2023-10-16 03:36:09,741][05219] Updated weights for policy 1, policy_version 20970 (0.0007) -[2023-10-16 03:36:10,110][05219] Updated weights for policy 1, policy_version 20980 (0.0009) -[2023-10-16 03:36:10,483][05219] Updated weights for policy 1, policy_version 20990 (0.0011) -[2023-10-16 03:36:12,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 43057152. Throughput: 0: 1777.0, 1: 1785.3. Samples: 10771574. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-16 03:36:12,351][03835] Avg episode reward: [(0, '5.090'), (1, '5.100')] -[2023-10-16 03:36:12,403][05218] Updated weights for policy 0, policy_version 21062 (0.0008) -[2023-10-16 03:36:12,774][05218] Updated weights for policy 0, policy_version 21072 (0.0008) -[2023-10-16 03:36:13,150][05218] Updated weights for policy 0, policy_version 21082 (0.0010) -[2023-10-16 03:36:14,311][05219] Updated weights for policy 1, policy_version 21000 (0.0008) -[2023-10-16 03:36:14,687][05219] Updated weights for policy 1, policy_version 21010 (0.0008) -[2023-10-16 03:36:15,058][05219] Updated weights for policy 1, policy_version 21020 (0.0009) -[2023-10-16 03:36:16,887][05218] Updated weights for policy 0, policy_version 21092 (0.0009) -[2023-10-16 03:36:17,266][05218] Updated weights for policy 0, policy_version 21102 (0.0008) -[2023-10-16 03:36:17,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 43122688. Throughput: 0: 1793.8, 1: 1767.3. Samples: 10793378. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:36:17,351][03835] Avg episode reward: [(0, '4.920'), (1, '5.100')] -[2023-10-16 03:36:17,631][05218] Updated weights for policy 0, policy_version 21112 (0.0007) -[2023-10-16 03:36:18,693][05219] Updated weights for policy 1, policy_version 21030 (0.0007) -[2023-10-16 03:36:19,064][05219] Updated weights for policy 1, policy_version 21040 (0.0008) -[2023-10-16 03:36:19,422][05219] Updated weights for policy 1, policy_version 21050 (0.0007) -[2023-10-16 03:36:21,306][05218] Updated weights for policy 0, policy_version 21122 (0.0008) -[2023-10-16 03:36:21,689][05218] Updated weights for policy 0, policy_version 21132 (0.0008) -[2023-10-16 03:36:22,058][05218] Updated weights for policy 0, policy_version 21142 (0.0007) -[2023-10-16 03:36:22,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.6, 300 sec: 14218.0). Total num frames: 43188224. Throughput: 0: 1785.9, 1: 1774.4. Samples: 10814626. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:36:22,351][03835] Avg episode reward: [(0, '5.190'), (1, '5.210')] -[2023-10-16 03:36:22,437][05218] Updated weights for policy 0, policy_version 21152 (0.0007) -[2023-10-16 03:36:23,127][05219] Updated weights for policy 1, policy_version 21060 (0.0008) -[2023-10-16 03:36:23,495][05219] Updated weights for policy 1, policy_version 21070 (0.0008) -[2023-10-16 03:36:23,855][05219] Updated weights for policy 1, policy_version 21080 (0.0009) -[2023-10-16 03:36:26,239][05218] Updated weights for policy 0, policy_version 21162 (0.0008) -[2023-10-16 03:36:26,623][05218] Updated weights for policy 0, policy_version 21172 (0.0011) -[2023-10-16 03:36:26,988][05218] Updated weights for policy 0, policy_version 21182 (0.0011) -[2023-10-16 03:36:27,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 43286528. Throughput: 0: 1784.1, 1: 1778.2. Samples: 10825726. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:36:27,351][03835] Avg episode reward: [(0, '5.380'), (1, '5.150')] -[2023-10-16 03:36:27,676][05219] Updated weights for policy 1, policy_version 21090 (0.0010) -[2023-10-16 03:36:28,052][05219] Updated weights for policy 1, policy_version 21100 (0.0009) -[2023-10-16 03:36:28,414][05219] Updated weights for policy 1, policy_version 21110 (0.0010) -[2023-10-16 03:36:28,786][05219] Updated weights for policy 1, policy_version 21120 (0.0008) -[2023-10-16 03:36:30,589][05218] Updated weights for policy 0, policy_version 21192 (0.0007) -[2023-10-16 03:36:30,975][05218] Updated weights for policy 0, policy_version 21202 (0.0010) -[2023-10-16 03:36:31,339][05218] Updated weights for policy 0, policy_version 21212 (0.0010) -[2023-10-16 03:36:32,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 43352064. Throughput: 0: 1786.4, 1: 1772.4. Samples: 10846902. Policy #0 lag: (min: 11.0, avg: 19.0, max: 43.0) -[2023-10-16 03:36:32,351][03835] Avg episode reward: [(0, '4.650'), (1, '5.210')] -[2023-10-16 03:36:32,752][05219] Updated weights for policy 1, policy_version 21130 (0.0008) -[2023-10-16 03:36:33,121][05219] Updated weights for policy 1, policy_version 21140 (0.0007) -[2023-10-16 03:36:33,502][05219] Updated weights for policy 1, policy_version 21150 (0.0008) -[2023-10-16 03:36:35,095][05218] Updated weights for policy 0, policy_version 21222 (0.0010) -[2023-10-16 03:36:35,467][05218] Updated weights for policy 0, policy_version 21232 (0.0009) -[2023-10-16 03:36:35,845][05218] Updated weights for policy 0, policy_version 21242 (0.0009) -[2023-10-16 03:36:37,235][05219] Updated weights for policy 1, policy_version 21160 (0.0008) -[2023-10-16 03:36:37,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.6, 300 sec: 14329.1). Total num frames: 43417600. Throughput: 0: 1788.3, 1: 1797.8. Samples: 10868716. Policy #0 lag: (min: 11.0, avg: 19.0, max: 43.0) -[2023-10-16 03:36:37,351][03835] Avg episode reward: [(0, '5.110'), (1, '5.170')] -[2023-10-16 03:36:37,608][05219] Updated weights for policy 1, policy_version 21170 (0.0009) -[2023-10-16 03:36:37,977][05219] Updated weights for policy 1, policy_version 21180 (0.0007) -[2023-10-16 03:36:39,448][05218] Updated weights for policy 0, policy_version 21252 (0.0008) -[2023-10-16 03:36:39,814][05218] Updated weights for policy 0, policy_version 21262 (0.0007) -[2023-10-16 03:36:40,186][05218] Updated weights for policy 0, policy_version 21272 (0.0007) -[2023-10-16 03:36:41,605][05219] Updated weights for policy 1, policy_version 21190 (0.0007) -[2023-10-16 03:36:41,974][05219] Updated weights for policy 1, policy_version 21200 (0.0007) -[2023-10-16 03:36:42,348][05219] Updated weights for policy 1, policy_version 21210 (0.0007) -[2023-10-16 03:36:42,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 43483136. Throughput: 0: 1798.2, 1: 1774.7. Samples: 10879098. Policy #0 lag: (min: 11.0, avg: 19.0, max: 43.0) -[2023-10-16 03:36:42,351][03835] Avg episode reward: [(0, '5.290'), (1, '5.100')] -[2023-10-16 03:36:43,996][05218] Updated weights for policy 0, policy_version 21282 (0.0008) -[2023-10-16 03:36:44,373][05218] Updated weights for policy 0, policy_version 21292 (0.0008) -[2023-10-16 03:36:44,754][05218] Updated weights for policy 0, policy_version 21302 (0.0009) -[2023-10-16 03:36:45,138][05218] Updated weights for policy 0, policy_version 21312 (0.0008) -[2023-10-16 03:36:46,039][05219] Updated weights for policy 1, policy_version 21220 (0.0010) -[2023-10-16 03:36:46,399][05219] Updated weights for policy 1, policy_version 21230 (0.0010) -[2023-10-16 03:36:46,762][05219] Updated weights for policy 1, policy_version 21240 (0.0009) -[2023-10-16 03:36:47,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 43581440. Throughput: 0: 1792.0, 1: 1803.9. Samples: 10901268. Policy #0 lag: (min: 11.0, avg: 19.0, max: 43.0) -[2023-10-16 03:36:47,351][03835] Avg episode reward: [(0, '5.200'), (1, '5.020')] -[2023-10-16 03:36:49,005][05218] Updated weights for policy 0, policy_version 21322 (0.0007) -[2023-10-16 03:36:49,381][05218] Updated weights for policy 0, policy_version 21332 (0.0008) -[2023-10-16 03:36:49,755][05218] Updated weights for policy 0, policy_version 21342 (0.0009) -[2023-10-16 03:36:50,619][05219] Updated weights for policy 1, policy_version 21250 (0.0010) -[2023-10-16 03:36:50,988][05219] Updated weights for policy 1, policy_version 21260 (0.0009) -[2023-10-16 03:36:51,348][05219] Updated weights for policy 1, policy_version 21270 (0.0007) -[2023-10-16 03:36:51,715][05219] Updated weights for policy 1, policy_version 21280 (0.0009) -[2023-10-16 03:36:52,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 43646976. Throughput: 0: 1796.7, 1: 1782.4. Samples: 10922524. Policy #0 lag: (min: 27.0, avg: 33.1, max: 59.0) -[2023-10-16 03:36:52,351][03835] Avg episode reward: [(0, '5.450'), (1, '5.280')] -[2023-10-16 03:36:53,512][05218] Updated weights for policy 0, policy_version 21352 (0.0009) -[2023-10-16 03:36:53,882][05218] Updated weights for policy 0, policy_version 21362 (0.0008) -[2023-10-16 03:36:54,260][05218] Updated weights for policy 0, policy_version 21372 (0.0007) -[2023-10-16 03:36:55,631][05219] Updated weights for policy 1, policy_version 21290 (0.0009) -[2023-10-16 03:36:56,002][05219] Updated weights for policy 1, policy_version 21300 (0.0007) -[2023-10-16 03:36:56,370][05219] Updated weights for policy 1, policy_version 21310 (0.0007) -[2023-10-16 03:36:57,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 43712512. Throughput: 0: 1796.8, 1: 1804.3. Samples: 10933624. Policy #0 lag: (min: 27.0, avg: 33.1, max: 59.0) -[2023-10-16 03:36:57,351][03835] Avg episode reward: [(0, '5.340'), (1, '4.760')] -[2023-10-16 03:36:57,930][05218] Updated weights for policy 0, policy_version 21382 (0.0008) -[2023-10-16 03:36:58,304][05218] Updated weights for policy 0, policy_version 21392 (0.0008) -[2023-10-16 03:36:58,672][05218] Updated weights for policy 0, policy_version 21402 (0.0009) -[2023-10-16 03:36:59,911][05219] Updated weights for policy 1, policy_version 21320 (0.0009) -[2023-10-16 03:37:00,275][05219] Updated weights for policy 1, policy_version 21330 (0.0009) -[2023-10-16 03:37:00,643][05219] Updated weights for policy 1, policy_version 21340 (0.0007) -[2023-10-16 03:37:02,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 43778048. Throughput: 0: 1795.9, 1: 1788.0. Samples: 10954656. Policy #0 lag: (min: 27.0, avg: 33.1, max: 59.0) -[2023-10-16 03:37:02,351][03835] Avg episode reward: [(0, '5.540'), (1, '5.110')] -[2023-10-16 03:37:02,366][05218] Updated weights for policy 0, policy_version 21412 (0.0010) -[2023-10-16 03:37:02,746][05218] Updated weights for policy 0, policy_version 21422 (0.0010) -[2023-10-16 03:37:03,111][05218] Updated weights for policy 0, policy_version 21432 (0.0009) -[2023-10-16 03:37:04,375][05219] Updated weights for policy 1, policy_version 21350 (0.0009) -[2023-10-16 03:37:04,740][05219] Updated weights for policy 1, policy_version 21360 (0.0008) -[2023-10-16 03:37:05,106][05219] Updated weights for policy 1, policy_version 21370 (0.0008) -[2023-10-16 03:37:06,819][05218] Updated weights for policy 0, policy_version 21442 (0.0011) -[2023-10-16 03:37:07,191][05218] Updated weights for policy 0, policy_version 21452 (0.0010) -[2023-10-16 03:37:07,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 43843584. Throughput: 0: 1808.1, 1: 1782.8. Samples: 10976216. Policy #0 lag: (min: 27.0, avg: 33.1, max: 59.0) -[2023-10-16 03:37:07,351][03835] Avg episode reward: [(0, '5.670'), (1, '5.020')] -[2023-10-16 03:37:07,576][05218] Updated weights for policy 0, policy_version 21462 (0.0008) -[2023-10-16 03:37:07,955][05218] Updated weights for policy 0, policy_version 21472 (0.0008) -[2023-10-16 03:37:09,031][05219] Updated weights for policy 1, policy_version 21380 (0.0009) -[2023-10-16 03:37:09,396][05219] Updated weights for policy 1, policy_version 21390 (0.0008) -[2023-10-16 03:37:09,767][05219] Updated weights for policy 1, policy_version 21400 (0.0008) -[2023-10-16 03:37:11,847][05218] Updated weights for policy 0, policy_version 21482 (0.0010) -[2023-10-16 03:37:12,223][05218] Updated weights for policy 0, policy_version 21492 (0.0009) -[2023-10-16 03:37:12,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 43909120. Throughput: 0: 1793.7, 1: 1779.9. Samples: 10986540. Policy #0 lag: (min: 17.0, avg: 28.9, max: 49.0) -[2023-10-16 03:37:12,351][03835] Avg episode reward: [(0, '5.380'), (1, '5.080')] -[2023-10-16 03:37:12,594][05218] Updated weights for policy 0, policy_version 21502 (0.0009) -[2023-10-16 03:37:13,478][05219] Updated weights for policy 1, policy_version 21410 (0.0011) -[2023-10-16 03:37:13,840][05219] Updated weights for policy 1, policy_version 21420 (0.0010) -[2023-10-16 03:37:14,210][05219] Updated weights for policy 1, policy_version 21430 (0.0009) -[2023-10-16 03:37:14,574][05219] Updated weights for policy 1, policy_version 21440 (0.0009) -[2023-10-16 03:37:16,124][05218] Updated weights for policy 0, policy_version 21512 (0.0009) -[2023-10-16 03:37:16,504][05218] Updated weights for policy 0, policy_version 21522 (0.0009) -[2023-10-16 03:37:16,883][05218] Updated weights for policy 0, policy_version 21532 (0.0009) -[2023-10-16 03:37:17,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 44007424. Throughput: 0: 1804.8, 1: 1784.1. Samples: 11008400. Policy #0 lag: (min: 17.0, avg: 28.9, max: 49.0) -[2023-10-16 03:37:17,351][03835] Avg episode reward: [(0, '6.100'), (1, '5.370')] -[2023-10-16 03:37:17,352][04766] Saving new best policy, reward=6.100! -[2023-10-16 03:37:18,310][05219] Updated weights for policy 1, policy_version 21450 (0.0008) -[2023-10-16 03:37:18,681][05219] Updated weights for policy 1, policy_version 21460 (0.0008) -[2023-10-16 03:37:19,055][05219] Updated weights for policy 1, policy_version 21470 (0.0008) -[2023-10-16 03:37:20,744][05218] Updated weights for policy 0, policy_version 21542 (0.0008) -[2023-10-16 03:37:21,131][05218] Updated weights for policy 0, policy_version 21552 (0.0008) -[2023-10-16 03:37:21,502][05218] Updated weights for policy 0, policy_version 21562 (0.0007) -[2023-10-16 03:37:22,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 44072960. Throughput: 0: 1785.6, 1: 1795.5. Samples: 11029864. Policy #0 lag: (min: 17.0, avg: 28.9, max: 49.0) -[2023-10-16 03:37:22,351][03835] Avg episode reward: [(0, '5.100'), (1, '5.000')] -[2023-10-16 03:37:22,730][05219] Updated weights for policy 1, policy_version 21480 (0.0010) -[2023-10-16 03:37:23,098][05219] Updated weights for policy 1, policy_version 21490 (0.0008) -[2023-10-16 03:37:23,461][05219] Updated weights for policy 1, policy_version 21500 (0.0010) -[2023-10-16 03:37:25,167][05218] Updated weights for policy 0, policy_version 21572 (0.0008) -[2023-10-16 03:37:25,533][05218] Updated weights for policy 0, policy_version 21582 (0.0010) -[2023-10-16 03:37:25,910][05218] Updated weights for policy 0, policy_version 21592 (0.0010) -[2023-10-16 03:37:27,222][05219] Updated weights for policy 1, policy_version 21510 (0.0008) -[2023-10-16 03:37:27,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 44138496. Throughput: 0: 1801.9, 1: 1790.1. Samples: 11040740. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) -[2023-10-16 03:37:27,351][03835] Avg episode reward: [(0, '5.680'), (1, '4.850')] -[2023-10-16 03:37:27,586][05219] Updated weights for policy 1, policy_version 21520 (0.0007) -[2023-10-16 03:37:27,961][05219] Updated weights for policy 1, policy_version 21530 (0.0007) -[2023-10-16 03:37:29,636][05218] Updated weights for policy 0, policy_version 21602 (0.0010) -[2023-10-16 03:37:30,025][05218] Updated weights for policy 0, policy_version 21612 (0.0007) -[2023-10-16 03:37:30,401][05218] Updated weights for policy 0, policy_version 21622 (0.0007) -[2023-10-16 03:37:30,778][05218] Updated weights for policy 0, policy_version 21632 (0.0009) -[2023-10-16 03:37:31,753][05219] Updated weights for policy 1, policy_version 21540 (0.0008) -[2023-10-16 03:37:32,115][05219] Updated weights for policy 1, policy_version 21550 (0.0008) -[2023-10-16 03:37:32,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 44204032. Throughput: 0: 1786.3, 1: 1790.2. Samples: 11062210. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) -[2023-10-16 03:37:32,351][03835] Avg episode reward: [(0, '5.540'), (1, '4.900')] -[2023-10-16 03:37:32,474][05219] Updated weights for policy 1, policy_version 21560 (0.0008) -[2023-10-16 03:37:34,542][05218] Updated weights for policy 0, policy_version 21642 (0.0008) -[2023-10-16 03:37:34,914][05218] Updated weights for policy 0, policy_version 21652 (0.0010) -[2023-10-16 03:37:35,295][05218] Updated weights for policy 0, policy_version 21662 (0.0010) -[2023-10-16 03:37:36,302][05219] Updated weights for policy 1, policy_version 21570 (0.0010) -[2023-10-16 03:37:36,662][05219] Updated weights for policy 1, policy_version 21580 (0.0008) -[2023-10-16 03:37:37,027][05219] Updated weights for policy 1, policy_version 21590 (0.0007) -[2023-10-16 03:37:37,351][03835] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 44269568. Throughput: 0: 1785.4, 1: 1791.9. Samples: 11083502. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) -[2023-10-16 03:37:37,352][03835] Avg episode reward: [(0, '5.120'), (1, '5.120')] -[2023-10-16 03:37:37,363][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000021664_22183936.pth... -[2023-10-16 03:37:37,387][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000021600_22118400.pth... -[2023-10-16 03:37:37,391][05219] Updated weights for policy 1, policy_version 21600 (0.0009) -[2023-10-16 03:37:37,399][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000020000_20480000.pth -[2023-10-16 03:37:37,424][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000019904_20381696.pth -[2023-10-16 03:37:39,021][05218] Updated weights for policy 0, policy_version 21672 (0.0008) -[2023-10-16 03:37:39,408][05218] Updated weights for policy 0, policy_version 21682 (0.0008) -[2023-10-16 03:37:39,782][05218] Updated weights for policy 0, policy_version 21692 (0.0007) -[2023-10-16 03:37:41,378][05219] Updated weights for policy 1, policy_version 21610 (0.0008) -[2023-10-16 03:37:41,737][05219] Updated weights for policy 1, policy_version 21620 (0.0010) -[2023-10-16 03:37:42,105][05219] Updated weights for policy 1, policy_version 21630 (0.0009) -[2023-10-16 03:37:42,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 44367872. Throughput: 0: 1784.2, 1: 1783.8. Samples: 11094186. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) -[2023-10-16 03:37:42,351][03835] Avg episode reward: [(0, '5.450'), (1, '5.400')] -[2023-10-16 03:37:43,552][05218] Updated weights for policy 0, policy_version 21702 (0.0008) -[2023-10-16 03:37:43,925][05218] Updated weights for policy 0, policy_version 21712 (0.0009) -[2023-10-16 03:37:44,305][05218] Updated weights for policy 0, policy_version 21722 (0.0008) -[2023-10-16 03:37:45,755][05219] Updated weights for policy 1, policy_version 21640 (0.0008) -[2023-10-16 03:37:46,133][05219] Updated weights for policy 1, policy_version 21650 (0.0009) -[2023-10-16 03:37:46,509][05219] Updated weights for policy 1, policy_version 21660 (0.0009) -[2023-10-16 03:37:47,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 44433408. Throughput: 0: 1787.2, 1: 1794.6. Samples: 11115838. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:37:47,351][03835] Avg episode reward: [(0, '4.700'), (1, '5.090')] -[2023-10-16 03:37:47,921][05218] Updated weights for policy 0, policy_version 21732 (0.0009) -[2023-10-16 03:37:48,298][05218] Updated weights for policy 0, policy_version 21742 (0.0008) -[2023-10-16 03:37:48,673][05218] Updated weights for policy 0, policy_version 21752 (0.0009) -[2023-10-16 03:37:50,246][05219] Updated weights for policy 1, policy_version 21670 (0.0007) -[2023-10-16 03:37:50,603][05219] Updated weights for policy 1, policy_version 21680 (0.0009) -[2023-10-16 03:37:50,964][05219] Updated weights for policy 1, policy_version 21690 (0.0009) -[2023-10-16 03:37:52,304][05218] Updated weights for policy 0, policy_version 21762 (0.0010) -[2023-10-16 03:37:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 44498944. Throughput: 0: 1806.8, 1: 1782.3. Samples: 11137730. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:37:52,351][03835] Avg episode reward: [(0, '5.120'), (1, '4.920')] -[2023-10-16 03:37:52,675][05218] Updated weights for policy 0, policy_version 21772 (0.0007) -[2023-10-16 03:37:53,046][05218] Updated weights for policy 0, policy_version 21782 (0.0008) -[2023-10-16 03:37:53,425][05218] Updated weights for policy 0, policy_version 21792 (0.0010) -[2023-10-16 03:37:54,767][05219] Updated weights for policy 1, policy_version 21700 (0.0008) -[2023-10-16 03:37:55,128][05219] Updated weights for policy 1, policy_version 21710 (0.0007) -[2023-10-16 03:37:55,485][05219] Updated weights for policy 1, policy_version 21720 (0.0008) -[2023-10-16 03:37:57,219][05218] Updated weights for policy 0, policy_version 21802 (0.0008) -[2023-10-16 03:37:57,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 44564480. Throughput: 0: 1795.7, 1: 1800.4. Samples: 11148362. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:37:57,351][03835] Avg episode reward: [(0, '5.360'), (1, '4.970')] -[2023-10-16 03:37:57,589][05218] Updated weights for policy 0, policy_version 21812 (0.0011) -[2023-10-16 03:37:57,965][05218] Updated weights for policy 0, policy_version 21822 (0.0011) -[2023-10-16 03:37:59,322][05219] Updated weights for policy 1, policy_version 21730 (0.0009) -[2023-10-16 03:37:59,687][05219] Updated weights for policy 1, policy_version 21740 (0.0008) -[2023-10-16 03:38:00,047][05219] Updated weights for policy 1, policy_version 21750 (0.0010) -[2023-10-16 03:38:00,404][05219] Updated weights for policy 1, policy_version 21760 (0.0009) -[2023-10-16 03:38:01,833][05218] Updated weights for policy 0, policy_version 21832 (0.0009) -[2023-10-16 03:38:02,203][05218] Updated weights for policy 0, policy_version 21842 (0.0009) -[2023-10-16 03:38:02,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 44630016. Throughput: 0: 1806.0, 1: 1779.3. Samples: 11169736. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:38:02,351][03835] Avg episode reward: [(0, '5.080'), (1, '5.330')] -[2023-10-16 03:38:02,579][05218] Updated weights for policy 0, policy_version 21852 (0.0009) -[2023-10-16 03:38:04,219][05219] Updated weights for policy 1, policy_version 21770 (0.0009) -[2023-10-16 03:38:04,593][05219] Updated weights for policy 1, policy_version 21780 (0.0010) -[2023-10-16 03:38:04,951][05219] Updated weights for policy 1, policy_version 21790 (0.0009) -[2023-10-16 03:38:06,454][05218] Updated weights for policy 0, policy_version 21862 (0.0010) -[2023-10-16 03:38:06,833][05218] Updated weights for policy 0, policy_version 21872 (0.0011) -[2023-10-16 03:38:07,198][05218] Updated weights for policy 0, policy_version 21882 (0.0010) -[2023-10-16 03:38:07,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 44695552. Throughput: 0: 1792.9, 1: 1776.8. Samples: 11190502. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-16 03:38:07,351][03835] Avg episode reward: [(0, '4.810'), (1, '5.090')] -[2023-10-16 03:38:08,828][05219] Updated weights for policy 1, policy_version 21800 (0.0008) -[2023-10-16 03:38:09,186][05219] Updated weights for policy 1, policy_version 21810 (0.0008) -[2023-10-16 03:38:09,552][05219] Updated weights for policy 1, policy_version 21820 (0.0008) -[2023-10-16 03:38:10,805][05218] Updated weights for policy 0, policy_version 21892 (0.0010) -[2023-10-16 03:38:11,186][05218] Updated weights for policy 0, policy_version 21902 (0.0009) -[2023-10-16 03:38:11,565][05218] Updated weights for policy 0, policy_version 21912 (0.0008) -[2023-10-16 03:38:12,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 44793856. Throughput: 0: 1803.1, 1: 1776.8. Samples: 11201838. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-16 03:38:12,351][03835] Avg episode reward: [(0, '4.670'), (1, '5.600')] -[2023-10-16 03:38:13,215][05219] Updated weights for policy 1, policy_version 21830 (0.0010) -[2023-10-16 03:38:13,581][05219] Updated weights for policy 1, policy_version 21840 (0.0008) -[2023-10-16 03:38:13,940][05219] Updated weights for policy 1, policy_version 21850 (0.0008) -[2023-10-16 03:38:15,528][05218] Updated weights for policy 0, policy_version 21922 (0.0009) -[2023-10-16 03:38:15,911][05218] Updated weights for policy 0, policy_version 21932 (0.0010) -[2023-10-16 03:38:16,296][05218] Updated weights for policy 0, policy_version 21942 (0.0010) -[2023-10-16 03:38:16,667][05218] Updated weights for policy 0, policy_version 21952 (0.0010) -[2023-10-16 03:38:17,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 44859392. Throughput: 0: 1793.9, 1: 1778.8. Samples: 11222980. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-16 03:38:17,351][03835] Avg episode reward: [(0, '5.040'), (1, '5.050')] -[2023-10-16 03:38:17,634][05219] Updated weights for policy 1, policy_version 21860 (0.0008) -[2023-10-16 03:38:18,003][05219] Updated weights for policy 1, policy_version 21870 (0.0008) -[2023-10-16 03:38:18,372][05219] Updated weights for policy 1, policy_version 21880 (0.0007) -[2023-10-16 03:38:20,427][05218] Updated weights for policy 0, policy_version 21962 (0.0008) -[2023-10-16 03:38:20,801][05218] Updated weights for policy 0, policy_version 21972 (0.0009) -[2023-10-16 03:38:21,180][05218] Updated weights for policy 0, policy_version 21982 (0.0007) -[2023-10-16 03:38:22,222][05219] Updated weights for policy 1, policy_version 21890 (0.0008) -[2023-10-16 03:38:22,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 44924928. Throughput: 0: 1790.8, 1: 1801.2. Samples: 11245140. Policy #0 lag: (min: 18.0, avg: 19.3, max: 41.0) -[2023-10-16 03:38:22,352][03835] Avg episode reward: [(0, '4.890'), (1, '5.460')] -[2023-10-16 03:38:22,581][05219] Updated weights for policy 1, policy_version 21900 (0.0009) -[2023-10-16 03:38:22,949][05219] Updated weights for policy 1, policy_version 21910 (0.0009) -[2023-10-16 03:38:23,313][05219] Updated weights for policy 1, policy_version 21920 (0.0009) -[2023-10-16 03:38:24,704][05218] Updated weights for policy 0, policy_version 21992 (0.0010) -[2023-10-16 03:38:25,079][05218] Updated weights for policy 0, policy_version 22002 (0.0007) -[2023-10-16 03:38:25,450][05218] Updated weights for policy 0, policy_version 22012 (0.0008) -[2023-10-16 03:38:27,253][05219] Updated weights for policy 1, policy_version 21930 (0.0007) -[2023-10-16 03:38:27,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 44990464. Throughput: 0: 1805.5, 1: 1778.2. Samples: 11255452. Policy #0 lag: (min: 18.0, avg: 19.3, max: 41.0) -[2023-10-16 03:38:27,351][03835] Avg episode reward: [(0, '5.150'), (1, '5.220')] -[2023-10-16 03:38:27,620][05219] Updated weights for policy 1, policy_version 21940 (0.0010) -[2023-10-16 03:38:27,981][05219] Updated weights for policy 1, policy_version 21950 (0.0009) -[2023-10-16 03:38:29,357][05218] Updated weights for policy 0, policy_version 22022 (0.0010) -[2023-10-16 03:38:29,742][05218] Updated weights for policy 0, policy_version 22032 (0.0009) -[2023-10-16 03:38:30,107][05218] Updated weights for policy 0, policy_version 22042 (0.0008) -[2023-10-16 03:38:31,759][05219] Updated weights for policy 1, policy_version 21960 (0.0007) -[2023-10-16 03:38:32,123][05219] Updated weights for policy 1, policy_version 21970 (0.0008) -[2023-10-16 03:38:32,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 45056000. Throughput: 0: 1785.9, 1: 1796.6. Samples: 11277050. Policy #0 lag: (min: 18.0, avg: 19.3, max: 41.0) -[2023-10-16 03:38:32,351][03835] Avg episode reward: [(0, '5.440'), (1, '5.150')] -[2023-10-16 03:38:32,490][05219] Updated weights for policy 1, policy_version 21980 (0.0007) -[2023-10-16 03:38:33,868][05218] Updated weights for policy 0, policy_version 22052 (0.0007) -[2023-10-16 03:38:34,243][05218] Updated weights for policy 0, policy_version 22062 (0.0008) -[2023-10-16 03:38:34,628][05218] Updated weights for policy 0, policy_version 22072 (0.0007) -[2023-10-16 03:38:36,142][05219] Updated weights for policy 1, policy_version 21990 (0.0008) -[2023-10-16 03:38:36,503][05219] Updated weights for policy 1, policy_version 22000 (0.0011) -[2023-10-16 03:38:36,877][05219] Updated weights for policy 1, policy_version 22010 (0.0011) -[2023-10-16 03:38:37,351][03835] Fps is (10 sec: 16383.2, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 45154304. Throughput: 0: 1775.0, 1: 1785.9. Samples: 11297970. Policy #0 lag: (min: 18.0, avg: 19.3, max: 41.0) -[2023-10-16 03:38:37,352][03835] Avg episode reward: [(0, '5.390'), (1, '4.560')] -[2023-10-16 03:38:38,594][05218] Updated weights for policy 0, policy_version 22082 (0.0008) -[2023-10-16 03:38:38,968][05218] Updated weights for policy 0, policy_version 22092 (0.0008) -[2023-10-16 03:38:39,344][05218] Updated weights for policy 0, policy_version 22102 (0.0009) -[2023-10-16 03:38:39,732][05218] Updated weights for policy 0, policy_version 22112 (0.0008) -[2023-10-16 03:38:40,534][05219] Updated weights for policy 1, policy_version 22020 (0.0010) -[2023-10-16 03:38:40,899][05219] Updated weights for policy 1, policy_version 22030 (0.0010) -[2023-10-16 03:38:41,264][05219] Updated weights for policy 1, policy_version 22040 (0.0007) -[2023-10-16 03:38:42,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 45219840. Throughput: 0: 1769.4, 1: 1805.1. Samples: 11309216. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:38:42,351][03835] Avg episode reward: [(0, '5.760'), (1, '5.290')] -[2023-10-16 03:38:43,400][05218] Updated weights for policy 0, policy_version 22122 (0.0008) -[2023-10-16 03:38:43,783][05218] Updated weights for policy 0, policy_version 22132 (0.0010) -[2023-10-16 03:38:44,151][05218] Updated weights for policy 0, policy_version 22142 (0.0008) -[2023-10-16 03:38:45,039][05219] Updated weights for policy 1, policy_version 22050 (0.0008) -[2023-10-16 03:38:45,402][05219] Updated weights for policy 1, policy_version 22060 (0.0007) -[2023-10-16 03:38:45,769][05219] Updated weights for policy 1, policy_version 22070 (0.0008) -[2023-10-16 03:38:46,128][05219] Updated weights for policy 1, policy_version 22080 (0.0010) -[2023-10-16 03:38:47,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 45285376. Throughput: 0: 1773.6, 1: 1795.9. Samples: 11330364. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:38:47,351][03835] Avg episode reward: [(0, '5.000'), (1, '4.970')] -[2023-10-16 03:38:47,884][05218] Updated weights for policy 0, policy_version 22152 (0.0008) -[2023-10-16 03:38:48,255][05218] Updated weights for policy 0, policy_version 22162 (0.0009) -[2023-10-16 03:38:48,627][05218] Updated weights for policy 0, policy_version 22172 (0.0009) -[2023-10-16 03:38:49,956][05219] Updated weights for policy 1, policy_version 22090 (0.0009) -[2023-10-16 03:38:50,329][05219] Updated weights for policy 1, policy_version 22100 (0.0008) -[2023-10-16 03:38:50,696][05219] Updated weights for policy 1, policy_version 22110 (0.0008) -[2023-10-16 03:38:52,313][05218] Updated weights for policy 0, policy_version 22182 (0.0009) -[2023-10-16 03:38:52,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 45350912. Throughput: 0: 1804.4, 1: 1792.8. Samples: 11352378. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:38:52,351][03835] Avg episode reward: [(0, '5.180'), (1, '5.200')] -[2023-10-16 03:38:52,693][05218] Updated weights for policy 0, policy_version 22192 (0.0009) -[2023-10-16 03:38:53,061][05218] Updated weights for policy 0, policy_version 22202 (0.0010) -[2023-10-16 03:38:54,373][05219] Updated weights for policy 1, policy_version 22120 (0.0007) -[2023-10-16 03:38:54,734][05219] Updated weights for policy 1, policy_version 22130 (0.0009) -[2023-10-16 03:38:55,100][05219] Updated weights for policy 1, policy_version 22140 (0.0010) -[2023-10-16 03:38:56,792][05218] Updated weights for policy 0, policy_version 22212 (0.0009) -[2023-10-16 03:38:57,165][05218] Updated weights for policy 0, policy_version 22222 (0.0007) -[2023-10-16 03:38:57,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 45416448. Throughput: 0: 1776.9, 1: 1798.0. Samples: 11362706. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:38:57,351][03835] Avg episode reward: [(0, '4.810'), (1, '5.180')] -[2023-10-16 03:38:57,544][05218] Updated weights for policy 0, policy_version 22232 (0.0008) -[2023-10-16 03:38:58,929][05219] Updated weights for policy 1, policy_version 22150 (0.0009) -[2023-10-16 03:38:59,286][05219] Updated weights for policy 1, policy_version 22160 (0.0008) -[2023-10-16 03:38:59,660][05219] Updated weights for policy 1, policy_version 22170 (0.0009) -[2023-10-16 03:39:01,148][05218] Updated weights for policy 0, policy_version 22242 (0.0008) -[2023-10-16 03:39:01,519][05218] Updated weights for policy 0, policy_version 22252 (0.0007) -[2023-10-16 03:39:01,887][05218] Updated weights for policy 0, policy_version 22262 (0.0007) -[2023-10-16 03:39:02,266][05218] Updated weights for policy 0, policy_version 22272 (0.0008) -[2023-10-16 03:39:02,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 45514752. Throughput: 0: 1802.6, 1: 1781.6. Samples: 11384270. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:39:02,351][03835] Avg episode reward: [(0, '5.210'), (1, '5.170')] -[2023-10-16 03:39:03,550][05219] Updated weights for policy 1, policy_version 22180 (0.0011) -[2023-10-16 03:39:03,923][05219] Updated weights for policy 1, policy_version 22190 (0.0009) -[2023-10-16 03:39:04,284][05219] Updated weights for policy 1, policy_version 22200 (0.0008) -[2023-10-16 03:39:06,106][05218] Updated weights for policy 0, policy_version 22282 (0.0007) -[2023-10-16 03:39:06,475][05218] Updated weights for policy 0, policy_version 22292 (0.0009) -[2023-10-16 03:39:06,854][05218] Updated weights for policy 0, policy_version 22302 (0.0008) -[2023-10-16 03:39:07,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 45580288. Throughput: 0: 1776.4, 1: 1784.9. Samples: 11405398. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:39:07,351][03835] Avg episode reward: [(0, '5.750'), (1, '5.160')] -[2023-10-16 03:39:08,130][05219] Updated weights for policy 1, policy_version 22210 (0.0008) -[2023-10-16 03:39:08,482][05219] Updated weights for policy 1, policy_version 22220 (0.0009) -[2023-10-16 03:39:08,853][05219] Updated weights for policy 1, policy_version 22230 (0.0011) -[2023-10-16 03:39:09,227][05219] Updated weights for policy 1, policy_version 22240 (0.0007) -[2023-10-16 03:39:10,538][05218] Updated weights for policy 0, policy_version 22312 (0.0009) -[2023-10-16 03:39:10,911][05218] Updated weights for policy 0, policy_version 22322 (0.0009) -[2023-10-16 03:39:11,289][05218] Updated weights for policy 0, policy_version 22332 (0.0007) -[2023-10-16 03:39:12,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 45645824. Throughput: 0: 1796.9, 1: 1782.0. Samples: 11416504. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:39:12,351][03835] Avg episode reward: [(0, '5.480'), (1, '5.110')] -[2023-10-16 03:39:13,161][05219] Updated weights for policy 1, policy_version 22250 (0.0008) -[2023-10-16 03:39:13,524][05219] Updated weights for policy 1, policy_version 22260 (0.0007) -[2023-10-16 03:39:13,878][05219] Updated weights for policy 1, policy_version 22270 (0.0007) -[2023-10-16 03:39:15,034][05218] Updated weights for policy 0, policy_version 22342 (0.0009) -[2023-10-16 03:39:15,412][05218] Updated weights for policy 0, policy_version 22352 (0.0008) -[2023-10-16 03:39:15,792][05218] Updated weights for policy 0, policy_version 22362 (0.0010) -[2023-10-16 03:39:17,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 45711360. Throughput: 0: 1780.1, 1: 1781.3. Samples: 11437314. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:39:17,351][03835] Avg episode reward: [(0, '5.710'), (1, '5.050')] -[2023-10-16 03:39:17,564][05219] Updated weights for policy 1, policy_version 22280 (0.0009) -[2023-10-16 03:39:17,929][05219] Updated weights for policy 1, policy_version 22290 (0.0008) -[2023-10-16 03:39:18,293][05219] Updated weights for policy 1, policy_version 22300 (0.0007) -[2023-10-16 03:39:19,458][05218] Updated weights for policy 0, policy_version 22372 (0.0009) -[2023-10-16 03:39:19,834][05218] Updated weights for policy 0, policy_version 22382 (0.0008) -[2023-10-16 03:39:20,210][05218] Updated weights for policy 0, policy_version 22392 (0.0007) -[2023-10-16 03:39:21,868][05219] Updated weights for policy 1, policy_version 22310 (0.0008) -[2023-10-16 03:39:22,234][05219] Updated weights for policy 1, policy_version 22320 (0.0007) -[2023-10-16 03:39:22,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 45776896. Throughput: 0: 1789.6, 1: 1797.3. Samples: 11459382. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:39:22,351][03835] Avg episode reward: [(0, '5.600'), (1, '4.640')] -[2023-10-16 03:39:22,603][05219] Updated weights for policy 1, policy_version 22330 (0.0007) -[2023-10-16 03:39:24,064][05218] Updated weights for policy 0, policy_version 22402 (0.0008) -[2023-10-16 03:39:24,435][05218] Updated weights for policy 0, policy_version 22412 (0.0009) -[2023-10-16 03:39:24,812][05218] Updated weights for policy 0, policy_version 22422 (0.0008) -[2023-10-16 03:39:25,188][05218] Updated weights for policy 0, policy_version 22432 (0.0007) -[2023-10-16 03:39:26,375][05219] Updated weights for policy 1, policy_version 22340 (0.0008) -[2023-10-16 03:39:26,742][05219] Updated weights for policy 1, policy_version 22350 (0.0009) -[2023-10-16 03:39:27,108][05219] Updated weights for policy 1, policy_version 22360 (0.0008) -[2023-10-16 03:39:27,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 45842432. Throughput: 0: 1795.5, 1: 1775.5. Samples: 11469910. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:39:27,351][03835] Avg episode reward: [(0, '5.150'), (1, '4.230')] -[2023-10-16 03:39:28,943][05218] Updated weights for policy 0, policy_version 22442 (0.0009) -[2023-10-16 03:39:29,309][05218] Updated weights for policy 0, policy_version 22452 (0.0011) -[2023-10-16 03:39:29,685][05218] Updated weights for policy 0, policy_version 22462 (0.0009) -[2023-10-16 03:39:31,000][05219] Updated weights for policy 1, policy_version 22370 (0.0008) -[2023-10-16 03:39:31,368][05219] Updated weights for policy 1, policy_version 22380 (0.0008) -[2023-10-16 03:39:31,730][05219] Updated weights for policy 1, policy_version 22390 (0.0007) -[2023-10-16 03:39:32,094][05219] Updated weights for policy 1, policy_version 22400 (0.0008) -[2023-10-16 03:39:32,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 45940736. Throughput: 0: 1793.0, 1: 1799.8. Samples: 11492040. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:39:32,351][03835] Avg episode reward: [(0, '5.650'), (1, '3.960')] -[2023-10-16 03:39:33,324][05218] Updated weights for policy 0, policy_version 22472 (0.0010) -[2023-10-16 03:39:33,708][05218] Updated weights for policy 0, policy_version 22482 (0.0007) -[2023-10-16 03:39:34,089][05218] Updated weights for policy 0, policy_version 22492 (0.0009) -[2023-10-16 03:39:35,736][05219] Updated weights for policy 1, policy_version 22410 (0.0008) -[2023-10-16 03:39:36,091][05219] Updated weights for policy 1, policy_version 22420 (0.0008) -[2023-10-16 03:39:36,463][05219] Updated weights for policy 1, policy_version 22430 (0.0007) -[2023-10-16 03:39:37,351][03835] Fps is (10 sec: 16383.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 46006272. Throughput: 0: 1800.7, 1: 1777.1. Samples: 11513380. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-16 03:39:37,352][03835] Avg episode reward: [(0, '5.480'), (1, '4.170')] -[2023-10-16 03:39:37,364][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000022496_23035904.pth... -[2023-10-16 03:39:37,364][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000022432_22970368.pth... -[2023-10-16 03:39:37,404][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000020768_21266432.pth -[2023-10-16 03:39:37,407][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000020832_21331968.pth -[2023-10-16 03:39:37,920][05218] Updated weights for policy 0, policy_version 22502 (0.0007) -[2023-10-16 03:39:38,300][05218] Updated weights for policy 0, policy_version 22512 (0.0007) -[2023-10-16 03:39:38,683][05218] Updated weights for policy 0, policy_version 22522 (0.0009) -[2023-10-16 03:39:40,175][05219] Updated weights for policy 1, policy_version 22440 (0.0010) -[2023-10-16 03:39:40,543][05219] Updated weights for policy 1, policy_version 22450 (0.0009) -[2023-10-16 03:39:40,906][05219] Updated weights for policy 1, policy_version 22460 (0.0009) -[2023-10-16 03:39:42,351][03835] Fps is (10 sec: 13106.5, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 46071808. Throughput: 0: 1792.8, 1: 1799.0. Samples: 11524342. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-16 03:39:42,352][03835] Avg episode reward: [(0, '5.200'), (1, '4.210')] -[2023-10-16 03:39:42,433][05218] Updated weights for policy 0, policy_version 22532 (0.0008) -[2023-10-16 03:39:42,806][05218] Updated weights for policy 0, policy_version 22542 (0.0009) -[2023-10-16 03:39:43,184][05218] Updated weights for policy 0, policy_version 22552 (0.0008) -[2023-10-16 03:39:44,816][05219] Updated weights for policy 1, policy_version 22470 (0.0008) -[2023-10-16 03:39:45,191][05219] Updated weights for policy 1, policy_version 22480 (0.0011) -[2023-10-16 03:39:45,561][05219] Updated weights for policy 1, policy_version 22490 (0.0010) -[2023-10-16 03:39:46,970][05218] Updated weights for policy 0, policy_version 22562 (0.0009) -[2023-10-16 03:39:47,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 46137344. Throughput: 0: 1796.1, 1: 1781.9. Samples: 11545278. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-16 03:39:47,351][03835] Avg episode reward: [(0, '5.550'), (1, '3.960')] -[2023-10-16 03:39:47,354][05218] Updated weights for policy 0, policy_version 22572 (0.0009) -[2023-10-16 03:39:47,724][05218] Updated weights for policy 0, policy_version 22582 (0.0010) -[2023-10-16 03:39:48,099][05218] Updated weights for policy 0, policy_version 22592 (0.0008) -[2023-10-16 03:39:49,158][05219] Updated weights for policy 1, policy_version 22500 (0.0010) -[2023-10-16 03:39:49,517][05219] Updated weights for policy 1, policy_version 22510 (0.0008) -[2023-10-16 03:39:49,884][05219] Updated weights for policy 1, policy_version 22520 (0.0008) -[2023-10-16 03:39:51,670][05218] Updated weights for policy 0, policy_version 22602 (0.0010) -[2023-10-16 03:39:52,046][05218] Updated weights for policy 0, policy_version 22612 (0.0007) -[2023-10-16 03:39:52,350][03835] Fps is (10 sec: 13107.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 46202880. Throughput: 0: 1803.2, 1: 1783.1. Samples: 11566782. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-16 03:39:52,351][03835] Avg episode reward: [(0, '5.010'), (1, '3.860')] -[2023-10-16 03:39:52,421][05218] Updated weights for policy 0, policy_version 22622 (0.0007) -[2023-10-16 03:39:53,705][05219] Updated weights for policy 1, policy_version 22530 (0.0007) -[2023-10-16 03:39:54,071][05219] Updated weights for policy 1, policy_version 22540 (0.0008) -[2023-10-16 03:39:54,432][05219] Updated weights for policy 1, policy_version 22550 (0.0007) -[2023-10-16 03:39:54,800][05219] Updated weights for policy 1, policy_version 22560 (0.0007) -[2023-10-16 03:39:56,048][05218] Updated weights for policy 0, policy_version 22632 (0.0009) -[2023-10-16 03:39:56,418][05218] Updated weights for policy 0, policy_version 22642 (0.0011) -[2023-10-16 03:39:56,786][05218] Updated weights for policy 0, policy_version 22652 (0.0009) -[2023-10-16 03:39:57,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 46301184. Throughput: 0: 1802.1, 1: 1786.9. Samples: 11578008. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 03:39:57,351][03835] Avg episode reward: [(0, '5.340'), (1, '4.170')] -[2023-10-16 03:39:58,769][05219] Updated weights for policy 1, policy_version 22570 (0.0009) -[2023-10-16 03:39:59,125][05219] Updated weights for policy 1, policy_version 22580 (0.0008) -[2023-10-16 03:39:59,491][05219] Updated weights for policy 1, policy_version 22590 (0.0008) -[2023-10-16 03:40:00,466][05218] Updated weights for policy 0, policy_version 22662 (0.0007) -[2023-10-16 03:40:00,834][05218] Updated weights for policy 0, policy_version 22672 (0.0008) -[2023-10-16 03:40:01,216][05218] Updated weights for policy 0, policy_version 22682 (0.0007) -[2023-10-16 03:40:02,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 46366720. Throughput: 0: 1808.1, 1: 1788.1. Samples: 11599144. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 03:40:02,352][03835] Avg episode reward: [(0, '5.940'), (1, '4.510')] -[2023-10-16 03:40:03,250][05219] Updated weights for policy 1, policy_version 22600 (0.0007) -[2023-10-16 03:40:03,617][05219] Updated weights for policy 1, policy_version 22610 (0.0007) -[2023-10-16 03:40:03,988][05219] Updated weights for policy 1, policy_version 22620 (0.0008) -[2023-10-16 03:40:04,823][05218] Updated weights for policy 0, policy_version 22692 (0.0008) -[2023-10-16 03:40:05,201][05218] Updated weights for policy 0, policy_version 22702 (0.0009) -[2023-10-16 03:40:05,565][05218] Updated weights for policy 0, policy_version 22712 (0.0008) -[2023-10-16 03:40:07,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 46432256. Throughput: 0: 1804.8, 1: 1799.7. Samples: 11621586. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 03:40:07,351][03835] Avg episode reward: [(0, '5.780'), (1, '4.660')] -[2023-10-16 03:40:07,715][05219] Updated weights for policy 1, policy_version 22630 (0.0009) -[2023-10-16 03:40:08,077][05219] Updated weights for policy 1, policy_version 22640 (0.0011) -[2023-10-16 03:40:08,437][05219] Updated weights for policy 1, policy_version 22650 (0.0010) -[2023-10-16 03:40:09,275][05218] Updated weights for policy 0, policy_version 22722 (0.0008) -[2023-10-16 03:40:09,655][05218] Updated weights for policy 0, policy_version 22732 (0.0012) -[2023-10-16 03:40:10,024][05218] Updated weights for policy 0, policy_version 22742 (0.0011) -[2023-10-16 03:40:10,410][05218] Updated weights for policy 0, policy_version 22752 (0.0011) -[2023-10-16 03:40:12,291][05219] Updated weights for policy 1, policy_version 22660 (0.0009) -[2023-10-16 03:40:12,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 46497792. Throughput: 0: 1807.3, 1: 1784.2. Samples: 11631530. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 03:40:12,351][03835] Avg episode reward: [(0, '5.620'), (1, '4.600')] -[2023-10-16 03:40:12,657][05219] Updated weights for policy 1, policy_version 22670 (0.0008) -[2023-10-16 03:40:13,022][05219] Updated weights for policy 1, policy_version 22680 (0.0009) -[2023-10-16 03:40:14,185][05218] Updated weights for policy 0, policy_version 22762 (0.0009) -[2023-10-16 03:40:14,569][05218] Updated weights for policy 0, policy_version 22772 (0.0007) -[2023-10-16 03:40:14,938][05218] Updated weights for policy 0, policy_version 22782 (0.0009) -[2023-10-16 03:40:16,827][05219] Updated weights for policy 1, policy_version 22690 (0.0009) -[2023-10-16 03:40:17,189][05219] Updated weights for policy 1, policy_version 22700 (0.0007) -[2023-10-16 03:40:17,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 46563328. Throughput: 0: 1803.8, 1: 1787.6. Samples: 11653650. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 03:40:17,351][03835] Avg episode reward: [(0, '5.250'), (1, '4.230')] -[2023-10-16 03:40:17,560][05219] Updated weights for policy 1, policy_version 22710 (0.0009) -[2023-10-16 03:40:17,927][05219] Updated weights for policy 1, policy_version 22720 (0.0009) -[2023-10-16 03:40:18,524][05218] Updated weights for policy 0, policy_version 22792 (0.0007) -[2023-10-16 03:40:18,903][05218] Updated weights for policy 0, policy_version 22802 (0.0009) -[2023-10-16 03:40:19,276][05218] Updated weights for policy 0, policy_version 22812 (0.0010) -[2023-10-16 03:40:21,650][05219] Updated weights for policy 1, policy_version 22730 (0.0007) -[2023-10-16 03:40:22,014][05219] Updated weights for policy 1, policy_version 22740 (0.0008) -[2023-10-16 03:40:22,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 46628864. Throughput: 0: 1802.8, 1: 1793.4. Samples: 11675206. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 03:40:22,351][03835] Avg episode reward: [(0, '5.270'), (1, '3.880')] -[2023-10-16 03:40:22,386][05219] Updated weights for policy 1, policy_version 22750 (0.0009) -[2023-10-16 03:40:23,273][05218] Updated weights for policy 0, policy_version 22822 (0.0008) -[2023-10-16 03:40:23,657][05218] Updated weights for policy 0, policy_version 22832 (0.0009) -[2023-10-16 03:40:24,036][05218] Updated weights for policy 0, policy_version 22842 (0.0009) -[2023-10-16 03:40:25,970][05219] Updated weights for policy 1, policy_version 22760 (0.0009) -[2023-10-16 03:40:26,338][05219] Updated weights for policy 1, policy_version 22770 (0.0008) -[2023-10-16 03:40:26,707][05219] Updated weights for policy 1, policy_version 22780 (0.0008) -[2023-10-16 03:40:27,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 46727168. Throughput: 0: 1798.9, 1: 1790.3. Samples: 11685856. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 03:40:27,351][03835] Avg episode reward: [(0, '5.320'), (1, '3.980')] -[2023-10-16 03:40:27,862][05218] Updated weights for policy 0, policy_version 22852 (0.0009) -[2023-10-16 03:40:28,228][05218] Updated weights for policy 0, policy_version 22862 (0.0008) -[2023-10-16 03:40:28,601][05218] Updated weights for policy 0, policy_version 22872 (0.0009) -[2023-10-16 03:40:30,475][05219] Updated weights for policy 1, policy_version 22790 (0.0008) -[2023-10-16 03:40:30,834][05219] Updated weights for policy 1, policy_version 22800 (0.0008) -[2023-10-16 03:40:31,197][05219] Updated weights for policy 1, policy_version 22810 (0.0009) -[2023-10-16 03:40:32,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 46792704. Throughput: 0: 1800.7, 1: 1801.5. Samples: 11707376. Policy #0 lag: (min: 16.0, avg: 43.8, max: 48.0) -[2023-10-16 03:40:32,351][03835] Avg episode reward: [(0, '5.470'), (1, '3.880')] -[2023-10-16 03:40:32,411][05218] Updated weights for policy 0, policy_version 22882 (0.0008) -[2023-10-16 03:40:32,796][05218] Updated weights for policy 0, policy_version 22892 (0.0008) -[2023-10-16 03:40:33,177][05218] Updated weights for policy 0, policy_version 22902 (0.0010) -[2023-10-16 03:40:33,552][05218] Updated weights for policy 0, policy_version 22912 (0.0011) -[2023-10-16 03:40:34,880][05219] Updated weights for policy 1, policy_version 22820 (0.0008) -[2023-10-16 03:40:35,240][05219] Updated weights for policy 1, policy_version 22830 (0.0008) -[2023-10-16 03:40:35,602][05219] Updated weights for policy 1, policy_version 22840 (0.0012) -[2023-10-16 03:40:37,249][05218] Updated weights for policy 0, policy_version 22922 (0.0008) -[2023-10-16 03:40:37,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 46858240. Throughput: 0: 1809.6, 1: 1792.8. Samples: 11728894. Policy #0 lag: (min: 16.0, avg: 43.8, max: 48.0) -[2023-10-16 03:40:37,351][03835] Avg episode reward: [(0, '5.360'), (1, '4.090')] -[2023-10-16 03:40:37,622][05218] Updated weights for policy 0, policy_version 22932 (0.0008) -[2023-10-16 03:40:37,997][05218] Updated weights for policy 0, policy_version 22942 (0.0010) -[2023-10-16 03:40:39,324][05219] Updated weights for policy 1, policy_version 22850 (0.0009) -[2023-10-16 03:40:39,701][05219] Updated weights for policy 1, policy_version 22860 (0.0008) -[2023-10-16 03:40:40,065][05219] Updated weights for policy 1, policy_version 22870 (0.0007) -[2023-10-16 03:40:40,427][05219] Updated weights for policy 1, policy_version 22880 (0.0009) -[2023-10-16 03:40:41,748][05218] Updated weights for policy 0, policy_version 22952 (0.0010) -[2023-10-16 03:40:42,130][05218] Updated weights for policy 0, policy_version 22962 (0.0008) -[2023-10-16 03:40:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.6, 300 sec: 14329.1). Total num frames: 46923776. Throughput: 0: 1792.8, 1: 1803.0. Samples: 11739822. Policy #0 lag: (min: 16.0, avg: 43.8, max: 48.0) -[2023-10-16 03:40:42,351][03835] Avg episode reward: [(0, '5.640'), (1, '4.530')] -[2023-10-16 03:40:42,496][05218] Updated weights for policy 0, policy_version 22972 (0.0009) -[2023-10-16 03:40:44,158][05219] Updated weights for policy 1, policy_version 22890 (0.0008) -[2023-10-16 03:40:44,530][05219] Updated weights for policy 1, policy_version 22900 (0.0007) -[2023-10-16 03:40:44,893][05219] Updated weights for policy 1, policy_version 22910 (0.0008) -[2023-10-16 03:40:46,250][05218] Updated weights for policy 0, policy_version 22982 (0.0008) -[2023-10-16 03:40:46,634][05218] Updated weights for policy 0, policy_version 22992 (0.0009) -[2023-10-16 03:40:47,012][05218] Updated weights for policy 0, policy_version 23002 (0.0008) -[2023-10-16 03:40:47,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 47022080. Throughput: 0: 1805.2, 1: 1795.6. Samples: 11761180. Policy #0 lag: (min: 6.0, avg: 19.6, max: 38.0) -[2023-10-16 03:40:47,351][03835] Avg episode reward: [(0, '5.520'), (1, '4.450')] -[2023-10-16 03:40:48,587][05219] Updated weights for policy 1, policy_version 22920 (0.0008) -[2023-10-16 03:40:48,957][05219] Updated weights for policy 1, policy_version 22930 (0.0010) -[2023-10-16 03:40:49,321][05219] Updated weights for policy 1, policy_version 22940 (0.0009) -[2023-10-16 03:40:50,907][05218] Updated weights for policy 0, policy_version 23012 (0.0010) -[2023-10-16 03:40:51,279][05218] Updated weights for policy 0, policy_version 23022 (0.0011) -[2023-10-16 03:40:51,652][05218] Updated weights for policy 0, policy_version 23032 (0.0011) -[2023-10-16 03:40:52,350][03835] Fps is (10 sec: 16383.5, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 47087616. Throughput: 0: 1780.3, 1: 1798.4. Samples: 11782630. Policy #0 lag: (min: 6.0, avg: 19.6, max: 38.0) -[2023-10-16 03:40:52,351][03835] Avg episode reward: [(0, '5.420'), (1, '4.410')] -[2023-10-16 03:40:53,102][05219] Updated weights for policy 1, policy_version 22950 (0.0009) -[2023-10-16 03:40:53,464][05219] Updated weights for policy 1, policy_version 22960 (0.0009) -[2023-10-16 03:40:53,830][05219] Updated weights for policy 1, policy_version 22970 (0.0007) -[2023-10-16 03:40:55,439][05218] Updated weights for policy 0, policy_version 23042 (0.0011) -[2023-10-16 03:40:55,820][05218] Updated weights for policy 0, policy_version 23052 (0.0007) -[2023-10-16 03:40:56,193][05218] Updated weights for policy 0, policy_version 23062 (0.0009) -[2023-10-16 03:40:56,575][05218] Updated weights for policy 0, policy_version 23072 (0.0007) -[2023-10-16 03:40:57,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 47153152. Throughput: 0: 1806.0, 1: 1798.8. Samples: 11793746. Policy #0 lag: (min: 6.0, avg: 19.6, max: 38.0) -[2023-10-16 03:40:57,351][03835] Avg episode reward: [(0, '6.030'), (1, '4.510')] -[2023-10-16 03:40:57,618][05219] Updated weights for policy 1, policy_version 22980 (0.0007) -[2023-10-16 03:40:57,984][05219] Updated weights for policy 1, policy_version 22990 (0.0008) -[2023-10-16 03:40:58,360][05219] Updated weights for policy 1, policy_version 23000 (0.0009) -[2023-10-16 03:41:00,150][05218] Updated weights for policy 0, policy_version 23082 (0.0008) -[2023-10-16 03:41:00,523][05218] Updated weights for policy 0, policy_version 23092 (0.0008) -[2023-10-16 03:41:00,898][05218] Updated weights for policy 0, policy_version 23102 (0.0009) -[2023-10-16 03:41:02,238][05219] Updated weights for policy 1, policy_version 23010 (0.0008) -[2023-10-16 03:41:02,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 47218688. Throughput: 0: 1779.7, 1: 1803.7. Samples: 11814906. Policy #0 lag: (min: 6.0, avg: 19.6, max: 38.0) -[2023-10-16 03:41:02,351][03835] Avg episode reward: [(0, '5.350'), (1, '4.340')] -[2023-10-16 03:41:02,610][05219] Updated weights for policy 1, policy_version 23020 (0.0007) -[2023-10-16 03:41:02,972][05219] Updated weights for policy 1, policy_version 23030 (0.0007) -[2023-10-16 03:41:03,336][05219] Updated weights for policy 1, policy_version 23040 (0.0007) -[2023-10-16 03:41:04,598][05218] Updated weights for policy 0, policy_version 23112 (0.0007) -[2023-10-16 03:41:04,977][05218] Updated weights for policy 0, policy_version 23122 (0.0010) -[2023-10-16 03:41:05,360][05218] Updated weights for policy 0, policy_version 23132 (0.0011) -[2023-10-16 03:41:07,054][05219] Updated weights for policy 1, policy_version 23050 (0.0009) -[2023-10-16 03:41:07,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 47284224. Throughput: 0: 1780.0, 1: 1815.2. Samples: 11836994. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-16 03:41:07,351][03835] Avg episode reward: [(0, '5.080'), (1, '4.710')] -[2023-10-16 03:41:07,410][05219] Updated weights for policy 1, policy_version 23060 (0.0008) -[2023-10-16 03:41:07,776][05219] Updated weights for policy 1, policy_version 23070 (0.0007) -[2023-10-16 03:41:09,164][05218] Updated weights for policy 0, policy_version 23142 (0.0010) -[2023-10-16 03:41:09,554][05218] Updated weights for policy 0, policy_version 23152 (0.0009) -[2023-10-16 03:41:09,936][05218] Updated weights for policy 0, policy_version 23162 (0.0009) -[2023-10-16 03:41:11,528][05219] Updated weights for policy 1, policy_version 23080 (0.0007) -[2023-10-16 03:41:11,892][05219] Updated weights for policy 1, policy_version 23090 (0.0009) -[2023-10-16 03:41:12,256][05219] Updated weights for policy 1, policy_version 23100 (0.0008) -[2023-10-16 03:41:12,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 47349760. Throughput: 0: 1781.5, 1: 1803.6. Samples: 11847186. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-16 03:41:12,352][03835] Avg episode reward: [(0, '5.480'), (1, '4.640')] -[2023-10-16 03:41:13,827][05218] Updated weights for policy 0, policy_version 23172 (0.0009) -[2023-10-16 03:41:14,209][05218] Updated weights for policy 0, policy_version 23182 (0.0011) -[2023-10-16 03:41:14,578][05218] Updated weights for policy 0, policy_version 23192 (0.0008) -[2023-10-16 03:41:16,048][05219] Updated weights for policy 1, policy_version 23110 (0.0008) -[2023-10-16 03:41:16,401][05219] Updated weights for policy 1, policy_version 23120 (0.0009) -[2023-10-16 03:41:16,769][05219] Updated weights for policy 1, policy_version 23130 (0.0009) -[2023-10-16 03:41:17,351][03835] Fps is (10 sec: 16383.3, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 47448064. Throughput: 0: 1779.5, 1: 1815.4. Samples: 11869146. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-16 03:41:17,352][03835] Avg episode reward: [(0, '4.920'), (1, '4.560')] -[2023-10-16 03:41:18,157][05218] Updated weights for policy 0, policy_version 23202 (0.0010) -[2023-10-16 03:41:18,531][05218] Updated weights for policy 0, policy_version 23212 (0.0009) -[2023-10-16 03:41:18,904][05218] Updated weights for policy 0, policy_version 23222 (0.0009) -[2023-10-16 03:41:19,279][05218] Updated weights for policy 0, policy_version 23232 (0.0010) -[2023-10-16 03:41:20,518][05219] Updated weights for policy 1, policy_version 23140 (0.0010) -[2023-10-16 03:41:20,892][05219] Updated weights for policy 1, policy_version 23150 (0.0009) -[2023-10-16 03:41:21,252][05219] Updated weights for policy 1, policy_version 23160 (0.0008) -[2023-10-16 03:41:22,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 47513600. Throughput: 0: 1797.6, 1: 1797.1. Samples: 11890656. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-16 03:41:22,351][03835] Avg episode reward: [(0, '5.430'), (1, '4.580')] -[2023-10-16 03:41:22,877][05218] Updated weights for policy 0, policy_version 23242 (0.0007) -[2023-10-16 03:41:23,260][05218] Updated weights for policy 0, policy_version 23252 (0.0007) -[2023-10-16 03:41:23,632][05218] Updated weights for policy 0, policy_version 23262 (0.0007) -[2023-10-16 03:41:25,012][05219] Updated weights for policy 1, policy_version 23170 (0.0009) -[2023-10-16 03:41:25,376][05219] Updated weights for policy 1, policy_version 23180 (0.0009) -[2023-10-16 03:41:25,750][05219] Updated weights for policy 1, policy_version 23190 (0.0009) -[2023-10-16 03:41:26,110][05219] Updated weights for policy 1, policy_version 23200 (0.0008) -[2023-10-16 03:41:27,350][03835] Fps is (10 sec: 13107.8, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 47579136. Throughput: 0: 1779.6, 1: 1815.4. Samples: 11901594. Policy #0 lag: (min: 0.0, avg: 24.6, max: 32.0) -[2023-10-16 03:41:27,351][03835] Avg episode reward: [(0, '5.630'), (1, '5.120')] -[2023-10-16 03:41:27,518][05218] Updated weights for policy 0, policy_version 23272 (0.0007) -[2023-10-16 03:41:27,888][05218] Updated weights for policy 0, policy_version 23282 (0.0007) -[2023-10-16 03:41:28,265][05218] Updated weights for policy 0, policy_version 23292 (0.0007) -[2023-10-16 03:41:29,965][05219] Updated weights for policy 1, policy_version 23210 (0.0007) -[2023-10-16 03:41:30,337][05219] Updated weights for policy 1, policy_version 23220 (0.0008) -[2023-10-16 03:41:30,698][05219] Updated weights for policy 1, policy_version 23230 (0.0008) -[2023-10-16 03:41:31,916][05218] Updated weights for policy 0, policy_version 23302 (0.0008) -[2023-10-16 03:41:32,292][05218] Updated weights for policy 0, policy_version 23312 (0.0007) -[2023-10-16 03:41:32,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 47644672. Throughput: 0: 1795.3, 1: 1795.2. Samples: 11922752. Policy #0 lag: (min: 0.0, avg: 24.6, max: 32.0) -[2023-10-16 03:41:32,351][03835] Avg episode reward: [(0, '5.150'), (1, '4.950')] -[2023-10-16 03:41:32,672][05218] Updated weights for policy 0, policy_version 23322 (0.0009) -[2023-10-16 03:41:34,542][05219] Updated weights for policy 1, policy_version 23240 (0.0009) -[2023-10-16 03:41:34,921][05219] Updated weights for policy 1, policy_version 23250 (0.0007) -[2023-10-16 03:41:35,296][05219] Updated weights for policy 1, policy_version 23260 (0.0007) -[2023-10-16 03:41:36,458][05218] Updated weights for policy 0, policy_version 23332 (0.0007) -[2023-10-16 03:41:36,838][05218] Updated weights for policy 0, policy_version 23342 (0.0007) -[2023-10-16 03:41:37,206][05218] Updated weights for policy 0, policy_version 23352 (0.0009) -[2023-10-16 03:41:37,351][03835] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 47710208. Throughput: 0: 1794.4, 1: 1788.4. Samples: 11943852. Policy #0 lag: (min: 0.0, avg: 24.6, max: 32.0) -[2023-10-16 03:41:37,352][03835] Avg episode reward: [(0, '5.750'), (1, '4.850')] -[2023-10-16 03:41:37,361][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000023264_23822336.pth... -[2023-10-16 03:41:37,398][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000021600_22118400.pth -[2023-10-16 03:41:37,505][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000023360_23920640.pth... -[2023-10-16 03:41:37,534][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000021664_22183936.pth -[2023-10-16 03:41:38,975][05219] Updated weights for policy 1, policy_version 23270 (0.0008) -[2023-10-16 03:41:39,342][05219] Updated weights for policy 1, policy_version 23280 (0.0008) -[2023-10-16 03:41:39,712][05219] Updated weights for policy 1, policy_version 23290 (0.0007) -[2023-10-16 03:41:40,796][05218] Updated weights for policy 0, policy_version 23362 (0.0011) -[2023-10-16 03:41:41,171][05218] Updated weights for policy 0, policy_version 23372 (0.0009) -[2023-10-16 03:41:41,545][05218] Updated weights for policy 0, policy_version 23382 (0.0008) -[2023-10-16 03:41:41,920][05218] Updated weights for policy 0, policy_version 23392 (0.0008) -[2023-10-16 03:41:42,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 47808512. Throughput: 0: 1795.8, 1: 1785.9. Samples: 11954922. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-16 03:41:42,351][03835] Avg episode reward: [(0, '6.010'), (1, '4.250')] -[2023-10-16 03:41:43,594][05219] Updated weights for policy 1, policy_version 23300 (0.0007) -[2023-10-16 03:41:43,961][05219] Updated weights for policy 1, policy_version 23310 (0.0008) -[2023-10-16 03:41:44,323][05219] Updated weights for policy 1, policy_version 23320 (0.0008) -[2023-10-16 03:41:45,646][05218] Updated weights for policy 0, policy_version 23402 (0.0011) -[2023-10-16 03:41:46,005][05218] Updated weights for policy 0, policy_version 23412 (0.0010) -[2023-10-16 03:41:46,388][05218] Updated weights for policy 0, policy_version 23422 (0.0008) -[2023-10-16 03:41:47,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 47874048. Throughput: 0: 1796.4, 1: 1780.7. Samples: 11975874. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-16 03:41:47,351][03835] Avg episode reward: [(0, '5.830'), (1, '4.960')] -[2023-10-16 03:41:47,742][05219] Updated weights for policy 1, policy_version 23330 (0.0008) -[2023-10-16 03:41:48,097][05219] Updated weights for policy 1, policy_version 23340 (0.0009) -[2023-10-16 03:41:48,467][05219] Updated weights for policy 1, policy_version 23350 (0.0010) -[2023-10-16 03:41:48,825][05219] Updated weights for policy 1, policy_version 23360 (0.0009) -[2023-10-16 03:41:50,087][05218] Updated weights for policy 0, policy_version 23432 (0.0009) -[2023-10-16 03:41:50,477][05218] Updated weights for policy 0, policy_version 23442 (0.0010) -[2023-10-16 03:41:50,837][05218] Updated weights for policy 0, policy_version 23452 (0.0008) -[2023-10-16 03:41:52,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 47939584. Throughput: 0: 1790.2, 1: 1794.3. Samples: 11998296. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-16 03:41:52,352][03835] Avg episode reward: [(0, '6.000'), (1, '5.030')] -[2023-10-16 03:41:52,719][05219] Updated weights for policy 1, policy_version 23370 (0.0008) -[2023-10-16 03:41:53,084][05219] Updated weights for policy 1, policy_version 23380 (0.0009) -[2023-10-16 03:41:53,458][05219] Updated weights for policy 1, policy_version 23390 (0.0008) -[2023-10-16 03:41:54,570][05218] Updated weights for policy 0, policy_version 23462 (0.0008) -[2023-10-16 03:41:54,948][05218] Updated weights for policy 0, policy_version 23472 (0.0009) -[2023-10-16 03:41:55,326][05218] Updated weights for policy 0, policy_version 23482 (0.0008) -[2023-10-16 03:41:57,264][05219] Updated weights for policy 1, policy_version 23400 (0.0009) -[2023-10-16 03:41:57,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 48005120. Throughput: 0: 1801.7, 1: 1778.9. Samples: 12008316. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-16 03:41:57,351][03835] Avg episode reward: [(0, '4.980'), (1, '5.360')] -[2023-10-16 03:41:57,633][05219] Updated weights for policy 1, policy_version 23410 (0.0010) -[2023-10-16 03:41:57,993][05219] Updated weights for policy 1, policy_version 23420 (0.0007) -[2023-10-16 03:41:58,980][05218] Updated weights for policy 0, policy_version 23492 (0.0007) -[2023-10-16 03:41:59,355][05218] Updated weights for policy 0, policy_version 23502 (0.0009) -[2023-10-16 03:41:59,725][05218] Updated weights for policy 0, policy_version 23512 (0.0007) -[2023-10-16 03:42:01,853][05219] Updated weights for policy 1, policy_version 23430 (0.0008) -[2023-10-16 03:42:02,220][05219] Updated weights for policy 1, policy_version 23440 (0.0007) -[2023-10-16 03:42:02,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 48070656. Throughput: 0: 1796.5, 1: 1785.3. Samples: 12030328. Policy #0 lag: (min: 8.0, avg: 34.2, max: 40.0) -[2023-10-16 03:42:02,351][03835] Avg episode reward: [(0, '5.260'), (1, '5.080')] -[2023-10-16 03:42:02,591][05219] Updated weights for policy 1, policy_version 23450 (0.0008) -[2023-10-16 03:42:03,447][05218] Updated weights for policy 0, policy_version 23522 (0.0010) -[2023-10-16 03:42:03,823][05218] Updated weights for policy 0, policy_version 23532 (0.0009) -[2023-10-16 03:42:04,202][05218] Updated weights for policy 0, policy_version 23542 (0.0009) -[2023-10-16 03:42:04,587][05218] Updated weights for policy 0, policy_version 23552 (0.0009) -[2023-10-16 03:42:06,371][05219] Updated weights for policy 1, policy_version 23460 (0.0008) -[2023-10-16 03:42:06,737][05219] Updated weights for policy 1, policy_version 23470 (0.0008) -[2023-10-16 03:42:07,104][05219] Updated weights for policy 1, policy_version 23480 (0.0007) -[2023-10-16 03:42:07,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 48136192. Throughput: 0: 1793.5, 1: 1784.7. Samples: 12051674. Policy #0 lag: (min: 8.0, avg: 34.2, max: 40.0) -[2023-10-16 03:42:07,351][03835] Avg episode reward: [(0, '4.310'), (1, '4.410')] -[2023-10-16 03:42:08,336][05218] Updated weights for policy 0, policy_version 23562 (0.0011) -[2023-10-16 03:42:08,718][05218] Updated weights for policy 0, policy_version 23572 (0.0010) -[2023-10-16 03:42:09,097][05218] Updated weights for policy 0, policy_version 23582 (0.0011) -[2023-10-16 03:42:10,954][05219] Updated weights for policy 1, policy_version 23490 (0.0010) -[2023-10-16 03:42:11,326][05219] Updated weights for policy 1, policy_version 23500 (0.0007) -[2023-10-16 03:42:11,687][05219] Updated weights for policy 1, policy_version 23510 (0.0009) -[2023-10-16 03:42:12,045][05219] Updated weights for policy 1, policy_version 23520 (0.0009) -[2023-10-16 03:42:12,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 48234496. Throughput: 0: 1797.5, 1: 1779.4. Samples: 12062552. Policy #0 lag: (min: 8.0, avg: 34.2, max: 40.0) -[2023-10-16 03:42:12,352][03835] Avg episode reward: [(0, '5.520'), (1, '5.100')] -[2023-10-16 03:42:12,882][05218] Updated weights for policy 0, policy_version 23592 (0.0009) -[2023-10-16 03:42:13,261][05218] Updated weights for policy 0, policy_version 23602 (0.0009) -[2023-10-16 03:42:13,635][05218] Updated weights for policy 0, policy_version 23612 (0.0010) -[2023-10-16 03:42:15,794][05219] Updated weights for policy 1, policy_version 23530 (0.0008) -[2023-10-16 03:42:16,152][05219] Updated weights for policy 1, policy_version 23540 (0.0009) -[2023-10-16 03:42:16,523][05219] Updated weights for policy 1, policy_version 23550 (0.0007) -[2023-10-16 03:42:17,336][05218] Updated weights for policy 0, policy_version 23622 (0.0008) -[2023-10-16 03:42:17,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14199.6, 300 sec: 14329.1). Total num frames: 48300032. Throughput: 0: 1799.1, 1: 1790.8. Samples: 12084294. Policy #0 lag: (min: 8.0, avg: 34.2, max: 40.0) -[2023-10-16 03:42:17,351][03835] Avg episode reward: [(0, '5.430'), (1, '4.650')] -[2023-10-16 03:42:17,712][05218] Updated weights for policy 0, policy_version 23632 (0.0007) -[2023-10-16 03:42:18,093][05218] Updated weights for policy 0, policy_version 23642 (0.0008) -[2023-10-16 03:42:20,258][05219] Updated weights for policy 1, policy_version 23560 (0.0007) -[2023-10-16 03:42:20,633][05219] Updated weights for policy 1, policy_version 23570 (0.0007) -[2023-10-16 03:42:21,008][05219] Updated weights for policy 1, policy_version 23580 (0.0008) -[2023-10-16 03:42:21,897][05218] Updated weights for policy 0, policy_version 23652 (0.0009) -[2023-10-16 03:42:22,275][05218] Updated weights for policy 0, policy_version 23662 (0.0007) -[2023-10-16 03:42:22,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 48365568. Throughput: 0: 1810.8, 1: 1780.7. Samples: 12105468. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:42:22,351][03835] Avg episode reward: [(0, '5.730'), (1, '5.080')] -[2023-10-16 03:42:22,656][05218] Updated weights for policy 0, policy_version 23672 (0.0010) -[2023-10-16 03:42:24,686][05219] Updated weights for policy 1, policy_version 23590 (0.0008) -[2023-10-16 03:42:25,056][05219] Updated weights for policy 1, policy_version 23600 (0.0009) -[2023-10-16 03:42:25,425][05219] Updated weights for policy 1, policy_version 23610 (0.0009) -[2023-10-16 03:42:26,408][05218] Updated weights for policy 0, policy_version 23682 (0.0009) -[2023-10-16 03:42:26,787][05218] Updated weights for policy 0, policy_version 23692 (0.0008) -[2023-10-16 03:42:27,161][05218] Updated weights for policy 0, policy_version 23702 (0.0008) -[2023-10-16 03:42:27,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 48431104. Throughput: 0: 1793.6, 1: 1797.5. Samples: 12116524. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:42:27,351][03835] Avg episode reward: [(0, '5.590'), (1, '5.300')] -[2023-10-16 03:42:27,540][05218] Updated weights for policy 0, policy_version 23712 (0.0009) -[2023-10-16 03:42:29,330][05219] Updated weights for policy 1, policy_version 23620 (0.0007) -[2023-10-16 03:42:29,697][05219] Updated weights for policy 1, policy_version 23630 (0.0008) -[2023-10-16 03:42:30,080][05219] Updated weights for policy 1, policy_version 23640 (0.0010) -[2023-10-16 03:42:31,340][05218] Updated weights for policy 0, policy_version 23722 (0.0010) -[2023-10-16 03:42:31,703][05218] Updated weights for policy 0, policy_version 23732 (0.0008) -[2023-10-16 03:42:32,077][05218] Updated weights for policy 0, policy_version 23742 (0.0009) -[2023-10-16 03:42:32,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.2). Total num frames: 48529408. Throughput: 0: 1807.2, 1: 1787.3. Samples: 12137628. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:42:32,351][03835] Avg episode reward: [(0, '5.370'), (1, '4.910')] -[2023-10-16 03:42:33,860][05219] Updated weights for policy 1, policy_version 23650 (0.0008) -[2023-10-16 03:42:34,222][05219] Updated weights for policy 1, policy_version 23660 (0.0007) -[2023-10-16 03:42:34,591][05219] Updated weights for policy 1, policy_version 23670 (0.0010) -[2023-10-16 03:42:34,947][05219] Updated weights for policy 1, policy_version 23680 (0.0010) -[2023-10-16 03:42:35,576][05218] Updated weights for policy 0, policy_version 23752 (0.0010) -[2023-10-16 03:42:35,953][05218] Updated weights for policy 0, policy_version 23762 (0.0011) -[2023-10-16 03:42:36,317][05218] Updated weights for policy 0, policy_version 23772 (0.0010) -[2023-10-16 03:42:37,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 48594944. Throughput: 0: 1792.7, 1: 1789.1. Samples: 12159478. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:42:37,351][03835] Avg episode reward: [(0, '5.330'), (1, '5.700')] -[2023-10-16 03:42:38,594][05219] Updated weights for policy 1, policy_version 23690 (0.0008) -[2023-10-16 03:42:38,961][05219] Updated weights for policy 1, policy_version 23700 (0.0008) -[2023-10-16 03:42:39,323][05219] Updated weights for policy 1, policy_version 23710 (0.0010) -[2023-10-16 03:42:40,131][05218] Updated weights for policy 0, policy_version 23782 (0.0008) -[2023-10-16 03:42:40,520][05218] Updated weights for policy 0, policy_version 23792 (0.0008) -[2023-10-16 03:42:40,894][05218] Updated weights for policy 0, policy_version 23802 (0.0008) -[2023-10-16 03:42:42,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 48660480. Throughput: 0: 1807.9, 1: 1786.9. Samples: 12170084. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:42:42,352][03835] Avg episode reward: [(0, '5.130'), (1, '4.690')] -[2023-10-16 03:42:43,221][05219] Updated weights for policy 1, policy_version 23720 (0.0009) -[2023-10-16 03:42:43,590][05219] Updated weights for policy 1, policy_version 23730 (0.0009) -[2023-10-16 03:42:43,956][05219] Updated weights for policy 1, policy_version 23740 (0.0009) -[2023-10-16 03:42:44,470][05218] Updated weights for policy 0, policy_version 23812 (0.0007) -[2023-10-16 03:42:44,851][05218] Updated weights for policy 0, policy_version 23822 (0.0007) -[2023-10-16 03:42:45,236][05218] Updated weights for policy 0, policy_version 23832 (0.0008) -[2023-10-16 03:42:47,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 48726016. Throughput: 0: 1800.4, 1: 1785.0. Samples: 12191670. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:42:47,352][03835] Avg episode reward: [(0, '5.230'), (1, '5.020')] -[2023-10-16 03:42:47,634][05219] Updated weights for policy 1, policy_version 23750 (0.0009) -[2023-10-16 03:42:48,003][05219] Updated weights for policy 1, policy_version 23760 (0.0010) -[2023-10-16 03:42:48,365][05219] Updated weights for policy 1, policy_version 23770 (0.0009) -[2023-10-16 03:42:49,063][05218] Updated weights for policy 0, policy_version 23842 (0.0009) -[2023-10-16 03:42:49,432][05218] Updated weights for policy 0, policy_version 23852 (0.0009) -[2023-10-16 03:42:49,802][05218] Updated weights for policy 0, policy_version 23862 (0.0009) -[2023-10-16 03:42:50,180][05218] Updated weights for policy 0, policy_version 23872 (0.0009) -[2023-10-16 03:42:52,049][05219] Updated weights for policy 1, policy_version 23780 (0.0008) -[2023-10-16 03:42:52,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 48791552. Throughput: 0: 1801.9, 1: 1807.8. Samples: 12214112. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:42:52,351][03835] Avg episode reward: [(0, '5.380'), (1, '4.990')] -[2023-10-16 03:42:52,406][05219] Updated weights for policy 1, policy_version 23790 (0.0010) -[2023-10-16 03:42:52,776][05219] Updated weights for policy 1, policy_version 23800 (0.0009) -[2023-10-16 03:42:53,925][05218] Updated weights for policy 0, policy_version 23882 (0.0008) -[2023-10-16 03:42:54,314][05218] Updated weights for policy 0, policy_version 23892 (0.0009) -[2023-10-16 03:42:54,685][05218] Updated weights for policy 0, policy_version 23902 (0.0009) -[2023-10-16 03:42:56,448][05219] Updated weights for policy 1, policy_version 23810 (0.0007) -[2023-10-16 03:42:56,810][05219] Updated weights for policy 1, policy_version 23820 (0.0007) -[2023-10-16 03:42:57,178][05219] Updated weights for policy 1, policy_version 23830 (0.0009) -[2023-10-16 03:42:57,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 48857088. Throughput: 0: 1801.2, 1: 1790.7. Samples: 12224186. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-16 03:42:57,351][03835] Avg episode reward: [(0, '5.500'), (1, '5.180')] -[2023-10-16 03:42:57,546][05219] Updated weights for policy 1, policy_version 23840 (0.0007) -[2023-10-16 03:42:58,434][05218] Updated weights for policy 0, policy_version 23912 (0.0010) -[2023-10-16 03:42:58,807][05218] Updated weights for policy 0, policy_version 23922 (0.0010) -[2023-10-16 03:42:59,184][05218] Updated weights for policy 0, policy_version 23932 (0.0008) -[2023-10-16 03:43:01,197][05219] Updated weights for policy 1, policy_version 23850 (0.0007) -[2023-10-16 03:43:01,562][05219] Updated weights for policy 1, policy_version 23860 (0.0008) -[2023-10-16 03:43:01,919][05219] Updated weights for policy 1, policy_version 23870 (0.0008) -[2023-10-16 03:43:02,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 48955392. Throughput: 0: 1796.2, 1: 1802.8. Samples: 12246250. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-16 03:43:02,351][03835] Avg episode reward: [(0, '5.170'), (1, '5.060')] -[2023-10-16 03:43:02,876][05218] Updated weights for policy 0, policy_version 23942 (0.0008) -[2023-10-16 03:43:03,252][05218] Updated weights for policy 0, policy_version 23952 (0.0008) -[2023-10-16 03:43:03,635][05218] Updated weights for policy 0, policy_version 23962 (0.0011) -[2023-10-16 03:43:05,844][05219] Updated weights for policy 1, policy_version 23880 (0.0008) -[2023-10-16 03:43:06,215][05219] Updated weights for policy 1, policy_version 23890 (0.0007) -[2023-10-16 03:43:06,580][05219] Updated weights for policy 1, policy_version 23900 (0.0008) -[2023-10-16 03:43:07,217][05218] Updated weights for policy 0, policy_version 23972 (0.0010) -[2023-10-16 03:43:07,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 49020928. Throughput: 0: 1807.0, 1: 1789.1. Samples: 12267294. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-16 03:43:07,351][03835] Avg episode reward: [(0, '5.480'), (1, '4.810')] -[2023-10-16 03:43:07,589][05218] Updated weights for policy 0, policy_version 23982 (0.0010) -[2023-10-16 03:43:07,977][05218] Updated weights for policy 0, policy_version 23992 (0.0010) -[2023-10-16 03:43:10,436][05219] Updated weights for policy 1, policy_version 23910 (0.0008) -[2023-10-16 03:43:10,806][05219] Updated weights for policy 1, policy_version 23920 (0.0009) -[2023-10-16 03:43:11,162][05219] Updated weights for policy 1, policy_version 23930 (0.0010) -[2023-10-16 03:43:11,802][05218] Updated weights for policy 0, policy_version 24002 (0.0009) -[2023-10-16 03:43:12,175][05218] Updated weights for policy 0, policy_version 24012 (0.0008) -[2023-10-16 03:43:12,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 49086464. Throughput: 0: 1798.4, 1: 1807.7. Samples: 12278800. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-16 03:43:12,351][03835] Avg episode reward: [(0, '4.930'), (1, '5.110')] -[2023-10-16 03:43:12,552][05218] Updated weights for policy 0, policy_version 24022 (0.0007) -[2023-10-16 03:43:12,918][05218] Updated weights for policy 0, policy_version 24032 (0.0009) -[2023-10-16 03:43:14,892][05219] Updated weights for policy 1, policy_version 23940 (0.0008) -[2023-10-16 03:43:15,259][05219] Updated weights for policy 1, policy_version 23950 (0.0009) -[2023-10-16 03:43:15,629][05219] Updated weights for policy 1, policy_version 23960 (0.0008) -[2023-10-16 03:43:16,678][05218] Updated weights for policy 0, policy_version 24042 (0.0009) -[2023-10-16 03:43:17,054][05218] Updated weights for policy 0, policy_version 24052 (0.0010) -[2023-10-16 03:43:17,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 49152000. Throughput: 0: 1813.6, 1: 1790.3. Samples: 12299806. Policy #0 lag: (min: 21.0, avg: 24.7, max: 53.0) -[2023-10-16 03:43:17,351][03835] Avg episode reward: [(0, '5.500'), (1, '5.610')] -[2023-10-16 03:43:17,434][05218] Updated weights for policy 0, policy_version 24062 (0.0009) -[2023-10-16 03:43:19,269][05219] Updated weights for policy 1, policy_version 23970 (0.0010) -[2023-10-16 03:43:19,628][05219] Updated weights for policy 1, policy_version 23980 (0.0010) -[2023-10-16 03:43:19,989][05219] Updated weights for policy 1, policy_version 23990 (0.0010) -[2023-10-16 03:43:20,353][05219] Updated weights for policy 1, policy_version 24000 (0.0011) -[2023-10-16 03:43:21,222][05218] Updated weights for policy 0, policy_version 24072 (0.0008) -[2023-10-16 03:43:21,595][05218] Updated weights for policy 0, policy_version 24082 (0.0008) -[2023-10-16 03:43:21,965][05218] Updated weights for policy 0, policy_version 24092 (0.0010) -[2023-10-16 03:43:22,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 49250304. Throughput: 0: 1798.1, 1: 1787.9. Samples: 12320846. Policy #0 lag: (min: 21.0, avg: 24.7, max: 53.0) -[2023-10-16 03:43:22,351][03835] Avg episode reward: [(0, '6.220'), (1, '5.850')] -[2023-10-16 03:43:22,359][04766] Saving new best policy, reward=6.220! -[2023-10-16 03:43:22,359][04891] Saving new best policy, reward=5.850! -[2023-10-16 03:43:24,196][05219] Updated weights for policy 1, policy_version 24010 (0.0007) -[2023-10-16 03:43:24,551][05219] Updated weights for policy 1, policy_version 24020 (0.0007) -[2023-10-16 03:43:24,917][05219] Updated weights for policy 1, policy_version 24030 (0.0007) -[2023-10-16 03:43:25,772][05218] Updated weights for policy 0, policy_version 24102 (0.0009) -[2023-10-16 03:43:26,160][05218] Updated weights for policy 0, policy_version 24112 (0.0007) -[2023-10-16 03:43:26,539][05218] Updated weights for policy 0, policy_version 24122 (0.0007) -[2023-10-16 03:43:27,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 49315840. Throughput: 0: 1810.9, 1: 1789.4. Samples: 12332096. Policy #0 lag: (min: 21.0, avg: 24.7, max: 53.0) -[2023-10-16 03:43:27,351][03835] Avg episode reward: [(0, '5.280'), (1, '5.060')] -[2023-10-16 03:43:28,608][05219] Updated weights for policy 1, policy_version 24040 (0.0009) -[2023-10-16 03:43:28,969][05219] Updated weights for policy 1, policy_version 24050 (0.0009) -[2023-10-16 03:43:29,336][05219] Updated weights for policy 1, policy_version 24060 (0.0011) -[2023-10-16 03:43:30,308][05218] Updated weights for policy 0, policy_version 24132 (0.0011) -[2023-10-16 03:43:30,686][05218] Updated weights for policy 0, policy_version 24142 (0.0013) -[2023-10-16 03:43:31,058][05218] Updated weights for policy 0, policy_version 24152 (0.0010) -[2023-10-16 03:43:32,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 49381376. Throughput: 0: 1789.1, 1: 1790.6. Samples: 12352756. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-16 03:43:32,351][03835] Avg episode reward: [(0, '5.480'), (1, '5.310')] -[2023-10-16 03:43:32,973][05219] Updated weights for policy 1, policy_version 24070 (0.0009) -[2023-10-16 03:43:33,328][05219] Updated weights for policy 1, policy_version 24080 (0.0010) -[2023-10-16 03:43:33,699][05219] Updated weights for policy 1, policy_version 24090 (0.0008) -[2023-10-16 03:43:34,780][05218] Updated weights for policy 0, policy_version 24162 (0.0008) -[2023-10-16 03:43:35,166][05218] Updated weights for policy 0, policy_version 24172 (0.0007) -[2023-10-16 03:43:35,536][05218] Updated weights for policy 0, policy_version 24182 (0.0008) -[2023-10-16 03:43:35,913][05218] Updated weights for policy 0, policy_version 24192 (0.0010) -[2023-10-16 03:43:37,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 49446912. Throughput: 0: 1784.2, 1: 1796.5. Samples: 12375244. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-16 03:43:37,351][03835] Avg episode reward: [(0, '5.410'), (1, '4.850')] -[2023-10-16 03:43:37,363][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000024192_24772608.pth... -[2023-10-16 03:43:37,402][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000022496_23035904.pth -[2023-10-16 03:43:37,553][05219] Updated weights for policy 1, policy_version 24100 (0.0008) -[2023-10-16 03:43:37,922][05219] Updated weights for policy 1, policy_version 24110 (0.0008) -[2023-10-16 03:43:38,280][05219] Updated weights for policy 1, policy_version 24120 (0.0009) -[2023-10-16 03:43:38,577][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000024128_24707072.pth... -[2023-10-16 03:43:38,606][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000022432_22970368.pth -[2023-10-16 03:43:39,719][05218] Updated weights for policy 0, policy_version 24202 (0.0007) -[2023-10-16 03:43:40,100][05218] Updated weights for policy 0, policy_version 24212 (0.0008) -[2023-10-16 03:43:40,476][05218] Updated weights for policy 0, policy_version 24222 (0.0009) -[2023-10-16 03:43:41,939][05219] Updated weights for policy 1, policy_version 24130 (0.0009) -[2023-10-16 03:43:42,313][05219] Updated weights for policy 1, policy_version 24140 (0.0007) -[2023-10-16 03:43:42,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 49512448. Throughput: 0: 1792.9, 1: 1792.2. Samples: 12385516. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-16 03:43:42,352][03835] Avg episode reward: [(0, '5.900'), (1, '5.170')] -[2023-10-16 03:43:42,668][05219] Updated weights for policy 1, policy_version 24150 (0.0007) -[2023-10-16 03:43:43,036][05219] Updated weights for policy 1, policy_version 24160 (0.0008) -[2023-10-16 03:43:44,180][05218] Updated weights for policy 0, policy_version 24232 (0.0008) -[2023-10-16 03:43:44,552][05218] Updated weights for policy 0, policy_version 24242 (0.0007) -[2023-10-16 03:43:44,925][05218] Updated weights for policy 0, policy_version 24252 (0.0007) -[2023-10-16 03:43:46,888][05219] Updated weights for policy 1, policy_version 24170 (0.0010) -[2023-10-16 03:43:47,258][05219] Updated weights for policy 1, policy_version 24180 (0.0009) -[2023-10-16 03:43:47,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 49577984. Throughput: 0: 1785.9, 1: 1796.9. Samples: 12407476. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-16 03:43:47,351][03835] Avg episode reward: [(0, '6.260'), (1, '5.460')] -[2023-10-16 03:43:47,353][04766] Saving new best policy, reward=6.260! -[2023-10-16 03:43:47,620][05219] Updated weights for policy 1, policy_version 24190 (0.0010) -[2023-10-16 03:43:48,676][05218] Updated weights for policy 0, policy_version 24262 (0.0009) -[2023-10-16 03:43:49,046][05218] Updated weights for policy 0, policy_version 24272 (0.0010) -[2023-10-16 03:43:49,419][05218] Updated weights for policy 0, policy_version 24282 (0.0009) -[2023-10-16 03:43:51,470][05219] Updated weights for policy 1, policy_version 24200 (0.0010) -[2023-10-16 03:43:51,844][05219] Updated weights for policy 1, policy_version 24210 (0.0008) -[2023-10-16 03:43:52,210][05219] Updated weights for policy 1, policy_version 24220 (0.0008) -[2023-10-16 03:43:52,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 49643520. Throughput: 0: 1790.3, 1: 1799.2. Samples: 12428820. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:43:52,352][03835] Avg episode reward: [(0, '6.240'), (1, '5.440')] -[2023-10-16 03:43:53,195][05218] Updated weights for policy 0, policy_version 24292 (0.0009) -[2023-10-16 03:43:53,569][05218] Updated weights for policy 0, policy_version 24302 (0.0008) -[2023-10-16 03:43:53,945][05218] Updated weights for policy 0, policy_version 24312 (0.0007) -[2023-10-16 03:43:55,782][05219] Updated weights for policy 1, policy_version 24230 (0.0009) -[2023-10-16 03:43:56,144][05219] Updated weights for policy 1, policy_version 24240 (0.0007) -[2023-10-16 03:43:56,507][05219] Updated weights for policy 1, policy_version 24250 (0.0007) -[2023-10-16 03:43:57,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 49741824. Throughput: 0: 1780.0, 1: 1795.9. Samples: 12439718. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:43:57,351][03835] Avg episode reward: [(0, '6.200'), (1, '5.690')] -[2023-10-16 03:43:57,742][05218] Updated weights for policy 0, policy_version 24322 (0.0008) -[2023-10-16 03:43:58,111][05218] Updated weights for policy 0, policy_version 24332 (0.0007) -[2023-10-16 03:43:58,490][05218] Updated weights for policy 0, policy_version 24342 (0.0007) -[2023-10-16 03:43:58,868][05218] Updated weights for policy 0, policy_version 24352 (0.0007) -[2023-10-16 03:44:00,119][05219] Updated weights for policy 1, policy_version 24260 (0.0007) -[2023-10-16 03:44:00,488][05219] Updated weights for policy 1, policy_version 24270 (0.0008) -[2023-10-16 03:44:00,850][05219] Updated weights for policy 1, policy_version 24280 (0.0008) -[2023-10-16 03:44:02,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 49807360. Throughput: 0: 1785.1, 1: 1804.1. Samples: 12461320. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:44:02,351][03835] Avg episode reward: [(0, '5.580'), (1, '5.300')] -[2023-10-16 03:44:02,601][05218] Updated weights for policy 0, policy_version 24362 (0.0007) -[2023-10-16 03:44:02,975][05218] Updated weights for policy 0, policy_version 24372 (0.0008) -[2023-10-16 03:44:03,346][05218] Updated weights for policy 0, policy_version 24382 (0.0008) -[2023-10-16 03:44:04,686][05219] Updated weights for policy 1, policy_version 24290 (0.0009) -[2023-10-16 03:44:05,050][05219] Updated weights for policy 1, policy_version 24300 (0.0007) -[2023-10-16 03:44:05,408][05219] Updated weights for policy 1, policy_version 24310 (0.0010) -[2023-10-16 03:44:05,776][05219] Updated weights for policy 1, policy_version 24320 (0.0008) -[2023-10-16 03:44:07,181][05218] Updated weights for policy 0, policy_version 24392 (0.0009) -[2023-10-16 03:44:07,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 49872896. Throughput: 0: 1804.5, 1: 1798.7. Samples: 12482988. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:44:07,351][03835] Avg episode reward: [(0, '5.400'), (1, '5.260')] -[2023-10-16 03:44:07,557][05218] Updated weights for policy 0, policy_version 24402 (0.0009) -[2023-10-16 03:44:07,923][05218] Updated weights for policy 0, policy_version 24412 (0.0008) -[2023-10-16 03:44:09,542][05219] Updated weights for policy 1, policy_version 24330 (0.0009) -[2023-10-16 03:44:09,911][05219] Updated weights for policy 1, policy_version 24340 (0.0008) -[2023-10-16 03:44:10,272][05219] Updated weights for policy 1, policy_version 24350 (0.0008) -[2023-10-16 03:44:11,595][05218] Updated weights for policy 0, policy_version 24422 (0.0009) -[2023-10-16 03:44:11,967][05218] Updated weights for policy 0, policy_version 24432 (0.0010) -[2023-10-16 03:44:12,348][05218] Updated weights for policy 0, policy_version 24442 (0.0008) -[2023-10-16 03:44:12,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 49938432. Throughput: 0: 1785.1, 1: 1808.6. Samples: 12493812. Policy #0 lag: (min: 16.0, avg: 42.3, max: 48.0) -[2023-10-16 03:44:12,351][03835] Avg episode reward: [(0, '5.080'), (1, '5.040')] -[2023-10-16 03:44:13,994][05219] Updated weights for policy 1, policy_version 24360 (0.0010) -[2023-10-16 03:44:14,365][05219] Updated weights for policy 1, policy_version 24370 (0.0008) -[2023-10-16 03:44:14,719][05219] Updated weights for policy 1, policy_version 24380 (0.0008) -[2023-10-16 03:44:16,059][05218] Updated weights for policy 0, policy_version 24452 (0.0009) -[2023-10-16 03:44:16,442][05218] Updated weights for policy 0, policy_version 24462 (0.0009) -[2023-10-16 03:44:16,817][05218] Updated weights for policy 0, policy_version 24472 (0.0008) -[2023-10-16 03:44:17,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 50036736. Throughput: 0: 1807.8, 1: 1801.0. Samples: 12515154. Policy #0 lag: (min: 16.0, avg: 42.3, max: 48.0) -[2023-10-16 03:44:17,351][03835] Avg episode reward: [(0, '5.050'), (1, '4.890')] -[2023-10-16 03:44:18,442][05219] Updated weights for policy 1, policy_version 24390 (0.0008) -[2023-10-16 03:44:18,816][05219] Updated weights for policy 1, policy_version 24400 (0.0008) -[2023-10-16 03:44:19,183][05219] Updated weights for policy 1, policy_version 24410 (0.0008) -[2023-10-16 03:44:20,629][05218] Updated weights for policy 0, policy_version 24482 (0.0010) -[2023-10-16 03:44:21,001][05218] Updated weights for policy 0, policy_version 24492 (0.0011) -[2023-10-16 03:44:21,379][05218] Updated weights for policy 0, policy_version 24502 (0.0007) -[2023-10-16 03:44:21,756][05218] Updated weights for policy 0, policy_version 24512 (0.0008) -[2023-10-16 03:44:22,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 50102272. Throughput: 0: 1783.5, 1: 1802.4. Samples: 12536610. Policy #0 lag: (min: 16.0, avg: 42.3, max: 48.0) -[2023-10-16 03:44:22,351][03835] Avg episode reward: [(0, '5.370'), (1, '6.310')] -[2023-10-16 03:44:22,362][04891] Saving new best policy, reward=6.310! -[2023-10-16 03:44:23,082][05219] Updated weights for policy 1, policy_version 24420 (0.0007) -[2023-10-16 03:44:23,453][05219] Updated weights for policy 1, policy_version 24430 (0.0007) -[2023-10-16 03:44:23,817][05219] Updated weights for policy 1, policy_version 24440 (0.0007) -[2023-10-16 03:44:25,502][05218] Updated weights for policy 0, policy_version 24522 (0.0009) -[2023-10-16 03:44:25,869][05218] Updated weights for policy 0, policy_version 24532 (0.0009) -[2023-10-16 03:44:26,234][05218] Updated weights for policy 0, policy_version 24542 (0.0008) -[2023-10-16 03:44:27,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 50167808. Throughput: 0: 1805.1, 1: 1801.1. Samples: 12547792. Policy #0 lag: (min: 3.0, avg: 3.3, max: 13.0) -[2023-10-16 03:44:27,351][03835] Avg episode reward: [(0, '5.300'), (1, '5.190')] -[2023-10-16 03:44:27,526][05219] Updated weights for policy 1, policy_version 24450 (0.0008) -[2023-10-16 03:44:27,878][05219] Updated weights for policy 1, policy_version 24460 (0.0009) -[2023-10-16 03:44:28,254][05219] Updated weights for policy 1, policy_version 24470 (0.0008) -[2023-10-16 03:44:28,615][05219] Updated weights for policy 1, policy_version 24480 (0.0008) -[2023-10-16 03:44:29,920][05218] Updated weights for policy 0, policy_version 24552 (0.0008) -[2023-10-16 03:44:30,296][05218] Updated weights for policy 0, policy_version 24562 (0.0009) -[2023-10-16 03:44:30,665][05218] Updated weights for policy 0, policy_version 24572 (0.0009) -[2023-10-16 03:44:32,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 50233344. Throughput: 0: 1788.5, 1: 1807.2. Samples: 12569280. Policy #0 lag: (min: 3.0, avg: 3.3, max: 13.0) -[2023-10-16 03:44:32,351][03835] Avg episode reward: [(0, '5.430'), (1, '5.840')] -[2023-10-16 03:44:32,395][05219] Updated weights for policy 1, policy_version 24490 (0.0010) -[2023-10-16 03:44:32,762][05219] Updated weights for policy 1, policy_version 24500 (0.0011) -[2023-10-16 03:44:33,123][05219] Updated weights for policy 1, policy_version 24510 (0.0010) -[2023-10-16 03:44:34,170][05218] Updated weights for policy 0, policy_version 24582 (0.0008) -[2023-10-16 03:44:34,544][05218] Updated weights for policy 0, policy_version 24592 (0.0009) -[2023-10-16 03:44:34,921][05218] Updated weights for policy 0, policy_version 24602 (0.0007) -[2023-10-16 03:44:36,975][05219] Updated weights for policy 1, policy_version 24520 (0.0009) -[2023-10-16 03:44:37,333][05219] Updated weights for policy 1, policy_version 24530 (0.0008) -[2023-10-16 03:44:37,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 50298880. Throughput: 0: 1796.4, 1: 1817.9. Samples: 12591462. Policy #0 lag: (min: 3.0, avg: 3.3, max: 13.0) -[2023-10-16 03:44:37,351][03835] Avg episode reward: [(0, '5.080'), (1, '4.920')] -[2023-10-16 03:44:37,698][05219] Updated weights for policy 1, policy_version 24540 (0.0007) -[2023-10-16 03:44:38,583][05218] Updated weights for policy 0, policy_version 24612 (0.0010) -[2023-10-16 03:44:38,951][05218] Updated weights for policy 0, policy_version 24622 (0.0009) -[2023-10-16 03:44:39,327][05218] Updated weights for policy 0, policy_version 24632 (0.0007) -[2023-10-16 03:44:41,246][05219] Updated weights for policy 1, policy_version 24550 (0.0008) -[2023-10-16 03:44:41,607][05219] Updated weights for policy 1, policy_version 24560 (0.0008) -[2023-10-16 03:44:41,982][05219] Updated weights for policy 1, policy_version 24570 (0.0007) -[2023-10-16 03:44:42,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 50397184. Throughput: 0: 1799.7, 1: 1802.4. Samples: 12601814. Policy #0 lag: (min: 3.0, avg: 3.3, max: 13.0) -[2023-10-16 03:44:42,351][03835] Avg episode reward: [(0, '5.180'), (1, '4.850')] -[2023-10-16 03:44:43,034][05218] Updated weights for policy 0, policy_version 24642 (0.0009) -[2023-10-16 03:44:43,405][05218] Updated weights for policy 0, policy_version 24652 (0.0010) -[2023-10-16 03:44:43,787][05218] Updated weights for policy 0, policy_version 24662 (0.0009) -[2023-10-16 03:44:44,157][05218] Updated weights for policy 0, policy_version 24672 (0.0009) -[2023-10-16 03:44:45,712][05219] Updated weights for policy 1, policy_version 24580 (0.0007) -[2023-10-16 03:44:46,077][05219] Updated weights for policy 1, policy_version 24590 (0.0010) -[2023-10-16 03:44:46,445][05219] Updated weights for policy 1, policy_version 24600 (0.0008) -[2023-10-16 03:44:47,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 50462720. Throughput: 0: 1796.8, 1: 1809.6. Samples: 12623604. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-16 03:44:47,351][03835] Avg episode reward: [(0, '5.420'), (1, '5.550')] -[2023-10-16 03:44:47,885][05218] Updated weights for policy 0, policy_version 24682 (0.0008) -[2023-10-16 03:44:48,264][05218] Updated weights for policy 0, policy_version 24692 (0.0010) -[2023-10-16 03:44:48,639][05218] Updated weights for policy 0, policy_version 24702 (0.0009) -[2023-10-16 03:44:50,209][05219] Updated weights for policy 1, policy_version 24610 (0.0010) -[2023-10-16 03:44:50,570][05219] Updated weights for policy 1, policy_version 24620 (0.0009) -[2023-10-16 03:44:50,933][05219] Updated weights for policy 1, policy_version 24630 (0.0010) -[2023-10-16 03:44:51,291][05219] Updated weights for policy 1, policy_version 24640 (0.0009) -[2023-10-16 03:44:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 50528256. Throughput: 0: 1810.2, 1: 1791.7. Samples: 12645074. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-16 03:44:52,351][03835] Avg episode reward: [(0, '5.760'), (1, '5.070')] -[2023-10-16 03:44:52,409][05218] Updated weights for policy 0, policy_version 24712 (0.0010) -[2023-10-16 03:44:52,795][05218] Updated weights for policy 0, policy_version 24722 (0.0007) -[2023-10-16 03:44:53,158][05218] Updated weights for policy 0, policy_version 24732 (0.0007) -[2023-10-16 03:44:55,066][05219] Updated weights for policy 1, policy_version 24650 (0.0009) -[2023-10-16 03:44:55,439][05219] Updated weights for policy 1, policy_version 24660 (0.0007) -[2023-10-16 03:44:55,795][05219] Updated weights for policy 1, policy_version 24670 (0.0007) -[2023-10-16 03:44:57,132][05218] Updated weights for policy 0, policy_version 24742 (0.0010) -[2023-10-16 03:44:57,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 50593792. Throughput: 0: 1796.5, 1: 1807.7. Samples: 12656002. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-16 03:44:57,351][03835] Avg episode reward: [(0, '6.200'), (1, '5.980')] -[2023-10-16 03:44:57,509][05218] Updated weights for policy 0, policy_version 24752 (0.0007) -[2023-10-16 03:44:57,883][05218] Updated weights for policy 0, policy_version 24762 (0.0008) -[2023-10-16 03:44:59,520][05219] Updated weights for policy 1, policy_version 24680 (0.0008) -[2023-10-16 03:44:59,893][05219] Updated weights for policy 1, policy_version 24690 (0.0007) -[2023-10-16 03:45:00,253][05219] Updated weights for policy 1, policy_version 24700 (0.0007) -[2023-10-16 03:45:01,518][05218] Updated weights for policy 0, policy_version 24772 (0.0009) -[2023-10-16 03:45:01,890][05218] Updated weights for policy 0, policy_version 24782 (0.0009) -[2023-10-16 03:45:02,259][05218] Updated weights for policy 0, policy_version 24792 (0.0007) -[2023-10-16 03:45:02,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 50659328. Throughput: 0: 1810.1, 1: 1799.3. Samples: 12677578. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-16 03:45:02,351][03835] Avg episode reward: [(0, '5.820'), (1, '5.310')] -[2023-10-16 03:45:04,042][05219] Updated weights for policy 1, policy_version 24710 (0.0008) -[2023-10-16 03:45:04,408][05219] Updated weights for policy 1, policy_version 24720 (0.0008) -[2023-10-16 03:45:04,775][05219] Updated weights for policy 1, policy_version 24730 (0.0008) -[2023-10-16 03:45:05,987][05218] Updated weights for policy 0, policy_version 24802 (0.0010) -[2023-10-16 03:45:06,349][05218] Updated weights for policy 0, policy_version 24812 (0.0009) -[2023-10-16 03:45:06,732][05218] Updated weights for policy 0, policy_version 24822 (0.0008) -[2023-10-16 03:45:07,103][05218] Updated weights for policy 0, policy_version 24832 (0.0009) -[2023-10-16 03:45:07,351][03835] Fps is (10 sec: 16383.4, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 50757632. Throughput: 0: 1800.7, 1: 1797.4. Samples: 12698528. Policy #0 lag: (min: 7.0, avg: 11.4, max: 39.0) -[2023-10-16 03:45:07,352][03835] Avg episode reward: [(0, '5.940'), (1, '5.500')] -[2023-10-16 03:45:08,533][05219] Updated weights for policy 1, policy_version 24740 (0.0008) -[2023-10-16 03:45:08,900][05219] Updated weights for policy 1, policy_version 24750 (0.0008) -[2023-10-16 03:45:09,258][05219] Updated weights for policy 1, policy_version 24760 (0.0008) -[2023-10-16 03:45:10,919][05218] Updated weights for policy 0, policy_version 24842 (0.0009) -[2023-10-16 03:45:11,292][05218] Updated weights for policy 0, policy_version 24852 (0.0008) -[2023-10-16 03:45:11,668][05218] Updated weights for policy 0, policy_version 24862 (0.0009) -[2023-10-16 03:45:12,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 50823168. Throughput: 0: 1803.4, 1: 1797.0. Samples: 12709810. Policy #0 lag: (min: 7.0, avg: 11.4, max: 39.0) -[2023-10-16 03:45:12,351][03835] Avg episode reward: [(0, '5.490'), (1, '5.330')] -[2023-10-16 03:45:12,988][05219] Updated weights for policy 1, policy_version 24770 (0.0007) -[2023-10-16 03:45:13,356][05219] Updated weights for policy 1, policy_version 24780 (0.0009) -[2023-10-16 03:45:13,726][05219] Updated weights for policy 1, policy_version 24790 (0.0009) -[2023-10-16 03:45:14,088][05219] Updated weights for policy 1, policy_version 24800 (0.0008) -[2023-10-16 03:45:15,383][05218] Updated weights for policy 0, policy_version 24872 (0.0008) -[2023-10-16 03:45:15,768][05218] Updated weights for policy 0, policy_version 24882 (0.0009) -[2023-10-16 03:45:16,137][05218] Updated weights for policy 0, policy_version 24892 (0.0010) -[2023-10-16 03:45:17,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 50888704. Throughput: 0: 1794.8, 1: 1792.9. Samples: 12730730. Policy #0 lag: (min: 7.0, avg: 11.4, max: 39.0) -[2023-10-16 03:45:17,351][03835] Avg episode reward: [(0, '5.820'), (1, '4.860')] -[2023-10-16 03:45:17,867][05219] Updated weights for policy 1, policy_version 24810 (0.0009) -[2023-10-16 03:45:18,227][05219] Updated weights for policy 1, policy_version 24820 (0.0007) -[2023-10-16 03:45:18,588][05219] Updated weights for policy 1, policy_version 24830 (0.0007) -[2023-10-16 03:45:19,777][05218] Updated weights for policy 0, policy_version 24902 (0.0010) -[2023-10-16 03:45:20,155][05218] Updated weights for policy 0, policy_version 24912 (0.0007) -[2023-10-16 03:45:20,535][05218] Updated weights for policy 0, policy_version 24922 (0.0008) -[2023-10-16 03:45:22,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 50954240. Throughput: 0: 1791.3, 1: 1806.0. Samples: 12753338. Policy #0 lag: (min: 29.0, avg: 29.2, max: 40.0) -[2023-10-16 03:45:22,351][03835] Avg episode reward: [(0, '5.930'), (1, '5.880')] -[2023-10-16 03:45:22,353][05219] Updated weights for policy 1, policy_version 24840 (0.0010) -[2023-10-16 03:45:22,721][05219] Updated weights for policy 1, policy_version 24850 (0.0007) -[2023-10-16 03:45:23,088][05219] Updated weights for policy 1, policy_version 24860 (0.0007) -[2023-10-16 03:45:24,281][05218] Updated weights for policy 0, policy_version 24932 (0.0009) -[2023-10-16 03:45:24,645][05218] Updated weights for policy 0, policy_version 24942 (0.0009) -[2023-10-16 03:45:25,022][05218] Updated weights for policy 0, policy_version 24952 (0.0009) -[2023-10-16 03:45:26,992][05219] Updated weights for policy 1, policy_version 24870 (0.0008) -[2023-10-16 03:45:27,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 51019776. Throughput: 0: 1794.0, 1: 1795.6. Samples: 12763344. Policy #0 lag: (min: 29.0, avg: 29.2, max: 40.0) -[2023-10-16 03:45:27,351][03835] Avg episode reward: [(0, '6.020'), (1, '4.930')] -[2023-10-16 03:45:27,355][05219] Updated weights for policy 1, policy_version 24880 (0.0008) -[2023-10-16 03:45:27,713][05219] Updated weights for policy 1, policy_version 24890 (0.0010) -[2023-10-16 03:45:28,731][05218] Updated weights for policy 0, policy_version 24962 (0.0010) -[2023-10-16 03:45:29,102][05218] Updated weights for policy 0, policy_version 24972 (0.0009) -[2023-10-16 03:45:29,484][05218] Updated weights for policy 0, policy_version 24982 (0.0009) -[2023-10-16 03:45:29,867][05218] Updated weights for policy 0, policy_version 24992 (0.0009) -[2023-10-16 03:45:31,525][05219] Updated weights for policy 1, policy_version 24900 (0.0008) -[2023-10-16 03:45:31,881][05219] Updated weights for policy 1, policy_version 24910 (0.0008) -[2023-10-16 03:45:32,250][05219] Updated weights for policy 1, policy_version 24920 (0.0009) -[2023-10-16 03:45:32,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 51085312. Throughput: 0: 1791.1, 1: 1812.0. Samples: 12785746. Policy #0 lag: (min: 29.0, avg: 29.2, max: 40.0) -[2023-10-16 03:45:32,351][03835] Avg episode reward: [(0, '5.710'), (1, '5.580')] -[2023-10-16 03:45:33,614][05218] Updated weights for policy 0, policy_version 25002 (0.0008) -[2023-10-16 03:45:33,994][05218] Updated weights for policy 0, policy_version 25012 (0.0009) -[2023-10-16 03:45:34,359][05218] Updated weights for policy 0, policy_version 25022 (0.0008) -[2023-10-16 03:45:36,017][05219] Updated weights for policy 1, policy_version 24930 (0.0009) -[2023-10-16 03:45:36,374][05219] Updated weights for policy 1, policy_version 24940 (0.0011) -[2023-10-16 03:45:36,730][05219] Updated weights for policy 1, policy_version 24950 (0.0010) -[2023-10-16 03:45:37,095][05219] Updated weights for policy 1, policy_version 24960 (0.0009) -[2023-10-16 03:45:37,351][03835] Fps is (10 sec: 16383.4, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 51183616. Throughput: 0: 1794.6, 1: 1802.1. Samples: 12806924. Policy #0 lag: (min: 29.0, avg: 29.2, max: 40.0) -[2023-10-16 03:45:37,352][03835] Avg episode reward: [(0, '5.300'), (1, '5.760')] -[2023-10-16 03:45:37,366][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000025024_25624576.pth... -[2023-10-16 03:45:37,366][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000024960_25559040.pth... -[2023-10-16 03:45:37,402][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000023264_23822336.pth -[2023-10-16 03:45:37,402][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000023360_23920640.pth -[2023-10-16 03:45:37,406][04891] Saving a milestone ./train_atari/atari_timepilot_APPO/checkpoint_p1/milestones/checkpoint_000024960_25559040.pth -[2023-10-16 03:45:37,407][04766] Saving a milestone ./train_atari/atari_timepilot_APPO/checkpoint_p0/milestones/checkpoint_000025024_25624576.pth -[2023-10-16 03:45:38,252][05218] Updated weights for policy 0, policy_version 25032 (0.0009) -[2023-10-16 03:45:38,632][05218] Updated weights for policy 0, policy_version 25042 (0.0008) -[2023-10-16 03:45:38,999][05218] Updated weights for policy 0, policy_version 25052 (0.0008) -[2023-10-16 03:45:40,858][05219] Updated weights for policy 1, policy_version 24970 (0.0011) -[2023-10-16 03:45:41,218][05219] Updated weights for policy 1, policy_version 24980 (0.0010) -[2023-10-16 03:45:41,590][05219] Updated weights for policy 1, policy_version 24990 (0.0011) -[2023-10-16 03:45:42,351][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 51249152. Throughput: 0: 1789.9, 1: 1807.6. Samples: 12817892. Policy #0 lag: (min: 1.0, avg: 2.3, max: 21.0) -[2023-10-16 03:45:42,352][03835] Avg episode reward: [(0, '5.380'), (1, '5.370')] -[2023-10-16 03:45:42,740][05218] Updated weights for policy 0, policy_version 25062 (0.0008) -[2023-10-16 03:45:43,124][05218] Updated weights for policy 0, policy_version 25072 (0.0007) -[2023-10-16 03:45:43,497][05218] Updated weights for policy 0, policy_version 25082 (0.0008) -[2023-10-16 03:45:45,346][05219] Updated weights for policy 1, policy_version 25000 (0.0007) -[2023-10-16 03:45:45,710][05219] Updated weights for policy 1, policy_version 25010 (0.0008) -[2023-10-16 03:45:46,076][05219] Updated weights for policy 1, policy_version 25020 (0.0008) -[2023-10-16 03:45:47,246][05218] Updated weights for policy 0, policy_version 25092 (0.0008) -[2023-10-16 03:45:47,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 51314688. Throughput: 0: 1789.0, 1: 1796.4. Samples: 12838920. Policy #0 lag: (min: 1.0, avg: 2.3, max: 21.0) -[2023-10-16 03:45:47,351][03835] Avg episode reward: [(0, '5.130'), (1, '5.800')] -[2023-10-16 03:45:47,616][05218] Updated weights for policy 0, policy_version 25102 (0.0009) -[2023-10-16 03:45:47,997][05218] Updated weights for policy 0, policy_version 25112 (0.0007) -[2023-10-16 03:45:49,615][05219] Updated weights for policy 1, policy_version 25030 (0.0008) -[2023-10-16 03:45:49,974][05219] Updated weights for policy 1, policy_version 25040 (0.0010) -[2023-10-16 03:45:50,345][05219] Updated weights for policy 1, policy_version 25050 (0.0008) -[2023-10-16 03:45:51,765][05218] Updated weights for policy 0, policy_version 25122 (0.0008) -[2023-10-16 03:45:52,139][05218] Updated weights for policy 0, policy_version 25132 (0.0008) -[2023-10-16 03:45:52,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 51380224. Throughput: 0: 1802.3, 1: 1790.4. Samples: 12860198. Policy #0 lag: (min: 1.0, avg: 2.3, max: 21.0) -[2023-10-16 03:45:52,351][03835] Avg episode reward: [(0, '4.810'), (1, '5.220')] -[2023-10-16 03:45:52,517][05218] Updated weights for policy 0, policy_version 25142 (0.0008) -[2023-10-16 03:45:52,896][05218] Updated weights for policy 0, policy_version 25152 (0.0007) -[2023-10-16 03:45:53,966][05219] Updated weights for policy 1, policy_version 25060 (0.0009) -[2023-10-16 03:45:54,329][05219] Updated weights for policy 1, policy_version 25070 (0.0009) -[2023-10-16 03:45:54,700][05219] Updated weights for policy 1, policy_version 25080 (0.0010) -[2023-10-16 03:45:56,638][05218] Updated weights for policy 0, policy_version 25162 (0.0011) -[2023-10-16 03:45:57,008][05218] Updated weights for policy 0, policy_version 25172 (0.0011) -[2023-10-16 03:45:57,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 51445760. Throughput: 0: 1787.6, 1: 1790.6. Samples: 12870826. Policy #0 lag: (min: 1.0, avg: 2.3, max: 21.0) -[2023-10-16 03:45:57,351][03835] Avg episode reward: [(0, '5.140'), (1, '5.470')] -[2023-10-16 03:45:57,385][05218] Updated weights for policy 0, policy_version 25182 (0.0008) -[2023-10-16 03:45:58,439][05219] Updated weights for policy 1, policy_version 25090 (0.0011) -[2023-10-16 03:45:58,811][05219] Updated weights for policy 1, policy_version 25100 (0.0008) -[2023-10-16 03:45:59,175][05219] Updated weights for policy 1, policy_version 25110 (0.0008) -[2023-10-16 03:45:59,542][05219] Updated weights for policy 1, policy_version 25120 (0.0009) -[2023-10-16 03:46:01,198][05218] Updated weights for policy 0, policy_version 25192 (0.0010) -[2023-10-16 03:46:01,571][05218] Updated weights for policy 0, policy_version 25202 (0.0010) -[2023-10-16 03:46:01,946][05218] Updated weights for policy 0, policy_version 25212 (0.0009) -[2023-10-16 03:46:02,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 51544064. Throughput: 0: 1802.5, 1: 1791.2. Samples: 12892444. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:46:02,351][03835] Avg episode reward: [(0, '5.040'), (1, '5.520')] -[2023-10-16 03:46:03,376][05219] Updated weights for policy 1, policy_version 25130 (0.0008) -[2023-10-16 03:46:03,739][05219] Updated weights for policy 1, policy_version 25140 (0.0009) -[2023-10-16 03:46:04,095][05219] Updated weights for policy 1, policy_version 25150 (0.0007) -[2023-10-16 03:46:05,640][05218] Updated weights for policy 0, policy_version 25222 (0.0009) -[2023-10-16 03:46:06,017][05218] Updated weights for policy 0, policy_version 25232 (0.0008) -[2023-10-16 03:46:06,399][05218] Updated weights for policy 0, policy_version 25242 (0.0011) -[2023-10-16 03:46:07,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 51609600. Throughput: 0: 1774.8, 1: 1793.9. Samples: 12913928. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:46:07,352][03835] Avg episode reward: [(0, '4.960'), (1, '5.170')] -[2023-10-16 03:46:07,979][05219] Updated weights for policy 1, policy_version 25160 (0.0008) -[2023-10-16 03:46:08,346][05219] Updated weights for policy 1, policy_version 25170 (0.0008) -[2023-10-16 03:46:08,721][05219] Updated weights for policy 1, policy_version 25180 (0.0007) -[2023-10-16 03:46:10,200][05218] Updated weights for policy 0, policy_version 25252 (0.0009) -[2023-10-16 03:46:10,583][05218] Updated weights for policy 0, policy_version 25262 (0.0007) -[2023-10-16 03:46:10,955][05218] Updated weights for policy 0, policy_version 25272 (0.0008) -[2023-10-16 03:46:12,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 51675136. Throughput: 0: 1799.1, 1: 1785.8. Samples: 12924666. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:46:12,351][03835] Avg episode reward: [(0, '5.820'), (1, '5.540')] -[2023-10-16 03:46:12,461][05219] Updated weights for policy 1, policy_version 25190 (0.0010) -[2023-10-16 03:46:12,821][05219] Updated weights for policy 1, policy_version 25200 (0.0010) -[2023-10-16 03:46:13,187][05219] Updated weights for policy 1, policy_version 25210 (0.0011) -[2023-10-16 03:46:14,784][05218] Updated weights for policy 0, policy_version 25282 (0.0010) -[2023-10-16 03:46:15,152][05218] Updated weights for policy 0, policy_version 25292 (0.0010) -[2023-10-16 03:46:15,531][05218] Updated weights for policy 0, policy_version 25302 (0.0011) -[2023-10-16 03:46:15,896][05218] Updated weights for policy 0, policy_version 25312 (0.0009) -[2023-10-16 03:46:17,007][05219] Updated weights for policy 1, policy_version 25220 (0.0011) -[2023-10-16 03:46:17,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 51740672. Throughput: 0: 1776.0, 1: 1787.9. Samples: 12946120. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-16 03:46:17,351][03835] Avg episode reward: [(0, '6.160'), (1, '5.840')] -[2023-10-16 03:46:17,380][05219] Updated weights for policy 1, policy_version 25230 (0.0007) -[2023-10-16 03:46:17,757][05219] Updated weights for policy 1, policy_version 25240 (0.0009) -[2023-10-16 03:46:19,664][05218] Updated weights for policy 0, policy_version 25322 (0.0007) -[2023-10-16 03:46:20,043][05218] Updated weights for policy 0, policy_version 25332 (0.0008) -[2023-10-16 03:46:20,413][05218] Updated weights for policy 0, policy_version 25342 (0.0010) -[2023-10-16 03:46:21,525][05219] Updated weights for policy 1, policy_version 25250 (0.0009) -[2023-10-16 03:46:21,905][05219] Updated weights for policy 1, policy_version 25260 (0.0008) -[2023-10-16 03:46:22,267][05219] Updated weights for policy 1, policy_version 25270 (0.0010) -[2023-10-16 03:46:22,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 51806208. Throughput: 0: 1775.1, 1: 1801.3. Samples: 12967860. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-16 03:46:22,351][03835] Avg episode reward: [(0, '5.690'), (1, '5.280')] -[2023-10-16 03:46:22,636][05219] Updated weights for policy 1, policy_version 25280 (0.0010) -[2023-10-16 03:46:24,233][05218] Updated weights for policy 0, policy_version 25352 (0.0008) -[2023-10-16 03:46:24,600][05218] Updated weights for policy 0, policy_version 25362 (0.0009) -[2023-10-16 03:46:24,973][05218] Updated weights for policy 0, policy_version 25372 (0.0007) -[2023-10-16 03:46:26,599][05219] Updated weights for policy 1, policy_version 25290 (0.0011) -[2023-10-16 03:46:26,958][05219] Updated weights for policy 1, policy_version 25300 (0.0009) -[2023-10-16 03:46:27,331][05219] Updated weights for policy 1, policy_version 25310 (0.0007) -[2023-10-16 03:46:27,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 51871744. Throughput: 0: 1775.5, 1: 1787.2. Samples: 12978212. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-16 03:46:27,351][03835] Avg episode reward: [(0, '6.170'), (1, '5.910')] -[2023-10-16 03:46:28,704][05218] Updated weights for policy 0, policy_version 25382 (0.0010) -[2023-10-16 03:46:29,079][05218] Updated weights for policy 0, policy_version 25392 (0.0010) -[2023-10-16 03:46:29,454][05218] Updated weights for policy 0, policy_version 25402 (0.0010) -[2023-10-16 03:46:31,071][05219] Updated weights for policy 1, policy_version 25320 (0.0010) -[2023-10-16 03:46:31,442][05219] Updated weights for policy 1, policy_version 25330 (0.0010) -[2023-10-16 03:46:31,809][05219] Updated weights for policy 1, policy_version 25340 (0.0010) -[2023-10-16 03:46:32,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 51970048. Throughput: 0: 1780.8, 1: 1801.2. Samples: 13000108. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-16 03:46:32,351][03835] Avg episode reward: [(0, '5.280'), (1, '5.450')] -[2023-10-16 03:46:32,948][05218] Updated weights for policy 0, policy_version 25412 (0.0008) -[2023-10-16 03:46:33,331][05218] Updated weights for policy 0, policy_version 25422 (0.0009) -[2023-10-16 03:46:33,709][05218] Updated weights for policy 0, policy_version 25432 (0.0010) -[2023-10-16 03:46:35,551][05219] Updated weights for policy 1, policy_version 25350 (0.0009) -[2023-10-16 03:46:35,913][05219] Updated weights for policy 1, policy_version 25360 (0.0007) -[2023-10-16 03:46:36,280][05219] Updated weights for policy 1, policy_version 25370 (0.0007) -[2023-10-16 03:46:37,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 52035584. Throughput: 0: 1806.7, 1: 1776.7. Samples: 13021454. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-16 03:46:37,352][03835] Avg episode reward: [(0, '5.680'), (1, '5.440')] -[2023-10-16 03:46:37,538][05218] Updated weights for policy 0, policy_version 25442 (0.0009) -[2023-10-16 03:46:37,912][05218] Updated weights for policy 0, policy_version 25452 (0.0008) -[2023-10-16 03:46:38,290][05218] Updated weights for policy 0, policy_version 25462 (0.0009) -[2023-10-16 03:46:38,665][05218] Updated weights for policy 0, policy_version 25472 (0.0008) -[2023-10-16 03:46:39,885][05219] Updated weights for policy 1, policy_version 25380 (0.0010) -[2023-10-16 03:46:40,259][05219] Updated weights for policy 1, policy_version 25390 (0.0009) -[2023-10-16 03:46:40,629][05219] Updated weights for policy 1, policy_version 25400 (0.0009) -[2023-10-16 03:46:42,331][05218] Updated weights for policy 0, policy_version 25482 (0.0008) -[2023-10-16 03:46:42,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.6, 300 sec: 14329.1). Total num frames: 52101120. Throughput: 0: 1786.4, 1: 1803.0. Samples: 13032352. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-16 03:46:42,351][03835] Avg episode reward: [(0, '5.420'), (1, '5.390')] -[2023-10-16 03:46:42,702][05218] Updated weights for policy 0, policy_version 25492 (0.0008) -[2023-10-16 03:46:43,076][05218] Updated weights for policy 0, policy_version 25502 (0.0009) -[2023-10-16 03:46:44,315][05219] Updated weights for policy 1, policy_version 25410 (0.0011) -[2023-10-16 03:46:44,684][05219] Updated weights for policy 1, policy_version 25420 (0.0008) -[2023-10-16 03:46:45,049][05219] Updated weights for policy 1, policy_version 25430 (0.0008) -[2023-10-16 03:46:45,401][05219] Updated weights for policy 1, policy_version 25440 (0.0009) -[2023-10-16 03:46:46,762][05218] Updated weights for policy 0, policy_version 25512 (0.0008) -[2023-10-16 03:46:47,145][05218] Updated weights for policy 0, policy_version 25522 (0.0008) -[2023-10-16 03:46:47,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 52166656. Throughput: 0: 1809.2, 1: 1779.8. Samples: 13053950. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-16 03:46:47,351][03835] Avg episode reward: [(0, '5.330'), (1, '5.210')] -[2023-10-16 03:46:47,516][05218] Updated weights for policy 0, policy_version 25532 (0.0008) -[2023-10-16 03:46:49,199][05219] Updated weights for policy 1, policy_version 25450 (0.0008) -[2023-10-16 03:46:49,562][05219] Updated weights for policy 1, policy_version 25460 (0.0007) -[2023-10-16 03:46:49,943][05219] Updated weights for policy 1, policy_version 25470 (0.0008) -[2023-10-16 03:46:51,217][05218] Updated weights for policy 0, policy_version 25542 (0.0009) -[2023-10-16 03:46:51,596][05218] Updated weights for policy 0, policy_version 25552 (0.0009) -[2023-10-16 03:46:51,983][05218] Updated weights for policy 0, policy_version 25562 (0.0008) -[2023-10-16 03:46:52,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 52264960. Throughput: 0: 1800.1, 1: 1775.9. Samples: 13074846. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-16 03:46:52,351][03835] Avg episode reward: [(0, '6.070'), (1, '5.840')] -[2023-10-16 03:46:53,835][05219] Updated weights for policy 1, policy_version 25480 (0.0009) -[2023-10-16 03:46:54,214][05219] Updated weights for policy 1, policy_version 25490 (0.0009) -[2023-10-16 03:46:54,577][05219] Updated weights for policy 1, policy_version 25500 (0.0008) -[2023-10-16 03:46:55,669][05218] Updated weights for policy 0, policy_version 25572 (0.0010) -[2023-10-16 03:46:56,047][05218] Updated weights for policy 0, policy_version 25582 (0.0008) -[2023-10-16 03:46:56,423][05218] Updated weights for policy 0, policy_version 25592 (0.0008) -[2023-10-16 03:46:57,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 52330496. Throughput: 0: 1810.1, 1: 1778.6. Samples: 13086160. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-16 03:46:57,351][03835] Avg episode reward: [(0, '5.290'), (1, '5.160')] -[2023-10-16 03:46:58,367][05219] Updated weights for policy 1, policy_version 25510 (0.0009) -[2023-10-16 03:46:58,730][05219] Updated weights for policy 1, policy_version 25520 (0.0008) -[2023-10-16 03:46:59,096][05219] Updated weights for policy 1, policy_version 25530 (0.0008) -[2023-10-16 03:47:00,061][05218] Updated weights for policy 0, policy_version 25602 (0.0007) -[2023-10-16 03:47:00,442][05218] Updated weights for policy 0, policy_version 25612 (0.0009) -[2023-10-16 03:47:00,821][05218] Updated weights for policy 0, policy_version 25622 (0.0008) -[2023-10-16 03:47:01,194][05218] Updated weights for policy 0, policy_version 25632 (0.0007) -[2023-10-16 03:47:02,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 52396032. Throughput: 0: 1802.8, 1: 1774.3. Samples: 13107092. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-16 03:47:02,351][03835] Avg episode reward: [(0, '6.250'), (1, '5.650')] -[2023-10-16 03:47:03,047][05219] Updated weights for policy 1, policy_version 25540 (0.0009) -[2023-10-16 03:47:03,419][05219] Updated weights for policy 1, policy_version 25550 (0.0008) -[2023-10-16 03:47:03,773][05219] Updated weights for policy 1, policy_version 25560 (0.0008) -[2023-10-16 03:47:04,830][05218] Updated weights for policy 0, policy_version 25642 (0.0009) -[2023-10-16 03:47:05,220][05218] Updated weights for policy 0, policy_version 25652 (0.0008) -[2023-10-16 03:47:05,598][05218] Updated weights for policy 0, policy_version 25662 (0.0009) -[2023-10-16 03:47:07,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 52461568. Throughput: 0: 1802.9, 1: 1786.2. Samples: 13129370. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-16 03:47:07,351][03835] Avg episode reward: [(0, '6.100'), (1, '5.960')] -[2023-10-16 03:47:07,596][05219] Updated weights for policy 1, policy_version 25570 (0.0008) -[2023-10-16 03:47:07,963][05219] Updated weights for policy 1, policy_version 25580 (0.0008) -[2023-10-16 03:47:08,318][05219] Updated weights for policy 1, policy_version 25590 (0.0008) -[2023-10-16 03:47:08,686][05219] Updated weights for policy 1, policy_version 25600 (0.0009) -[2023-10-16 03:47:09,263][05218] Updated weights for policy 0, policy_version 25672 (0.0009) -[2023-10-16 03:47:09,644][05218] Updated weights for policy 0, policy_version 25682 (0.0010) -[2023-10-16 03:47:10,023][05218] Updated weights for policy 0, policy_version 25692 (0.0010) -[2023-10-16 03:47:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 52527104. Throughput: 0: 1806.0, 1: 1772.7. Samples: 13139254. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-16 03:47:12,351][03835] Avg episode reward: [(0, '5.590'), (1, '5.620')] -[2023-10-16 03:47:12,465][05219] Updated weights for policy 1, policy_version 25610 (0.0009) -[2023-10-16 03:47:12,823][05219] Updated weights for policy 1, policy_version 25620 (0.0008) -[2023-10-16 03:47:13,195][05219] Updated weights for policy 1, policy_version 25630 (0.0008) -[2023-10-16 03:47:13,824][05218] Updated weights for policy 0, policy_version 25702 (0.0009) -[2023-10-16 03:47:14,199][05218] Updated weights for policy 0, policy_version 25712 (0.0008) -[2023-10-16 03:47:14,576][05218] Updated weights for policy 0, policy_version 25722 (0.0009) -[2023-10-16 03:47:16,988][05219] Updated weights for policy 1, policy_version 25640 (0.0008) -[2023-10-16 03:47:17,349][05219] Updated weights for policy 1, policy_version 25650 (0.0007) -[2023-10-16 03:47:17,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 52592640. Throughput: 0: 1796.2, 1: 1785.5. Samples: 13161282. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-16 03:47:17,351][03835] Avg episode reward: [(0, '5.960'), (1, '6.120')] -[2023-10-16 03:47:17,718][05219] Updated weights for policy 1, policy_version 25660 (0.0008) -[2023-10-16 03:47:18,447][05218] Updated weights for policy 0, policy_version 25732 (0.0007) -[2023-10-16 03:47:18,834][05218] Updated weights for policy 0, policy_version 25742 (0.0007) -[2023-10-16 03:47:19,208][05218] Updated weights for policy 0, policy_version 25752 (0.0008) -[2023-10-16 03:47:21,601][05219] Updated weights for policy 1, policy_version 25670 (0.0009) -[2023-10-16 03:47:21,974][05219] Updated weights for policy 1, policy_version 25680 (0.0009) -[2023-10-16 03:47:22,326][05219] Updated weights for policy 1, policy_version 25690 (0.0008) -[2023-10-16 03:47:22,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 52658176. Throughput: 0: 1792.8, 1: 1791.3. Samples: 13182736. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-16 03:47:22,351][03835] Avg episode reward: [(0, '5.490'), (1, '5.250')] -[2023-10-16 03:47:22,987][05218] Updated weights for policy 0, policy_version 25762 (0.0007) -[2023-10-16 03:47:23,357][05218] Updated weights for policy 0, policy_version 25772 (0.0008) -[2023-10-16 03:47:23,735][05218] Updated weights for policy 0, policy_version 25782 (0.0009) -[2023-10-16 03:47:24,097][05218] Updated weights for policy 0, policy_version 25792 (0.0009) -[2023-10-16 03:47:25,917][05219] Updated weights for policy 1, policy_version 25700 (0.0009) -[2023-10-16 03:47:26,277][05219] Updated weights for policy 1, policy_version 25710 (0.0010) -[2023-10-16 03:47:26,645][05219] Updated weights for policy 1, policy_version 25720 (0.0009) -[2023-10-16 03:47:27,350][03835] Fps is (10 sec: 16383.4, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 52756480. Throughput: 0: 1792.5, 1: 1788.8. Samples: 13193510. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-16 03:47:27,352][03835] Avg episode reward: [(0, '5.450'), (1, '5.120')] -[2023-10-16 03:47:27,950][05218] Updated weights for policy 0, policy_version 25802 (0.0008) -[2023-10-16 03:47:28,323][05218] Updated weights for policy 0, policy_version 25812 (0.0009) -[2023-10-16 03:47:28,697][05218] Updated weights for policy 0, policy_version 25822 (0.0007) -[2023-10-16 03:47:30,386][05219] Updated weights for policy 1, policy_version 25730 (0.0010) -[2023-10-16 03:47:30,738][05219] Updated weights for policy 1, policy_version 25740 (0.0008) -[2023-10-16 03:47:31,100][05219] Updated weights for policy 1, policy_version 25750 (0.0007) -[2023-10-16 03:47:31,461][05219] Updated weights for policy 1, policy_version 25760 (0.0009) -[2023-10-16 03:47:32,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 52822016. Throughput: 0: 1788.5, 1: 1787.2. Samples: 13214854. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:47:32,351][03835] Avg episode reward: [(0, '5.650'), (1, '6.010')] -[2023-10-16 03:47:32,486][05218] Updated weights for policy 0, policy_version 25832 (0.0007) -[2023-10-16 03:47:32,866][05218] Updated weights for policy 0, policy_version 25842 (0.0008) -[2023-10-16 03:47:33,239][05218] Updated weights for policy 0, policy_version 25852 (0.0009) -[2023-10-16 03:47:35,246][05219] Updated weights for policy 1, policy_version 25770 (0.0008) -[2023-10-16 03:47:35,611][05219] Updated weights for policy 1, policy_version 25780 (0.0010) -[2023-10-16 03:47:35,978][05219] Updated weights for policy 1, policy_version 25790 (0.0010) -[2023-10-16 03:47:36,841][05218] Updated weights for policy 0, policy_version 25862 (0.0009) -[2023-10-16 03:47:37,206][05218] Updated weights for policy 0, policy_version 25872 (0.0009) -[2023-10-16 03:47:37,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 52887552. Throughput: 0: 1799.5, 1: 1777.5. Samples: 13235812. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:47:37,351][03835] Avg episode reward: [(0, '5.480'), (1, '5.060')] -[2023-10-16 03:47:37,361][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000025792_26411008.pth... -[2023-10-16 03:47:37,392][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000024128_24707072.pth -[2023-10-16 03:47:37,579][05218] Updated weights for policy 0, policy_version 25882 (0.0007) -[2023-10-16 03:47:37,804][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000025888_26509312.pth... -[2023-10-16 03:47:37,845][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000024192_24772608.pth -[2023-10-16 03:47:39,795][05219] Updated weights for policy 1, policy_version 25800 (0.0008) -[2023-10-16 03:47:40,167][05219] Updated weights for policy 1, policy_version 25810 (0.0009) -[2023-10-16 03:47:40,525][05219] Updated weights for policy 1, policy_version 25820 (0.0007) -[2023-10-16 03:47:41,371][05218] Updated weights for policy 0, policy_version 25892 (0.0007) -[2023-10-16 03:47:41,752][05218] Updated weights for policy 0, policy_version 25902 (0.0009) -[2023-10-16 03:47:42,124][05218] Updated weights for policy 0, policy_version 25912 (0.0009) -[2023-10-16 03:47:42,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 52953088. Throughput: 0: 1783.0, 1: 1793.8. Samples: 13247114. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:47:42,351][03835] Avg episode reward: [(0, '5.370'), (1, '5.440')] -[2023-10-16 03:47:44,068][05219] Updated weights for policy 1, policy_version 25830 (0.0007) -[2023-10-16 03:47:44,445][05219] Updated weights for policy 1, policy_version 25840 (0.0007) -[2023-10-16 03:47:44,816][05219] Updated weights for policy 1, policy_version 25850 (0.0009) -[2023-10-16 03:47:45,838][05218] Updated weights for policy 0, policy_version 25922 (0.0009) -[2023-10-16 03:47:46,218][05218] Updated weights for policy 0, policy_version 25932 (0.0008) -[2023-10-16 03:47:46,583][05218] Updated weights for policy 0, policy_version 25942 (0.0007) -[2023-10-16 03:47:46,964][05218] Updated weights for policy 0, policy_version 25952 (0.0008) -[2023-10-16 03:47:47,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 53051392. Throughput: 0: 1798.7, 1: 1781.3. Samples: 13268194. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:47:47,351][03835] Avg episode reward: [(0, '5.700'), (1, '4.710')] -[2023-10-16 03:47:48,615][05219] Updated weights for policy 1, policy_version 25860 (0.0008) -[2023-10-16 03:47:48,979][05219] Updated weights for policy 1, policy_version 25870 (0.0010) -[2023-10-16 03:47:49,345][05219] Updated weights for policy 1, policy_version 25880 (0.0011) -[2023-10-16 03:47:50,762][05218] Updated weights for policy 0, policy_version 25962 (0.0010) -[2023-10-16 03:47:51,134][05218] Updated weights for policy 0, policy_version 25972 (0.0007) -[2023-10-16 03:47:51,507][05218] Updated weights for policy 0, policy_version 25982 (0.0010) -[2023-10-16 03:47:52,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 53116928. Throughput: 0: 1775.0, 1: 1788.4. Samples: 13289720. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:47:52,351][03835] Avg episode reward: [(0, '5.640'), (1, '5.240')] -[2023-10-16 03:47:53,056][05219] Updated weights for policy 1, policy_version 25890 (0.0007) -[2023-10-16 03:47:53,418][05219] Updated weights for policy 1, policy_version 25900 (0.0008) -[2023-10-16 03:47:53,785][05219] Updated weights for policy 1, policy_version 25910 (0.0008) -[2023-10-16 03:47:54,142][05219] Updated weights for policy 1, policy_version 25920 (0.0007) -[2023-10-16 03:47:55,364][05218] Updated weights for policy 0, policy_version 25992 (0.0008) -[2023-10-16 03:47:55,735][05218] Updated weights for policy 0, policy_version 26002 (0.0008) -[2023-10-16 03:47:56,104][05218] Updated weights for policy 0, policy_version 26012 (0.0008) -[2023-10-16 03:47:57,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 53182464. Throughput: 0: 1798.2, 1: 1787.6. Samples: 13300612. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:47:57,351][03835] Avg episode reward: [(0, '5.160'), (1, '5.000')] -[2023-10-16 03:47:57,998][05219] Updated weights for policy 1, policy_version 25930 (0.0009) -[2023-10-16 03:47:58,359][05219] Updated weights for policy 1, policy_version 25940 (0.0009) -[2023-10-16 03:47:58,727][05219] Updated weights for policy 1, policy_version 25950 (0.0008) -[2023-10-16 03:47:59,869][05218] Updated weights for policy 0, policy_version 26022 (0.0009) -[2023-10-16 03:48:00,249][05218] Updated weights for policy 0, policy_version 26032 (0.0010) -[2023-10-16 03:48:00,626][05218] Updated weights for policy 0, policy_version 26042 (0.0010) -[2023-10-16 03:48:02,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 53248000. Throughput: 0: 1776.8, 1: 1785.7. Samples: 13321596. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:48:02,351][03835] Avg episode reward: [(0, '5.290'), (1, '5.050')] -[2023-10-16 03:48:02,581][05219] Updated weights for policy 1, policy_version 25960 (0.0007) -[2023-10-16 03:48:02,943][05219] Updated weights for policy 1, policy_version 25970 (0.0007) -[2023-10-16 03:48:03,310][05219] Updated weights for policy 1, policy_version 25980 (0.0008) -[2023-10-16 03:48:04,483][05218] Updated weights for policy 0, policy_version 26052 (0.0010) -[2023-10-16 03:48:04,866][05218] Updated weights for policy 0, policy_version 26062 (0.0008) -[2023-10-16 03:48:05,248][05218] Updated weights for policy 0, policy_version 26072 (0.0008) -[2023-10-16 03:48:07,128][05219] Updated weights for policy 1, policy_version 25990 (0.0008) -[2023-10-16 03:48:07,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 53313536. Throughput: 0: 1774.3, 1: 1800.5. Samples: 13343600. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:48:07,351][03835] Avg episode reward: [(0, '5.790'), (1, '4.530')] -[2023-10-16 03:48:07,491][05219] Updated weights for policy 1, policy_version 26000 (0.0007) -[2023-10-16 03:48:07,858][05219] Updated weights for policy 1, policy_version 26010 (0.0008) -[2023-10-16 03:48:08,933][05218] Updated weights for policy 0, policy_version 26082 (0.0008) -[2023-10-16 03:48:09,311][05218] Updated weights for policy 0, policy_version 26092 (0.0007) -[2023-10-16 03:48:09,690][05218] Updated weights for policy 0, policy_version 26102 (0.0008) -[2023-10-16 03:48:10,075][05218] Updated weights for policy 0, policy_version 26112 (0.0008) -[2023-10-16 03:48:11,697][05219] Updated weights for policy 1, policy_version 26020 (0.0010) -[2023-10-16 03:48:12,072][05219] Updated weights for policy 1, policy_version 26030 (0.0010) -[2023-10-16 03:48:12,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 53379072. Throughput: 0: 1777.3, 1: 1785.7. Samples: 13353840. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:48:12,351][03835] Avg episode reward: [(0, '5.890'), (1, '4.460')] -[2023-10-16 03:48:12,453][05219] Updated weights for policy 1, policy_version 26040 (0.0009) -[2023-10-16 03:48:13,940][05218] Updated weights for policy 0, policy_version 26122 (0.0011) -[2023-10-16 03:48:14,317][05218] Updated weights for policy 0, policy_version 26132 (0.0008) -[2023-10-16 03:48:14,706][05218] Updated weights for policy 0, policy_version 26142 (0.0009) -[2023-10-16 03:48:16,312][05219] Updated weights for policy 1, policy_version 26050 (0.0008) -[2023-10-16 03:48:16,678][05219] Updated weights for policy 1, policy_version 26060 (0.0007) -[2023-10-16 03:48:17,048][05219] Updated weights for policy 1, policy_version 26070 (0.0008) -[2023-10-16 03:48:17,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 53444608. Throughput: 0: 1769.1, 1: 1806.0. Samples: 13375736. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:48:17,351][03835] Avg episode reward: [(0, '5.430'), (1, '4.480')] -[2023-10-16 03:48:17,417][05219] Updated weights for policy 1, policy_version 26080 (0.0008) -[2023-10-16 03:48:18,507][05218] Updated weights for policy 0, policy_version 26152 (0.0008) -[2023-10-16 03:48:18,878][05218] Updated weights for policy 0, policy_version 26162 (0.0010) -[2023-10-16 03:48:19,257][05218] Updated weights for policy 0, policy_version 26172 (0.0010) -[2023-10-16 03:48:21,270][05219] Updated weights for policy 1, policy_version 26090 (0.0008) -[2023-10-16 03:48:21,637][05219] Updated weights for policy 1, policy_version 26100 (0.0008) -[2023-10-16 03:48:22,003][05219] Updated weights for policy 1, policy_version 26110 (0.0007) -[2023-10-16 03:48:22,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 53542912. Throughput: 0: 1792.0, 1: 1782.9. Samples: 13396682. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:48:22,351][03835] Avg episode reward: [(0, '5.730'), (1, '4.900')] -[2023-10-16 03:48:22,941][05218] Updated weights for policy 0, policy_version 26182 (0.0009) -[2023-10-16 03:48:23,322][05218] Updated weights for policy 0, policy_version 26192 (0.0008) -[2023-10-16 03:48:23,698][05218] Updated weights for policy 0, policy_version 26202 (0.0010) -[2023-10-16 03:48:25,754][05219] Updated weights for policy 1, policy_version 26120 (0.0011) -[2023-10-16 03:48:26,126][05219] Updated weights for policy 1, policy_version 26130 (0.0008) -[2023-10-16 03:48:26,500][05219] Updated weights for policy 1, policy_version 26140 (0.0007) -[2023-10-16 03:48:27,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 53608448. Throughput: 0: 1771.2, 1: 1798.6. Samples: 13407752. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:48:27,351][03835] Avg episode reward: [(0, '5.270'), (1, '5.390')] -[2023-10-16 03:48:27,462][05218] Updated weights for policy 0, policy_version 26212 (0.0009) -[2023-10-16 03:48:27,834][05218] Updated weights for policy 0, policy_version 26222 (0.0009) -[2023-10-16 03:48:28,209][05218] Updated weights for policy 0, policy_version 26232 (0.0008) -[2023-10-16 03:48:30,198][05219] Updated weights for policy 1, policy_version 26150 (0.0008) -[2023-10-16 03:48:30,562][05219] Updated weights for policy 1, policy_version 26160 (0.0008) -[2023-10-16 03:48:30,929][05219] Updated weights for policy 1, policy_version 26170 (0.0008) -[2023-10-16 03:48:32,099][05218] Updated weights for policy 0, policy_version 26242 (0.0007) -[2023-10-16 03:48:32,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 53673984. Throughput: 0: 1786.8, 1: 1779.3. Samples: 13428668. Policy #0 lag: (min: 11.0, avg: 16.5, max: 43.0) -[2023-10-16 03:48:32,352][03835] Avg episode reward: [(0, '5.680'), (1, '5.720')] -[2023-10-16 03:48:32,474][05218] Updated weights for policy 0, policy_version 26252 (0.0008) -[2023-10-16 03:48:32,857][05218] Updated weights for policy 0, policy_version 26262 (0.0007) -[2023-10-16 03:48:33,225][05218] Updated weights for policy 0, policy_version 26272 (0.0009) -[2023-10-16 03:48:34,844][05219] Updated weights for policy 1, policy_version 26180 (0.0009) -[2023-10-16 03:48:35,209][05219] Updated weights for policy 1, policy_version 26190 (0.0010) -[2023-10-16 03:48:35,578][05219] Updated weights for policy 1, policy_version 26200 (0.0011) -[2023-10-16 03:48:37,119][05218] Updated weights for policy 0, policy_version 26282 (0.0011) -[2023-10-16 03:48:37,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 53739520. Throughput: 0: 1786.6, 1: 1766.4. Samples: 13449604. Policy #0 lag: (min: 11.0, avg: 16.5, max: 43.0) -[2023-10-16 03:48:37,351][03835] Avg episode reward: [(0, '5.580'), (1, '5.380')] -[2023-10-16 03:48:37,493][05218] Updated weights for policy 0, policy_version 26292 (0.0011) -[2023-10-16 03:48:37,864][05218] Updated weights for policy 0, policy_version 26302 (0.0008) -[2023-10-16 03:48:39,396][05219] Updated weights for policy 1, policy_version 26210 (0.0009) -[2023-10-16 03:48:39,768][05219] Updated weights for policy 1, policy_version 26220 (0.0008) -[2023-10-16 03:48:40,146][05219] Updated weights for policy 1, policy_version 26230 (0.0009) -[2023-10-16 03:48:40,500][05219] Updated weights for policy 1, policy_version 26240 (0.0009) -[2023-10-16 03:48:41,532][05218] Updated weights for policy 0, policy_version 26312 (0.0011) -[2023-10-16 03:48:41,908][05218] Updated weights for policy 0, policy_version 26322 (0.0010) -[2023-10-16 03:48:42,299][05218] Updated weights for policy 0, policy_version 26332 (0.0012) -[2023-10-16 03:48:42,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 53805056. Throughput: 0: 1781.3, 1: 1775.2. Samples: 13460656. Policy #0 lag: (min: 11.0, avg: 16.5, max: 43.0) -[2023-10-16 03:48:42,352][03835] Avg episode reward: [(0, '5.810'), (1, '5.630')] -[2023-10-16 03:48:44,289][05219] Updated weights for policy 1, policy_version 26250 (0.0009) -[2023-10-16 03:48:44,664][05219] Updated weights for policy 1, policy_version 26260 (0.0008) -[2023-10-16 03:48:45,038][05219] Updated weights for policy 1, policy_version 26270 (0.0008) -[2023-10-16 03:48:45,931][05218] Updated weights for policy 0, policy_version 26342 (0.0009) -[2023-10-16 03:48:46,306][05218] Updated weights for policy 0, policy_version 26352 (0.0009) -[2023-10-16 03:48:46,680][05218] Updated weights for policy 0, policy_version 26362 (0.0007) -[2023-10-16 03:48:47,351][03835] Fps is (10 sec: 16383.3, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 53903360. Throughput: 0: 1793.4, 1: 1767.0. Samples: 13481816. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) -[2023-10-16 03:48:47,352][03835] Avg episode reward: [(0, '5.690'), (1, '4.910')] -[2023-10-16 03:48:48,951][05219] Updated weights for policy 1, policy_version 26280 (0.0008) -[2023-10-16 03:48:49,317][05219] Updated weights for policy 1, policy_version 26290 (0.0010) -[2023-10-16 03:48:49,681][05219] Updated weights for policy 1, policy_version 26300 (0.0010) -[2023-10-16 03:48:50,595][05218] Updated weights for policy 0, policy_version 26372 (0.0008) -[2023-10-16 03:48:50,982][05218] Updated weights for policy 0, policy_version 26382 (0.0007) -[2023-10-16 03:48:51,365][05218] Updated weights for policy 0, policy_version 26392 (0.0007) -[2023-10-16 03:48:52,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 53968896. Throughput: 0: 1779.4, 1: 1767.8. Samples: 13503224. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) -[2023-10-16 03:48:52,351][03835] Avg episode reward: [(0, '5.430'), (1, '5.080')] -[2023-10-16 03:48:53,444][05219] Updated weights for policy 1, policy_version 26310 (0.0009) -[2023-10-16 03:48:53,815][05219] Updated weights for policy 1, policy_version 26320 (0.0009) -[2023-10-16 03:48:54,172][05219] Updated weights for policy 1, policy_version 26330 (0.0009) -[2023-10-16 03:48:54,929][05218] Updated weights for policy 0, policy_version 26402 (0.0007) -[2023-10-16 03:48:55,295][05218] Updated weights for policy 0, policy_version 26412 (0.0007) -[2023-10-16 03:48:55,667][05218] Updated weights for policy 0, policy_version 26422 (0.0009) -[2023-10-16 03:48:56,041][05218] Updated weights for policy 0, policy_version 26432 (0.0009) -[2023-10-16 03:48:57,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 54034432. Throughput: 0: 1799.8, 1: 1759.3. Samples: 13514000. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) -[2023-10-16 03:48:57,351][03835] Avg episode reward: [(0, '5.790'), (1, '4.850')] -[2023-10-16 03:48:57,984][05219] Updated weights for policy 1, policy_version 26340 (0.0008) -[2023-10-16 03:48:58,356][05219] Updated weights for policy 1, policy_version 26350 (0.0010) -[2023-10-16 03:48:58,723][05219] Updated weights for policy 1, policy_version 26360 (0.0010) -[2023-10-16 03:48:59,703][05218] Updated weights for policy 0, policy_version 26442 (0.0011) -[2023-10-16 03:49:00,081][05218] Updated weights for policy 0, policy_version 26452 (0.0008) -[2023-10-16 03:49:00,460][05218] Updated weights for policy 0, policy_version 26462 (0.0008) -[2023-10-16 03:49:02,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 54099968. Throughput: 0: 1783.1, 1: 1761.9. Samples: 13535258. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) -[2023-10-16 03:49:02,351][03835] Avg episode reward: [(0, '5.870'), (1, '5.080')] -[2023-10-16 03:49:02,471][05219] Updated weights for policy 1, policy_version 26370 (0.0009) -[2023-10-16 03:49:02,840][05219] Updated weights for policy 1, policy_version 26380 (0.0008) -[2023-10-16 03:49:03,196][05219] Updated weights for policy 1, policy_version 26390 (0.0009) -[2023-10-16 03:49:03,567][05219] Updated weights for policy 1, policy_version 26400 (0.0007) -[2023-10-16 03:49:04,340][05218] Updated weights for policy 0, policy_version 26472 (0.0010) -[2023-10-16 03:49:04,722][05218] Updated weights for policy 0, policy_version 26482 (0.0008) -[2023-10-16 03:49:05,096][05218] Updated weights for policy 0, policy_version 26492 (0.0008) -[2023-10-16 03:49:07,281][05219] Updated weights for policy 1, policy_version 26410 (0.0009) -[2023-10-16 03:49:07,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 54165504. Throughput: 0: 1779.4, 1: 1790.5. Samples: 13557326. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) -[2023-10-16 03:49:07,351][03835] Avg episode reward: [(0, '5.220'), (1, '5.790')] -[2023-10-16 03:49:07,648][05219] Updated weights for policy 1, policy_version 26420 (0.0010) -[2023-10-16 03:49:08,005][05219] Updated weights for policy 1, policy_version 26430 (0.0010) -[2023-10-16 03:49:08,866][05218] Updated weights for policy 0, policy_version 26502 (0.0008) -[2023-10-16 03:49:09,245][05218] Updated weights for policy 0, policy_version 26512 (0.0009) -[2023-10-16 03:49:09,609][05218] Updated weights for policy 0, policy_version 26522 (0.0007) -[2023-10-16 03:49:11,939][05219] Updated weights for policy 1, policy_version 26440 (0.0008) -[2023-10-16 03:49:12,317][05219] Updated weights for policy 1, policy_version 26450 (0.0007) -[2023-10-16 03:49:12,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 54231040. Throughput: 0: 1780.1, 1: 1762.6. Samples: 13567174. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-16 03:49:12,351][03835] Avg episode reward: [(0, '5.230'), (1, '5.540')] -[2023-10-16 03:49:12,690][05219] Updated weights for policy 1, policy_version 26460 (0.0008) -[2023-10-16 03:49:13,327][05218] Updated weights for policy 0, policy_version 26532 (0.0008) -[2023-10-16 03:49:13,705][05218] Updated weights for policy 0, policy_version 26542 (0.0009) -[2023-10-16 03:49:14,087][05218] Updated weights for policy 0, policy_version 26552 (0.0010) -[2023-10-16 03:49:16,242][05219] Updated weights for policy 1, policy_version 26470 (0.0008) -[2023-10-16 03:49:16,600][05219] Updated weights for policy 1, policy_version 26480 (0.0009) -[2023-10-16 03:49:16,966][05219] Updated weights for policy 1, policy_version 26490 (0.0008) -[2023-10-16 03:49:17,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 54329344. Throughput: 0: 1772.9, 1: 1790.9. Samples: 13589042. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-16 03:49:17,351][03835] Avg episode reward: [(0, '5.680'), (1, '5.870')] -[2023-10-16 03:49:17,940][05218] Updated weights for policy 0, policy_version 26562 (0.0008) -[2023-10-16 03:49:18,320][05218] Updated weights for policy 0, policy_version 26572 (0.0007) -[2023-10-16 03:49:18,699][05218] Updated weights for policy 0, policy_version 26582 (0.0008) -[2023-10-16 03:49:19,074][05218] Updated weights for policy 0, policy_version 26592 (0.0008) -[2023-10-16 03:49:20,875][05219] Updated weights for policy 1, policy_version 26500 (0.0010) -[2023-10-16 03:49:21,234][05219] Updated weights for policy 1, policy_version 26510 (0.0007) -[2023-10-16 03:49:21,604][05219] Updated weights for policy 1, policy_version 26520 (0.0008) -[2023-10-16 03:49:22,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 54394880. Throughput: 0: 1800.6, 1: 1769.7. Samples: 13610270. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-16 03:49:22,351][03835] Avg episode reward: [(0, '5.180'), (1, '5.290')] -[2023-10-16 03:49:22,930][05218] Updated weights for policy 0, policy_version 26602 (0.0009) -[2023-10-16 03:49:23,301][05218] Updated weights for policy 0, policy_version 26612 (0.0008) -[2023-10-16 03:49:23,680][05218] Updated weights for policy 0, policy_version 26622 (0.0008) -[2023-10-16 03:49:25,316][05219] Updated weights for policy 1, policy_version 26530 (0.0008) -[2023-10-16 03:49:25,675][05219] Updated weights for policy 1, policy_version 26540 (0.0010) -[2023-10-16 03:49:26,036][05219] Updated weights for policy 1, policy_version 26550 (0.0009) -[2023-10-16 03:49:26,401][05219] Updated weights for policy 1, policy_version 26560 (0.0010) -[2023-10-16 03:49:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 54460416. Throughput: 0: 1778.1, 1: 1795.9. Samples: 13621488. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-16 03:49:27,351][03835] Avg episode reward: [(0, '5.230'), (1, '5.940')] -[2023-10-16 03:49:27,406][05218] Updated weights for policy 0, policy_version 26632 (0.0008) -[2023-10-16 03:49:27,782][05218] Updated weights for policy 0, policy_version 26642 (0.0009) -[2023-10-16 03:49:28,166][05218] Updated weights for policy 0, policy_version 26652 (0.0010) -[2023-10-16 03:49:30,258][05219] Updated weights for policy 1, policy_version 26570 (0.0009) -[2023-10-16 03:49:30,622][05219] Updated weights for policy 1, policy_version 26580 (0.0007) -[2023-10-16 03:49:30,990][05219] Updated weights for policy 1, policy_version 26590 (0.0008) -[2023-10-16 03:49:31,740][05218] Updated weights for policy 0, policy_version 26662 (0.0010) -[2023-10-16 03:49:32,102][05218] Updated weights for policy 0, policy_version 26672 (0.0011) -[2023-10-16 03:49:32,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.6, 300 sec: 14329.1). Total num frames: 54525952. Throughput: 0: 1788.9, 1: 1773.4. Samples: 13642114. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-16 03:49:32,351][03835] Avg episode reward: [(0, '6.270'), (1, '5.380')] -[2023-10-16 03:49:32,473][05218] Updated weights for policy 0, policy_version 26682 (0.0009) -[2023-10-16 03:49:32,701][04766] Saving new best policy, reward=6.270! -[2023-10-16 03:49:34,607][05219] Updated weights for policy 1, policy_version 26600 (0.0007) -[2023-10-16 03:49:34,975][05219] Updated weights for policy 1, policy_version 26610 (0.0007) -[2023-10-16 03:49:35,337][05219] Updated weights for policy 1, policy_version 26620 (0.0007) -[2023-10-16 03:49:36,266][05218] Updated weights for policy 0, policy_version 26692 (0.0010) -[2023-10-16 03:49:36,644][05218] Updated weights for policy 0, policy_version 26702 (0.0007) -[2023-10-16 03:49:37,019][05218] Updated weights for policy 0, policy_version 26712 (0.0009) -[2023-10-16 03:49:37,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 54624256. Throughput: 0: 1771.1, 1: 1787.0. Samples: 13663338. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:49:37,351][03835] Avg episode reward: [(0, '5.560'), (1, '5.580')] -[2023-10-16 03:49:37,359][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000026624_27262976.pth... -[2023-10-16 03:49:37,359][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000026720_27361280.pth... -[2023-10-16 03:49:37,406][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000025024_25624576.pth -[2023-10-16 03:49:37,406][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000024960_25559040.pth -[2023-10-16 03:49:38,908][05219] Updated weights for policy 1, policy_version 26630 (0.0007) -[2023-10-16 03:49:39,270][05219] Updated weights for policy 1, policy_version 26640 (0.0008) -[2023-10-16 03:49:39,642][05219] Updated weights for policy 1, policy_version 26650 (0.0007) -[2023-10-16 03:49:40,839][05218] Updated weights for policy 0, policy_version 26722 (0.0009) -[2023-10-16 03:49:41,206][05218] Updated weights for policy 0, policy_version 26732 (0.0009) -[2023-10-16 03:49:41,583][05218] Updated weights for policy 0, policy_version 26742 (0.0009) -[2023-10-16 03:49:41,955][05218] Updated weights for policy 0, policy_version 26752 (0.0011) -[2023-10-16 03:49:42,350][03835] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 54689792. Throughput: 0: 1783.5, 1: 1787.2. Samples: 13674680. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:49:42,351][03835] Avg episode reward: [(0, '6.160'), (1, '5.820')] -[2023-10-16 03:49:43,288][05219] Updated weights for policy 1, policy_version 26660 (0.0007) -[2023-10-16 03:49:43,656][05219] Updated weights for policy 1, policy_version 26670 (0.0007) -[2023-10-16 03:49:44,020][05219] Updated weights for policy 1, policy_version 26680 (0.0008) -[2023-10-16 03:49:45,667][05218] Updated weights for policy 0, policy_version 26762 (0.0010) -[2023-10-16 03:49:46,054][05218] Updated weights for policy 0, policy_version 26772 (0.0009) -[2023-10-16 03:49:46,422][05218] Updated weights for policy 0, policy_version 26782 (0.0009) -[2023-10-16 03:49:47,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 54755328. Throughput: 0: 1780.7, 1: 1792.8. Samples: 13696062. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:49:47,351][03835] Avg episode reward: [(0, '5.630'), (1, '5.820')] -[2023-10-16 03:49:47,714][05219] Updated weights for policy 1, policy_version 26690 (0.0008) -[2023-10-16 03:49:48,083][05219] Updated weights for policy 1, policy_version 26700 (0.0010) -[2023-10-16 03:49:48,451][05219] Updated weights for policy 1, policy_version 26710 (0.0008) -[2023-10-16 03:49:48,817][05219] Updated weights for policy 1, policy_version 26720 (0.0010) -[2023-10-16 03:49:50,160][05218] Updated weights for policy 0, policy_version 26792 (0.0008) -[2023-10-16 03:49:50,538][05218] Updated weights for policy 0, policy_version 26802 (0.0009) -[2023-10-16 03:49:50,916][05218] Updated weights for policy 0, policy_version 26812 (0.0008) -[2023-10-16 03:49:52,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 54820864. Throughput: 0: 1778.3, 1: 1800.3. Samples: 13718364. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:49:52,351][03835] Avg episode reward: [(0, '5.600'), (1, '5.920')] -[2023-10-16 03:49:52,750][05219] Updated weights for policy 1, policy_version 26730 (0.0007) -[2023-10-16 03:49:53,125][05219] Updated weights for policy 1, policy_version 26740 (0.0008) -[2023-10-16 03:49:53,486][05219] Updated weights for policy 1, policy_version 26750 (0.0008) -[2023-10-16 03:49:54,573][05218] Updated weights for policy 0, policy_version 26822 (0.0009) -[2023-10-16 03:49:54,948][05218] Updated weights for policy 0, policy_version 26832 (0.0007) -[2023-10-16 03:49:55,328][05218] Updated weights for policy 0, policy_version 26842 (0.0007) -[2023-10-16 03:49:57,209][05219] Updated weights for policy 1, policy_version 26760 (0.0009) -[2023-10-16 03:49:57,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 54886400. Throughput: 0: 1786.5, 1: 1800.5. Samples: 13728586. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-16 03:49:57,351][03835] Avg episode reward: [(0, '6.300'), (1, '5.130')] -[2023-10-16 03:49:57,351][04766] Saving new best policy, reward=6.300! -[2023-10-16 03:49:57,578][05219] Updated weights for policy 1, policy_version 26770 (0.0010) -[2023-10-16 03:49:57,947][05219] Updated weights for policy 1, policy_version 26780 (0.0009) -[2023-10-16 03:49:59,104][05218] Updated weights for policy 0, policy_version 26852 (0.0009) -[2023-10-16 03:49:59,480][05218] Updated weights for policy 0, policy_version 26862 (0.0008) -[2023-10-16 03:49:59,854][05218] Updated weights for policy 0, policy_version 26872 (0.0009) -[2023-10-16 03:50:01,732][05219] Updated weights for policy 1, policy_version 26790 (0.0008) -[2023-10-16 03:50:02,097][05219] Updated weights for policy 1, policy_version 26800 (0.0008) -[2023-10-16 03:50:02,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 54951936. Throughput: 0: 1787.7, 1: 1806.7. Samples: 13750794. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-16 03:50:02,351][03835] Avg episode reward: [(0, '6.560'), (1, '5.340')] -[2023-10-16 03:50:02,352][04766] Saving new best policy, reward=6.560! -[2023-10-16 03:50:02,459][05219] Updated weights for policy 1, policy_version 26810 (0.0008) -[2023-10-16 03:50:03,621][05218] Updated weights for policy 0, policy_version 26882 (0.0010) -[2023-10-16 03:50:03,988][05218] Updated weights for policy 0, policy_version 26892 (0.0010) -[2023-10-16 03:50:04,366][05218] Updated weights for policy 0, policy_version 26902 (0.0010) -[2023-10-16 03:50:04,742][05218] Updated weights for policy 0, policy_version 26912 (0.0011) -[2023-10-16 03:50:06,255][05219] Updated weights for policy 1, policy_version 26820 (0.0007) -[2023-10-16 03:50:06,624][05219] Updated weights for policy 1, policy_version 26830 (0.0007) -[2023-10-16 03:50:06,994][05219] Updated weights for policy 1, policy_version 26840 (0.0009) -[2023-10-16 03:50:07,350][03835] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 55050240. Throughput: 0: 1789.1, 1: 1810.3. Samples: 13772242. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-16 03:50:07,351][03835] Avg episode reward: [(0, '6.320'), (1, '5.670')] -[2023-10-16 03:50:08,333][05218] Updated weights for policy 0, policy_version 26922 (0.0009) -[2023-10-16 03:50:08,705][05218] Updated weights for policy 0, policy_version 26932 (0.0010) -[2023-10-16 03:50:09,094][05218] Updated weights for policy 0, policy_version 26942 (0.0008) -[2023-10-16 03:50:10,669][05219] Updated weights for policy 1, policy_version 26850 (0.0008) -[2023-10-16 03:50:11,046][05219] Updated weights for policy 1, policy_version 26860 (0.0010) -[2023-10-16 03:50:11,403][05219] Updated weights for policy 1, policy_version 26870 (0.0008) -[2023-10-16 03:50:11,772][05219] Updated weights for policy 1, policy_version 26880 (0.0009) -[2023-10-16 03:50:12,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 55115776. Throughput: 0: 1792.1, 1: 1802.8. Samples: 13783260. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-16 03:50:12,351][03835] Avg episode reward: [(0, '5.780'), (1, '5.690')] -[2023-10-16 03:50:12,857][05218] Updated weights for policy 0, policy_version 26952 (0.0009) -[2023-10-16 03:50:13,245][05218] Updated weights for policy 0, policy_version 26962 (0.0009) -[2023-10-16 03:50:13,621][05218] Updated weights for policy 0, policy_version 26972 (0.0008) -[2023-10-16 03:50:15,643][05219] Updated weights for policy 1, policy_version 26890 (0.0009) -[2023-10-16 03:50:15,999][05219] Updated weights for policy 1, policy_version 26900 (0.0010) -[2023-10-16 03:50:16,361][05219] Updated weights for policy 1, policy_version 26910 (0.0011) -[2023-10-16 03:50:17,333][05218] Updated weights for policy 0, policy_version 26982 (0.0009) -[2023-10-16 03:50:17,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 55181312. Throughput: 0: 1800.3, 1: 1813.1. Samples: 13804714. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-16 03:50:17,351][03835] Avg episode reward: [(0, '5.600'), (1, '5.090')] -[2023-10-16 03:50:17,715][05218] Updated weights for policy 0, policy_version 26992 (0.0007) -[2023-10-16 03:50:18,082][05218] Updated weights for policy 0, policy_version 27002 (0.0007) -[2023-10-16 03:50:20,098][05219] Updated weights for policy 1, policy_version 26920 (0.0008) -[2023-10-16 03:50:20,470][05219] Updated weights for policy 1, policy_version 26930 (0.0007) -[2023-10-16 03:50:20,838][05219] Updated weights for policy 1, policy_version 26940 (0.0008) -[2023-10-16 03:50:21,952][05218] Updated weights for policy 0, policy_version 27012 (0.0008) -[2023-10-16 03:50:22,346][05218] Updated weights for policy 0, policy_version 27022 (0.0008) -[2023-10-16 03:50:22,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 55246848. Throughput: 0: 1816.1, 1: 1800.4. Samples: 13826082. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:50:22,351][03835] Avg episode reward: [(0, '6.170'), (1, '6.060')] -[2023-10-16 03:50:22,717][05218] Updated weights for policy 0, policy_version 27032 (0.0008) -[2023-10-16 03:50:24,679][05219] Updated weights for policy 1, policy_version 26950 (0.0007) -[2023-10-16 03:50:25,040][05219] Updated weights for policy 1, policy_version 26960 (0.0007) -[2023-10-16 03:50:25,411][05219] Updated weights for policy 1, policy_version 26970 (0.0009) -[2023-10-16 03:50:26,372][05218] Updated weights for policy 0, policy_version 27042 (0.0008) -[2023-10-16 03:50:26,754][05218] Updated weights for policy 0, policy_version 27052 (0.0008) -[2023-10-16 03:50:27,125][05218] Updated weights for policy 0, policy_version 27062 (0.0010) -[2023-10-16 03:50:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 55312384. Throughput: 0: 1798.7, 1: 1812.1. Samples: 13837164. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:50:27,351][03835] Avg episode reward: [(0, '5.550'), (1, '5.710')] -[2023-10-16 03:50:27,498][05218] Updated weights for policy 0, policy_version 27072 (0.0007) -[2023-10-16 03:50:29,136][05219] Updated weights for policy 1, policy_version 26980 (0.0009) -[2023-10-16 03:50:29,509][05219] Updated weights for policy 1, policy_version 26990 (0.0007) -[2023-10-16 03:50:29,874][05219] Updated weights for policy 1, policy_version 27000 (0.0008) -[2023-10-16 03:50:31,157][05218] Updated weights for policy 0, policy_version 27082 (0.0009) -[2023-10-16 03:50:31,539][05218] Updated weights for policy 0, policy_version 27092 (0.0008) -[2023-10-16 03:50:31,910][05218] Updated weights for policy 0, policy_version 27102 (0.0009) -[2023-10-16 03:50:32,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 55410688. Throughput: 0: 1817.2, 1: 1792.7. Samples: 13858508. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:50:32,351][03835] Avg episode reward: [(0, '5.450'), (1, '5.830')] -[2023-10-16 03:50:33,499][05219] Updated weights for policy 1, policy_version 27010 (0.0009) -[2023-10-16 03:50:33,873][05219] Updated weights for policy 1, policy_version 27020 (0.0008) -[2023-10-16 03:50:34,233][05219] Updated weights for policy 1, policy_version 27030 (0.0009) -[2023-10-16 03:50:34,597][05219] Updated weights for policy 1, policy_version 27040 (0.0010) -[2023-10-16 03:50:35,690][05218] Updated weights for policy 0, policy_version 27112 (0.0009) -[2023-10-16 03:50:36,066][05218] Updated weights for policy 0, policy_version 27122 (0.0010) -[2023-10-16 03:50:36,446][05218] Updated weights for policy 0, policy_version 27132 (0.0009) -[2023-10-16 03:50:37,350][03835] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 55476224. Throughput: 0: 1800.7, 1: 1788.3. Samples: 13879870. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:50:37,352][03835] Avg episode reward: [(0, '5.870'), (1, '5.910')] -[2023-10-16 03:50:38,371][05219] Updated weights for policy 1, policy_version 27050 (0.0007) -[2023-10-16 03:50:38,733][05219] Updated weights for policy 1, policy_version 27060 (0.0008) -[2023-10-16 03:50:39,100][05219] Updated weights for policy 1, policy_version 27070 (0.0009) -[2023-10-16 03:50:40,264][05218] Updated weights for policy 0, policy_version 27142 (0.0008) -[2023-10-16 03:50:40,634][05218] Updated weights for policy 0, policy_version 27152 (0.0008) -[2023-10-16 03:50:41,009][05218] Updated weights for policy 0, policy_version 27162 (0.0008) -[2023-10-16 03:50:42,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 55541760. Throughput: 0: 1817.8, 1: 1787.2. Samples: 13890810. Policy #0 lag: (min: 31.0, avg: 32.8, max: 61.0) -[2023-10-16 03:50:42,351][03835] Avg episode reward: [(0, '5.270'), (1, '6.020')] -[2023-10-16 03:50:43,037][05219] Updated weights for policy 1, policy_version 27080 (0.0009) -[2023-10-16 03:50:43,400][05219] Updated weights for policy 1, policy_version 27090 (0.0008) -[2023-10-16 03:50:43,763][05219] Updated weights for policy 1, policy_version 27100 (0.0007) -[2023-10-16 03:50:44,676][05218] Updated weights for policy 0, policy_version 27172 (0.0008) -[2023-10-16 03:50:45,051][05218] Updated weights for policy 0, policy_version 27182 (0.0008) -[2023-10-16 03:50:45,424][05218] Updated weights for policy 0, policy_version 27192 (0.0008) -[2023-10-16 03:50:47,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 55607296. Throughput: 0: 1802.0, 1: 1786.1. Samples: 13912256. Policy #0 lag: (min: 31.0, avg: 32.8, max: 61.0) -[2023-10-16 03:50:47,351][03835] Avg episode reward: [(0, '6.120'), (1, '5.240')] -[2023-10-16 03:50:47,493][05219] Updated weights for policy 1, policy_version 27110 (0.0008) -[2023-10-16 03:50:47,860][05219] Updated weights for policy 1, policy_version 27120 (0.0009) -[2023-10-16 03:50:48,229][05219] Updated weights for policy 1, policy_version 27130 (0.0008) -[2023-10-16 03:50:49,218][05218] Updated weights for policy 0, policy_version 27202 (0.0009) -[2023-10-16 03:50:49,595][05218] Updated weights for policy 0, policy_version 27212 (0.0010) -[2023-10-16 03:50:49,970][05218] Updated weights for policy 0, policy_version 27222 (0.0008) -[2023-10-16 03:50:50,354][05218] Updated weights for policy 0, policy_version 27232 (0.0008) -[2023-10-16 03:50:52,079][05219] Updated weights for policy 1, policy_version 27140 (0.0007) -[2023-10-16 03:50:52,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 55672832. Throughput: 0: 1797.6, 1: 1808.3. Samples: 13934508. Policy #0 lag: (min: 31.0, avg: 32.8, max: 61.0) -[2023-10-16 03:50:52,351][03835] Avg episode reward: [(0, '5.990'), (1, '5.560')] -[2023-10-16 03:50:52,445][05219] Updated weights for policy 1, policy_version 27150 (0.0008) -[2023-10-16 03:50:52,821][05219] Updated weights for policy 1, policy_version 27160 (0.0009) -[2023-10-16 03:50:53,936][05218] Updated weights for policy 0, policy_version 27242 (0.0007) -[2023-10-16 03:50:54,301][05218] Updated weights for policy 0, policy_version 27252 (0.0009) -[2023-10-16 03:50:54,679][05218] Updated weights for policy 0, policy_version 27262 (0.0007) -[2023-10-16 03:50:56,684][05219] Updated weights for policy 1, policy_version 27170 (0.0008) -[2023-10-16 03:50:57,062][05219] Updated weights for policy 1, policy_version 27180 (0.0009) -[2023-10-16 03:50:57,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 55738368. Throughput: 0: 1797.5, 1: 1784.2. Samples: 13944438. Policy #0 lag: (min: 31.0, avg: 32.8, max: 61.0) -[2023-10-16 03:50:57,351][03835] Avg episode reward: [(0, '5.600'), (1, '5.290')] -[2023-10-16 03:50:57,424][05219] Updated weights for policy 1, policy_version 27190 (0.0007) -[2023-10-16 03:50:57,794][05219] Updated weights for policy 1, policy_version 27200 (0.0009) -[2023-10-16 03:50:58,364][05218] Updated weights for policy 0, policy_version 27272 (0.0009) -[2023-10-16 03:50:58,745][05218] Updated weights for policy 0, policy_version 27282 (0.0009) -[2023-10-16 03:50:59,124][05218] Updated weights for policy 0, policy_version 27292 (0.0011) -[2023-10-16 03:51:01,654][05219] Updated weights for policy 1, policy_version 27210 (0.0009) -[2023-10-16 03:51:02,019][05219] Updated weights for policy 1, policy_version 27220 (0.0008) -[2023-10-16 03:51:02,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 55803904. Throughput: 0: 1796.8, 1: 1804.7. Samples: 13966780. Policy #0 lag: (min: 31.0, avg: 32.8, max: 61.0) -[2023-10-16 03:51:02,351][03835] Avg episode reward: [(0, '6.200'), (1, '5.470')] -[2023-10-16 03:51:02,381][05219] Updated weights for policy 1, policy_version 27230 (0.0007) -[2023-10-16 03:51:02,796][05218] Updated weights for policy 0, policy_version 27302 (0.0011) -[2023-10-16 03:51:03,186][05218] Updated weights for policy 0, policy_version 27312 (0.0008) -[2023-10-16 03:51:03,544][05218] Updated weights for policy 0, policy_version 27322 (0.0011) -[2023-10-16 03:51:06,069][05219] Updated weights for policy 1, policy_version 27240 (0.0009) -[2023-10-16 03:51:06,429][05219] Updated weights for policy 1, policy_version 27250 (0.0009) -[2023-10-16 03:51:06,793][05219] Updated weights for policy 1, policy_version 27260 (0.0010) -[2023-10-16 03:51:07,350][03835] Fps is (10 sec: 16383.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 55902208. Throughput: 0: 1813.5, 1: 1779.9. Samples: 13987786. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-16 03:51:07,351][03835] Avg episode reward: [(0, '6.260'), (1, '5.600')] -[2023-10-16 03:51:07,445][05218] Updated weights for policy 0, policy_version 27332 (0.0008) -[2023-10-16 03:51:07,831][05218] Updated weights for policy 0, policy_version 27342 (0.0007) -[2023-10-16 03:51:08,208][05218] Updated weights for policy 0, policy_version 27352 (0.0010) -[2023-10-16 03:51:10,391][05219] Updated weights for policy 1, policy_version 27270 (0.0009) -[2023-10-16 03:51:10,753][05219] Updated weights for policy 1, policy_version 27280 (0.0008) -[2023-10-16 03:51:11,120][05219] Updated weights for policy 1, policy_version 27290 (0.0007) -[2023-10-16 03:51:11,855][05218] Updated weights for policy 0, policy_version 27362 (0.0010) -[2023-10-16 03:51:12,225][05218] Updated weights for policy 0, policy_version 27372 (0.0008) -[2023-10-16 03:51:12,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 55967744. Throughput: 0: 1797.3, 1: 1802.6. Samples: 13999160. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-16 03:51:12,351][03835] Avg episode reward: [(0, '5.600'), (1, '5.860')] -[2023-10-16 03:51:12,602][05218] Updated weights for policy 0, policy_version 27382 (0.0007) -[2023-10-16 03:51:12,980][05218] Updated weights for policy 0, policy_version 27392 (0.0008) -[2023-10-16 03:51:14,894][05219] Updated weights for policy 1, policy_version 27300 (0.0007) -[2023-10-16 03:51:15,260][05219] Updated weights for policy 1, policy_version 27310 (0.0007) -[2023-10-16 03:51:15,613][05219] Updated weights for policy 1, policy_version 27320 (0.0008) -[2023-10-16 03:51:16,708][05218] Updated weights for policy 0, policy_version 27402 (0.0008) -[2023-10-16 03:51:17,072][05218] Updated weights for policy 0, policy_version 27412 (0.0007) -[2023-10-16 03:51:17,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 56033280. Throughput: 0: 1807.6, 1: 1788.2. Samples: 14020316. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-16 03:51:17,351][03835] Avg episode reward: [(0, '5.660'), (1, '5.870')] -[2023-10-16 03:51:17,446][05218] Updated weights for policy 0, policy_version 27422 (0.0010) -[2023-10-16 03:51:19,346][05219] Updated weights for policy 1, policy_version 27330 (0.0008) -[2023-10-16 03:51:19,721][05219] Updated weights for policy 1, policy_version 27340 (0.0007) -[2023-10-16 03:51:20,092][05219] Updated weights for policy 1, policy_version 27350 (0.0009) -[2023-10-16 03:51:20,457][05219] Updated weights for policy 1, policy_version 27360 (0.0010) -[2023-10-16 03:51:21,211][05218] Updated weights for policy 0, policy_version 27432 (0.0010) -[2023-10-16 03:51:21,589][05218] Updated weights for policy 0, policy_version 27442 (0.0010) -[2023-10-16 03:51:21,958][05218] Updated weights for policy 0, policy_version 27452 (0.0010) -[2023-10-16 03:51:22,350][03835] Fps is (10 sec: 16383.5, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 56131584. Throughput: 0: 1794.4, 1: 1788.6. Samples: 14041106. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-16 03:51:22,352][03835] Avg episode reward: [(0, '5.510'), (1, '5.640')] -[2023-10-16 03:51:24,386][05219] Updated weights for policy 1, policy_version 27370 (0.0010) -[2023-10-16 03:51:24,747][05219] Updated weights for policy 1, policy_version 27380 (0.0010) -[2023-10-16 03:51:25,123][05219] Updated weights for policy 1, policy_version 27390 (0.0008) -[2023-10-16 03:51:25,770][05218] Updated weights for policy 0, policy_version 27462 (0.0009) -[2023-10-16 03:51:26,144][05218] Updated weights for policy 0, policy_version 27472 (0.0008) -[2023-10-16 03:51:26,524][05218] Updated weights for policy 0, policy_version 27482 (0.0007) -[2023-10-16 03:51:27,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 56197120. Throughput: 0: 1806.8, 1: 1786.6. Samples: 14052514. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-16 03:51:27,351][03835] Avg episode reward: [(0, '5.830'), (1, '5.050')] -[2023-10-16 03:51:28,957][05219] Updated weights for policy 1, policy_version 27400 (0.0008) -[2023-10-16 03:51:29,325][05219] Updated weights for policy 1, policy_version 27410 (0.0008) -[2023-10-16 03:51:29,696][05219] Updated weights for policy 1, policy_version 27420 (0.0008) -[2023-10-16 03:51:30,241][05218] Updated weights for policy 0, policy_version 27492 (0.0009) -[2023-10-16 03:51:30,612][05218] Updated weights for policy 0, policy_version 27502 (0.0010) -[2023-10-16 03:51:30,984][05218] Updated weights for policy 0, policy_version 27512 (0.0009) -[2023-10-16 03:51:32,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 56262656. Throughput: 0: 1795.6, 1: 1780.4. Samples: 14073174. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-16 03:51:32,351][03835] Avg episode reward: [(0, '6.530'), (1, '5.280')] -[2023-10-16 03:51:33,436][05219] Updated weights for policy 1, policy_version 27430 (0.0009) -[2023-10-16 03:51:33,800][05219] Updated weights for policy 1, policy_version 27440 (0.0008) -[2023-10-16 03:51:34,162][05219] Updated weights for policy 1, policy_version 27450 (0.0007) -[2023-10-16 03:51:34,672][05218] Updated weights for policy 0, policy_version 27522 (0.0010) -[2023-10-16 03:51:35,052][05218] Updated weights for policy 0, policy_version 27532 (0.0009) -[2023-10-16 03:51:35,427][05218] Updated weights for policy 0, policy_version 27542 (0.0009) -[2023-10-16 03:51:35,801][05218] Updated weights for policy 0, policy_version 27552 (0.0010) -[2023-10-16 03:51:37,351][03835] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 56328192. Throughput: 0: 1792.0, 1: 1793.6. Samples: 14095862. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-16 03:51:37,352][03835] Avg episode reward: [(0, '5.940'), (1, '5.670')] -[2023-10-16 03:51:37,362][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000027552_28213248.pth... -[2023-10-16 03:51:37,362][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000027456_28114944.pth... -[2023-10-16 03:51:37,392][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000025792_26411008.pth -[2023-10-16 03:51:37,393][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000025888_26509312.pth -[2023-10-16 03:51:37,739][05219] Updated weights for policy 1, policy_version 27460 (0.0007) -[2023-10-16 03:51:38,106][05219] Updated weights for policy 1, policy_version 27470 (0.0007) -[2023-10-16 03:51:38,471][05219] Updated weights for policy 1, policy_version 27480 (0.0007) -[2023-10-16 03:51:39,410][05218] Updated weights for policy 0, policy_version 27562 (0.0007) -[2023-10-16 03:51:39,779][05218] Updated weights for policy 0, policy_version 27572 (0.0009) -[2023-10-16 03:51:40,151][05218] Updated weights for policy 0, policy_version 27582 (0.0009) -[2023-10-16 03:51:42,266][05219] Updated weights for policy 1, policy_version 27490 (0.0008) -[2023-10-16 03:51:42,351][03835] Fps is (10 sec: 13106.6, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 56393728. Throughput: 0: 1795.5, 1: 1788.6. Samples: 14105728. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-16 03:51:42,352][03835] Avg episode reward: [(0, '6.200'), (1, '5.650')] -[2023-10-16 03:51:42,633][05219] Updated weights for policy 1, policy_version 27500 (0.0009) -[2023-10-16 03:51:42,991][05219] Updated weights for policy 1, policy_version 27510 (0.0007) -[2023-10-16 03:51:43,351][05219] Updated weights for policy 1, policy_version 27520 (0.0009) -[2023-10-16 03:51:43,934][05218] Updated weights for policy 0, policy_version 27592 (0.0008) -[2023-10-16 03:51:44,314][05218] Updated weights for policy 0, policy_version 27602 (0.0010) -[2023-10-16 03:51:44,696][05218] Updated weights for policy 0, policy_version 27612 (0.0010) -[2023-10-16 03:51:47,343][05219] Updated weights for policy 1, policy_version 27530 (0.0008) -[2023-10-16 03:51:47,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 56459264. Throughput: 0: 1794.4, 1: 1786.8. Samples: 14127934. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-16 03:51:47,351][03835] Avg episode reward: [(0, '5.760'), (1, '5.320')] -[2023-10-16 03:51:47,700][05219] Updated weights for policy 1, policy_version 27540 (0.0007) -[2023-10-16 03:51:48,061][05219] Updated weights for policy 1, policy_version 27550 (0.0009) -[2023-10-16 03:51:48,231][05218] Updated weights for policy 0, policy_version 27622 (0.0009) -[2023-10-16 03:51:48,612][05218] Updated weights for policy 0, policy_version 27632 (0.0009) -[2023-10-16 03:51:48,978][05218] Updated weights for policy 0, policy_version 27642 (0.0008) -[2023-10-16 03:51:51,961][05219] Updated weights for policy 1, policy_version 27560 (0.0008) -[2023-10-16 03:51:52,334][05219] Updated weights for policy 1, policy_version 27570 (0.0010) -[2023-10-16 03:51:52,351][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 56524800. Throughput: 0: 1797.7, 1: 1798.9. Samples: 14149634. Policy #0 lag: (min: 18.0, avg: 26.0, max: 50.0) -[2023-10-16 03:51:52,352][03835] Avg episode reward: [(0, '6.010'), (1, '5.470')] -[2023-10-16 03:51:52,696][05219] Updated weights for policy 1, policy_version 27580 (0.0009) -[2023-10-16 03:51:52,797][05218] Updated weights for policy 0, policy_version 27652 (0.0007) -[2023-10-16 03:51:53,190][05218] Updated weights for policy 0, policy_version 27662 (0.0010) -[2023-10-16 03:51:53,570][05218] Updated weights for policy 0, policy_version 27672 (0.0008) -[2023-10-16 03:51:56,334][05219] Updated weights for policy 1, policy_version 27590 (0.0007) -[2023-10-16 03:51:56,701][05219] Updated weights for policy 1, policy_version 27600 (0.0007) -[2023-10-16 03:51:57,069][05219] Updated weights for policy 1, policy_version 27610 (0.0007) -[2023-10-16 03:51:57,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 56623104. Throughput: 0: 1794.3, 1: 1776.2. Samples: 14159832. Policy #0 lag: (min: 18.0, avg: 26.0, max: 50.0) -[2023-10-16 03:51:57,351][03835] Avg episode reward: [(0, '5.810'), (1, '5.310')] -[2023-10-16 03:51:57,379][05218] Updated weights for policy 0, policy_version 27682 (0.0009) -[2023-10-16 03:51:57,758][05218] Updated weights for policy 0, policy_version 27692 (0.0010) -[2023-10-16 03:51:58,125][05218] Updated weights for policy 0, policy_version 27702 (0.0010) -[2023-10-16 03:51:58,501][05218] Updated weights for policy 0, policy_version 27712 (0.0010) -[2023-10-16 03:52:00,860][05219] Updated weights for policy 1, policy_version 27620 (0.0007) -[2023-10-16 03:52:01,226][05219] Updated weights for policy 1, policy_version 27630 (0.0010) -[2023-10-16 03:52:01,598][05219] Updated weights for policy 1, policy_version 27640 (0.0010) -[2023-10-16 03:52:02,212][05218] Updated weights for policy 0, policy_version 27722 (0.0009) -[2023-10-16 03:52:02,350][03835] Fps is (10 sec: 16384.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 56688640. Throughput: 0: 1796.8, 1: 1795.5. Samples: 14181970. Policy #0 lag: (min: 18.0, avg: 26.0, max: 50.0) -[2023-10-16 03:52:02,351][03835] Avg episode reward: [(0, '5.960'), (1, '5.530')] -[2023-10-16 03:52:02,579][05218] Updated weights for policy 0, policy_version 27732 (0.0009) -[2023-10-16 03:52:02,953][05218] Updated weights for policy 0, policy_version 27742 (0.0007) -[2023-10-16 03:52:05,431][05219] Updated weights for policy 1, policy_version 27650 (0.0007) -[2023-10-16 03:52:05,802][05219] Updated weights for policy 1, policy_version 27660 (0.0007) -[2023-10-16 03:52:06,153][05219] Updated weights for policy 1, policy_version 27670 (0.0009) -[2023-10-16 03:52:06,513][05219] Updated weights for policy 1, policy_version 27680 (0.0010) -[2023-10-16 03:52:06,816][05218] Updated weights for policy 0, policy_version 27752 (0.0007) -[2023-10-16 03:52:07,190][05218] Updated weights for policy 0, policy_version 27762 (0.0008) -[2023-10-16 03:52:07,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 56754176. Throughput: 0: 1807.4, 1: 1774.5. Samples: 14202292. Policy #0 lag: (min: 18.0, avg: 26.0, max: 50.0) -[2023-10-16 03:52:07,351][03835] Avg episode reward: [(0, '5.580'), (1, '5.120')] -[2023-10-16 03:52:07,560][05218] Updated weights for policy 0, policy_version 27772 (0.0007) -[2023-10-16 03:52:10,202][05219] Updated weights for policy 1, policy_version 27690 (0.0008) -[2023-10-16 03:52:10,575][05219] Updated weights for policy 1, policy_version 27700 (0.0008) -[2023-10-16 03:52:10,945][05219] Updated weights for policy 1, policy_version 27710 (0.0009) -[2023-10-16 03:52:11,348][05218] Updated weights for policy 0, policy_version 27782 (0.0010) -[2023-10-16 03:52:11,726][05218] Updated weights for policy 0, policy_version 27792 (0.0011) -[2023-10-16 03:52:12,097][05218] Updated weights for policy 0, policy_version 27802 (0.0011) -[2023-10-16 03:52:12,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 56852480. Throughput: 0: 1790.9, 1: 1801.9. Samples: 14214190. Policy #0 lag: (min: 9.0, avg: 26.5, max: 41.0) -[2023-10-16 03:52:12,351][03835] Avg episode reward: [(0, '5.850'), (1, '4.740')] -[2023-10-16 03:52:14,679][05219] Updated weights for policy 1, policy_version 27720 (0.0010) -[2023-10-16 03:52:15,051][05219] Updated weights for policy 1, policy_version 27730 (0.0008) -[2023-10-16 03:52:15,415][05219] Updated weights for policy 1, policy_version 27740 (0.0008) -[2023-10-16 03:52:15,799][05218] Updated weights for policy 0, policy_version 27812 (0.0010) -[2023-10-16 03:52:16,169][05218] Updated weights for policy 0, policy_version 27822 (0.0009) -[2023-10-16 03:52:16,542][05218] Updated weights for policy 0, policy_version 27832 (0.0010) -[2023-10-16 03:52:17,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 56918016. Throughput: 0: 1803.8, 1: 1781.6. Samples: 14234520. Policy #0 lag: (min: 9.0, avg: 26.5, max: 41.0) -[2023-10-16 03:52:17,351][03835] Avg episode reward: [(0, '5.670'), (1, '4.100')] -[2023-10-16 03:52:19,290][05219] Updated weights for policy 1, policy_version 27750 (0.0009) -[2023-10-16 03:52:19,665][05219] Updated weights for policy 1, policy_version 27760 (0.0007) -[2023-10-16 03:52:20,017][05219] Updated weights for policy 1, policy_version 27770 (0.0007) -[2023-10-16 03:52:20,091][05218] Updated weights for policy 0, policy_version 27842 (0.0009) -[2023-10-16 03:52:20,461][05218] Updated weights for policy 0, policy_version 27852 (0.0010) -[2023-10-16 03:52:20,834][05218] Updated weights for policy 0, policy_version 27862 (0.0014) -[2023-10-16 03:52:21,215][05218] Updated weights for policy 0, policy_version 27872 (0.0008) -[2023-10-16 03:52:22,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 56983552. Throughput: 0: 1793.5, 1: 1773.3. Samples: 14256368. Policy #0 lag: (min: 9.0, avg: 26.5, max: 41.0) -[2023-10-16 03:52:22,352][03835] Avg episode reward: [(0, '5.720'), (1, '4.740')] -[2023-10-16 03:52:23,747][05219] Updated weights for policy 1, policy_version 27780 (0.0010) -[2023-10-16 03:52:24,106][05219] Updated weights for policy 1, policy_version 27790 (0.0009) -[2023-10-16 03:52:24,473][05219] Updated weights for policy 1, policy_version 27800 (0.0010) -[2023-10-16 03:52:24,831][05218] Updated weights for policy 0, policy_version 27882 (0.0010) -[2023-10-16 03:52:25,212][05218] Updated weights for policy 0, policy_version 27892 (0.0009) -[2023-10-16 03:52:25,585][05218] Updated weights for policy 0, policy_version 27902 (0.0007) -[2023-10-16 03:52:27,351][03835] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 57049088. Throughput: 0: 1800.7, 1: 1769.3. Samples: 14266380. Policy #0 lag: (min: 9.0, avg: 26.5, max: 41.0) -[2023-10-16 03:52:27,352][03835] Avg episode reward: [(0, '4.910'), (1, '4.860')] -[2023-10-16 03:52:28,233][05219] Updated weights for policy 1, policy_version 27810 (0.0009) -[2023-10-16 03:52:28,598][05219] Updated weights for policy 1, policy_version 27820 (0.0009) -[2023-10-16 03:52:28,956][05219] Updated weights for policy 1, policy_version 27830 (0.0010) -[2023-10-16 03:52:29,248][05218] Updated weights for policy 0, policy_version 27912 (0.0010) -[2023-10-16 03:52:29,314][05219] Updated weights for policy 1, policy_version 27840 (0.0009) -[2023-10-16 03:52:29,626][05218] Updated weights for policy 0, policy_version 27922 (0.0010) -[2023-10-16 03:52:30,003][05218] Updated weights for policy 0, policy_version 27932 (0.0009) -[2023-10-16 03:52:32,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 57114624. Throughput: 0: 1791.7, 1: 1771.9. Samples: 14288298. Policy #0 lag: (min: 9.0, avg: 26.5, max: 41.0) -[2023-10-16 03:52:32,351][03835] Avg episode reward: [(0, '5.520'), (1, '5.310')] -[2023-10-16 03:52:33,151][05219] Updated weights for policy 1, policy_version 27850 (0.0011) -[2023-10-16 03:52:33,517][05219] Updated weights for policy 1, policy_version 27860 (0.0010) -[2023-10-16 03:52:33,838][05218] Updated weights for policy 0, policy_version 27942 (0.0008) -[2023-10-16 03:52:33,880][05219] Updated weights for policy 1, policy_version 27870 (0.0007) -[2023-10-16 03:52:34,203][05218] Updated weights for policy 0, policy_version 27952 (0.0009) -[2023-10-16 03:52:34,575][05218] Updated weights for policy 0, policy_version 27962 (0.0010) -[2023-10-16 03:52:37,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 57180160. Throughput: 0: 1791.0, 1: 1787.4. Samples: 14310664. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:52:37,352][03835] Avg episode reward: [(0, '5.740'), (1, '5.360')] -[2023-10-16 03:52:37,760][05219] Updated weights for policy 1, policy_version 27880 (0.0008) -[2023-10-16 03:52:38,116][05219] Updated weights for policy 1, policy_version 27890 (0.0008) -[2023-10-16 03:52:38,269][05218] Updated weights for policy 0, policy_version 27972 (0.0009) -[2023-10-16 03:52:38,484][05219] Updated weights for policy 1, policy_version 27900 (0.0009) -[2023-10-16 03:52:38,653][05218] Updated weights for policy 0, policy_version 27982 (0.0007) -[2023-10-16 03:52:39,027][05218] Updated weights for policy 0, policy_version 27992 (0.0009) -[2023-10-16 03:52:42,315][05219] Updated weights for policy 1, policy_version 27910 (0.0008) -[2023-10-16 03:52:42,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 57245696. Throughput: 0: 1793.9, 1: 1772.7. Samples: 14320328. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:52:42,351][03835] Avg episode reward: [(0, '5.440'), (1, '5.180')] -[2023-10-16 03:52:42,669][05219] Updated weights for policy 1, policy_version 27920 (0.0008) -[2023-10-16 03:52:42,946][05218] Updated weights for policy 0, policy_version 28002 (0.0010) -[2023-10-16 03:52:43,031][05219] Updated weights for policy 1, policy_version 27930 (0.0009) -[2023-10-16 03:52:43,319][05218] Updated weights for policy 0, policy_version 28012 (0.0008) -[2023-10-16 03:52:43,696][05218] Updated weights for policy 0, policy_version 28022 (0.0007) -[2023-10-16 03:52:44,070][05218] Updated weights for policy 0, policy_version 28032 (0.0008) -[2023-10-16 03:52:46,891][05219] Updated weights for policy 1, policy_version 27940 (0.0008) -[2023-10-16 03:52:47,254][05219] Updated weights for policy 1, policy_version 27950 (0.0007) -[2023-10-16 03:52:47,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 57311232. Throughput: 0: 1787.1, 1: 1774.9. Samples: 14342258. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:52:47,352][03835] Avg episode reward: [(0, '6.060'), (1, '5.650')] -[2023-10-16 03:52:47,623][05219] Updated weights for policy 1, policy_version 27960 (0.0009) -[2023-10-16 03:52:47,838][05218] Updated weights for policy 0, policy_version 28042 (0.0007) -[2023-10-16 03:52:48,207][05218] Updated weights for policy 0, policy_version 28052 (0.0009) -[2023-10-16 03:52:48,594][05218] Updated weights for policy 0, policy_version 28062 (0.0009) -[2023-10-16 03:52:51,454][05219] Updated weights for policy 1, policy_version 27970 (0.0007) -[2023-10-16 03:52:51,820][05219] Updated weights for policy 1, policy_version 27980 (0.0009) -[2023-10-16 03:52:52,186][05219] Updated weights for policy 1, policy_version 27990 (0.0008) -[2023-10-16 03:52:52,288][05218] Updated weights for policy 0, policy_version 28072 (0.0007) -[2023-10-16 03:52:52,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 57376768. Throughput: 0: 1800.8, 1: 1774.3. Samples: 14363174. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:52:52,351][03835] Avg episode reward: [(0, '5.570'), (1, '5.470')] -[2023-10-16 03:52:52,546][05219] Updated weights for policy 1, policy_version 28000 (0.0008) -[2023-10-16 03:52:52,650][05218] Updated weights for policy 0, policy_version 28082 (0.0007) -[2023-10-16 03:52:53,030][05218] Updated weights for policy 0, policy_version 28092 (0.0007) -[2023-10-16 03:52:56,322][05219] Updated weights for policy 1, policy_version 28010 (0.0009) -[2023-10-16 03:52:56,696][05219] Updated weights for policy 1, policy_version 28020 (0.0007) -[2023-10-16 03:52:56,924][05218] Updated weights for policy 0, policy_version 28102 (0.0009) -[2023-10-16 03:52:57,060][05219] Updated weights for policy 1, policy_version 28030 (0.0007) -[2023-10-16 03:52:57,302][05218] Updated weights for policy 0, policy_version 28112 (0.0009) -[2023-10-16 03:52:57,350][03835] Fps is (10 sec: 16384.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 57475072. Throughput: 0: 1786.6, 1: 1766.1. Samples: 14374060. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:52:57,351][03835] Avg episode reward: [(0, '5.050'), (1, '6.270')] -[2023-10-16 03:52:57,685][05218] Updated weights for policy 0, policy_version 28122 (0.0007) -[2023-10-16 03:53:00,837][05219] Updated weights for policy 1, policy_version 28040 (0.0008) -[2023-10-16 03:53:01,197][05219] Updated weights for policy 1, policy_version 28050 (0.0007) -[2023-10-16 03:53:01,385][05218] Updated weights for policy 0, policy_version 28132 (0.0008) -[2023-10-16 03:53:01,571][05219] Updated weights for policy 1, policy_version 28060 (0.0007) -[2023-10-16 03:53:01,755][05218] Updated weights for policy 0, policy_version 28142 (0.0009) -[2023-10-16 03:53:02,127][05218] Updated weights for policy 0, policy_version 28152 (0.0007) -[2023-10-16 03:53:02,351][03835] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 57540608. Throughput: 0: 1803.9, 1: 1779.6. Samples: 14395778. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:53:02,351][03835] Avg episode reward: [(0, '5.740'), (1, '5.920')] -[2023-10-16 03:53:05,257][05219] Updated weights for policy 1, policy_version 28070 (0.0007) -[2023-10-16 03:53:05,629][05219] Updated weights for policy 1, policy_version 28080 (0.0010) -[2023-10-16 03:53:05,828][05218] Updated weights for policy 0, policy_version 28162 (0.0008) -[2023-10-16 03:53:05,992][05219] Updated weights for policy 1, policy_version 28090 (0.0008) -[2023-10-16 03:53:06,210][05218] Updated weights for policy 0, policy_version 28172 (0.0009) -[2023-10-16 03:53:06,575][05218] Updated weights for policy 0, policy_version 28182 (0.0009) -[2023-10-16 03:53:06,951][05218] Updated weights for policy 0, policy_version 28192 (0.0009) -[2023-10-16 03:53:07,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 57638912. Throughput: 0: 1789.4, 1: 1765.3. Samples: 14416328. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:53:07,351][03835] Avg episode reward: [(0, '5.580'), (1, '5.700')] -[2023-10-16 03:53:09,643][05219] Updated weights for policy 1, policy_version 28100 (0.0010) -[2023-10-16 03:53:10,007][05219] Updated weights for policy 1, policy_version 28110 (0.0007) -[2023-10-16 03:53:10,368][05219] Updated weights for policy 1, policy_version 28120 (0.0009) -[2023-10-16 03:53:10,553][05218] Updated weights for policy 0, policy_version 28202 (0.0009) -[2023-10-16 03:53:10,925][05218] Updated weights for policy 0, policy_version 28212 (0.0009) -[2023-10-16 03:53:11,305][05218] Updated weights for policy 0, policy_version 28222 (0.0011) -[2023-10-16 03:53:12,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 57704448. Throughput: 0: 1813.6, 1: 1786.5. Samples: 14428388. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:53:12,351][03835] Avg episode reward: [(0, '5.890'), (1, '5.810')] -[2023-10-16 03:53:14,290][05219] Updated weights for policy 1, policy_version 28130 (0.0008) -[2023-10-16 03:53:14,661][05219] Updated weights for policy 1, policy_version 28140 (0.0008) -[2023-10-16 03:53:15,029][05219] Updated weights for policy 1, policy_version 28150 (0.0009) -[2023-10-16 03:53:15,043][05218] Updated weights for policy 0, policy_version 28232 (0.0008) -[2023-10-16 03:53:15,394][05219] Updated weights for policy 1, policy_version 28160 (0.0007) -[2023-10-16 03:53:15,421][05218] Updated weights for policy 0, policy_version 28242 (0.0008) -[2023-10-16 03:53:15,797][05218] Updated weights for policy 0, policy_version 28252 (0.0008) -[2023-10-16 03:53:17,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 57769984. Throughput: 0: 1790.4, 1: 1772.1. Samples: 14448612. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:53:17,351][03835] Avg episode reward: [(0, '5.830'), (1, '5.420')] -[2023-10-16 03:53:19,376][05219] Updated weights for policy 1, policy_version 28170 (0.0008) -[2023-10-16 03:53:19,595][05218] Updated weights for policy 0, policy_version 28262 (0.0009) -[2023-10-16 03:53:19,749][05219] Updated weights for policy 1, policy_version 28180 (0.0009) -[2023-10-16 03:53:19,969][05218] Updated weights for policy 0, policy_version 28272 (0.0009) -[2023-10-16 03:53:20,113][05219] Updated weights for policy 1, policy_version 28190 (0.0008) -[2023-10-16 03:53:20,344][05218] Updated weights for policy 0, policy_version 28282 (0.0008) -[2023-10-16 03:53:22,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 57835520. Throughput: 0: 1789.5, 1: 1766.1. Samples: 14470668. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:53:22,352][03835] Avg episode reward: [(0, '6.030'), (1, '5.760')] -[2023-10-16 03:53:23,983][05219] Updated weights for policy 1, policy_version 28200 (0.0010) -[2023-10-16 03:53:24,138][05218] Updated weights for policy 0, policy_version 28292 (0.0007) -[2023-10-16 03:53:24,344][05219] Updated weights for policy 1, policy_version 28210 (0.0009) -[2023-10-16 03:53:24,518][05218] Updated weights for policy 0, policy_version 28302 (0.0010) -[2023-10-16 03:53:24,699][05219] Updated weights for policy 1, policy_version 28220 (0.0008) -[2023-10-16 03:53:24,900][05218] Updated weights for policy 0, policy_version 28312 (0.0010) -[2023-10-16 03:53:27,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 57901056. Throughput: 0: 1784.5, 1: 1768.0. Samples: 14480192. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:53:27,351][03835] Avg episode reward: [(0, '5.350'), (1, '5.670')] -[2023-10-16 03:53:28,236][05219] Updated weights for policy 1, policy_version 28230 (0.0008) -[2023-10-16 03:53:28,609][05219] Updated weights for policy 1, policy_version 28240 (0.0009) -[2023-10-16 03:53:28,760][05218] Updated weights for policy 0, policy_version 28322 (0.0009) -[2023-10-16 03:53:28,968][05219] Updated weights for policy 1, policy_version 28250 (0.0008) -[2023-10-16 03:53:29,128][05218] Updated weights for policy 0, policy_version 28332 (0.0007) -[2023-10-16 03:53:29,499][05218] Updated weights for policy 0, policy_version 28342 (0.0008) -[2023-10-16 03:53:29,881][05218] Updated weights for policy 0, policy_version 28352 (0.0009) -[2023-10-16 03:53:32,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 57966592. Throughput: 0: 1781.0, 1: 1782.0. Samples: 14502594. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:53:32,351][03835] Avg episode reward: [(0, '5.650'), (1, '5.980')] -[2023-10-16 03:53:32,772][05219] Updated weights for policy 1, policy_version 28260 (0.0008) -[2023-10-16 03:53:33,142][05219] Updated weights for policy 1, policy_version 28270 (0.0008) -[2023-10-16 03:53:33,504][05219] Updated weights for policy 1, policy_version 28280 (0.0007) -[2023-10-16 03:53:33,691][05218] Updated weights for policy 0, policy_version 28362 (0.0008) -[2023-10-16 03:53:34,065][05218] Updated weights for policy 0, policy_version 28372 (0.0009) -[2023-10-16 03:53:34,444][05218] Updated weights for policy 0, policy_version 28382 (0.0011) -[2023-10-16 03:53:37,268][05219] Updated weights for policy 1, policy_version 28290 (0.0008) -[2023-10-16 03:53:37,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 58032128. Throughput: 0: 1794.3, 1: 1807.5. Samples: 14525254. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:53:37,351][03835] Avg episode reward: [(0, '5.840'), (1, '5.660')] -[2023-10-16 03:53:37,361][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000028384_29065216.pth... -[2023-10-16 03:53:37,399][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000026720_27361280.pth -[2023-10-16 03:53:37,641][05219] Updated weights for policy 1, policy_version 28300 (0.0008) -[2023-10-16 03:53:37,997][05219] Updated weights for policy 1, policy_version 28310 (0.0008) -[2023-10-16 03:53:38,051][05218] Updated weights for policy 0, policy_version 28392 (0.0007) -[2023-10-16 03:53:38,357][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000028320_28999680.pth... -[2023-10-16 03:53:38,358][05219] Updated weights for policy 1, policy_version 28320 (0.0007) -[2023-10-16 03:53:38,387][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000026624_27262976.pth -[2023-10-16 03:53:38,433][05218] Updated weights for policy 0, policy_version 28402 (0.0008) -[2023-10-16 03:53:38,808][05218] Updated weights for policy 0, policy_version 28412 (0.0009) -[2023-10-16 03:53:42,175][05219] Updated weights for policy 1, policy_version 28330 (0.0009) -[2023-10-16 03:53:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 58097664. Throughput: 0: 1789.0, 1: 1786.3. Samples: 14534948. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:53:42,351][03835] Avg episode reward: [(0, '5.520'), (1, '5.550')] -[2023-10-16 03:53:42,526][05219] Updated weights for policy 1, policy_version 28340 (0.0008) -[2023-10-16 03:53:42,554][05218] Updated weights for policy 0, policy_version 28422 (0.0008) -[2023-10-16 03:53:42,896][05219] Updated weights for policy 1, policy_version 28350 (0.0008) -[2023-10-16 03:53:42,934][05218] Updated weights for policy 0, policy_version 28432 (0.0008) -[2023-10-16 03:53:43,304][05218] Updated weights for policy 0, policy_version 28442 (0.0010) -[2023-10-16 03:53:46,762][05219] Updated weights for policy 1, policy_version 28360 (0.0008) -[2023-10-16 03:53:47,128][05219] Updated weights for policy 1, policy_version 28370 (0.0008) -[2023-10-16 03:53:47,168][05218] Updated weights for policy 0, policy_version 28452 (0.0009) -[2023-10-16 03:53:47,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 58163200. Throughput: 0: 1787.0, 1: 1796.1. Samples: 14557020. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:53:47,351][03835] Avg episode reward: [(0, '6.290'), (1, '5.400')] -[2023-10-16 03:53:47,494][05219] Updated weights for policy 1, policy_version 28380 (0.0007) -[2023-10-16 03:53:47,543][05218] Updated weights for policy 0, policy_version 28462 (0.0008) -[2023-10-16 03:53:47,922][05218] Updated weights for policy 0, policy_version 28472 (0.0009) -[2023-10-16 03:53:51,378][05219] Updated weights for policy 1, policy_version 28390 (0.0008) -[2023-10-16 03:53:51,643][05218] Updated weights for policy 0, policy_version 28482 (0.0009) -[2023-10-16 03:53:51,748][05219] Updated weights for policy 1, policy_version 28400 (0.0009) -[2023-10-16 03:53:52,020][05218] Updated weights for policy 0, policy_version 28492 (0.0007) -[2023-10-16 03:53:52,099][05219] Updated weights for policy 1, policy_version 28410 (0.0007) -[2023-10-16 03:53:52,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 58261504. Throughput: 0: 1789.9, 1: 1779.0. Samples: 14576926. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:53:52,352][03835] Avg episode reward: [(0, '6.220'), (1, '5.650')] -[2023-10-16 03:53:52,395][05218] Updated weights for policy 0, policy_version 28502 (0.0008) -[2023-10-16 03:53:52,768][05218] Updated weights for policy 0, policy_version 28512 (0.0008) -[2023-10-16 03:53:55,850][05219] Updated weights for policy 1, policy_version 28420 (0.0008) -[2023-10-16 03:53:56,209][05219] Updated weights for policy 1, policy_version 28430 (0.0010) -[2023-10-16 03:53:56,536][05218] Updated weights for policy 0, policy_version 28522 (0.0008) -[2023-10-16 03:53:56,576][05219] Updated weights for policy 1, policy_version 28440 (0.0008) -[2023-10-16 03:53:56,916][05218] Updated weights for policy 0, policy_version 28532 (0.0009) -[2023-10-16 03:53:57,299][05218] Updated weights for policy 0, policy_version 28542 (0.0008) -[2023-10-16 03:53:57,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 58327040. Throughput: 0: 1776.4, 1: 1789.6. Samples: 14588858. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:53:57,351][03835] Avg episode reward: [(0, '5.330'), (1, '6.350')] -[2023-10-16 03:53:57,353][04891] Saving new best policy, reward=6.350! -[2023-10-16 03:54:00,339][05219] Updated weights for policy 1, policy_version 28450 (0.0008) -[2023-10-16 03:54:00,708][05219] Updated weights for policy 1, policy_version 28460 (0.0007) -[2023-10-16 03:54:00,989][05218] Updated weights for policy 0, policy_version 28552 (0.0007) -[2023-10-16 03:54:01,070][05219] Updated weights for policy 1, policy_version 28470 (0.0008) -[2023-10-16 03:54:01,355][05218] Updated weights for policy 0, policy_version 28562 (0.0011) -[2023-10-16 03:54:01,427][05219] Updated weights for policy 1, policy_version 28480 (0.0008) -[2023-10-16 03:54:01,737][05218] Updated weights for policy 0, policy_version 28572 (0.0008) -[2023-10-16 03:54:02,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 58425344. Throughput: 0: 1788.5, 1: 1783.9. Samples: 14609372. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:54:02,351][03835] Avg episode reward: [(0, '5.720'), (1, '5.390')] -[2023-10-16 03:54:05,175][05219] Updated weights for policy 1, policy_version 28490 (0.0008) -[2023-10-16 03:54:05,436][05218] Updated weights for policy 0, policy_version 28582 (0.0008) -[2023-10-16 03:54:05,530][05219] Updated weights for policy 1, policy_version 28500 (0.0009) -[2023-10-16 03:54:05,808][05218] Updated weights for policy 0, policy_version 28592 (0.0009) -[2023-10-16 03:54:05,898][05219] Updated weights for policy 1, policy_version 28510 (0.0009) -[2023-10-16 03:54:06,188][05218] Updated weights for policy 0, policy_version 28602 (0.0008) -[2023-10-16 03:54:07,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 58490880. Throughput: 0: 1770.0, 1: 1786.0. Samples: 14630684. Policy #0 lag: (min: 17.0, avg: 25.0, max: 49.0) -[2023-10-16 03:54:07,351][03835] Avg episode reward: [(0, '5.700'), (1, '5.400')] -[2023-10-16 03:54:09,779][05219] Updated weights for policy 1, policy_version 28520 (0.0008) -[2023-10-16 03:54:10,057][05218] Updated weights for policy 0, policy_version 28612 (0.0008) -[2023-10-16 03:54:10,145][05219] Updated weights for policy 1, policy_version 28530 (0.0008) -[2023-10-16 03:54:10,455][05218] Updated weights for policy 0, policy_version 28622 (0.0009) -[2023-10-16 03:54:10,508][05219] Updated weights for policy 1, policy_version 28540 (0.0009) -[2023-10-16 03:54:10,817][05218] Updated weights for policy 0, policy_version 28632 (0.0009) -[2023-10-16 03:54:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 58556416. Throughput: 0: 1797.1, 1: 1796.7. Samples: 14641912. Policy #0 lag: (min: 17.0, avg: 25.0, max: 49.0) -[2023-10-16 03:54:12,351][03835] Avg episode reward: [(0, '5.880'), (1, '5.780')] -[2023-10-16 03:54:14,270][05219] Updated weights for policy 1, policy_version 28550 (0.0009) -[2023-10-16 03:54:14,549][05218] Updated weights for policy 0, policy_version 28642 (0.0007) -[2023-10-16 03:54:14,637][05219] Updated weights for policy 1, policy_version 28560 (0.0009) -[2023-10-16 03:54:14,934][05218] Updated weights for policy 0, policy_version 28652 (0.0007) -[2023-10-16 03:54:14,998][05219] Updated weights for policy 1, policy_version 28570 (0.0008) -[2023-10-16 03:54:15,294][05218] Updated weights for policy 0, policy_version 28662 (0.0007) -[2023-10-16 03:54:15,664][05218] Updated weights for policy 0, policy_version 28672 (0.0010) -[2023-10-16 03:54:17,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 58621952. Throughput: 0: 1780.8, 1: 1773.8. Samples: 14662552. Policy #0 lag: (min: 17.0, avg: 25.0, max: 49.0) -[2023-10-16 03:54:17,351][03835] Avg episode reward: [(0, '5.350'), (1, '5.610')] -[2023-10-16 03:54:18,711][05219] Updated weights for policy 1, policy_version 28580 (0.0008) -[2023-10-16 03:54:19,082][05219] Updated weights for policy 1, policy_version 28590 (0.0011) -[2023-10-16 03:54:19,441][05219] Updated weights for policy 1, policy_version 28600 (0.0008) -[2023-10-16 03:54:19,451][05218] Updated weights for policy 0, policy_version 28682 (0.0008) -[2023-10-16 03:54:19,830][05218] Updated weights for policy 0, policy_version 28692 (0.0010) -[2023-10-16 03:54:20,198][05218] Updated weights for policy 0, policy_version 28702 (0.0009) -[2023-10-16 03:54:22,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 58687488. Throughput: 0: 1780.7, 1: 1772.3. Samples: 14685136. Policy #0 lag: (min: 17.0, avg: 25.0, max: 49.0) -[2023-10-16 03:54:22,351][03835] Avg episode reward: [(0, '5.410'), (1, '5.750')] -[2023-10-16 03:54:23,441][05219] Updated weights for policy 1, policy_version 28610 (0.0008) -[2023-10-16 03:54:23,801][05219] Updated weights for policy 1, policy_version 28620 (0.0007) -[2023-10-16 03:54:23,855][05218] Updated weights for policy 0, policy_version 28712 (0.0008) -[2023-10-16 03:54:24,171][05219] Updated weights for policy 1, policy_version 28630 (0.0008) -[2023-10-16 03:54:24,220][05218] Updated weights for policy 0, policy_version 28722 (0.0007) -[2023-10-16 03:54:24,529][05219] Updated weights for policy 1, policy_version 28640 (0.0007) -[2023-10-16 03:54:24,598][05218] Updated weights for policy 0, policy_version 28732 (0.0009) -[2023-10-16 03:54:27,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 58753024. Throughput: 0: 1782.2, 1: 1775.5. Samples: 14695044. Policy #0 lag: (min: 17.0, avg: 25.0, max: 49.0) -[2023-10-16 03:54:27,351][03835] Avg episode reward: [(0, '4.890'), (1, '5.970')] -[2023-10-16 03:54:28,224][05219] Updated weights for policy 1, policy_version 28650 (0.0008) -[2023-10-16 03:54:28,324][05218] Updated weights for policy 0, policy_version 28742 (0.0010) -[2023-10-16 03:54:28,594][05219] Updated weights for policy 1, policy_version 28660 (0.0008) -[2023-10-16 03:54:28,694][05218] Updated weights for policy 0, policy_version 28752 (0.0009) -[2023-10-16 03:54:28,949][05219] Updated weights for policy 1, policy_version 28670 (0.0007) -[2023-10-16 03:54:29,065][05218] Updated weights for policy 0, policy_version 28762 (0.0007) -[2023-10-16 03:54:32,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 58818560. Throughput: 0: 1784.4, 1: 1780.5. Samples: 14717440. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-16 03:54:32,351][03835] Avg episode reward: [(0, '5.720'), (1, '5.510')] -[2023-10-16 03:54:32,725][05219] Updated weights for policy 1, policy_version 28680 (0.0008) -[2023-10-16 03:54:32,916][05218] Updated weights for policy 0, policy_version 28772 (0.0009) -[2023-10-16 03:54:33,089][05219] Updated weights for policy 1, policy_version 28690 (0.0009) -[2023-10-16 03:54:33,295][05218] Updated weights for policy 0, policy_version 28782 (0.0008) -[2023-10-16 03:54:33,452][05219] Updated weights for policy 1, policy_version 28700 (0.0009) -[2023-10-16 03:54:33,663][05218] Updated weights for policy 0, policy_version 28792 (0.0008) -[2023-10-16 03:54:37,285][05219] Updated weights for policy 1, policy_version 28710 (0.0008) -[2023-10-16 03:54:37,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 58884096. Throughput: 0: 1804.4, 1: 1808.5. Samples: 14739508. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-16 03:54:37,351][03835] Avg episode reward: [(0, '6.070'), (1, '6.470')] -[2023-10-16 03:54:37,506][05218] Updated weights for policy 0, policy_version 28802 (0.0007) -[2023-10-16 03:54:37,647][05219] Updated weights for policy 1, policy_version 28720 (0.0007) -[2023-10-16 03:54:37,881][05218] Updated weights for policy 0, policy_version 28812 (0.0007) -[2023-10-16 03:54:38,016][05219] Updated weights for policy 1, policy_version 28730 (0.0008) -[2023-10-16 03:54:38,226][04891] Saving new best policy, reward=6.470! -[2023-10-16 03:54:38,262][05218] Updated weights for policy 0, policy_version 28822 (0.0007) -[2023-10-16 03:54:38,628][05218] Updated weights for policy 0, policy_version 28832 (0.0007) -[2023-10-16 03:54:41,806][05219] Updated weights for policy 1, policy_version 28740 (0.0010) -[2023-10-16 03:54:42,181][05219] Updated weights for policy 1, policy_version 28750 (0.0010) -[2023-10-16 03:54:42,334][05218] Updated weights for policy 0, policy_version 28842 (0.0008) -[2023-10-16 03:54:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 58949632. Throughput: 0: 1784.5, 1: 1782.5. Samples: 14749372. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-16 03:54:42,351][03835] Avg episode reward: [(0, '5.990'), (1, '6.190')] -[2023-10-16 03:54:42,541][05219] Updated weights for policy 1, policy_version 28760 (0.0009) -[2023-10-16 03:54:42,712][05218] Updated weights for policy 0, policy_version 28852 (0.0008) -[2023-10-16 03:54:43,085][05218] Updated weights for policy 0, policy_version 28862 (0.0008) -[2023-10-16 03:54:46,420][05219] Updated weights for policy 1, policy_version 28770 (0.0007) -[2023-10-16 03:54:46,688][05218] Updated weights for policy 0, policy_version 28872 (0.0008) -[2023-10-16 03:54:46,781][05219] Updated weights for policy 1, policy_version 28780 (0.0009) -[2023-10-16 03:54:47,057][05218] Updated weights for policy 0, policy_version 28882 (0.0008) -[2023-10-16 03:54:47,159][05219] Updated weights for policy 1, policy_version 28790 (0.0009) -[2023-10-16 03:54:47,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 59015168. Throughput: 0: 1808.9, 1: 1798.1. Samples: 14771688. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-16 03:54:47,351][03835] Avg episode reward: [(0, '5.680'), (1, '6.070')] -[2023-10-16 03:54:47,441][05218] Updated weights for policy 0, policy_version 28892 (0.0009) -[2023-10-16 03:54:47,516][05219] Updated weights for policy 1, policy_version 28800 (0.0008) -[2023-10-16 03:54:51,167][05218] Updated weights for policy 0, policy_version 28902 (0.0008) -[2023-10-16 03:54:51,415][05219] Updated weights for policy 1, policy_version 28810 (0.0008) -[2023-10-16 03:54:51,534][05218] Updated weights for policy 0, policy_version 28912 (0.0007) -[2023-10-16 03:54:51,785][05219] Updated weights for policy 1, policy_version 28820 (0.0007) -[2023-10-16 03:54:51,912][05218] Updated weights for policy 0, policy_version 28922 (0.0007) -[2023-10-16 03:54:52,156][05219] Updated weights for policy 1, policy_version 28830 (0.0007) -[2023-10-16 03:54:52,350][03835] Fps is (10 sec: 19660.5, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 59146240. Throughput: 0: 1791.9, 1: 1770.5. Samples: 14790990. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:54:52,351][03835] Avg episode reward: [(0, '5.320'), (1, '5.970')] -[2023-10-16 03:54:55,725][05218] Updated weights for policy 0, policy_version 28932 (0.0008) -[2023-10-16 03:54:55,887][05219] Updated weights for policy 1, policy_version 28840 (0.0009) -[2023-10-16 03:54:56,108][05218] Updated weights for policy 0, policy_version 28942 (0.0009) -[2023-10-16 03:54:56,258][05219] Updated weights for policy 1, policy_version 28850 (0.0008) -[2023-10-16 03:54:56,488][05218] Updated weights for policy 0, policy_version 28952 (0.0009) -[2023-10-16 03:54:56,631][05219] Updated weights for policy 1, policy_version 28860 (0.0009) -[2023-10-16 03:54:57,350][03835] Fps is (10 sec: 19660.4, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 59211776. Throughput: 0: 1805.1, 1: 1789.4. Samples: 14803664. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:54:57,351][03835] Avg episode reward: [(0, '5.820'), (1, '5.740')] -[2023-10-16 03:55:00,353][05219] Updated weights for policy 1, policy_version 28870 (0.0007) -[2023-10-16 03:55:00,379][05218] Updated weights for policy 0, policy_version 28962 (0.0009) -[2023-10-16 03:55:00,725][05219] Updated weights for policy 1, policy_version 28880 (0.0008) -[2023-10-16 03:55:00,751][05218] Updated weights for policy 0, policy_version 28972 (0.0008) -[2023-10-16 03:55:01,088][05219] Updated weights for policy 1, policy_version 28890 (0.0008) -[2023-10-16 03:55:01,127][05218] Updated weights for policy 0, policy_version 28982 (0.0007) -[2023-10-16 03:55:01,506][05218] Updated weights for policy 0, policy_version 28992 (0.0007) -[2023-10-16 03:55:02,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 59277312. Throughput: 0: 1794.5, 1: 1778.4. Samples: 14823330. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:55:02,351][03835] Avg episode reward: [(0, '5.510'), (1, '5.610')] -[2023-10-16 03:55:04,657][05219] Updated weights for policy 1, policy_version 28900 (0.0007) -[2023-10-16 03:55:05,017][05219] Updated weights for policy 1, policy_version 28910 (0.0008) -[2023-10-16 03:55:05,216][05218] Updated weights for policy 0, policy_version 29002 (0.0009) -[2023-10-16 03:55:05,381][05219] Updated weights for policy 1, policy_version 28920 (0.0007) -[2023-10-16 03:55:05,591][05218] Updated weights for policy 0, policy_version 29012 (0.0009) -[2023-10-16 03:55:05,974][05218] Updated weights for policy 0, policy_version 29022 (0.0007) -[2023-10-16 03:55:07,351][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 59342848. Throughput: 0: 1787.9, 1: 1773.8. Samples: 14845412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:55:07,352][03835] Avg episode reward: [(0, '6.150'), (1, '5.790')] -[2023-10-16 03:55:09,229][05219] Updated weights for policy 1, policy_version 28930 (0.0008) -[2023-10-16 03:55:09,593][05219] Updated weights for policy 1, policy_version 28940 (0.0007) -[2023-10-16 03:55:09,768][05218] Updated weights for policy 0, policy_version 29032 (0.0007) -[2023-10-16 03:55:09,950][05219] Updated weights for policy 1, policy_version 28950 (0.0007) -[2023-10-16 03:55:10,147][05218] Updated weights for policy 0, policy_version 29042 (0.0010) -[2023-10-16 03:55:10,321][05219] Updated weights for policy 1, policy_version 28960 (0.0008) -[2023-10-16 03:55:10,520][05218] Updated weights for policy 0, policy_version 29052 (0.0008) -[2023-10-16 03:55:12,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 59408384. Throughput: 0: 1794.1, 1: 1778.3. Samples: 14855804. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:55:12,352][03835] Avg episode reward: [(0, '6.410'), (1, '5.530')] -[2023-10-16 03:55:14,159][05219] Updated weights for policy 1, policy_version 28970 (0.0008) -[2023-10-16 03:55:14,271][05218] Updated weights for policy 0, policy_version 29062 (0.0010) -[2023-10-16 03:55:14,523][05219] Updated weights for policy 1, policy_version 28980 (0.0007) -[2023-10-16 03:55:14,651][05218] Updated weights for policy 0, policy_version 29072 (0.0008) -[2023-10-16 03:55:14,892][05219] Updated weights for policy 1, policy_version 28990 (0.0007) -[2023-10-16 03:55:15,026][05218] Updated weights for policy 0, policy_version 29082 (0.0007) -[2023-10-16 03:55:17,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 59473920. Throughput: 0: 1782.3, 1: 1762.3. Samples: 14876948. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-16 03:55:17,351][03835] Avg episode reward: [(0, '5.660'), (1, '5.770')] -[2023-10-16 03:55:18,747][05219] Updated weights for policy 1, policy_version 29000 (0.0008) -[2023-10-16 03:55:18,794][05218] Updated weights for policy 0, policy_version 29092 (0.0007) -[2023-10-16 03:55:19,104][05219] Updated weights for policy 1, policy_version 29010 (0.0007) -[2023-10-16 03:55:19,172][05218] Updated weights for policy 0, policy_version 29102 (0.0008) -[2023-10-16 03:55:19,470][05219] Updated weights for policy 1, policy_version 29020 (0.0009) -[2023-10-16 03:55:19,542][05218] Updated weights for policy 0, policy_version 29112 (0.0008) -[2023-10-16 03:55:22,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 59539456. Throughput: 0: 1783.1, 1: 1764.9. Samples: 14899168. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-16 03:55:22,351][03835] Avg episode reward: [(0, '5.810'), (1, '5.050')] -[2023-10-16 03:55:23,311][05219] Updated weights for policy 1, policy_version 29030 (0.0008) -[2023-10-16 03:55:23,364][05218] Updated weights for policy 0, policy_version 29122 (0.0008) -[2023-10-16 03:55:23,687][05219] Updated weights for policy 1, policy_version 29040 (0.0009) -[2023-10-16 03:55:23,745][05218] Updated weights for policy 0, policy_version 29132 (0.0009) -[2023-10-16 03:55:24,046][05219] Updated weights for policy 1, policy_version 29050 (0.0008) -[2023-10-16 03:55:24,117][05218] Updated weights for policy 0, policy_version 29142 (0.0009) -[2023-10-16 03:55:24,479][05218] Updated weights for policy 0, policy_version 29152 (0.0008) -[2023-10-16 03:55:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 59604992. Throughput: 0: 1781.8, 1: 1761.3. Samples: 14908812. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-16 03:55:27,351][03835] Avg episode reward: [(0, '5.700'), (1, '5.100')] -[2023-10-16 03:55:27,778][05219] Updated weights for policy 1, policy_version 29060 (0.0008) -[2023-10-16 03:55:28,149][05219] Updated weights for policy 1, policy_version 29070 (0.0008) -[2023-10-16 03:55:28,221][05218] Updated weights for policy 0, policy_version 29162 (0.0007) -[2023-10-16 03:55:28,516][05219] Updated weights for policy 1, policy_version 29080 (0.0010) -[2023-10-16 03:55:28,609][05218] Updated weights for policy 0, policy_version 29172 (0.0008) -[2023-10-16 03:55:28,988][05218] Updated weights for policy 0, policy_version 29182 (0.0007) -[2023-10-16 03:55:32,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 59670528. Throughput: 0: 1772.4, 1: 1767.8. Samples: 14931000. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-16 03:55:32,351][03835] Avg episode reward: [(0, '5.090'), (1, '5.210')] -[2023-10-16 03:55:32,371][05219] Updated weights for policy 1, policy_version 29090 (0.0008) -[2023-10-16 03:55:32,745][05219] Updated weights for policy 1, policy_version 29100 (0.0008) -[2023-10-16 03:55:32,852][05218] Updated weights for policy 0, policy_version 29192 (0.0008) -[2023-10-16 03:55:33,106][05219] Updated weights for policy 1, policy_version 29110 (0.0009) -[2023-10-16 03:55:33,214][05218] Updated weights for policy 0, policy_version 29202 (0.0010) -[2023-10-16 03:55:33,471][05219] Updated weights for policy 1, policy_version 29120 (0.0008) -[2023-10-16 03:55:33,584][05218] Updated weights for policy 0, policy_version 29212 (0.0009) -[2023-10-16 03:55:37,283][05219] Updated weights for policy 1, policy_version 29130 (0.0010) -[2023-10-16 03:55:37,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 59736064. Throughput: 0: 1797.3, 1: 1797.1. Samples: 14952736. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-16 03:55:37,351][03835] Avg episode reward: [(0, '5.690'), (1, '5.550')] -[2023-10-16 03:55:37,437][05218] Updated weights for policy 0, policy_version 29222 (0.0007) -[2023-10-16 03:55:37,647][05219] Updated weights for policy 1, policy_version 29140 (0.0007) -[2023-10-16 03:55:37,807][05218] Updated weights for policy 0, policy_version 29232 (0.0007) -[2023-10-16 03:55:38,016][05219] Updated weights for policy 1, policy_version 29150 (0.0007) -[2023-10-16 03:55:38,083][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000029152_29851648.pth... -[2023-10-16 03:55:38,111][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000027456_28114944.pth -[2023-10-16 03:55:38,182][05218] Updated weights for policy 0, policy_version 29242 (0.0009) -[2023-10-16 03:55:38,412][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000029248_29949952.pth... -[2023-10-16 03:55:38,442][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000027552_28213248.pth -[2023-10-16 03:55:41,939][05219] Updated weights for policy 1, policy_version 29160 (0.0008) -[2023-10-16 03:55:42,080][05218] Updated weights for policy 0, policy_version 29252 (0.0008) -[2023-10-16 03:55:42,301][05219] Updated weights for policy 1, policy_version 29170 (0.0008) -[2023-10-16 03:55:42,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 59801600. Throughput: 0: 1763.6, 1: 1771.2. Samples: 14962730. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) -[2023-10-16 03:55:42,351][03835] Avg episode reward: [(0, '5.280'), (1, '5.880')] -[2023-10-16 03:55:42,453][05218] Updated weights for policy 0, policy_version 29262 (0.0007) -[2023-10-16 03:55:42,669][05219] Updated weights for policy 1, policy_version 29180 (0.0009) -[2023-10-16 03:55:42,829][05218] Updated weights for policy 0, policy_version 29272 (0.0009) -[2023-10-16 03:55:46,421][05219] Updated weights for policy 1, policy_version 29190 (0.0009) -[2023-10-16 03:55:46,643][05218] Updated weights for policy 0, policy_version 29282 (0.0007) -[2023-10-16 03:55:46,798][05219] Updated weights for policy 1, policy_version 29200 (0.0009) -[2023-10-16 03:55:47,019][05218] Updated weights for policy 0, policy_version 29292 (0.0008) -[2023-10-16 03:55:47,159][05219] Updated weights for policy 1, policy_version 29210 (0.0009) -[2023-10-16 03:55:47,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 59867136. Throughput: 0: 1790.9, 1: 1797.0. Samples: 14984786. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) -[2023-10-16 03:55:47,351][03835] Avg episode reward: [(0, '5.540'), (1, '5.570')] -[2023-10-16 03:55:47,390][05218] Updated weights for policy 0, policy_version 29302 (0.0010) -[2023-10-16 03:55:47,764][05218] Updated weights for policy 0, policy_version 29312 (0.0010) -[2023-10-16 03:55:50,790][05219] Updated weights for policy 1, policy_version 29220 (0.0008) -[2023-10-16 03:55:51,146][05219] Updated weights for policy 1, policy_version 29230 (0.0008) -[2023-10-16 03:55:51,504][05218] Updated weights for policy 0, policy_version 29322 (0.0009) -[2023-10-16 03:55:51,513][05219] Updated weights for policy 1, policy_version 29240 (0.0009) -[2023-10-16 03:55:51,882][05218] Updated weights for policy 0, policy_version 29332 (0.0007) -[2023-10-16 03:55:52,262][05218] Updated weights for policy 0, policy_version 29342 (0.0011) -[2023-10-16 03:55:52,351][03835] Fps is (10 sec: 19660.5, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 59998208. Throughput: 0: 1759.2, 1: 1771.0. Samples: 15004274. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) -[2023-10-16 03:55:52,352][03835] Avg episode reward: [(0, '5.770'), (1, '5.210')] -[2023-10-16 03:55:55,506][05219] Updated weights for policy 1, policy_version 29250 (0.0009) -[2023-10-16 03:55:55,875][05219] Updated weights for policy 1, policy_version 29260 (0.0007) -[2023-10-16 03:55:55,888][05218] Updated weights for policy 0, policy_version 29352 (0.0009) -[2023-10-16 03:55:56,245][05219] Updated weights for policy 1, policy_version 29270 (0.0007) -[2023-10-16 03:55:56,261][05218] Updated weights for policy 0, policy_version 29362 (0.0008) -[2023-10-16 03:55:56,599][05219] Updated weights for policy 1, policy_version 29280 (0.0007) -[2023-10-16 03:55:56,636][05218] Updated weights for policy 0, policy_version 29372 (0.0008) -[2023-10-16 03:55:57,350][03835] Fps is (10 sec: 19660.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 60063744. Throughput: 0: 1783.1, 1: 1795.3. Samples: 15016832. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) -[2023-10-16 03:55:57,351][03835] Avg episode reward: [(0, '5.680'), (1, '5.420')] -[2023-10-16 03:56:00,404][05219] Updated weights for policy 1, policy_version 29290 (0.0008) -[2023-10-16 03:56:00,421][05218] Updated weights for policy 0, policy_version 29382 (0.0009) -[2023-10-16 03:56:00,776][05219] Updated weights for policy 1, policy_version 29300 (0.0008) -[2023-10-16 03:56:00,797][05218] Updated weights for policy 0, policy_version 29392 (0.0008) -[2023-10-16 03:56:01,132][05219] Updated weights for policy 1, policy_version 29310 (0.0008) -[2023-10-16 03:56:01,166][05218] Updated weights for policy 0, policy_version 29402 (0.0007) -[2023-10-16 03:56:02,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 60129280. Throughput: 0: 1763.3, 1: 1783.6. Samples: 15036558. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-16 03:56:02,351][03835] Avg episode reward: [(0, '5.550'), (1, '5.640')] -[2023-10-16 03:56:04,783][05219] Updated weights for policy 1, policy_version 29320 (0.0008) -[2023-10-16 03:56:04,888][05218] Updated weights for policy 0, policy_version 29412 (0.0008) -[2023-10-16 03:56:05,160][05219] Updated weights for policy 1, policy_version 29330 (0.0008) -[2023-10-16 03:56:05,269][05218] Updated weights for policy 0, policy_version 29422 (0.0007) -[2023-10-16 03:56:05,524][05219] Updated weights for policy 1, policy_version 29340 (0.0009) -[2023-10-16 03:56:05,641][05218] Updated weights for policy 0, policy_version 29432 (0.0008) -[2023-10-16 03:56:07,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.6, 300 sec: 14329.1). Total num frames: 60194816. Throughput: 0: 1761.9, 1: 1776.4. Samples: 15058392. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-16 03:56:07,351][03835] Avg episode reward: [(0, '5.000'), (1, '5.890')] -[2023-10-16 03:56:09,361][05219] Updated weights for policy 1, policy_version 29350 (0.0008) -[2023-10-16 03:56:09,364][05218] Updated weights for policy 0, policy_version 29442 (0.0009) -[2023-10-16 03:56:09,725][05219] Updated weights for policy 1, policy_version 29360 (0.0009) -[2023-10-16 03:56:09,735][05218] Updated weights for policy 0, policy_version 29452 (0.0010) -[2023-10-16 03:56:10,076][05219] Updated weights for policy 1, policy_version 29370 (0.0008) -[2023-10-16 03:56:10,115][05218] Updated weights for policy 0, policy_version 29462 (0.0008) -[2023-10-16 03:56:10,483][05218] Updated weights for policy 0, policy_version 29472 (0.0009) -[2023-10-16 03:56:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 60260352. Throughput: 0: 1769.0, 1: 1784.1. Samples: 15068702. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-16 03:56:12,351][03835] Avg episode reward: [(0, '5.500'), (1, '5.420')] -[2023-10-16 03:56:13,795][05219] Updated weights for policy 1, policy_version 29380 (0.0009) -[2023-10-16 03:56:14,175][05219] Updated weights for policy 1, policy_version 29390 (0.0009) -[2023-10-16 03:56:14,176][05218] Updated weights for policy 0, policy_version 29482 (0.0009) -[2023-10-16 03:56:14,547][05219] Updated weights for policy 1, policy_version 29400 (0.0008) -[2023-10-16 03:56:14,548][05218] Updated weights for policy 0, policy_version 29492 (0.0008) -[2023-10-16 03:56:14,928][05218] Updated weights for policy 0, policy_version 29502 (0.0007) -[2023-10-16 03:56:17,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 60325888. Throughput: 0: 1773.7, 1: 1780.7. Samples: 15090946. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-16 03:56:17,351][03835] Avg episode reward: [(0, '5.810'), (1, '5.540')] -[2023-10-16 03:56:18,398][05219] Updated weights for policy 1, policy_version 29410 (0.0008) -[2023-10-16 03:56:18,615][05218] Updated weights for policy 0, policy_version 29512 (0.0008) -[2023-10-16 03:56:18,759][05219] Updated weights for policy 1, policy_version 29420 (0.0007) -[2023-10-16 03:56:18,989][05218] Updated weights for policy 0, policy_version 29522 (0.0008) -[2023-10-16 03:56:19,124][05219] Updated weights for policy 1, policy_version 29430 (0.0007) -[2023-10-16 03:56:19,364][05218] Updated weights for policy 0, policy_version 29532 (0.0007) -[2023-10-16 03:56:19,482][05219] Updated weights for policy 1, policy_version 29440 (0.0009) -[2023-10-16 03:56:22,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 60391424. Throughput: 0: 1783.1, 1: 1780.4. Samples: 15113096. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-16 03:56:22,352][03835] Avg episode reward: [(0, '5.960'), (1, '5.730')] -[2023-10-16 03:56:23,165][05218] Updated weights for policy 0, policy_version 29542 (0.0009) -[2023-10-16 03:56:23,270][05219] Updated weights for policy 1, policy_version 29450 (0.0008) -[2023-10-16 03:56:23,543][05218] Updated weights for policy 0, policy_version 29552 (0.0008) -[2023-10-16 03:56:23,628][05219] Updated weights for policy 1, policy_version 29460 (0.0008) -[2023-10-16 03:56:23,921][05218] Updated weights for policy 0, policy_version 29562 (0.0008) -[2023-10-16 03:56:24,008][05219] Updated weights for policy 1, policy_version 29470 (0.0009) -[2023-10-16 03:56:27,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 60456960. Throughput: 0: 1781.9, 1: 1773.5. Samples: 15122724. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-16 03:56:27,351][03835] Avg episode reward: [(0, '6.030'), (1, '6.370')] -[2023-10-16 03:56:27,774][05218] Updated weights for policy 0, policy_version 29572 (0.0009) -[2023-10-16 03:56:27,841][05219] Updated weights for policy 1, policy_version 29480 (0.0009) -[2023-10-16 03:56:28,159][05218] Updated weights for policy 0, policy_version 29582 (0.0009) -[2023-10-16 03:56:28,203][05219] Updated weights for policy 1, policy_version 29490 (0.0007) -[2023-10-16 03:56:28,536][05218] Updated weights for policy 0, policy_version 29592 (0.0009) -[2023-10-16 03:56:28,561][05219] Updated weights for policy 1, policy_version 29500 (0.0008) -[2023-10-16 03:56:32,318][05218] Updated weights for policy 0, policy_version 29602 (0.0009) -[2023-10-16 03:56:32,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 60522496. Throughput: 0: 1787.4, 1: 1772.6. Samples: 15144986. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-16 03:56:32,351][03835] Avg episode reward: [(0, '5.460'), (1, '5.660')] -[2023-10-16 03:56:32,398][05219] Updated weights for policy 1, policy_version 29510 (0.0007) -[2023-10-16 03:56:32,690][05218] Updated weights for policy 0, policy_version 29612 (0.0007) -[2023-10-16 03:56:32,765][05219] Updated weights for policy 1, policy_version 29520 (0.0009) -[2023-10-16 03:56:33,069][05218] Updated weights for policy 0, policy_version 29622 (0.0007) -[2023-10-16 03:56:33,130][05219] Updated weights for policy 1, policy_version 29530 (0.0007) -[2023-10-16 03:56:33,445][05218] Updated weights for policy 0, policy_version 29632 (0.0009) -[2023-10-16 03:56:36,909][05219] Updated weights for policy 1, policy_version 29540 (0.0008) -[2023-10-16 03:56:37,208][05218] Updated weights for policy 0, policy_version 29642 (0.0007) -[2023-10-16 03:56:37,273][05219] Updated weights for policy 1, policy_version 29550 (0.0008) -[2023-10-16 03:56:37,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 60588032. Throughput: 0: 1809.1, 1: 1789.5. Samples: 15166210. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-16 03:56:37,351][03835] Avg episode reward: [(0, '5.210'), (1, '5.890')] -[2023-10-16 03:56:37,585][05218] Updated weights for policy 0, policy_version 29652 (0.0007) -[2023-10-16 03:56:37,642][05219] Updated weights for policy 1, policy_version 29560 (0.0007) -[2023-10-16 03:56:37,970][05218] Updated weights for policy 0, policy_version 29662 (0.0008) -[2023-10-16 03:56:41,409][05219] Updated weights for policy 1, policy_version 29570 (0.0008) -[2023-10-16 03:56:41,747][05218] Updated weights for policy 0, policy_version 29672 (0.0009) -[2023-10-16 03:56:41,776][05219] Updated weights for policy 1, policy_version 29580 (0.0008) -[2023-10-16 03:56:42,126][05218] Updated weights for policy 0, policy_version 29682 (0.0009) -[2023-10-16 03:56:42,143][05219] Updated weights for policy 1, policy_version 29590 (0.0007) -[2023-10-16 03:56:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 60653568. Throughput: 0: 1787.5, 1: 1768.3. Samples: 15176842. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-16 03:56:42,351][03835] Avg episode reward: [(0, '5.220'), (1, '5.520')] -[2023-10-16 03:56:42,493][05218] Updated weights for policy 0, policy_version 29692 (0.0007) -[2023-10-16 03:56:42,503][05219] Updated weights for policy 1, policy_version 29600 (0.0008) -[2023-10-16 03:56:46,295][05218] Updated weights for policy 0, policy_version 29702 (0.0008) -[2023-10-16 03:56:46,435][05219] Updated weights for policy 1, policy_version 29610 (0.0010) -[2023-10-16 03:56:46,673][05218] Updated weights for policy 0, policy_version 29712 (0.0007) -[2023-10-16 03:56:46,803][05219] Updated weights for policy 1, policy_version 29620 (0.0007) -[2023-10-16 03:56:47,042][05218] Updated weights for policy 0, policy_version 29722 (0.0008) -[2023-10-16 03:56:47,169][05219] Updated weights for policy 1, policy_version 29630 (0.0008) -[2023-10-16 03:56:47,350][03835] Fps is (10 sec: 19660.4, 60 sec: 15291.7, 300 sec: 14440.1). Total num frames: 60784640. Throughput: 0: 1814.5, 1: 1792.4. Samples: 15198868. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:56:47,352][03835] Avg episode reward: [(0, '5.530'), (1, '5.900')] -[2023-10-16 03:56:50,870][05218] Updated weights for policy 0, policy_version 29732 (0.0008) -[2023-10-16 03:56:50,968][05219] Updated weights for policy 1, policy_version 29640 (0.0008) -[2023-10-16 03:56:51,246][05218] Updated weights for policy 0, policy_version 29742 (0.0007) -[2023-10-16 03:56:51,326][05219] Updated weights for policy 1, policy_version 29650 (0.0007) -[2023-10-16 03:56:51,622][05218] Updated weights for policy 0, policy_version 29752 (0.0009) -[2023-10-16 03:56:51,693][05219] Updated weights for policy 1, policy_version 29660 (0.0009) -[2023-10-16 03:56:52,350][03835] Fps is (10 sec: 19660.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 60850176. Throughput: 0: 1788.9, 1: 1767.5. Samples: 15218428. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:56:52,351][03835] Avg episode reward: [(0, '5.420'), (1, '5.380')] -[2023-10-16 03:56:55,292][05218] Updated weights for policy 0, policy_version 29762 (0.0008) -[2023-10-16 03:56:55,505][05219] Updated weights for policy 1, policy_version 29670 (0.0007) -[2023-10-16 03:56:55,668][05218] Updated weights for policy 0, policy_version 29772 (0.0008) -[2023-10-16 03:56:55,882][05219] Updated weights for policy 1, policy_version 29680 (0.0007) -[2023-10-16 03:56:56,033][05218] Updated weights for policy 0, policy_version 29782 (0.0008) -[2023-10-16 03:56:56,247][05219] Updated weights for policy 1, policy_version 29690 (0.0009) -[2023-10-16 03:56:56,410][05218] Updated weights for policy 0, policy_version 29792 (0.0008) -[2023-10-16 03:56:57,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 60915712. Throughput: 0: 1810.9, 1: 1796.0. Samples: 15231012. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:56:57,351][03835] Avg episode reward: [(0, '5.430'), (1, '5.740')] -[2023-10-16 03:57:00,050][05219] Updated weights for policy 1, policy_version 29700 (0.0008) -[2023-10-16 03:57:00,337][05218] Updated weights for policy 0, policy_version 29802 (0.0010) -[2023-10-16 03:57:00,413][05219] Updated weights for policy 1, policy_version 29710 (0.0008) -[2023-10-16 03:57:00,710][05218] Updated weights for policy 0, policy_version 29812 (0.0009) -[2023-10-16 03:57:00,777][05219] Updated weights for policy 1, policy_version 29720 (0.0010) -[2023-10-16 03:57:01,087][05218] Updated weights for policy 0, policy_version 29822 (0.0007) -[2023-10-16 03:57:02,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 60981248. Throughput: 0: 1777.9, 1: 1765.1. Samples: 15250380. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:57:02,351][03835] Avg episode reward: [(0, '5.740'), (1, '5.830')] -[2023-10-16 03:57:04,594][05219] Updated weights for policy 1, policy_version 29730 (0.0008) -[2023-10-16 03:57:04,921][05218] Updated weights for policy 0, policy_version 29832 (0.0010) -[2023-10-16 03:57:04,957][05219] Updated weights for policy 1, policy_version 29740 (0.0009) -[2023-10-16 03:57:05,294][05218] Updated weights for policy 0, policy_version 29842 (0.0008) -[2023-10-16 03:57:05,320][05219] Updated weights for policy 1, policy_version 29750 (0.0007) -[2023-10-16 03:57:05,670][05218] Updated weights for policy 0, policy_version 29852 (0.0007) -[2023-10-16 03:57:05,683][05219] Updated weights for policy 1, policy_version 29760 (0.0008) -[2023-10-16 03:57:07,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 61046784. Throughput: 0: 1777.9, 1: 1765.9. Samples: 15272566. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:57:07,352][03835] Avg episode reward: [(0, '5.450'), (1, '5.480')] -[2023-10-16 03:57:09,360][05218] Updated weights for policy 0, policy_version 29862 (0.0008) -[2023-10-16 03:57:09,432][05219] Updated weights for policy 1, policy_version 29770 (0.0007) -[2023-10-16 03:57:09,728][05218] Updated weights for policy 0, policy_version 29872 (0.0008) -[2023-10-16 03:57:09,796][05219] Updated weights for policy 1, policy_version 29780 (0.0010) -[2023-10-16 03:57:10,107][05218] Updated weights for policy 0, policy_version 29882 (0.0009) -[2023-10-16 03:57:10,163][05219] Updated weights for policy 1, policy_version 29790 (0.0008) -[2023-10-16 03:57:12,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 61112320. Throughput: 0: 1780.6, 1: 1773.9. Samples: 15282676. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:57:12,351][03835] Avg episode reward: [(0, '6.170'), (1, '5.890')] -[2023-10-16 03:57:13,529][05218] Updated weights for policy 0, policy_version 29892 (0.0010) -[2023-10-16 03:57:13,902][05218] Updated weights for policy 0, policy_version 29902 (0.0007) -[2023-10-16 03:57:13,914][05219] Updated weights for policy 1, policy_version 29800 (0.0007) -[2023-10-16 03:57:14,275][05218] Updated weights for policy 0, policy_version 29912 (0.0009) -[2023-10-16 03:57:14,288][05219] Updated weights for policy 1, policy_version 29810 (0.0008) -[2023-10-16 03:57:14,655][05219] Updated weights for policy 1, policy_version 29820 (0.0009) -[2023-10-16 03:57:17,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 61177856. Throughput: 0: 1784.4, 1: 1770.2. Samples: 15304940. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:57:17,351][03835] Avg episode reward: [(0, '6.310'), (1, '5.560')] -[2023-10-16 03:57:18,036][05218] Updated weights for policy 0, policy_version 29922 (0.0008) -[2023-10-16 03:57:18,211][05219] Updated weights for policy 1, policy_version 29830 (0.0008) -[2023-10-16 03:57:18,437][05218] Updated weights for policy 0, policy_version 29932 (0.0007) -[2023-10-16 03:57:18,577][05219] Updated weights for policy 1, policy_version 29840 (0.0007) -[2023-10-16 03:57:18,813][05218] Updated weights for policy 0, policy_version 29942 (0.0008) -[2023-10-16 03:57:18,941][05219] Updated weights for policy 1, policy_version 29850 (0.0008) -[2023-10-16 03:57:19,183][05218] Updated weights for policy 0, policy_version 29952 (0.0008) -[2023-10-16 03:57:22,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 61243392. Throughput: 0: 1794.2, 1: 1787.1. Samples: 15327368. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:57:22,351][03835] Avg episode reward: [(0, '6.070'), (1, '5.980')] -[2023-10-16 03:57:22,733][05219] Updated weights for policy 1, policy_version 29860 (0.0008) -[2023-10-16 03:57:23,006][05218] Updated weights for policy 0, policy_version 29962 (0.0009) -[2023-10-16 03:57:23,099][05219] Updated weights for policy 1, policy_version 29870 (0.0008) -[2023-10-16 03:57:23,371][05218] Updated weights for policy 0, policy_version 29972 (0.0009) -[2023-10-16 03:57:23,460][05219] Updated weights for policy 1, policy_version 29880 (0.0007) -[2023-10-16 03:57:23,740][05218] Updated weights for policy 0, policy_version 29982 (0.0009) -[2023-10-16 03:57:27,321][05218] Updated weights for policy 0, policy_version 29992 (0.0007) -[2023-10-16 03:57:27,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 61308928. Throughput: 0: 1783.1, 1: 1779.4. Samples: 15337154. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:57:27,351][03835] Avg episode reward: [(0, '6.210'), (1, '6.200')] -[2023-10-16 03:57:27,426][05219] Updated weights for policy 1, policy_version 29890 (0.0008) -[2023-10-16 03:57:27,695][05218] Updated weights for policy 0, policy_version 30002 (0.0008) -[2023-10-16 03:57:27,794][05219] Updated weights for policy 1, policy_version 29900 (0.0009) -[2023-10-16 03:57:28,072][05218] Updated weights for policy 0, policy_version 30012 (0.0007) -[2023-10-16 03:57:28,161][05219] Updated weights for policy 1, policy_version 29910 (0.0008) -[2023-10-16 03:57:28,532][05219] Updated weights for policy 1, policy_version 29920 (0.0007) -[2023-10-16 03:57:31,916][05218] Updated weights for policy 0, policy_version 30022 (0.0009) -[2023-10-16 03:57:32,295][05218] Updated weights for policy 0, policy_version 30032 (0.0007) -[2023-10-16 03:57:32,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 61374464. Throughput: 0: 1789.7, 1: 1776.1. Samples: 15359326. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:57:32,351][03835] Avg episode reward: [(0, '6.170'), (1, '5.400')] -[2023-10-16 03:57:32,547][05219] Updated weights for policy 1, policy_version 29930 (0.0009) -[2023-10-16 03:57:32,671][05218] Updated weights for policy 0, policy_version 30042 (0.0008) -[2023-10-16 03:57:32,915][05219] Updated weights for policy 1, policy_version 29940 (0.0007) -[2023-10-16 03:57:33,273][05219] Updated weights for policy 1, policy_version 29950 (0.0008) -[2023-10-16 03:57:36,601][05218] Updated weights for policy 0, policy_version 30052 (0.0008) -[2023-10-16 03:57:36,968][05218] Updated weights for policy 0, policy_version 30062 (0.0008) -[2023-10-16 03:57:36,998][05219] Updated weights for policy 1, policy_version 29960 (0.0008) -[2023-10-16 03:57:37,347][05218] Updated weights for policy 0, policy_version 30072 (0.0008) -[2023-10-16 03:57:37,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 61440000. Throughput: 0: 1793.3, 1: 1799.2. Samples: 15380088. Policy #0 lag: (min: 14.0, avg: 14.4, max: 28.0) -[2023-10-16 03:57:37,351][03835] Avg episode reward: [(0, '5.560'), (1, '5.520')] -[2023-10-16 03:57:37,370][05219] Updated weights for policy 1, policy_version 29970 (0.0008) -[2023-10-16 03:57:37,635][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000030080_30801920.pth... -[2023-10-16 03:57:37,673][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000028384_29065216.pth -[2023-10-16 03:57:37,736][05219] Updated weights for policy 1, policy_version 29980 (0.0008) -[2023-10-16 03:57:37,880][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000029984_30703616.pth... -[2023-10-16 03:57:37,912][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000028320_28999680.pth -[2023-10-16 03:57:41,164][05218] Updated weights for policy 0, policy_version 30082 (0.0010) -[2023-10-16 03:57:41,409][05219] Updated weights for policy 1, policy_version 29990 (0.0007) -[2023-10-16 03:57:41,536][05218] Updated weights for policy 0, policy_version 30092 (0.0008) -[2023-10-16 03:57:41,792][05219] Updated weights for policy 1, policy_version 30000 (0.0007) -[2023-10-16 03:57:41,908][05218] Updated weights for policy 0, policy_version 30102 (0.0010) -[2023-10-16 03:57:42,155][05219] Updated weights for policy 1, policy_version 30010 (0.0007) -[2023-10-16 03:57:42,288][05218] Updated weights for policy 0, policy_version 30112 (0.0009) -[2023-10-16 03:57:42,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 61538304. Throughput: 0: 1788.9, 1: 1778.5. Samples: 15391546. Policy #0 lag: (min: 14.0, avg: 14.4, max: 28.0) -[2023-10-16 03:57:42,351][03835] Avg episode reward: [(0, '5.550'), (1, '6.240')] -[2023-10-16 03:57:45,968][05218] Updated weights for policy 0, policy_version 30122 (0.0007) -[2023-10-16 03:57:46,040][05219] Updated weights for policy 1, policy_version 30020 (0.0008) -[2023-10-16 03:57:46,341][05218] Updated weights for policy 0, policy_version 30132 (0.0007) -[2023-10-16 03:57:46,401][05219] Updated weights for policy 1, policy_version 30030 (0.0009) -[2023-10-16 03:57:46,706][05218] Updated weights for policy 0, policy_version 30142 (0.0008) -[2023-10-16 03:57:46,768][05219] Updated weights for policy 1, policy_version 30040 (0.0007) -[2023-10-16 03:57:47,350][03835] Fps is (10 sec: 19660.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 61636608. Throughput: 0: 1800.8, 1: 1801.9. Samples: 15412504. Policy #0 lag: (min: 14.0, avg: 14.4, max: 28.0) -[2023-10-16 03:57:47,352][03835] Avg episode reward: [(0, '6.020'), (1, '5.460')] -[2023-10-16 03:57:50,479][05218] Updated weights for policy 0, policy_version 30152 (0.0010) -[2023-10-16 03:57:50,636][05219] Updated weights for policy 1, policy_version 30050 (0.0010) -[2023-10-16 03:57:50,846][05218] Updated weights for policy 0, policy_version 30162 (0.0010) -[2023-10-16 03:57:51,007][05219] Updated weights for policy 1, policy_version 30060 (0.0007) -[2023-10-16 03:57:51,209][05218] Updated weights for policy 0, policy_version 30172 (0.0007) -[2023-10-16 03:57:51,374][05219] Updated weights for policy 1, policy_version 30070 (0.0009) -[2023-10-16 03:57:51,742][05219] Updated weights for policy 1, policy_version 30080 (0.0008) -[2023-10-16 03:57:52,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 61702144. Throughput: 0: 1787.9, 1: 1774.2. Samples: 15432860. Policy #0 lag: (min: 14.0, avg: 14.4, max: 28.0) -[2023-10-16 03:57:52,351][03835] Avg episode reward: [(0, '5.430'), (1, '5.300')] -[2023-10-16 03:57:54,852][05218] Updated weights for policy 0, policy_version 30182 (0.0007) -[2023-10-16 03:57:55,229][05218] Updated weights for policy 0, policy_version 30192 (0.0010) -[2023-10-16 03:57:55,490][05219] Updated weights for policy 1, policy_version 30090 (0.0008) -[2023-10-16 03:57:55,605][05218] Updated weights for policy 0, policy_version 30202 (0.0008) -[2023-10-16 03:57:55,856][05219] Updated weights for policy 1, policy_version 30100 (0.0007) -[2023-10-16 03:57:56,231][05219] Updated weights for policy 1, policy_version 30110 (0.0007) -[2023-10-16 03:57:57,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 61767680. Throughput: 0: 1800.8, 1: 1794.5. Samples: 15444464. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-16 03:57:57,351][03835] Avg episode reward: [(0, '6.530'), (1, '5.960')] -[2023-10-16 03:57:59,390][05218] Updated weights for policy 0, policy_version 30212 (0.0009) -[2023-10-16 03:57:59,763][05218] Updated weights for policy 0, policy_version 30222 (0.0008) -[2023-10-16 03:57:59,979][05219] Updated weights for policy 1, policy_version 30120 (0.0007) -[2023-10-16 03:58:00,142][05218] Updated weights for policy 0, policy_version 30232 (0.0008) -[2023-10-16 03:58:00,351][05219] Updated weights for policy 1, policy_version 30130 (0.0007) -[2023-10-16 03:58:00,711][05219] Updated weights for policy 1, policy_version 30140 (0.0008) -[2023-10-16 03:58:02,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 61833216. Throughput: 0: 1777.9, 1: 1773.6. Samples: 15464758. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-16 03:58:02,351][03835] Avg episode reward: [(0, '5.390'), (1, '5.600')] -[2023-10-16 03:58:04,007][05218] Updated weights for policy 0, policy_version 30242 (0.0008) -[2023-10-16 03:58:04,399][05218] Updated weights for policy 0, policy_version 30252 (0.0009) -[2023-10-16 03:58:04,522][05219] Updated weights for policy 1, policy_version 30150 (0.0008) -[2023-10-16 03:58:04,767][05218] Updated weights for policy 0, policy_version 30262 (0.0007) -[2023-10-16 03:58:04,885][05219] Updated weights for policy 1, policy_version 30160 (0.0007) -[2023-10-16 03:58:05,142][05218] Updated weights for policy 0, policy_version 30272 (0.0007) -[2023-10-16 03:58:05,243][05219] Updated weights for policy 1, policy_version 30170 (0.0009) -[2023-10-16 03:58:07,351][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 61898752. Throughput: 0: 1781.2, 1: 1771.6. Samples: 15487244. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-16 03:58:07,352][03835] Avg episode reward: [(0, '5.260'), (1, '5.730')] -[2023-10-16 03:58:08,935][05218] Updated weights for policy 0, policy_version 30282 (0.0008) -[2023-10-16 03:58:09,024][05219] Updated weights for policy 1, policy_version 30180 (0.0009) -[2023-10-16 03:58:09,305][05218] Updated weights for policy 0, policy_version 30292 (0.0009) -[2023-10-16 03:58:09,392][05219] Updated weights for policy 1, policy_version 30190 (0.0007) -[2023-10-16 03:58:09,679][05218] Updated weights for policy 0, policy_version 30302 (0.0010) -[2023-10-16 03:58:09,755][05219] Updated weights for policy 1, policy_version 30200 (0.0009) -[2023-10-16 03:58:12,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 61964288. Throughput: 0: 1779.3, 1: 1769.2. Samples: 15496840. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-16 03:58:12,352][03835] Avg episode reward: [(0, '6.130'), (1, '5.440')] -[2023-10-16 03:58:13,338][05218] Updated weights for policy 0, policy_version 30312 (0.0009) -[2023-10-16 03:58:13,711][05219] Updated weights for policy 1, policy_version 30210 (0.0009) -[2023-10-16 03:58:13,720][05218] Updated weights for policy 0, policy_version 30322 (0.0010) -[2023-10-16 03:58:14,075][05219] Updated weights for policy 1, policy_version 30220 (0.0010) -[2023-10-16 03:58:14,097][05218] Updated weights for policy 0, policy_version 30332 (0.0008) -[2023-10-16 03:58:14,444][05219] Updated weights for policy 1, policy_version 30230 (0.0010) -[2023-10-16 03:58:14,814][05219] Updated weights for policy 1, policy_version 30240 (0.0008) -[2023-10-16 03:58:17,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 62029824. Throughput: 0: 1780.1, 1: 1766.8. Samples: 15518940. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-16 03:58:17,352][03835] Avg episode reward: [(0, '5.960'), (1, '5.170')] -[2023-10-16 03:58:17,905][05218] Updated weights for policy 0, policy_version 30342 (0.0009) -[2023-10-16 03:58:18,278][05218] Updated weights for policy 0, policy_version 30352 (0.0008) -[2023-10-16 03:58:18,650][05218] Updated weights for policy 0, policy_version 30362 (0.0009) -[2023-10-16 03:58:18,699][05219] Updated weights for policy 1, policy_version 30250 (0.0007) -[2023-10-16 03:58:19,065][05219] Updated weights for policy 1, policy_version 30260 (0.0007) -[2023-10-16 03:58:19,436][05219] Updated weights for policy 1, policy_version 30270 (0.0007) -[2023-10-16 03:58:22,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 62095360. Throughput: 0: 1805.2, 1: 1774.8. Samples: 15541186. Policy #0 lag: (min: 31.0, avg: 33.0, max: 62.0) -[2023-10-16 03:58:22,351][03835] Avg episode reward: [(0, '5.650'), (1, '5.750')] -[2023-10-16 03:58:22,476][05218] Updated weights for policy 0, policy_version 30372 (0.0009) -[2023-10-16 03:58:22,854][05218] Updated weights for policy 0, policy_version 30382 (0.0008) -[2023-10-16 03:58:23,230][05218] Updated weights for policy 0, policy_version 30392 (0.0009) -[2023-10-16 03:58:23,234][05219] Updated weights for policy 1, policy_version 30280 (0.0007) -[2023-10-16 03:58:23,598][05219] Updated weights for policy 1, policy_version 30290 (0.0008) -[2023-10-16 03:58:23,952][05219] Updated weights for policy 1, policy_version 30300 (0.0010) -[2023-10-16 03:58:26,993][05218] Updated weights for policy 0, policy_version 30402 (0.0007) -[2023-10-16 03:58:27,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 62160896. Throughput: 0: 1780.4, 1: 1761.6. Samples: 15550936. Policy #0 lag: (min: 31.0, avg: 33.0, max: 62.0) -[2023-10-16 03:58:27,351][03835] Avg episode reward: [(0, '6.050'), (1, '5.050')] -[2023-10-16 03:58:27,366][05218] Updated weights for policy 0, policy_version 30412 (0.0010) -[2023-10-16 03:58:27,747][05218] Updated weights for policy 0, policy_version 30422 (0.0007) -[2023-10-16 03:58:27,926][05219] Updated weights for policy 1, policy_version 30310 (0.0008) -[2023-10-16 03:58:28,123][05218] Updated weights for policy 0, policy_version 30432 (0.0008) -[2023-10-16 03:58:28,308][05219] Updated weights for policy 1, policy_version 30320 (0.0010) -[2023-10-16 03:58:28,671][05219] Updated weights for policy 1, policy_version 30330 (0.0010) -[2023-10-16 03:58:31,835][05218] Updated weights for policy 0, policy_version 30442 (0.0007) -[2023-10-16 03:58:32,209][05218] Updated weights for policy 0, policy_version 30452 (0.0007) -[2023-10-16 03:58:32,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 62226432. Throughput: 0: 1800.6, 1: 1762.0. Samples: 15572822. Policy #0 lag: (min: 31.0, avg: 33.0, max: 62.0) -[2023-10-16 03:58:32,351][03835] Avg episode reward: [(0, '6.410'), (1, '6.060')] -[2023-10-16 03:58:32,451][05219] Updated weights for policy 1, policy_version 30340 (0.0008) -[2023-10-16 03:58:32,586][05218] Updated weights for policy 0, policy_version 30462 (0.0008) -[2023-10-16 03:58:32,809][05219] Updated weights for policy 1, policy_version 30350 (0.0008) -[2023-10-16 03:58:33,171][05219] Updated weights for policy 1, policy_version 30360 (0.0008) -[2023-10-16 03:58:36,284][05218] Updated weights for policy 0, policy_version 30472 (0.0010) -[2023-10-16 03:58:36,664][05218] Updated weights for policy 0, policy_version 30482 (0.0009) -[2023-10-16 03:58:36,967][05219] Updated weights for policy 1, policy_version 30370 (0.0010) -[2023-10-16 03:58:37,036][05218] Updated weights for policy 0, policy_version 30492 (0.0008) -[2023-10-16 03:58:37,322][05219] Updated weights for policy 1, policy_version 30380 (0.0007) -[2023-10-16 03:58:37,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 62324736. Throughput: 0: 1776.4, 1: 1784.5. Samples: 15593102. Policy #0 lag: (min: 31.0, avg: 33.0, max: 62.0) -[2023-10-16 03:58:37,351][03835] Avg episode reward: [(0, '6.220'), (1, '6.340')] -[2023-10-16 03:58:37,689][05219] Updated weights for policy 1, policy_version 30390 (0.0008) -[2023-10-16 03:58:38,054][05219] Updated weights for policy 1, policy_version 30400 (0.0007) -[2023-10-16 03:58:40,688][05218] Updated weights for policy 0, policy_version 30502 (0.0009) -[2023-10-16 03:58:41,061][05218] Updated weights for policy 0, policy_version 30512 (0.0008) -[2023-10-16 03:58:41,444][05218] Updated weights for policy 0, policy_version 30522 (0.0007) -[2023-10-16 03:58:41,757][05219] Updated weights for policy 1, policy_version 30410 (0.0009) -[2023-10-16 03:58:42,124][05219] Updated weights for policy 1, policy_version 30420 (0.0009) -[2023-10-16 03:58:42,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 62390272. Throughput: 0: 1799.7, 1: 1765.8. Samples: 15604910. Policy #0 lag: (min: 21.0, avg: 45.5, max: 48.0) -[2023-10-16 03:58:42,351][03835] Avg episode reward: [(0, '5.900'), (1, '5.980')] -[2023-10-16 03:58:42,496][05219] Updated weights for policy 1, policy_version 30430 (0.0011) -[2023-10-16 03:58:45,143][05218] Updated weights for policy 0, policy_version 30532 (0.0010) -[2023-10-16 03:58:45,523][05218] Updated weights for policy 0, policy_version 30542 (0.0008) -[2023-10-16 03:58:45,895][05218] Updated weights for policy 0, policy_version 30552 (0.0010) -[2023-10-16 03:58:46,195][05219] Updated weights for policy 1, policy_version 30440 (0.0009) -[2023-10-16 03:58:46,561][05219] Updated weights for policy 1, policy_version 30450 (0.0009) -[2023-10-16 03:58:46,922][05219] Updated weights for policy 1, policy_version 30460 (0.0011) -[2023-10-16 03:58:47,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 62488576. Throughput: 0: 1785.5, 1: 1783.7. Samples: 15625372. Policy #0 lag: (min: 21.0, avg: 45.5, max: 48.0) -[2023-10-16 03:58:47,351][03835] Avg episode reward: [(0, '6.200'), (1, '6.230')] -[2023-10-16 03:58:49,634][05218] Updated weights for policy 0, policy_version 30562 (0.0009) -[2023-10-16 03:58:50,035][05218] Updated weights for policy 0, policy_version 30572 (0.0009) -[2023-10-16 03:58:50,412][05218] Updated weights for policy 0, policy_version 30582 (0.0009) -[2023-10-16 03:58:50,664][05219] Updated weights for policy 1, policy_version 30470 (0.0009) -[2023-10-16 03:58:50,795][05218] Updated weights for policy 0, policy_version 30592 (0.0008) -[2023-10-16 03:58:51,023][05219] Updated weights for policy 1, policy_version 30480 (0.0009) -[2023-10-16 03:58:51,393][05219] Updated weights for policy 1, policy_version 30490 (0.0010) -[2023-10-16 03:58:52,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 62554112. Throughput: 0: 1786.3, 1: 1754.1. Samples: 15646562. Policy #0 lag: (min: 21.0, avg: 45.5, max: 48.0) -[2023-10-16 03:58:52,351][03835] Avg episode reward: [(0, '5.320'), (1, '5.690')] -[2023-10-16 03:58:54,528][05218] Updated weights for policy 0, policy_version 30602 (0.0007) -[2023-10-16 03:58:54,901][05218] Updated weights for policy 0, policy_version 30612 (0.0007) -[2023-10-16 03:58:55,223][05219] Updated weights for policy 1, policy_version 30500 (0.0009) -[2023-10-16 03:58:55,287][05218] Updated weights for policy 0, policy_version 30622 (0.0008) -[2023-10-16 03:58:55,579][05219] Updated weights for policy 1, policy_version 30510 (0.0010) -[2023-10-16 03:58:55,952][05219] Updated weights for policy 1, policy_version 30520 (0.0009) -[2023-10-16 03:58:57,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 62619648. Throughput: 0: 1788.9, 1: 1788.9. Samples: 15657838. Policy #0 lag: (min: 21.0, avg: 45.5, max: 48.0) -[2023-10-16 03:58:57,351][03835] Avg episode reward: [(0, '5.500'), (1, '5.560')] -[2023-10-16 03:58:59,066][05218] Updated weights for policy 0, policy_version 30632 (0.0008) -[2023-10-16 03:58:59,437][05218] Updated weights for policy 0, policy_version 30642 (0.0007) -[2023-10-16 03:58:59,768][05219] Updated weights for policy 1, policy_version 30530 (0.0009) -[2023-10-16 03:58:59,814][05218] Updated weights for policy 0, policy_version 30652 (0.0008) -[2023-10-16 03:59:00,131][05219] Updated weights for policy 1, policy_version 30540 (0.0007) -[2023-10-16 03:59:00,509][05219] Updated weights for policy 1, policy_version 30550 (0.0008) -[2023-10-16 03:59:00,867][05219] Updated weights for policy 1, policy_version 30560 (0.0008) -[2023-10-16 03:59:02,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 62685184. Throughput: 0: 1786.1, 1: 1766.1. Samples: 15678784. Policy #0 lag: (min: 21.0, avg: 45.5, max: 48.0) -[2023-10-16 03:59:02,351][03835] Avg episode reward: [(0, '5.970'), (1, '6.050')] -[2023-10-16 03:59:03,703][05218] Updated weights for policy 0, policy_version 30662 (0.0010) -[2023-10-16 03:59:04,075][05218] Updated weights for policy 0, policy_version 30672 (0.0008) -[2023-10-16 03:59:04,439][05218] Updated weights for policy 0, policy_version 30682 (0.0009) -[2023-10-16 03:59:04,536][05219] Updated weights for policy 1, policy_version 30570 (0.0008) -[2023-10-16 03:59:04,893][05219] Updated weights for policy 1, policy_version 30580 (0.0008) -[2023-10-16 03:59:05,258][05219] Updated weights for policy 1, policy_version 30590 (0.0007) -[2023-10-16 03:59:07,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 62750720. Throughput: 0: 1782.1, 1: 1771.9. Samples: 15701118. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:59:07,352][03835] Avg episode reward: [(0, '6.080'), (1, '5.770')] -[2023-10-16 03:59:08,220][05218] Updated weights for policy 0, policy_version 30692 (0.0010) -[2023-10-16 03:59:08,594][05218] Updated weights for policy 0, policy_version 30702 (0.0008) -[2023-10-16 03:59:08,968][05218] Updated weights for policy 0, policy_version 30712 (0.0008) -[2023-10-16 03:59:09,040][05219] Updated weights for policy 1, policy_version 30600 (0.0007) -[2023-10-16 03:59:09,407][05219] Updated weights for policy 1, policy_version 30610 (0.0008) -[2023-10-16 03:59:09,777][05219] Updated weights for policy 1, policy_version 30620 (0.0007) -[2023-10-16 03:59:12,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 62816256. Throughput: 0: 1783.3, 1: 1772.0. Samples: 15710922. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:59:12,351][03835] Avg episode reward: [(0, '5.780'), (1, '4.450')] -[2023-10-16 03:59:12,845][05218] Updated weights for policy 0, policy_version 30722 (0.0008) -[2023-10-16 03:59:13,216][05218] Updated weights for policy 0, policy_version 30732 (0.0007) -[2023-10-16 03:59:13,562][05219] Updated weights for policy 1, policy_version 30630 (0.0007) -[2023-10-16 03:59:13,594][05218] Updated weights for policy 0, policy_version 30742 (0.0007) -[2023-10-16 03:59:13,925][05219] Updated weights for policy 1, policy_version 30640 (0.0007) -[2023-10-16 03:59:13,979][05218] Updated weights for policy 0, policy_version 30752 (0.0007) -[2023-10-16 03:59:14,295][05219] Updated weights for policy 1, policy_version 30650 (0.0007) -[2023-10-16 03:59:17,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 62881792. Throughput: 0: 1778.2, 1: 1782.7. Samples: 15733064. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:59:17,352][03835] Avg episode reward: [(0, '5.870'), (1, '3.970')] -[2023-10-16 03:59:17,676][05218] Updated weights for policy 0, policy_version 30762 (0.0009) -[2023-10-16 03:59:18,049][05218] Updated weights for policy 0, policy_version 30772 (0.0007) -[2023-10-16 03:59:18,209][05219] Updated weights for policy 1, policy_version 30660 (0.0008) -[2023-10-16 03:59:18,419][05218] Updated weights for policy 0, policy_version 30782 (0.0010) -[2023-10-16 03:59:18,602][05219] Updated weights for policy 1, policy_version 30670 (0.0007) -[2023-10-16 03:59:18,967][05219] Updated weights for policy 1, policy_version 30680 (0.0010) -[2023-10-16 03:59:22,155][05218] Updated weights for policy 0, policy_version 30792 (0.0010) -[2023-10-16 03:59:22,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 62947328. Throughput: 0: 1799.4, 1: 1791.1. Samples: 15754674. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:59:22,351][03835] Avg episode reward: [(0, '6.290'), (1, '3.640')] -[2023-10-16 03:59:22,531][05218] Updated weights for policy 0, policy_version 30802 (0.0009) -[2023-10-16 03:59:22,609][05219] Updated weights for policy 1, policy_version 30690 (0.0007) -[2023-10-16 03:59:22,915][05218] Updated weights for policy 0, policy_version 30812 (0.0008) -[2023-10-16 03:59:22,981][05219] Updated weights for policy 1, policy_version 30700 (0.0007) -[2023-10-16 03:59:23,343][05219] Updated weights for policy 1, policy_version 30710 (0.0007) -[2023-10-16 03:59:23,713][05219] Updated weights for policy 1, policy_version 30720 (0.0009) -[2023-10-16 03:59:26,896][05218] Updated weights for policy 0, policy_version 30822 (0.0010) -[2023-10-16 03:59:27,277][05218] Updated weights for policy 0, policy_version 30832 (0.0009) -[2023-10-16 03:59:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 63012864. Throughput: 0: 1770.7, 1: 1786.1. Samples: 15764968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:59:27,352][03835] Avg episode reward: [(0, '5.620'), (1, '3.980')] -[2023-10-16 03:59:27,488][05219] Updated weights for policy 1, policy_version 30730 (0.0008) -[2023-10-16 03:59:27,643][05218] Updated weights for policy 0, policy_version 30842 (0.0009) -[2023-10-16 03:59:27,864][05219] Updated weights for policy 1, policy_version 30740 (0.0007) -[2023-10-16 03:59:28,232][05219] Updated weights for policy 1, policy_version 30750 (0.0009) -[2023-10-16 03:59:31,388][05218] Updated weights for policy 0, policy_version 30852 (0.0008) -[2023-10-16 03:59:31,759][05218] Updated weights for policy 0, policy_version 30862 (0.0009) -[2023-10-16 03:59:31,923][05219] Updated weights for policy 1, policy_version 30760 (0.0008) -[2023-10-16 03:59:32,140][05218] Updated weights for policy 0, policy_version 30872 (0.0007) -[2023-10-16 03:59:32,285][05219] Updated weights for policy 1, policy_version 30770 (0.0009) -[2023-10-16 03:59:32,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 63078400. Throughput: 0: 1798.4, 1: 1799.6. Samples: 15787284. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-16 03:59:32,351][03835] Avg episode reward: [(0, '5.670'), (1, '4.420')] -[2023-10-16 03:59:32,658][05219] Updated weights for policy 1, policy_version 30780 (0.0007) -[2023-10-16 03:59:35,993][05218] Updated weights for policy 0, policy_version 30882 (0.0008) -[2023-10-16 03:59:36,407][05218] Updated weights for policy 0, policy_version 30892 (0.0009) -[2023-10-16 03:59:36,425][05219] Updated weights for policy 1, policy_version 30790 (0.0008) -[2023-10-16 03:59:36,771][05218] Updated weights for policy 0, policy_version 30902 (0.0008) -[2023-10-16 03:59:36,777][05219] Updated weights for policy 1, policy_version 30800 (0.0008) -[2023-10-16 03:59:37,142][05218] Updated weights for policy 0, policy_version 30912 (0.0007) -[2023-10-16 03:59:37,145][05219] Updated weights for policy 1, policy_version 30810 (0.0009) -[2023-10-16 03:59:37,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 63176704. Throughput: 0: 1763.6, 1: 1805.2. Samples: 15807160. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-16 03:59:37,351][03835] Avg episode reward: [(0, '5.050'), (1, '5.200')] -[2023-10-16 03:59:37,361][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000030816_31555584.pth... -[2023-10-16 03:59:37,362][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000030912_31653888.pth... -[2023-10-16 03:59:37,391][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000029152_29851648.pth -[2023-10-16 03:59:37,408][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000029248_29949952.pth -[2023-10-16 03:59:40,726][05218] Updated weights for policy 0, policy_version 30922 (0.0009) -[2023-10-16 03:59:41,075][05219] Updated weights for policy 1, policy_version 30820 (0.0008) -[2023-10-16 03:59:41,107][05218] Updated weights for policy 0, policy_version 30932 (0.0008) -[2023-10-16 03:59:41,438][05219] Updated weights for policy 1, policy_version 30830 (0.0008) -[2023-10-16 03:59:41,486][05218] Updated weights for policy 0, policy_version 30942 (0.0009) -[2023-10-16 03:59:41,794][05219] Updated weights for policy 1, policy_version 30840 (0.0011) -[2023-10-16 03:59:42,350][03835] Fps is (10 sec: 19660.6, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 63275008. Throughput: 0: 1801.8, 1: 1793.8. Samples: 15819642. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-16 03:59:42,351][03835] Avg episode reward: [(0, '5.590'), (1, '5.560')] -[2023-10-16 03:59:45,200][05218] Updated weights for policy 0, policy_version 30952 (0.0007) -[2023-10-16 03:59:45,483][05219] Updated weights for policy 1, policy_version 30850 (0.0010) -[2023-10-16 03:59:45,563][05218] Updated weights for policy 0, policy_version 30962 (0.0009) -[2023-10-16 03:59:45,850][05219] Updated weights for policy 1, policy_version 30860 (0.0007) -[2023-10-16 03:59:45,942][05218] Updated weights for policy 0, policy_version 30972 (0.0008) -[2023-10-16 03:59:46,218][05219] Updated weights for policy 1, policy_version 30870 (0.0008) -[2023-10-16 03:59:46,577][05219] Updated weights for policy 1, policy_version 30880 (0.0007) -[2023-10-16 03:59:47,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 63340544. Throughput: 0: 1770.4, 1: 1806.9. Samples: 15839766. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-16 03:59:47,351][03835] Avg episode reward: [(0, '5.590'), (1, '6.190')] -[2023-10-16 03:59:49,816][05218] Updated weights for policy 0, policy_version 30982 (0.0008) -[2023-10-16 03:59:50,187][05218] Updated weights for policy 0, policy_version 30992 (0.0008) -[2023-10-16 03:59:50,384][05219] Updated weights for policy 1, policy_version 30890 (0.0007) -[2023-10-16 03:59:50,570][05218] Updated weights for policy 0, policy_version 31002 (0.0008) -[2023-10-16 03:59:50,745][05219] Updated weights for policy 1, policy_version 30900 (0.0008) -[2023-10-16 03:59:51,106][05219] Updated weights for policy 1, policy_version 30910 (0.0010) -[2023-10-16 03:59:52,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 63406080. Throughput: 0: 1770.3, 1: 1789.1. Samples: 15861292. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:59:52,351][03835] Avg episode reward: [(0, '6.050'), (1, '5.480')] -[2023-10-16 03:59:54,372][05218] Updated weights for policy 0, policy_version 31012 (0.0008) -[2023-10-16 03:59:54,746][05218] Updated weights for policy 0, policy_version 31022 (0.0007) -[2023-10-16 03:59:54,940][05219] Updated weights for policy 1, policy_version 30920 (0.0008) -[2023-10-16 03:59:55,126][05218] Updated weights for policy 0, policy_version 31032 (0.0009) -[2023-10-16 03:59:55,301][05219] Updated weights for policy 1, policy_version 30930 (0.0007) -[2023-10-16 03:59:55,672][05219] Updated weights for policy 1, policy_version 30940 (0.0010) -[2023-10-16 03:59:57,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 63471616. Throughput: 0: 1770.0, 1: 1810.7. Samples: 15872052. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 03:59:57,351][03835] Avg episode reward: [(0, '5.390'), (1, '6.020')] -[2023-10-16 03:59:58,775][05218] Updated weights for policy 0, policy_version 31042 (0.0010) -[2023-10-16 03:59:59,148][05218] Updated weights for policy 0, policy_version 31052 (0.0009) -[2023-10-16 03:59:59,326][05219] Updated weights for policy 1, policy_version 30950 (0.0008) -[2023-10-16 03:59:59,524][05218] Updated weights for policy 0, policy_version 31062 (0.0007) -[2023-10-16 03:59:59,686][05219] Updated weights for policy 1, policy_version 30960 (0.0007) -[2023-10-16 03:59:59,899][05218] Updated weights for policy 0, policy_version 31072 (0.0010) -[2023-10-16 04:00:00,049][05219] Updated weights for policy 1, policy_version 30970 (0.0007) -[2023-10-16 04:00:02,351][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 63537152. Throughput: 0: 1777.2, 1: 1788.6. Samples: 15893526. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:00:02,352][03835] Avg episode reward: [(0, '6.130'), (1, '5.410')] -[2023-10-16 04:00:03,514][05218] Updated weights for policy 0, policy_version 31082 (0.0007) -[2023-10-16 04:00:03,839][05219] Updated weights for policy 1, policy_version 30980 (0.0008) -[2023-10-16 04:00:03,896][05218] Updated weights for policy 0, policy_version 31092 (0.0008) -[2023-10-16 04:00:04,222][05219] Updated weights for policy 1, policy_version 30990 (0.0007) -[2023-10-16 04:00:04,267][05218] Updated weights for policy 0, policy_version 31102 (0.0007) -[2023-10-16 04:00:04,591][05219] Updated weights for policy 1, policy_version 31000 (0.0007) -[2023-10-16 04:00:07,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.6, 300 sec: 14218.0). Total num frames: 63602688. Throughput: 0: 1799.7, 1: 1785.2. Samples: 15915998. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:00:07,351][03835] Avg episode reward: [(0, '6.360'), (1, '5.820')] -[2023-10-16 04:00:07,928][05218] Updated weights for policy 0, policy_version 31112 (0.0011) -[2023-10-16 04:00:08,300][05218] Updated weights for policy 0, policy_version 31122 (0.0008) -[2023-10-16 04:00:08,391][05219] Updated weights for policy 1, policy_version 31010 (0.0008) -[2023-10-16 04:00:08,678][05218] Updated weights for policy 0, policy_version 31132 (0.0008) -[2023-10-16 04:00:08,756][05219] Updated weights for policy 1, policy_version 31020 (0.0008) -[2023-10-16 04:00:09,123][05219] Updated weights for policy 1, policy_version 31030 (0.0007) -[2023-10-16 04:00:09,481][05219] Updated weights for policy 1, policy_version 31040 (0.0007) -[2023-10-16 04:00:12,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 63668224. Throughput: 0: 1788.6, 1: 1788.8. Samples: 15925952. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:00:12,351][03835] Avg episode reward: [(0, '5.930'), (1, '5.040')] -[2023-10-16 04:00:12,600][05218] Updated weights for policy 0, policy_version 31142 (0.0008) -[2023-10-16 04:00:12,962][05218] Updated weights for policy 0, policy_version 31152 (0.0009) -[2023-10-16 04:00:13,247][05219] Updated weights for policy 1, policy_version 31050 (0.0007) -[2023-10-16 04:00:13,343][05218] Updated weights for policy 0, policy_version 31162 (0.0008) -[2023-10-16 04:00:13,613][05219] Updated weights for policy 1, policy_version 31060 (0.0008) -[2023-10-16 04:00:13,973][05219] Updated weights for policy 1, policy_version 31070 (0.0008) -[2023-10-16 04:00:16,933][05218] Updated weights for policy 0, policy_version 31172 (0.0009) -[2023-10-16 04:00:17,314][05218] Updated weights for policy 0, policy_version 31182 (0.0010) -[2023-10-16 04:00:17,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 63733760. Throughput: 0: 1796.6, 1: 1783.1. Samples: 15948372. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:00:17,351][03835] Avg episode reward: [(0, '6.560'), (1, '5.060')] -[2023-10-16 04:00:17,678][05219] Updated weights for policy 1, policy_version 31080 (0.0007) -[2023-10-16 04:00:17,690][05218] Updated weights for policy 0, policy_version 31192 (0.0008) -[2023-10-16 04:00:18,042][05219] Updated weights for policy 1, policy_version 31090 (0.0007) -[2023-10-16 04:00:18,414][05219] Updated weights for policy 1, policy_version 31100 (0.0008) -[2023-10-16 04:00:21,388][05218] Updated weights for policy 0, policy_version 31202 (0.0008) -[2023-10-16 04:00:21,791][05218] Updated weights for policy 0, policy_version 31212 (0.0010) -[2023-10-16 04:00:22,171][05218] Updated weights for policy 0, policy_version 31222 (0.0009) -[2023-10-16 04:00:22,236][05219] Updated weights for policy 1, policy_version 31110 (0.0008) -[2023-10-16 04:00:22,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 63799296. Throughput: 0: 1805.3, 1: 1802.0. Samples: 15969490. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:00:22,351][03835] Avg episode reward: [(0, '6.260'), (1, '4.970')] -[2023-10-16 04:00:22,532][05218] Updated weights for policy 0, policy_version 31232 (0.0008) -[2023-10-16 04:00:22,598][05219] Updated weights for policy 1, policy_version 31120 (0.0007) -[2023-10-16 04:00:22,963][05219] Updated weights for policy 1, policy_version 31130 (0.0007) -[2023-10-16 04:00:26,097][05218] Updated weights for policy 0, policy_version 31242 (0.0008) -[2023-10-16 04:00:26,476][05218] Updated weights for policy 0, policy_version 31252 (0.0007) -[2023-10-16 04:00:26,631][05219] Updated weights for policy 1, policy_version 31140 (0.0009) -[2023-10-16 04:00:26,855][05218] Updated weights for policy 0, policy_version 31262 (0.0009) -[2023-10-16 04:00:26,988][05219] Updated weights for policy 1, policy_version 31150 (0.0008) -[2023-10-16 04:00:27,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 63897600. Throughput: 0: 1795.1, 1: 1781.8. Samples: 15980602. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:00:27,351][03835] Avg episode reward: [(0, '6.200'), (1, '4.860')] -[2023-10-16 04:00:27,356][05219] Updated weights for policy 1, policy_version 31160 (0.0009) -[2023-10-16 04:00:30,674][05218] Updated weights for policy 0, policy_version 31272 (0.0010) -[2023-10-16 04:00:31,048][05218] Updated weights for policy 0, policy_version 31282 (0.0009) -[2023-10-16 04:00:31,077][05219] Updated weights for policy 1, policy_version 31170 (0.0009) -[2023-10-16 04:00:31,418][05218] Updated weights for policy 0, policy_version 31292 (0.0008) -[2023-10-16 04:00:31,451][05219] Updated weights for policy 1, policy_version 31180 (0.0010) -[2023-10-16 04:00:31,819][05219] Updated weights for policy 1, policy_version 31190 (0.0008) -[2023-10-16 04:00:32,175][05219] Updated weights for policy 1, policy_version 31200 (0.0007) -[2023-10-16 04:00:32,350][03835] Fps is (10 sec: 19661.3, 60 sec: 15291.7, 300 sec: 14440.1). Total num frames: 63995904. Throughput: 0: 1800.5, 1: 1797.2. Samples: 16001658. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:00:32,351][03835] Avg episode reward: [(0, '6.360'), (1, '6.110')] -[2023-10-16 04:00:35,273][05218] Updated weights for policy 0, policy_version 31302 (0.0009) -[2023-10-16 04:00:35,646][05218] Updated weights for policy 0, policy_version 31312 (0.0009) -[2023-10-16 04:00:36,018][05218] Updated weights for policy 0, policy_version 31322 (0.0009) -[2023-10-16 04:00:36,036][05219] Updated weights for policy 1, policy_version 31210 (0.0009) -[2023-10-16 04:00:36,404][05219] Updated weights for policy 1, policy_version 31220 (0.0009) -[2023-10-16 04:00:36,770][05219] Updated weights for policy 1, policy_version 31230 (0.0010) -[2023-10-16 04:00:37,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 64061440. Throughput: 0: 1791.3, 1: 1781.2. Samples: 16022058. Policy #0 lag: (min: 0.0, avg: 22.6, max: 32.0) -[2023-10-16 04:00:37,351][03835] Avg episode reward: [(0, '6.580'), (1, '5.830')] -[2023-10-16 04:00:37,359][04766] Saving new best policy, reward=6.580! -[2023-10-16 04:00:39,625][05218] Updated weights for policy 0, policy_version 31332 (0.0008) -[2023-10-16 04:00:40,005][05218] Updated weights for policy 0, policy_version 31342 (0.0008) -[2023-10-16 04:00:40,382][05218] Updated weights for policy 0, policy_version 31352 (0.0008) -[2023-10-16 04:00:40,649][05219] Updated weights for policy 1, policy_version 31240 (0.0008) -[2023-10-16 04:00:41,014][05219] Updated weights for policy 1, policy_version 31250 (0.0010) -[2023-10-16 04:00:41,382][05219] Updated weights for policy 1, policy_version 31260 (0.0009) -[2023-10-16 04:00:42,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 64126976. Throughput: 0: 1803.6, 1: 1789.5. Samples: 16033740. Policy #0 lag: (min: 0.0, avg: 22.6, max: 32.0) -[2023-10-16 04:00:42,351][03835] Avg episode reward: [(0, '5.760'), (1, '5.600')] -[2023-10-16 04:00:44,253][05218] Updated weights for policy 0, policy_version 31362 (0.0009) -[2023-10-16 04:00:44,628][05218] Updated weights for policy 0, policy_version 31372 (0.0007) -[2023-10-16 04:00:45,005][05218] Updated weights for policy 0, policy_version 31382 (0.0007) -[2023-10-16 04:00:45,375][05219] Updated weights for policy 1, policy_version 31270 (0.0008) -[2023-10-16 04:00:45,381][05218] Updated weights for policy 0, policy_version 31392 (0.0007) -[2023-10-16 04:00:45,735][05219] Updated weights for policy 1, policy_version 31280 (0.0010) -[2023-10-16 04:00:46,102][05219] Updated weights for policy 1, policy_version 31290 (0.0011) -[2023-10-16 04:00:47,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 64192512. Throughput: 0: 1784.9, 1: 1781.8. Samples: 16054028. Policy #0 lag: (min: 0.0, avg: 22.6, max: 32.0) -[2023-10-16 04:00:47,351][03835] Avg episode reward: [(0, '5.600'), (1, '5.040')] -[2023-10-16 04:00:49,299][05218] Updated weights for policy 0, policy_version 31402 (0.0009) -[2023-10-16 04:00:49,679][05218] Updated weights for policy 0, policy_version 31412 (0.0009) -[2023-10-16 04:00:49,904][05219] Updated weights for policy 1, policy_version 31300 (0.0009) -[2023-10-16 04:00:50,046][05218] Updated weights for policy 0, policy_version 31422 (0.0007) -[2023-10-16 04:00:50,291][05219] Updated weights for policy 1, policy_version 31310 (0.0009) -[2023-10-16 04:00:50,649][05219] Updated weights for policy 1, policy_version 31320 (0.0010) -[2023-10-16 04:00:52,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 64258048. Throughput: 0: 1777.1, 1: 1775.0. Samples: 16075842. Policy #0 lag: (min: 0.0, avg: 22.6, max: 32.0) -[2023-10-16 04:00:52,351][03835] Avg episode reward: [(0, '6.350'), (1, '5.390')] -[2023-10-16 04:00:53,698][05218] Updated weights for policy 0, policy_version 31432 (0.0008) -[2023-10-16 04:00:54,077][05218] Updated weights for policy 0, policy_version 31442 (0.0007) -[2023-10-16 04:00:54,402][05219] Updated weights for policy 1, policy_version 31330 (0.0011) -[2023-10-16 04:00:54,453][05218] Updated weights for policy 0, policy_version 31452 (0.0008) -[2023-10-16 04:00:54,765][05219] Updated weights for policy 1, policy_version 31340 (0.0009) -[2023-10-16 04:00:55,145][05219] Updated weights for policy 1, policy_version 31350 (0.0009) -[2023-10-16 04:00:55,505][05219] Updated weights for policy 1, policy_version 31360 (0.0008) -[2023-10-16 04:00:57,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 64323584. Throughput: 0: 1779.9, 1: 1783.6. Samples: 16086310. Policy #0 lag: (min: 0.0, avg: 22.6, max: 32.0) -[2023-10-16 04:00:57,352][03835] Avg episode reward: [(0, '5.690'), (1, '5.980')] -[2023-10-16 04:00:58,260][05218] Updated weights for policy 0, policy_version 31462 (0.0009) -[2023-10-16 04:00:58,633][05218] Updated weights for policy 0, policy_version 31472 (0.0009) -[2023-10-16 04:00:59,003][05218] Updated weights for policy 0, policy_version 31482 (0.0008) -[2023-10-16 04:00:59,107][05219] Updated weights for policy 1, policy_version 31370 (0.0007) -[2023-10-16 04:00:59,462][05219] Updated weights for policy 1, policy_version 31380 (0.0009) -[2023-10-16 04:00:59,832][05219] Updated weights for policy 1, policy_version 31390 (0.0008) -[2023-10-16 04:01:02,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.6, 300 sec: 14218.0). Total num frames: 64389120. Throughput: 0: 1777.3, 1: 1772.6. Samples: 16108118. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-10-16 04:01:02,351][03835] Avg episode reward: [(0, '5.940'), (1, '6.030')] -[2023-10-16 04:01:02,791][05218] Updated weights for policy 0, policy_version 31492 (0.0009) -[2023-10-16 04:01:03,165][05218] Updated weights for policy 0, policy_version 31502 (0.0008) -[2023-10-16 04:01:03,541][05218] Updated weights for policy 0, policy_version 31512 (0.0009) -[2023-10-16 04:01:03,657][05219] Updated weights for policy 1, policy_version 31400 (0.0008) -[2023-10-16 04:01:04,034][05219] Updated weights for policy 1, policy_version 31410 (0.0010) -[2023-10-16 04:01:04,399][05219] Updated weights for policy 1, policy_version 31420 (0.0009) -[2023-10-16 04:01:07,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 64454656. Throughput: 0: 1792.7, 1: 1772.0. Samples: 16129898. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-10-16 04:01:07,351][03835] Avg episode reward: [(0, '6.160'), (1, '5.340')] -[2023-10-16 04:01:07,430][05218] Updated weights for policy 0, policy_version 31522 (0.0008) -[2023-10-16 04:01:07,841][05218] Updated weights for policy 0, policy_version 31532 (0.0008) -[2023-10-16 04:01:08,208][05218] Updated weights for policy 0, policy_version 31542 (0.0009) -[2023-10-16 04:01:08,315][05219] Updated weights for policy 1, policy_version 31430 (0.0008) -[2023-10-16 04:01:08,587][05218] Updated weights for policy 0, policy_version 31552 (0.0007) -[2023-10-16 04:01:08,686][05219] Updated weights for policy 1, policy_version 31440 (0.0010) -[2023-10-16 04:01:09,057][05219] Updated weights for policy 1, policy_version 31450 (0.0009) -[2023-10-16 04:01:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 64520192. Throughput: 0: 1762.0, 1: 1771.1. Samples: 16139592. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-10-16 04:01:12,351][03835] Avg episode reward: [(0, '5.480'), (1, '5.620')] -[2023-10-16 04:01:12,436][05218] Updated weights for policy 0, policy_version 31562 (0.0009) -[2023-10-16 04:01:12,806][05218] Updated weights for policy 0, policy_version 31572 (0.0007) -[2023-10-16 04:01:12,985][05219] Updated weights for policy 1, policy_version 31460 (0.0008) -[2023-10-16 04:01:13,185][05218] Updated weights for policy 0, policy_version 31582 (0.0007) -[2023-10-16 04:01:13,352][05219] Updated weights for policy 1, policy_version 31470 (0.0009) -[2023-10-16 04:01:13,708][05219] Updated weights for policy 1, policy_version 31480 (0.0008) -[2023-10-16 04:01:16,962][05218] Updated weights for policy 0, policy_version 31592 (0.0009) -[2023-10-16 04:01:17,332][05218] Updated weights for policy 0, policy_version 31602 (0.0010) -[2023-10-16 04:01:17,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 64585728. Throughput: 0: 1787.2, 1: 1770.9. Samples: 16161776. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-10-16 04:01:17,351][03835] Avg episode reward: [(0, '5.970'), (1, '5.360')] -[2023-10-16 04:01:17,358][05219] Updated weights for policy 1, policy_version 31490 (0.0008) -[2023-10-16 04:01:17,704][05218] Updated weights for policy 0, policy_version 31612 (0.0007) -[2023-10-16 04:01:17,726][05219] Updated weights for policy 1, policy_version 31500 (0.0007) -[2023-10-16 04:01:18,097][05219] Updated weights for policy 1, policy_version 31510 (0.0008) -[2023-10-16 04:01:18,462][05219] Updated weights for policy 1, policy_version 31520 (0.0010) -[2023-10-16 04:01:21,455][05218] Updated weights for policy 0, policy_version 31622 (0.0008) -[2023-10-16 04:01:21,831][05218] Updated weights for policy 0, policy_version 31632 (0.0010) -[2023-10-16 04:01:22,152][05219] Updated weights for policy 1, policy_version 31530 (0.0008) -[2023-10-16 04:01:22,197][05218] Updated weights for policy 0, policy_version 31642 (0.0008) -[2023-10-16 04:01:22,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 64651264. Throughput: 0: 1774.9, 1: 1791.6. Samples: 16182552. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-10-16 04:01:22,351][03835] Avg episode reward: [(0, '6.180'), (1, '5.270')] -[2023-10-16 04:01:22,524][05219] Updated weights for policy 1, policy_version 31540 (0.0008) -[2023-10-16 04:01:22,890][05219] Updated weights for policy 1, policy_version 31550 (0.0011) -[2023-10-16 04:01:25,995][05218] Updated weights for policy 0, policy_version 31652 (0.0008) -[2023-10-16 04:01:26,368][05218] Updated weights for policy 0, policy_version 31662 (0.0008) -[2023-10-16 04:01:26,742][05218] Updated weights for policy 0, policy_version 31672 (0.0009) -[2023-10-16 04:01:26,745][05219] Updated weights for policy 1, policy_version 31560 (0.0008) -[2023-10-16 04:01:27,105][05219] Updated weights for policy 1, policy_version 31570 (0.0009) -[2023-10-16 04:01:27,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 64749568. Throughput: 0: 1791.5, 1: 1769.2. Samples: 16193972. Policy #0 lag: (min: 31.0, avg: 32.6, max: 59.0) -[2023-10-16 04:01:27,351][03835] Avg episode reward: [(0, '5.800'), (1, '5.880')] -[2023-10-16 04:01:27,473][05219] Updated weights for policy 1, policy_version 31580 (0.0010) -[2023-10-16 04:01:30,467][05218] Updated weights for policy 0, policy_version 31682 (0.0008) -[2023-10-16 04:01:30,843][05218] Updated weights for policy 0, policy_version 31692 (0.0007) -[2023-10-16 04:01:31,222][05218] Updated weights for policy 0, policy_version 31702 (0.0009) -[2023-10-16 04:01:31,309][05219] Updated weights for policy 1, policy_version 31590 (0.0010) -[2023-10-16 04:01:31,601][05218] Updated weights for policy 0, policy_version 31712 (0.0007) -[2023-10-16 04:01:31,667][05219] Updated weights for policy 1, policy_version 31600 (0.0007) -[2023-10-16 04:01:32,032][05219] Updated weights for policy 1, policy_version 31610 (0.0007) -[2023-10-16 04:01:32,350][03835] Fps is (10 sec: 19661.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 64847872. Throughput: 0: 1785.8, 1: 1794.2. Samples: 16215128. Policy #0 lag: (min: 31.0, avg: 32.6, max: 59.0) -[2023-10-16 04:01:32,351][03835] Avg episode reward: [(0, '6.310'), (1, '5.840')] -[2023-10-16 04:01:35,312][05218] Updated weights for policy 0, policy_version 31722 (0.0008) -[2023-10-16 04:01:35,693][05218] Updated weights for policy 0, policy_version 31732 (0.0009) -[2023-10-16 04:01:35,872][05219] Updated weights for policy 1, policy_version 31620 (0.0007) -[2023-10-16 04:01:36,065][05218] Updated weights for policy 0, policy_version 31742 (0.0009) -[2023-10-16 04:01:36,260][05219] Updated weights for policy 1, policy_version 31630 (0.0010) -[2023-10-16 04:01:36,623][05219] Updated weights for policy 1, policy_version 31640 (0.0011) -[2023-10-16 04:01:37,351][03835] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 64913408. Throughput: 0: 1775.7, 1: 1770.8. Samples: 16235436. Policy #0 lag: (min: 31.0, avg: 32.6, max: 59.0) -[2023-10-16 04:01:37,352][03835] Avg episode reward: [(0, '5.890'), (1, '6.420')] -[2023-10-16 04:01:37,364][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000031744_32505856.pth... -[2023-10-16 04:01:37,364][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000031648_32407552.pth... -[2023-10-16 04:01:37,402][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000030080_30801920.pth -[2023-10-16 04:01:37,402][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000029984_30703616.pth -[2023-10-16 04:01:39,801][05218] Updated weights for policy 0, policy_version 31752 (0.0008) -[2023-10-16 04:01:40,180][05218] Updated weights for policy 0, policy_version 31762 (0.0007) -[2023-10-16 04:01:40,396][05219] Updated weights for policy 1, policy_version 31650 (0.0009) -[2023-10-16 04:01:40,551][05218] Updated weights for policy 0, policy_version 31772 (0.0010) -[2023-10-16 04:01:40,764][05219] Updated weights for policy 1, policy_version 31660 (0.0009) -[2023-10-16 04:01:41,119][05219] Updated weights for policy 1, policy_version 31670 (0.0008) -[2023-10-16 04:01:41,483][05219] Updated weights for policy 1, policy_version 31680 (0.0010) -[2023-10-16 04:01:42,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 64978944. Throughput: 0: 1787.4, 1: 1789.0. Samples: 16247250. Policy #0 lag: (min: 31.0, avg: 32.6, max: 59.0) -[2023-10-16 04:01:42,351][03835] Avg episode reward: [(0, '5.840'), (1, '6.390')] -[2023-10-16 04:01:44,248][05218] Updated weights for policy 0, policy_version 31782 (0.0008) -[2023-10-16 04:01:44,620][05218] Updated weights for policy 0, policy_version 31792 (0.0007) -[2023-10-16 04:01:45,000][05218] Updated weights for policy 0, policy_version 31802 (0.0007) -[2023-10-16 04:01:45,282][05219] Updated weights for policy 1, policy_version 31690 (0.0008) -[2023-10-16 04:01:45,644][05219] Updated weights for policy 1, policy_version 31700 (0.0009) -[2023-10-16 04:01:46,001][05219] Updated weights for policy 1, policy_version 31710 (0.0008) -[2023-10-16 04:01:47,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 65044480. Throughput: 0: 1779.9, 1: 1767.9. Samples: 16267768. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:01:47,351][03835] Avg episode reward: [(0, '5.950'), (1, '6.300')] -[2023-10-16 04:01:48,918][05218] Updated weights for policy 0, policy_version 31812 (0.0007) -[2023-10-16 04:01:49,291][05218] Updated weights for policy 0, policy_version 31822 (0.0008) -[2023-10-16 04:01:49,649][05219] Updated weights for policy 1, policy_version 31720 (0.0008) -[2023-10-16 04:01:49,670][05218] Updated weights for policy 0, policy_version 31832 (0.0009) -[2023-10-16 04:01:50,018][05219] Updated weights for policy 1, policy_version 31730 (0.0008) -[2023-10-16 04:01:50,384][05219] Updated weights for policy 1, policy_version 31740 (0.0011) -[2023-10-16 04:01:52,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 65110016. Throughput: 0: 1787.1, 1: 1766.6. Samples: 16289814. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:01:52,351][03835] Avg episode reward: [(0, '5.800'), (1, '6.380')] -[2023-10-16 04:01:53,366][05218] Updated weights for policy 0, policy_version 31842 (0.0008) -[2023-10-16 04:01:53,764][05218] Updated weights for policy 0, policy_version 31852 (0.0007) -[2023-10-16 04:01:54,150][05218] Updated weights for policy 0, policy_version 31862 (0.0009) -[2023-10-16 04:01:54,228][05219] Updated weights for policy 1, policy_version 31750 (0.0009) -[2023-10-16 04:01:54,519][05218] Updated weights for policy 0, policy_version 31872 (0.0008) -[2023-10-16 04:01:54,586][05219] Updated weights for policy 1, policy_version 31760 (0.0007) -[2023-10-16 04:01:54,955][05219] Updated weights for policy 1, policy_version 31770 (0.0009) -[2023-10-16 04:01:57,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 65175552. Throughput: 0: 1788.3, 1: 1771.9. Samples: 16299802. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:01:57,351][03835] Avg episode reward: [(0, '5.550'), (1, '5.980')] -[2023-10-16 04:01:58,226][05218] Updated weights for policy 0, policy_version 31882 (0.0008) -[2023-10-16 04:01:58,606][05218] Updated weights for policy 0, policy_version 31892 (0.0008) -[2023-10-16 04:01:58,698][05219] Updated weights for policy 1, policy_version 31780 (0.0008) -[2023-10-16 04:01:58,989][05218] Updated weights for policy 0, policy_version 31902 (0.0010) -[2023-10-16 04:01:59,059][05219] Updated weights for policy 1, policy_version 31790 (0.0008) -[2023-10-16 04:01:59,421][05219] Updated weights for policy 1, policy_version 31800 (0.0011) -[2023-10-16 04:02:02,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 65241088. Throughput: 0: 1794.5, 1: 1764.9. Samples: 16321950. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:02:02,351][03835] Avg episode reward: [(0, '6.700'), (1, '6.230')] -[2023-10-16 04:02:02,429][05218] Updated weights for policy 0, policy_version 31912 (0.0009) -[2023-10-16 04:02:02,806][05218] Updated weights for policy 0, policy_version 31922 (0.0008) -[2023-10-16 04:02:03,195][05218] Updated weights for policy 0, policy_version 31932 (0.0009) -[2023-10-16 04:02:03,336][04766] Saving new best policy, reward=6.700! -[2023-10-16 04:02:03,374][05219] Updated weights for policy 1, policy_version 31810 (0.0010) -[2023-10-16 04:02:03,734][05219] Updated weights for policy 1, policy_version 31820 (0.0008) -[2023-10-16 04:02:04,103][05219] Updated weights for policy 1, policy_version 31830 (0.0008) -[2023-10-16 04:02:04,477][05219] Updated weights for policy 1, policy_version 31840 (0.0008) -[2023-10-16 04:02:06,896][05218] Updated weights for policy 0, policy_version 31942 (0.0009) -[2023-10-16 04:02:07,265][05218] Updated weights for policy 0, policy_version 31952 (0.0010) -[2023-10-16 04:02:07,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 65306624. Throughput: 0: 1807.7, 1: 1774.6. Samples: 16343754. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:02:07,351][03835] Avg episode reward: [(0, '5.300'), (1, '6.110')] -[2023-10-16 04:02:07,642][05218] Updated weights for policy 0, policy_version 31962 (0.0010) -[2023-10-16 04:02:08,341][05219] Updated weights for policy 1, policy_version 31850 (0.0007) -[2023-10-16 04:02:08,712][05219] Updated weights for policy 1, policy_version 31860 (0.0007) -[2023-10-16 04:02:09,079][05219] Updated weights for policy 1, policy_version 31870 (0.0007) -[2023-10-16 04:02:11,415][05218] Updated weights for policy 0, policy_version 31972 (0.0007) -[2023-10-16 04:02:11,786][05218] Updated weights for policy 0, policy_version 31982 (0.0009) -[2023-10-16 04:02:12,158][05218] Updated weights for policy 0, policy_version 31992 (0.0011) -[2023-10-16 04:02:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 65372160. Throughput: 0: 1793.9, 1: 1765.7. Samples: 16354152. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-16 04:02:12,351][03835] Avg episode reward: [(0, '5.720'), (1, '5.970')] -[2023-10-16 04:02:13,047][05219] Updated weights for policy 1, policy_version 31880 (0.0009) -[2023-10-16 04:02:13,406][05219] Updated weights for policy 1, policy_version 31890 (0.0010) -[2023-10-16 04:02:13,777][05219] Updated weights for policy 1, policy_version 31900 (0.0009) -[2023-10-16 04:02:15,913][05218] Updated weights for policy 0, policy_version 32002 (0.0009) -[2023-10-16 04:02:16,294][05218] Updated weights for policy 0, policy_version 32012 (0.0007) -[2023-10-16 04:02:16,680][05218] Updated weights for policy 0, policy_version 32022 (0.0008) -[2023-10-16 04:02:17,051][05218] Updated weights for policy 0, policy_version 32032 (0.0010) -[2023-10-16 04:02:17,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 65470464. Throughput: 0: 1802.3, 1: 1774.5. Samples: 16376084. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-16 04:02:17,351][03835] Avg episode reward: [(0, '6.270'), (1, '6.470')] -[2023-10-16 04:02:17,458][05219] Updated weights for policy 1, policy_version 31910 (0.0007) -[2023-10-16 04:02:17,821][05219] Updated weights for policy 1, policy_version 31920 (0.0007) -[2023-10-16 04:02:18,194][05219] Updated weights for policy 1, policy_version 31930 (0.0010) -[2023-10-16 04:02:20,813][05218] Updated weights for policy 0, policy_version 32042 (0.0009) -[2023-10-16 04:02:21,187][05218] Updated weights for policy 0, policy_version 32052 (0.0009) -[2023-10-16 04:02:21,568][05218] Updated weights for policy 0, policy_version 32062 (0.0010) -[2023-10-16 04:02:21,912][05219] Updated weights for policy 1, policy_version 31940 (0.0008) -[2023-10-16 04:02:22,309][05219] Updated weights for policy 1, policy_version 31950 (0.0008) -[2023-10-16 04:02:22,350][03835] Fps is (10 sec: 16383.5, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 65536000. Throughput: 0: 1797.2, 1: 1797.5. Samples: 16397194. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-16 04:02:22,352][03835] Avg episode reward: [(0, '5.670'), (1, '5.480')] -[2023-10-16 04:02:22,672][05219] Updated weights for policy 1, policy_version 31960 (0.0007) -[2023-10-16 04:02:25,327][05218] Updated weights for policy 0, policy_version 32072 (0.0007) -[2023-10-16 04:02:25,698][05218] Updated weights for policy 0, policy_version 32082 (0.0008) -[2023-10-16 04:02:26,077][05218] Updated weights for policy 0, policy_version 32092 (0.0009) -[2023-10-16 04:02:26,456][05219] Updated weights for policy 1, policy_version 31970 (0.0009) -[2023-10-16 04:02:26,817][05219] Updated weights for policy 1, policy_version 31980 (0.0007) -[2023-10-16 04:02:27,179][05219] Updated weights for policy 1, policy_version 31990 (0.0010) -[2023-10-16 04:02:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 65601536. Throughput: 0: 1808.0, 1: 1767.8. Samples: 16408160. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-16 04:02:27,351][03835] Avg episode reward: [(0, '6.390'), (1, '6.000')] -[2023-10-16 04:02:27,539][05219] Updated weights for policy 1, policy_version 32000 (0.0008) -[2023-10-16 04:02:29,734][05218] Updated weights for policy 0, policy_version 32102 (0.0009) -[2023-10-16 04:02:30,116][05218] Updated weights for policy 0, policy_version 32112 (0.0007) -[2023-10-16 04:02:30,497][05218] Updated weights for policy 0, policy_version 32122 (0.0008) -[2023-10-16 04:02:31,417][05219] Updated weights for policy 1, policy_version 32010 (0.0007) -[2023-10-16 04:02:31,773][05219] Updated weights for policy 1, policy_version 32020 (0.0007) -[2023-10-16 04:02:32,143][05219] Updated weights for policy 1, policy_version 32030 (0.0007) -[2023-10-16 04:02:32,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 65699840. Throughput: 0: 1790.1, 1: 1801.3. Samples: 16429378. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-16 04:02:32,351][03835] Avg episode reward: [(0, '6.170'), (1, '6.330')] -[2023-10-16 04:02:34,160][05218] Updated weights for policy 0, policy_version 32132 (0.0009) -[2023-10-16 04:02:34,534][05218] Updated weights for policy 0, policy_version 32142 (0.0011) -[2023-10-16 04:02:34,911][05218] Updated weights for policy 0, policy_version 32152 (0.0008) -[2023-10-16 04:02:35,854][05219] Updated weights for policy 1, policy_version 32040 (0.0008) -[2023-10-16 04:02:36,221][05219] Updated weights for policy 1, policy_version 32050 (0.0007) -[2023-10-16 04:02:36,593][05219] Updated weights for policy 1, policy_version 32060 (0.0009) -[2023-10-16 04:02:37,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 65765376. Throughput: 0: 1799.1, 1: 1777.6. Samples: 16450766. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-16 04:02:37,352][03835] Avg episode reward: [(0, '5.630'), (1, '6.380')] -[2023-10-16 04:02:38,833][05218] Updated weights for policy 0, policy_version 32162 (0.0008) -[2023-10-16 04:02:39,243][05218] Updated weights for policy 0, policy_version 32172 (0.0012) -[2023-10-16 04:02:39,617][05218] Updated weights for policy 0, policy_version 32182 (0.0009) -[2023-10-16 04:02:39,990][05218] Updated weights for policy 0, policy_version 32192 (0.0008) -[2023-10-16 04:02:40,330][05219] Updated weights for policy 1, policy_version 32070 (0.0009) -[2023-10-16 04:02:40,701][05219] Updated weights for policy 1, policy_version 32080 (0.0008) -[2023-10-16 04:02:41,070][05219] Updated weights for policy 1, policy_version 32090 (0.0009) -[2023-10-16 04:02:42,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 65830912. Throughput: 0: 1795.2, 1: 1803.2. Samples: 16461730. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-16 04:02:42,351][03835] Avg episode reward: [(0, '6.270'), (1, '6.110')] -[2023-10-16 04:02:43,754][05218] Updated weights for policy 0, policy_version 32202 (0.0008) -[2023-10-16 04:02:44,127][05218] Updated weights for policy 0, policy_version 32212 (0.0007) -[2023-10-16 04:02:44,506][05218] Updated weights for policy 0, policy_version 32222 (0.0007) -[2023-10-16 04:02:44,855][05219] Updated weights for policy 1, policy_version 32100 (0.0007) -[2023-10-16 04:02:45,216][05219] Updated weights for policy 1, policy_version 32110 (0.0010) -[2023-10-16 04:02:45,583][05219] Updated weights for policy 1, policy_version 32120 (0.0007) -[2023-10-16 04:02:47,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 65896448. Throughput: 0: 1791.8, 1: 1780.7. Samples: 16482712. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-16 04:02:47,351][03835] Avg episode reward: [(0, '6.210'), (1, '6.800')] -[2023-10-16 04:02:47,352][04891] Saving new best policy, reward=6.800! -[2023-10-16 04:02:48,125][05218] Updated weights for policy 0, policy_version 32232 (0.0010) -[2023-10-16 04:02:48,505][05218] Updated weights for policy 0, policy_version 32242 (0.0008) -[2023-10-16 04:02:48,873][05218] Updated weights for policy 0, policy_version 32252 (0.0008) -[2023-10-16 04:02:49,390][05219] Updated weights for policy 1, policy_version 32130 (0.0008) -[2023-10-16 04:02:49,757][05219] Updated weights for policy 1, policy_version 32140 (0.0008) -[2023-10-16 04:02:50,121][05219] Updated weights for policy 1, policy_version 32150 (0.0008) -[2023-10-16 04:02:50,478][05219] Updated weights for policy 1, policy_version 32160 (0.0009) -[2023-10-16 04:02:52,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 65961984. Throughput: 0: 1809.2, 1: 1783.2. Samples: 16505412. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-16 04:02:52,351][03835] Avg episode reward: [(0, '5.880'), (1, '5.380')] -[2023-10-16 04:02:52,541][05218] Updated weights for policy 0, policy_version 32262 (0.0009) -[2023-10-16 04:02:52,905][05218] Updated weights for policy 0, policy_version 32272 (0.0009) -[2023-10-16 04:02:53,276][05218] Updated weights for policy 0, policy_version 32282 (0.0011) -[2023-10-16 04:02:54,184][05219] Updated weights for policy 1, policy_version 32170 (0.0010) -[2023-10-16 04:02:54,544][05219] Updated weights for policy 1, policy_version 32180 (0.0008) -[2023-10-16 04:02:54,916][05219] Updated weights for policy 1, policy_version 32190 (0.0007) -[2023-10-16 04:02:57,110][05218] Updated weights for policy 0, policy_version 32292 (0.0010) -[2023-10-16 04:02:57,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 66027520. Throughput: 0: 1790.4, 1: 1785.3. Samples: 16515056. Policy #0 lag: (min: 29.0, avg: 30.3, max: 54.0) -[2023-10-16 04:02:57,351][03835] Avg episode reward: [(0, '6.290'), (1, '5.880')] -[2023-10-16 04:02:57,492][05218] Updated weights for policy 0, policy_version 32302 (0.0010) -[2023-10-16 04:02:57,868][05218] Updated weights for policy 0, policy_version 32312 (0.0010) -[2023-10-16 04:02:58,895][05219] Updated weights for policy 1, policy_version 32200 (0.0008) -[2023-10-16 04:02:59,257][05219] Updated weights for policy 1, policy_version 32210 (0.0008) -[2023-10-16 04:02:59,620][05219] Updated weights for policy 1, policy_version 32220 (0.0008) -[2023-10-16 04:03:01,643][05218] Updated weights for policy 0, policy_version 32322 (0.0009) -[2023-10-16 04:03:02,020][05218] Updated weights for policy 0, policy_version 32332 (0.0010) -[2023-10-16 04:03:02,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 66093056. Throughput: 0: 1799.3, 1: 1772.7. Samples: 16536826. Policy #0 lag: (min: 29.0, avg: 30.3, max: 54.0) -[2023-10-16 04:03:02,351][03835] Avg episode reward: [(0, '6.210'), (1, '5.980')] -[2023-10-16 04:03:02,386][05218] Updated weights for policy 0, policy_version 32342 (0.0011) -[2023-10-16 04:03:02,758][05218] Updated weights for policy 0, policy_version 32352 (0.0010) -[2023-10-16 04:03:03,329][05219] Updated weights for policy 1, policy_version 32230 (0.0011) -[2023-10-16 04:03:03,699][05219] Updated weights for policy 1, policy_version 32240 (0.0010) -[2023-10-16 04:03:04,064][05219] Updated weights for policy 1, policy_version 32250 (0.0007) -[2023-10-16 04:03:06,549][05218] Updated weights for policy 0, policy_version 32362 (0.0009) -[2023-10-16 04:03:06,923][05218] Updated weights for policy 0, policy_version 32372 (0.0007) -[2023-10-16 04:03:07,295][05218] Updated weights for policy 0, policy_version 32382 (0.0008) -[2023-10-16 04:03:07,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 66158592. Throughput: 0: 1783.5, 1: 1789.5. Samples: 16557978. Policy #0 lag: (min: 29.0, avg: 30.3, max: 54.0) -[2023-10-16 04:03:07,352][03835] Avg episode reward: [(0, '5.800'), (1, '6.380')] -[2023-10-16 04:03:07,944][05219] Updated weights for policy 1, policy_version 32260 (0.0008) -[2023-10-16 04:03:08,325][05219] Updated weights for policy 1, policy_version 32270 (0.0008) -[2023-10-16 04:03:08,694][05219] Updated weights for policy 1, policy_version 32280 (0.0007) -[2023-10-16 04:03:10,974][05218] Updated weights for policy 0, policy_version 32392 (0.0010) -[2023-10-16 04:03:11,354][05218] Updated weights for policy 0, policy_version 32402 (0.0009) -[2023-10-16 04:03:11,721][05218] Updated weights for policy 0, policy_version 32412 (0.0009) -[2023-10-16 04:03:12,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 66256896. Throughput: 0: 1790.6, 1: 1782.1. Samples: 16568932. Policy #0 lag: (min: 29.0, avg: 30.3, max: 54.0) -[2023-10-16 04:03:12,351][03835] Avg episode reward: [(0, '6.440'), (1, '6.390')] -[2023-10-16 04:03:12,489][05219] Updated weights for policy 1, policy_version 32290 (0.0008) -[2023-10-16 04:03:12,857][05219] Updated weights for policy 1, policy_version 32300 (0.0008) -[2023-10-16 04:03:13,224][05219] Updated weights for policy 1, policy_version 32310 (0.0008) -[2023-10-16 04:03:13,585][05219] Updated weights for policy 1, policy_version 32320 (0.0007) -[2023-10-16 04:03:15,536][05218] Updated weights for policy 0, policy_version 32422 (0.0010) -[2023-10-16 04:03:15,904][05218] Updated weights for policy 0, policy_version 32432 (0.0009) -[2023-10-16 04:03:16,277][05218] Updated weights for policy 0, policy_version 32442 (0.0009) -[2023-10-16 04:03:17,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 66322432. Throughput: 0: 1788.7, 1: 1784.8. Samples: 16590188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:03:17,351][03835] Avg episode reward: [(0, '6.250'), (1, '6.490')] -[2023-10-16 04:03:17,362][05219] Updated weights for policy 1, policy_version 32330 (0.0008) -[2023-10-16 04:03:17,727][05219] Updated weights for policy 1, policy_version 32340 (0.0007) -[2023-10-16 04:03:18,096][05219] Updated weights for policy 1, policy_version 32350 (0.0008) -[2023-10-16 04:03:19,881][05218] Updated weights for policy 0, policy_version 32452 (0.0007) -[2023-10-16 04:03:20,254][05218] Updated weights for policy 0, policy_version 32462 (0.0009) -[2023-10-16 04:03:20,622][05218] Updated weights for policy 0, policy_version 32472 (0.0009) -[2023-10-16 04:03:21,802][05219] Updated weights for policy 1, policy_version 32360 (0.0008) -[2023-10-16 04:03:22,175][05219] Updated weights for policy 1, policy_version 32370 (0.0009) -[2023-10-16 04:03:22,351][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 66387968. Throughput: 0: 1782.1, 1: 1796.2. Samples: 16611792. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:03:22,352][03835] Avg episode reward: [(0, '6.750'), (1, '6.420')] -[2023-10-16 04:03:22,362][04766] Saving new best policy, reward=6.750! -[2023-10-16 04:03:22,550][05219] Updated weights for policy 1, policy_version 32380 (0.0008) -[2023-10-16 04:03:24,423][05218] Updated weights for policy 0, policy_version 32482 (0.0010) -[2023-10-16 04:03:24,814][05218] Updated weights for policy 0, policy_version 32492 (0.0007) -[2023-10-16 04:03:25,194][05218] Updated weights for policy 0, policy_version 32502 (0.0007) -[2023-10-16 04:03:25,564][05218] Updated weights for policy 0, policy_version 32512 (0.0007) -[2023-10-16 04:03:26,152][05219] Updated weights for policy 1, policy_version 32390 (0.0009) -[2023-10-16 04:03:26,512][05219] Updated weights for policy 1, policy_version 32400 (0.0011) -[2023-10-16 04:03:26,887][05219] Updated weights for policy 1, policy_version 32410 (0.0010) -[2023-10-16 04:03:27,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 66486272. Throughput: 0: 1791.5, 1: 1784.4. Samples: 16622646. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:03:27,351][03835] Avg episode reward: [(0, '6.630'), (1, '5.970')] -[2023-10-16 04:03:29,259][05218] Updated weights for policy 0, policy_version 32522 (0.0009) -[2023-10-16 04:03:29,646][05218] Updated weights for policy 0, policy_version 32532 (0.0007) -[2023-10-16 04:03:30,024][05218] Updated weights for policy 0, policy_version 32542 (0.0010) -[2023-10-16 04:03:30,514][05219] Updated weights for policy 1, policy_version 32420 (0.0010) -[2023-10-16 04:03:30,886][05219] Updated weights for policy 1, policy_version 32430 (0.0008) -[2023-10-16 04:03:31,246][05219] Updated weights for policy 1, policy_version 32440 (0.0008) -[2023-10-16 04:03:32,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 66551808. Throughput: 0: 1782.4, 1: 1797.2. Samples: 16643794. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:03:32,351][03835] Avg episode reward: [(0, '6.200'), (1, '6.390')] -[2023-10-16 04:03:33,680][05218] Updated weights for policy 0, policy_version 32552 (0.0009) -[2023-10-16 04:03:34,054][05218] Updated weights for policy 0, policy_version 32562 (0.0009) -[2023-10-16 04:03:34,421][05218] Updated weights for policy 0, policy_version 32572 (0.0008) -[2023-10-16 04:03:35,115][05219] Updated weights for policy 1, policy_version 32450 (0.0007) -[2023-10-16 04:03:35,487][05219] Updated weights for policy 1, policy_version 32460 (0.0007) -[2023-10-16 04:03:35,851][05219] Updated weights for policy 1, policy_version 32470 (0.0007) -[2023-10-16 04:03:36,215][05219] Updated weights for policy 1, policy_version 32480 (0.0008) -[2023-10-16 04:03:37,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 66617344. Throughput: 0: 1784.1, 1: 1783.8. Samples: 16665970. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:03:37,351][03835] Avg episode reward: [(0, '6.290'), (1, '6.070')] -[2023-10-16 04:03:37,360][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000032480_33259520.pth... -[2023-10-16 04:03:37,361][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000032576_33357824.pth... -[2023-10-16 04:03:37,395][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000030816_31555584.pth -[2023-10-16 04:03:37,397][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000030912_31653888.pth -[2023-10-16 04:03:38,282][05218] Updated weights for policy 0, policy_version 32582 (0.0008) -[2023-10-16 04:03:38,654][05218] Updated weights for policy 0, policy_version 32592 (0.0008) -[2023-10-16 04:03:39,028][05218] Updated weights for policy 0, policy_version 32602 (0.0009) -[2023-10-16 04:03:39,840][05219] Updated weights for policy 1, policy_version 32490 (0.0008) -[2023-10-16 04:03:40,215][05219] Updated weights for policy 1, policy_version 32500 (0.0007) -[2023-10-16 04:03:40,593][05219] Updated weights for policy 1, policy_version 32510 (0.0009) -[2023-10-16 04:03:42,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 66682880. Throughput: 0: 1785.8, 1: 1802.4. Samples: 16676526. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-16 04:03:42,352][03835] Avg episode reward: [(0, '5.590'), (1, '6.160')] -[2023-10-16 04:03:42,738][05218] Updated weights for policy 0, policy_version 32612 (0.0010) -[2023-10-16 04:03:43,102][05218] Updated weights for policy 0, policy_version 32622 (0.0007) -[2023-10-16 04:03:43,475][05218] Updated weights for policy 0, policy_version 32632 (0.0009) -[2023-10-16 04:03:44,340][05219] Updated weights for policy 1, policy_version 32520 (0.0009) -[2023-10-16 04:03:44,703][05219] Updated weights for policy 1, policy_version 32530 (0.0008) -[2023-10-16 04:03:45,066][05219] Updated weights for policy 1, policy_version 32540 (0.0010) -[2023-10-16 04:03:47,217][05218] Updated weights for policy 0, policy_version 32642 (0.0009) -[2023-10-16 04:03:47,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 66748416. Throughput: 0: 1791.9, 1: 1797.9. Samples: 16698368. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-16 04:03:47,351][03835] Avg episode reward: [(0, '5.810'), (1, '5.780')] -[2023-10-16 04:03:47,593][05218] Updated weights for policy 0, policy_version 32652 (0.0011) -[2023-10-16 04:03:47,980][05218] Updated weights for policy 0, policy_version 32662 (0.0008) -[2023-10-16 04:03:48,352][05218] Updated weights for policy 0, policy_version 32672 (0.0009) -[2023-10-16 04:03:48,793][05219] Updated weights for policy 1, policy_version 32550 (0.0010) -[2023-10-16 04:03:49,163][05219] Updated weights for policy 1, policy_version 32560 (0.0009) -[2023-10-16 04:03:49,540][05219] Updated weights for policy 1, policy_version 32570 (0.0010) -[2023-10-16 04:03:52,131][05218] Updated weights for policy 0, policy_version 32682 (0.0008) -[2023-10-16 04:03:52,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 66813952. Throughput: 0: 1809.6, 1: 1797.8. Samples: 16720308. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-16 04:03:52,352][03835] Avg episode reward: [(0, '6.070'), (1, '6.020')] -[2023-10-16 04:03:52,493][05218] Updated weights for policy 0, policy_version 32692 (0.0008) -[2023-10-16 04:03:52,869][05218] Updated weights for policy 0, policy_version 32702 (0.0008) -[2023-10-16 04:03:53,312][05219] Updated weights for policy 1, policy_version 32580 (0.0009) -[2023-10-16 04:03:53,703][05219] Updated weights for policy 1, policy_version 32590 (0.0007) -[2023-10-16 04:03:54,057][05219] Updated weights for policy 1, policy_version 32600 (0.0009) -[2023-10-16 04:03:56,626][05218] Updated weights for policy 0, policy_version 32712 (0.0008) -[2023-10-16 04:03:56,999][05218] Updated weights for policy 0, policy_version 32722 (0.0007) -[2023-10-16 04:03:57,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 66879488. Throughput: 0: 1795.3, 1: 1800.4. Samples: 16730738. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-16 04:03:57,351][03835] Avg episode reward: [(0, '6.210'), (1, '6.190')] -[2023-10-16 04:03:57,368][05218] Updated weights for policy 0, policy_version 32732 (0.0010) -[2023-10-16 04:03:57,750][05219] Updated weights for policy 1, policy_version 32610 (0.0008) -[2023-10-16 04:03:58,116][05219] Updated weights for policy 1, policy_version 32620 (0.0007) -[2023-10-16 04:03:58,478][05219] Updated weights for policy 1, policy_version 32630 (0.0007) -[2023-10-16 04:03:58,842][05219] Updated weights for policy 1, policy_version 32640 (0.0007) -[2023-10-16 04:04:01,111][05218] Updated weights for policy 0, policy_version 32742 (0.0008) -[2023-10-16 04:04:01,499][05218] Updated weights for policy 0, policy_version 32752 (0.0009) -[2023-10-16 04:04:01,876][05218] Updated weights for policy 0, policy_version 32762 (0.0009) -[2023-10-16 04:04:02,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 66977792. Throughput: 0: 1810.8, 1: 1793.3. Samples: 16752374. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-16 04:04:02,351][03835] Avg episode reward: [(0, '5.570'), (1, '5.850')] -[2023-10-16 04:04:02,627][05219] Updated weights for policy 1, policy_version 32650 (0.0007) -[2023-10-16 04:04:02,995][05219] Updated weights for policy 1, policy_version 32660 (0.0008) -[2023-10-16 04:04:03,350][05219] Updated weights for policy 1, policy_version 32670 (0.0007) -[2023-10-16 04:04:05,461][05218] Updated weights for policy 0, policy_version 32772 (0.0010) -[2023-10-16 04:04:05,839][05218] Updated weights for policy 0, policy_version 32782 (0.0011) -[2023-10-16 04:04:06,218][05218] Updated weights for policy 0, policy_version 32792 (0.0007) -[2023-10-16 04:04:07,244][05219] Updated weights for policy 1, policy_version 32680 (0.0009) -[2023-10-16 04:04:07,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 67043328. Throughput: 0: 1794.9, 1: 1803.2. Samples: 16773706. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-16 04:04:07,351][03835] Avg episode reward: [(0, '6.160'), (1, '6.030')] -[2023-10-16 04:04:07,616][05219] Updated weights for policy 1, policy_version 32690 (0.0007) -[2023-10-16 04:04:07,980][05219] Updated weights for policy 1, policy_version 32700 (0.0008) -[2023-10-16 04:04:09,970][05218] Updated weights for policy 0, policy_version 32802 (0.0007) -[2023-10-16 04:04:10,361][05218] Updated weights for policy 0, policy_version 32812 (0.0009) -[2023-10-16 04:04:10,731][05218] Updated weights for policy 0, policy_version 32822 (0.0009) -[2023-10-16 04:04:11,102][05218] Updated weights for policy 0, policy_version 32832 (0.0010) -[2023-10-16 04:04:11,817][05219] Updated weights for policy 1, policy_version 32710 (0.0008) -[2023-10-16 04:04:12,191][05219] Updated weights for policy 1, policy_version 32720 (0.0009) -[2023-10-16 04:04:12,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 67108864. Throughput: 0: 1812.9, 1: 1787.1. Samples: 16784646. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-16 04:04:12,351][03835] Avg episode reward: [(0, '6.040'), (1, '5.640')] -[2023-10-16 04:04:12,559][05219] Updated weights for policy 1, policy_version 32730 (0.0007) -[2023-10-16 04:04:14,910][05218] Updated weights for policy 0, policy_version 32842 (0.0010) -[2023-10-16 04:04:15,295][05218] Updated weights for policy 0, policy_version 32852 (0.0011) -[2023-10-16 04:04:15,660][05218] Updated weights for policy 0, policy_version 32862 (0.0008) -[2023-10-16 04:04:16,292][05219] Updated weights for policy 1, policy_version 32740 (0.0007) -[2023-10-16 04:04:16,662][05219] Updated weights for policy 1, policy_version 32750 (0.0007) -[2023-10-16 04:04:17,022][05219] Updated weights for policy 1, policy_version 32760 (0.0008) -[2023-10-16 04:04:17,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 67207168. Throughput: 0: 1797.5, 1: 1806.2. Samples: 16805960. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-16 04:04:17,351][03835] Avg episode reward: [(0, '6.010'), (1, '5.850')] -[2023-10-16 04:04:19,278][05218] Updated weights for policy 0, policy_version 32872 (0.0010) -[2023-10-16 04:04:19,645][05218] Updated weights for policy 0, policy_version 32882 (0.0010) -[2023-10-16 04:04:20,028][05218] Updated weights for policy 0, policy_version 32892 (0.0009) -[2023-10-16 04:04:20,919][05219] Updated weights for policy 1, policy_version 32770 (0.0008) -[2023-10-16 04:04:21,279][05219] Updated weights for policy 1, policy_version 32780 (0.0008) -[2023-10-16 04:04:21,653][05219] Updated weights for policy 1, policy_version 32790 (0.0007) -[2023-10-16 04:04:22,013][05219] Updated weights for policy 1, policy_version 32800 (0.0008) -[2023-10-16 04:04:22,350][03835] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 67272704. Throughput: 0: 1799.9, 1: 1782.5. Samples: 16827178. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-16 04:04:22,351][03835] Avg episode reward: [(0, '6.200'), (1, '5.810')] -[2023-10-16 04:04:23,750][05218] Updated weights for policy 0, policy_version 32902 (0.0008) -[2023-10-16 04:04:24,124][05218] Updated weights for policy 0, policy_version 32912 (0.0009) -[2023-10-16 04:04:24,504][05218] Updated weights for policy 0, policy_version 32922 (0.0009) -[2023-10-16 04:04:25,738][05219] Updated weights for policy 1, policy_version 32810 (0.0009) -[2023-10-16 04:04:26,106][05219] Updated weights for policy 1, policy_version 32820 (0.0010) -[2023-10-16 04:04:26,467][05219] Updated weights for policy 1, policy_version 32830 (0.0007) -[2023-10-16 04:04:27,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 67338240. Throughput: 0: 1800.6, 1: 1796.8. Samples: 16838412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:04:27,351][03835] Avg episode reward: [(0, '6.220'), (1, '5.810')] -[2023-10-16 04:04:28,136][05218] Updated weights for policy 0, policy_version 32932 (0.0009) -[2023-10-16 04:04:28,522][05218] Updated weights for policy 0, policy_version 32942 (0.0009) -[2023-10-16 04:04:28,902][05218] Updated weights for policy 0, policy_version 32952 (0.0008) -[2023-10-16 04:04:30,233][05219] Updated weights for policy 1, policy_version 32840 (0.0008) -[2023-10-16 04:04:30,597][05219] Updated weights for policy 1, policy_version 32850 (0.0009) -[2023-10-16 04:04:30,970][05219] Updated weights for policy 1, policy_version 32860 (0.0008) -[2023-10-16 04:04:32,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 67403776. Throughput: 0: 1805.6, 1: 1781.3. Samples: 16859778. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:04:32,352][03835] Avg episode reward: [(0, '6.060'), (1, '5.610')] -[2023-10-16 04:04:32,565][05218] Updated weights for policy 0, policy_version 32962 (0.0010) -[2023-10-16 04:04:32,946][05218] Updated weights for policy 0, policy_version 32972 (0.0007) -[2023-10-16 04:04:33,324][05218] Updated weights for policy 0, policy_version 32982 (0.0007) -[2023-10-16 04:04:33,701][05218] Updated weights for policy 0, policy_version 32992 (0.0007) -[2023-10-16 04:04:34,745][05219] Updated weights for policy 1, policy_version 32870 (0.0008) -[2023-10-16 04:04:35,121][05219] Updated weights for policy 1, policy_version 32880 (0.0009) -[2023-10-16 04:04:35,478][05219] Updated weights for policy 1, policy_version 32890 (0.0008) -[2023-10-16 04:04:37,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 67469312. Throughput: 0: 1816.7, 1: 1772.1. Samples: 16881804. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:04:37,351][03835] Avg episode reward: [(0, '5.930'), (1, '5.770')] -[2023-10-16 04:04:37,376][05218] Updated weights for policy 0, policy_version 33002 (0.0009) -[2023-10-16 04:04:37,751][05218] Updated weights for policy 0, policy_version 33012 (0.0007) -[2023-10-16 04:04:38,137][05218] Updated weights for policy 0, policy_version 33022 (0.0008) -[2023-10-16 04:04:39,392][05219] Updated weights for policy 1, policy_version 32900 (0.0009) -[2023-10-16 04:04:39,769][05219] Updated weights for policy 1, policy_version 32910 (0.0008) -[2023-10-16 04:04:40,131][05219] Updated weights for policy 1, policy_version 32920 (0.0007) -[2023-10-16 04:04:41,922][05218] Updated weights for policy 0, policy_version 33032 (0.0008) -[2023-10-16 04:04:42,293][05218] Updated weights for policy 0, policy_version 33042 (0.0009) -[2023-10-16 04:04:42,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.6, 300 sec: 14218.0). Total num frames: 67534848. Throughput: 0: 1809.3, 1: 1782.9. Samples: 16892384. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:04:42,351][03835] Avg episode reward: [(0, '5.780'), (1, '6.060')] -[2023-10-16 04:04:42,672][05218] Updated weights for policy 0, policy_version 33052 (0.0007) -[2023-10-16 04:04:43,952][05219] Updated weights for policy 1, policy_version 32930 (0.0008) -[2023-10-16 04:04:44,314][05219] Updated weights for policy 1, policy_version 32940 (0.0011) -[2023-10-16 04:04:44,690][05219] Updated weights for policy 1, policy_version 32950 (0.0009) -[2023-10-16 04:04:45,050][05219] Updated weights for policy 1, policy_version 32960 (0.0008) -[2023-10-16 04:04:46,415][05218] Updated weights for policy 0, policy_version 33062 (0.0009) -[2023-10-16 04:04:46,788][05218] Updated weights for policy 0, policy_version 33072 (0.0010) -[2023-10-16 04:04:47,172][05218] Updated weights for policy 0, policy_version 33082 (0.0010) -[2023-10-16 04:04:47,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 67600384. Throughput: 0: 1816.3, 1: 1772.7. Samples: 16913882. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:04:47,352][03835] Avg episode reward: [(0, '5.650'), (1, '5.960')] -[2023-10-16 04:04:48,821][05219] Updated weights for policy 1, policy_version 32970 (0.0010) -[2023-10-16 04:04:49,181][05219] Updated weights for policy 1, policy_version 32980 (0.0010) -[2023-10-16 04:04:49,546][05219] Updated weights for policy 1, policy_version 32990 (0.0010) -[2023-10-16 04:04:50,832][05218] Updated weights for policy 0, policy_version 33092 (0.0009) -[2023-10-16 04:04:51,213][05218] Updated weights for policy 0, policy_version 33102 (0.0007) -[2023-10-16 04:04:51,590][05218] Updated weights for policy 0, policy_version 33112 (0.0007) -[2023-10-16 04:04:52,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 67698688. Throughput: 0: 1804.8, 1: 1780.4. Samples: 16935036. Policy #0 lag: (min: 21.0, avg: 44.4, max: 48.0) -[2023-10-16 04:04:52,351][03835] Avg episode reward: [(0, '6.000'), (1, '6.350')] -[2023-10-16 04:04:53,260][05219] Updated weights for policy 1, policy_version 33000 (0.0010) -[2023-10-16 04:04:53,632][05219] Updated weights for policy 1, policy_version 33010 (0.0009) -[2023-10-16 04:04:54,000][05219] Updated weights for policy 1, policy_version 33020 (0.0008) -[2023-10-16 04:04:55,275][05218] Updated weights for policy 0, policy_version 33122 (0.0008) -[2023-10-16 04:04:55,693][05218] Updated weights for policy 0, policy_version 33132 (0.0010) -[2023-10-16 04:04:56,058][05218] Updated weights for policy 0, policy_version 33142 (0.0008) -[2023-10-16 04:04:56,431][05218] Updated weights for policy 0, policy_version 33152 (0.0010) -[2023-10-16 04:04:57,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 67764224. Throughput: 0: 1815.1, 1: 1774.5. Samples: 16946180. Policy #0 lag: (min: 21.0, avg: 44.4, max: 48.0) -[2023-10-16 04:04:57,351][03835] Avg episode reward: [(0, '5.920'), (1, '5.970')] -[2023-10-16 04:04:57,766][05219] Updated weights for policy 1, policy_version 33030 (0.0009) -[2023-10-16 04:04:58,143][05219] Updated weights for policy 1, policy_version 33040 (0.0009) -[2023-10-16 04:04:58,510][05219] Updated weights for policy 1, policy_version 33050 (0.0009) -[2023-10-16 04:05:00,152][05218] Updated weights for policy 0, policy_version 33162 (0.0007) -[2023-10-16 04:05:00,529][05218] Updated weights for policy 0, policy_version 33172 (0.0008) -[2023-10-16 04:05:00,896][05218] Updated weights for policy 0, policy_version 33182 (0.0010) -[2023-10-16 04:05:02,332][05219] Updated weights for policy 1, policy_version 33060 (0.0009) -[2023-10-16 04:05:02,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 67829760. Throughput: 0: 1809.5, 1: 1772.4. Samples: 16967146. Policy #0 lag: (min: 21.0, avg: 44.4, max: 48.0) -[2023-10-16 04:05:02,351][03835] Avg episode reward: [(0, '6.530'), (1, '6.180')] -[2023-10-16 04:05:02,697][05219] Updated weights for policy 1, policy_version 33070 (0.0008) -[2023-10-16 04:05:03,073][05219] Updated weights for policy 1, policy_version 33080 (0.0008) -[2023-10-16 04:05:04,562][05218] Updated weights for policy 0, policy_version 33192 (0.0008) -[2023-10-16 04:05:04,928][05218] Updated weights for policy 0, policy_version 33202 (0.0008) -[2023-10-16 04:05:05,308][05218] Updated weights for policy 0, policy_version 33212 (0.0009) -[2023-10-16 04:05:06,775][05219] Updated weights for policy 1, policy_version 33090 (0.0009) -[2023-10-16 04:05:07,149][05219] Updated weights for policy 1, policy_version 33100 (0.0010) -[2023-10-16 04:05:07,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 67895296. Throughput: 0: 1802.3, 1: 1798.5. Samples: 16989210. Policy #0 lag: (min: 21.0, avg: 44.4, max: 48.0) -[2023-10-16 04:05:07,351][03835] Avg episode reward: [(0, '6.630'), (1, '5.810')] -[2023-10-16 04:05:07,512][05219] Updated weights for policy 1, policy_version 33110 (0.0010) -[2023-10-16 04:05:07,880][05219] Updated weights for policy 1, policy_version 33120 (0.0010) -[2023-10-16 04:05:08,932][05218] Updated weights for policy 0, policy_version 33222 (0.0010) -[2023-10-16 04:05:09,306][05218] Updated weights for policy 0, policy_version 33232 (0.0010) -[2023-10-16 04:05:09,686][05218] Updated weights for policy 0, policy_version 33242 (0.0008) -[2023-10-16 04:05:11,857][05219] Updated weights for policy 1, policy_version 33130 (0.0008) -[2023-10-16 04:05:12,219][05219] Updated weights for policy 1, policy_version 33140 (0.0007) -[2023-10-16 04:05:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 67960832. Throughput: 0: 1805.6, 1: 1771.6. Samples: 16999390. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-16 04:05:12,351][03835] Avg episode reward: [(0, '5.830'), (1, '5.810')] -[2023-10-16 04:05:12,577][05219] Updated weights for policy 1, policy_version 33150 (0.0009) -[2023-10-16 04:05:13,534][05218] Updated weights for policy 0, policy_version 33252 (0.0009) -[2023-10-16 04:05:13,908][05218] Updated weights for policy 0, policy_version 33262 (0.0009) -[2023-10-16 04:05:14,284][05218] Updated weights for policy 0, policy_version 33272 (0.0009) -[2023-10-16 04:05:16,508][05219] Updated weights for policy 1, policy_version 33160 (0.0009) -[2023-10-16 04:05:16,873][05219] Updated weights for policy 1, policy_version 33170 (0.0010) -[2023-10-16 04:05:17,237][05219] Updated weights for policy 1, policy_version 33180 (0.0010) -[2023-10-16 04:05:17,350][03835] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 14329.1). Total num frames: 68026368. Throughput: 0: 1800.5, 1: 1799.7. Samples: 17021790. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-16 04:05:17,352][03835] Avg episode reward: [(0, '6.280'), (1, '5.990')] -[2023-10-16 04:05:18,058][05218] Updated weights for policy 0, policy_version 33282 (0.0008) -[2023-10-16 04:05:18,433][05218] Updated weights for policy 0, policy_version 33292 (0.0009) -[2023-10-16 04:05:18,816][05218] Updated weights for policy 0, policy_version 33302 (0.0009) -[2023-10-16 04:05:19,188][05218] Updated weights for policy 0, policy_version 33312 (0.0009) -[2023-10-16 04:05:20,884][05219] Updated weights for policy 1, policy_version 33190 (0.0009) -[2023-10-16 04:05:21,255][05219] Updated weights for policy 1, policy_version 33200 (0.0010) -[2023-10-16 04:05:21,610][05219] Updated weights for policy 1, policy_version 33210 (0.0008) -[2023-10-16 04:05:22,351][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 68124672. Throughput: 0: 1811.0, 1: 1774.0. Samples: 17043132. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-16 04:05:22,352][03835] Avg episode reward: [(0, '5.820'), (1, '6.660')] -[2023-10-16 04:05:22,869][05218] Updated weights for policy 0, policy_version 33322 (0.0009) -[2023-10-16 04:05:23,236][05218] Updated weights for policy 0, policy_version 33332 (0.0008) -[2023-10-16 04:05:23,612][05218] Updated weights for policy 0, policy_version 33342 (0.0007) -[2023-10-16 04:05:25,433][05219] Updated weights for policy 1, policy_version 33220 (0.0007) -[2023-10-16 04:05:25,814][05219] Updated weights for policy 1, policy_version 33230 (0.0007) -[2023-10-16 04:05:26,175][05219] Updated weights for policy 1, policy_version 33240 (0.0008) -[2023-10-16 04:05:27,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 68190208. Throughput: 0: 1801.3, 1: 1798.6. Samples: 17054380. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-16 04:05:27,351][03835] Avg episode reward: [(0, '6.220'), (1, '6.400')] -[2023-10-16 04:05:27,432][05218] Updated weights for policy 0, policy_version 33352 (0.0008) -[2023-10-16 04:05:27,811][05218] Updated weights for policy 0, policy_version 33362 (0.0007) -[2023-10-16 04:05:28,188][05218] Updated weights for policy 0, policy_version 33372 (0.0008) -[2023-10-16 04:05:29,941][05219] Updated weights for policy 1, policy_version 33250 (0.0009) -[2023-10-16 04:05:30,305][05219] Updated weights for policy 1, policy_version 33260 (0.0007) -[2023-10-16 04:05:30,673][05219] Updated weights for policy 1, policy_version 33270 (0.0008) -[2023-10-16 04:05:31,041][05219] Updated weights for policy 1, policy_version 33280 (0.0008) -[2023-10-16 04:05:31,834][05218] Updated weights for policy 0, policy_version 33382 (0.0008) -[2023-10-16 04:05:32,208][05218] Updated weights for policy 0, policy_version 33392 (0.0007) -[2023-10-16 04:05:32,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 68255744. Throughput: 0: 1809.5, 1: 1778.6. Samples: 17075346. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-16 04:05:32,351][03835] Avg episode reward: [(0, '6.060'), (1, '6.640')] -[2023-10-16 04:05:32,590][05218] Updated weights for policy 0, policy_version 33402 (0.0007) -[2023-10-16 04:05:34,826][05219] Updated weights for policy 1, policy_version 33290 (0.0010) -[2023-10-16 04:05:35,189][05219] Updated weights for policy 1, policy_version 33300 (0.0011) -[2023-10-16 04:05:35,559][05219] Updated weights for policy 1, policy_version 33310 (0.0009) -[2023-10-16 04:05:36,359][05218] Updated weights for policy 0, policy_version 33412 (0.0010) -[2023-10-16 04:05:36,732][05218] Updated weights for policy 0, policy_version 33422 (0.0007) -[2023-10-16 04:05:37,099][05218] Updated weights for policy 0, policy_version 33432 (0.0008) -[2023-10-16 04:05:37,351][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 68321280. Throughput: 0: 1805.1, 1: 1777.0. Samples: 17096232. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-16 04:05:37,352][03835] Avg episode reward: [(0, '6.180'), (1, '6.420')] -[2023-10-16 04:05:37,365][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000033312_34111488.pth... -[2023-10-16 04:05:37,394][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000031648_32407552.pth -[2023-10-16 04:05:37,398][04891] Saving a milestone ./train_atari/atari_timepilot_APPO/checkpoint_p1/milestones/checkpoint_000033312_34111488.pth -[2023-10-16 04:05:37,401][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000033440_34242560.pth... -[2023-10-16 04:05:37,440][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000031744_32505856.pth -[2023-10-16 04:05:37,446][04766] Saving a milestone ./train_atari/atari_timepilot_APPO/checkpoint_p0/milestones/checkpoint_000033440_34242560.pth -[2023-10-16 04:05:39,223][05219] Updated weights for policy 1, policy_version 33320 (0.0008) -[2023-10-16 04:05:39,595][05219] Updated weights for policy 1, policy_version 33330 (0.0007) -[2023-10-16 04:05:39,962][05219] Updated weights for policy 1, policy_version 33340 (0.0009) -[2023-10-16 04:05:40,879][05218] Updated weights for policy 0, policy_version 33442 (0.0007) -[2023-10-16 04:05:41,275][05218] Updated weights for policy 0, policy_version 33452 (0.0011) -[2023-10-16 04:05:41,651][05218] Updated weights for policy 0, policy_version 33462 (0.0008) -[2023-10-16 04:05:42,028][05218] Updated weights for policy 0, policy_version 33472 (0.0008) -[2023-10-16 04:05:42,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 68419584. Throughput: 0: 1803.0, 1: 1780.6. Samples: 17107444. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-16 04:05:42,352][03835] Avg episode reward: [(0, '6.360'), (1, '6.700')] -[2023-10-16 04:05:43,590][05219] Updated weights for policy 1, policy_version 33350 (0.0010) -[2023-10-16 04:05:43,953][05219] Updated weights for policy 1, policy_version 33360 (0.0009) -[2023-10-16 04:05:44,324][05219] Updated weights for policy 1, policy_version 33370 (0.0011) -[2023-10-16 04:05:45,784][05218] Updated weights for policy 0, policy_version 33482 (0.0011) -[2023-10-16 04:05:46,164][05218] Updated weights for policy 0, policy_version 33492 (0.0010) -[2023-10-16 04:05:46,535][05218] Updated weights for policy 0, policy_version 33502 (0.0008) -[2023-10-16 04:05:47,350][03835] Fps is (10 sec: 16384.6, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 68485120. Throughput: 0: 1803.0, 1: 1783.2. Samples: 17128528. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-16 04:05:47,351][03835] Avg episode reward: [(0, '6.000'), (1, '7.440')] -[2023-10-16 04:05:47,352][04891] Saving new best policy, reward=7.440! -[2023-10-16 04:05:48,205][05219] Updated weights for policy 1, policy_version 33380 (0.0008) -[2023-10-16 04:05:48,559][05219] Updated weights for policy 1, policy_version 33390 (0.0008) -[2023-10-16 04:05:48,925][05219] Updated weights for policy 1, policy_version 33400 (0.0010) -[2023-10-16 04:05:50,261][05218] Updated weights for policy 0, policy_version 33512 (0.0008) -[2023-10-16 04:05:50,635][05218] Updated weights for policy 0, policy_version 33522 (0.0009) -[2023-10-16 04:05:51,016][05218] Updated weights for policy 0, policy_version 33532 (0.0008) -[2023-10-16 04:05:52,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 68550656. Throughput: 0: 1792.8, 1: 1787.0. Samples: 17150300. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-16 04:05:52,351][03835] Avg episode reward: [(0, '6.280'), (1, '6.040')] -[2023-10-16 04:05:52,716][05219] Updated weights for policy 1, policy_version 33410 (0.0007) -[2023-10-16 04:05:53,081][05219] Updated weights for policy 1, policy_version 33420 (0.0007) -[2023-10-16 04:05:53,445][05219] Updated weights for policy 1, policy_version 33430 (0.0008) -[2023-10-16 04:05:53,815][05219] Updated weights for policy 1, policy_version 33440 (0.0007) -[2023-10-16 04:05:54,646][05218] Updated weights for policy 0, policy_version 33542 (0.0007) -[2023-10-16 04:05:55,014][05218] Updated weights for policy 0, policy_version 33552 (0.0008) -[2023-10-16 04:05:55,388][05218] Updated weights for policy 0, policy_version 33562 (0.0008) -[2023-10-16 04:05:57,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 68616192. Throughput: 0: 1802.9, 1: 1783.8. Samples: 17160794. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:05:57,351][03835] Avg episode reward: [(0, '6.290'), (1, '6.190')] -[2023-10-16 04:05:57,497][05219] Updated weights for policy 1, policy_version 33450 (0.0008) -[2023-10-16 04:05:57,866][05219] Updated weights for policy 1, policy_version 33460 (0.0008) -[2023-10-16 04:05:58,233][05219] Updated weights for policy 1, policy_version 33470 (0.0009) -[2023-10-16 04:05:59,202][05218] Updated weights for policy 0, policy_version 33572 (0.0009) -[2023-10-16 04:05:59,583][05218] Updated weights for policy 0, policy_version 33582 (0.0008) -[2023-10-16 04:05:59,955][05218] Updated weights for policy 0, policy_version 33592 (0.0007) -[2023-10-16 04:06:02,038][05219] Updated weights for policy 1, policy_version 33480 (0.0008) -[2023-10-16 04:06:02,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 68681728. Throughput: 0: 1794.0, 1: 1785.1. Samples: 17182848. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:06:02,351][03835] Avg episode reward: [(0, '5.850'), (1, '5.800')] -[2023-10-16 04:06:02,410][05219] Updated weights for policy 1, policy_version 33490 (0.0008) -[2023-10-16 04:06:02,775][05219] Updated weights for policy 1, policy_version 33500 (0.0010) -[2023-10-16 04:06:03,731][05218] Updated weights for policy 0, policy_version 33602 (0.0007) -[2023-10-16 04:06:04,094][05218] Updated weights for policy 0, policy_version 33612 (0.0008) -[2023-10-16 04:06:04,467][05218] Updated weights for policy 0, policy_version 33622 (0.0009) -[2023-10-16 04:06:04,838][05218] Updated weights for policy 0, policy_version 33632 (0.0011) -[2023-10-16 04:06:06,765][05219] Updated weights for policy 1, policy_version 33510 (0.0007) -[2023-10-16 04:06:07,133][05219] Updated weights for policy 1, policy_version 33520 (0.0008) -[2023-10-16 04:06:07,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 68747264. Throughput: 0: 1782.1, 1: 1796.2. Samples: 17204154. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:06:07,351][03835] Avg episode reward: [(0, '5.910'), (1, '5.970')] -[2023-10-16 04:06:07,506][05219] Updated weights for policy 1, policy_version 33530 (0.0007) -[2023-10-16 04:06:08,725][05218] Updated weights for policy 0, policy_version 33642 (0.0010) -[2023-10-16 04:06:09,095][05218] Updated weights for policy 0, policy_version 33652 (0.0009) -[2023-10-16 04:06:09,470][05218] Updated weights for policy 0, policy_version 33662 (0.0007) -[2023-10-16 04:06:11,273][05219] Updated weights for policy 1, policy_version 33540 (0.0007) -[2023-10-16 04:06:11,664][05219] Updated weights for policy 1, policy_version 33550 (0.0008) -[2023-10-16 04:06:12,025][05219] Updated weights for policy 1, policy_version 33560 (0.0008) -[2023-10-16 04:06:12,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 68845568. Throughput: 0: 1784.9, 1: 1781.7. Samples: 17214880. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:06:12,351][03835] Avg episode reward: [(0, '5.930'), (1, '6.410')] -[2023-10-16 04:06:13,140][05218] Updated weights for policy 0, policy_version 33672 (0.0009) -[2023-10-16 04:06:13,513][05218] Updated weights for policy 0, policy_version 33682 (0.0010) -[2023-10-16 04:06:13,892][05218] Updated weights for policy 0, policy_version 33692 (0.0009) -[2023-10-16 04:06:15,866][05219] Updated weights for policy 1, policy_version 33570 (0.0008) -[2023-10-16 04:06:16,231][05219] Updated weights for policy 1, policy_version 33580 (0.0010) -[2023-10-16 04:06:16,592][05219] Updated weights for policy 1, policy_version 33590 (0.0007) -[2023-10-16 04:06:16,961][05219] Updated weights for policy 1, policy_version 33600 (0.0008) -[2023-10-16 04:06:17,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 68911104. Throughput: 0: 1785.0, 1: 1804.9. Samples: 17236890. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:06:17,351][03835] Avg episode reward: [(0, '5.700'), (1, '6.030')] -[2023-10-16 04:06:17,693][05218] Updated weights for policy 0, policy_version 33702 (0.0007) -[2023-10-16 04:06:18,065][05218] Updated weights for policy 0, policy_version 33712 (0.0010) -[2023-10-16 04:06:18,448][05218] Updated weights for policy 0, policy_version 33722 (0.0007) -[2023-10-16 04:06:20,584][05219] Updated weights for policy 1, policy_version 33610 (0.0010) -[2023-10-16 04:06:20,944][05219] Updated weights for policy 1, policy_version 33620 (0.0010) -[2023-10-16 04:06:21,307][05219] Updated weights for policy 1, policy_version 33630 (0.0008) -[2023-10-16 04:06:22,180][05218] Updated weights for policy 0, policy_version 33732 (0.0007) -[2023-10-16 04:06:22,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 68976640. Throughput: 0: 1810.1, 1: 1788.3. Samples: 17258160. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-16 04:06:22,351][03835] Avg episode reward: [(0, '6.360'), (1, '6.070')] -[2023-10-16 04:06:22,561][05218] Updated weights for policy 0, policy_version 33742 (0.0008) -[2023-10-16 04:06:22,945][05218] Updated weights for policy 0, policy_version 33752 (0.0009) -[2023-10-16 04:06:24,962][05219] Updated weights for policy 1, policy_version 33640 (0.0008) -[2023-10-16 04:06:25,327][05219] Updated weights for policy 1, policy_version 33650 (0.0007) -[2023-10-16 04:06:25,696][05219] Updated weights for policy 1, policy_version 33660 (0.0009) -[2023-10-16 04:06:26,574][05218] Updated weights for policy 0, policy_version 33762 (0.0009) -[2023-10-16 04:06:26,981][05218] Updated weights for policy 0, policy_version 33772 (0.0009) -[2023-10-16 04:06:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 69042176. Throughput: 0: 1787.4, 1: 1809.4. Samples: 17269298. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-16 04:06:27,351][03835] Avg episode reward: [(0, '5.700'), (1, '5.340')] -[2023-10-16 04:06:27,359][05218] Updated weights for policy 0, policy_version 33782 (0.0008) -[2023-10-16 04:06:27,734][05218] Updated weights for policy 0, policy_version 33792 (0.0007) -[2023-10-16 04:06:29,554][05219] Updated weights for policy 1, policy_version 33670 (0.0010) -[2023-10-16 04:06:29,923][05219] Updated weights for policy 1, policy_version 33680 (0.0007) -[2023-10-16 04:06:30,291][05219] Updated weights for policy 1, policy_version 33690 (0.0008) -[2023-10-16 04:06:31,415][05218] Updated weights for policy 0, policy_version 33802 (0.0008) -[2023-10-16 04:06:31,796][05218] Updated weights for policy 0, policy_version 33812 (0.0007) -[2023-10-16 04:06:32,165][05218] Updated weights for policy 0, policy_version 33822 (0.0010) -[2023-10-16 04:06:32,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 69140480. Throughput: 0: 1806.1, 1: 1786.8. Samples: 17290208. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-16 04:06:32,351][03835] Avg episode reward: [(0, '6.040'), (1, '6.260')] -[2023-10-16 04:06:34,089][05219] Updated weights for policy 1, policy_version 33700 (0.0008) -[2023-10-16 04:06:34,458][05219] Updated weights for policy 1, policy_version 33710 (0.0009) -[2023-10-16 04:06:34,823][05219] Updated weights for policy 1, policy_version 33720 (0.0009) -[2023-10-16 04:06:35,854][05218] Updated weights for policy 0, policy_version 33832 (0.0008) -[2023-10-16 04:06:36,234][05218] Updated weights for policy 0, policy_version 33842 (0.0007) -[2023-10-16 04:06:36,611][05218] Updated weights for policy 0, policy_version 33852 (0.0008) -[2023-10-16 04:06:37,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 69206016. Throughput: 0: 1794.4, 1: 1791.6. Samples: 17311674. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-16 04:06:37,351][03835] Avg episode reward: [(0, '6.420'), (1, '5.720')] -[2023-10-16 04:06:38,594][05219] Updated weights for policy 1, policy_version 33730 (0.0008) -[2023-10-16 04:06:38,960][05219] Updated weights for policy 1, policy_version 33740 (0.0010) -[2023-10-16 04:06:39,338][05219] Updated weights for policy 1, policy_version 33750 (0.0010) -[2023-10-16 04:06:39,696][05219] Updated weights for policy 1, policy_version 33760 (0.0008) -[2023-10-16 04:06:40,324][05218] Updated weights for policy 0, policy_version 33862 (0.0009) -[2023-10-16 04:06:40,703][05218] Updated weights for policy 0, policy_version 33872 (0.0008) -[2023-10-16 04:06:41,084][05218] Updated weights for policy 0, policy_version 33882 (0.0008) -[2023-10-16 04:06:42,351][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 69271552. Throughput: 0: 1807.7, 1: 1785.5. Samples: 17322488. Policy #0 lag: (min: 4.0, avg: 11.3, max: 36.0) -[2023-10-16 04:06:42,352][03835] Avg episode reward: [(0, '5.740'), (1, '5.410')] -[2023-10-16 04:06:43,472][05219] Updated weights for policy 1, policy_version 33770 (0.0010) -[2023-10-16 04:06:43,830][05219] Updated weights for policy 1, policy_version 33780 (0.0010) -[2023-10-16 04:06:44,204][05219] Updated weights for policy 1, policy_version 33790 (0.0011) -[2023-10-16 04:06:44,740][05218] Updated weights for policy 0, policy_version 33892 (0.0008) -[2023-10-16 04:06:45,123][05218] Updated weights for policy 0, policy_version 33902 (0.0009) -[2023-10-16 04:06:45,497][05218] Updated weights for policy 0, policy_version 33912 (0.0010) -[2023-10-16 04:06:47,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 69337088. Throughput: 0: 1791.2, 1: 1779.1. Samples: 17343510. Policy #0 lag: (min: 4.0, avg: 11.3, max: 36.0) -[2023-10-16 04:06:47,351][03835] Avg episode reward: [(0, '5.670'), (1, '6.170')] -[2023-10-16 04:06:48,048][05219] Updated weights for policy 1, policy_version 33800 (0.0010) -[2023-10-16 04:06:48,410][05219] Updated weights for policy 1, policy_version 33810 (0.0010) -[2023-10-16 04:06:48,769][05219] Updated weights for policy 1, policy_version 33820 (0.0008) -[2023-10-16 04:06:49,278][05218] Updated weights for policy 0, policy_version 33922 (0.0009) -[2023-10-16 04:06:49,652][05218] Updated weights for policy 0, policy_version 33932 (0.0010) -[2023-10-16 04:06:50,033][05218] Updated weights for policy 0, policy_version 33942 (0.0008) -[2023-10-16 04:06:50,404][05218] Updated weights for policy 0, policy_version 33952 (0.0008) -[2023-10-16 04:06:52,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 69402624. Throughput: 0: 1795.9, 1: 1796.0. Samples: 17365788. Policy #0 lag: (min: 4.0, avg: 11.3, max: 36.0) -[2023-10-16 04:06:52,351][03835] Avg episode reward: [(0, '5.400'), (1, '6.190')] -[2023-10-16 04:06:52,474][05219] Updated weights for policy 1, policy_version 33830 (0.0008) -[2023-10-16 04:06:52,844][05219] Updated weights for policy 1, policy_version 33840 (0.0008) -[2023-10-16 04:06:53,203][05219] Updated weights for policy 1, policy_version 33850 (0.0008) -[2023-10-16 04:06:54,083][05218] Updated weights for policy 0, policy_version 33962 (0.0008) -[2023-10-16 04:06:54,459][05218] Updated weights for policy 0, policy_version 33972 (0.0008) -[2023-10-16 04:06:54,836][05218] Updated weights for policy 0, policy_version 33982 (0.0011) -[2023-10-16 04:06:57,146][05219] Updated weights for policy 1, policy_version 33860 (0.0009) -[2023-10-16 04:06:57,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 69468160. Throughput: 0: 1795.2, 1: 1776.9. Samples: 17375624. Policy #0 lag: (min: 4.0, avg: 11.3, max: 36.0) -[2023-10-16 04:06:57,351][03835] Avg episode reward: [(0, '5.340'), (1, '6.100')] -[2023-10-16 04:06:57,540][05219] Updated weights for policy 1, policy_version 33870 (0.0010) -[2023-10-16 04:06:57,908][05219] Updated weights for policy 1, policy_version 33880 (0.0011) -[2023-10-16 04:06:58,626][05218] Updated weights for policy 0, policy_version 33992 (0.0010) -[2023-10-16 04:06:59,009][05218] Updated weights for policy 0, policy_version 34002 (0.0010) -[2023-10-16 04:06:59,387][05218] Updated weights for policy 0, policy_version 34012 (0.0011) -[2023-10-16 04:07:01,725][05219] Updated weights for policy 1, policy_version 33890 (0.0007) -[2023-10-16 04:07:02,080][05219] Updated weights for policy 1, policy_version 33900 (0.0007) -[2023-10-16 04:07:02,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 69533696. Throughput: 0: 1790.5, 1: 1782.0. Samples: 17397654. Policy #0 lag: (min: 4.0, avg: 11.3, max: 36.0) -[2023-10-16 04:07:02,351][03835] Avg episode reward: [(0, '6.320'), (1, '6.190')] -[2023-10-16 04:07:02,440][05219] Updated weights for policy 1, policy_version 33910 (0.0007) -[2023-10-16 04:07:02,800][05219] Updated weights for policy 1, policy_version 33920 (0.0007) -[2023-10-16 04:07:02,994][05218] Updated weights for policy 0, policy_version 34022 (0.0008) -[2023-10-16 04:07:03,372][05218] Updated weights for policy 0, policy_version 34032 (0.0009) -[2023-10-16 04:07:03,751][05218] Updated weights for policy 0, policy_version 34042 (0.0009) -[2023-10-16 04:07:06,685][05219] Updated weights for policy 1, policy_version 33930 (0.0008) -[2023-10-16 04:07:07,057][05219] Updated weights for policy 1, policy_version 33940 (0.0008) -[2023-10-16 04:07:07,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 69599232. Throughput: 0: 1799.7, 1: 1778.9. Samples: 17419198. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-16 04:07:07,351][03835] Avg episode reward: [(0, '6.240'), (1, '5.910')] -[2023-10-16 04:07:07,421][05219] Updated weights for policy 1, policy_version 33950 (0.0007) -[2023-10-16 04:07:07,532][05218] Updated weights for policy 0, policy_version 34052 (0.0010) -[2023-10-16 04:07:07,912][05218] Updated weights for policy 0, policy_version 34062 (0.0010) -[2023-10-16 04:07:08,285][05218] Updated weights for policy 0, policy_version 34072 (0.0009) -[2023-10-16 04:07:11,081][05219] Updated weights for policy 1, policy_version 33960 (0.0009) -[2023-10-16 04:07:11,454][05219] Updated weights for policy 1, policy_version 33970 (0.0009) -[2023-10-16 04:07:11,818][05219] Updated weights for policy 1, policy_version 33980 (0.0007) -[2023-10-16 04:07:11,978][05218] Updated weights for policy 0, policy_version 34082 (0.0009) -[2023-10-16 04:07:12,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 69697536. Throughput: 0: 1790.9, 1: 1777.8. Samples: 17429890. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-16 04:07:12,351][03835] Avg episode reward: [(0, '5.970'), (1, '6.300')] -[2023-10-16 04:07:12,380][05218] Updated weights for policy 0, policy_version 34092 (0.0011) -[2023-10-16 04:07:12,763][05218] Updated weights for policy 0, policy_version 34102 (0.0009) -[2023-10-16 04:07:13,133][05218] Updated weights for policy 0, policy_version 34112 (0.0009) -[2023-10-16 04:07:15,460][05219] Updated weights for policy 1, policy_version 33990 (0.0007) -[2023-10-16 04:07:15,831][05219] Updated weights for policy 1, policy_version 34000 (0.0008) -[2023-10-16 04:07:16,192][05219] Updated weights for policy 1, policy_version 34010 (0.0009) -[2023-10-16 04:07:16,886][05218] Updated weights for policy 0, policy_version 34122 (0.0008) -[2023-10-16 04:07:17,252][05218] Updated weights for policy 0, policy_version 34132 (0.0008) -[2023-10-16 04:07:17,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 69763072. Throughput: 0: 1801.8, 1: 1780.1. Samples: 17451394. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-16 04:07:17,351][03835] Avg episode reward: [(0, '5.210'), (1, '6.230')] -[2023-10-16 04:07:17,627][05218] Updated weights for policy 0, policy_version 34142 (0.0009) -[2023-10-16 04:07:20,048][05219] Updated weights for policy 1, policy_version 34020 (0.0011) -[2023-10-16 04:07:20,422][05219] Updated weights for policy 1, policy_version 34030 (0.0011) -[2023-10-16 04:07:20,779][05219] Updated weights for policy 1, policy_version 34040 (0.0011) -[2023-10-16 04:07:21,325][05218] Updated weights for policy 0, policy_version 34152 (0.0009) -[2023-10-16 04:07:21,705][05218] Updated weights for policy 0, policy_version 34162 (0.0008) -[2023-10-16 04:07:22,087][05218] Updated weights for policy 0, policy_version 34172 (0.0009) -[2023-10-16 04:07:22,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 69861376. Throughput: 0: 1790.3, 1: 1769.3. Samples: 17471854. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-16 04:07:22,351][03835] Avg episode reward: [(0, '6.060'), (1, '5.920')] -[2023-10-16 04:07:24,543][05219] Updated weights for policy 1, policy_version 34050 (0.0009) -[2023-10-16 04:07:24,909][05219] Updated weights for policy 1, policy_version 34060 (0.0008) -[2023-10-16 04:07:25,280][05219] Updated weights for policy 1, policy_version 34070 (0.0008) -[2023-10-16 04:07:25,638][05219] Updated weights for policy 1, policy_version 34080 (0.0008) -[2023-10-16 04:07:25,735][05218] Updated weights for policy 0, policy_version 34182 (0.0008) -[2023-10-16 04:07:26,115][05218] Updated weights for policy 0, policy_version 34192 (0.0010) -[2023-10-16 04:07:26,482][05218] Updated weights for policy 0, policy_version 34202 (0.0011) -[2023-10-16 04:07:27,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 69926912. Throughput: 0: 1803.2, 1: 1788.7. Samples: 17484120. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-16 04:07:27,351][03835] Avg episode reward: [(0, '5.840'), (1, '5.700')] -[2023-10-16 04:07:29,381][05219] Updated weights for policy 1, policy_version 34090 (0.0009) -[2023-10-16 04:07:29,757][05219] Updated weights for policy 1, policy_version 34100 (0.0009) -[2023-10-16 04:07:30,101][05218] Updated weights for policy 0, policy_version 34212 (0.0011) -[2023-10-16 04:07:30,117][05219] Updated weights for policy 1, policy_version 34110 (0.0009) -[2023-10-16 04:07:30,487][05218] Updated weights for policy 0, policy_version 34222 (0.0010) -[2023-10-16 04:07:30,852][05218] Updated weights for policy 0, policy_version 34232 (0.0010) -[2023-10-16 04:07:32,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 69992448. Throughput: 0: 1794.7, 1: 1780.9. Samples: 17504412. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-10-16 04:07:32,351][03835] Avg episode reward: [(0, '6.120'), (1, '6.770')] -[2023-10-16 04:07:33,928][05219] Updated weights for policy 1, policy_version 34120 (0.0008) -[2023-10-16 04:07:34,290][05219] Updated weights for policy 1, policy_version 34130 (0.0010) -[2023-10-16 04:07:34,640][05218] Updated weights for policy 0, policy_version 34242 (0.0010) -[2023-10-16 04:07:34,655][05219] Updated weights for policy 1, policy_version 34140 (0.0008) -[2023-10-16 04:07:35,004][05218] Updated weights for policy 0, policy_version 34252 (0.0010) -[2023-10-16 04:07:35,378][05218] Updated weights for policy 0, policy_version 34262 (0.0009) -[2023-10-16 04:07:35,755][05218] Updated weights for policy 0, policy_version 34272 (0.0008) -[2023-10-16 04:07:37,351][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 70057984. Throughput: 0: 1793.8, 1: 1781.6. Samples: 17526680. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-10-16 04:07:37,352][03835] Avg episode reward: [(0, '6.110'), (1, '6.430')] -[2023-10-16 04:07:37,361][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000034272_35094528.pth... -[2023-10-16 04:07:37,361][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000034144_34963456.pth... -[2023-10-16 04:07:37,391][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000032576_33357824.pth -[2023-10-16 04:07:37,397][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000032480_33259520.pth -[2023-10-16 04:07:38,438][05219] Updated weights for policy 1, policy_version 34150 (0.0009) -[2023-10-16 04:07:38,800][05219] Updated weights for policy 1, policy_version 34160 (0.0010) -[2023-10-16 04:07:39,169][05219] Updated weights for policy 1, policy_version 34170 (0.0009) -[2023-10-16 04:07:39,551][05218] Updated weights for policy 0, policy_version 34282 (0.0007) -[2023-10-16 04:07:39,935][05218] Updated weights for policy 0, policy_version 34292 (0.0007) -[2023-10-16 04:07:40,307][05218] Updated weights for policy 0, policy_version 34302 (0.0008) -[2023-10-16 04:07:42,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 70123520. Throughput: 0: 1796.9, 1: 1781.7. Samples: 17536664. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-10-16 04:07:42,351][03835] Avg episode reward: [(0, '6.520'), (1, '5.440')] -[2023-10-16 04:07:42,848][05219] Updated weights for policy 1, policy_version 34180 (0.0010) -[2023-10-16 04:07:43,217][05219] Updated weights for policy 1, policy_version 34190 (0.0011) -[2023-10-16 04:07:43,595][05219] Updated weights for policy 1, policy_version 34200 (0.0007) -[2023-10-16 04:07:44,037][05218] Updated weights for policy 0, policy_version 34312 (0.0010) -[2023-10-16 04:07:44,411][05218] Updated weights for policy 0, policy_version 34322 (0.0010) -[2023-10-16 04:07:44,784][05218] Updated weights for policy 0, policy_version 34332 (0.0008) -[2023-10-16 04:07:47,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 70189056. Throughput: 0: 1797.1, 1: 1787.6. Samples: 17558964. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-10-16 04:07:47,351][03835] Avg episode reward: [(0, '5.970'), (1, '6.010')] -[2023-10-16 04:07:47,469][05219] Updated weights for policy 1, policy_version 34210 (0.0010) -[2023-10-16 04:07:47,822][05219] Updated weights for policy 1, policy_version 34220 (0.0008) -[2023-10-16 04:07:48,190][05219] Updated weights for policy 1, policy_version 34230 (0.0012) -[2023-10-16 04:07:48,561][05219] Updated weights for policy 1, policy_version 34240 (0.0010) -[2023-10-16 04:07:48,652][05218] Updated weights for policy 0, policy_version 34342 (0.0008) -[2023-10-16 04:07:49,023][05218] Updated weights for policy 0, policy_version 34352 (0.0008) -[2023-10-16 04:07:49,405][05218] Updated weights for policy 0, policy_version 34362 (0.0009) -[2023-10-16 04:07:52,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 70254592. Throughput: 0: 1797.1, 1: 1803.1. Samples: 17581206. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-10-16 04:07:52,351][03835] Avg episode reward: [(0, '6.560'), (1, '5.880')] -[2023-10-16 04:07:52,390][05219] Updated weights for policy 1, policy_version 34250 (0.0010) -[2023-10-16 04:07:52,755][05219] Updated weights for policy 1, policy_version 34260 (0.0008) -[2023-10-16 04:07:53,009][05218] Updated weights for policy 0, policy_version 34372 (0.0009) -[2023-10-16 04:07:53,122][05219] Updated weights for policy 1, policy_version 34270 (0.0007) -[2023-10-16 04:07:53,393][05218] Updated weights for policy 0, policy_version 34382 (0.0007) -[2023-10-16 04:07:53,769][05218] Updated weights for policy 0, policy_version 34392 (0.0007) -[2023-10-16 04:07:56,899][05219] Updated weights for policy 1, policy_version 34280 (0.0007) -[2023-10-16 04:07:57,264][05219] Updated weights for policy 1, policy_version 34290 (0.0007) -[2023-10-16 04:07:57,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 70320128. Throughput: 0: 1797.7, 1: 1782.3. Samples: 17590992. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-10-16 04:07:57,351][03835] Avg episode reward: [(0, '6.380'), (1, '5.910')] -[2023-10-16 04:07:57,578][05218] Updated weights for policy 0, policy_version 34402 (0.0007) -[2023-10-16 04:07:57,619][05219] Updated weights for policy 1, policy_version 34300 (0.0009) -[2023-10-16 04:07:57,990][05218] Updated weights for policy 0, policy_version 34412 (0.0007) -[2023-10-16 04:07:58,357][05218] Updated weights for policy 0, policy_version 34422 (0.0008) -[2023-10-16 04:07:58,737][05218] Updated weights for policy 0, policy_version 34432 (0.0009) -[2023-10-16 04:08:01,443][05219] Updated weights for policy 1, policy_version 34310 (0.0008) -[2023-10-16 04:08:01,810][05219] Updated weights for policy 1, policy_version 34320 (0.0007) -[2023-10-16 04:08:02,165][05219] Updated weights for policy 1, policy_version 34330 (0.0008) -[2023-10-16 04:08:02,318][05218] Updated weights for policy 0, policy_version 34442 (0.0008) -[2023-10-16 04:08:02,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 70385664. Throughput: 0: 1795.2, 1: 1800.5. Samples: 17613200. Policy #0 lag: (min: 31.0, avg: 32.1, max: 51.0) -[2023-10-16 04:08:02,351][03835] Avg episode reward: [(0, '5.570'), (1, '6.540')] -[2023-10-16 04:08:02,697][05218] Updated weights for policy 0, policy_version 34452 (0.0010) -[2023-10-16 04:08:03,075][05218] Updated weights for policy 0, policy_version 34462 (0.0009) -[2023-10-16 04:08:06,039][05219] Updated weights for policy 1, policy_version 34340 (0.0008) -[2023-10-16 04:08:06,410][05219] Updated weights for policy 1, policy_version 34350 (0.0008) -[2023-10-16 04:08:06,777][05219] Updated weights for policy 1, policy_version 34360 (0.0007) -[2023-10-16 04:08:06,805][05218] Updated weights for policy 0, policy_version 34472 (0.0010) -[2023-10-16 04:08:07,176][05218] Updated weights for policy 0, policy_version 34482 (0.0011) -[2023-10-16 04:08:07,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 70483968. Throughput: 0: 1807.6, 1: 1773.6. Samples: 17633004. Policy #0 lag: (min: 31.0, avg: 32.1, max: 51.0) -[2023-10-16 04:08:07,351][03835] Avg episode reward: [(0, '5.510'), (1, '5.960')] -[2023-10-16 04:08:07,554][05218] Updated weights for policy 0, policy_version 34492 (0.0011) -[2023-10-16 04:08:10,473][05219] Updated weights for policy 1, policy_version 34370 (0.0009) -[2023-10-16 04:08:10,843][05219] Updated weights for policy 1, policy_version 34380 (0.0008) -[2023-10-16 04:08:11,222][05219] Updated weights for policy 1, policy_version 34390 (0.0009) -[2023-10-16 04:08:11,283][05218] Updated weights for policy 0, policy_version 34502 (0.0008) -[2023-10-16 04:08:11,580][05219] Updated weights for policy 1, policy_version 34400 (0.0007) -[2023-10-16 04:08:11,655][05218] Updated weights for policy 0, policy_version 34512 (0.0009) -[2023-10-16 04:08:12,025][05218] Updated weights for policy 0, policy_version 34522 (0.0008) -[2023-10-16 04:08:12,350][03835] Fps is (10 sec: 19660.8, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 70582272. Throughput: 0: 1791.9, 1: 1789.4. Samples: 17645280. Policy #0 lag: (min: 31.0, avg: 32.1, max: 51.0) -[2023-10-16 04:08:12,351][03835] Avg episode reward: [(0, '6.050'), (1, '6.210')] -[2023-10-16 04:08:15,423][05219] Updated weights for policy 1, policy_version 34410 (0.0009) -[2023-10-16 04:08:15,780][05219] Updated weights for policy 1, policy_version 34420 (0.0009) -[2023-10-16 04:08:15,870][05218] Updated weights for policy 0, policy_version 34532 (0.0008) -[2023-10-16 04:08:16,143][05219] Updated weights for policy 1, policy_version 34430 (0.0007) -[2023-10-16 04:08:16,252][05218] Updated weights for policy 0, policy_version 34542 (0.0008) -[2023-10-16 04:08:16,626][05218] Updated weights for policy 0, policy_version 34552 (0.0008) -[2023-10-16 04:08:17,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.2). Total num frames: 70647808. Throughput: 0: 1810.8, 1: 1774.2. Samples: 17665738. Policy #0 lag: (min: 31.0, avg: 32.1, max: 51.0) -[2023-10-16 04:08:17,351][03835] Avg episode reward: [(0, '5.790'), (1, '6.130')] -[2023-10-16 04:08:19,998][05219] Updated weights for policy 1, policy_version 34440 (0.0007) -[2023-10-16 04:08:20,372][05219] Updated weights for policy 1, policy_version 34450 (0.0009) -[2023-10-16 04:08:20,439][05218] Updated weights for policy 0, policy_version 34562 (0.0008) -[2023-10-16 04:08:20,733][05219] Updated weights for policy 1, policy_version 34460 (0.0007) -[2023-10-16 04:08:20,812][05218] Updated weights for policy 0, policy_version 34572 (0.0010) -[2023-10-16 04:08:21,193][05218] Updated weights for policy 0, policy_version 34582 (0.0008) -[2023-10-16 04:08:21,564][05218] Updated weights for policy 0, policy_version 34592 (0.0009) -[2023-10-16 04:08:22,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 70713344. Throughput: 0: 1793.0, 1: 1768.2. Samples: 17686936. Policy #0 lag: (min: 31.0, avg: 32.1, max: 51.0) -[2023-10-16 04:08:22,351][03835] Avg episode reward: [(0, '5.680'), (1, '5.860')] -[2023-10-16 04:08:24,591][05219] Updated weights for policy 1, policy_version 34470 (0.0008) -[2023-10-16 04:08:24,962][05219] Updated weights for policy 1, policy_version 34480 (0.0007) -[2023-10-16 04:08:25,302][05218] Updated weights for policy 0, policy_version 34602 (0.0009) -[2023-10-16 04:08:25,322][05219] Updated weights for policy 1, policy_version 34490 (0.0008) -[2023-10-16 04:08:25,687][05218] Updated weights for policy 0, policy_version 34612 (0.0010) -[2023-10-16 04:08:26,052][05218] Updated weights for policy 0, policy_version 34622 (0.0010) -[2023-10-16 04:08:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 70778880. Throughput: 0: 1812.0, 1: 1778.7. Samples: 17698244. Policy #0 lag: (min: 18.0, avg: 19.5, max: 45.0) -[2023-10-16 04:08:27,351][03835] Avg episode reward: [(0, '6.140'), (1, '5.870')] -[2023-10-16 04:08:28,965][05219] Updated weights for policy 1, policy_version 34500 (0.0008) -[2023-10-16 04:08:29,324][05219] Updated weights for policy 1, policy_version 34510 (0.0009) -[2023-10-16 04:08:29,627][05218] Updated weights for policy 0, policy_version 34632 (0.0007) -[2023-10-16 04:08:29,692][05219] Updated weights for policy 1, policy_version 34520 (0.0007) -[2023-10-16 04:08:30,007][05218] Updated weights for policy 0, policy_version 34642 (0.0007) -[2023-10-16 04:08:30,373][05218] Updated weights for policy 0, policy_version 34652 (0.0010) -[2023-10-16 04:08:32,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 70844416. Throughput: 0: 1792.8, 1: 1766.9. Samples: 17719150. Policy #0 lag: (min: 18.0, avg: 19.5, max: 45.0) -[2023-10-16 04:08:32,351][03835] Avg episode reward: [(0, '6.060'), (1, '6.030')] -[2023-10-16 04:08:33,491][05219] Updated weights for policy 1, policy_version 34530 (0.0008) -[2023-10-16 04:08:33,887][05219] Updated weights for policy 1, policy_version 34540 (0.0010) -[2023-10-16 04:08:34,048][05218] Updated weights for policy 0, policy_version 34662 (0.0009) -[2023-10-16 04:08:34,246][05219] Updated weights for policy 1, policy_version 34550 (0.0008) -[2023-10-16 04:08:34,426][05218] Updated weights for policy 0, policy_version 34672 (0.0009) -[2023-10-16 04:08:34,610][05219] Updated weights for policy 1, policy_version 34560 (0.0008) -[2023-10-16 04:08:34,792][05218] Updated weights for policy 0, policy_version 34682 (0.0010) -[2023-10-16 04:08:37,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 70909952. Throughput: 0: 1791.8, 1: 1766.7. Samples: 17741340. Policy #0 lag: (min: 18.0, avg: 19.5, max: 45.0) -[2023-10-16 04:08:37,351][03835] Avg episode reward: [(0, '6.040'), (1, '5.800')] -[2023-10-16 04:08:38,361][05219] Updated weights for policy 1, policy_version 34570 (0.0007) -[2023-10-16 04:08:38,664][05218] Updated weights for policy 0, policy_version 34692 (0.0008) -[2023-10-16 04:08:38,728][05219] Updated weights for policy 1, policy_version 34580 (0.0007) -[2023-10-16 04:08:39,032][05218] Updated weights for policy 0, policy_version 34702 (0.0008) -[2023-10-16 04:08:39,082][05219] Updated weights for policy 1, policy_version 34590 (0.0008) -[2023-10-16 04:08:39,412][05218] Updated weights for policy 0, policy_version 34712 (0.0009) -[2023-10-16 04:08:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 70975488. Throughput: 0: 1791.0, 1: 1767.6. Samples: 17751128. Policy #0 lag: (min: 18.0, avg: 19.5, max: 45.0) -[2023-10-16 04:08:42,351][03835] Avg episode reward: [(0, '5.860'), (1, '6.720')] -[2023-10-16 04:08:42,958][05219] Updated weights for policy 1, policy_version 34600 (0.0010) -[2023-10-16 04:08:43,230][05218] Updated weights for policy 0, policy_version 34722 (0.0007) -[2023-10-16 04:08:43,316][05219] Updated weights for policy 1, policy_version 34610 (0.0008) -[2023-10-16 04:08:43,604][05218] Updated weights for policy 0, policy_version 34732 (0.0008) -[2023-10-16 04:08:43,692][05219] Updated weights for policy 1, policy_version 34620 (0.0008) -[2023-10-16 04:08:43,974][05218] Updated weights for policy 0, policy_version 34742 (0.0009) -[2023-10-16 04:08:44,350][05218] Updated weights for policy 0, policy_version 34752 (0.0009) -[2023-10-16 04:08:47,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 71041024. Throughput: 0: 1786.5, 1: 1767.8. Samples: 17773144. Policy #0 lag: (min: 18.0, avg: 19.5, max: 45.0) -[2023-10-16 04:08:47,351][03835] Avg episode reward: [(0, '5.530'), (1, '6.430')] -[2023-10-16 04:08:47,598][05219] Updated weights for policy 1, policy_version 34630 (0.0008) -[2023-10-16 04:08:47,956][05219] Updated weights for policy 1, policy_version 34640 (0.0007) -[2023-10-16 04:08:48,011][05218] Updated weights for policy 0, policy_version 34762 (0.0008) -[2023-10-16 04:08:48,328][05219] Updated weights for policy 1, policy_version 34650 (0.0008) -[2023-10-16 04:08:48,399][05218] Updated weights for policy 0, policy_version 34772 (0.0007) -[2023-10-16 04:08:48,760][05218] Updated weights for policy 0, policy_version 34782 (0.0008) -[2023-10-16 04:08:52,116][05219] Updated weights for policy 1, policy_version 34660 (0.0009) -[2023-10-16 04:08:52,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 71106560. Throughput: 0: 1803.4, 1: 1798.4. Samples: 17795088. Policy #0 lag: (min: 18.0, avg: 19.5, max: 45.0) -[2023-10-16 04:08:52,351][03835] Avg episode reward: [(0, '5.440'), (1, '6.370')] -[2023-10-16 04:08:52,480][05219] Updated weights for policy 1, policy_version 34670 (0.0009) -[2023-10-16 04:08:52,545][05218] Updated weights for policy 0, policy_version 34792 (0.0008) -[2023-10-16 04:08:52,842][05219] Updated weights for policy 1, policy_version 34680 (0.0007) -[2023-10-16 04:08:52,920][05218] Updated weights for policy 0, policy_version 34802 (0.0009) -[2023-10-16 04:08:53,301][05218] Updated weights for policy 0, policy_version 34812 (0.0009) -[2023-10-16 04:08:56,645][05219] Updated weights for policy 1, policy_version 34690 (0.0008) -[2023-10-16 04:08:57,006][05219] Updated weights for policy 1, policy_version 34700 (0.0009) -[2023-10-16 04:08:57,193][05218] Updated weights for policy 0, policy_version 34822 (0.0009) -[2023-10-16 04:08:57,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 71172096. Throughput: 0: 1780.8, 1: 1769.8. Samples: 17805058. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-16 04:08:57,351][03835] Avg episode reward: [(0, '6.870'), (1, '6.410')] -[2023-10-16 04:08:57,371][05219] Updated weights for policy 1, policy_version 34710 (0.0008) -[2023-10-16 04:08:57,570][05218] Updated weights for policy 0, policy_version 34832 (0.0008) -[2023-10-16 04:08:57,736][05219] Updated weights for policy 1, policy_version 34720 (0.0008) -[2023-10-16 04:08:57,945][05218] Updated weights for policy 0, policy_version 34842 (0.0009) -[2023-10-16 04:08:58,172][04766] Saving new best policy, reward=6.870! -[2023-10-16 04:09:01,512][05219] Updated weights for policy 1, policy_version 34730 (0.0008) -[2023-10-16 04:09:01,867][05219] Updated weights for policy 1, policy_version 34740 (0.0007) -[2023-10-16 04:09:01,879][05218] Updated weights for policy 0, policy_version 34852 (0.0009) -[2023-10-16 04:09:02,233][05219] Updated weights for policy 1, policy_version 34750 (0.0008) -[2023-10-16 04:09:02,255][05218] Updated weights for policy 0, policy_version 34862 (0.0008) -[2023-10-16 04:09:02,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 71270400. Throughput: 0: 1790.0, 1: 1801.2. Samples: 17827344. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-16 04:09:02,351][03835] Avg episode reward: [(0, '6.680'), (1, '5.990')] -[2023-10-16 04:09:02,636][05218] Updated weights for policy 0, policy_version 34872 (0.0008) -[2023-10-16 04:09:05,977][05219] Updated weights for policy 1, policy_version 34760 (0.0011) -[2023-10-16 04:09:06,343][05219] Updated weights for policy 1, policy_version 34770 (0.0009) -[2023-10-16 04:09:06,428][05218] Updated weights for policy 0, policy_version 34882 (0.0009) -[2023-10-16 04:09:06,707][05219] Updated weights for policy 1, policy_version 34780 (0.0007) -[2023-10-16 04:09:06,805][05218] Updated weights for policy 0, policy_version 34892 (0.0007) -[2023-10-16 04:09:07,175][05218] Updated weights for policy 0, policy_version 34902 (0.0007) -[2023-10-16 04:09:07,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 71335936. Throughput: 0: 1783.5, 1: 1777.0. Samples: 17847158. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-16 04:09:07,351][03835] Avg episode reward: [(0, '6.270'), (1, '6.960')] -[2023-10-16 04:09:07,551][05218] Updated weights for policy 0, policy_version 34912 (0.0008) -[2023-10-16 04:09:10,492][05219] Updated weights for policy 1, policy_version 34790 (0.0009) -[2023-10-16 04:09:10,864][05219] Updated weights for policy 1, policy_version 34800 (0.0007) -[2023-10-16 04:09:11,231][05219] Updated weights for policy 1, policy_version 34810 (0.0007) -[2023-10-16 04:09:11,322][05218] Updated weights for policy 0, policy_version 34922 (0.0009) -[2023-10-16 04:09:11,698][05218] Updated weights for policy 0, policy_version 34932 (0.0007) -[2023-10-16 04:09:12,072][05218] Updated weights for policy 0, policy_version 34942 (0.0007) -[2023-10-16 04:09:12,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 71434240. Throughput: 0: 1783.4, 1: 1796.7. Samples: 17859348. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-16 04:09:12,351][03835] Avg episode reward: [(0, '7.000'), (1, '5.430')] -[2023-10-16 04:09:12,351][04766] Saving new best policy, reward=7.000! -[2023-10-16 04:09:15,151][05219] Updated weights for policy 1, policy_version 34820 (0.0009) -[2023-10-16 04:09:15,527][05219] Updated weights for policy 1, policy_version 34830 (0.0010) -[2023-10-16 04:09:15,791][05218] Updated weights for policy 0, policy_version 34952 (0.0008) -[2023-10-16 04:09:15,890][05219] Updated weights for policy 1, policy_version 34840 (0.0008) -[2023-10-16 04:09:16,166][05218] Updated weights for policy 0, policy_version 34962 (0.0009) -[2023-10-16 04:09:16,545][05218] Updated weights for policy 0, policy_version 34972 (0.0007) -[2023-10-16 04:09:17,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 71499776. Throughput: 0: 1783.9, 1: 1778.1. Samples: 17879442. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-16 04:09:17,351][03835] Avg episode reward: [(0, '6.420'), (1, '5.530')] -[2023-10-16 04:09:19,708][05219] Updated weights for policy 1, policy_version 34850 (0.0008) -[2023-10-16 04:09:20,109][05219] Updated weights for policy 1, policy_version 34860 (0.0010) -[2023-10-16 04:09:20,236][05218] Updated weights for policy 0, policy_version 34982 (0.0010) -[2023-10-16 04:09:20,474][05219] Updated weights for policy 1, policy_version 34870 (0.0008) -[2023-10-16 04:09:20,609][05218] Updated weights for policy 0, policy_version 34992 (0.0011) -[2023-10-16 04:09:20,837][05219] Updated weights for policy 1, policy_version 34880 (0.0009) -[2023-10-16 04:09:20,986][05218] Updated weights for policy 0, policy_version 35002 (0.0008) -[2023-10-16 04:09:22,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 71565312. Throughput: 0: 1771.3, 1: 1777.9. Samples: 17901054. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:09:22,351][03835] Avg episode reward: [(0, '6.560'), (1, '5.840')] -[2023-10-16 04:09:24,483][05219] Updated weights for policy 1, policy_version 34890 (0.0007) -[2023-10-16 04:09:24,690][05218] Updated weights for policy 0, policy_version 35012 (0.0007) -[2023-10-16 04:09:24,848][05219] Updated weights for policy 1, policy_version 34900 (0.0007) -[2023-10-16 04:09:25,062][05218] Updated weights for policy 0, policy_version 35022 (0.0008) -[2023-10-16 04:09:25,208][05219] Updated weights for policy 1, policy_version 34910 (0.0008) -[2023-10-16 04:09:25,435][05218] Updated weights for policy 0, policy_version 35032 (0.0010) -[2023-10-16 04:09:27,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 71630848. Throughput: 0: 1786.1, 1: 1781.2. Samples: 17911658. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:09:27,351][03835] Avg episode reward: [(0, '6.290'), (1, '5.620')] -[2023-10-16 04:09:29,024][05219] Updated weights for policy 1, policy_version 34920 (0.0009) -[2023-10-16 04:09:29,107][05218] Updated weights for policy 0, policy_version 35042 (0.0008) -[2023-10-16 04:09:29,392][05219] Updated weights for policy 1, policy_version 34930 (0.0008) -[2023-10-16 04:09:29,508][05218] Updated weights for policy 0, policy_version 35052 (0.0008) -[2023-10-16 04:09:29,752][05219] Updated weights for policy 1, policy_version 34940 (0.0007) -[2023-10-16 04:09:29,880][05218] Updated weights for policy 0, policy_version 35062 (0.0007) -[2023-10-16 04:09:30,262][05218] Updated weights for policy 0, policy_version 35072 (0.0008) -[2023-10-16 04:09:32,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 71696384. Throughput: 0: 1777.8, 1: 1774.1. Samples: 17932978. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:09:32,351][03835] Avg episode reward: [(0, '6.420'), (1, '6.130')] -[2023-10-16 04:09:33,374][05219] Updated weights for policy 1, policy_version 34950 (0.0008) -[2023-10-16 04:09:33,739][05219] Updated weights for policy 1, policy_version 34960 (0.0007) -[2023-10-16 04:09:34,037][05218] Updated weights for policy 0, policy_version 35082 (0.0009) -[2023-10-16 04:09:34,115][05219] Updated weights for policy 1, policy_version 34970 (0.0008) -[2023-10-16 04:09:34,413][05218] Updated weights for policy 0, policy_version 35092 (0.0009) -[2023-10-16 04:09:34,787][05218] Updated weights for policy 0, policy_version 35102 (0.0011) -[2023-10-16 04:09:37,351][03835] Fps is (10 sec: 13106.6, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 71761920. Throughput: 0: 1777.1, 1: 1784.3. Samples: 17955354. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:09:37,352][03835] Avg episode reward: [(0, '5.500'), (1, '6.240')] -[2023-10-16 04:09:37,365][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000034976_35815424.pth... -[2023-10-16 04:09:37,365][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000035104_35946496.pth... -[2023-10-16 04:09:37,397][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000033312_34111488.pth -[2023-10-16 04:09:37,399][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000033440_34242560.pth -[2023-10-16 04:09:37,784][05219] Updated weights for policy 1, policy_version 34980 (0.0009) -[2023-10-16 04:09:38,155][05219] Updated weights for policy 1, policy_version 34990 (0.0011) -[2023-10-16 04:09:38,525][05219] Updated weights for policy 1, policy_version 35000 (0.0010) -[2023-10-16 04:09:38,669][05218] Updated weights for policy 0, policy_version 35112 (0.0009) -[2023-10-16 04:09:39,052][05218] Updated weights for policy 0, policy_version 35122 (0.0008) -[2023-10-16 04:09:39,418][05218] Updated weights for policy 0, policy_version 35132 (0.0010) -[2023-10-16 04:09:42,263][05219] Updated weights for policy 1, policy_version 35010 (0.0007) -[2023-10-16 04:09:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 71827456. Throughput: 0: 1773.9, 1: 1779.7. Samples: 17964968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:09:42,351][03835] Avg episode reward: [(0, '5.860'), (1, '6.250')] -[2023-10-16 04:09:42,623][05219] Updated weights for policy 1, policy_version 35020 (0.0008) -[2023-10-16 04:09:43,000][05219] Updated weights for policy 1, policy_version 35030 (0.0008) -[2023-10-16 04:09:43,235][05218] Updated weights for policy 0, policy_version 35142 (0.0007) -[2023-10-16 04:09:43,361][05219] Updated weights for policy 1, policy_version 35040 (0.0008) -[2023-10-16 04:09:43,607][05218] Updated weights for policy 0, policy_version 35152 (0.0008) -[2023-10-16 04:09:43,986][05218] Updated weights for policy 0, policy_version 35162 (0.0008) -[2023-10-16 04:09:47,189][05219] Updated weights for policy 1, policy_version 35050 (0.0008) -[2023-10-16 04:09:47,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 71892992. Throughput: 0: 1780.1, 1: 1773.5. Samples: 17987258. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:09:47,351][03835] Avg episode reward: [(0, '6.370'), (1, '5.920')] -[2023-10-16 04:09:47,551][05219] Updated weights for policy 1, policy_version 35060 (0.0008) -[2023-10-16 04:09:47,795][05218] Updated weights for policy 0, policy_version 35172 (0.0008) -[2023-10-16 04:09:47,920][05219] Updated weights for policy 1, policy_version 35070 (0.0008) -[2023-10-16 04:09:48,159][05218] Updated weights for policy 0, policy_version 35182 (0.0008) -[2023-10-16 04:09:48,551][05218] Updated weights for policy 0, policy_version 35192 (0.0008) -[2023-10-16 04:09:51,785][05219] Updated weights for policy 1, policy_version 35080 (0.0008) -[2023-10-16 04:09:52,154][05219] Updated weights for policy 1, policy_version 35090 (0.0007) -[2023-10-16 04:09:52,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 71958528. Throughput: 0: 1805.2, 1: 1784.2. Samples: 18008684. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:09:52,351][03835] Avg episode reward: [(0, '6.370'), (1, '6.390')] -[2023-10-16 04:09:52,360][05218] Updated weights for policy 0, policy_version 35202 (0.0010) -[2023-10-16 04:09:52,525][05219] Updated weights for policy 1, policy_version 35100 (0.0008) -[2023-10-16 04:09:52,741][05218] Updated weights for policy 0, policy_version 35212 (0.0007) -[2023-10-16 04:09:53,107][05218] Updated weights for policy 0, policy_version 35222 (0.0009) -[2023-10-16 04:09:53,479][05218] Updated weights for policy 0, policy_version 35232 (0.0008) -[2023-10-16 04:09:56,470][05219] Updated weights for policy 1, policy_version 35110 (0.0010) -[2023-10-16 04:09:56,833][05219] Updated weights for policy 1, policy_version 35120 (0.0009) -[2023-10-16 04:09:57,153][05218] Updated weights for policy 0, policy_version 35242 (0.0007) -[2023-10-16 04:09:57,192][05219] Updated weights for policy 1, policy_version 35130 (0.0007) -[2023-10-16 04:09:57,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 72024064. Throughput: 0: 1782.8, 1: 1766.6. Samples: 18019074. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:09:57,351][03835] Avg episode reward: [(0, '6.470'), (1, '6.450')] -[2023-10-16 04:09:57,527][05218] Updated weights for policy 0, policy_version 35252 (0.0007) -[2023-10-16 04:09:57,905][05218] Updated weights for policy 0, policy_version 35262 (0.0007) -[2023-10-16 04:10:01,120][05219] Updated weights for policy 1, policy_version 35140 (0.0007) -[2023-10-16 04:10:01,486][05219] Updated weights for policy 1, policy_version 35150 (0.0009) -[2023-10-16 04:10:01,817][05218] Updated weights for policy 0, policy_version 35272 (0.0007) -[2023-10-16 04:10:01,851][05219] Updated weights for policy 1, policy_version 35160 (0.0008) -[2023-10-16 04:10:02,194][05218] Updated weights for policy 0, policy_version 35282 (0.0009) -[2023-10-16 04:10:02,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 72122368. Throughput: 0: 1797.3, 1: 1791.5. Samples: 18040936. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:10:02,351][03835] Avg episode reward: [(0, '6.290'), (1, '6.500')] -[2023-10-16 04:10:02,568][05218] Updated weights for policy 0, policy_version 35292 (0.0010) -[2023-10-16 04:10:05,588][05219] Updated weights for policy 1, policy_version 35170 (0.0008) -[2023-10-16 04:10:05,963][05219] Updated weights for policy 1, policy_version 35180 (0.0008) -[2023-10-16 04:10:06,236][05218] Updated weights for policy 0, policy_version 35302 (0.0008) -[2023-10-16 04:10:06,330][05219] Updated weights for policy 1, policy_version 35190 (0.0008) -[2023-10-16 04:10:06,618][05218] Updated weights for policy 0, policy_version 35312 (0.0008) -[2023-10-16 04:10:06,697][05219] Updated weights for policy 1, policy_version 35200 (0.0008) -[2023-10-16 04:10:06,989][05218] Updated weights for policy 0, policy_version 35322 (0.0008) -[2023-10-16 04:10:07,350][03835] Fps is (10 sec: 19661.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 72220672. Throughput: 0: 1777.6, 1: 1769.8. Samples: 18060688. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:10:07,351][03835] Avg episode reward: [(0, '6.150'), (1, '6.050')] -[2023-10-16 04:10:10,445][05219] Updated weights for policy 1, policy_version 35210 (0.0009) -[2023-10-16 04:10:10,627][05218] Updated weights for policy 0, policy_version 35332 (0.0009) -[2023-10-16 04:10:10,811][05219] Updated weights for policy 1, policy_version 35220 (0.0008) -[2023-10-16 04:10:11,001][05218] Updated weights for policy 0, policy_version 35342 (0.0008) -[2023-10-16 04:10:11,179][05219] Updated weights for policy 1, policy_version 35230 (0.0007) -[2023-10-16 04:10:11,379][05218] Updated weights for policy 0, policy_version 35352 (0.0007) -[2023-10-16 04:10:12,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 72286208. Throughput: 0: 1799.4, 1: 1797.0. Samples: 18073498. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:10:12,351][03835] Avg episode reward: [(0, '6.100'), (1, '5.910')] -[2023-10-16 04:10:15,116][05218] Updated weights for policy 0, policy_version 35362 (0.0007) -[2023-10-16 04:10:15,139][05219] Updated weights for policy 1, policy_version 35240 (0.0008) -[2023-10-16 04:10:15,510][05219] Updated weights for policy 1, policy_version 35250 (0.0009) -[2023-10-16 04:10:15,516][05218] Updated weights for policy 0, policy_version 35372 (0.0009) -[2023-10-16 04:10:15,868][05219] Updated weights for policy 1, policy_version 35260 (0.0008) -[2023-10-16 04:10:15,888][05218] Updated weights for policy 0, policy_version 35382 (0.0009) -[2023-10-16 04:10:16,265][05218] Updated weights for policy 0, policy_version 35392 (0.0010) -[2023-10-16 04:10:17,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 72351744. Throughput: 0: 1778.9, 1: 1769.2. Samples: 18092644. Policy #0 lag: (min: 31.0, avg: 32.8, max: 59.0) -[2023-10-16 04:10:17,351][03835] Avg episode reward: [(0, '5.880'), (1, '5.160')] -[2023-10-16 04:10:19,670][05219] Updated weights for policy 1, policy_version 35270 (0.0008) -[2023-10-16 04:10:20,025][05218] Updated weights for policy 0, policy_version 35402 (0.0007) -[2023-10-16 04:10:20,036][05219] Updated weights for policy 1, policy_version 35280 (0.0007) -[2023-10-16 04:10:20,395][05219] Updated weights for policy 1, policy_version 35290 (0.0009) -[2023-10-16 04:10:20,395][05218] Updated weights for policy 0, policy_version 35412 (0.0009) -[2023-10-16 04:10:20,764][05218] Updated weights for policy 0, policy_version 35422 (0.0009) -[2023-10-16 04:10:22,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 72417280. Throughput: 0: 1783.8, 1: 1765.4. Samples: 18115068. Policy #0 lag: (min: 31.0, avg: 32.8, max: 59.0) -[2023-10-16 04:10:22,351][03835] Avg episode reward: [(0, '6.460'), (1, '5.790')] -[2023-10-16 04:10:24,277][05219] Updated weights for policy 1, policy_version 35300 (0.0009) -[2023-10-16 04:10:24,513][05218] Updated weights for policy 0, policy_version 35432 (0.0009) -[2023-10-16 04:10:24,650][05219] Updated weights for policy 1, policy_version 35310 (0.0008) -[2023-10-16 04:10:24,893][05218] Updated weights for policy 0, policy_version 35442 (0.0007) -[2023-10-16 04:10:25,009][05219] Updated weights for policy 1, policy_version 35320 (0.0008) -[2023-10-16 04:10:25,267][05218] Updated weights for policy 0, policy_version 35452 (0.0007) -[2023-10-16 04:10:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 72482816. Throughput: 0: 1788.5, 1: 1771.8. Samples: 18125180. Policy #0 lag: (min: 31.0, avg: 32.8, max: 59.0) -[2023-10-16 04:10:27,351][03835] Avg episode reward: [(0, '6.150'), (1, '6.430')] -[2023-10-16 04:10:28,747][05219] Updated weights for policy 1, policy_version 35330 (0.0007) -[2023-10-16 04:10:29,054][05218] Updated weights for policy 0, policy_version 35462 (0.0008) -[2023-10-16 04:10:29,111][05219] Updated weights for policy 1, policy_version 35340 (0.0008) -[2023-10-16 04:10:29,422][05218] Updated weights for policy 0, policy_version 35472 (0.0008) -[2023-10-16 04:10:29,481][05219] Updated weights for policy 1, policy_version 35350 (0.0007) -[2023-10-16 04:10:29,790][05218] Updated weights for policy 0, policy_version 35482 (0.0009) -[2023-10-16 04:10:29,844][05219] Updated weights for policy 1, policy_version 35360 (0.0008) -[2023-10-16 04:10:32,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 72548352. Throughput: 0: 1782.2, 1: 1767.7. Samples: 18147002. Policy #0 lag: (min: 31.0, avg: 32.8, max: 59.0) -[2023-10-16 04:10:32,351][03835] Avg episode reward: [(0, '6.530'), (1, '6.830')] -[2023-10-16 04:10:33,529][05219] Updated weights for policy 1, policy_version 35370 (0.0008) -[2023-10-16 04:10:33,529][05218] Updated weights for policy 0, policy_version 35492 (0.0008) -[2023-10-16 04:10:33,896][05219] Updated weights for policy 1, policy_version 35380 (0.0008) -[2023-10-16 04:10:33,908][05218] Updated weights for policy 0, policy_version 35502 (0.0009) -[2023-10-16 04:10:34,254][05219] Updated weights for policy 1, policy_version 35390 (0.0008) -[2023-10-16 04:10:34,290][05218] Updated weights for policy 0, policy_version 35512 (0.0007) -[2023-10-16 04:10:37,351][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 72613888. Throughput: 0: 1781.2, 1: 1791.9. Samples: 18169474. Policy #0 lag: (min: 31.0, avg: 32.8, max: 59.0) -[2023-10-16 04:10:37,352][03835] Avg episode reward: [(0, '6.700'), (1, '6.470')] -[2023-10-16 04:10:38,086][05218] Updated weights for policy 0, policy_version 35522 (0.0008) -[2023-10-16 04:10:38,094][05219] Updated weights for policy 1, policy_version 35400 (0.0009) -[2023-10-16 04:10:38,468][05218] Updated weights for policy 0, policy_version 35532 (0.0009) -[2023-10-16 04:10:38,470][05219] Updated weights for policy 1, policy_version 35410 (0.0008) -[2023-10-16 04:10:38,839][05219] Updated weights for policy 1, policy_version 35420 (0.0008) -[2023-10-16 04:10:38,840][05218] Updated weights for policy 0, policy_version 35542 (0.0008) -[2023-10-16 04:10:39,209][05218] Updated weights for policy 0, policy_version 35552 (0.0007) -[2023-10-16 04:10:42,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 72679424. Throughput: 0: 1779.5, 1: 1780.6. Samples: 18179278. Policy #0 lag: (min: 31.0, avg: 32.8, max: 59.0) -[2023-10-16 04:10:42,351][03835] Avg episode reward: [(0, '5.620'), (1, '5.790')] -[2023-10-16 04:10:42,648][05219] Updated weights for policy 1, policy_version 35430 (0.0009) -[2023-10-16 04:10:42,872][05218] Updated weights for policy 0, policy_version 35562 (0.0009) -[2023-10-16 04:10:43,004][05219] Updated weights for policy 1, policy_version 35440 (0.0008) -[2023-10-16 04:10:43,244][05218] Updated weights for policy 0, policy_version 35572 (0.0009) -[2023-10-16 04:10:43,364][05219] Updated weights for policy 1, policy_version 35450 (0.0008) -[2023-10-16 04:10:43,622][05218] Updated weights for policy 0, policy_version 35582 (0.0008) -[2023-10-16 04:10:47,025][05219] Updated weights for policy 1, policy_version 35460 (0.0007) -[2023-10-16 04:10:47,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 72744960. Throughput: 0: 1778.1, 1: 1787.7. Samples: 18201398. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-16 04:10:47,351][03835] Avg episode reward: [(0, '6.150'), (1, '4.840')] -[2023-10-16 04:10:47,396][05219] Updated weights for policy 1, policy_version 35470 (0.0010) -[2023-10-16 04:10:47,461][05218] Updated weights for policy 0, policy_version 35592 (0.0011) -[2023-10-16 04:10:47,757][05219] Updated weights for policy 1, policy_version 35480 (0.0008) -[2023-10-16 04:10:47,829][05218] Updated weights for policy 0, policy_version 35602 (0.0010) -[2023-10-16 04:10:48,208][05218] Updated weights for policy 0, policy_version 35612 (0.0010) -[2023-10-16 04:10:51,441][05219] Updated weights for policy 1, policy_version 35490 (0.0009) -[2023-10-16 04:10:51,841][05219] Updated weights for policy 1, policy_version 35500 (0.0008) -[2023-10-16 04:10:51,983][05218] Updated weights for policy 0, policy_version 35622 (0.0008) -[2023-10-16 04:10:52,201][05219] Updated weights for policy 1, policy_version 35510 (0.0009) -[2023-10-16 04:10:52,347][05218] Updated weights for policy 0, policy_version 35632 (0.0008) -[2023-10-16 04:10:52,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 72810496. Throughput: 0: 1791.4, 1: 1792.1. Samples: 18221946. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-16 04:10:52,352][03835] Avg episode reward: [(0, '6.010'), (1, '4.780')] -[2023-10-16 04:10:52,566][05219] Updated weights for policy 1, policy_version 35520 (0.0007) -[2023-10-16 04:10:52,728][05218] Updated weights for policy 0, policy_version 35642 (0.0010) -[2023-10-16 04:10:56,325][05219] Updated weights for policy 1, policy_version 35530 (0.0009) -[2023-10-16 04:10:56,450][05218] Updated weights for policy 0, policy_version 35652 (0.0009) -[2023-10-16 04:10:56,691][05219] Updated weights for policy 1, policy_version 35540 (0.0008) -[2023-10-16 04:10:56,817][05218] Updated weights for policy 0, policy_version 35662 (0.0008) -[2023-10-16 04:10:57,067][05219] Updated weights for policy 1, policy_version 35550 (0.0008) -[2023-10-16 04:10:57,189][05218] Updated weights for policy 0, policy_version 35672 (0.0009) -[2023-10-16 04:10:57,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 72908800. Throughput: 0: 1769.6, 1: 1779.7. Samples: 18233220. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-16 04:10:57,351][03835] Avg episode reward: [(0, '6.070'), (1, '5.540')] -[2023-10-16 04:11:00,956][05219] Updated weights for policy 1, policy_version 35560 (0.0009) -[2023-10-16 04:11:01,034][05218] Updated weights for policy 0, policy_version 35682 (0.0008) -[2023-10-16 04:11:01,317][05219] Updated weights for policy 1, policy_version 35570 (0.0009) -[2023-10-16 04:11:01,430][05218] Updated weights for policy 0, policy_version 35692 (0.0009) -[2023-10-16 04:11:01,677][05219] Updated weights for policy 1, policy_version 35580 (0.0009) -[2023-10-16 04:11:01,800][05218] Updated weights for policy 0, policy_version 35702 (0.0008) -[2023-10-16 04:11:02,169][05218] Updated weights for policy 0, policy_version 35712 (0.0008) -[2023-10-16 04:11:02,350][03835] Fps is (10 sec: 19661.4, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 73007104. Throughput: 0: 1796.8, 1: 1799.7. Samples: 18254490. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-16 04:11:02,351][03835] Avg episode reward: [(0, '6.100'), (1, '6.420')] -[2023-10-16 04:11:05,465][05219] Updated weights for policy 1, policy_version 35590 (0.0008) -[2023-10-16 04:11:05,825][05219] Updated weights for policy 1, policy_version 35600 (0.0007) -[2023-10-16 04:11:05,878][05218] Updated weights for policy 0, policy_version 35722 (0.0007) -[2023-10-16 04:11:06,183][05219] Updated weights for policy 1, policy_version 35610 (0.0007) -[2023-10-16 04:11:06,240][05218] Updated weights for policy 0, policy_version 35732 (0.0009) -[2023-10-16 04:11:06,613][05218] Updated weights for policy 0, policy_version 35742 (0.0009) -[2023-10-16 04:11:07,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 73072640. Throughput: 0: 1771.9, 1: 1781.1. Samples: 18274950. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-16 04:11:07,351][03835] Avg episode reward: [(0, '6.020'), (1, '6.010')] -[2023-10-16 04:11:09,883][05219] Updated weights for policy 1, policy_version 35620 (0.0008) -[2023-10-16 04:11:10,255][05219] Updated weights for policy 1, policy_version 35630 (0.0008) -[2023-10-16 04:11:10,335][05218] Updated weights for policy 0, policy_version 35752 (0.0008) -[2023-10-16 04:11:10,626][05219] Updated weights for policy 1, policy_version 35640 (0.0008) -[2023-10-16 04:11:10,711][05218] Updated weights for policy 0, policy_version 35762 (0.0009) -[2023-10-16 04:11:11,089][05218] Updated weights for policy 0, policy_version 35772 (0.0009) -[2023-10-16 04:11:12,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 73138176. Throughput: 0: 1797.4, 1: 1794.8. Samples: 18286830. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) -[2023-10-16 04:11:12,351][03835] Avg episode reward: [(0, '5.780'), (1, '5.990')] -[2023-10-16 04:11:14,463][05219] Updated weights for policy 1, policy_version 35650 (0.0009) -[2023-10-16 04:11:14,822][05219] Updated weights for policy 1, policy_version 35660 (0.0008) -[2023-10-16 04:11:14,960][05218] Updated weights for policy 0, policy_version 35782 (0.0008) -[2023-10-16 04:11:15,193][05219] Updated weights for policy 1, policy_version 35670 (0.0008) -[2023-10-16 04:11:15,339][05218] Updated weights for policy 0, policy_version 35792 (0.0007) -[2023-10-16 04:11:15,556][05219] Updated weights for policy 1, policy_version 35680 (0.0008) -[2023-10-16 04:11:15,716][05218] Updated weights for policy 0, policy_version 35802 (0.0009) -[2023-10-16 04:11:17,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 73203712. Throughput: 0: 1773.5, 1: 1776.1. Samples: 18306734. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) -[2023-10-16 04:11:17,351][03835] Avg episode reward: [(0, '5.430'), (1, '5.460')] -[2023-10-16 04:11:19,410][05219] Updated weights for policy 1, policy_version 35690 (0.0010) -[2023-10-16 04:11:19,445][05218] Updated weights for policy 0, policy_version 35812 (0.0010) -[2023-10-16 04:11:19,780][05219] Updated weights for policy 1, policy_version 35700 (0.0008) -[2023-10-16 04:11:19,812][05218] Updated weights for policy 0, policy_version 35822 (0.0008) -[2023-10-16 04:11:20,138][05219] Updated weights for policy 1, policy_version 35710 (0.0010) -[2023-10-16 04:11:20,182][05218] Updated weights for policy 0, policy_version 35832 (0.0008) -[2023-10-16 04:11:22,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 73269248. Throughput: 0: 1776.1, 1: 1775.5. Samples: 18329294. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) -[2023-10-16 04:11:22,351][03835] Avg episode reward: [(0, '6.760'), (1, '5.980')] -[2023-10-16 04:11:24,032][05219] Updated weights for policy 1, policy_version 35720 (0.0009) -[2023-10-16 04:11:24,080][05218] Updated weights for policy 0, policy_version 35842 (0.0009) -[2023-10-16 04:11:24,394][05219] Updated weights for policy 1, policy_version 35730 (0.0008) -[2023-10-16 04:11:24,457][05218] Updated weights for policy 0, policy_version 35852 (0.0009) -[2023-10-16 04:11:24,755][05219] Updated weights for policy 1, policy_version 35740 (0.0008) -[2023-10-16 04:11:24,833][05218] Updated weights for policy 0, policy_version 35862 (0.0009) -[2023-10-16 04:11:25,205][05218] Updated weights for policy 0, policy_version 35872 (0.0009) -[2023-10-16 04:11:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 73334784. Throughput: 0: 1772.2, 1: 1771.1. Samples: 18338726. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) -[2023-10-16 04:11:27,351][03835] Avg episode reward: [(0, '6.730'), (1, '5.730')] -[2023-10-16 04:11:28,566][05219] Updated weights for policy 1, policy_version 35750 (0.0009) -[2023-10-16 04:11:28,935][05219] Updated weights for policy 1, policy_version 35760 (0.0009) -[2023-10-16 04:11:29,091][05218] Updated weights for policy 0, policy_version 35882 (0.0007) -[2023-10-16 04:11:29,295][05219] Updated weights for policy 1, policy_version 35770 (0.0008) -[2023-10-16 04:11:29,459][05218] Updated weights for policy 0, policy_version 35892 (0.0009) -[2023-10-16 04:11:29,832][05218] Updated weights for policy 0, policy_version 35902 (0.0010) -[2023-10-16 04:11:32,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 73400320. Throughput: 0: 1773.1, 1: 1773.7. Samples: 18361004. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) -[2023-10-16 04:11:32,351][03835] Avg episode reward: [(0, '6.650'), (1, '5.860')] -[2023-10-16 04:11:33,064][05219] Updated weights for policy 1, policy_version 35780 (0.0008) -[2023-10-16 04:11:33,430][05219] Updated weights for policy 1, policy_version 35790 (0.0007) -[2023-10-16 04:11:33,588][05218] Updated weights for policy 0, policy_version 35912 (0.0009) -[2023-10-16 04:11:33,801][05219] Updated weights for policy 1, policy_version 35800 (0.0007) -[2023-10-16 04:11:33,954][05218] Updated weights for policy 0, policy_version 35922 (0.0008) -[2023-10-16 04:11:34,331][05218] Updated weights for policy 0, policy_version 35932 (0.0009) -[2023-10-16 04:11:37,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 73465856. Throughput: 0: 1788.4, 1: 1793.7. Samples: 18383140. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) -[2023-10-16 04:11:37,351][03835] Avg episode reward: [(0, '5.780'), (1, '6.180')] -[2023-10-16 04:11:37,360][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000035808_36667392.pth... -[2023-10-16 04:11:37,360][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000035936_36798464.pth... -[2023-10-16 04:11:37,401][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000034272_35094528.pth -[2023-10-16 04:11:37,401][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000034144_34963456.pth -[2023-10-16 04:11:37,711][05219] Updated weights for policy 1, policy_version 35810 (0.0008) -[2023-10-16 04:11:38,069][05219] Updated weights for policy 1, policy_version 35820 (0.0008) -[2023-10-16 04:11:38,119][05218] Updated weights for policy 0, policy_version 35942 (0.0008) -[2023-10-16 04:11:38,437][05219] Updated weights for policy 1, policy_version 35830 (0.0007) -[2023-10-16 04:11:38,488][05218] Updated weights for policy 0, policy_version 35952 (0.0010) -[2023-10-16 04:11:38,791][05219] Updated weights for policy 1, policy_version 35840 (0.0010) -[2023-10-16 04:11:38,865][05218] Updated weights for policy 0, policy_version 35962 (0.0008) -[2023-10-16 04:11:42,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 73531392. Throughput: 0: 1773.9, 1: 1773.9. Samples: 18392872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:11:42,351][03835] Avg episode reward: [(0, '6.290'), (1, '6.210')] -[2023-10-16 04:11:42,512][05218] Updated weights for policy 0, policy_version 35972 (0.0008) -[2023-10-16 04:11:42,639][05219] Updated weights for policy 1, policy_version 35850 (0.0009) -[2023-10-16 04:11:42,885][05218] Updated weights for policy 0, policy_version 35982 (0.0007) -[2023-10-16 04:11:43,006][05219] Updated weights for policy 1, policy_version 35860 (0.0009) -[2023-10-16 04:11:43,257][05218] Updated weights for policy 0, policy_version 35992 (0.0008) -[2023-10-16 04:11:43,367][05219] Updated weights for policy 1, policy_version 35870 (0.0007) -[2023-10-16 04:11:47,106][05218] Updated weights for policy 0, policy_version 36002 (0.0010) -[2023-10-16 04:11:47,245][05219] Updated weights for policy 1, policy_version 35880 (0.0007) -[2023-10-16 04:11:47,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 73596928. Throughput: 0: 1785.4, 1: 1783.5. Samples: 18415090. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:11:47,351][03835] Avg episode reward: [(0, '6.180'), (1, '6.160')] -[2023-10-16 04:11:47,508][05218] Updated weights for policy 0, policy_version 36012 (0.0008) -[2023-10-16 04:11:47,604][05219] Updated weights for policy 1, policy_version 35890 (0.0008) -[2023-10-16 04:11:47,877][05218] Updated weights for policy 0, policy_version 36022 (0.0008) -[2023-10-16 04:11:47,972][05219] Updated weights for policy 1, policy_version 35900 (0.0008) -[2023-10-16 04:11:48,256][05218] Updated weights for policy 0, policy_version 36032 (0.0009) -[2023-10-16 04:11:51,713][05219] Updated weights for policy 1, policy_version 35910 (0.0008) -[2023-10-16 04:11:51,930][05218] Updated weights for policy 0, policy_version 36042 (0.0007) -[2023-10-16 04:11:52,076][05219] Updated weights for policy 1, policy_version 35920 (0.0008) -[2023-10-16 04:11:52,307][05218] Updated weights for policy 0, policy_version 36052 (0.0007) -[2023-10-16 04:11:52,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.6, 300 sec: 14218.0). Total num frames: 73662464. Throughput: 0: 1788.5, 1: 1782.5. Samples: 18435644. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:11:52,351][03835] Avg episode reward: [(0, '5.750'), (1, '5.990')] -[2023-10-16 04:11:52,438][05219] Updated weights for policy 1, policy_version 35930 (0.0008) -[2023-10-16 04:11:52,689][05218] Updated weights for policy 0, policy_version 36062 (0.0009) -[2023-10-16 04:11:56,194][05219] Updated weights for policy 1, policy_version 35940 (0.0008) -[2023-10-16 04:11:56,498][05218] Updated weights for policy 0, policy_version 36072 (0.0007) -[2023-10-16 04:11:56,551][05219] Updated weights for policy 1, policy_version 35950 (0.0008) -[2023-10-16 04:11:56,879][05218] Updated weights for policy 0, policy_version 36082 (0.0009) -[2023-10-16 04:11:56,920][05219] Updated weights for policy 1, policy_version 35960 (0.0007) -[2023-10-16 04:11:57,252][05218] Updated weights for policy 0, policy_version 36092 (0.0009) -[2023-10-16 04:11:57,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 73760768. Throughput: 0: 1779.7, 1: 1780.0. Samples: 18447016. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:11:57,351][03835] Avg episode reward: [(0, '5.990'), (1, '5.850')] -[2023-10-16 04:12:00,573][05219] Updated weights for policy 1, policy_version 35970 (0.0010) -[2023-10-16 04:12:00,937][05219] Updated weights for policy 1, policy_version 35980 (0.0008) -[2023-10-16 04:12:01,059][05218] Updated weights for policy 0, policy_version 36102 (0.0009) -[2023-10-16 04:12:01,297][05219] Updated weights for policy 1, policy_version 35990 (0.0007) -[2023-10-16 04:12:01,426][05218] Updated weights for policy 0, policy_version 36112 (0.0008) -[2023-10-16 04:12:01,661][05219] Updated weights for policy 1, policy_version 36000 (0.0007) -[2023-10-16 04:12:01,807][05218] Updated weights for policy 0, policy_version 36122 (0.0007) -[2023-10-16 04:12:02,350][03835] Fps is (10 sec: 19660.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 73859072. Throughput: 0: 1792.2, 1: 1791.1. Samples: 18467984. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:12:02,351][03835] Avg episode reward: [(0, '6.090'), (1, '6.200')] -[2023-10-16 04:12:05,388][05219] Updated weights for policy 1, policy_version 36010 (0.0008) -[2023-10-16 04:12:05,481][05218] Updated weights for policy 0, policy_version 36132 (0.0008) -[2023-10-16 04:12:05,756][05219] Updated weights for policy 1, policy_version 36020 (0.0008) -[2023-10-16 04:12:05,857][05218] Updated weights for policy 0, policy_version 36142 (0.0007) -[2023-10-16 04:12:06,116][05219] Updated weights for policy 1, policy_version 36030 (0.0008) -[2023-10-16 04:12:06,230][05218] Updated weights for policy 0, policy_version 36152 (0.0009) -[2023-10-16 04:12:07,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 73924608. Throughput: 0: 1775.3, 1: 1770.5. Samples: 18488854. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-16 04:12:07,351][03835] Avg episode reward: [(0, '6.110'), (1, '6.370')] -[2023-10-16 04:12:09,980][05219] Updated weights for policy 1, policy_version 36040 (0.0009) -[2023-10-16 04:12:09,990][05218] Updated weights for policy 0, policy_version 36162 (0.0010) -[2023-10-16 04:12:10,354][05219] Updated weights for policy 1, policy_version 36050 (0.0008) -[2023-10-16 04:12:10,359][05218] Updated weights for policy 0, policy_version 36172 (0.0008) -[2023-10-16 04:12:10,716][05219] Updated weights for policy 1, policy_version 36060 (0.0007) -[2023-10-16 04:12:10,729][05218] Updated weights for policy 0, policy_version 36182 (0.0010) -[2023-10-16 04:12:11,111][05218] Updated weights for policy 0, policy_version 36192 (0.0009) -[2023-10-16 04:12:12,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 73990144. Throughput: 0: 1800.3, 1: 1791.3. Samples: 18500350. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-16 04:12:12,351][03835] Avg episode reward: [(0, '6.770'), (1, '5.780')] -[2023-10-16 04:12:14,474][05219] Updated weights for policy 1, policy_version 36070 (0.0008) -[2023-10-16 04:12:14,848][05219] Updated weights for policy 1, policy_version 36080 (0.0008) -[2023-10-16 04:12:14,874][05218] Updated weights for policy 0, policy_version 36202 (0.0007) -[2023-10-16 04:12:15,221][05219] Updated weights for policy 1, policy_version 36090 (0.0007) -[2023-10-16 04:12:15,246][05218] Updated weights for policy 0, policy_version 36212 (0.0008) -[2023-10-16 04:12:15,624][05218] Updated weights for policy 0, policy_version 36222 (0.0008) -[2023-10-16 04:12:17,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 74055680. Throughput: 0: 1784.3, 1: 1764.7. Samples: 18520708. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-16 04:12:17,351][03835] Avg episode reward: [(0, '6.000'), (1, '5.940')] -[2023-10-16 04:12:19,125][05219] Updated weights for policy 1, policy_version 36100 (0.0009) -[2023-10-16 04:12:19,296][05218] Updated weights for policy 0, policy_version 36232 (0.0010) -[2023-10-16 04:12:19,488][05219] Updated weights for policy 1, policy_version 36110 (0.0007) -[2023-10-16 04:12:19,676][05218] Updated weights for policy 0, policy_version 36242 (0.0009) -[2023-10-16 04:12:19,855][05219] Updated weights for policy 1, policy_version 36120 (0.0007) -[2023-10-16 04:12:20,046][05218] Updated weights for policy 0, policy_version 36252 (0.0008) -[2023-10-16 04:12:22,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 74121216. Throughput: 0: 1794.1, 1: 1764.0. Samples: 18543258. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-16 04:12:22,351][03835] Avg episode reward: [(0, '6.350'), (1, '6.420')] -[2023-10-16 04:12:23,646][05218] Updated weights for policy 0, policy_version 36262 (0.0008) -[2023-10-16 04:12:23,846][05219] Updated weights for policy 1, policy_version 36130 (0.0008) -[2023-10-16 04:12:24,026][05218] Updated weights for policy 0, policy_version 36272 (0.0008) -[2023-10-16 04:12:24,244][05219] Updated weights for policy 1, policy_version 36140 (0.0009) -[2023-10-16 04:12:24,405][05218] Updated weights for policy 0, policy_version 36282 (0.0009) -[2023-10-16 04:12:24,617][05219] Updated weights for policy 1, policy_version 36150 (0.0008) -[2023-10-16 04:12:24,975][05219] Updated weights for policy 1, policy_version 36160 (0.0009) -[2023-10-16 04:12:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 74186752. Throughput: 0: 1792.8, 1: 1759.2. Samples: 18552708. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-16 04:12:27,351][03835] Avg episode reward: [(0, '6.530'), (1, '6.250')] -[2023-10-16 04:12:28,139][05218] Updated weights for policy 0, policy_version 36292 (0.0008) -[2023-10-16 04:12:28,514][05218] Updated weights for policy 0, policy_version 36302 (0.0009) -[2023-10-16 04:12:28,778][05219] Updated weights for policy 1, policy_version 36170 (0.0007) -[2023-10-16 04:12:28,881][05218] Updated weights for policy 0, policy_version 36312 (0.0008) -[2023-10-16 04:12:29,134][05219] Updated weights for policy 1, policy_version 36180 (0.0009) -[2023-10-16 04:12:29,496][05219] Updated weights for policy 1, policy_version 36190 (0.0010) -[2023-10-16 04:12:32,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 74252288. Throughput: 0: 1793.4, 1: 1761.5. Samples: 18575060. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-16 04:12:32,351][03835] Avg episode reward: [(0, '6.250'), (1, '5.970')] -[2023-10-16 04:12:32,722][05218] Updated weights for policy 0, policy_version 36322 (0.0008) -[2023-10-16 04:12:33,126][05218] Updated weights for policy 0, policy_version 36332 (0.0007) -[2023-10-16 04:12:33,326][05219] Updated weights for policy 1, policy_version 36200 (0.0008) -[2023-10-16 04:12:33,505][05218] Updated weights for policy 0, policy_version 36342 (0.0009) -[2023-10-16 04:12:33,691][05219] Updated weights for policy 1, policy_version 36210 (0.0007) -[2023-10-16 04:12:33,873][05218] Updated weights for policy 0, policy_version 36352 (0.0008) -[2023-10-16 04:12:34,054][05219] Updated weights for policy 1, policy_version 36220 (0.0007) -[2023-10-16 04:12:37,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 74317824. Throughput: 0: 1807.5, 1: 1784.1. Samples: 18597270. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:12:37,352][03835] Avg episode reward: [(0, '6.550'), (1, '5.850')] -[2023-10-16 04:12:37,504][05218] Updated weights for policy 0, policy_version 36362 (0.0010) -[2023-10-16 04:12:37,818][05219] Updated weights for policy 1, policy_version 36230 (0.0008) -[2023-10-16 04:12:37,881][05218] Updated weights for policy 0, policy_version 36372 (0.0009) -[2023-10-16 04:12:38,186][05219] Updated weights for policy 1, policy_version 36240 (0.0008) -[2023-10-16 04:12:38,255][05218] Updated weights for policy 0, policy_version 36382 (0.0009) -[2023-10-16 04:12:38,540][05219] Updated weights for policy 1, policy_version 36250 (0.0009) -[2023-10-16 04:12:41,991][05218] Updated weights for policy 0, policy_version 36392 (0.0008) -[2023-10-16 04:12:42,208][05219] Updated weights for policy 1, policy_version 36260 (0.0008) -[2023-10-16 04:12:42,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 74383360. Throughput: 0: 1794.8, 1: 1768.0. Samples: 18607340. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:12:42,351][03835] Avg episode reward: [(0, '6.450'), (1, '5.700')] -[2023-10-16 04:12:42,369][05218] Updated weights for policy 0, policy_version 36402 (0.0007) -[2023-10-16 04:12:42,580][05219] Updated weights for policy 1, policy_version 36270 (0.0008) -[2023-10-16 04:12:42,746][05218] Updated weights for policy 0, policy_version 36412 (0.0007) -[2023-10-16 04:12:42,933][05219] Updated weights for policy 1, policy_version 36280 (0.0008) -[2023-10-16 04:12:46,516][05218] Updated weights for policy 0, policy_version 36422 (0.0008) -[2023-10-16 04:12:46,655][05219] Updated weights for policy 1, policy_version 36290 (0.0011) -[2023-10-16 04:12:46,893][05218] Updated weights for policy 0, policy_version 36432 (0.0007) -[2023-10-16 04:12:47,023][05219] Updated weights for policy 1, policy_version 36300 (0.0008) -[2023-10-16 04:12:47,264][05218] Updated weights for policy 0, policy_version 36442 (0.0007) -[2023-10-16 04:12:47,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 74448896. Throughput: 0: 1805.6, 1: 1782.7. Samples: 18629456. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:12:47,351][03835] Avg episode reward: [(0, '6.480'), (1, '5.810')] -[2023-10-16 04:12:47,386][05219] Updated weights for policy 1, policy_version 36310 (0.0008) -[2023-10-16 04:12:47,752][05219] Updated weights for policy 1, policy_version 36320 (0.0008) -[2023-10-16 04:12:51,142][05218] Updated weights for policy 0, policy_version 36452 (0.0008) -[2023-10-16 04:12:51,514][05218] Updated weights for policy 0, policy_version 36462 (0.0007) -[2023-10-16 04:12:51,598][05219] Updated weights for policy 1, policy_version 36330 (0.0009) -[2023-10-16 04:12:51,892][05218] Updated weights for policy 0, policy_version 36472 (0.0007) -[2023-10-16 04:12:51,971][05219] Updated weights for policy 1, policy_version 36340 (0.0008) -[2023-10-16 04:12:52,335][05219] Updated weights for policy 1, policy_version 36350 (0.0009) -[2023-10-16 04:12:52,350][03835] Fps is (10 sec: 16383.5, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 74547200. Throughput: 0: 1785.4, 1: 1777.6. Samples: 18649188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:12:52,351][03835] Avg episode reward: [(0, '5.940'), (1, '5.840')] -[2023-10-16 04:12:55,635][05218] Updated weights for policy 0, policy_version 36482 (0.0007) -[2023-10-16 04:12:56,015][05218] Updated weights for policy 0, policy_version 36492 (0.0009) -[2023-10-16 04:12:56,158][05219] Updated weights for policy 1, policy_version 36360 (0.0009) -[2023-10-16 04:12:56,383][05218] Updated weights for policy 0, policy_version 36502 (0.0007) -[2023-10-16 04:12:56,526][05219] Updated weights for policy 1, policy_version 36370 (0.0008) -[2023-10-16 04:12:56,755][05218] Updated weights for policy 0, policy_version 36512 (0.0009) -[2023-10-16 04:12:56,889][05219] Updated weights for policy 1, policy_version 36380 (0.0009) -[2023-10-16 04:12:57,350][03835] Fps is (10 sec: 19660.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 74645504. Throughput: 0: 1797.6, 1: 1779.8. Samples: 18661336. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:12:57,351][03835] Avg episode reward: [(0, '6.310'), (1, '6.260')] -[2023-10-16 04:13:00,389][05218] Updated weights for policy 0, policy_version 36522 (0.0009) -[2023-10-16 04:13:00,513][05219] Updated weights for policy 1, policy_version 36390 (0.0009) -[2023-10-16 04:13:00,783][05218] Updated weights for policy 0, policy_version 36532 (0.0008) -[2023-10-16 04:13:00,874][05219] Updated weights for policy 1, policy_version 36400 (0.0008) -[2023-10-16 04:13:01,144][05218] Updated weights for policy 0, policy_version 36542 (0.0007) -[2023-10-16 04:13:01,244][05219] Updated weights for policy 1, policy_version 36410 (0.0007) -[2023-10-16 04:13:02,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 74711040. Throughput: 0: 1790.5, 1: 1783.6. Samples: 18681544. Policy #0 lag: (min: 15.0, avg: 15.9, max: 35.0) -[2023-10-16 04:13:02,351][03835] Avg episode reward: [(0, '6.730'), (1, '5.570')] -[2023-10-16 04:13:04,920][05218] Updated weights for policy 0, policy_version 36552 (0.0008) -[2023-10-16 04:13:05,023][05219] Updated weights for policy 1, policy_version 36420 (0.0009) -[2023-10-16 04:13:05,303][05218] Updated weights for policy 0, policy_version 36562 (0.0008) -[2023-10-16 04:13:05,392][05219] Updated weights for policy 1, policy_version 36430 (0.0009) -[2023-10-16 04:13:05,666][05218] Updated weights for policy 0, policy_version 36572 (0.0007) -[2023-10-16 04:13:05,750][05219] Updated weights for policy 1, policy_version 36440 (0.0009) -[2023-10-16 04:13:07,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 74776576. Throughput: 0: 1784.7, 1: 1776.5. Samples: 18703516. Policy #0 lag: (min: 15.0, avg: 15.9, max: 35.0) -[2023-10-16 04:13:07,351][03835] Avg episode reward: [(0, '6.110'), (1, '6.000')] -[2023-10-16 04:13:09,419][05218] Updated weights for policy 0, policy_version 36582 (0.0008) -[2023-10-16 04:13:09,709][05219] Updated weights for policy 1, policy_version 36450 (0.0008) -[2023-10-16 04:13:09,795][05218] Updated weights for policy 0, policy_version 36592 (0.0007) -[2023-10-16 04:13:10,111][05219] Updated weights for policy 1, policy_version 36460 (0.0009) -[2023-10-16 04:13:10,173][05218] Updated weights for policy 0, policy_version 36602 (0.0007) -[2023-10-16 04:13:10,472][05219] Updated weights for policy 1, policy_version 36470 (0.0008) -[2023-10-16 04:13:10,836][05219] Updated weights for policy 1, policy_version 36480 (0.0010) -[2023-10-16 04:13:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 74842112. Throughput: 0: 1790.5, 1: 1799.5. Samples: 18714262. Policy #0 lag: (min: 15.0, avg: 15.9, max: 35.0) -[2023-10-16 04:13:12,351][03835] Avg episode reward: [(0, '5.950'), (1, '5.500')] -[2023-10-16 04:13:13,799][05218] Updated weights for policy 0, policy_version 36612 (0.0009) -[2023-10-16 04:13:14,176][05218] Updated weights for policy 0, policy_version 36622 (0.0009) -[2023-10-16 04:13:14,547][05218] Updated weights for policy 0, policy_version 36632 (0.0009) -[2023-10-16 04:13:14,827][05219] Updated weights for policy 1, policy_version 36490 (0.0007) -[2023-10-16 04:13:15,183][05219] Updated weights for policy 1, policy_version 36500 (0.0007) -[2023-10-16 04:13:15,544][05219] Updated weights for policy 1, policy_version 36510 (0.0008) -[2023-10-16 04:13:17,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 74907648. Throughput: 0: 1791.6, 1: 1774.4. Samples: 18735534. Policy #0 lag: (min: 15.0, avg: 15.9, max: 35.0) -[2023-10-16 04:13:17,351][03835] Avg episode reward: [(0, '6.160'), (1, '5.230')] -[2023-10-16 04:13:18,327][05218] Updated weights for policy 0, policy_version 36642 (0.0008) -[2023-10-16 04:13:18,718][05218] Updated weights for policy 0, policy_version 36652 (0.0009) -[2023-10-16 04:13:19,097][05218] Updated weights for policy 0, policy_version 36662 (0.0010) -[2023-10-16 04:13:19,253][05219] Updated weights for policy 1, policy_version 36520 (0.0007) -[2023-10-16 04:13:19,474][05218] Updated weights for policy 0, policy_version 36672 (0.0009) -[2023-10-16 04:13:19,615][05219] Updated weights for policy 1, policy_version 36530 (0.0007) -[2023-10-16 04:13:19,990][05219] Updated weights for policy 1, policy_version 36540 (0.0010) -[2023-10-16 04:13:22,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 74973184. Throughput: 0: 1799.9, 1: 1770.1. Samples: 18757920. Policy #0 lag: (min: 15.0, avg: 15.9, max: 35.0) -[2023-10-16 04:13:22,351][03835] Avg episode reward: [(0, '5.960'), (1, '5.660')] -[2023-10-16 04:13:23,219][05218] Updated weights for policy 0, policy_version 36682 (0.0009) -[2023-10-16 04:13:23,600][05218] Updated weights for policy 0, policy_version 36692 (0.0008) -[2023-10-16 04:13:23,833][05219] Updated weights for policy 1, policy_version 36550 (0.0008) -[2023-10-16 04:13:23,973][05218] Updated weights for policy 0, policy_version 36702 (0.0007) -[2023-10-16 04:13:24,196][05219] Updated weights for policy 1, policy_version 36560 (0.0009) -[2023-10-16 04:13:24,563][05219] Updated weights for policy 1, policy_version 36570 (0.0009) -[2023-10-16 04:13:27,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 75038720. Throughput: 0: 1794.7, 1: 1770.5. Samples: 18767776. Policy #0 lag: (min: 15.0, avg: 15.9, max: 35.0) -[2023-10-16 04:13:27,351][03835] Avg episode reward: [(0, '6.310'), (1, '5.660')] -[2023-10-16 04:13:27,569][05218] Updated weights for policy 0, policy_version 36712 (0.0009) -[2023-10-16 04:13:27,945][05218] Updated weights for policy 0, policy_version 36722 (0.0009) -[2023-10-16 04:13:28,318][05218] Updated weights for policy 0, policy_version 36732 (0.0009) -[2023-10-16 04:13:28,424][05219] Updated weights for policy 1, policy_version 36580 (0.0008) -[2023-10-16 04:13:28,775][05219] Updated weights for policy 1, policy_version 36590 (0.0008) -[2023-10-16 04:13:29,133][05219] Updated weights for policy 1, policy_version 36600 (0.0011) -[2023-10-16 04:13:32,038][05218] Updated weights for policy 0, policy_version 36742 (0.0009) -[2023-10-16 04:13:32,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 75104256. Throughput: 0: 1803.5, 1: 1770.6. Samples: 18790292. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-16 04:13:32,351][03835] Avg episode reward: [(0, '6.310'), (1, '6.590')] -[2023-10-16 04:13:32,403][05218] Updated weights for policy 0, policy_version 36752 (0.0009) -[2023-10-16 04:13:32,782][05218] Updated weights for policy 0, policy_version 36762 (0.0009) -[2023-10-16 04:13:32,787][05219] Updated weights for policy 1, policy_version 36610 (0.0007) -[2023-10-16 04:13:33,155][05219] Updated weights for policy 1, policy_version 36620 (0.0008) -[2023-10-16 04:13:33,524][05219] Updated weights for policy 1, policy_version 36630 (0.0009) -[2023-10-16 04:13:33,891][05219] Updated weights for policy 1, policy_version 36640 (0.0010) -[2023-10-16 04:13:36,579][05218] Updated weights for policy 0, policy_version 36772 (0.0010) -[2023-10-16 04:13:36,955][05218] Updated weights for policy 0, policy_version 36782 (0.0010) -[2023-10-16 04:13:37,335][05218] Updated weights for policy 0, policy_version 36792 (0.0008) -[2023-10-16 04:13:37,351][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 75169792. Throughput: 0: 1814.8, 1: 1798.8. Samples: 18811802. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-16 04:13:37,352][03835] Avg episode reward: [(0, '5.910'), (1, '6.560')] -[2023-10-16 04:13:37,637][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000036800_37683200.pth... -[2023-10-16 04:13:37,675][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000035104_35946496.pth -[2023-10-16 04:13:37,686][05219] Updated weights for policy 1, policy_version 36650 (0.0007) -[2023-10-16 04:13:38,058][05219] Updated weights for policy 1, policy_version 36660 (0.0009) -[2023-10-16 04:13:38,423][05219] Updated weights for policy 1, policy_version 36670 (0.0010) -[2023-10-16 04:13:38,492][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000036672_37552128.pth... -[2023-10-16 04:13:38,522][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000034976_35815424.pth -[2023-10-16 04:13:41,143][05218] Updated weights for policy 0, policy_version 36802 (0.0008) -[2023-10-16 04:13:41,519][05218] Updated weights for policy 0, policy_version 36812 (0.0007) -[2023-10-16 04:13:41,894][05218] Updated weights for policy 0, policy_version 36822 (0.0010) -[2023-10-16 04:13:42,149][05219] Updated weights for policy 1, policy_version 36680 (0.0007) -[2023-10-16 04:13:42,265][05218] Updated weights for policy 0, policy_version 36832 (0.0010) -[2023-10-16 04:13:42,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 75268096. Throughput: 0: 1804.0, 1: 1777.5. Samples: 18822500. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-16 04:13:42,351][03835] Avg episode reward: [(0, '6.370'), (1, '6.210')] -[2023-10-16 04:13:42,517][05219] Updated weights for policy 1, policy_version 36690 (0.0007) -[2023-10-16 04:13:42,890][05219] Updated weights for policy 1, policy_version 36700 (0.0011) -[2023-10-16 04:13:46,100][05218] Updated weights for policy 0, policy_version 36842 (0.0008) -[2023-10-16 04:13:46,479][05218] Updated weights for policy 0, policy_version 36852 (0.0009) -[2023-10-16 04:13:46,611][05219] Updated weights for policy 1, policy_version 36710 (0.0010) -[2023-10-16 04:13:46,849][05218] Updated weights for policy 0, policy_version 36862 (0.0009) -[2023-10-16 04:13:46,971][05219] Updated weights for policy 1, policy_version 36720 (0.0009) -[2023-10-16 04:13:47,338][05219] Updated weights for policy 1, policy_version 36730 (0.0008) -[2023-10-16 04:13:47,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 75333632. Throughput: 0: 1813.2, 1: 1791.7. Samples: 18843764. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-16 04:13:47,352][03835] Avg episode reward: [(0, '6.340'), (1, '6.500')] -[2023-10-16 04:13:50,693][05218] Updated weights for policy 0, policy_version 36872 (0.0010) -[2023-10-16 04:13:51,050][05219] Updated weights for policy 1, policy_version 36740 (0.0009) -[2023-10-16 04:13:51,064][05218] Updated weights for policy 0, policy_version 36882 (0.0009) -[2023-10-16 04:13:51,417][05219] Updated weights for policy 1, policy_version 36750 (0.0008) -[2023-10-16 04:13:51,440][05218] Updated weights for policy 0, policy_version 36892 (0.0007) -[2023-10-16 04:13:51,775][05219] Updated weights for policy 1, policy_version 36760 (0.0008) -[2023-10-16 04:13:52,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 75431936. Throughput: 0: 1790.7, 1: 1770.9. Samples: 18863786. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-16 04:13:52,351][03835] Avg episode reward: [(0, '5.920'), (1, '6.010')] -[2023-10-16 04:13:55,201][05218] Updated weights for policy 0, policy_version 36902 (0.0007) -[2023-10-16 04:13:55,580][05218] Updated weights for policy 0, policy_version 36912 (0.0009) -[2023-10-16 04:13:55,619][05219] Updated weights for policy 1, policy_version 36770 (0.0007) -[2023-10-16 04:13:55,957][05218] Updated weights for policy 0, policy_version 36922 (0.0009) -[2023-10-16 04:13:56,025][05219] Updated weights for policy 1, policy_version 36780 (0.0008) -[2023-10-16 04:13:56,393][05219] Updated weights for policy 1, policy_version 36790 (0.0009) -[2023-10-16 04:13:56,749][05219] Updated weights for policy 1, policy_version 36800 (0.0007) -[2023-10-16 04:13:57,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 75497472. Throughput: 0: 1803.5, 1: 1785.2. Samples: 18875754. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 04:13:57,351][03835] Avg episode reward: [(0, '5.930'), (1, '5.890')] -[2023-10-16 04:13:59,615][05218] Updated weights for policy 0, policy_version 36932 (0.0009) -[2023-10-16 04:13:59,998][05218] Updated weights for policy 0, policy_version 36942 (0.0009) -[2023-10-16 04:14:00,389][05218] Updated weights for policy 0, policy_version 36952 (0.0009) -[2023-10-16 04:14:00,631][05219] Updated weights for policy 1, policy_version 36810 (0.0009) -[2023-10-16 04:14:00,994][05219] Updated weights for policy 1, policy_version 36820 (0.0008) -[2023-10-16 04:14:01,373][05219] Updated weights for policy 1, policy_version 36830 (0.0010) -[2023-10-16 04:14:02,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 75563008. Throughput: 0: 1779.1, 1: 1788.8. Samples: 18896092. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 04:14:02,351][03835] Avg episode reward: [(0, '6.190'), (1, '6.560')] -[2023-10-16 04:14:04,211][05218] Updated weights for policy 0, policy_version 36962 (0.0011) -[2023-10-16 04:14:04,605][05218] Updated weights for policy 0, policy_version 36972 (0.0010) -[2023-10-16 04:14:04,979][05218] Updated weights for policy 0, policy_version 36982 (0.0008) -[2023-10-16 04:14:05,256][05219] Updated weights for policy 1, policy_version 36840 (0.0009) -[2023-10-16 04:14:05,361][05218] Updated weights for policy 0, policy_version 36992 (0.0007) -[2023-10-16 04:14:05,614][05219] Updated weights for policy 1, policy_version 36850 (0.0008) -[2023-10-16 04:14:05,981][05219] Updated weights for policy 1, policy_version 36860 (0.0007) -[2023-10-16 04:14:07,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 75628544. Throughput: 0: 1776.8, 1: 1776.5. Samples: 18917818. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 04:14:07,351][03835] Avg episode reward: [(0, '5.930'), (1, '5.870')] -[2023-10-16 04:14:09,076][05218] Updated weights for policy 0, policy_version 37002 (0.0010) -[2023-10-16 04:14:09,452][05218] Updated weights for policy 0, policy_version 37012 (0.0007) -[2023-10-16 04:14:09,747][05219] Updated weights for policy 1, policy_version 36870 (0.0008) -[2023-10-16 04:14:09,828][05218] Updated weights for policy 0, policy_version 37022 (0.0008) -[2023-10-16 04:14:10,114][05219] Updated weights for policy 1, policy_version 36880 (0.0009) -[2023-10-16 04:14:10,487][05219] Updated weights for policy 1, policy_version 36890 (0.0009) -[2023-10-16 04:14:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 75694080. Throughput: 0: 1774.6, 1: 1790.0. Samples: 18928180. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 04:14:12,351][03835] Avg episode reward: [(0, '6.200'), (1, '6.080')] -[2023-10-16 04:14:13,759][05218] Updated weights for policy 0, policy_version 37032 (0.0007) -[2023-10-16 04:14:14,128][05218] Updated weights for policy 0, policy_version 37042 (0.0007) -[2023-10-16 04:14:14,284][05219] Updated weights for policy 1, policy_version 36900 (0.0009) -[2023-10-16 04:14:14,500][05218] Updated weights for policy 0, policy_version 37052 (0.0009) -[2023-10-16 04:14:14,661][05219] Updated weights for policy 1, policy_version 36910 (0.0008) -[2023-10-16 04:14:15,021][05219] Updated weights for policy 1, policy_version 36920 (0.0007) -[2023-10-16 04:14:17,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 75759616. Throughput: 0: 1766.8, 1: 1772.8. Samples: 18949572. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 04:14:17,351][03835] Avg episode reward: [(0, '6.710'), (1, '5.940')] -[2023-10-16 04:14:18,135][05218] Updated weights for policy 0, policy_version 37062 (0.0010) -[2023-10-16 04:14:18,517][05218] Updated weights for policy 0, policy_version 37072 (0.0010) -[2023-10-16 04:14:18,735][05219] Updated weights for policy 1, policy_version 36930 (0.0010) -[2023-10-16 04:14:18,879][05218] Updated weights for policy 0, policy_version 37082 (0.0009) -[2023-10-16 04:14:19,110][05219] Updated weights for policy 1, policy_version 36940 (0.0009) -[2023-10-16 04:14:19,478][05219] Updated weights for policy 1, policy_version 36950 (0.0011) -[2023-10-16 04:14:19,836][05219] Updated weights for policy 1, policy_version 36960 (0.0010) -[2023-10-16 04:14:22,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 75825152. Throughput: 0: 1791.0, 1: 1768.8. Samples: 18971992. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 04:14:22,351][03835] Avg episode reward: [(0, '6.240'), (1, '5.660')] -[2023-10-16 04:14:22,654][05218] Updated weights for policy 0, policy_version 37092 (0.0008) -[2023-10-16 04:14:23,037][05218] Updated weights for policy 0, policy_version 37102 (0.0007) -[2023-10-16 04:14:23,409][05218] Updated weights for policy 0, policy_version 37112 (0.0007) -[2023-10-16 04:14:23,595][05219] Updated weights for policy 1, policy_version 36970 (0.0009) -[2023-10-16 04:14:23,958][05219] Updated weights for policy 1, policy_version 36980 (0.0010) -[2023-10-16 04:14:24,319][05219] Updated weights for policy 1, policy_version 36990 (0.0008) -[2023-10-16 04:14:27,112][05218] Updated weights for policy 0, policy_version 37122 (0.0008) -[2023-10-16 04:14:27,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 75890688. Throughput: 0: 1768.2, 1: 1769.9. Samples: 18981712. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-16 04:14:27,351][03835] Avg episode reward: [(0, '5.770'), (1, '6.280')] -[2023-10-16 04:14:27,492][05218] Updated weights for policy 0, policy_version 37132 (0.0010) -[2023-10-16 04:14:27,867][05218] Updated weights for policy 0, policy_version 37142 (0.0008) -[2023-10-16 04:14:28,091][05219] Updated weights for policy 1, policy_version 37000 (0.0007) -[2023-10-16 04:14:28,231][05218] Updated weights for policy 0, policy_version 37152 (0.0010) -[2023-10-16 04:14:28,464][05219] Updated weights for policy 1, policy_version 37010 (0.0009) -[2023-10-16 04:14:28,827][05219] Updated weights for policy 1, policy_version 37020 (0.0009) -[2023-10-16 04:14:31,863][05218] Updated weights for policy 0, policy_version 37162 (0.0008) -[2023-10-16 04:14:32,235][05218] Updated weights for policy 0, policy_version 37172 (0.0007) -[2023-10-16 04:14:32,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 75956224. Throughput: 0: 1792.4, 1: 1774.1. Samples: 19004254. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-16 04:14:32,351][03835] Avg episode reward: [(0, '6.440'), (1, '6.060')] -[2023-10-16 04:14:32,576][05219] Updated weights for policy 1, policy_version 37030 (0.0008) -[2023-10-16 04:14:32,603][05218] Updated weights for policy 0, policy_version 37182 (0.0008) -[2023-10-16 04:14:32,939][05219] Updated weights for policy 1, policy_version 37040 (0.0008) -[2023-10-16 04:14:33,316][05219] Updated weights for policy 1, policy_version 37050 (0.0008) -[2023-10-16 04:14:36,289][05218] Updated weights for policy 0, policy_version 37192 (0.0008) -[2023-10-16 04:14:36,663][05218] Updated weights for policy 0, policy_version 37202 (0.0009) -[2023-10-16 04:14:37,030][05218] Updated weights for policy 0, policy_version 37212 (0.0007) -[2023-10-16 04:14:37,212][05219] Updated weights for policy 1, policy_version 37060 (0.0007) -[2023-10-16 04:14:37,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 76054528. Throughput: 0: 1781.5, 1: 1802.5. Samples: 19025064. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-16 04:14:37,351][03835] Avg episode reward: [(0, '5.540'), (1, '6.510')] -[2023-10-16 04:14:37,582][05219] Updated weights for policy 1, policy_version 37070 (0.0008) -[2023-10-16 04:14:37,947][05219] Updated weights for policy 1, policy_version 37080 (0.0007) -[2023-10-16 04:14:40,727][05218] Updated weights for policy 0, policy_version 37222 (0.0008) -[2023-10-16 04:14:41,096][05218] Updated weights for policy 0, policy_version 37232 (0.0008) -[2023-10-16 04:14:41,471][05218] Updated weights for policy 0, policy_version 37242 (0.0010) -[2023-10-16 04:14:41,646][05219] Updated weights for policy 1, policy_version 37090 (0.0008) -[2023-10-16 04:14:42,010][05219] Updated weights for policy 1, policy_version 37100 (0.0009) -[2023-10-16 04:14:42,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 76120064. Throughput: 0: 1802.2, 1: 1773.9. Samples: 19036678. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-16 04:14:42,351][03835] Avg episode reward: [(0, '6.040'), (1, '6.850')] -[2023-10-16 04:14:42,373][05219] Updated weights for policy 1, policy_version 37110 (0.0010) -[2023-10-16 04:14:42,742][05219] Updated weights for policy 1, policy_version 37120 (0.0011) -[2023-10-16 04:14:45,110][05218] Updated weights for policy 0, policy_version 37252 (0.0009) -[2023-10-16 04:14:45,496][05218] Updated weights for policy 0, policy_version 37262 (0.0011) -[2023-10-16 04:14:45,872][05218] Updated weights for policy 0, policy_version 37272 (0.0009) -[2023-10-16 04:14:46,806][05219] Updated weights for policy 1, policy_version 37130 (0.0010) -[2023-10-16 04:14:47,167][05219] Updated weights for policy 1, policy_version 37140 (0.0010) -[2023-10-16 04:14:47,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 76185600. Throughput: 0: 1791.2, 1: 1790.1. Samples: 19057248. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-16 04:14:47,351][03835] Avg episode reward: [(0, '6.280'), (1, '6.650')] -[2023-10-16 04:14:47,540][05219] Updated weights for policy 1, policy_version 37150 (0.0009) -[2023-10-16 04:14:49,729][05218] Updated weights for policy 0, policy_version 37282 (0.0010) -[2023-10-16 04:14:50,123][05218] Updated weights for policy 0, policy_version 37292 (0.0008) -[2023-10-16 04:14:50,504][05218] Updated weights for policy 0, policy_version 37302 (0.0007) -[2023-10-16 04:14:50,881][05218] Updated weights for policy 0, policy_version 37312 (0.0009) -[2023-10-16 04:14:51,269][05219] Updated weights for policy 1, policy_version 37160 (0.0007) -[2023-10-16 04:14:51,643][05219] Updated weights for policy 1, policy_version 37170 (0.0009) -[2023-10-16 04:14:52,013][05219] Updated weights for policy 1, policy_version 37180 (0.0007) -[2023-10-16 04:14:52,351][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 76283904. Throughput: 0: 1791.8, 1: 1775.7. Samples: 19078356. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-16 04:14:52,352][03835] Avg episode reward: [(0, '5.930'), (1, '6.230')] -[2023-10-16 04:14:54,640][05218] Updated weights for policy 0, policy_version 37322 (0.0009) -[2023-10-16 04:14:55,016][05218] Updated weights for policy 0, policy_version 37332 (0.0007) -[2023-10-16 04:14:55,381][05218] Updated weights for policy 0, policy_version 37342 (0.0008) -[2023-10-16 04:14:55,871][05219] Updated weights for policy 1, policy_version 37190 (0.0008) -[2023-10-16 04:14:56,232][05219] Updated weights for policy 1, policy_version 37200 (0.0007) -[2023-10-16 04:14:56,590][05219] Updated weights for policy 1, policy_version 37210 (0.0009) -[2023-10-16 04:14:57,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 76349440. Throughput: 0: 1796.3, 1: 1788.3. Samples: 19089484. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-16 04:14:57,351][03835] Avg episode reward: [(0, '5.730'), (1, '6.770')] -[2023-10-16 04:14:59,114][05218] Updated weights for policy 0, policy_version 37352 (0.0011) -[2023-10-16 04:14:59,483][05218] Updated weights for policy 0, policy_version 37362 (0.0010) -[2023-10-16 04:14:59,862][05218] Updated weights for policy 0, policy_version 37372 (0.0007) -[2023-10-16 04:15:00,316][05219] Updated weights for policy 1, policy_version 37220 (0.0007) -[2023-10-16 04:15:00,684][05219] Updated weights for policy 1, policy_version 37230 (0.0008) -[2023-10-16 04:15:01,042][05219] Updated weights for policy 1, policy_version 37240 (0.0010) -[2023-10-16 04:15:02,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 76414976. Throughput: 0: 1797.2, 1: 1784.8. Samples: 19110758. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-16 04:15:02,351][03835] Avg episode reward: [(0, '6.190'), (1, '6.490')] -[2023-10-16 04:15:03,582][05218] Updated weights for policy 0, policy_version 37382 (0.0008) -[2023-10-16 04:15:03,955][05218] Updated weights for policy 0, policy_version 37392 (0.0009) -[2023-10-16 04:15:04,333][05218] Updated weights for policy 0, policy_version 37402 (0.0009) -[2023-10-16 04:15:04,751][05219] Updated weights for policy 1, policy_version 37250 (0.0007) -[2023-10-16 04:15:05,114][05219] Updated weights for policy 1, policy_version 37260 (0.0008) -[2023-10-16 04:15:05,479][05219] Updated weights for policy 1, policy_version 37270 (0.0010) -[2023-10-16 04:15:05,839][05219] Updated weights for policy 1, policy_version 37280 (0.0009) -[2023-10-16 04:15:07,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 76480512. Throughput: 0: 1803.0, 1: 1776.3. Samples: 19133062. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-16 04:15:07,351][03835] Avg episode reward: [(0, '6.520'), (1, '6.260')] -[2023-10-16 04:15:08,105][05218] Updated weights for policy 0, policy_version 37412 (0.0008) -[2023-10-16 04:15:08,477][05218] Updated weights for policy 0, policy_version 37422 (0.0009) -[2023-10-16 04:15:08,853][05218] Updated weights for policy 0, policy_version 37432 (0.0007) -[2023-10-16 04:15:09,583][05219] Updated weights for policy 1, policy_version 37290 (0.0007) -[2023-10-16 04:15:09,949][05219] Updated weights for policy 1, policy_version 37300 (0.0009) -[2023-10-16 04:15:10,322][05219] Updated weights for policy 1, policy_version 37310 (0.0007) -[2023-10-16 04:15:12,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 76546048. Throughput: 0: 1804.2, 1: 1786.1. Samples: 19143276. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-16 04:15:12,351][03835] Avg episode reward: [(0, '6.240'), (1, '6.030')] -[2023-10-16 04:15:12,514][05218] Updated weights for policy 0, policy_version 37442 (0.0009) -[2023-10-16 04:15:12,887][05218] Updated weights for policy 0, policy_version 37452 (0.0008) -[2023-10-16 04:15:13,261][05218] Updated weights for policy 0, policy_version 37462 (0.0010) -[2023-10-16 04:15:13,636][05218] Updated weights for policy 0, policy_version 37472 (0.0010) -[2023-10-16 04:15:14,053][05219] Updated weights for policy 1, policy_version 37320 (0.0007) -[2023-10-16 04:15:14,419][05219] Updated weights for policy 1, policy_version 37330 (0.0009) -[2023-10-16 04:15:14,781][05219] Updated weights for policy 1, policy_version 37340 (0.0007) -[2023-10-16 04:15:17,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 76611584. Throughput: 0: 1795.1, 1: 1777.2. Samples: 19165008. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-16 04:15:17,352][03835] Avg episode reward: [(0, '6.280'), (1, '6.040')] -[2023-10-16 04:15:17,505][05218] Updated weights for policy 0, policy_version 37482 (0.0008) -[2023-10-16 04:15:17,883][05218] Updated weights for policy 0, policy_version 37492 (0.0008) -[2023-10-16 04:15:18,256][05218] Updated weights for policy 0, policy_version 37502 (0.0007) -[2023-10-16 04:15:18,690][05219] Updated weights for policy 1, policy_version 37350 (0.0007) -[2023-10-16 04:15:19,052][05219] Updated weights for policy 1, policy_version 37360 (0.0008) -[2023-10-16 04:15:19,415][05219] Updated weights for policy 1, policy_version 37370 (0.0009) -[2023-10-16 04:15:21,964][05218] Updated weights for policy 0, policy_version 37512 (0.0007) -[2023-10-16 04:15:22,348][05218] Updated weights for policy 0, policy_version 37522 (0.0007) -[2023-10-16 04:15:22,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 76677120. Throughput: 0: 1808.4, 1: 1783.7. Samples: 19186710. Policy #0 lag: (min: 8.0, avg: 36.5, max: 40.0) -[2023-10-16 04:15:22,352][03835] Avg episode reward: [(0, '6.830'), (1, '5.840')] -[2023-10-16 04:15:22,718][05218] Updated weights for policy 0, policy_version 37532 (0.0007) -[2023-10-16 04:15:23,041][05219] Updated weights for policy 1, policy_version 37380 (0.0007) -[2023-10-16 04:15:23,402][05219] Updated weights for policy 1, policy_version 37390 (0.0008) -[2023-10-16 04:15:23,771][05219] Updated weights for policy 1, policy_version 37400 (0.0009) -[2023-10-16 04:15:26,500][05218] Updated weights for policy 0, policy_version 37542 (0.0008) -[2023-10-16 04:15:26,883][05218] Updated weights for policy 0, policy_version 37552 (0.0008) -[2023-10-16 04:15:27,268][05218] Updated weights for policy 0, policy_version 37562 (0.0009) -[2023-10-16 04:15:27,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 76742656. Throughput: 0: 1789.3, 1: 1780.8. Samples: 19197332. Policy #0 lag: (min: 8.0, avg: 36.5, max: 40.0) -[2023-10-16 04:15:27,351][03835] Avg episode reward: [(0, '6.040'), (1, '6.640')] -[2023-10-16 04:15:27,592][05219] Updated weights for policy 1, policy_version 37410 (0.0007) -[2023-10-16 04:15:27,979][05219] Updated weights for policy 1, policy_version 37420 (0.0007) -[2023-10-16 04:15:28,344][05219] Updated weights for policy 1, policy_version 37430 (0.0009) -[2023-10-16 04:15:28,713][05219] Updated weights for policy 1, policy_version 37440 (0.0010) -[2023-10-16 04:15:30,913][05218] Updated weights for policy 0, policy_version 37572 (0.0008) -[2023-10-16 04:15:31,291][05218] Updated weights for policy 0, policy_version 37582 (0.0007) -[2023-10-16 04:15:31,663][05218] Updated weights for policy 0, policy_version 37592 (0.0009) -[2023-10-16 04:15:32,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 76840960. Throughput: 0: 1805.9, 1: 1786.2. Samples: 19218892. Policy #0 lag: (min: 8.0, avg: 36.5, max: 40.0) -[2023-10-16 04:15:32,352][03835] Avg episode reward: [(0, '6.240'), (1, '6.400')] -[2023-10-16 04:15:32,591][05219] Updated weights for policy 1, policy_version 37450 (0.0008) -[2023-10-16 04:15:32,955][05219] Updated weights for policy 1, policy_version 37460 (0.0008) -[2023-10-16 04:15:33,319][05219] Updated weights for policy 1, policy_version 37470 (0.0008) -[2023-10-16 04:15:35,420][05218] Updated weights for policy 0, policy_version 37602 (0.0009) -[2023-10-16 04:15:35,818][05218] Updated weights for policy 0, policy_version 37612 (0.0007) -[2023-10-16 04:15:36,190][05218] Updated weights for policy 0, policy_version 37622 (0.0009) -[2023-10-16 04:15:36,560][05218] Updated weights for policy 0, policy_version 37632 (0.0008) -[2023-10-16 04:15:37,112][05219] Updated weights for policy 1, policy_version 37480 (0.0007) -[2023-10-16 04:15:37,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 76906496. Throughput: 0: 1788.9, 1: 1803.4. Samples: 19240012. Policy #0 lag: (min: 8.0, avg: 36.5, max: 40.0) -[2023-10-16 04:15:37,351][03835] Avg episode reward: [(0, '6.970'), (1, '5.520')] -[2023-10-16 04:15:37,358][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000037632_38535168.pth... -[2023-10-16 04:15:37,392][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000035936_36798464.pth -[2023-10-16 04:15:37,478][05219] Updated weights for policy 1, policy_version 37490 (0.0009) -[2023-10-16 04:15:37,834][05219] Updated weights for policy 1, policy_version 37500 (0.0008) -[2023-10-16 04:15:37,981][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000037504_38404096.pth... -[2023-10-16 04:15:38,010][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000035808_36667392.pth -[2023-10-16 04:15:40,243][05218] Updated weights for policy 0, policy_version 37642 (0.0008) -[2023-10-16 04:15:40,622][05218] Updated weights for policy 0, policy_version 37652 (0.0010) -[2023-10-16 04:15:40,994][05218] Updated weights for policy 0, policy_version 37662 (0.0008) -[2023-10-16 04:15:41,517][05219] Updated weights for policy 1, policy_version 37510 (0.0007) -[2023-10-16 04:15:41,881][05219] Updated weights for policy 1, policy_version 37520 (0.0007) -[2023-10-16 04:15:42,244][05219] Updated weights for policy 1, policy_version 37530 (0.0007) -[2023-10-16 04:15:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 76972032. Throughput: 0: 1807.8, 1: 1785.5. Samples: 19251182. Policy #0 lag: (min: 8.0, avg: 36.5, max: 40.0) -[2023-10-16 04:15:42,351][03835] Avg episode reward: [(0, '5.810'), (1, '6.580')] -[2023-10-16 04:15:44,576][05218] Updated weights for policy 0, policy_version 37672 (0.0008) -[2023-10-16 04:15:44,955][05218] Updated weights for policy 0, policy_version 37682 (0.0011) -[2023-10-16 04:15:45,334][05218] Updated weights for policy 0, policy_version 37692 (0.0009) -[2023-10-16 04:15:45,867][05219] Updated weights for policy 1, policy_version 37540 (0.0009) -[2023-10-16 04:15:46,230][05219] Updated weights for policy 1, policy_version 37550 (0.0010) -[2023-10-16 04:15:46,605][05219] Updated weights for policy 1, policy_version 37560 (0.0009) -[2023-10-16 04:15:47,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.2). Total num frames: 77070336. Throughput: 0: 1795.1, 1: 1803.8. Samples: 19272708. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-16 04:15:47,351][03835] Avg episode reward: [(0, '6.570'), (1, '6.560')] -[2023-10-16 04:15:49,100][05218] Updated weights for policy 0, policy_version 37702 (0.0011) -[2023-10-16 04:15:49,481][05218] Updated weights for policy 0, policy_version 37712 (0.0009) -[2023-10-16 04:15:49,847][05218] Updated weights for policy 0, policy_version 37722 (0.0007) -[2023-10-16 04:15:50,469][05219] Updated weights for policy 1, policy_version 37570 (0.0008) -[2023-10-16 04:15:50,836][05219] Updated weights for policy 1, policy_version 37580 (0.0009) -[2023-10-16 04:15:51,207][05219] Updated weights for policy 1, policy_version 37590 (0.0008) -[2023-10-16 04:15:51,562][05219] Updated weights for policy 1, policy_version 37600 (0.0008) -[2023-10-16 04:15:52,351][03835] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 77135872. Throughput: 0: 1789.2, 1: 1785.8. Samples: 19293940. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-16 04:15:52,352][03835] Avg episode reward: [(0, '7.050'), (1, '6.120')] -[2023-10-16 04:15:52,361][04766] Saving new best policy, reward=7.050! -[2023-10-16 04:15:53,540][05218] Updated weights for policy 0, policy_version 37732 (0.0007) -[2023-10-16 04:15:53,919][05218] Updated weights for policy 0, policy_version 37742 (0.0009) -[2023-10-16 04:15:54,297][05218] Updated weights for policy 0, policy_version 37752 (0.0009) -[2023-10-16 04:15:55,336][05219] Updated weights for policy 1, policy_version 37610 (0.0008) -[2023-10-16 04:15:55,693][05219] Updated weights for policy 1, policy_version 37620 (0.0007) -[2023-10-16 04:15:56,057][05219] Updated weights for policy 1, policy_version 37630 (0.0007) -[2023-10-16 04:15:57,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 77201408. Throughput: 0: 1789.9, 1: 1804.5. Samples: 19305024. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-16 04:15:57,351][03835] Avg episode reward: [(0, '6.590'), (1, '6.360')] -[2023-10-16 04:15:58,080][05218] Updated weights for policy 0, policy_version 37762 (0.0009) -[2023-10-16 04:15:58,452][05218] Updated weights for policy 0, policy_version 37772 (0.0010) -[2023-10-16 04:15:58,819][05218] Updated weights for policy 0, policy_version 37782 (0.0009) -[2023-10-16 04:15:59,192][05218] Updated weights for policy 0, policy_version 37792 (0.0010) -[2023-10-16 04:15:59,749][05219] Updated weights for policy 1, policy_version 37640 (0.0008) -[2023-10-16 04:16:00,106][05219] Updated weights for policy 1, policy_version 37650 (0.0010) -[2023-10-16 04:16:00,470][05219] Updated weights for policy 1, policy_version 37660 (0.0010) -[2023-10-16 04:16:02,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 77266944. Throughput: 0: 1793.1, 1: 1790.5. Samples: 19326270. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-16 04:16:02,351][03835] Avg episode reward: [(0, '6.560'), (1, '5.950')] -[2023-10-16 04:16:02,997][05218] Updated weights for policy 0, policy_version 37802 (0.0008) -[2023-10-16 04:16:03,378][05218] Updated weights for policy 0, policy_version 37812 (0.0007) -[2023-10-16 04:16:03,747][05218] Updated weights for policy 0, policy_version 37822 (0.0008) -[2023-10-16 04:16:04,207][05219] Updated weights for policy 1, policy_version 37670 (0.0008) -[2023-10-16 04:16:04,565][05219] Updated weights for policy 1, policy_version 37680 (0.0007) -[2023-10-16 04:16:04,932][05219] Updated weights for policy 1, policy_version 37690 (0.0007) -[2023-10-16 04:16:07,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 77332480. Throughput: 0: 1809.2, 1: 1790.9. Samples: 19348712. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-16 04:16:07,352][03835] Avg episode reward: [(0, '6.730'), (1, '5.420')] -[2023-10-16 04:16:07,406][05218] Updated weights for policy 0, policy_version 37832 (0.0007) -[2023-10-16 04:16:07,776][05218] Updated weights for policy 0, policy_version 37842 (0.0007) -[2023-10-16 04:16:08,162][05218] Updated weights for policy 0, policy_version 37852 (0.0010) -[2023-10-16 04:16:08,622][05219] Updated weights for policy 1, policy_version 37700 (0.0008) -[2023-10-16 04:16:08,990][05219] Updated weights for policy 1, policy_version 37710 (0.0008) -[2023-10-16 04:16:09,353][05219] Updated weights for policy 1, policy_version 37720 (0.0009) -[2023-10-16 04:16:11,792][05218] Updated weights for policy 0, policy_version 37862 (0.0009) -[2023-10-16 04:16:12,174][05218] Updated weights for policy 0, policy_version 37872 (0.0010) -[2023-10-16 04:16:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 77398016. Throughput: 0: 1797.3, 1: 1795.1. Samples: 19358990. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-16 04:16:12,351][03835] Avg episode reward: [(0, '6.390'), (1, '6.450')] -[2023-10-16 04:16:12,557][05218] Updated weights for policy 0, policy_version 37882 (0.0008) -[2023-10-16 04:16:13,105][05219] Updated weights for policy 1, policy_version 37730 (0.0009) -[2023-10-16 04:16:13,460][05219] Updated weights for policy 1, policy_version 37740 (0.0010) -[2023-10-16 04:16:13,824][05219] Updated weights for policy 1, policy_version 37750 (0.0008) -[2023-10-16 04:16:14,192][05219] Updated weights for policy 1, policy_version 37760 (0.0007) -[2023-10-16 04:16:16,360][05218] Updated weights for policy 0, policy_version 37892 (0.0010) -[2023-10-16 04:16:16,735][05218] Updated weights for policy 0, policy_version 37902 (0.0008) -[2023-10-16 04:16:17,114][05218] Updated weights for policy 0, policy_version 37912 (0.0008) -[2023-10-16 04:16:17,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 77463552. Throughput: 0: 1810.0, 1: 1795.6. Samples: 19381146. Policy #0 lag: (min: 25.0, avg: 26.9, max: 54.0) -[2023-10-16 04:16:17,351][03835] Avg episode reward: [(0, '6.390'), (1, '6.400')] -[2023-10-16 04:16:17,944][05219] Updated weights for policy 1, policy_version 37770 (0.0008) -[2023-10-16 04:16:18,311][05219] Updated weights for policy 1, policy_version 37780 (0.0009) -[2023-10-16 04:16:18,686][05219] Updated weights for policy 1, policy_version 37790 (0.0007) -[2023-10-16 04:16:20,987][05218] Updated weights for policy 0, policy_version 37922 (0.0007) -[2023-10-16 04:16:21,387][05218] Updated weights for policy 0, policy_version 37932 (0.0009) -[2023-10-16 04:16:21,764][05218] Updated weights for policy 0, policy_version 37942 (0.0007) -[2023-10-16 04:16:22,132][05218] Updated weights for policy 0, policy_version 37952 (0.0011) -[2023-10-16 04:16:22,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 77561856. Throughput: 0: 1790.0, 1: 1805.1. Samples: 19401794. Policy #0 lag: (min: 25.0, avg: 26.9, max: 54.0) -[2023-10-16 04:16:22,351][03835] Avg episode reward: [(0, '6.550'), (1, '6.260')] -[2023-10-16 04:16:22,483][05219] Updated weights for policy 1, policy_version 37800 (0.0009) -[2023-10-16 04:16:22,848][05219] Updated weights for policy 1, policy_version 37810 (0.0011) -[2023-10-16 04:16:23,220][05219] Updated weights for policy 1, policy_version 37820 (0.0008) -[2023-10-16 04:16:25,972][05218] Updated weights for policy 0, policy_version 37962 (0.0008) -[2023-10-16 04:16:26,353][05218] Updated weights for policy 0, policy_version 37972 (0.0007) -[2023-10-16 04:16:26,731][05218] Updated weights for policy 0, policy_version 37982 (0.0007) -[2023-10-16 04:16:26,917][05219] Updated weights for policy 1, policy_version 37830 (0.0008) -[2023-10-16 04:16:27,282][05219] Updated weights for policy 1, policy_version 37840 (0.0007) -[2023-10-16 04:16:27,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 77627392. Throughput: 0: 1798.6, 1: 1794.7. Samples: 19412882. Policy #0 lag: (min: 25.0, avg: 26.9, max: 54.0) -[2023-10-16 04:16:27,351][03835] Avg episode reward: [(0, '6.130'), (1, '6.490')] -[2023-10-16 04:16:27,644][05219] Updated weights for policy 1, policy_version 37850 (0.0007) -[2023-10-16 04:16:30,510][05218] Updated weights for policy 0, policy_version 37992 (0.0010) -[2023-10-16 04:16:30,881][05218] Updated weights for policy 0, policy_version 38002 (0.0009) -[2023-10-16 04:16:31,254][05218] Updated weights for policy 0, policy_version 38012 (0.0008) -[2023-10-16 04:16:31,394][05219] Updated weights for policy 1, policy_version 37860 (0.0009) -[2023-10-16 04:16:31,767][05219] Updated weights for policy 1, policy_version 37870 (0.0012) -[2023-10-16 04:16:32,136][05219] Updated weights for policy 1, policy_version 37880 (0.0011) -[2023-10-16 04:16:32,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 77692928. Throughput: 0: 1782.7, 1: 1802.1. Samples: 19434026. Policy #0 lag: (min: 25.0, avg: 26.9, max: 54.0) -[2023-10-16 04:16:32,351][03835] Avg episode reward: [(0, '6.320'), (1, '6.010')] -[2023-10-16 04:16:34,904][05218] Updated weights for policy 0, policy_version 38022 (0.0010) -[2023-10-16 04:16:35,278][05218] Updated weights for policy 0, policy_version 38032 (0.0010) -[2023-10-16 04:16:35,657][05218] Updated weights for policy 0, policy_version 38042 (0.0009) -[2023-10-16 04:16:35,952][05219] Updated weights for policy 1, policy_version 37890 (0.0010) -[2023-10-16 04:16:36,319][05219] Updated weights for policy 1, policy_version 37900 (0.0008) -[2023-10-16 04:16:36,685][05219] Updated weights for policy 1, policy_version 37910 (0.0008) -[2023-10-16 04:16:37,039][05219] Updated weights for policy 1, policy_version 37920 (0.0008) -[2023-10-16 04:16:37,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 77791232. Throughput: 0: 1782.2, 1: 1797.7. Samples: 19455036. Policy #0 lag: (min: 25.0, avg: 26.9, max: 54.0) -[2023-10-16 04:16:37,351][03835] Avg episode reward: [(0, '6.450'), (1, '6.070')] -[2023-10-16 04:16:39,392][05218] Updated weights for policy 0, policy_version 38052 (0.0007) -[2023-10-16 04:16:39,764][05218] Updated weights for policy 0, policy_version 38062 (0.0007) -[2023-10-16 04:16:40,136][05218] Updated weights for policy 0, policy_version 38072 (0.0007) -[2023-10-16 04:16:40,851][05219] Updated weights for policy 1, policy_version 37930 (0.0010) -[2023-10-16 04:16:41,222][05219] Updated weights for policy 1, policy_version 37940 (0.0010) -[2023-10-16 04:16:41,579][05219] Updated weights for policy 1, policy_version 37950 (0.0008) -[2023-10-16 04:16:42,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 77856768. Throughput: 0: 1787.4, 1: 1801.6. Samples: 19466526. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:16:42,351][03835] Avg episode reward: [(0, '5.860'), (1, '6.380')] -[2023-10-16 04:16:43,880][05218] Updated weights for policy 0, policy_version 38082 (0.0009) -[2023-10-16 04:16:44,262][05218] Updated weights for policy 0, policy_version 38092 (0.0009) -[2023-10-16 04:16:44,629][05218] Updated weights for policy 0, policy_version 38102 (0.0007) -[2023-10-16 04:16:45,014][05218] Updated weights for policy 0, policy_version 38112 (0.0008) -[2023-10-16 04:16:45,431][05219] Updated weights for policy 1, policy_version 37960 (0.0008) -[2023-10-16 04:16:45,794][05219] Updated weights for policy 1, policy_version 37970 (0.0008) -[2023-10-16 04:16:46,160][05219] Updated weights for policy 1, policy_version 37980 (0.0008) -[2023-10-16 04:16:47,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 77922304. Throughput: 0: 1782.7, 1: 1799.1. Samples: 19487452. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:16:47,351][03835] Avg episode reward: [(0, '5.750'), (1, '6.330')] -[2023-10-16 04:16:48,671][05218] Updated weights for policy 0, policy_version 38122 (0.0008) -[2023-10-16 04:16:49,039][05218] Updated weights for policy 0, policy_version 38132 (0.0010) -[2023-10-16 04:16:49,418][05218] Updated weights for policy 0, policy_version 38142 (0.0009) -[2023-10-16 04:16:50,039][05219] Updated weights for policy 1, policy_version 37990 (0.0008) -[2023-10-16 04:16:50,408][05219] Updated weights for policy 1, policy_version 38000 (0.0010) -[2023-10-16 04:16:50,771][05219] Updated weights for policy 1, policy_version 38010 (0.0009) -[2023-10-16 04:16:52,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 77987840. Throughput: 0: 1792.5, 1: 1790.8. Samples: 19509958. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:16:52,351][03835] Avg episode reward: [(0, '6.520'), (1, '5.950')] -[2023-10-16 04:16:53,115][05218] Updated weights for policy 0, policy_version 38152 (0.0008) -[2023-10-16 04:16:53,499][05218] Updated weights for policy 0, policy_version 38162 (0.0009) -[2023-10-16 04:16:53,868][05218] Updated weights for policy 0, policy_version 38172 (0.0009) -[2023-10-16 04:16:54,553][05219] Updated weights for policy 1, policy_version 38020 (0.0010) -[2023-10-16 04:16:54,913][05219] Updated weights for policy 1, policy_version 38030 (0.0008) -[2023-10-16 04:16:55,281][05219] Updated weights for policy 1, policy_version 38040 (0.0009) -[2023-10-16 04:16:57,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 78053376. Throughput: 0: 1786.9, 1: 1798.9. Samples: 19520350. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:16:57,351][03835] Avg episode reward: [(0, '6.580'), (1, '6.250')] -[2023-10-16 04:16:57,557][05218] Updated weights for policy 0, policy_version 38182 (0.0010) -[2023-10-16 04:16:57,932][05218] Updated weights for policy 0, policy_version 38192 (0.0009) -[2023-10-16 04:16:58,311][05218] Updated weights for policy 0, policy_version 38202 (0.0008) -[2023-10-16 04:16:59,139][05219] Updated weights for policy 1, policy_version 38050 (0.0009) -[2023-10-16 04:16:59,513][05219] Updated weights for policy 1, policy_version 38060 (0.0008) -[2023-10-16 04:16:59,878][05219] Updated weights for policy 1, policy_version 38070 (0.0008) -[2023-10-16 04:17:00,238][05219] Updated weights for policy 1, policy_version 38080 (0.0008) -[2023-10-16 04:17:02,017][05218] Updated weights for policy 0, policy_version 38212 (0.0007) -[2023-10-16 04:17:02,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 78118912. Throughput: 0: 1792.0, 1: 1786.9. Samples: 19542200. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:17:02,351][03835] Avg episode reward: [(0, '6.670'), (1, '5.760')] -[2023-10-16 04:17:02,384][05218] Updated weights for policy 0, policy_version 38222 (0.0009) -[2023-10-16 04:17:02,763][05218] Updated weights for policy 0, policy_version 38232 (0.0008) -[2023-10-16 04:17:03,941][05219] Updated weights for policy 1, policy_version 38090 (0.0010) -[2023-10-16 04:17:04,309][05219] Updated weights for policy 1, policy_version 38100 (0.0008) -[2023-10-16 04:17:04,682][05219] Updated weights for policy 1, policy_version 38110 (0.0010) -[2023-10-16 04:17:06,459][05218] Updated weights for policy 0, policy_version 38242 (0.0007) -[2023-10-16 04:17:06,872][05218] Updated weights for policy 0, policy_version 38252 (0.0010) -[2023-10-16 04:17:07,254][05218] Updated weights for policy 0, policy_version 38262 (0.0010) -[2023-10-16 04:17:07,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 78184448. Throughput: 0: 1801.7, 1: 1788.6. Samples: 19563360. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:17:07,351][03835] Avg episode reward: [(0, '6.670'), (1, '6.070')] -[2023-10-16 04:17:07,616][05218] Updated weights for policy 0, policy_version 38272 (0.0008) -[2023-10-16 04:17:08,424][05219] Updated weights for policy 1, policy_version 38120 (0.0009) -[2023-10-16 04:17:08,785][05219] Updated weights for policy 1, policy_version 38130 (0.0010) -[2023-10-16 04:17:09,147][05219] Updated weights for policy 1, policy_version 38140 (0.0008) -[2023-10-16 04:17:11,478][05218] Updated weights for policy 0, policy_version 38282 (0.0010) -[2023-10-16 04:17:11,856][05218] Updated weights for policy 0, policy_version 38292 (0.0008) -[2023-10-16 04:17:12,228][05218] Updated weights for policy 0, policy_version 38302 (0.0009) -[2023-10-16 04:17:12,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 78282752. Throughput: 0: 1798.2, 1: 1786.8. Samples: 19574206. Policy #0 lag: (min: 10.0, avg: 17.8, max: 42.0) -[2023-10-16 04:17:12,352][03835] Avg episode reward: [(0, '6.000'), (1, '6.130')] -[2023-10-16 04:17:13,019][05219] Updated weights for policy 1, policy_version 38150 (0.0009) -[2023-10-16 04:17:13,383][05219] Updated weights for policy 1, policy_version 38160 (0.0010) -[2023-10-16 04:17:13,751][05219] Updated weights for policy 1, policy_version 38170 (0.0011) -[2023-10-16 04:17:16,150][05218] Updated weights for policy 0, policy_version 38312 (0.0009) -[2023-10-16 04:17:16,530][05218] Updated weights for policy 0, policy_version 38322 (0.0008) -[2023-10-16 04:17:16,896][05218] Updated weights for policy 0, policy_version 38332 (0.0009) -[2023-10-16 04:17:17,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 78348288. Throughput: 0: 1813.4, 1: 1781.6. Samples: 19595800. Policy #0 lag: (min: 10.0, avg: 17.8, max: 42.0) -[2023-10-16 04:17:17,351][03835] Avg episode reward: [(0, '6.240'), (1, '5.980')] -[2023-10-16 04:17:17,426][05219] Updated weights for policy 1, policy_version 38180 (0.0008) -[2023-10-16 04:17:17,781][05219] Updated weights for policy 1, policy_version 38190 (0.0011) -[2023-10-16 04:17:18,138][05219] Updated weights for policy 1, policy_version 38200 (0.0010) -[2023-10-16 04:17:20,562][05218] Updated weights for policy 0, policy_version 38342 (0.0010) -[2023-10-16 04:17:20,931][05218] Updated weights for policy 0, policy_version 38352 (0.0008) -[2023-10-16 04:17:21,319][05218] Updated weights for policy 0, policy_version 38362 (0.0007) -[2023-10-16 04:17:21,946][05219] Updated weights for policy 1, policy_version 38210 (0.0009) -[2023-10-16 04:17:22,305][05219] Updated weights for policy 1, policy_version 38220 (0.0010) -[2023-10-16 04:17:22,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 78413824. Throughput: 0: 1795.7, 1: 1806.5. Samples: 19617136. Policy #0 lag: (min: 10.0, avg: 17.8, max: 42.0) -[2023-10-16 04:17:22,352][03835] Avg episode reward: [(0, '6.060'), (1, '6.190')] -[2023-10-16 04:17:22,676][05219] Updated weights for policy 1, policy_version 38230 (0.0007) -[2023-10-16 04:17:23,036][05219] Updated weights for policy 1, policy_version 38240 (0.0007) -[2023-10-16 04:17:24,891][05218] Updated weights for policy 0, policy_version 38372 (0.0010) -[2023-10-16 04:17:25,266][05218] Updated weights for policy 0, policy_version 38382 (0.0008) -[2023-10-16 04:17:25,643][05218] Updated weights for policy 0, policy_version 38392 (0.0008) -[2023-10-16 04:17:26,756][05219] Updated weights for policy 1, policy_version 38250 (0.0008) -[2023-10-16 04:17:27,124][05219] Updated weights for policy 1, policy_version 38260 (0.0007) -[2023-10-16 04:17:27,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 78479360. Throughput: 0: 1809.2, 1: 1782.8. Samples: 19628168. Policy #0 lag: (min: 10.0, avg: 17.8, max: 42.0) -[2023-10-16 04:17:27,351][03835] Avg episode reward: [(0, '7.100'), (1, '6.420')] -[2023-10-16 04:17:27,352][04766] Saving new best policy, reward=7.100! -[2023-10-16 04:17:27,488][05219] Updated weights for policy 1, policy_version 38270 (0.0009) -[2023-10-16 04:17:29,426][05218] Updated weights for policy 0, policy_version 38402 (0.0008) -[2023-10-16 04:17:29,799][05218] Updated weights for policy 0, policy_version 38412 (0.0007) -[2023-10-16 04:17:30,177][05218] Updated weights for policy 0, policy_version 38422 (0.0007) -[2023-10-16 04:17:30,549][05218] Updated weights for policy 0, policy_version 38432 (0.0007) -[2023-10-16 04:17:31,024][05219] Updated weights for policy 1, policy_version 38280 (0.0007) -[2023-10-16 04:17:31,387][05219] Updated weights for policy 1, policy_version 38290 (0.0007) -[2023-10-16 04:17:31,760][05219] Updated weights for policy 1, policy_version 38300 (0.0009) -[2023-10-16 04:17:32,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14745.6, 300 sec: 14440.2). Total num frames: 78577664. Throughput: 0: 1800.4, 1: 1803.7. Samples: 19649638. Policy #0 lag: (min: 10.0, avg: 17.8, max: 42.0) -[2023-10-16 04:17:32,351][03835] Avg episode reward: [(0, '6.480'), (1, '6.370')] -[2023-10-16 04:17:34,344][05218] Updated weights for policy 0, policy_version 38442 (0.0007) -[2023-10-16 04:17:34,723][05218] Updated weights for policy 0, policy_version 38452 (0.0008) -[2023-10-16 04:17:35,102][05218] Updated weights for policy 0, policy_version 38462 (0.0008) -[2023-10-16 04:17:35,560][05219] Updated weights for policy 1, policy_version 38310 (0.0009) -[2023-10-16 04:17:35,924][05219] Updated weights for policy 1, policy_version 38320 (0.0007) -[2023-10-16 04:17:36,301][05219] Updated weights for policy 1, policy_version 38330 (0.0009) -[2023-10-16 04:17:37,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 78643200. Throughput: 0: 1790.4, 1: 1784.9. Samples: 19670844. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-16 04:17:37,351][03835] Avg episode reward: [(0, '6.550'), (1, '6.240')] -[2023-10-16 04:17:37,361][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000038336_39256064.pth... -[2023-10-16 04:17:37,362][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000038464_39387136.pth... -[2023-10-16 04:17:37,398][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000036800_37683200.pth -[2023-10-16 04:17:37,400][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000036672_37552128.pth -[2023-10-16 04:17:38,668][05218] Updated weights for policy 0, policy_version 38472 (0.0007) -[2023-10-16 04:17:39,035][05218] Updated weights for policy 0, policy_version 38482 (0.0007) -[2023-10-16 04:17:39,412][05218] Updated weights for policy 0, policy_version 38492 (0.0007) -[2023-10-16 04:17:39,950][05219] Updated weights for policy 1, policy_version 38340 (0.0009) -[2023-10-16 04:17:40,317][05219] Updated weights for policy 1, policy_version 38350 (0.0007) -[2023-10-16 04:17:40,682][05219] Updated weights for policy 1, policy_version 38360 (0.0008) -[2023-10-16 04:17:42,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 78708736. Throughput: 0: 1789.2, 1: 1796.8. Samples: 19681720. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-16 04:17:42,351][03835] Avg episode reward: [(0, '6.440'), (1, '5.770')] -[2023-10-16 04:17:43,219][05218] Updated weights for policy 0, policy_version 38502 (0.0010) -[2023-10-16 04:17:43,605][05218] Updated weights for policy 0, policy_version 38512 (0.0010) -[2023-10-16 04:17:43,978][05218] Updated weights for policy 0, policy_version 38522 (0.0011) -[2023-10-16 04:17:44,357][05219] Updated weights for policy 1, policy_version 38370 (0.0008) -[2023-10-16 04:17:44,718][05219] Updated weights for policy 1, policy_version 38380 (0.0009) -[2023-10-16 04:17:45,080][05219] Updated weights for policy 1, policy_version 38390 (0.0007) -[2023-10-16 04:17:45,447][05219] Updated weights for policy 1, policy_version 38400 (0.0009) -[2023-10-16 04:17:47,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 78774272. Throughput: 0: 1784.8, 1: 1786.3. Samples: 19702898. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-16 04:17:47,351][03835] Avg episode reward: [(0, '6.190'), (1, '5.080')] -[2023-10-16 04:17:47,713][05218] Updated weights for policy 0, policy_version 38532 (0.0007) -[2023-10-16 04:17:48,095][05218] Updated weights for policy 0, policy_version 38542 (0.0007) -[2023-10-16 04:17:48,466][05218] Updated weights for policy 0, policy_version 38552 (0.0008) -[2023-10-16 04:17:49,269][05219] Updated weights for policy 1, policy_version 38410 (0.0008) -[2023-10-16 04:17:49,631][05219] Updated weights for policy 1, policy_version 38420 (0.0010) -[2023-10-16 04:17:49,997][05219] Updated weights for policy 1, policy_version 38430 (0.0011) -[2023-10-16 04:17:52,218][05218] Updated weights for policy 0, policy_version 38562 (0.0008) -[2023-10-16 04:17:52,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 78839808. Throughput: 0: 1805.3, 1: 1781.7. Samples: 19724776. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-16 04:17:52,351][03835] Avg episode reward: [(0, '6.140'), (1, '5.570')] -[2023-10-16 04:17:52,609][05218] Updated weights for policy 0, policy_version 38572 (0.0009) -[2023-10-16 04:17:52,987][05218] Updated weights for policy 0, policy_version 38582 (0.0008) -[2023-10-16 04:17:53,355][05218] Updated weights for policy 0, policy_version 38592 (0.0008) -[2023-10-16 04:17:53,871][05219] Updated weights for policy 1, policy_version 38440 (0.0009) -[2023-10-16 04:17:54,239][05219] Updated weights for policy 1, policy_version 38450 (0.0010) -[2023-10-16 04:17:54,611][05219] Updated weights for policy 1, policy_version 38460 (0.0008) -[2023-10-16 04:17:57,149][05218] Updated weights for policy 0, policy_version 38602 (0.0008) -[2023-10-16 04:17:57,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 78905344. Throughput: 0: 1783.2, 1: 1786.9. Samples: 19734864. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-16 04:17:57,351][03835] Avg episode reward: [(0, '6.690'), (1, '6.070')] -[2023-10-16 04:17:57,514][05218] Updated weights for policy 0, policy_version 38612 (0.0010) -[2023-10-16 04:17:57,895][05218] Updated weights for policy 0, policy_version 38622 (0.0009) -[2023-10-16 04:17:58,353][05219] Updated weights for policy 1, policy_version 38470 (0.0008) -[2023-10-16 04:17:58,726][05219] Updated weights for policy 1, policy_version 38480 (0.0009) -[2023-10-16 04:17:59,091][05219] Updated weights for policy 1, policy_version 38490 (0.0008) -[2023-10-16 04:18:01,545][05218] Updated weights for policy 0, policy_version 38632 (0.0010) -[2023-10-16 04:18:01,922][05218] Updated weights for policy 0, policy_version 38642 (0.0008) -[2023-10-16 04:18:02,296][05218] Updated weights for policy 0, policy_version 38652 (0.0010) -[2023-10-16 04:18:02,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 78970880. Throughput: 0: 1797.3, 1: 1793.6. Samples: 19757390. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-16 04:18:02,351][03835] Avg episode reward: [(0, '6.920'), (1, '6.480')] -[2023-10-16 04:18:02,946][05219] Updated weights for policy 1, policy_version 38500 (0.0008) -[2023-10-16 04:18:03,310][05219] Updated weights for policy 1, policy_version 38510 (0.0008) -[2023-10-16 04:18:03,679][05219] Updated weights for policy 1, policy_version 38520 (0.0010) -[2023-10-16 04:18:06,072][05218] Updated weights for policy 0, policy_version 38662 (0.0010) -[2023-10-16 04:18:06,447][05218] Updated weights for policy 0, policy_version 38672 (0.0009) -[2023-10-16 04:18:06,838][05218] Updated weights for policy 0, policy_version 38682 (0.0008) -[2023-10-16 04:18:07,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 79069184. Throughput: 0: 1782.7, 1: 1806.9. Samples: 19778666. Policy #0 lag: (min: 1.0, avg: 9.0, max: 33.0) -[2023-10-16 04:18:07,351][03835] Avg episode reward: [(0, '6.650'), (1, '6.880')] -[2023-10-16 04:18:07,401][05219] Updated weights for policy 1, policy_version 38530 (0.0010) -[2023-10-16 04:18:07,759][05219] Updated weights for policy 1, policy_version 38540 (0.0009) -[2023-10-16 04:18:08,122][05219] Updated weights for policy 1, policy_version 38550 (0.0010) -[2023-10-16 04:18:08,497][05219] Updated weights for policy 1, policy_version 38560 (0.0009) -[2023-10-16 04:18:10,697][05218] Updated weights for policy 0, policy_version 38692 (0.0009) -[2023-10-16 04:18:11,066][05218] Updated weights for policy 0, policy_version 38702 (0.0008) -[2023-10-16 04:18:11,437][05218] Updated weights for policy 0, policy_version 38712 (0.0008) -[2023-10-16 04:18:12,200][05219] Updated weights for policy 1, policy_version 38570 (0.0009) -[2023-10-16 04:18:12,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 79134720. Throughput: 0: 1792.4, 1: 1800.3. Samples: 19789838. Policy #0 lag: (min: 1.0, avg: 9.0, max: 33.0) -[2023-10-16 04:18:12,351][03835] Avg episode reward: [(0, '6.470'), (1, '6.070')] -[2023-10-16 04:18:12,565][05219] Updated weights for policy 1, policy_version 38580 (0.0007) -[2023-10-16 04:18:12,937][05219] Updated weights for policy 1, policy_version 38590 (0.0008) -[2023-10-16 04:18:15,163][05218] Updated weights for policy 0, policy_version 38722 (0.0007) -[2023-10-16 04:18:15,532][05218] Updated weights for policy 0, policy_version 38732 (0.0009) -[2023-10-16 04:18:15,914][05218] Updated weights for policy 0, policy_version 38742 (0.0009) -[2023-10-16 04:18:16,275][05218] Updated weights for policy 0, policy_version 38752 (0.0009) -[2023-10-16 04:18:16,682][05219] Updated weights for policy 1, policy_version 38600 (0.0009) -[2023-10-16 04:18:17,051][05219] Updated weights for policy 1, policy_version 38610 (0.0007) -[2023-10-16 04:18:17,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 79200256. Throughput: 0: 1775.2, 1: 1804.4. Samples: 19810722. Policy #0 lag: (min: 1.0, avg: 9.0, max: 33.0) -[2023-10-16 04:18:17,351][03835] Avg episode reward: [(0, '6.150'), (1, '6.470')] -[2023-10-16 04:18:17,410][05219] Updated weights for policy 1, policy_version 38620 (0.0008) -[2023-10-16 04:18:19,983][05218] Updated weights for policy 0, policy_version 38762 (0.0011) -[2023-10-16 04:18:20,365][05218] Updated weights for policy 0, policy_version 38772 (0.0009) -[2023-10-16 04:18:20,739][05218] Updated weights for policy 0, policy_version 38782 (0.0007) -[2023-10-16 04:18:21,271][05219] Updated weights for policy 1, policy_version 38630 (0.0009) -[2023-10-16 04:18:21,624][05219] Updated weights for policy 1, policy_version 38640 (0.0007) -[2023-10-16 04:18:21,996][05219] Updated weights for policy 1, policy_version 38650 (0.0007) -[2023-10-16 04:18:22,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 79298560. Throughput: 0: 1782.4, 1: 1794.0. Samples: 19831782. Policy #0 lag: (min: 1.0, avg: 9.0, max: 33.0) -[2023-10-16 04:18:22,351][03835] Avg episode reward: [(0, '6.480'), (1, '6.250')] -[2023-10-16 04:18:24,461][05218] Updated weights for policy 0, policy_version 38792 (0.0008) -[2023-10-16 04:18:24,833][05218] Updated weights for policy 0, policy_version 38802 (0.0008) -[2023-10-16 04:18:25,215][05218] Updated weights for policy 0, policy_version 38812 (0.0007) -[2023-10-16 04:18:25,740][05219] Updated weights for policy 1, policy_version 38660 (0.0010) -[2023-10-16 04:18:26,107][05219] Updated weights for policy 1, policy_version 38670 (0.0010) -[2023-10-16 04:18:26,464][05219] Updated weights for policy 1, policy_version 38680 (0.0008) -[2023-10-16 04:18:27,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 79364096. Throughput: 0: 1784.4, 1: 1796.8. Samples: 19842872. Policy #0 lag: (min: 1.0, avg: 9.0, max: 33.0) -[2023-10-16 04:18:27,351][03835] Avg episode reward: [(0, '5.890'), (1, '6.250')] -[2023-10-16 04:18:28,863][05218] Updated weights for policy 0, policy_version 38822 (0.0007) -[2023-10-16 04:18:29,236][05218] Updated weights for policy 0, policy_version 38832 (0.0010) -[2023-10-16 04:18:29,610][05218] Updated weights for policy 0, policy_version 38842 (0.0010) -[2023-10-16 04:18:30,157][05219] Updated weights for policy 1, policy_version 38690 (0.0009) -[2023-10-16 04:18:30,521][05219] Updated weights for policy 1, policy_version 38700 (0.0010) -[2023-10-16 04:18:30,883][05219] Updated weights for policy 1, policy_version 38710 (0.0009) -[2023-10-16 04:18:31,245][05219] Updated weights for policy 1, policy_version 38720 (0.0007) -[2023-10-16 04:18:32,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 79429632. Throughput: 0: 1792.6, 1: 1794.7. Samples: 19864326. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-16 04:18:32,351][03835] Avg episode reward: [(0, '6.070'), (1, '6.200')] -[2023-10-16 04:18:33,346][05218] Updated weights for policy 0, policy_version 38852 (0.0008) -[2023-10-16 04:18:33,727][05218] Updated weights for policy 0, policy_version 38862 (0.0009) -[2023-10-16 04:18:34,100][05218] Updated weights for policy 0, policy_version 38872 (0.0009) -[2023-10-16 04:18:35,199][05219] Updated weights for policy 1, policy_version 38730 (0.0010) -[2023-10-16 04:18:35,562][05219] Updated weights for policy 1, policy_version 38740 (0.0010) -[2023-10-16 04:18:35,928][05219] Updated weights for policy 1, policy_version 38750 (0.0009) -[2023-10-16 04:18:37,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 79495168. Throughput: 0: 1805.3, 1: 1790.1. Samples: 19886570. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-16 04:18:37,351][03835] Avg episode reward: [(0, '6.160'), (1, '6.510')] -[2023-10-16 04:18:37,810][05218] Updated weights for policy 0, policy_version 38882 (0.0009) -[2023-10-16 04:18:38,199][05218] Updated weights for policy 0, policy_version 38892 (0.0009) -[2023-10-16 04:18:38,570][05218] Updated weights for policy 0, policy_version 38902 (0.0008) -[2023-10-16 04:18:38,943][05218] Updated weights for policy 0, policy_version 38912 (0.0009) -[2023-10-16 04:18:39,629][05219] Updated weights for policy 1, policy_version 38760 (0.0010) -[2023-10-16 04:18:39,994][05219] Updated weights for policy 1, policy_version 38770 (0.0008) -[2023-10-16 04:18:40,360][05219] Updated weights for policy 1, policy_version 38780 (0.0007) -[2023-10-16 04:18:42,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 79560704. Throughput: 0: 1802.0, 1: 1801.8. Samples: 19897038. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-16 04:18:42,351][03835] Avg episode reward: [(0, '6.020'), (1, '6.190')] -[2023-10-16 04:18:42,698][05218] Updated weights for policy 0, policy_version 38922 (0.0007) -[2023-10-16 04:18:43,064][05218] Updated weights for policy 0, policy_version 38932 (0.0009) -[2023-10-16 04:18:43,440][05218] Updated weights for policy 0, policy_version 38942 (0.0008) -[2023-10-16 04:18:44,171][05219] Updated weights for policy 1, policy_version 38790 (0.0010) -[2023-10-16 04:18:44,533][05219] Updated weights for policy 1, policy_version 38800 (0.0009) -[2023-10-16 04:18:44,897][05219] Updated weights for policy 1, policy_version 38810 (0.0008) -[2023-10-16 04:18:47,316][05218] Updated weights for policy 0, policy_version 38952 (0.0008) -[2023-10-16 04:18:47,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 79626240. Throughput: 0: 1801.0, 1: 1783.2. Samples: 19918678. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-16 04:18:47,351][03835] Avg episode reward: [(0, '6.610'), (1, '6.060')] -[2023-10-16 04:18:47,682][05218] Updated weights for policy 0, policy_version 38962 (0.0007) -[2023-10-16 04:18:48,049][05218] Updated weights for policy 0, policy_version 38972 (0.0008) -[2023-10-16 04:18:48,641][05219] Updated weights for policy 1, policy_version 38820 (0.0010) -[2023-10-16 04:18:49,005][05219] Updated weights for policy 1, policy_version 38830 (0.0008) -[2023-10-16 04:18:49,372][05219] Updated weights for policy 1, policy_version 38840 (0.0007) -[2023-10-16 04:18:51,903][05218] Updated weights for policy 0, policy_version 38982 (0.0009) -[2023-10-16 04:18:52,284][05218] Updated weights for policy 0, policy_version 38992 (0.0009) -[2023-10-16 04:18:52,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 79691776. Throughput: 0: 1814.9, 1: 1777.4. Samples: 19940320. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-16 04:18:52,351][03835] Avg episode reward: [(0, '6.600'), (1, '5.920')] -[2023-10-16 04:18:52,658][05218] Updated weights for policy 0, policy_version 39002 (0.0008) -[2023-10-16 04:18:53,128][05219] Updated weights for policy 1, policy_version 38850 (0.0008) -[2023-10-16 04:18:53,497][05219] Updated weights for policy 1, policy_version 38860 (0.0008) -[2023-10-16 04:18:53,859][05219] Updated weights for policy 1, policy_version 38870 (0.0008) -[2023-10-16 04:18:54,223][05219] Updated weights for policy 1, policy_version 38880 (0.0007) -[2023-10-16 04:18:56,363][05218] Updated weights for policy 0, policy_version 39012 (0.0008) -[2023-10-16 04:18:56,739][05218] Updated weights for policy 0, policy_version 39022 (0.0010) -[2023-10-16 04:18:57,117][05218] Updated weights for policy 0, policy_version 39032 (0.0011) -[2023-10-16 04:18:57,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 79757312. Throughput: 0: 1802.8, 1: 1775.3. Samples: 19950850. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-16 04:18:57,351][03835] Avg episode reward: [(0, '6.850'), (1, '6.170')] -[2023-10-16 04:18:58,006][05219] Updated weights for policy 1, policy_version 38890 (0.0008) -[2023-10-16 04:18:58,377][05219] Updated weights for policy 1, policy_version 38900 (0.0009) -[2023-10-16 04:18:58,728][05219] Updated weights for policy 1, policy_version 38910 (0.0011) -[2023-10-16 04:19:00,725][05218] Updated weights for policy 0, policy_version 39042 (0.0009) -[2023-10-16 04:19:01,099][05218] Updated weights for policy 0, policy_version 39052 (0.0010) -[2023-10-16 04:19:01,477][05218] Updated weights for policy 0, policy_version 39062 (0.0009) -[2023-10-16 04:19:01,843][05218] Updated weights for policy 0, policy_version 39072 (0.0008) -[2023-10-16 04:19:02,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 79855616. Throughput: 0: 1817.8, 1: 1771.7. Samples: 19972248. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-16 04:19:02,351][03835] Avg episode reward: [(0, '6.360'), (1, '6.330')] -[2023-10-16 04:19:02,598][05219] Updated weights for policy 1, policy_version 38920 (0.0009) -[2023-10-16 04:19:02,965][05219] Updated weights for policy 1, policy_version 38930 (0.0007) -[2023-10-16 04:19:03,318][05219] Updated weights for policy 1, policy_version 38940 (0.0007) -[2023-10-16 04:19:05,633][05218] Updated weights for policy 0, policy_version 39082 (0.0009) -[2023-10-16 04:19:06,011][05218] Updated weights for policy 0, policy_version 39092 (0.0009) -[2023-10-16 04:19:06,386][05218] Updated weights for policy 0, policy_version 39102 (0.0011) -[2023-10-16 04:19:07,247][05219] Updated weights for policy 1, policy_version 38950 (0.0009) -[2023-10-16 04:19:07,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 79921152. Throughput: 0: 1797.7, 1: 1802.0. Samples: 19993768. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-16 04:19:07,351][03835] Avg episode reward: [(0, '6.070'), (1, '6.260')] -[2023-10-16 04:19:07,609][05219] Updated weights for policy 1, policy_version 38960 (0.0008) -[2023-10-16 04:19:07,979][05219] Updated weights for policy 1, policy_version 38970 (0.0008) -[2023-10-16 04:19:10,153][05218] Updated weights for policy 0, policy_version 39112 (0.0009) -[2023-10-16 04:19:10,539][05218] Updated weights for policy 0, policy_version 39122 (0.0009) -[2023-10-16 04:19:10,910][05218] Updated weights for policy 0, policy_version 39132 (0.0011) -[2023-10-16 04:19:11,818][05219] Updated weights for policy 1, policy_version 38980 (0.0009) -[2023-10-16 04:19:12,177][05219] Updated weights for policy 1, policy_version 38990 (0.0008) -[2023-10-16 04:19:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 79986688. Throughput: 0: 1819.4, 1: 1776.4. Samples: 20004684. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-16 04:19:12,351][03835] Avg episode reward: [(0, '6.620'), (1, '5.940')] -[2023-10-16 04:19:12,540][05219] Updated weights for policy 1, policy_version 39000 (0.0008) -[2023-10-16 04:19:14,576][05218] Updated weights for policy 0, policy_version 39142 (0.0008) -[2023-10-16 04:19:14,941][05218] Updated weights for policy 0, policy_version 39152 (0.0008) -[2023-10-16 04:19:15,317][05218] Updated weights for policy 0, policy_version 39162 (0.0009) -[2023-10-16 04:19:16,098][05219] Updated weights for policy 1, policy_version 39010 (0.0009) -[2023-10-16 04:19:16,465][05219] Updated weights for policy 1, policy_version 39020 (0.0008) -[2023-10-16 04:19:16,831][05219] Updated weights for policy 1, policy_version 39030 (0.0007) -[2023-10-16 04:19:17,198][05219] Updated weights for policy 1, policy_version 39040 (0.0007) -[2023-10-16 04:19:17,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 80084992. Throughput: 0: 1790.0, 1: 1805.9. Samples: 20026142. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-16 04:19:17,351][03835] Avg episode reward: [(0, '6.160'), (1, '5.590')] -[2023-10-16 04:19:19,039][05218] Updated weights for policy 0, policy_version 39172 (0.0007) -[2023-10-16 04:19:19,416][05218] Updated weights for policy 0, policy_version 39182 (0.0007) -[2023-10-16 04:19:19,800][05218] Updated weights for policy 0, policy_version 39192 (0.0008) -[2023-10-16 04:19:20,911][05219] Updated weights for policy 1, policy_version 39050 (0.0009) -[2023-10-16 04:19:21,279][05219] Updated weights for policy 1, policy_version 39060 (0.0009) -[2023-10-16 04:19:21,648][05219] Updated weights for policy 1, policy_version 39070 (0.0008) -[2023-10-16 04:19:22,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 80150528. Throughput: 0: 1787.9, 1: 1783.7. Samples: 20047288. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-16 04:19:22,351][03835] Avg episode reward: [(0, '5.980'), (1, '5.870')] -[2023-10-16 04:19:23,467][05218] Updated weights for policy 0, policy_version 39202 (0.0008) -[2023-10-16 04:19:23,862][05218] Updated weights for policy 0, policy_version 39212 (0.0008) -[2023-10-16 04:19:24,231][05218] Updated weights for policy 0, policy_version 39222 (0.0007) -[2023-10-16 04:19:24,603][05218] Updated weights for policy 0, policy_version 39232 (0.0008) -[2023-10-16 04:19:25,471][05219] Updated weights for policy 1, policy_version 39080 (0.0007) -[2023-10-16 04:19:25,831][05219] Updated weights for policy 1, policy_version 39090 (0.0008) -[2023-10-16 04:19:26,189][05219] Updated weights for policy 1, policy_version 39100 (0.0009) -[2023-10-16 04:19:27,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 80216064. Throughput: 0: 1788.6, 1: 1798.4. Samples: 20058454. Policy #0 lag: (min: 23.0, avg: 24.9, max: 53.0) -[2023-10-16 04:19:27,351][03835] Avg episode reward: [(0, '6.780'), (1, '6.490')] -[2023-10-16 04:19:28,198][05218] Updated weights for policy 0, policy_version 39242 (0.0010) -[2023-10-16 04:19:28,575][05218] Updated weights for policy 0, policy_version 39252 (0.0010) -[2023-10-16 04:19:28,955][05218] Updated weights for policy 0, policy_version 39262 (0.0007) -[2023-10-16 04:19:30,019][05219] Updated weights for policy 1, policy_version 39110 (0.0007) -[2023-10-16 04:19:30,386][05219] Updated weights for policy 1, policy_version 39120 (0.0007) -[2023-10-16 04:19:30,749][05219] Updated weights for policy 1, policy_version 39130 (0.0010) -[2023-10-16 04:19:32,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 80281600. Throughput: 0: 1795.5, 1: 1777.0. Samples: 20079440. Policy #0 lag: (min: 23.0, avg: 24.9, max: 53.0) -[2023-10-16 04:19:32,351][03835] Avg episode reward: [(0, '6.370'), (1, '5.960')] -[2023-10-16 04:19:32,634][05218] Updated weights for policy 0, policy_version 39272 (0.0010) -[2023-10-16 04:19:33,015][05218] Updated weights for policy 0, policy_version 39282 (0.0009) -[2023-10-16 04:19:33,383][05218] Updated weights for policy 0, policy_version 39292 (0.0009) -[2023-10-16 04:19:34,686][05219] Updated weights for policy 1, policy_version 39140 (0.0009) -[2023-10-16 04:19:35,044][05219] Updated weights for policy 1, policy_version 39150 (0.0008) -[2023-10-16 04:19:35,410][05219] Updated weights for policy 1, policy_version 39160 (0.0008) -[2023-10-16 04:19:37,260][05218] Updated weights for policy 0, policy_version 39302 (0.0010) -[2023-10-16 04:19:37,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 80347136. Throughput: 0: 1806.2, 1: 1768.4. Samples: 20101176. Policy #0 lag: (min: 23.0, avg: 24.9, max: 53.0) -[2023-10-16 04:19:37,351][03835] Avg episode reward: [(0, '5.890'), (1, '6.270')] -[2023-10-16 04:19:37,361][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000039168_40108032.pth... -[2023-10-16 04:19:37,396][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000037504_38404096.pth -[2023-10-16 04:19:37,634][05218] Updated weights for policy 0, policy_version 39312 (0.0008) -[2023-10-16 04:19:38,012][05218] Updated weights for policy 0, policy_version 39322 (0.0008) -[2023-10-16 04:19:38,238][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000039328_40271872.pth... -[2023-10-16 04:19:38,276][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000037632_38535168.pth -[2023-10-16 04:19:39,274][05219] Updated weights for policy 1, policy_version 39170 (0.0008) -[2023-10-16 04:19:39,639][05219] Updated weights for policy 1, policy_version 39180 (0.0007) -[2023-10-16 04:19:40,004][05219] Updated weights for policy 1, policy_version 39190 (0.0007) -[2023-10-16 04:19:40,366][05219] Updated weights for policy 1, policy_version 39200 (0.0008) -[2023-10-16 04:19:41,821][05218] Updated weights for policy 0, policy_version 39332 (0.0009) -[2023-10-16 04:19:42,208][05218] Updated weights for policy 0, policy_version 39342 (0.0009) -[2023-10-16 04:19:42,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 80412672. Throughput: 0: 1796.3, 1: 1775.4. Samples: 20111576. Policy #0 lag: (min: 23.0, avg: 24.9, max: 53.0) -[2023-10-16 04:19:42,351][03835] Avg episode reward: [(0, '6.480'), (1, '6.430')] -[2023-10-16 04:19:42,575][05218] Updated weights for policy 0, policy_version 39352 (0.0007) -[2023-10-16 04:19:44,254][05219] Updated weights for policy 1, policy_version 39210 (0.0009) -[2023-10-16 04:19:44,627][05219] Updated weights for policy 1, policy_version 39220 (0.0011) -[2023-10-16 04:19:44,997][05219] Updated weights for policy 1, policy_version 39230 (0.0010) -[2023-10-16 04:19:46,215][05218] Updated weights for policy 0, policy_version 39362 (0.0008) -[2023-10-16 04:19:46,590][05218] Updated weights for policy 0, policy_version 39372 (0.0010) -[2023-10-16 04:19:46,966][05218] Updated weights for policy 0, policy_version 39382 (0.0011) -[2023-10-16 04:19:47,342][05218] Updated weights for policy 0, policy_version 39392 (0.0009) -[2023-10-16 04:19:47,351][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 80510976. Throughput: 0: 1813.5, 1: 1770.3. Samples: 20133522. Policy #0 lag: (min: 23.0, avg: 24.9, max: 53.0) -[2023-10-16 04:19:47,351][03835] Avg episode reward: [(0, '5.830'), (1, '6.370')] -[2023-10-16 04:19:48,959][05219] Updated weights for policy 1, policy_version 39240 (0.0008) -[2023-10-16 04:19:49,323][05219] Updated weights for policy 1, policy_version 39250 (0.0008) -[2023-10-16 04:19:49,697][05219] Updated weights for policy 1, policy_version 39260 (0.0008) -[2023-10-16 04:19:51,035][05218] Updated weights for policy 0, policy_version 39402 (0.0009) -[2023-10-16 04:19:51,409][05218] Updated weights for policy 0, policy_version 39412 (0.0009) -[2023-10-16 04:19:51,792][05218] Updated weights for policy 0, policy_version 39422 (0.0007) -[2023-10-16 04:19:52,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 80576512. Throughput: 0: 1799.4, 1: 1769.7. Samples: 20154376. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) -[2023-10-16 04:19:52,352][03835] Avg episode reward: [(0, '6.210'), (1, '6.110')] -[2023-10-16 04:19:53,359][05219] Updated weights for policy 1, policy_version 39270 (0.0009) -[2023-10-16 04:19:53,728][05219] Updated weights for policy 1, policy_version 39280 (0.0008) -[2023-10-16 04:19:54,090][05219] Updated weights for policy 1, policy_version 39290 (0.0008) -[2023-10-16 04:19:55,529][05218] Updated weights for policy 0, policy_version 39432 (0.0008) -[2023-10-16 04:19:55,906][05218] Updated weights for policy 0, policy_version 39442 (0.0008) -[2023-10-16 04:19:56,273][05218] Updated weights for policy 0, policy_version 39452 (0.0011) -[2023-10-16 04:19:57,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 80642048. Throughput: 0: 1807.2, 1: 1767.1. Samples: 20165528. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) -[2023-10-16 04:19:57,351][03835] Avg episode reward: [(0, '6.400'), (1, '6.440')] -[2023-10-16 04:19:57,695][05219] Updated weights for policy 1, policy_version 39300 (0.0009) -[2023-10-16 04:19:58,054][05219] Updated weights for policy 1, policy_version 39310 (0.0008) -[2023-10-16 04:19:58,420][05219] Updated weights for policy 1, policy_version 39320 (0.0009) -[2023-10-16 04:20:00,006][05218] Updated weights for policy 0, policy_version 39462 (0.0010) -[2023-10-16 04:20:00,389][05218] Updated weights for policy 0, policy_version 39472 (0.0009) -[2023-10-16 04:20:00,776][05218] Updated weights for policy 0, policy_version 39482 (0.0008) -[2023-10-16 04:20:02,095][05219] Updated weights for policy 1, policy_version 39330 (0.0010) -[2023-10-16 04:20:02,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 80707584. Throughput: 0: 1797.1, 1: 1770.4. Samples: 20186678. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) -[2023-10-16 04:20:02,351][03835] Avg episode reward: [(0, '6.350'), (1, '6.830')] -[2023-10-16 04:20:02,453][05219] Updated weights for policy 1, policy_version 39340 (0.0007) -[2023-10-16 04:20:02,810][05219] Updated weights for policy 1, policy_version 39350 (0.0010) -[2023-10-16 04:20:03,181][05219] Updated weights for policy 1, policy_version 39360 (0.0008) -[2023-10-16 04:20:04,513][05218] Updated weights for policy 0, policy_version 39492 (0.0009) -[2023-10-16 04:20:04,884][05218] Updated weights for policy 0, policy_version 39502 (0.0009) -[2023-10-16 04:20:05,271][05218] Updated weights for policy 0, policy_version 39512 (0.0007) -[2023-10-16 04:20:07,123][05219] Updated weights for policy 1, policy_version 39370 (0.0007) -[2023-10-16 04:20:07,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 80773120. Throughput: 0: 1796.4, 1: 1793.3. Samples: 20208822. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) -[2023-10-16 04:20:07,351][03835] Avg episode reward: [(0, '5.480'), (1, '5.830')] -[2023-10-16 04:20:07,488][05219] Updated weights for policy 1, policy_version 39380 (0.0007) -[2023-10-16 04:20:07,857][05219] Updated weights for policy 1, policy_version 39390 (0.0008) -[2023-10-16 04:20:08,979][05218] Updated weights for policy 0, policy_version 39522 (0.0008) -[2023-10-16 04:20:09,377][05218] Updated weights for policy 0, policy_version 39532 (0.0008) -[2023-10-16 04:20:09,754][05218] Updated weights for policy 0, policy_version 39542 (0.0010) -[2023-10-16 04:20:10,132][05218] Updated weights for policy 0, policy_version 39552 (0.0009) -[2023-10-16 04:20:11,847][05219] Updated weights for policy 1, policy_version 39400 (0.0011) -[2023-10-16 04:20:12,212][05219] Updated weights for policy 1, policy_version 39410 (0.0009) -[2023-10-16 04:20:12,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 80838656. Throughput: 0: 1792.2, 1: 1773.4. Samples: 20218906. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) -[2023-10-16 04:20:12,352][03835] Avg episode reward: [(0, '6.050'), (1, '6.280')] -[2023-10-16 04:20:12,584][05219] Updated weights for policy 1, policy_version 39420 (0.0011) -[2023-10-16 04:20:13,746][05218] Updated weights for policy 0, policy_version 39562 (0.0009) -[2023-10-16 04:20:14,117][05218] Updated weights for policy 0, policy_version 39572 (0.0011) -[2023-10-16 04:20:14,488][05218] Updated weights for policy 0, policy_version 39582 (0.0010) -[2023-10-16 04:20:16,335][05219] Updated weights for policy 1, policy_version 39430 (0.0009) -[2023-10-16 04:20:16,704][05219] Updated weights for policy 1, policy_version 39440 (0.0008) -[2023-10-16 04:20:17,060][05219] Updated weights for policy 1, policy_version 39450 (0.0010) -[2023-10-16 04:20:17,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 80936960. Throughput: 0: 1793.0, 1: 1797.4. Samples: 20241006. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) -[2023-10-16 04:20:17,351][03835] Avg episode reward: [(0, '6.560'), (1, '6.280')] -[2023-10-16 04:20:18,263][05218] Updated weights for policy 0, policy_version 39592 (0.0008) -[2023-10-16 04:20:18,643][05218] Updated weights for policy 0, policy_version 39602 (0.0009) -[2023-10-16 04:20:19,025][05218] Updated weights for policy 0, policy_version 39612 (0.0009) -[2023-10-16 04:20:20,671][05219] Updated weights for policy 1, policy_version 39460 (0.0010) -[2023-10-16 04:20:21,046][05219] Updated weights for policy 1, policy_version 39470 (0.0009) -[2023-10-16 04:20:21,408][05219] Updated weights for policy 1, policy_version 39480 (0.0008) -[2023-10-16 04:20:22,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 81002496. Throughput: 0: 1808.8, 1: 1772.1. Samples: 20262314. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) -[2023-10-16 04:20:22,351][03835] Avg episode reward: [(0, '5.790'), (1, '5.110')] -[2023-10-16 04:20:22,681][05218] Updated weights for policy 0, policy_version 39622 (0.0009) -[2023-10-16 04:20:23,047][05218] Updated weights for policy 0, policy_version 39632 (0.0007) -[2023-10-16 04:20:23,424][05218] Updated weights for policy 0, policy_version 39642 (0.0007) -[2023-10-16 04:20:25,346][05219] Updated weights for policy 1, policy_version 39490 (0.0009) -[2023-10-16 04:20:25,719][05219] Updated weights for policy 1, policy_version 39500 (0.0009) -[2023-10-16 04:20:26,075][05219] Updated weights for policy 1, policy_version 39510 (0.0009) -[2023-10-16 04:20:26,445][05219] Updated weights for policy 1, policy_version 39520 (0.0007) -[2023-10-16 04:20:27,053][05218] Updated weights for policy 0, policy_version 39652 (0.0008) -[2023-10-16 04:20:27,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 81068032. Throughput: 0: 1804.9, 1: 1796.8. Samples: 20273652. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) -[2023-10-16 04:20:27,351][03835] Avg episode reward: [(0, '6.230'), (1, '5.610')] -[2023-10-16 04:20:27,420][05218] Updated weights for policy 0, policy_version 39662 (0.0010) -[2023-10-16 04:20:27,803][05218] Updated weights for policy 0, policy_version 39672 (0.0007) -[2023-10-16 04:20:30,103][05219] Updated weights for policy 1, policy_version 39530 (0.0010) -[2023-10-16 04:20:30,476][05219] Updated weights for policy 1, policy_version 39540 (0.0010) -[2023-10-16 04:20:30,838][05219] Updated weights for policy 1, policy_version 39550 (0.0011) -[2023-10-16 04:20:31,425][05218] Updated weights for policy 0, policy_version 39682 (0.0007) -[2023-10-16 04:20:31,790][05218] Updated weights for policy 0, policy_version 39692 (0.0009) -[2023-10-16 04:20:32,171][05218] Updated weights for policy 0, policy_version 39702 (0.0007) -[2023-10-16 04:20:32,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 81133568. Throughput: 0: 1807.5, 1: 1776.1. Samples: 20294784. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) -[2023-10-16 04:20:32,351][03835] Avg episode reward: [(0, '6.100'), (1, '6.240')] -[2023-10-16 04:20:32,541][05218] Updated weights for policy 0, policy_version 39712 (0.0008) -[2023-10-16 04:20:34,638][05219] Updated weights for policy 1, policy_version 39560 (0.0011) -[2023-10-16 04:20:34,996][05219] Updated weights for policy 1, policy_version 39570 (0.0008) -[2023-10-16 04:20:35,366][05219] Updated weights for policy 1, policy_version 39580 (0.0007) -[2023-10-16 04:20:36,325][05218] Updated weights for policy 0, policy_version 39722 (0.0009) -[2023-10-16 04:20:36,695][05218] Updated weights for policy 0, policy_version 39732 (0.0008) -[2023-10-16 04:20:37,076][05218] Updated weights for policy 0, policy_version 39742 (0.0009) -[2023-10-16 04:20:37,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 81231872. Throughput: 0: 1800.1, 1: 1783.3. Samples: 20315626. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) -[2023-10-16 04:20:37,351][03835] Avg episode reward: [(0, '6.010'), (1, '6.740')] -[2023-10-16 04:20:39,175][05219] Updated weights for policy 1, policy_version 39590 (0.0010) -[2023-10-16 04:20:39,541][05219] Updated weights for policy 1, policy_version 39600 (0.0008) -[2023-10-16 04:20:39,904][05219] Updated weights for policy 1, policy_version 39610 (0.0007) -[2023-10-16 04:20:40,764][05218] Updated weights for policy 0, policy_version 39752 (0.0009) -[2023-10-16 04:20:41,140][05218] Updated weights for policy 0, policy_version 39762 (0.0011) -[2023-10-16 04:20:41,500][05218] Updated weights for policy 0, policy_version 39772 (0.0011) -[2023-10-16 04:20:42,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 81297408. Throughput: 0: 1805.1, 1: 1786.9. Samples: 20327166. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) -[2023-10-16 04:20:42,351][03835] Avg episode reward: [(0, '6.270'), (1, '6.960')] -[2023-10-16 04:20:43,761][05219] Updated weights for policy 1, policy_version 39620 (0.0009) -[2023-10-16 04:20:44,138][05219] Updated weights for policy 1, policy_version 39630 (0.0011) -[2023-10-16 04:20:44,503][05219] Updated weights for policy 1, policy_version 39640 (0.0008) -[2023-10-16 04:20:45,317][05218] Updated weights for policy 0, policy_version 39782 (0.0008) -[2023-10-16 04:20:45,682][05218] Updated weights for policy 0, policy_version 39792 (0.0009) -[2023-10-16 04:20:46,063][05218] Updated weights for policy 0, policy_version 39802 (0.0011) -[2023-10-16 04:20:47,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 81362944. Throughput: 0: 1800.4, 1: 1783.2. Samples: 20347938. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-16 04:20:47,351][03835] Avg episode reward: [(0, '6.100'), (1, '6.660')] -[2023-10-16 04:20:48,169][05219] Updated weights for policy 1, policy_version 39650 (0.0007) -[2023-10-16 04:20:48,537][05219] Updated weights for policy 1, policy_version 39660 (0.0008) -[2023-10-16 04:20:48,898][05219] Updated weights for policy 1, policy_version 39670 (0.0009) -[2023-10-16 04:20:49,264][05219] Updated weights for policy 1, policy_version 39680 (0.0007) -[2023-10-16 04:20:49,747][05218] Updated weights for policy 0, policy_version 39812 (0.0009) -[2023-10-16 04:20:50,126][05218] Updated weights for policy 0, policy_version 39822 (0.0012) -[2023-10-16 04:20:50,504][05218] Updated weights for policy 0, policy_version 39832 (0.0010) -[2023-10-16 04:20:52,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 81428480. Throughput: 0: 1798.4, 1: 1793.8. Samples: 20370472. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-16 04:20:52,352][03835] Avg episode reward: [(0, '6.480'), (1, '6.920')] -[2023-10-16 04:20:53,003][05219] Updated weights for policy 1, policy_version 39690 (0.0008) -[2023-10-16 04:20:53,367][05219] Updated weights for policy 1, policy_version 39700 (0.0008) -[2023-10-16 04:20:53,740][05219] Updated weights for policy 1, policy_version 39710 (0.0007) -[2023-10-16 04:20:54,238][05218] Updated weights for policy 0, policy_version 39842 (0.0010) -[2023-10-16 04:20:54,641][05218] Updated weights for policy 0, policy_version 39852 (0.0008) -[2023-10-16 04:20:55,015][05218] Updated weights for policy 0, policy_version 39862 (0.0008) -[2023-10-16 04:20:55,398][05218] Updated weights for policy 0, policy_version 39872 (0.0008) -[2023-10-16 04:20:57,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 81494016. Throughput: 0: 1803.9, 1: 1783.5. Samples: 20380338. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-16 04:20:57,351][03835] Avg episode reward: [(0, '6.640'), (1, '6.120')] -[2023-10-16 04:20:57,360][05219] Updated weights for policy 1, policy_version 39720 (0.0009) -[2023-10-16 04:20:57,735][05219] Updated weights for policy 1, policy_version 39730 (0.0008) -[2023-10-16 04:20:58,093][05219] Updated weights for policy 1, policy_version 39740 (0.0009) -[2023-10-16 04:20:59,078][05218] Updated weights for policy 0, policy_version 39882 (0.0009) -[2023-10-16 04:20:59,451][05218] Updated weights for policy 0, policy_version 39892 (0.0009) -[2023-10-16 04:20:59,821][05218] Updated weights for policy 0, policy_version 39902 (0.0008) -[2023-10-16 04:21:01,881][05219] Updated weights for policy 1, policy_version 39750 (0.0009) -[2023-10-16 04:21:02,258][05219] Updated weights for policy 1, policy_version 39760 (0.0010) -[2023-10-16 04:21:02,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 81559552. Throughput: 0: 1798.2, 1: 1791.4. Samples: 20402540. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-16 04:21:02,351][03835] Avg episode reward: [(0, '6.140'), (1, '6.510')] -[2023-10-16 04:21:02,624][05219] Updated weights for policy 1, policy_version 39770 (0.0007) -[2023-10-16 04:21:03,736][05218] Updated weights for policy 0, policy_version 39912 (0.0010) -[2023-10-16 04:21:04,114][05218] Updated weights for policy 0, policy_version 39922 (0.0009) -[2023-10-16 04:21:04,483][05218] Updated weights for policy 0, policy_version 39932 (0.0009) -[2023-10-16 04:21:06,400][05219] Updated weights for policy 1, policy_version 39780 (0.0008) -[2023-10-16 04:21:06,764][05219] Updated weights for policy 1, policy_version 39790 (0.0008) -[2023-10-16 04:21:07,118][05219] Updated weights for policy 1, policy_version 39800 (0.0008) -[2023-10-16 04:21:07,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 81625088. Throughput: 0: 1790.1, 1: 1803.0. Samples: 20424006. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-16 04:21:07,352][03835] Avg episode reward: [(0, '6.390'), (1, '6.960')] -[2023-10-16 04:21:08,357][05218] Updated weights for policy 0, policy_version 39942 (0.0008) -[2023-10-16 04:21:08,735][05218] Updated weights for policy 0, policy_version 39952 (0.0009) -[2023-10-16 04:21:09,102][05218] Updated weights for policy 0, policy_version 39962 (0.0008) -[2023-10-16 04:21:10,935][05219] Updated weights for policy 1, policy_version 39810 (0.0009) -[2023-10-16 04:21:11,315][05219] Updated weights for policy 1, policy_version 39820 (0.0008) -[2023-10-16 04:21:11,683][05219] Updated weights for policy 1, policy_version 39830 (0.0007) -[2023-10-16 04:21:12,048][05219] Updated weights for policy 1, policy_version 39840 (0.0008) -[2023-10-16 04:21:12,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 81723392. Throughput: 0: 1786.9, 1: 1795.0. Samples: 20434840. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-16 04:21:12,351][03835] Avg episode reward: [(0, '5.880'), (1, '7.220')] -[2023-10-16 04:21:12,781][05218] Updated weights for policy 0, policy_version 39972 (0.0007) -[2023-10-16 04:21:13,158][05218] Updated weights for policy 0, policy_version 39982 (0.0009) -[2023-10-16 04:21:13,540][05218] Updated weights for policy 0, policy_version 39992 (0.0007) -[2023-10-16 04:21:15,838][05219] Updated weights for policy 1, policy_version 39850 (0.0008) -[2023-10-16 04:21:16,203][05219] Updated weights for policy 1, policy_version 39860 (0.0009) -[2023-10-16 04:21:16,556][05219] Updated weights for policy 1, policy_version 39870 (0.0008) -[2023-10-16 04:21:17,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 81788928. Throughput: 0: 1785.3, 1: 1807.8. Samples: 20456474. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:21:17,351][03835] Avg episode reward: [(0, '6.350'), (1, '6.530')] -[2023-10-16 04:21:17,374][05218] Updated weights for policy 0, policy_version 40002 (0.0008) -[2023-10-16 04:21:17,751][05218] Updated weights for policy 0, policy_version 40012 (0.0007) -[2023-10-16 04:21:18,121][05218] Updated weights for policy 0, policy_version 40022 (0.0009) -[2023-10-16 04:21:18,498][05218] Updated weights for policy 0, policy_version 40032 (0.0009) -[2023-10-16 04:21:20,185][05219] Updated weights for policy 1, policy_version 39880 (0.0009) -[2023-10-16 04:21:20,546][05219] Updated weights for policy 1, policy_version 39890 (0.0009) -[2023-10-16 04:21:20,916][05219] Updated weights for policy 1, policy_version 39900 (0.0009) -[2023-10-16 04:21:22,211][05218] Updated weights for policy 0, policy_version 40042 (0.0007) -[2023-10-16 04:21:22,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 81854464. Throughput: 0: 1808.7, 1: 1796.2. Samples: 20477846. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:21:22,351][03835] Avg episode reward: [(0, '6.090'), (1, '6.050')] -[2023-10-16 04:21:22,585][05218] Updated weights for policy 0, policy_version 40052 (0.0007) -[2023-10-16 04:21:22,968][05218] Updated weights for policy 0, policy_version 40062 (0.0007) -[2023-10-16 04:21:24,702][05219] Updated weights for policy 1, policy_version 39910 (0.0010) -[2023-10-16 04:21:25,062][05219] Updated weights for policy 1, policy_version 39920 (0.0010) -[2023-10-16 04:21:25,445][05219] Updated weights for policy 1, policy_version 39930 (0.0010) -[2023-10-16 04:21:26,706][05218] Updated weights for policy 0, policy_version 40072 (0.0007) -[2023-10-16 04:21:27,081][05218] Updated weights for policy 0, policy_version 40082 (0.0008) -[2023-10-16 04:21:27,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 81920000. Throughput: 0: 1788.3, 1: 1808.9. Samples: 20489042. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:21:27,351][03835] Avg episode reward: [(0, '5.920'), (1, '6.530')] -[2023-10-16 04:21:27,444][05218] Updated weights for policy 0, policy_version 40092 (0.0009) -[2023-10-16 04:21:29,078][05219] Updated weights for policy 1, policy_version 39940 (0.0008) -[2023-10-16 04:21:29,442][05219] Updated weights for policy 1, policy_version 39950 (0.0007) -[2023-10-16 04:21:29,807][05219] Updated weights for policy 1, policy_version 39960 (0.0008) -[2023-10-16 04:21:31,064][05218] Updated weights for policy 0, policy_version 40102 (0.0007) -[2023-10-16 04:21:31,435][05218] Updated weights for policy 0, policy_version 40112 (0.0008) -[2023-10-16 04:21:31,816][05218] Updated weights for policy 0, policy_version 40122 (0.0007) -[2023-10-16 04:21:32,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 82018304. Throughput: 0: 1816.7, 1: 1793.5. Samples: 20510396. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:21:32,351][03835] Avg episode reward: [(0, '6.260'), (1, '6.390')] -[2023-10-16 04:21:33,656][05219] Updated weights for policy 1, policy_version 39970 (0.0007) -[2023-10-16 04:21:34,020][05219] Updated weights for policy 1, policy_version 39980 (0.0010) -[2023-10-16 04:21:34,386][05219] Updated weights for policy 1, policy_version 39990 (0.0008) -[2023-10-16 04:21:34,751][05219] Updated weights for policy 1, policy_version 40000 (0.0007) -[2023-10-16 04:21:35,578][05218] Updated weights for policy 0, policy_version 40132 (0.0009) -[2023-10-16 04:21:35,962][05218] Updated weights for policy 0, policy_version 40142 (0.0010) -[2023-10-16 04:21:36,330][05218] Updated weights for policy 0, policy_version 40152 (0.0009) -[2023-10-16 04:21:37,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 82083840. Throughput: 0: 1798.7, 1: 1793.7. Samples: 20532126. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:21:37,351][03835] Avg episode reward: [(0, '6.110'), (1, '6.260')] -[2023-10-16 04:21:37,360][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000040000_40960000.pth... -[2023-10-16 04:21:37,360][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000040160_41123840.pth... -[2023-10-16 04:21:37,398][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000038336_39256064.pth -[2023-10-16 04:21:37,401][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000038464_39387136.pth -[2023-10-16 04:21:38,534][05219] Updated weights for policy 1, policy_version 40010 (0.0010) -[2023-10-16 04:21:38,899][05219] Updated weights for policy 1, policy_version 40020 (0.0010) -[2023-10-16 04:21:39,268][05219] Updated weights for policy 1, policy_version 40030 (0.0009) -[2023-10-16 04:21:39,890][05218] Updated weights for policy 0, policy_version 40162 (0.0008) -[2023-10-16 04:21:40,290][05218] Updated weights for policy 0, policy_version 40172 (0.0009) -[2023-10-16 04:21:40,660][05218] Updated weights for policy 0, policy_version 40182 (0.0010) -[2023-10-16 04:21:41,025][05218] Updated weights for policy 0, policy_version 40192 (0.0009) -[2023-10-16 04:21:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 82149376. Throughput: 0: 1813.4, 1: 1793.7. Samples: 20542658. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 04:21:42,351][03835] Avg episode reward: [(0, '5.550'), (1, '6.220')] -[2023-10-16 04:21:42,903][05219] Updated weights for policy 1, policy_version 40040 (0.0007) -[2023-10-16 04:21:43,262][05219] Updated weights for policy 1, policy_version 40050 (0.0009) -[2023-10-16 04:21:43,630][05219] Updated weights for policy 1, policy_version 40060 (0.0008) -[2023-10-16 04:21:44,549][05218] Updated weights for policy 0, policy_version 40202 (0.0007) -[2023-10-16 04:21:44,924][05218] Updated weights for policy 0, policy_version 40212 (0.0007) -[2023-10-16 04:21:45,305][05218] Updated weights for policy 0, policy_version 40222 (0.0007) -[2023-10-16 04:21:47,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 82214912. Throughput: 0: 1807.1, 1: 1795.9. Samples: 20564676. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 04:21:47,351][03835] Avg episode reward: [(0, '5.850'), (1, '6.040')] -[2023-10-16 04:21:47,504][05219] Updated weights for policy 1, policy_version 40070 (0.0007) -[2023-10-16 04:21:47,869][05219] Updated weights for policy 1, policy_version 40080 (0.0008) -[2023-10-16 04:21:48,229][05219] Updated weights for policy 1, policy_version 40090 (0.0009) -[2023-10-16 04:21:48,827][05218] Updated weights for policy 0, policy_version 40232 (0.0009) -[2023-10-16 04:21:49,200][05218] Updated weights for policy 0, policy_version 40242 (0.0010) -[2023-10-16 04:21:49,577][05218] Updated weights for policy 0, policy_version 40252 (0.0011) -[2023-10-16 04:21:51,955][05219] Updated weights for policy 1, policy_version 40100 (0.0010) -[2023-10-16 04:21:52,324][05219] Updated weights for policy 1, policy_version 40110 (0.0007) -[2023-10-16 04:21:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 82280448. Throughput: 0: 1809.9, 1: 1805.3. Samples: 20586690. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 04:21:52,351][03835] Avg episode reward: [(0, '6.430'), (1, '6.350')] -[2023-10-16 04:21:52,697][05219] Updated weights for policy 1, policy_version 40120 (0.0007) -[2023-10-16 04:21:53,318][05218] Updated weights for policy 0, policy_version 40262 (0.0009) -[2023-10-16 04:21:53,695][05218] Updated weights for policy 0, policy_version 40272 (0.0010) -[2023-10-16 04:21:54,070][05218] Updated weights for policy 0, policy_version 40282 (0.0009) -[2023-10-16 04:21:56,350][05219] Updated weights for policy 1, policy_version 40130 (0.0007) -[2023-10-16 04:21:56,718][05219] Updated weights for policy 1, policy_version 40140 (0.0008) -[2023-10-16 04:21:57,085][05219] Updated weights for policy 1, policy_version 40150 (0.0008) -[2023-10-16 04:21:57,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 82345984. Throughput: 0: 1810.9, 1: 1794.0. Samples: 20597060. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 04:21:57,351][03835] Avg episode reward: [(0, '6.130'), (1, '6.390')] -[2023-10-16 04:21:57,452][05219] Updated weights for policy 1, policy_version 40160 (0.0009) -[2023-10-16 04:21:57,819][05218] Updated weights for policy 0, policy_version 40292 (0.0009) -[2023-10-16 04:21:58,193][05218] Updated weights for policy 0, policy_version 40302 (0.0007) -[2023-10-16 04:21:58,573][05218] Updated weights for policy 0, policy_version 40312 (0.0008) -[2023-10-16 04:22:01,194][05219] Updated weights for policy 1, policy_version 40170 (0.0010) -[2023-10-16 04:22:01,558][05219] Updated weights for policy 1, policy_version 40180 (0.0010) -[2023-10-16 04:22:01,934][05219] Updated weights for policy 1, policy_version 40190 (0.0009) -[2023-10-16 04:22:02,203][05218] Updated weights for policy 0, policy_version 40322 (0.0009) -[2023-10-16 04:22:02,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 82444288. Throughput: 0: 1813.3, 1: 1803.9. Samples: 20619248. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 04:22:02,351][03835] Avg episode reward: [(0, '6.610'), (1, '5.780')] -[2023-10-16 04:22:02,576][05218] Updated weights for policy 0, policy_version 40332 (0.0010) -[2023-10-16 04:22:02,951][05218] Updated weights for policy 0, policy_version 40342 (0.0009) -[2023-10-16 04:22:03,328][05218] Updated weights for policy 0, policy_version 40352 (0.0008) -[2023-10-16 04:22:05,628][05219] Updated weights for policy 1, policy_version 40200 (0.0009) -[2023-10-16 04:22:06,003][05219] Updated weights for policy 1, policy_version 40210 (0.0009) -[2023-10-16 04:22:06,359][05219] Updated weights for policy 1, policy_version 40220 (0.0008) -[2023-10-16 04:22:07,101][05218] Updated weights for policy 0, policy_version 40362 (0.0009) -[2023-10-16 04:22:07,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 82509824. Throughput: 0: 1814.3, 1: 1791.7. Samples: 20640118. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 04:22:07,351][03835] Avg episode reward: [(0, '7.200'), (1, '6.210')] -[2023-10-16 04:22:07,485][05218] Updated weights for policy 0, policy_version 40372 (0.0010) -[2023-10-16 04:22:07,860][05218] Updated weights for policy 0, policy_version 40382 (0.0008) -[2023-10-16 04:22:07,933][04766] Saving new best policy, reward=7.200! -[2023-10-16 04:22:10,120][05219] Updated weights for policy 1, policy_version 40230 (0.0007) -[2023-10-16 04:22:10,485][05219] Updated weights for policy 1, policy_version 40240 (0.0007) -[2023-10-16 04:22:10,858][05219] Updated weights for policy 1, policy_version 40250 (0.0010) -[2023-10-16 04:22:11,673][05218] Updated weights for policy 0, policy_version 40392 (0.0008) -[2023-10-16 04:22:12,051][05218] Updated weights for policy 0, policy_version 40402 (0.0008) -[2023-10-16 04:22:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 82575360. Throughput: 0: 1813.5, 1: 1801.7. Samples: 20651726. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-16 04:22:12,351][03835] Avg episode reward: [(0, '6.390'), (1, '6.140')] -[2023-10-16 04:22:12,430][05218] Updated weights for policy 0, policy_version 40412 (0.0010) -[2023-10-16 04:22:14,626][05219] Updated weights for policy 1, policy_version 40260 (0.0009) -[2023-10-16 04:22:14,995][05219] Updated weights for policy 1, policy_version 40270 (0.0007) -[2023-10-16 04:22:15,368][05219] Updated weights for policy 1, policy_version 40280 (0.0008) -[2023-10-16 04:22:16,165][05218] Updated weights for policy 0, policy_version 40422 (0.0007) -[2023-10-16 04:22:16,544][05218] Updated weights for policy 0, policy_version 40432 (0.0007) -[2023-10-16 04:22:16,912][05218] Updated weights for policy 0, policy_version 40442 (0.0008) -[2023-10-16 04:22:17,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 82673664. Throughput: 0: 1811.6, 1: 1791.9. Samples: 20672554. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-16 04:22:17,351][03835] Avg episode reward: [(0, '6.540'), (1, '5.880')] -[2023-10-16 04:22:18,964][05219] Updated weights for policy 1, policy_version 40290 (0.0009) -[2023-10-16 04:22:19,337][05219] Updated weights for policy 1, policy_version 40300 (0.0009) -[2023-10-16 04:22:19,702][05219] Updated weights for policy 1, policy_version 40310 (0.0007) -[2023-10-16 04:22:20,070][05219] Updated weights for policy 1, policy_version 40320 (0.0008) -[2023-10-16 04:22:20,687][05218] Updated weights for policy 0, policy_version 40452 (0.0009) -[2023-10-16 04:22:21,056][05218] Updated weights for policy 0, policy_version 40462 (0.0010) -[2023-10-16 04:22:21,428][05218] Updated weights for policy 0, policy_version 40472 (0.0011) -[2023-10-16 04:22:22,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 82739200. Throughput: 0: 1804.5, 1: 1794.2. Samples: 20694068. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-16 04:22:22,351][03835] Avg episode reward: [(0, '6.660'), (1, '6.540')] -[2023-10-16 04:22:23,920][05219] Updated weights for policy 1, policy_version 40330 (0.0008) -[2023-10-16 04:22:24,295][05219] Updated weights for policy 1, policy_version 40340 (0.0008) -[2023-10-16 04:22:24,659][05219] Updated weights for policy 1, policy_version 40350 (0.0008) -[2023-10-16 04:22:25,133][05218] Updated weights for policy 0, policy_version 40482 (0.0010) -[2023-10-16 04:22:25,515][05218] Updated weights for policy 0, policy_version 40492 (0.0008) -[2023-10-16 04:22:25,890][05218] Updated weights for policy 0, policy_version 40502 (0.0010) -[2023-10-16 04:22:26,258][05218] Updated weights for policy 0, policy_version 40512 (0.0007) -[2023-10-16 04:22:27,351][03835] Fps is (10 sec: 13106.9, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 82804736. Throughput: 0: 1816.8, 1: 1791.3. Samples: 20705022. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-16 04:22:27,352][03835] Avg episode reward: [(0, '6.790'), (1, '6.060')] -[2023-10-16 04:22:28,608][05219] Updated weights for policy 1, policy_version 40360 (0.0008) -[2023-10-16 04:22:28,977][05219] Updated weights for policy 1, policy_version 40370 (0.0010) -[2023-10-16 04:22:29,340][05219] Updated weights for policy 1, policy_version 40380 (0.0009) -[2023-10-16 04:22:29,952][05218] Updated weights for policy 0, policy_version 40522 (0.0011) -[2023-10-16 04:22:30,325][05218] Updated weights for policy 0, policy_version 40532 (0.0011) -[2023-10-16 04:22:30,697][05218] Updated weights for policy 0, policy_version 40542 (0.0009) -[2023-10-16 04:22:32,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 82870272. Throughput: 0: 1798.9, 1: 1796.7. Samples: 20726482. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-16 04:22:32,351][03835] Avg episode reward: [(0, '6.340'), (1, '6.530')] -[2023-10-16 04:22:33,079][05219] Updated weights for policy 1, policy_version 40390 (0.0007) -[2023-10-16 04:22:33,454][05219] Updated weights for policy 1, policy_version 40400 (0.0009) -[2023-10-16 04:22:33,816][05219] Updated weights for policy 1, policy_version 40410 (0.0007) -[2023-10-16 04:22:34,376][05218] Updated weights for policy 0, policy_version 40552 (0.0009) -[2023-10-16 04:22:34,752][05218] Updated weights for policy 0, policy_version 40562 (0.0010) -[2023-10-16 04:22:35,130][05218] Updated weights for policy 0, policy_version 40572 (0.0008) -[2023-10-16 04:22:37,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 82935808. Throughput: 0: 1799.5, 1: 1807.5. Samples: 20749006. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-16 04:22:37,352][03835] Avg episode reward: [(0, '6.760'), (1, '6.790')] -[2023-10-16 04:22:37,530][05219] Updated weights for policy 1, policy_version 40420 (0.0008) -[2023-10-16 04:22:37,910][05219] Updated weights for policy 1, policy_version 40430 (0.0007) -[2023-10-16 04:22:38,272][05219] Updated weights for policy 1, policy_version 40440 (0.0011) -[2023-10-16 04:22:38,841][05218] Updated weights for policy 0, policy_version 40582 (0.0009) -[2023-10-16 04:22:39,213][05218] Updated weights for policy 0, policy_version 40592 (0.0008) -[2023-10-16 04:22:39,587][05218] Updated weights for policy 0, policy_version 40602 (0.0008) -[2023-10-16 04:22:42,061][05219] Updated weights for policy 1, policy_version 40450 (0.0008) -[2023-10-16 04:22:42,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 83001344. Throughput: 0: 1798.6, 1: 1796.4. Samples: 20758836. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-16 04:22:42,351][03835] Avg episode reward: [(0, '6.480'), (1, '6.210')] -[2023-10-16 04:22:42,426][05219] Updated weights for policy 1, policy_version 40460 (0.0007) -[2023-10-16 04:22:42,781][05219] Updated weights for policy 1, policy_version 40470 (0.0009) -[2023-10-16 04:22:43,142][05219] Updated weights for policy 1, policy_version 40480 (0.0008) -[2023-10-16 04:22:43,409][05218] Updated weights for policy 0, policy_version 40612 (0.0010) -[2023-10-16 04:22:43,783][05218] Updated weights for policy 0, policy_version 40622 (0.0007) -[2023-10-16 04:22:44,161][05218] Updated weights for policy 0, policy_version 40632 (0.0008) -[2023-10-16 04:22:46,943][05219] Updated weights for policy 1, policy_version 40490 (0.0008) -[2023-10-16 04:22:47,308][05219] Updated weights for policy 1, policy_version 40500 (0.0011) -[2023-10-16 04:22:47,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 83066880. Throughput: 0: 1793.3, 1: 1797.5. Samples: 20780834. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-16 04:22:47,351][03835] Avg episode reward: [(0, '6.330'), (1, '5.770')] -[2023-10-16 04:22:47,668][05219] Updated weights for policy 1, policy_version 40510 (0.0010) -[2023-10-16 04:22:47,899][05218] Updated weights for policy 0, policy_version 40642 (0.0008) -[2023-10-16 04:22:48,270][05218] Updated weights for policy 0, policy_version 40652 (0.0009) -[2023-10-16 04:22:48,644][05218] Updated weights for policy 0, policy_version 40662 (0.0010) -[2023-10-16 04:22:49,020][05218] Updated weights for policy 0, policy_version 40672 (0.0009) -[2023-10-16 04:22:51,571][05219] Updated weights for policy 1, policy_version 40520 (0.0009) -[2023-10-16 04:22:51,930][05219] Updated weights for policy 1, policy_version 40530 (0.0008) -[2023-10-16 04:22:52,294][05219] Updated weights for policy 1, policy_version 40540 (0.0008) -[2023-10-16 04:22:52,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 83132416. Throughput: 0: 1807.7, 1: 1795.4. Samples: 20802258. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-16 04:22:52,351][03835] Avg episode reward: [(0, '6.110'), (1, '6.020')] -[2023-10-16 04:22:52,772][05218] Updated weights for policy 0, policy_version 40682 (0.0009) -[2023-10-16 04:22:53,145][05218] Updated weights for policy 0, policy_version 40692 (0.0008) -[2023-10-16 04:22:53,517][05218] Updated weights for policy 0, policy_version 40702 (0.0009) -[2023-10-16 04:22:55,862][05219] Updated weights for policy 1, policy_version 40550 (0.0007) -[2023-10-16 04:22:56,222][05219] Updated weights for policy 1, policy_version 40560 (0.0009) -[2023-10-16 04:22:56,582][05219] Updated weights for policy 1, policy_version 40570 (0.0009) -[2023-10-16 04:22:57,283][05218] Updated weights for policy 0, policy_version 40712 (0.0009) -[2023-10-16 04:22:57,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 83230720. Throughput: 0: 1791.6, 1: 1796.2. Samples: 20813176. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-16 04:22:57,351][03835] Avg episode reward: [(0, '6.190'), (1, '6.190')] -[2023-10-16 04:22:57,655][05218] Updated weights for policy 0, policy_version 40722 (0.0008) -[2023-10-16 04:22:58,031][05218] Updated weights for policy 0, policy_version 40732 (0.0008) -[2023-10-16 04:23:00,251][05219] Updated weights for policy 1, policy_version 40580 (0.0008) -[2023-10-16 04:23:00,606][05219] Updated weights for policy 1, policy_version 40590 (0.0007) -[2023-10-16 04:23:00,966][05219] Updated weights for policy 1, policy_version 40600 (0.0009) -[2023-10-16 04:23:01,700][05218] Updated weights for policy 0, policy_version 40742 (0.0009) -[2023-10-16 04:23:02,073][05218] Updated weights for policy 0, policy_version 40752 (0.0010) -[2023-10-16 04:23:02,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 83296256. Throughput: 0: 1809.3, 1: 1801.2. Samples: 20835022. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-16 04:23:02,351][03835] Avg episode reward: [(0, '6.580'), (1, '6.230')] -[2023-10-16 04:23:02,451][05218] Updated weights for policy 0, policy_version 40762 (0.0007) -[2023-10-16 04:23:04,754][05219] Updated weights for policy 1, policy_version 40610 (0.0009) -[2023-10-16 04:23:05,119][05219] Updated weights for policy 1, policy_version 40620 (0.0007) -[2023-10-16 04:23:05,474][05219] Updated weights for policy 1, policy_version 40630 (0.0008) -[2023-10-16 04:23:05,849][05219] Updated weights for policy 1, policy_version 40640 (0.0008) -[2023-10-16 04:23:06,219][05218] Updated weights for policy 0, policy_version 40772 (0.0007) -[2023-10-16 04:23:06,596][05218] Updated weights for policy 0, policy_version 40782 (0.0009) -[2023-10-16 04:23:06,973][05218] Updated weights for policy 0, policy_version 40792 (0.0008) -[2023-10-16 04:23:07,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 83394560. Throughput: 0: 1799.1, 1: 1794.7. Samples: 20855788. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-16 04:23:07,351][03835] Avg episode reward: [(0, '6.030'), (1, '6.460')] -[2023-10-16 04:23:09,773][05219] Updated weights for policy 1, policy_version 40650 (0.0008) -[2023-10-16 04:23:10,140][05219] Updated weights for policy 1, policy_version 40660 (0.0008) -[2023-10-16 04:23:10,490][05219] Updated weights for policy 1, policy_version 40670 (0.0008) -[2023-10-16 04:23:10,587][05218] Updated weights for policy 0, policy_version 40802 (0.0009) -[2023-10-16 04:23:10,991][05218] Updated weights for policy 0, policy_version 40812 (0.0010) -[2023-10-16 04:23:11,364][05218] Updated weights for policy 0, policy_version 40822 (0.0009) -[2023-10-16 04:23:11,738][05218] Updated weights for policy 0, policy_version 40832 (0.0007) -[2023-10-16 04:23:12,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 83460096. Throughput: 0: 1808.7, 1: 1809.2. Samples: 20867826. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-16 04:23:12,351][03835] Avg episode reward: [(0, '6.450'), (1, '6.730')] -[2023-10-16 04:23:14,261][05219] Updated weights for policy 1, policy_version 40680 (0.0007) -[2023-10-16 04:23:14,635][05219] Updated weights for policy 1, policy_version 40690 (0.0008) -[2023-10-16 04:23:15,004][05219] Updated weights for policy 1, policy_version 40700 (0.0009) -[2023-10-16 04:23:15,357][05218] Updated weights for policy 0, policy_version 40842 (0.0008) -[2023-10-16 04:23:15,743][05218] Updated weights for policy 0, policy_version 40852 (0.0009) -[2023-10-16 04:23:16,112][05218] Updated weights for policy 0, policy_version 40862 (0.0007) -[2023-10-16 04:23:17,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 83525632. Throughput: 0: 1802.1, 1: 1789.5. Samples: 20888104. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-16 04:23:17,351][03835] Avg episode reward: [(0, '6.680'), (1, '6.210')] -[2023-10-16 04:23:18,674][05219] Updated weights for policy 1, policy_version 40710 (0.0008) -[2023-10-16 04:23:19,030][05219] Updated weights for policy 1, policy_version 40720 (0.0009) -[2023-10-16 04:23:19,396][05219] Updated weights for policy 1, policy_version 40730 (0.0010) -[2023-10-16 04:23:19,919][05218] Updated weights for policy 0, policy_version 40872 (0.0009) -[2023-10-16 04:23:20,299][05218] Updated weights for policy 0, policy_version 40882 (0.0008) -[2023-10-16 04:23:20,674][05218] Updated weights for policy 0, policy_version 40892 (0.0008) -[2023-10-16 04:23:22,351][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 83591168. Throughput: 0: 1798.7, 1: 1794.8. Samples: 20910712. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-16 04:23:22,352][03835] Avg episode reward: [(0, '6.060'), (1, '5.920')] -[2023-10-16 04:23:23,032][05219] Updated weights for policy 1, policy_version 40740 (0.0007) -[2023-10-16 04:23:23,395][05219] Updated weights for policy 1, policy_version 40750 (0.0008) -[2023-10-16 04:23:23,762][05219] Updated weights for policy 1, policy_version 40760 (0.0009) -[2023-10-16 04:23:24,320][05218] Updated weights for policy 0, policy_version 40902 (0.0009) -[2023-10-16 04:23:24,693][05218] Updated weights for policy 0, policy_version 40912 (0.0009) -[2023-10-16 04:23:25,075][05218] Updated weights for policy 0, policy_version 40922 (0.0008) -[2023-10-16 04:23:27,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 83656704. Throughput: 0: 1801.1, 1: 1793.8. Samples: 20920606. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-16 04:23:27,351][03835] Avg episode reward: [(0, '6.150'), (1, '6.630')] -[2023-10-16 04:23:27,489][05219] Updated weights for policy 1, policy_version 40770 (0.0008) -[2023-10-16 04:23:27,861][05219] Updated weights for policy 1, policy_version 40780 (0.0007) -[2023-10-16 04:23:28,226][05219] Updated weights for policy 1, policy_version 40790 (0.0008) -[2023-10-16 04:23:28,546][05218] Updated weights for policy 0, policy_version 40932 (0.0007) -[2023-10-16 04:23:28,597][05219] Updated weights for policy 1, policy_version 40800 (0.0007) -[2023-10-16 04:23:28,922][05218] Updated weights for policy 0, policy_version 40942 (0.0009) -[2023-10-16 04:23:29,289][05218] Updated weights for policy 0, policy_version 40952 (0.0008) -[2023-10-16 04:23:32,350][03835] Fps is (10 sec: 13107.8, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 83722240. Throughput: 0: 1809.3, 1: 1798.1. Samples: 20943166. Policy #0 lag: (min: 18.0, avg: 21.7, max: 50.0) -[2023-10-16 04:23:32,351][03835] Avg episode reward: [(0, '6.340'), (1, '6.190')] -[2023-10-16 04:23:32,362][05219] Updated weights for policy 1, policy_version 40810 (0.0008) -[2023-10-16 04:23:32,720][05219] Updated weights for policy 1, policy_version 40820 (0.0009) -[2023-10-16 04:23:33,087][05219] Updated weights for policy 1, policy_version 40830 (0.0009) -[2023-10-16 04:23:33,092][05218] Updated weights for policy 0, policy_version 40962 (0.0009) -[2023-10-16 04:23:33,465][05218] Updated weights for policy 0, policy_version 40972 (0.0009) -[2023-10-16 04:23:33,843][05218] Updated weights for policy 0, policy_version 40982 (0.0010) -[2023-10-16 04:23:34,218][05218] Updated weights for policy 0, policy_version 40992 (0.0008) -[2023-10-16 04:23:36,836][05219] Updated weights for policy 1, policy_version 40840 (0.0008) -[2023-10-16 04:23:37,198][05219] Updated weights for policy 1, policy_version 40850 (0.0010) -[2023-10-16 04:23:37,351][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 83787776. Throughput: 0: 1811.0, 1: 1806.7. Samples: 20965054. Policy #0 lag: (min: 18.0, avg: 21.7, max: 50.0) -[2023-10-16 04:23:37,352][03835] Avg episode reward: [(0, '6.250'), (1, '6.440')] -[2023-10-16 04:23:37,363][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000040992_41975808.pth... -[2023-10-16 04:23:37,393][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000039328_40271872.pth -[2023-10-16 04:23:37,558][05219] Updated weights for policy 1, policy_version 40860 (0.0009) -[2023-10-16 04:23:37,701][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000040864_41844736.pth... -[2023-10-16 04:23:37,734][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000039168_40108032.pth -[2023-10-16 04:23:37,955][05218] Updated weights for policy 0, policy_version 41002 (0.0008) -[2023-10-16 04:23:38,318][05218] Updated weights for policy 0, policy_version 41012 (0.0009) -[2023-10-16 04:23:38,691][05218] Updated weights for policy 0, policy_version 41022 (0.0011) -[2023-10-16 04:23:41,297][05219] Updated weights for policy 1, policy_version 40870 (0.0009) -[2023-10-16 04:23:41,675][05219] Updated weights for policy 1, policy_version 40880 (0.0009) -[2023-10-16 04:23:42,037][05219] Updated weights for policy 1, policy_version 40890 (0.0009) -[2023-10-16 04:23:42,350][03835] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 83886080. Throughput: 0: 1809.3, 1: 1797.6. Samples: 20975486. Policy #0 lag: (min: 18.0, avg: 21.7, max: 50.0) -[2023-10-16 04:23:42,351][03835] Avg episode reward: [(0, '6.710'), (1, '6.090')] -[2023-10-16 04:23:42,562][05218] Updated weights for policy 0, policy_version 41032 (0.0009) -[2023-10-16 04:23:42,942][05218] Updated weights for policy 0, policy_version 41042 (0.0007) -[2023-10-16 04:23:43,322][05218] Updated weights for policy 0, policy_version 41052 (0.0008) -[2023-10-16 04:23:45,622][05219] Updated weights for policy 1, policy_version 40900 (0.0008) -[2023-10-16 04:23:45,988][05219] Updated weights for policy 1, policy_version 40910 (0.0008) -[2023-10-16 04:23:46,355][05219] Updated weights for policy 1, policy_version 40920 (0.0009) -[2023-10-16 04:23:46,931][05218] Updated weights for policy 0, policy_version 41062 (0.0009) -[2023-10-16 04:23:47,308][05218] Updated weights for policy 0, policy_version 41072 (0.0008) -[2023-10-16 04:23:47,350][03835] Fps is (10 sec: 16384.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 83951616. Throughput: 0: 1807.0, 1: 1804.9. Samples: 20997560. Policy #0 lag: (min: 18.0, avg: 21.7, max: 50.0) -[2023-10-16 04:23:47,351][03835] Avg episode reward: [(0, '6.690'), (1, '6.760')] -[2023-10-16 04:23:47,688][05218] Updated weights for policy 0, policy_version 41082 (0.0008) -[2023-10-16 04:23:50,185][05219] Updated weights for policy 1, policy_version 40930 (0.0007) -[2023-10-16 04:23:50,543][05219] Updated weights for policy 1, policy_version 40940 (0.0008) -[2023-10-16 04:23:50,906][05219] Updated weights for policy 1, policy_version 40950 (0.0008) -[2023-10-16 04:23:51,273][05219] Updated weights for policy 1, policy_version 40960 (0.0008) -[2023-10-16 04:23:51,439][05218] Updated weights for policy 0, policy_version 41092 (0.0009) -[2023-10-16 04:23:51,816][05218] Updated weights for policy 0, policy_version 41102 (0.0008) -[2023-10-16 04:23:52,197][05218] Updated weights for policy 0, policy_version 41112 (0.0009) -[2023-10-16 04:23:52,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 84017152. Throughput: 0: 1812.0, 1: 1789.9. Samples: 21017876. Policy #0 lag: (min: 18.0, avg: 21.7, max: 50.0) -[2023-10-16 04:23:52,351][03835] Avg episode reward: [(0, '6.160'), (1, '6.600')] -[2023-10-16 04:23:55,138][05219] Updated weights for policy 1, policy_version 40970 (0.0009) -[2023-10-16 04:23:55,502][05219] Updated weights for policy 1, policy_version 40980 (0.0009) -[2023-10-16 04:23:55,861][05219] Updated weights for policy 1, policy_version 40990 (0.0008) -[2023-10-16 04:23:55,953][05218] Updated weights for policy 0, policy_version 41122 (0.0007) -[2023-10-16 04:23:56,352][05218] Updated weights for policy 0, policy_version 41132 (0.0009) -[2023-10-16 04:23:56,735][05218] Updated weights for policy 0, policy_version 41142 (0.0010) -[2023-10-16 04:23:57,103][05218] Updated weights for policy 0, policy_version 41152 (0.0009) -[2023-10-16 04:23:57,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 84115456. Throughput: 0: 1803.9, 1: 1797.6. Samples: 21029894. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:23:57,351][03835] Avg episode reward: [(0, '6.370'), (1, '6.370')] -[2023-10-16 04:23:59,529][05219] Updated weights for policy 1, policy_version 41000 (0.0008) -[2023-10-16 04:23:59,903][05219] Updated weights for policy 1, policy_version 41010 (0.0009) -[2023-10-16 04:24:00,272][05219] Updated weights for policy 1, policy_version 41020 (0.0008) -[2023-10-16 04:24:00,822][05218] Updated weights for policy 0, policy_version 41162 (0.0009) -[2023-10-16 04:24:01,191][05218] Updated weights for policy 0, policy_version 41172 (0.0007) -[2023-10-16 04:24:01,563][05218] Updated weights for policy 0, policy_version 41182 (0.0008) -[2023-10-16 04:24:02,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 84180992. Throughput: 0: 1812.1, 1: 1795.3. Samples: 21050438. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:24:02,351][03835] Avg episode reward: [(0, '6.620'), (1, '7.100')] -[2023-10-16 04:24:04,203][05219] Updated weights for policy 1, policy_version 41030 (0.0010) -[2023-10-16 04:24:04,560][05219] Updated weights for policy 1, policy_version 41040 (0.0010) -[2023-10-16 04:24:04,923][05219] Updated weights for policy 1, policy_version 41050 (0.0007) -[2023-10-16 04:24:05,472][05218] Updated weights for policy 0, policy_version 41192 (0.0008) -[2023-10-16 04:24:05,843][05218] Updated weights for policy 0, policy_version 41202 (0.0010) -[2023-10-16 04:24:06,222][05218] Updated weights for policy 0, policy_version 41212 (0.0009) -[2023-10-16 04:24:07,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 84246528. Throughput: 0: 1799.1, 1: 1789.2. Samples: 21072184. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:24:07,351][03835] Avg episode reward: [(0, '6.000'), (1, '6.070')] -[2023-10-16 04:24:08,780][05219] Updated weights for policy 1, policy_version 41060 (0.0008) -[2023-10-16 04:24:09,146][05219] Updated weights for policy 1, policy_version 41070 (0.0007) -[2023-10-16 04:24:09,516][05219] Updated weights for policy 1, policy_version 41080 (0.0007) -[2023-10-16 04:24:09,934][05218] Updated weights for policy 0, policy_version 41222 (0.0008) -[2023-10-16 04:24:10,312][05218] Updated weights for policy 0, policy_version 41232 (0.0007) -[2023-10-16 04:24:10,688][05218] Updated weights for policy 0, policy_version 41242 (0.0010) -[2023-10-16 04:24:12,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 84312064. Throughput: 0: 1814.4, 1: 1787.0. Samples: 21082670. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:24:12,351][03835] Avg episode reward: [(0, '6.340'), (1, '6.170')] -[2023-10-16 04:24:13,345][05219] Updated weights for policy 1, policy_version 41090 (0.0007) -[2023-10-16 04:24:13,706][05219] Updated weights for policy 1, policy_version 41100 (0.0010) -[2023-10-16 04:24:14,076][05219] Updated weights for policy 1, policy_version 41110 (0.0010) -[2023-10-16 04:24:14,392][05218] Updated weights for policy 0, policy_version 41252 (0.0009) -[2023-10-16 04:24:14,445][05219] Updated weights for policy 1, policy_version 41120 (0.0008) -[2023-10-16 04:24:14,766][05218] Updated weights for policy 0, policy_version 41262 (0.0009) -[2023-10-16 04:24:15,142][05218] Updated weights for policy 0, policy_version 41272 (0.0009) -[2023-10-16 04:24:17,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 84377600. Throughput: 0: 1791.3, 1: 1791.6. Samples: 21104398. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:24:17,351][03835] Avg episode reward: [(0, '6.190'), (1, '5.390')] -[2023-10-16 04:24:18,109][05219] Updated weights for policy 1, policy_version 41130 (0.0008) -[2023-10-16 04:24:18,469][05219] Updated weights for policy 1, policy_version 41140 (0.0008) -[2023-10-16 04:24:18,799][05218] Updated weights for policy 0, policy_version 41282 (0.0009) -[2023-10-16 04:24:18,833][05219] Updated weights for policy 1, policy_version 41150 (0.0009) -[2023-10-16 04:24:19,171][05218] Updated weights for policy 0, policy_version 41292 (0.0009) -[2023-10-16 04:24:19,546][05218] Updated weights for policy 0, policy_version 41302 (0.0009) -[2023-10-16 04:24:19,934][05218] Updated weights for policy 0, policy_version 41312 (0.0009) -[2023-10-16 04:24:22,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 84443136. Throughput: 0: 1794.8, 1: 1811.9. Samples: 21127356. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:24:22,352][03835] Avg episode reward: [(0, '6.140'), (1, '5.310')] -[2023-10-16 04:24:22,593][05219] Updated weights for policy 1, policy_version 41160 (0.0007) -[2023-10-16 04:24:22,960][05219] Updated weights for policy 1, policy_version 41170 (0.0007) -[2023-10-16 04:24:23,330][05219] Updated weights for policy 1, policy_version 41180 (0.0008) -[2023-10-16 04:24:23,492][05218] Updated weights for policy 0, policy_version 41322 (0.0010) -[2023-10-16 04:24:23,873][05218] Updated weights for policy 0, policy_version 41332 (0.0010) -[2023-10-16 04:24:24,251][05218] Updated weights for policy 0, policy_version 41342 (0.0009) -[2023-10-16 04:24:27,045][05219] Updated weights for policy 1, policy_version 41190 (0.0010) -[2023-10-16 04:24:27,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.6, 300 sec: 14329.1). Total num frames: 84508672. Throughput: 0: 1800.1, 1: 1796.6. Samples: 21137338. Policy #0 lag: (min: 11.0, avg: 11.1, max: 18.0) -[2023-10-16 04:24:27,351][03835] Avg episode reward: [(0, '6.400'), (1, '6.140')] -[2023-10-16 04:24:27,398][05219] Updated weights for policy 1, policy_version 41200 (0.0010) -[2023-10-16 04:24:27,764][05219] Updated weights for policy 1, policy_version 41210 (0.0008) -[2023-10-16 04:24:27,876][05218] Updated weights for policy 0, policy_version 41352 (0.0008) -[2023-10-16 04:24:28,257][05218] Updated weights for policy 0, policy_version 41362 (0.0010) -[2023-10-16 04:24:28,624][05218] Updated weights for policy 0, policy_version 41372 (0.0010) -[2023-10-16 04:24:31,574][05219] Updated weights for policy 1, policy_version 41220 (0.0009) -[2023-10-16 04:24:31,946][05219] Updated weights for policy 1, policy_version 41230 (0.0007) -[2023-10-16 04:24:32,316][05218] Updated weights for policy 0, policy_version 41382 (0.0009) -[2023-10-16 04:24:32,322][05219] Updated weights for policy 1, policy_version 41240 (0.0007) -[2023-10-16 04:24:32,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 84574208. Throughput: 0: 1794.2, 1: 1807.2. Samples: 21159624. Policy #0 lag: (min: 11.0, avg: 11.1, max: 18.0) -[2023-10-16 04:24:32,351][03835] Avg episode reward: [(0, '5.700'), (1, '5.970')] -[2023-10-16 04:24:32,692][05218] Updated weights for policy 0, policy_version 41392 (0.0007) -[2023-10-16 04:24:33,069][05218] Updated weights for policy 0, policy_version 41402 (0.0008) -[2023-10-16 04:24:35,999][05219] Updated weights for policy 1, policy_version 41250 (0.0007) -[2023-10-16 04:24:36,371][05219] Updated weights for policy 1, policy_version 41260 (0.0010) -[2023-10-16 04:24:36,735][05219] Updated weights for policy 1, policy_version 41270 (0.0008) -[2023-10-16 04:24:36,934][05218] Updated weights for policy 0, policy_version 41412 (0.0008) -[2023-10-16 04:24:37,097][05219] Updated weights for policy 1, policy_version 41280 (0.0007) -[2023-10-16 04:24:37,311][05218] Updated weights for policy 0, policy_version 41422 (0.0007) -[2023-10-16 04:24:37,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 84672512. Throughput: 0: 1805.6, 1: 1792.5. Samples: 21179794. Policy #0 lag: (min: 11.0, avg: 11.1, max: 18.0) -[2023-10-16 04:24:37,351][03835] Avg episode reward: [(0, '6.220'), (1, '6.920')] -[2023-10-16 04:24:37,685][05218] Updated weights for policy 0, policy_version 41432 (0.0009) -[2023-10-16 04:24:40,924][05219] Updated weights for policy 1, policy_version 41290 (0.0010) -[2023-10-16 04:24:41,293][05219] Updated weights for policy 1, policy_version 41300 (0.0009) -[2023-10-16 04:24:41,535][05218] Updated weights for policy 0, policy_version 41442 (0.0008) -[2023-10-16 04:24:41,650][05219] Updated weights for policy 1, policy_version 41310 (0.0008) -[2023-10-16 04:24:41,935][05218] Updated weights for policy 0, policy_version 41452 (0.0008) -[2023-10-16 04:24:42,312][05218] Updated weights for policy 0, policy_version 41462 (0.0008) -[2023-10-16 04:24:42,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 84738048. Throughput: 0: 1784.9, 1: 1809.5. Samples: 21191642. Policy #0 lag: (min: 11.0, avg: 11.1, max: 18.0) -[2023-10-16 04:24:42,351][03835] Avg episode reward: [(0, '5.600'), (1, '7.180')] -[2023-10-16 04:24:42,690][05218] Updated weights for policy 0, policy_version 41472 (0.0008) -[2023-10-16 04:24:45,500][05219] Updated weights for policy 1, policy_version 41320 (0.0007) -[2023-10-16 04:24:45,866][05219] Updated weights for policy 1, policy_version 41330 (0.0007) -[2023-10-16 04:24:46,228][05219] Updated weights for policy 1, policy_version 41340 (0.0008) -[2023-10-16 04:24:46,665][05218] Updated weights for policy 0, policy_version 41482 (0.0008) -[2023-10-16 04:24:47,044][05218] Updated weights for policy 0, policy_version 41492 (0.0010) -[2023-10-16 04:24:47,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 84803584. Throughput: 0: 1807.1, 1: 1794.5. Samples: 21212510. Policy #0 lag: (min: 11.0, avg: 11.1, max: 18.0) -[2023-10-16 04:24:47,351][03835] Avg episode reward: [(0, '6.120'), (1, '6.690')] -[2023-10-16 04:24:47,423][05218] Updated weights for policy 0, policy_version 41502 (0.0010) -[2023-10-16 04:24:50,007][05219] Updated weights for policy 1, policy_version 41350 (0.0007) -[2023-10-16 04:24:50,371][05219] Updated weights for policy 1, policy_version 41360 (0.0008) -[2023-10-16 04:24:50,728][05219] Updated weights for policy 1, policy_version 41370 (0.0009) -[2023-10-16 04:24:51,117][05218] Updated weights for policy 0, policy_version 41512 (0.0009) -[2023-10-16 04:24:51,495][05218] Updated weights for policy 0, policy_version 41522 (0.0009) -[2023-10-16 04:24:51,873][05218] Updated weights for policy 0, policy_version 41532 (0.0010) -[2023-10-16 04:24:52,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 84901888. Throughput: 0: 1790.0, 1: 1784.6. Samples: 21233040. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-16 04:24:52,351][03835] Avg episode reward: [(0, '7.110'), (1, '6.520')] -[2023-10-16 04:24:54,488][05219] Updated weights for policy 1, policy_version 41380 (0.0007) -[2023-10-16 04:24:54,849][05219] Updated weights for policy 1, policy_version 41390 (0.0007) -[2023-10-16 04:24:55,219][05219] Updated weights for policy 1, policy_version 41400 (0.0009) -[2023-10-16 04:24:55,653][05218] Updated weights for policy 0, policy_version 41542 (0.0009) -[2023-10-16 04:24:56,031][05218] Updated weights for policy 0, policy_version 41552 (0.0009) -[2023-10-16 04:24:56,406][05218] Updated weights for policy 0, policy_version 41562 (0.0011) -[2023-10-16 04:24:57,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 84967424. Throughput: 0: 1807.5, 1: 1797.9. Samples: 21244910. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-16 04:24:57,351][03835] Avg episode reward: [(0, '6.730'), (1, '6.220')] -[2023-10-16 04:24:58,946][05219] Updated weights for policy 1, policy_version 41410 (0.0009) -[2023-10-16 04:24:59,308][05219] Updated weights for policy 1, policy_version 41420 (0.0008) -[2023-10-16 04:24:59,672][05219] Updated weights for policy 1, policy_version 41430 (0.0008) -[2023-10-16 04:25:00,031][05218] Updated weights for policy 0, policy_version 41572 (0.0010) -[2023-10-16 04:25:00,033][05219] Updated weights for policy 1, policy_version 41440 (0.0008) -[2023-10-16 04:25:00,405][05218] Updated weights for policy 0, policy_version 41582 (0.0009) -[2023-10-16 04:25:00,780][05218] Updated weights for policy 0, policy_version 41592 (0.0009) -[2023-10-16 04:25:02,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 85032960. Throughput: 0: 1788.6, 1: 1783.5. Samples: 21265142. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-16 04:25:02,351][03835] Avg episode reward: [(0, '6.510'), (1, '5.730')] -[2023-10-16 04:25:03,853][05219] Updated weights for policy 1, policy_version 41450 (0.0009) -[2023-10-16 04:25:04,213][05219] Updated weights for policy 1, policy_version 41460 (0.0008) -[2023-10-16 04:25:04,586][05219] Updated weights for policy 1, policy_version 41470 (0.0009) -[2023-10-16 04:25:04,626][05218] Updated weights for policy 0, policy_version 41602 (0.0011) -[2023-10-16 04:25:05,001][05218] Updated weights for policy 0, policy_version 41612 (0.0007) -[2023-10-16 04:25:05,379][05218] Updated weights for policy 0, policy_version 41622 (0.0007) -[2023-10-16 04:25:05,751][05218] Updated weights for policy 0, policy_version 41632 (0.0007) -[2023-10-16 04:25:07,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 85098496. Throughput: 0: 1782.5, 1: 1779.4. Samples: 21287638. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-16 04:25:07,351][03835] Avg episode reward: [(0, '6.290'), (1, '6.370')] -[2023-10-16 04:25:08,385][05219] Updated weights for policy 1, policy_version 41480 (0.0009) -[2023-10-16 04:25:08,749][05219] Updated weights for policy 1, policy_version 41490 (0.0010) -[2023-10-16 04:25:09,109][05219] Updated weights for policy 1, policy_version 41500 (0.0010) -[2023-10-16 04:25:09,601][05218] Updated weights for policy 0, policy_version 41642 (0.0009) -[2023-10-16 04:25:09,979][05218] Updated weights for policy 0, policy_version 41652 (0.0008) -[2023-10-16 04:25:10,353][05218] Updated weights for policy 0, policy_version 41662 (0.0007) -[2023-10-16 04:25:12,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 85164032. Throughput: 0: 1782.8, 1: 1779.3. Samples: 21297634. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-16 04:25:12,351][03835] Avg episode reward: [(0, '6.320'), (1, '6.040')] -[2023-10-16 04:25:12,968][05219] Updated weights for policy 1, policy_version 41510 (0.0007) -[2023-10-16 04:25:13,337][05219] Updated weights for policy 1, policy_version 41520 (0.0007) -[2023-10-16 04:25:13,695][05219] Updated weights for policy 1, policy_version 41530 (0.0007) -[2023-10-16 04:25:13,935][05218] Updated weights for policy 0, policy_version 41672 (0.0010) -[2023-10-16 04:25:14,311][05218] Updated weights for policy 0, policy_version 41682 (0.0010) -[2023-10-16 04:25:14,690][05218] Updated weights for policy 0, policy_version 41692 (0.0009) -[2023-10-16 04:25:17,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 85229568. Throughput: 0: 1782.6, 1: 1779.1. Samples: 21319900. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-16 04:25:17,351][03835] Avg episode reward: [(0, '6.340'), (1, '6.320')] -[2023-10-16 04:25:17,504][05219] Updated weights for policy 1, policy_version 41540 (0.0008) -[2023-10-16 04:25:17,860][05219] Updated weights for policy 1, policy_version 41550 (0.0008) -[2023-10-16 04:25:18,222][05219] Updated weights for policy 1, policy_version 41560 (0.0007) -[2023-10-16 04:25:18,517][05218] Updated weights for policy 0, policy_version 41702 (0.0008) -[2023-10-16 04:25:18,892][05218] Updated weights for policy 0, policy_version 41712 (0.0009) -[2023-10-16 04:25:19,262][05218] Updated weights for policy 0, policy_version 41722 (0.0008) -[2023-10-16 04:25:22,000][05219] Updated weights for policy 1, policy_version 41570 (0.0008) -[2023-10-16 04:25:22,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 85295104. Throughput: 0: 1801.3, 1: 1807.3. Samples: 21342182. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:25:22,351][03835] Avg episode reward: [(0, '6.140'), (1, '6.240')] -[2023-10-16 04:25:22,369][05219] Updated weights for policy 1, policy_version 41580 (0.0009) -[2023-10-16 04:25:22,740][05219] Updated weights for policy 1, policy_version 41590 (0.0008) -[2023-10-16 04:25:22,986][05218] Updated weights for policy 0, policy_version 41732 (0.0008) -[2023-10-16 04:25:23,102][05219] Updated weights for policy 1, policy_version 41600 (0.0008) -[2023-10-16 04:25:23,347][05218] Updated weights for policy 0, policy_version 41742 (0.0009) -[2023-10-16 04:25:23,716][05218] Updated weights for policy 0, policy_version 41752 (0.0007) -[2023-10-16 04:25:26,915][05219] Updated weights for policy 1, policy_version 41610 (0.0007) -[2023-10-16 04:25:27,282][05219] Updated weights for policy 1, policy_version 41620 (0.0009) -[2023-10-16 04:25:27,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 85360640. Throughput: 0: 1786.6, 1: 1779.9. Samples: 21352134. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:25:27,351][03835] Avg episode reward: [(0, '7.190'), (1, '6.900')] -[2023-10-16 04:25:27,499][05218] Updated weights for policy 0, policy_version 41762 (0.0008) -[2023-10-16 04:25:27,648][05219] Updated weights for policy 1, policy_version 41630 (0.0007) -[2023-10-16 04:25:27,909][05218] Updated weights for policy 0, policy_version 41772 (0.0009) -[2023-10-16 04:25:28,289][05218] Updated weights for policy 0, policy_version 41782 (0.0010) -[2023-10-16 04:25:28,663][05218] Updated weights for policy 0, policy_version 41792 (0.0010) -[2023-10-16 04:25:31,229][05219] Updated weights for policy 1, policy_version 41640 (0.0008) -[2023-10-16 04:25:31,596][05219] Updated weights for policy 1, policy_version 41650 (0.0008) -[2023-10-16 04:25:31,973][05219] Updated weights for policy 1, policy_version 41660 (0.0009) -[2023-10-16 04:25:32,247][05218] Updated weights for policy 0, policy_version 41802 (0.0008) -[2023-10-16 04:25:32,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 85458944. Throughput: 0: 1793.3, 1: 1804.4. Samples: 21374410. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:25:32,351][03835] Avg episode reward: [(0, '6.330'), (1, '6.540')] -[2023-10-16 04:25:32,626][05218] Updated weights for policy 0, policy_version 41812 (0.0010) -[2023-10-16 04:25:33,003][05218] Updated weights for policy 0, policy_version 41822 (0.0010) -[2023-10-16 04:25:35,711][05219] Updated weights for policy 1, policy_version 41670 (0.0008) -[2023-10-16 04:25:36,073][05219] Updated weights for policy 1, policy_version 41680 (0.0008) -[2023-10-16 04:25:36,446][05219] Updated weights for policy 1, policy_version 41690 (0.0009) -[2023-10-16 04:25:36,747][05218] Updated weights for policy 0, policy_version 41832 (0.0009) -[2023-10-16 04:25:37,129][05218] Updated weights for policy 0, policy_version 41842 (0.0009) -[2023-10-16 04:25:37,351][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 85524480. Throughput: 0: 1797.8, 1: 1784.5. Samples: 21394248. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:25:37,352][03835] Avg episode reward: [(0, '6.330'), (1, '6.030')] -[2023-10-16 04:25:37,362][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000041696_42696704.pth... -[2023-10-16 04:25:37,394][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000040000_40960000.pth -[2023-10-16 04:25:37,398][04891] Saving a milestone ./train_atari/atari_timepilot_APPO/checkpoint_p1/milestones/checkpoint_000041696_42696704.pth -[2023-10-16 04:25:37,499][05218] Updated weights for policy 0, policy_version 41852 (0.0010) -[2023-10-16 04:25:37,639][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000041856_42860544.pth... -[2023-10-16 04:25:37,668][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000040160_41123840.pth -[2023-10-16 04:25:37,671][04766] Saving a milestone ./train_atari/atari_timepilot_APPO/checkpoint_p0/milestones/checkpoint_000041856_42860544.pth -[2023-10-16 04:25:40,196][05219] Updated weights for policy 1, policy_version 41700 (0.0009) -[2023-10-16 04:25:40,565][05219] Updated weights for policy 1, policy_version 41710 (0.0009) -[2023-10-16 04:25:40,926][05219] Updated weights for policy 1, policy_version 41720 (0.0008) -[2023-10-16 04:25:41,206][05218] Updated weights for policy 0, policy_version 41862 (0.0008) -[2023-10-16 04:25:41,581][05218] Updated weights for policy 0, policy_version 41872 (0.0010) -[2023-10-16 04:25:41,958][05218] Updated weights for policy 0, policy_version 41882 (0.0009) -[2023-10-16 04:25:42,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 85622784. Throughput: 0: 1786.3, 1: 1801.9. Samples: 21406380. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:25:42,351][03835] Avg episode reward: [(0, '7.120'), (1, '6.490')] -[2023-10-16 04:25:44,880][05219] Updated weights for policy 1, policy_version 41730 (0.0008) -[2023-10-16 04:25:45,237][05219] Updated weights for policy 1, policy_version 41740 (0.0011) -[2023-10-16 04:25:45,610][05219] Updated weights for policy 1, policy_version 41750 (0.0010) -[2023-10-16 04:25:45,842][05218] Updated weights for policy 0, policy_version 41892 (0.0008) -[2023-10-16 04:25:45,968][05219] Updated weights for policy 1, policy_version 41760 (0.0009) -[2023-10-16 04:25:46,220][05218] Updated weights for policy 0, policy_version 41902 (0.0009) -[2023-10-16 04:25:46,594][05218] Updated weights for policy 0, policy_version 41912 (0.0010) -[2023-10-16 04:25:47,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 85688320. Throughput: 0: 1802.9, 1: 1782.7. Samples: 21426496. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:25:47,351][03835] Avg episode reward: [(0, '6.730'), (1, '6.000')] -[2023-10-16 04:25:49,667][05219] Updated weights for policy 1, policy_version 41770 (0.0010) -[2023-10-16 04:25:50,034][05219] Updated weights for policy 1, policy_version 41780 (0.0008) -[2023-10-16 04:25:50,352][05218] Updated weights for policy 0, policy_version 41922 (0.0010) -[2023-10-16 04:25:50,392][05219] Updated weights for policy 1, policy_version 41790 (0.0007) -[2023-10-16 04:25:50,740][05218] Updated weights for policy 0, policy_version 41932 (0.0009) -[2023-10-16 04:25:51,110][05218] Updated weights for policy 0, policy_version 41942 (0.0008) -[2023-10-16 04:25:51,486][05218] Updated weights for policy 0, policy_version 41952 (0.0007) -[2023-10-16 04:25:52,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 85753856. Throughput: 0: 1784.2, 1: 1782.6. Samples: 21448144. Policy #0 lag: (min: 9.0, avg: 15.1, max: 41.0) -[2023-10-16 04:25:52,351][03835] Avg episode reward: [(0, '6.330'), (1, '5.950')] -[2023-10-16 04:25:54,204][05219] Updated weights for policy 1, policy_version 41800 (0.0009) -[2023-10-16 04:25:54,568][05219] Updated weights for policy 1, policy_version 41810 (0.0009) -[2023-10-16 04:25:54,936][05219] Updated weights for policy 1, policy_version 41820 (0.0007) -[2023-10-16 04:25:55,268][05218] Updated weights for policy 0, policy_version 41962 (0.0009) -[2023-10-16 04:25:55,635][05218] Updated weights for policy 0, policy_version 41972 (0.0009) -[2023-10-16 04:25:56,007][05218] Updated weights for policy 0, policy_version 41982 (0.0010) -[2023-10-16 04:25:57,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 85819392. Throughput: 0: 1798.9, 1: 1781.0. Samples: 21458730. Policy #0 lag: (min: 9.0, avg: 15.1, max: 41.0) -[2023-10-16 04:25:57,351][03835] Avg episode reward: [(0, '7.080'), (1, '6.110')] -[2023-10-16 04:25:58,547][05219] Updated weights for policy 1, policy_version 41830 (0.0007) -[2023-10-16 04:25:58,907][05219] Updated weights for policy 1, policy_version 41840 (0.0008) -[2023-10-16 04:25:59,274][05219] Updated weights for policy 1, policy_version 41850 (0.0008) -[2023-10-16 04:25:59,698][05218] Updated weights for policy 0, policy_version 41992 (0.0009) -[2023-10-16 04:26:00,069][05218] Updated weights for policy 0, policy_version 42002 (0.0009) -[2023-10-16 04:26:00,443][05218] Updated weights for policy 0, policy_version 42012 (0.0008) -[2023-10-16 04:26:02,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.2). Total num frames: 85884928. Throughput: 0: 1780.8, 1: 1788.5. Samples: 21480518. Policy #0 lag: (min: 9.0, avg: 15.1, max: 41.0) -[2023-10-16 04:26:02,351][03835] Avg episode reward: [(0, '6.580'), (1, '5.600')] -[2023-10-16 04:26:02,969][05219] Updated weights for policy 1, policy_version 41860 (0.0009) -[2023-10-16 04:26:03,330][05219] Updated weights for policy 1, policy_version 41870 (0.0009) -[2023-10-16 04:26:03,690][05219] Updated weights for policy 1, policy_version 41880 (0.0010) -[2023-10-16 04:26:04,239][05218] Updated weights for policy 0, policy_version 42022 (0.0008) -[2023-10-16 04:26:04,614][05218] Updated weights for policy 0, policy_version 42032 (0.0008) -[2023-10-16 04:26:04,990][05218] Updated weights for policy 0, policy_version 42042 (0.0008) -[2023-10-16 04:26:07,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 85950464. Throughput: 0: 1780.4, 1: 1793.8. Samples: 21503022. Policy #0 lag: (min: 9.0, avg: 15.1, max: 41.0) -[2023-10-16 04:26:07,352][03835] Avg episode reward: [(0, '6.430'), (1, '5.540')] -[2023-10-16 04:26:07,630][05219] Updated weights for policy 1, policy_version 41890 (0.0009) -[2023-10-16 04:26:07,998][05219] Updated weights for policy 1, policy_version 41900 (0.0007) -[2023-10-16 04:26:08,365][05219] Updated weights for policy 1, policy_version 41910 (0.0007) -[2023-10-16 04:26:08,732][05219] Updated weights for policy 1, policy_version 41920 (0.0007) -[2023-10-16 04:26:08,811][05218] Updated weights for policy 0, policy_version 42052 (0.0009) -[2023-10-16 04:26:09,184][05218] Updated weights for policy 0, policy_version 42062 (0.0008) -[2023-10-16 04:26:09,574][05218] Updated weights for policy 0, policy_version 42072 (0.0007) -[2023-10-16 04:26:12,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 86016000. Throughput: 0: 1782.8, 1: 1787.8. Samples: 21512810. Policy #0 lag: (min: 9.0, avg: 15.1, max: 41.0) -[2023-10-16 04:26:12,351][03835] Avg episode reward: [(0, '6.120'), (1, '6.380')] -[2023-10-16 04:26:12,544][05219] Updated weights for policy 1, policy_version 41930 (0.0008) -[2023-10-16 04:26:12,909][05219] Updated weights for policy 1, policy_version 41940 (0.0010) -[2023-10-16 04:26:13,264][05219] Updated weights for policy 1, policy_version 41950 (0.0007) -[2023-10-16 04:26:13,493][05218] Updated weights for policy 0, policy_version 42082 (0.0007) -[2023-10-16 04:26:13,864][05218] Updated weights for policy 0, policy_version 42092 (0.0007) -[2023-10-16 04:26:14,237][05218] Updated weights for policy 0, policy_version 42102 (0.0008) -[2023-10-16 04:26:14,613][05218] Updated weights for policy 0, policy_version 42112 (0.0007) -[2023-10-16 04:26:16,819][05219] Updated weights for policy 1, policy_version 41960 (0.0008) -[2023-10-16 04:26:17,182][05219] Updated weights for policy 1, policy_version 41970 (0.0007) -[2023-10-16 04:26:17,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 86081536. Throughput: 0: 1771.5, 1: 1792.1. Samples: 21534772. Policy #0 lag: (min: 9.0, avg: 15.1, max: 41.0) -[2023-10-16 04:26:17,351][03835] Avg episode reward: [(0, '6.380'), (1, '6.610')] -[2023-10-16 04:26:17,548][05219] Updated weights for policy 1, policy_version 41980 (0.0008) -[2023-10-16 04:26:18,415][05218] Updated weights for policy 0, policy_version 42122 (0.0007) -[2023-10-16 04:26:18,799][05218] Updated weights for policy 0, policy_version 42132 (0.0008) -[2023-10-16 04:26:19,175][05218] Updated weights for policy 0, policy_version 42142 (0.0009) -[2023-10-16 04:26:21,253][05219] Updated weights for policy 1, policy_version 41990 (0.0009) -[2023-10-16 04:26:21,607][05219] Updated weights for policy 1, policy_version 42000 (0.0009) -[2023-10-16 04:26:21,970][05219] Updated weights for policy 1, policy_version 42010 (0.0007) -[2023-10-16 04:26:22,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 86179840. Throughput: 0: 1799.5, 1: 1795.8. Samples: 21556036. Policy #0 lag: (min: 16.0, avg: 42.6, max: 48.0) -[2023-10-16 04:26:22,352][03835] Avg episode reward: [(0, '6.230'), (1, '6.340')] -[2023-10-16 04:26:22,791][05218] Updated weights for policy 0, policy_version 42152 (0.0008) -[2023-10-16 04:26:23,160][05218] Updated weights for policy 0, policy_version 42162 (0.0007) -[2023-10-16 04:26:23,536][05218] Updated weights for policy 0, policy_version 42172 (0.0011) -[2023-10-16 04:26:25,721][05219] Updated weights for policy 1, policy_version 42020 (0.0007) -[2023-10-16 04:26:26,086][05219] Updated weights for policy 1, policy_version 42030 (0.0008) -[2023-10-16 04:26:26,442][05219] Updated weights for policy 1, policy_version 42040 (0.0007) -[2023-10-16 04:26:27,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 86245376. Throughput: 0: 1770.8, 1: 1799.4. Samples: 21567040. Policy #0 lag: (min: 16.0, avg: 42.6, max: 48.0) -[2023-10-16 04:26:27,351][03835] Avg episode reward: [(0, '6.190'), (1, '5.860')] -[2023-10-16 04:26:27,442][05218] Updated weights for policy 0, policy_version 42182 (0.0007) -[2023-10-16 04:26:27,817][05218] Updated weights for policy 0, policy_version 42192 (0.0008) -[2023-10-16 04:26:28,192][05218] Updated weights for policy 0, policy_version 42202 (0.0009) -[2023-10-16 04:26:30,256][05219] Updated weights for policy 1, policy_version 42050 (0.0007) -[2023-10-16 04:26:30,613][05219] Updated weights for policy 1, policy_version 42060 (0.0010) -[2023-10-16 04:26:30,980][05219] Updated weights for policy 1, policy_version 42070 (0.0010) -[2023-10-16 04:26:31,346][05219] Updated weights for policy 1, policy_version 42080 (0.0010) -[2023-10-16 04:26:31,867][05218] Updated weights for policy 0, policy_version 42212 (0.0007) -[2023-10-16 04:26:32,250][05218] Updated weights for policy 0, policy_version 42222 (0.0007) -[2023-10-16 04:26:32,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 86310912. Throughput: 0: 1789.6, 1: 1806.5. Samples: 21588318. Policy #0 lag: (min: 16.0, avg: 42.6, max: 48.0) -[2023-10-16 04:26:32,351][03835] Avg episode reward: [(0, '6.530'), (1, '6.040')] -[2023-10-16 04:26:32,620][05218] Updated weights for policy 0, policy_version 42232 (0.0008) -[2023-10-16 04:26:35,143][05219] Updated weights for policy 1, policy_version 42090 (0.0008) -[2023-10-16 04:26:35,518][05219] Updated weights for policy 1, policy_version 42100 (0.0008) -[2023-10-16 04:26:35,884][05219] Updated weights for policy 1, policy_version 42110 (0.0008) -[2023-10-16 04:26:36,308][05218] Updated weights for policy 0, policy_version 42242 (0.0010) -[2023-10-16 04:26:36,686][05218] Updated weights for policy 0, policy_version 42252 (0.0008) -[2023-10-16 04:26:37,068][05218] Updated weights for policy 0, policy_version 42262 (0.0009) -[2023-10-16 04:26:37,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 86376448. Throughput: 0: 1779.4, 1: 1805.5. Samples: 21609464. Policy #0 lag: (min: 16.0, avg: 42.6, max: 48.0) -[2023-10-16 04:26:37,352][03835] Avg episode reward: [(0, '6.090'), (1, '6.380')] -[2023-10-16 04:26:37,448][05218] Updated weights for policy 0, policy_version 42272 (0.0009) -[2023-10-16 04:26:39,432][05219] Updated weights for policy 1, policy_version 42120 (0.0007) -[2023-10-16 04:26:39,798][05219] Updated weights for policy 1, policy_version 42130 (0.0007) -[2023-10-16 04:26:40,164][05219] Updated weights for policy 1, policy_version 42140 (0.0007) -[2023-10-16 04:26:41,111][05218] Updated weights for policy 0, policy_version 42282 (0.0007) -[2023-10-16 04:26:41,484][05218] Updated weights for policy 0, policy_version 42292 (0.0008) -[2023-10-16 04:26:41,857][05218] Updated weights for policy 0, policy_version 42302 (0.0009) -[2023-10-16 04:26:42,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 86474752. Throughput: 0: 1791.8, 1: 1810.9. Samples: 21620850. Policy #0 lag: (min: 16.0, avg: 42.6, max: 48.0) -[2023-10-16 04:26:42,351][03835] Avg episode reward: [(0, '6.060'), (1, '6.530')] -[2023-10-16 04:26:43,784][05219] Updated weights for policy 1, policy_version 42150 (0.0009) -[2023-10-16 04:26:44,158][05219] Updated weights for policy 1, policy_version 42160 (0.0009) -[2023-10-16 04:26:44,522][05219] Updated weights for policy 1, policy_version 42170 (0.0009) -[2023-10-16 04:26:45,539][05218] Updated weights for policy 0, policy_version 42312 (0.0009) -[2023-10-16 04:26:45,909][05218] Updated weights for policy 0, policy_version 42322 (0.0010) -[2023-10-16 04:26:46,284][05218] Updated weights for policy 0, policy_version 42332 (0.0010) -[2023-10-16 04:26:47,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 86540288. Throughput: 0: 1782.7, 1: 1801.1. Samples: 21641790. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-16 04:26:47,351][03835] Avg episode reward: [(0, '6.130'), (1, '6.340')] -[2023-10-16 04:26:48,212][05219] Updated weights for policy 1, policy_version 42180 (0.0009) -[2023-10-16 04:26:48,582][05219] Updated weights for policy 1, policy_version 42190 (0.0009) -[2023-10-16 04:26:48,941][05219] Updated weights for policy 1, policy_version 42200 (0.0008) -[2023-10-16 04:26:50,116][05218] Updated weights for policy 0, policy_version 42342 (0.0008) -[2023-10-16 04:26:50,495][05218] Updated weights for policy 0, policy_version 42352 (0.0010) -[2023-10-16 04:26:50,866][05218] Updated weights for policy 0, policy_version 42362 (0.0011) -[2023-10-16 04:26:52,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 86605824. Throughput: 0: 1775.3, 1: 1799.6. Samples: 21663890. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-16 04:26:52,352][03835] Avg episode reward: [(0, '6.800'), (1, '6.500')] -[2023-10-16 04:26:52,801][05219] Updated weights for policy 1, policy_version 42210 (0.0009) -[2023-10-16 04:26:53,167][05219] Updated weights for policy 1, policy_version 42220 (0.0008) -[2023-10-16 04:26:53,533][05219] Updated weights for policy 1, policy_version 42230 (0.0007) -[2023-10-16 04:26:53,889][05219] Updated weights for policy 1, policy_version 42240 (0.0007) -[2023-10-16 04:26:54,569][05218] Updated weights for policy 0, policy_version 42372 (0.0011) -[2023-10-16 04:26:54,950][05218] Updated weights for policy 0, policy_version 42382 (0.0009) -[2023-10-16 04:26:55,337][05218] Updated weights for policy 0, policy_version 42392 (0.0009) -[2023-10-16 04:26:57,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 86671360. Throughput: 0: 1782.9, 1: 1797.4. Samples: 21673924. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-16 04:26:57,351][03835] Avg episode reward: [(0, '7.010'), (1, '5.830')] -[2023-10-16 04:26:57,737][05219] Updated weights for policy 1, policy_version 42250 (0.0008) -[2023-10-16 04:26:58,115][05219] Updated weights for policy 1, policy_version 42260 (0.0008) -[2023-10-16 04:26:58,481][05219] Updated weights for policy 1, policy_version 42270 (0.0008) -[2023-10-16 04:26:59,114][05218] Updated weights for policy 0, policy_version 42402 (0.0010) -[2023-10-16 04:26:59,496][05218] Updated weights for policy 0, policy_version 42412 (0.0008) -[2023-10-16 04:26:59,875][05218] Updated weights for policy 0, policy_version 42422 (0.0008) -[2023-10-16 04:27:00,242][05218] Updated weights for policy 0, policy_version 42432 (0.0008) -[2023-10-16 04:27:02,296][05219] Updated weights for policy 1, policy_version 42280 (0.0007) -[2023-10-16 04:27:02,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 86736896. Throughput: 0: 1778.8, 1: 1799.3. Samples: 21695784. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-16 04:27:02,351][03835] Avg episode reward: [(0, '6.970'), (1, '5.810')] -[2023-10-16 04:27:02,660][05219] Updated weights for policy 1, policy_version 42290 (0.0007) -[2023-10-16 04:27:03,022][05219] Updated weights for policy 1, policy_version 42300 (0.0007) -[2023-10-16 04:27:03,957][05218] Updated weights for policy 0, policy_version 42442 (0.0007) -[2023-10-16 04:27:04,331][05218] Updated weights for policy 0, policy_version 42452 (0.0007) -[2023-10-16 04:27:04,703][05218] Updated weights for policy 0, policy_version 42462 (0.0008) -[2023-10-16 04:27:06,901][05219] Updated weights for policy 1, policy_version 42310 (0.0008) -[2023-10-16 04:27:07,268][05219] Updated weights for policy 1, policy_version 42320 (0.0009) -[2023-10-16 04:27:07,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 86802432. Throughput: 0: 1777.6, 1: 1814.1. Samples: 21717666. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-16 04:27:07,351][03835] Avg episode reward: [(0, '6.680'), (1, '6.100')] -[2023-10-16 04:27:07,632][05219] Updated weights for policy 1, policy_version 42330 (0.0010) -[2023-10-16 04:27:08,458][05218] Updated weights for policy 0, policy_version 42472 (0.0009) -[2023-10-16 04:27:08,838][05218] Updated weights for policy 0, policy_version 42482 (0.0008) -[2023-10-16 04:27:09,207][05218] Updated weights for policy 0, policy_version 42492 (0.0010) -[2023-10-16 04:27:11,259][05219] Updated weights for policy 1, policy_version 42340 (0.0007) -[2023-10-16 04:27:11,629][05219] Updated weights for policy 1, policy_version 42350 (0.0009) -[2023-10-16 04:27:11,992][05219] Updated weights for policy 1, policy_version 42360 (0.0009) -[2023-10-16 04:27:12,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 86900736. Throughput: 0: 1781.3, 1: 1799.5. Samples: 21728174. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-16 04:27:12,351][03835] Avg episode reward: [(0, '6.570'), (1, '6.350')] -[2023-10-16 04:27:13,065][05218] Updated weights for policy 0, policy_version 42502 (0.0010) -[2023-10-16 04:27:13,436][05218] Updated weights for policy 0, policy_version 42512 (0.0008) -[2023-10-16 04:27:13,817][05218] Updated weights for policy 0, policy_version 42522 (0.0009) -[2023-10-16 04:27:15,745][05219] Updated weights for policy 1, policy_version 42370 (0.0009) -[2023-10-16 04:27:16,112][05219] Updated weights for policy 1, policy_version 42380 (0.0010) -[2023-10-16 04:27:16,469][05219] Updated weights for policy 1, policy_version 42390 (0.0007) -[2023-10-16 04:27:16,838][05219] Updated weights for policy 1, policy_version 42400 (0.0007) -[2023-10-16 04:27:17,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 86966272. Throughput: 0: 1783.2, 1: 1809.7. Samples: 21749998. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-16 04:27:17,351][03835] Avg episode reward: [(0, '5.850'), (1, '5.950')] -[2023-10-16 04:27:17,611][05218] Updated weights for policy 0, policy_version 42532 (0.0008) -[2023-10-16 04:27:17,985][05218] Updated weights for policy 0, policy_version 42542 (0.0009) -[2023-10-16 04:27:18,360][05218] Updated weights for policy 0, policy_version 42552 (0.0009) -[2023-10-16 04:27:20,575][05219] Updated weights for policy 1, policy_version 42410 (0.0008) -[2023-10-16 04:27:20,937][05219] Updated weights for policy 1, policy_version 42420 (0.0010) -[2023-10-16 04:27:21,307][05219] Updated weights for policy 1, policy_version 42430 (0.0009) -[2023-10-16 04:27:22,115][05218] Updated weights for policy 0, policy_version 42562 (0.0009) -[2023-10-16 04:27:22,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 87031808. Throughput: 0: 1802.1, 1: 1790.5. Samples: 21771130. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-16 04:27:22,351][03835] Avg episode reward: [(0, '6.170'), (1, '5.800')] -[2023-10-16 04:27:22,484][05218] Updated weights for policy 0, policy_version 42572 (0.0007) -[2023-10-16 04:27:22,864][05218] Updated weights for policy 0, policy_version 42582 (0.0007) -[2023-10-16 04:27:23,237][05218] Updated weights for policy 0, policy_version 42592 (0.0008) -[2023-10-16 04:27:24,998][05219] Updated weights for policy 1, policy_version 42440 (0.0009) -[2023-10-16 04:27:25,359][05219] Updated weights for policy 1, policy_version 42450 (0.0007) -[2023-10-16 04:27:25,729][05219] Updated weights for policy 1, policy_version 42460 (0.0010) -[2023-10-16 04:27:27,033][05218] Updated weights for policy 0, policy_version 42602 (0.0010) -[2023-10-16 04:27:27,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 87097344. Throughput: 0: 1778.4, 1: 1811.2. Samples: 21782380. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-16 04:27:27,351][03835] Avg episode reward: [(0, '6.100'), (1, '6.030')] -[2023-10-16 04:27:27,407][05218] Updated weights for policy 0, policy_version 42612 (0.0008) -[2023-10-16 04:27:27,789][05218] Updated weights for policy 0, policy_version 42622 (0.0009) -[2023-10-16 04:27:29,529][05219] Updated weights for policy 1, policy_version 42470 (0.0008) -[2023-10-16 04:27:29,890][05219] Updated weights for policy 1, policy_version 42480 (0.0007) -[2023-10-16 04:27:30,259][05219] Updated weights for policy 1, policy_version 42490 (0.0008) -[2023-10-16 04:27:31,315][05218] Updated weights for policy 0, policy_version 42632 (0.0010) -[2023-10-16 04:27:31,687][05218] Updated weights for policy 0, policy_version 42642 (0.0009) -[2023-10-16 04:27:32,072][05218] Updated weights for policy 0, policy_version 42652 (0.0010) -[2023-10-16 04:27:32,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 87195648. Throughput: 0: 1808.6, 1: 1793.6. Samples: 21803888. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-16 04:27:32,351][03835] Avg episode reward: [(0, '5.540'), (1, '6.170')] -[2023-10-16 04:27:34,095][05219] Updated weights for policy 1, policy_version 42500 (0.0007) -[2023-10-16 04:27:34,467][05219] Updated weights for policy 1, policy_version 42510 (0.0008) -[2023-10-16 04:27:34,832][05219] Updated weights for policy 1, policy_version 42520 (0.0009) -[2023-10-16 04:27:35,745][05218] Updated weights for policy 0, policy_version 42662 (0.0008) -[2023-10-16 04:27:36,109][05218] Updated weights for policy 0, policy_version 42672 (0.0007) -[2023-10-16 04:27:36,483][05218] Updated weights for policy 0, policy_version 42682 (0.0007) -[2023-10-16 04:27:37,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 87261184. Throughput: 0: 1796.2, 1: 1790.0. Samples: 21825272. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-16 04:27:37,351][03835] Avg episode reward: [(0, '6.460'), (1, '5.930')] -[2023-10-16 04:27:37,361][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000042688_43712512.pth... -[2023-10-16 04:27:37,361][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000042528_43548672.pth... -[2023-10-16 04:27:37,393][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000040992_41975808.pth -[2023-10-16 04:27:37,401][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000040864_41844736.pth -[2023-10-16 04:27:38,579][05219] Updated weights for policy 1, policy_version 42530 (0.0008) -[2023-10-16 04:27:38,940][05219] Updated weights for policy 1, policy_version 42540 (0.0007) -[2023-10-16 04:27:39,316][05219] Updated weights for policy 1, policy_version 42550 (0.0009) -[2023-10-16 04:27:39,681][05219] Updated weights for policy 1, policy_version 42560 (0.0009) -[2023-10-16 04:27:40,169][05218] Updated weights for policy 0, policy_version 42692 (0.0009) -[2023-10-16 04:27:40,553][05218] Updated weights for policy 0, policy_version 42702 (0.0010) -[2023-10-16 04:27:40,917][05218] Updated weights for policy 0, policy_version 42712 (0.0010) -[2023-10-16 04:27:42,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 87326720. Throughput: 0: 1812.1, 1: 1789.4. Samples: 21835992. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-16 04:27:42,351][03835] Avg episode reward: [(0, '6.660'), (1, '6.630')] -[2023-10-16 04:27:43,373][05219] Updated weights for policy 1, policy_version 42570 (0.0010) -[2023-10-16 04:27:43,725][05219] Updated weights for policy 1, policy_version 42580 (0.0010) -[2023-10-16 04:27:44,090][05219] Updated weights for policy 1, policy_version 42590 (0.0009) -[2023-10-16 04:27:44,737][05218] Updated weights for policy 0, policy_version 42722 (0.0010) -[2023-10-16 04:27:45,107][05218] Updated weights for policy 0, policy_version 42732 (0.0009) -[2023-10-16 04:27:45,483][05218] Updated weights for policy 0, policy_version 42742 (0.0009) -[2023-10-16 04:27:45,859][05218] Updated weights for policy 0, policy_version 42752 (0.0010) -[2023-10-16 04:27:47,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 87392256. Throughput: 0: 1799.1, 1: 1799.1. Samples: 21857700. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-16 04:27:47,351][03835] Avg episode reward: [(0, '6.190'), (1, '5.800')] -[2023-10-16 04:27:47,926][05219] Updated weights for policy 1, policy_version 42600 (0.0008) -[2023-10-16 04:27:48,280][05219] Updated weights for policy 1, policy_version 42610 (0.0010) -[2023-10-16 04:27:48,645][05219] Updated weights for policy 1, policy_version 42620 (0.0009) -[2023-10-16 04:27:49,551][05218] Updated weights for policy 0, policy_version 42762 (0.0010) -[2023-10-16 04:27:49,919][05218] Updated weights for policy 0, policy_version 42772 (0.0009) -[2023-10-16 04:27:50,298][05218] Updated weights for policy 0, policy_version 42782 (0.0009) -[2023-10-16 04:27:52,243][05219] Updated weights for policy 1, policy_version 42630 (0.0009) -[2023-10-16 04:27:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 87457792. Throughput: 0: 1800.8, 1: 1804.0. Samples: 21879878. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-16 04:27:52,351][03835] Avg episode reward: [(0, '6.790'), (1, '6.250')] -[2023-10-16 04:27:52,599][05219] Updated weights for policy 1, policy_version 42640 (0.0008) -[2023-10-16 04:27:52,958][05219] Updated weights for policy 1, policy_version 42650 (0.0007) -[2023-10-16 04:27:53,874][05218] Updated weights for policy 0, policy_version 42792 (0.0009) -[2023-10-16 04:27:54,249][05218] Updated weights for policy 0, policy_version 42802 (0.0007) -[2023-10-16 04:27:54,625][05218] Updated weights for policy 0, policy_version 42812 (0.0007) -[2023-10-16 04:27:56,759][05219] Updated weights for policy 1, policy_version 42660 (0.0007) -[2023-10-16 04:27:57,134][05219] Updated weights for policy 1, policy_version 42670 (0.0008) -[2023-10-16 04:27:57,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 87523328. Throughput: 0: 1803.7, 1: 1790.1. Samples: 21889896. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-16 04:27:57,351][03835] Avg episode reward: [(0, '6.180'), (1, '6.590')] -[2023-10-16 04:27:57,501][05219] Updated weights for policy 1, policy_version 42680 (0.0009) -[2023-10-16 04:27:58,324][05218] Updated weights for policy 0, policy_version 42822 (0.0008) -[2023-10-16 04:27:58,705][05218] Updated weights for policy 0, policy_version 42832 (0.0007) -[2023-10-16 04:27:59,081][05218] Updated weights for policy 0, policy_version 42842 (0.0010) -[2023-10-16 04:28:01,163][05219] Updated weights for policy 1, policy_version 42690 (0.0010) -[2023-10-16 04:28:01,525][05219] Updated weights for policy 1, policy_version 42700 (0.0009) -[2023-10-16 04:28:01,893][05219] Updated weights for policy 1, policy_version 42710 (0.0008) -[2023-10-16 04:28:02,249][05219] Updated weights for policy 1, policy_version 42720 (0.0007) -[2023-10-16 04:28:02,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 87621632. Throughput: 0: 1802.8, 1: 1806.8. Samples: 21912428. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-16 04:28:02,351][03835] Avg episode reward: [(0, '6.480'), (1, '6.010')] -[2023-10-16 04:28:02,894][05218] Updated weights for policy 0, policy_version 42852 (0.0010) -[2023-10-16 04:28:03,272][05218] Updated weights for policy 0, policy_version 42862 (0.0010) -[2023-10-16 04:28:03,657][05218] Updated weights for policy 0, policy_version 42872 (0.0009) -[2023-10-16 04:28:05,961][05219] Updated weights for policy 1, policy_version 42730 (0.0007) -[2023-10-16 04:28:06,325][05219] Updated weights for policy 1, policy_version 42740 (0.0008) -[2023-10-16 04:28:06,692][05219] Updated weights for policy 1, policy_version 42750 (0.0008) -[2023-10-16 04:28:07,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 87687168. Throughput: 0: 1812.9, 1: 1799.9. Samples: 21933704. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-16 04:28:07,351][03835] Avg episode reward: [(0, '6.630'), (1, '6.400')] -[2023-10-16 04:28:07,478][05218] Updated weights for policy 0, policy_version 42882 (0.0008) -[2023-10-16 04:28:07,858][05218] Updated weights for policy 0, policy_version 42892 (0.0011) -[2023-10-16 04:28:08,232][05218] Updated weights for policy 0, policy_version 42902 (0.0007) -[2023-10-16 04:28:08,610][05218] Updated weights for policy 0, policy_version 42912 (0.0008) -[2023-10-16 04:28:10,425][05219] Updated weights for policy 1, policy_version 42760 (0.0008) -[2023-10-16 04:28:10,782][05219] Updated weights for policy 1, policy_version 42770 (0.0008) -[2023-10-16 04:28:11,155][05219] Updated weights for policy 1, policy_version 42780 (0.0008) -[2023-10-16 04:28:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 87752704. Throughput: 0: 1805.6, 1: 1806.4. Samples: 21944924. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-16 04:28:12,351][03835] Avg episode reward: [(0, '6.100'), (1, '6.090')] -[2023-10-16 04:28:12,472][05218] Updated weights for policy 0, policy_version 42922 (0.0009) -[2023-10-16 04:28:12,842][05218] Updated weights for policy 0, policy_version 42932 (0.0008) -[2023-10-16 04:28:13,234][05218] Updated weights for policy 0, policy_version 42942 (0.0008) -[2023-10-16 04:28:14,959][05219] Updated weights for policy 1, policy_version 42790 (0.0008) -[2023-10-16 04:28:15,324][05219] Updated weights for policy 1, policy_version 42800 (0.0008) -[2023-10-16 04:28:15,697][05219] Updated weights for policy 1, policy_version 42810 (0.0008) -[2023-10-16 04:28:16,988][05218] Updated weights for policy 0, policy_version 42952 (0.0008) -[2023-10-16 04:28:17,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 87818240. Throughput: 0: 1798.1, 1: 1794.7. Samples: 21965564. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-16 04:28:17,351][03835] Avg episode reward: [(0, '6.790'), (1, '5.940')] -[2023-10-16 04:28:17,365][05218] Updated weights for policy 0, policy_version 42962 (0.0007) -[2023-10-16 04:28:17,742][05218] Updated weights for policy 0, policy_version 42972 (0.0009) -[2023-10-16 04:28:19,556][05219] Updated weights for policy 1, policy_version 42820 (0.0008) -[2023-10-16 04:28:19,930][05219] Updated weights for policy 1, policy_version 42830 (0.0009) -[2023-10-16 04:28:20,294][05219] Updated weights for policy 1, policy_version 42840 (0.0011) -[2023-10-16 04:28:21,288][05218] Updated weights for policy 0, policy_version 42982 (0.0009) -[2023-10-16 04:28:21,670][05218] Updated weights for policy 0, policy_version 42992 (0.0008) -[2023-10-16 04:28:22,037][05218] Updated weights for policy 0, policy_version 43002 (0.0007) -[2023-10-16 04:28:22,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 87916544. Throughput: 0: 1789.2, 1: 1800.1. Samples: 21986792. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 04:28:22,351][03835] Avg episode reward: [(0, '6.470'), (1, '5.610')] -[2023-10-16 04:28:24,012][05219] Updated weights for policy 1, policy_version 42850 (0.0009) -[2023-10-16 04:28:24,382][05219] Updated weights for policy 1, policy_version 42860 (0.0009) -[2023-10-16 04:28:24,742][05219] Updated weights for policy 1, policy_version 42870 (0.0008) -[2023-10-16 04:28:25,118][05219] Updated weights for policy 1, policy_version 42880 (0.0008) -[2023-10-16 04:28:25,648][05218] Updated weights for policy 0, policy_version 43012 (0.0008) -[2023-10-16 04:28:26,018][05218] Updated weights for policy 0, policy_version 43022 (0.0010) -[2023-10-16 04:28:26,407][05218] Updated weights for policy 0, policy_version 43032 (0.0009) -[2023-10-16 04:28:27,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 87982080. Throughput: 0: 1804.5, 1: 1805.3. Samples: 21998434. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 04:28:27,351][03835] Avg episode reward: [(0, '6.510'), (1, '5.920')] -[2023-10-16 04:28:28,949][05219] Updated weights for policy 1, policy_version 42890 (0.0010) -[2023-10-16 04:28:29,319][05219] Updated weights for policy 1, policy_version 42900 (0.0010) -[2023-10-16 04:28:29,695][05219] Updated weights for policy 1, policy_version 42910 (0.0008) -[2023-10-16 04:28:30,058][05218] Updated weights for policy 0, policy_version 43042 (0.0010) -[2023-10-16 04:28:30,431][05218] Updated weights for policy 0, policy_version 43052 (0.0008) -[2023-10-16 04:28:30,809][05218] Updated weights for policy 0, policy_version 43062 (0.0009) -[2023-10-16 04:28:31,182][05218] Updated weights for policy 0, policy_version 43072 (0.0008) -[2023-10-16 04:28:32,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 88047616. Throughput: 0: 1799.2, 1: 1793.5. Samples: 22019372. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 04:28:32,351][03835] Avg episode reward: [(0, '7.110'), (1, '5.880')] -[2023-10-16 04:28:33,361][05219] Updated weights for policy 1, policy_version 42920 (0.0010) -[2023-10-16 04:28:33,741][05219] Updated weights for policy 1, policy_version 42930 (0.0007) -[2023-10-16 04:28:34,101][05219] Updated weights for policy 1, policy_version 42940 (0.0008) -[2023-10-16 04:28:34,990][05218] Updated weights for policy 0, policy_version 43082 (0.0007) -[2023-10-16 04:28:35,358][05218] Updated weights for policy 0, policy_version 43092 (0.0008) -[2023-10-16 04:28:35,731][05218] Updated weights for policy 0, policy_version 43102 (0.0009) -[2023-10-16 04:28:37,351][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 88113152. Throughput: 0: 1795.9, 1: 1803.4. Samples: 22041848. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 04:28:37,352][03835] Avg episode reward: [(0, '6.150'), (1, '6.140')] -[2023-10-16 04:28:37,746][05219] Updated weights for policy 1, policy_version 42950 (0.0008) -[2023-10-16 04:28:38,121][05219] Updated weights for policy 1, policy_version 42960 (0.0008) -[2023-10-16 04:28:38,479][05219] Updated weights for policy 1, policy_version 42970 (0.0008) -[2023-10-16 04:28:39,482][05218] Updated weights for policy 0, policy_version 43112 (0.0010) -[2023-10-16 04:28:39,854][05218] Updated weights for policy 0, policy_version 43122 (0.0009) -[2023-10-16 04:28:40,228][05218] Updated weights for policy 0, policy_version 43132 (0.0010) -[2023-10-16 04:28:42,263][05219] Updated weights for policy 1, policy_version 42980 (0.0007) -[2023-10-16 04:28:42,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 88178688. Throughput: 0: 1799.9, 1: 1802.3. Samples: 22051994. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 04:28:42,351][03835] Avg episode reward: [(0, '6.200'), (1, '5.940')] -[2023-10-16 04:28:42,629][05219] Updated weights for policy 1, policy_version 42990 (0.0007) -[2023-10-16 04:28:42,985][05219] Updated weights for policy 1, policy_version 43000 (0.0008) -[2023-10-16 04:28:43,915][05218] Updated weights for policy 0, policy_version 43142 (0.0008) -[2023-10-16 04:28:44,296][05218] Updated weights for policy 0, policy_version 43152 (0.0009) -[2023-10-16 04:28:44,666][05218] Updated weights for policy 0, policy_version 43162 (0.0007) -[2023-10-16 04:28:46,655][05219] Updated weights for policy 1, policy_version 43010 (0.0010) -[2023-10-16 04:28:47,018][05219] Updated weights for policy 1, policy_version 43020 (0.0008) -[2023-10-16 04:28:47,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 88244224. Throughput: 0: 1795.5, 1: 1801.9. Samples: 22074310. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 04:28:47,351][03835] Avg episode reward: [(0, '6.950'), (1, '5.790')] -[2023-10-16 04:28:47,385][05219] Updated weights for policy 1, policy_version 43030 (0.0007) -[2023-10-16 04:28:47,759][05219] Updated weights for policy 1, policy_version 43040 (0.0007) -[2023-10-16 04:28:48,470][05218] Updated weights for policy 0, policy_version 43172 (0.0008) -[2023-10-16 04:28:48,848][05218] Updated weights for policy 0, policy_version 43182 (0.0009) -[2023-10-16 04:28:49,222][05218] Updated weights for policy 0, policy_version 43192 (0.0007) -[2023-10-16 04:28:51,500][05219] Updated weights for policy 1, policy_version 43050 (0.0008) -[2023-10-16 04:28:51,860][05219] Updated weights for policy 1, policy_version 43060 (0.0009) -[2023-10-16 04:28:52,235][05219] Updated weights for policy 1, policy_version 43070 (0.0008) -[2023-10-16 04:28:52,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 88342528. Throughput: 0: 1797.6, 1: 1800.2. Samples: 22095602. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 04:28:52,351][03835] Avg episode reward: [(0, '6.720'), (1, '6.220')] -[2023-10-16 04:28:52,920][05218] Updated weights for policy 0, policy_version 43202 (0.0008) -[2023-10-16 04:28:53,295][05218] Updated weights for policy 0, policy_version 43212 (0.0009) -[2023-10-16 04:28:53,663][05218] Updated weights for policy 0, policy_version 43222 (0.0009) -[2023-10-16 04:28:54,044][05218] Updated weights for policy 0, policy_version 43232 (0.0009) -[2023-10-16 04:28:56,028][05219] Updated weights for policy 1, policy_version 43080 (0.0008) -[2023-10-16 04:28:56,386][05219] Updated weights for policy 1, policy_version 43090 (0.0008) -[2023-10-16 04:28:56,751][05219] Updated weights for policy 1, policy_version 43100 (0.0008) -[2023-10-16 04:28:57,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 88408064. Throughput: 0: 1798.6, 1: 1792.7. Samples: 22106530. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-16 04:28:57,351][03835] Avg episode reward: [(0, '6.170'), (1, '5.940')] -[2023-10-16 04:28:57,790][05218] Updated weights for policy 0, policy_version 43242 (0.0007) -[2023-10-16 04:28:58,171][05218] Updated weights for policy 0, policy_version 43252 (0.0008) -[2023-10-16 04:28:58,554][05218] Updated weights for policy 0, policy_version 43262 (0.0007) -[2023-10-16 04:29:00,595][05219] Updated weights for policy 1, policy_version 43110 (0.0010) -[2023-10-16 04:29:00,968][05219] Updated weights for policy 1, policy_version 43120 (0.0009) -[2023-10-16 04:29:01,332][05219] Updated weights for policy 1, policy_version 43130 (0.0008) -[2023-10-16 04:29:02,113][05218] Updated weights for policy 0, policy_version 43272 (0.0009) -[2023-10-16 04:29:02,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 88473600. Throughput: 0: 1807.2, 1: 1804.3. Samples: 22128080. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-16 04:29:02,351][03835] Avg episode reward: [(0, '7.070'), (1, '6.640')] -[2023-10-16 04:29:02,493][05218] Updated weights for policy 0, policy_version 43282 (0.0011) -[2023-10-16 04:29:02,863][05218] Updated weights for policy 0, policy_version 43292 (0.0008) -[2023-10-16 04:29:05,192][05219] Updated weights for policy 1, policy_version 43140 (0.0010) -[2023-10-16 04:29:05,555][05219] Updated weights for policy 1, policy_version 43150 (0.0007) -[2023-10-16 04:29:05,908][05219] Updated weights for policy 1, policy_version 43160 (0.0007) -[2023-10-16 04:29:06,563][05218] Updated weights for policy 0, policy_version 43302 (0.0009) -[2023-10-16 04:29:06,952][05218] Updated weights for policy 0, policy_version 43312 (0.0009) -[2023-10-16 04:29:07,325][05218] Updated weights for policy 0, policy_version 43322 (0.0009) -[2023-10-16 04:29:07,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 88539136. Throughput: 0: 1810.8, 1: 1792.0. Samples: 22148918. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-16 04:29:07,351][03835] Avg episode reward: [(0, '6.600'), (1, '6.340')] -[2023-10-16 04:29:09,553][05219] Updated weights for policy 1, policy_version 43170 (0.0009) -[2023-10-16 04:29:09,928][05219] Updated weights for policy 1, policy_version 43180 (0.0007) -[2023-10-16 04:29:10,295][05219] Updated weights for policy 1, policy_version 43190 (0.0007) -[2023-10-16 04:29:10,663][05219] Updated weights for policy 1, policy_version 43200 (0.0010) -[2023-10-16 04:29:11,152][05218] Updated weights for policy 0, policy_version 43332 (0.0009) -[2023-10-16 04:29:11,530][05218] Updated weights for policy 0, policy_version 43342 (0.0009) -[2023-10-16 04:29:11,912][05218] Updated weights for policy 0, policy_version 43352 (0.0009) -[2023-10-16 04:29:12,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 88637440. Throughput: 0: 1797.3, 1: 1805.1. Samples: 22160542. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-16 04:29:12,351][03835] Avg episode reward: [(0, '6.210'), (1, '6.570')] -[2023-10-16 04:29:14,417][05219] Updated weights for policy 1, policy_version 43210 (0.0009) -[2023-10-16 04:29:14,787][05219] Updated weights for policy 1, policy_version 43220 (0.0008) -[2023-10-16 04:29:15,160][05219] Updated weights for policy 1, policy_version 43230 (0.0010) -[2023-10-16 04:29:15,752][05218] Updated weights for policy 0, policy_version 43362 (0.0009) -[2023-10-16 04:29:16,124][05218] Updated weights for policy 0, policy_version 43372 (0.0010) -[2023-10-16 04:29:16,499][05218] Updated weights for policy 0, policy_version 43382 (0.0010) -[2023-10-16 04:29:16,875][05218] Updated weights for policy 0, policy_version 43392 (0.0008) -[2023-10-16 04:29:17,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.2). Total num frames: 88702976. Throughput: 0: 1805.8, 1: 1790.2. Samples: 22181192. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-16 04:29:17,351][03835] Avg episode reward: [(0, '6.520'), (1, '6.140')] -[2023-10-16 04:29:19,140][05219] Updated weights for policy 1, policy_version 43240 (0.0010) -[2023-10-16 04:29:19,513][05219] Updated weights for policy 1, policy_version 43250 (0.0009) -[2023-10-16 04:29:19,875][05219] Updated weights for policy 1, policy_version 43260 (0.0008) -[2023-10-16 04:29:20,639][05218] Updated weights for policy 0, policy_version 43402 (0.0010) -[2023-10-16 04:29:21,019][05218] Updated weights for policy 0, policy_version 43412 (0.0011) -[2023-10-16 04:29:21,389][05218] Updated weights for policy 0, policy_version 43422 (0.0008) -[2023-10-16 04:29:22,351][03835] Fps is (10 sec: 13106.6, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 88768512. Throughput: 0: 1794.0, 1: 1778.1. Samples: 22202590. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-16 04:29:22,352][03835] Avg episode reward: [(0, '6.680'), (1, '5.820')] -[2023-10-16 04:29:23,738][05219] Updated weights for policy 1, policy_version 43270 (0.0008) -[2023-10-16 04:29:24,109][05219] Updated weights for policy 1, policy_version 43280 (0.0007) -[2023-10-16 04:29:24,481][05219] Updated weights for policy 1, policy_version 43290 (0.0010) -[2023-10-16 04:29:25,082][05218] Updated weights for policy 0, policy_version 43432 (0.0007) -[2023-10-16 04:29:25,456][05218] Updated weights for policy 0, policy_version 43442 (0.0008) -[2023-10-16 04:29:25,837][05218] Updated weights for policy 0, policy_version 43452 (0.0009) -[2023-10-16 04:29:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 88834048. Throughput: 0: 1807.4, 1: 1775.3. Samples: 22213216. Policy #0 lag: (min: 26.0, avg: 28.7, max: 58.0) -[2023-10-16 04:29:27,351][03835] Avg episode reward: [(0, '6.730'), (1, '6.520')] -[2023-10-16 04:29:28,278][05219] Updated weights for policy 1, policy_version 43300 (0.0007) -[2023-10-16 04:29:28,641][05219] Updated weights for policy 1, policy_version 43310 (0.0007) -[2023-10-16 04:29:29,010][05219] Updated weights for policy 1, policy_version 43320 (0.0008) -[2023-10-16 04:29:29,518][05218] Updated weights for policy 0, policy_version 43462 (0.0008) -[2023-10-16 04:29:29,902][05218] Updated weights for policy 0, policy_version 43472 (0.0009) -[2023-10-16 04:29:30,282][05218] Updated weights for policy 0, policy_version 43482 (0.0010) -[2023-10-16 04:29:32,350][03835] Fps is (10 sec: 13107.8, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 88899584. Throughput: 0: 1789.7, 1: 1774.2. Samples: 22234686. Policy #0 lag: (min: 26.0, avg: 28.7, max: 58.0) -[2023-10-16 04:29:32,351][03835] Avg episode reward: [(0, '7.220'), (1, '5.920')] -[2023-10-16 04:29:32,351][04766] Saving new best policy, reward=7.220! -[2023-10-16 04:29:32,831][05219] Updated weights for policy 1, policy_version 43330 (0.0007) -[2023-10-16 04:29:33,198][05219] Updated weights for policy 1, policy_version 43340 (0.0007) -[2023-10-16 04:29:33,555][05219] Updated weights for policy 1, policy_version 43350 (0.0007) -[2023-10-16 04:29:33,922][05219] Updated weights for policy 1, policy_version 43360 (0.0010) -[2023-10-16 04:29:34,043][05218] Updated weights for policy 0, policy_version 43492 (0.0011) -[2023-10-16 04:29:34,428][05218] Updated weights for policy 0, policy_version 43502 (0.0007) -[2023-10-16 04:29:34,811][05218] Updated weights for policy 0, policy_version 43512 (0.0008) -[2023-10-16 04:29:37,351][03835] Fps is (10 sec: 13106.7, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 88965120. Throughput: 0: 1785.2, 1: 1798.8. Samples: 22256884. Policy #0 lag: (min: 26.0, avg: 28.7, max: 58.0) -[2023-10-16 04:29:37,352][03835] Avg episode reward: [(0, '6.590'), (1, '6.420')] -[2023-10-16 04:29:37,362][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000043520_44564480.pth... -[2023-10-16 04:29:37,394][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000041856_42860544.pth -[2023-10-16 04:29:37,719][05219] Updated weights for policy 1, policy_version 43370 (0.0008) -[2023-10-16 04:29:38,081][05219] Updated weights for policy 1, policy_version 43380 (0.0008) -[2023-10-16 04:29:38,443][05219] Updated weights for policy 1, policy_version 43390 (0.0008) -[2023-10-16 04:29:38,509][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000043392_44433408.pth... -[2023-10-16 04:29:38,538][05218] Updated weights for policy 0, policy_version 43522 (0.0008) -[2023-10-16 04:29:38,541][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000041696_42696704.pth -[2023-10-16 04:29:38,922][05218] Updated weights for policy 0, policy_version 43532 (0.0007) -[2023-10-16 04:29:39,305][05218] Updated weights for policy 0, policy_version 43542 (0.0007) -[2023-10-16 04:29:39,675][05218] Updated weights for policy 0, policy_version 43552 (0.0008) -[2023-10-16 04:29:42,143][05219] Updated weights for policy 1, policy_version 43400 (0.0007) -[2023-10-16 04:29:42,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 89030656. Throughput: 0: 1788.5, 1: 1773.7. Samples: 22266830. Policy #0 lag: (min: 26.0, avg: 28.7, max: 58.0) -[2023-10-16 04:29:42,351][03835] Avg episode reward: [(0, '6.050'), (1, '6.280')] -[2023-10-16 04:29:42,506][05219] Updated weights for policy 1, policy_version 43410 (0.0008) -[2023-10-16 04:29:42,862][05219] Updated weights for policy 1, policy_version 43420 (0.0008) -[2023-10-16 04:29:43,234][05218] Updated weights for policy 0, policy_version 43562 (0.0009) -[2023-10-16 04:29:43,605][05218] Updated weights for policy 0, policy_version 43572 (0.0008) -[2023-10-16 04:29:43,985][05218] Updated weights for policy 0, policy_version 43582 (0.0008) -[2023-10-16 04:29:46,570][05219] Updated weights for policy 1, policy_version 43430 (0.0009) -[2023-10-16 04:29:46,931][05219] Updated weights for policy 1, policy_version 43440 (0.0010) -[2023-10-16 04:29:47,297][05219] Updated weights for policy 1, policy_version 43450 (0.0011) -[2023-10-16 04:29:47,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 89096192. Throughput: 0: 1786.5, 1: 1796.0. Samples: 22289294. Policy #0 lag: (min: 26.0, avg: 28.7, max: 58.0) -[2023-10-16 04:29:47,351][03835] Avg episode reward: [(0, '5.340'), (1, '6.240')] -[2023-10-16 04:29:47,807][05218] Updated weights for policy 0, policy_version 43592 (0.0009) -[2023-10-16 04:29:48,179][05218] Updated weights for policy 0, policy_version 43602 (0.0008) -[2023-10-16 04:29:48,562][05218] Updated weights for policy 0, policy_version 43612 (0.0009) -[2023-10-16 04:29:51,088][05219] Updated weights for policy 1, policy_version 43460 (0.0008) -[2023-10-16 04:29:51,444][05219] Updated weights for policy 1, policy_version 43470 (0.0008) -[2023-10-16 04:29:51,804][05219] Updated weights for policy 1, policy_version 43480 (0.0008) -[2023-10-16 04:29:52,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 89194496. Throughput: 0: 1810.4, 1: 1772.9. Samples: 22310166. Policy #0 lag: (min: 26.0, avg: 28.7, max: 58.0) -[2023-10-16 04:29:52,351][03835] Avg episode reward: [(0, '5.710'), (1, '6.990')] -[2023-10-16 04:29:52,500][05218] Updated weights for policy 0, policy_version 43622 (0.0010) -[2023-10-16 04:29:52,870][05218] Updated weights for policy 0, policy_version 43632 (0.0009) -[2023-10-16 04:29:53,245][05218] Updated weights for policy 0, policy_version 43642 (0.0009) -[2023-10-16 04:29:55,696][05219] Updated weights for policy 1, policy_version 43490 (0.0009) -[2023-10-16 04:29:56,061][05219] Updated weights for policy 1, policy_version 43500 (0.0008) -[2023-10-16 04:29:56,435][05219] Updated weights for policy 1, policy_version 43510 (0.0007) -[2023-10-16 04:29:56,796][05219] Updated weights for policy 1, policy_version 43520 (0.0008) -[2023-10-16 04:29:56,906][05218] Updated weights for policy 0, policy_version 43652 (0.0010) -[2023-10-16 04:29:57,277][05218] Updated weights for policy 0, policy_version 43662 (0.0008) -[2023-10-16 04:29:57,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 89260032. Throughput: 0: 1784.9, 1: 1784.2. Samples: 22321154. Policy #0 lag: (min: 26.0, avg: 28.7, max: 58.0) -[2023-10-16 04:29:57,351][03835] Avg episode reward: [(0, '6.290'), (1, '5.860')] -[2023-10-16 04:29:57,658][05218] Updated weights for policy 0, policy_version 43672 (0.0009) -[2023-10-16 04:30:00,626][05219] Updated weights for policy 1, policy_version 43530 (0.0009) -[2023-10-16 04:30:00,995][05219] Updated weights for policy 1, policy_version 43540 (0.0009) -[2023-10-16 04:30:01,365][05219] Updated weights for policy 1, policy_version 43550 (0.0008) -[2023-10-16 04:30:01,502][05218] Updated weights for policy 0, policy_version 43682 (0.0011) -[2023-10-16 04:30:01,865][05218] Updated weights for policy 0, policy_version 43692 (0.0009) -[2023-10-16 04:30:02,246][05218] Updated weights for policy 0, policy_version 43702 (0.0010) -[2023-10-16 04:30:02,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 89325568. Throughput: 0: 1805.5, 1: 1775.4. Samples: 22342332. Policy #0 lag: (min: 25.0, avg: 39.9, max: 57.0) -[2023-10-16 04:30:02,351][03835] Avg episode reward: [(0, '5.850'), (1, '6.190')] -[2023-10-16 04:30:02,619][05218] Updated weights for policy 0, policy_version 43712 (0.0010) -[2023-10-16 04:30:05,223][05219] Updated weights for policy 1, policy_version 43560 (0.0009) -[2023-10-16 04:30:05,594][05219] Updated weights for policy 1, policy_version 43570 (0.0010) -[2023-10-16 04:30:05,967][05219] Updated weights for policy 1, policy_version 43580 (0.0008) -[2023-10-16 04:30:06,486][05218] Updated weights for policy 0, policy_version 43722 (0.0010) -[2023-10-16 04:30:06,861][05218] Updated weights for policy 0, policy_version 43732 (0.0010) -[2023-10-16 04:30:07,231][05218] Updated weights for policy 0, policy_version 43742 (0.0010) -[2023-10-16 04:30:07,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 89423872. Throughput: 0: 1780.6, 1: 1770.3. Samples: 22362380. Policy #0 lag: (min: 25.0, avg: 39.9, max: 57.0) -[2023-10-16 04:30:07,351][03835] Avg episode reward: [(0, '6.200'), (1, '6.640')] -[2023-10-16 04:30:09,826][05219] Updated weights for policy 1, policy_version 43590 (0.0008) -[2023-10-16 04:30:10,197][05219] Updated weights for policy 1, policy_version 43600 (0.0009) -[2023-10-16 04:30:10,563][05219] Updated weights for policy 1, policy_version 43610 (0.0008) -[2023-10-16 04:30:10,964][05218] Updated weights for policy 0, policy_version 43752 (0.0008) -[2023-10-16 04:30:11,341][05218] Updated weights for policy 0, policy_version 43762 (0.0008) -[2023-10-16 04:30:11,705][05218] Updated weights for policy 0, policy_version 43772 (0.0008) -[2023-10-16 04:30:12,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 89489408. Throughput: 0: 1793.2, 1: 1784.5. Samples: 22374212. Policy #0 lag: (min: 25.0, avg: 39.9, max: 57.0) -[2023-10-16 04:30:12,351][03835] Avg episode reward: [(0, '6.180'), (1, '6.490')] -[2023-10-16 04:30:14,452][05219] Updated weights for policy 1, policy_version 43620 (0.0008) -[2023-10-16 04:30:14,818][05219] Updated weights for policy 1, policy_version 43630 (0.0008) -[2023-10-16 04:30:15,168][05219] Updated weights for policy 1, policy_version 43640 (0.0007) -[2023-10-16 04:30:15,439][05218] Updated weights for policy 0, policy_version 43782 (0.0009) -[2023-10-16 04:30:15,799][05218] Updated weights for policy 0, policy_version 43792 (0.0009) -[2023-10-16 04:30:16,184][05218] Updated weights for policy 0, policy_version 43802 (0.0009) -[2023-10-16 04:30:17,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 89554944. Throughput: 0: 1787.1, 1: 1760.1. Samples: 22394310. Policy #0 lag: (min: 25.0, avg: 39.9, max: 57.0) -[2023-10-16 04:30:17,351][03835] Avg episode reward: [(0, '7.120'), (1, '6.160')] -[2023-10-16 04:30:18,961][05219] Updated weights for policy 1, policy_version 43650 (0.0009) -[2023-10-16 04:30:19,326][05219] Updated weights for policy 1, policy_version 43660 (0.0008) -[2023-10-16 04:30:19,690][05219] Updated weights for policy 1, policy_version 43670 (0.0009) -[2023-10-16 04:30:19,939][05218] Updated weights for policy 0, policy_version 43812 (0.0009) -[2023-10-16 04:30:20,051][05219] Updated weights for policy 1, policy_version 43680 (0.0007) -[2023-10-16 04:30:20,317][05218] Updated weights for policy 0, policy_version 43822 (0.0007) -[2023-10-16 04:30:20,691][05218] Updated weights for policy 0, policy_version 43832 (0.0008) -[2023-10-16 04:30:22,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.6, 300 sec: 14440.1). Total num frames: 89620480. Throughput: 0: 1791.2, 1: 1760.0. Samples: 22416686. Policy #0 lag: (min: 25.0, avg: 39.9, max: 57.0) -[2023-10-16 04:30:22,351][03835] Avg episode reward: [(0, '6.920'), (1, '5.890')] -[2023-10-16 04:30:23,932][05219] Updated weights for policy 1, policy_version 43690 (0.0007) -[2023-10-16 04:30:24,290][05219] Updated weights for policy 1, policy_version 43700 (0.0009) -[2023-10-16 04:30:24,365][05218] Updated weights for policy 0, policy_version 43842 (0.0009) -[2023-10-16 04:30:24,652][05219] Updated weights for policy 1, policy_version 43710 (0.0009) -[2023-10-16 04:30:24,737][05218] Updated weights for policy 0, policy_version 43852 (0.0007) -[2023-10-16 04:30:25,109][05218] Updated weights for policy 0, policy_version 43862 (0.0009) -[2023-10-16 04:30:25,493][05218] Updated weights for policy 0, policy_version 43872 (0.0009) -[2023-10-16 04:30:27,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 89686016. Throughput: 0: 1794.6, 1: 1758.1. Samples: 22426700. Policy #0 lag: (min: 25.0, avg: 39.9, max: 57.0) -[2023-10-16 04:30:27,351][03835] Avg episode reward: [(0, '6.310'), (1, '5.090')] -[2023-10-16 04:30:28,381][05219] Updated weights for policy 1, policy_version 43720 (0.0009) -[2023-10-16 04:30:28,749][05219] Updated weights for policy 1, policy_version 43730 (0.0008) -[2023-10-16 04:30:29,113][05219] Updated weights for policy 1, policy_version 43740 (0.0008) -[2023-10-16 04:30:29,117][05218] Updated weights for policy 0, policy_version 43882 (0.0008) -[2023-10-16 04:30:29,498][05218] Updated weights for policy 0, policy_version 43892 (0.0009) -[2023-10-16 04:30:29,877][05218] Updated weights for policy 0, policy_version 43902 (0.0010) -[2023-10-16 04:30:32,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 89751552. Throughput: 0: 1791.5, 1: 1756.2. Samples: 22448940. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:30:32,351][03835] Avg episode reward: [(0, '6.440'), (1, '5.870')] -[2023-10-16 04:30:32,979][05219] Updated weights for policy 1, policy_version 43750 (0.0008) -[2023-10-16 04:30:33,349][05219] Updated weights for policy 1, policy_version 43760 (0.0009) -[2023-10-16 04:30:33,396][05218] Updated weights for policy 0, policy_version 43912 (0.0008) -[2023-10-16 04:30:33,716][05219] Updated weights for policy 1, policy_version 43770 (0.0008) -[2023-10-16 04:30:33,770][05218] Updated weights for policy 0, policy_version 43922 (0.0009) -[2023-10-16 04:30:34,139][05218] Updated weights for policy 0, policy_version 43932 (0.0009) -[2023-10-16 04:30:37,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 89817088. Throughput: 0: 1796.0, 1: 1786.1. Samples: 22471362. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:30:37,351][03835] Avg episode reward: [(0, '6.430'), (1, '6.350')] -[2023-10-16 04:30:37,550][05219] Updated weights for policy 1, policy_version 43780 (0.0009) -[2023-10-16 04:30:37,922][05219] Updated weights for policy 1, policy_version 43790 (0.0007) -[2023-10-16 04:30:38,056][05218] Updated weights for policy 0, policy_version 43942 (0.0008) -[2023-10-16 04:30:38,291][05219] Updated weights for policy 1, policy_version 43800 (0.0008) -[2023-10-16 04:30:38,429][05218] Updated weights for policy 0, policy_version 43952 (0.0008) -[2023-10-16 04:30:38,810][05218] Updated weights for policy 0, policy_version 43962 (0.0007) -[2023-10-16 04:30:41,949][05219] Updated weights for policy 1, policy_version 43810 (0.0007) -[2023-10-16 04:30:42,318][05219] Updated weights for policy 1, policy_version 43820 (0.0008) -[2023-10-16 04:30:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 89882624. Throughput: 0: 1801.3, 1: 1758.4. Samples: 22481342. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:30:42,351][03835] Avg episode reward: [(0, '6.160'), (1, '6.930')] -[2023-10-16 04:30:42,487][05218] Updated weights for policy 0, policy_version 43972 (0.0007) -[2023-10-16 04:30:42,687][05219] Updated weights for policy 1, policy_version 43830 (0.0007) -[2023-10-16 04:30:42,855][05218] Updated weights for policy 0, policy_version 43982 (0.0010) -[2023-10-16 04:30:43,063][05219] Updated weights for policy 1, policy_version 43840 (0.0008) -[2023-10-16 04:30:43,227][05218] Updated weights for policy 0, policy_version 43992 (0.0009) -[2023-10-16 04:30:46,953][05218] Updated weights for policy 0, policy_version 44002 (0.0009) -[2023-10-16 04:30:46,988][05219] Updated weights for policy 1, policy_version 43850 (0.0008) -[2023-10-16 04:30:47,321][05218] Updated weights for policy 0, policy_version 44012 (0.0008) -[2023-10-16 04:30:47,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 89948160. Throughput: 0: 1800.1, 1: 1781.2. Samples: 22503488. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:30:47,351][03835] Avg episode reward: [(0, '6.490'), (1, '6.910')] -[2023-10-16 04:30:47,356][05219] Updated weights for policy 1, policy_version 43860 (0.0008) -[2023-10-16 04:30:47,699][05218] Updated weights for policy 0, policy_version 44022 (0.0008) -[2023-10-16 04:30:47,720][05219] Updated weights for policy 1, policy_version 43870 (0.0009) -[2023-10-16 04:30:48,067][05218] Updated weights for policy 0, policy_version 44032 (0.0009) -[2023-10-16 04:30:51,567][05219] Updated weights for policy 1, policy_version 43880 (0.0008) -[2023-10-16 04:30:51,930][05219] Updated weights for policy 1, policy_version 43890 (0.0007) -[2023-10-16 04:30:51,964][05218] Updated weights for policy 0, policy_version 44042 (0.0008) -[2023-10-16 04:30:52,297][05219] Updated weights for policy 1, policy_version 43900 (0.0007) -[2023-10-16 04:30:52,331][05218] Updated weights for policy 0, policy_version 44052 (0.0007) -[2023-10-16 04:30:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 14218.0). Total num frames: 90013696. Throughput: 0: 1811.7, 1: 1767.8. Samples: 22523456. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:30:52,351][03835] Avg episode reward: [(0, '5.960'), (1, '6.950')] -[2023-10-16 04:30:52,703][05218] Updated weights for policy 0, policy_version 44062 (0.0010) -[2023-10-16 04:30:55,870][05219] Updated weights for policy 1, policy_version 43910 (0.0008) -[2023-10-16 04:30:56,238][05219] Updated weights for policy 1, policy_version 43920 (0.0010) -[2023-10-16 04:30:56,377][05218] Updated weights for policy 0, policy_version 44072 (0.0009) -[2023-10-16 04:30:56,600][05219] Updated weights for policy 1, policy_version 43930 (0.0008) -[2023-10-16 04:30:56,748][05218] Updated weights for policy 0, policy_version 44082 (0.0009) -[2023-10-16 04:30:57,129][05218] Updated weights for policy 0, policy_version 44092 (0.0009) -[2023-10-16 04:30:57,350][03835] Fps is (10 sec: 19660.5, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 90144768. Throughput: 0: 1799.2, 1: 1781.3. Samples: 22535336. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:30:57,351][03835] Avg episode reward: [(0, '5.770'), (1, '7.190')] -[2023-10-16 04:31:00,338][05219] Updated weights for policy 1, policy_version 43940 (0.0007) -[2023-10-16 04:31:00,693][05219] Updated weights for policy 1, policy_version 43950 (0.0009) -[2023-10-16 04:31:01,014][05218] Updated weights for policy 0, policy_version 44102 (0.0008) -[2023-10-16 04:31:01,057][05219] Updated weights for policy 1, policy_version 43960 (0.0007) -[2023-10-16 04:31:01,388][05218] Updated weights for policy 0, policy_version 44112 (0.0008) -[2023-10-16 04:31:01,768][05218] Updated weights for policy 0, policy_version 44122 (0.0011) -[2023-10-16 04:31:02,350][03835] Fps is (10 sec: 19660.5, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 90210304. Throughput: 0: 1808.6, 1: 1783.0. Samples: 22555930. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-16 04:31:02,351][03835] Avg episode reward: [(0, '5.940'), (1, '6.430')] -[2023-10-16 04:31:04,831][05219] Updated weights for policy 1, policy_version 43970 (0.0008) -[2023-10-16 04:31:05,194][05219] Updated weights for policy 1, policy_version 43980 (0.0008) -[2023-10-16 04:31:05,537][05218] Updated weights for policy 0, policy_version 44132 (0.0008) -[2023-10-16 04:31:05,564][05219] Updated weights for policy 1, policy_version 43990 (0.0007) -[2023-10-16 04:31:05,909][05218] Updated weights for policy 0, policy_version 44142 (0.0009) -[2023-10-16 04:31:05,921][05219] Updated weights for policy 1, policy_version 44000 (0.0007) -[2023-10-16 04:31:06,299][05218] Updated weights for policy 0, policy_version 44152 (0.0009) -[2023-10-16 04:31:07,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 90275840. Throughput: 0: 1786.2, 1: 1781.5. Samples: 22577232. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-16 04:31:07,352][03835] Avg episode reward: [(0, '6.630'), (1, '6.420')] -[2023-10-16 04:31:09,754][05219] Updated weights for policy 1, policy_version 44010 (0.0008) -[2023-10-16 04:31:10,069][05218] Updated weights for policy 0, policy_version 44162 (0.0009) -[2023-10-16 04:31:10,120][05219] Updated weights for policy 1, policy_version 44020 (0.0010) -[2023-10-16 04:31:10,446][05218] Updated weights for policy 0, policy_version 44172 (0.0007) -[2023-10-16 04:31:10,472][05219] Updated weights for policy 1, policy_version 44030 (0.0008) -[2023-10-16 04:31:10,817][05218] Updated weights for policy 0, policy_version 44182 (0.0008) -[2023-10-16 04:31:11,189][05218] Updated weights for policy 0, policy_version 44192 (0.0010) -[2023-10-16 04:31:12,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 90341376. Throughput: 0: 1803.1, 1: 1795.9. Samples: 22588652. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-16 04:31:12,351][03835] Avg episode reward: [(0, '6.270'), (1, '5.920')] -[2023-10-16 04:31:14,229][05219] Updated weights for policy 1, policy_version 44040 (0.0008) -[2023-10-16 04:31:14,584][05219] Updated weights for policy 1, policy_version 44050 (0.0007) -[2023-10-16 04:31:14,942][05219] Updated weights for policy 1, policy_version 44060 (0.0007) -[2023-10-16 04:31:15,006][05218] Updated weights for policy 0, policy_version 44202 (0.0007) -[2023-10-16 04:31:15,373][05218] Updated weights for policy 0, policy_version 44212 (0.0007) -[2023-10-16 04:31:15,747][05218] Updated weights for policy 0, policy_version 44222 (0.0009) -[2023-10-16 04:31:17,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 90406912. Throughput: 0: 1777.1, 1: 1789.0. Samples: 22609416. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-16 04:31:17,351][03835] Avg episode reward: [(0, '6.610'), (1, '6.250')] -[2023-10-16 04:31:18,836][05219] Updated weights for policy 1, policy_version 44070 (0.0010) -[2023-10-16 04:31:19,197][05219] Updated weights for policy 1, policy_version 44080 (0.0008) -[2023-10-16 04:31:19,556][05219] Updated weights for policy 1, policy_version 44090 (0.0008) -[2023-10-16 04:31:19,597][05218] Updated weights for policy 0, policy_version 44232 (0.0008) -[2023-10-16 04:31:19,969][05218] Updated weights for policy 0, policy_version 44242 (0.0008) -[2023-10-16 04:31:20,347][05218] Updated weights for policy 0, policy_version 44252 (0.0007) -[2023-10-16 04:31:22,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 90472448. Throughput: 0: 1770.6, 1: 1794.5. Samples: 22631790. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-16 04:31:22,351][03835] Avg episode reward: [(0, '6.800'), (1, '6.250')] -[2023-10-16 04:31:23,175][05219] Updated weights for policy 1, policy_version 44100 (0.0007) -[2023-10-16 04:31:23,543][05219] Updated weights for policy 1, policy_version 44110 (0.0011) -[2023-10-16 04:31:23,903][05219] Updated weights for policy 1, policy_version 44120 (0.0010) -[2023-10-16 04:31:24,179][05218] Updated weights for policy 0, policy_version 44262 (0.0008) -[2023-10-16 04:31:24,545][05218] Updated weights for policy 0, policy_version 44272 (0.0008) -[2023-10-16 04:31:24,926][05218] Updated weights for policy 0, policy_version 44282 (0.0010) -[2023-10-16 04:31:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 90537984. Throughput: 0: 1760.5, 1: 1793.3. Samples: 22641266. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-16 04:31:27,351][03835] Avg episode reward: [(0, '6.680'), (1, '6.160')] -[2023-10-16 04:31:27,650][05219] Updated weights for policy 1, policy_version 44130 (0.0008) -[2023-10-16 04:31:28,015][05219] Updated weights for policy 1, policy_version 44140 (0.0008) -[2023-10-16 04:31:28,376][05219] Updated weights for policy 1, policy_version 44150 (0.0007) -[2023-10-16 04:31:28,626][05218] Updated weights for policy 0, policy_version 44292 (0.0008) -[2023-10-16 04:31:28,739][05219] Updated weights for policy 1, policy_version 44160 (0.0007) -[2023-10-16 04:31:28,998][05218] Updated weights for policy 0, policy_version 44302 (0.0008) -[2023-10-16 04:31:29,375][05218] Updated weights for policy 0, policy_version 44312 (0.0011) -[2023-10-16 04:31:32,351][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 90603520. Throughput: 0: 1763.6, 1: 1796.7. Samples: 22663706. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-16 04:31:32,352][03835] Avg episode reward: [(0, '6.730'), (1, '5.780')] -[2023-10-16 04:31:32,573][05219] Updated weights for policy 1, policy_version 44170 (0.0007) -[2023-10-16 04:31:32,944][05219] Updated weights for policy 1, policy_version 44180 (0.0008) -[2023-10-16 04:31:33,207][05218] Updated weights for policy 0, policy_version 44322 (0.0008) -[2023-10-16 04:31:33,305][05219] Updated weights for policy 1, policy_version 44190 (0.0009) -[2023-10-16 04:31:33,587][05218] Updated weights for policy 0, policy_version 44332 (0.0008) -[2023-10-16 04:31:33,963][05218] Updated weights for policy 0, policy_version 44342 (0.0008) -[2023-10-16 04:31:34,342][05218] Updated weights for policy 0, policy_version 44352 (0.0009) -[2023-10-16 04:31:37,209][05219] Updated weights for policy 1, policy_version 44200 (0.0008) -[2023-10-16 04:31:37,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 90669056. Throughput: 0: 1791.1, 1: 1814.4. Samples: 22685702. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:31:37,351][03835] Avg episode reward: [(0, '6.550'), (1, '6.210')] -[2023-10-16 04:31:37,359][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000044352_45416448.pth... -[2023-10-16 04:31:37,392][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000042688_43712512.pth -[2023-10-16 04:31:37,581][05219] Updated weights for policy 1, policy_version 44210 (0.0007) -[2023-10-16 04:31:37,948][05219] Updated weights for policy 1, policy_version 44220 (0.0008) -[2023-10-16 04:31:38,092][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000044224_45285376.pth... -[2023-10-16 04:31:38,121][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000042528_43548672.pth -[2023-10-16 04:31:38,212][05218] Updated weights for policy 0, policy_version 44362 (0.0008) -[2023-10-16 04:31:38,585][05218] Updated weights for policy 0, policy_version 44372 (0.0008) -[2023-10-16 04:31:38,962][05218] Updated weights for policy 0, policy_version 44382 (0.0007) -[2023-10-16 04:31:41,759][05219] Updated weights for policy 1, policy_version 44230 (0.0008) -[2023-10-16 04:31:42,141][05219] Updated weights for policy 1, policy_version 44240 (0.0009) -[2023-10-16 04:31:42,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 90734592. Throughput: 0: 1769.2, 1: 1794.3. Samples: 22695694. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:31:42,351][03835] Avg episode reward: [(0, '6.480'), (1, '6.410')] -[2023-10-16 04:31:42,496][05219] Updated weights for policy 1, policy_version 44250 (0.0008) -[2023-10-16 04:31:42,600][05218] Updated weights for policy 0, policy_version 44392 (0.0007) -[2023-10-16 04:31:42,970][05218] Updated weights for policy 0, policy_version 44402 (0.0008) -[2023-10-16 04:31:43,346][05218] Updated weights for policy 0, policy_version 44412 (0.0009) -[2023-10-16 04:31:46,333][05219] Updated weights for policy 1, policy_version 44260 (0.0008) -[2023-10-16 04:31:46,692][05219] Updated weights for policy 1, policy_version 44270 (0.0008) -[2023-10-16 04:31:47,009][05218] Updated weights for policy 0, policy_version 44422 (0.0008) -[2023-10-16 04:31:47,059][05219] Updated weights for policy 1, policy_version 44280 (0.0007) -[2023-10-16 04:31:47,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 90832896. Throughput: 0: 1789.4, 1: 1812.9. Samples: 22718030. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:31:47,351][03835] Avg episode reward: [(0, '6.350'), (1, '6.610')] -[2023-10-16 04:31:47,382][05218] Updated weights for policy 0, policy_version 44432 (0.0007) -[2023-10-16 04:31:47,763][05218] Updated weights for policy 0, policy_version 44442 (0.0007) -[2023-10-16 04:31:50,789][05219] Updated weights for policy 1, policy_version 44290 (0.0009) -[2023-10-16 04:31:51,149][05219] Updated weights for policy 1, policy_version 44300 (0.0009) -[2023-10-16 04:31:51,470][05218] Updated weights for policy 0, policy_version 44452 (0.0008) -[2023-10-16 04:31:51,511][05219] Updated weights for policy 1, policy_version 44310 (0.0008) -[2023-10-16 04:31:51,845][05218] Updated weights for policy 0, policy_version 44462 (0.0009) -[2023-10-16 04:31:51,885][05219] Updated weights for policy 1, policy_version 44320 (0.0008) -[2023-10-16 04:31:52,230][05218] Updated weights for policy 0, policy_version 44472 (0.0009) -[2023-10-16 04:31:52,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 90898432. Throughput: 0: 1784.7, 1: 1784.9. Samples: 22737864. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:31:52,351][03835] Avg episode reward: [(0, '6.390'), (1, '6.670')] -[2023-10-16 04:31:55,821][05219] Updated weights for policy 1, policy_version 44330 (0.0009) -[2023-10-16 04:31:55,998][05218] Updated weights for policy 0, policy_version 44482 (0.0010) -[2023-10-16 04:31:56,175][05219] Updated weights for policy 1, policy_version 44340 (0.0009) -[2023-10-16 04:31:56,371][05218] Updated weights for policy 0, policy_version 44492 (0.0008) -[2023-10-16 04:31:56,547][05219] Updated weights for policy 1, policy_version 44350 (0.0007) -[2023-10-16 04:31:56,750][05218] Updated weights for policy 0, policy_version 44502 (0.0008) -[2023-10-16 04:31:57,121][05218] Updated weights for policy 0, policy_version 44512 (0.0009) -[2023-10-16 04:31:57,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 90996736. Throughput: 0: 1782.7, 1: 1799.8. Samples: 22749866. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:31:57,351][03835] Avg episode reward: [(0, '6.480'), (1, '6.380')] -[2023-10-16 04:32:00,161][05219] Updated weights for policy 1, policy_version 44360 (0.0008) -[2023-10-16 04:32:00,529][05219] Updated weights for policy 1, policy_version 44370 (0.0008) -[2023-10-16 04:32:00,891][05219] Updated weights for policy 1, policy_version 44380 (0.0007) -[2023-10-16 04:32:00,968][05218] Updated weights for policy 0, policy_version 44522 (0.0008) -[2023-10-16 04:32:01,343][05218] Updated weights for policy 0, policy_version 44532 (0.0008) -[2023-10-16 04:32:01,729][05218] Updated weights for policy 0, policy_version 44542 (0.0009) -[2023-10-16 04:32:02,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 91062272. Throughput: 0: 1792.6, 1: 1782.2. Samples: 22770284. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:32:02,351][03835] Avg episode reward: [(0, '6.240'), (1, '6.160')] -[2023-10-16 04:32:04,442][05219] Updated weights for policy 1, policy_version 44390 (0.0008) -[2023-10-16 04:32:04,804][05219] Updated weights for policy 1, policy_version 44400 (0.0007) -[2023-10-16 04:32:05,176][05219] Updated weights for policy 1, policy_version 44410 (0.0009) -[2023-10-16 04:32:05,351][05218] Updated weights for policy 0, policy_version 44552 (0.0007) -[2023-10-16 04:32:05,735][05218] Updated weights for policy 0, policy_version 44562 (0.0009) -[2023-10-16 04:32:06,120][05218] Updated weights for policy 0, policy_version 44572 (0.0010) -[2023-10-16 04:32:07,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 91127808. Throughput: 0: 1785.6, 1: 1784.0. Samples: 22792422. Policy #0 lag: (min: 16.0, avg: 45.7, max: 48.0) -[2023-10-16 04:32:07,351][03835] Avg episode reward: [(0, '6.250'), (1, '6.390')] -[2023-10-16 04:32:08,888][05219] Updated weights for policy 1, policy_version 44420 (0.0009) -[2023-10-16 04:32:09,252][05219] Updated weights for policy 1, policy_version 44430 (0.0009) -[2023-10-16 04:32:09,619][05219] Updated weights for policy 1, policy_version 44440 (0.0007) -[2023-10-16 04:32:09,750][05218] Updated weights for policy 0, policy_version 44582 (0.0008) -[2023-10-16 04:32:10,123][05218] Updated weights for policy 0, policy_version 44592 (0.0011) -[2023-10-16 04:32:10,495][05218] Updated weights for policy 0, policy_version 44602 (0.0010) -[2023-10-16 04:32:12,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 91193344. Throughput: 0: 1804.1, 1: 1786.9. Samples: 22802864. Policy #0 lag: (min: 16.0, avg: 45.7, max: 48.0) -[2023-10-16 04:32:12,351][03835] Avg episode reward: [(0, '5.810'), (1, '6.540')] -[2023-10-16 04:32:13,282][05219] Updated weights for policy 1, policy_version 44450 (0.0009) -[2023-10-16 04:32:13,647][05219] Updated weights for policy 1, policy_version 44460 (0.0007) -[2023-10-16 04:32:14,009][05219] Updated weights for policy 1, policy_version 44470 (0.0007) -[2023-10-16 04:32:14,237][05218] Updated weights for policy 0, policy_version 44612 (0.0008) -[2023-10-16 04:32:14,367][05219] Updated weights for policy 1, policy_version 44480 (0.0008) -[2023-10-16 04:32:14,609][05218] Updated weights for policy 0, policy_version 44622 (0.0009) -[2023-10-16 04:32:14,985][05218] Updated weights for policy 0, policy_version 44632 (0.0009) -[2023-10-16 04:32:17,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 91258880. Throughput: 0: 1790.9, 1: 1789.9. Samples: 22824838. Policy #0 lag: (min: 16.0, avg: 45.7, max: 48.0) -[2023-10-16 04:32:17,352][03835] Avg episode reward: [(0, '5.600'), (1, '6.820')] -[2023-10-16 04:32:18,157][05219] Updated weights for policy 1, policy_version 44490 (0.0009) -[2023-10-16 04:32:18,523][05219] Updated weights for policy 1, policy_version 44500 (0.0008) -[2023-10-16 04:32:18,720][05218] Updated weights for policy 0, policy_version 44642 (0.0007) -[2023-10-16 04:32:18,878][05219] Updated weights for policy 1, policy_version 44510 (0.0008) -[2023-10-16 04:32:19,083][05218] Updated weights for policy 0, policy_version 44652 (0.0008) -[2023-10-16 04:32:19,463][05218] Updated weights for policy 0, policy_version 44662 (0.0008) -[2023-10-16 04:32:19,829][05218] Updated weights for policy 0, policy_version 44672 (0.0007) -[2023-10-16 04:32:22,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 91324416. Throughput: 0: 1798.9, 1: 1799.5. Samples: 22847632. Policy #0 lag: (min: 16.0, avg: 45.7, max: 48.0) -[2023-10-16 04:32:22,351][03835] Avg episode reward: [(0, '6.540'), (1, '6.370')] -[2023-10-16 04:32:22,699][05219] Updated weights for policy 1, policy_version 44520 (0.0009) -[2023-10-16 04:32:23,072][05219] Updated weights for policy 1, policy_version 44530 (0.0010) -[2023-10-16 04:32:23,440][05219] Updated weights for policy 1, policy_version 44540 (0.0010) -[2023-10-16 04:32:23,616][05218] Updated weights for policy 0, policy_version 44682 (0.0009) -[2023-10-16 04:32:23,983][05218] Updated weights for policy 0, policy_version 44692 (0.0008) -[2023-10-16 04:32:24,357][05218] Updated weights for policy 0, policy_version 44702 (0.0008) -[2023-10-16 04:32:27,323][05219] Updated weights for policy 1, policy_version 44550 (0.0008) -[2023-10-16 04:32:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 91389952. Throughput: 0: 1802.4, 1: 1788.1. Samples: 22857264. Policy #0 lag: (min: 16.0, avg: 45.7, max: 48.0) -[2023-10-16 04:32:27,351][03835] Avg episode reward: [(0, '6.030'), (1, '6.060')] -[2023-10-16 04:32:27,683][05219] Updated weights for policy 1, policy_version 44560 (0.0007) -[2023-10-16 04:32:28,028][05218] Updated weights for policy 0, policy_version 44712 (0.0009) -[2023-10-16 04:32:28,051][05219] Updated weights for policy 1, policy_version 44570 (0.0008) -[2023-10-16 04:32:28,407][05218] Updated weights for policy 0, policy_version 44722 (0.0010) -[2023-10-16 04:32:28,780][05218] Updated weights for policy 0, policy_version 44732 (0.0008) -[2023-10-16 04:32:31,753][05219] Updated weights for policy 1, policy_version 44580 (0.0007) -[2023-10-16 04:32:32,126][05219] Updated weights for policy 1, policy_version 44590 (0.0008) -[2023-10-16 04:32:32,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.6, 300 sec: 14218.0). Total num frames: 91455488. Throughput: 0: 1795.1, 1: 1790.5. Samples: 22879382. Policy #0 lag: (min: 16.0, avg: 45.7, max: 48.0) -[2023-10-16 04:32:32,351][03835] Avg episode reward: [(0, '6.710'), (1, '6.580')] -[2023-10-16 04:32:32,483][05218] Updated weights for policy 0, policy_version 44742 (0.0008) -[2023-10-16 04:32:32,488][05219] Updated weights for policy 1, policy_version 44600 (0.0007) -[2023-10-16 04:32:32,867][05218] Updated weights for policy 0, policy_version 44752 (0.0008) -[2023-10-16 04:32:33,252][05218] Updated weights for policy 0, policy_version 44762 (0.0010) -[2023-10-16 04:32:36,430][05219] Updated weights for policy 1, policy_version 44610 (0.0010) -[2023-10-16 04:32:36,786][05219] Updated weights for policy 1, policy_version 44620 (0.0007) -[2023-10-16 04:32:36,876][05218] Updated weights for policy 0, policy_version 44772 (0.0008) -[2023-10-16 04:32:37,149][05219] Updated weights for policy 1, policy_version 44630 (0.0007) -[2023-10-16 04:32:37,257][05218] Updated weights for policy 0, policy_version 44782 (0.0007) -[2023-10-16 04:32:37,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 91521024. Throughput: 0: 1805.9, 1: 1796.5. Samples: 22899972. Policy #0 lag: (min: 16.0, avg: 45.7, max: 48.0) -[2023-10-16 04:32:37,351][03835] Avg episode reward: [(0, '6.350'), (1, '7.390')] -[2023-10-16 04:32:37,512][05219] Updated weights for policy 1, policy_version 44640 (0.0008) -[2023-10-16 04:32:37,625][05218] Updated weights for policy 0, policy_version 44792 (0.0010) -[2023-10-16 04:32:41,191][05219] Updated weights for policy 1, policy_version 44650 (0.0007) -[2023-10-16 04:32:41,433][05218] Updated weights for policy 0, policy_version 44802 (0.0009) -[2023-10-16 04:32:41,553][05219] Updated weights for policy 1, policy_version 44660 (0.0007) -[2023-10-16 04:32:41,821][05218] Updated weights for policy 0, policy_version 44812 (0.0009) -[2023-10-16 04:32:41,918][05219] Updated weights for policy 1, policy_version 44670 (0.0007) -[2023-10-16 04:32:42,197][05218] Updated weights for policy 0, policy_version 44822 (0.0009) -[2023-10-16 04:32:42,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 91619328. Throughput: 0: 1794.0, 1: 1789.1. Samples: 22911102. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:32:42,351][03835] Avg episode reward: [(0, '5.410'), (1, '6.390')] -[2023-10-16 04:32:42,574][05218] Updated weights for policy 0, policy_version 44832 (0.0008) -[2023-10-16 04:32:45,852][05219] Updated weights for policy 1, policy_version 44680 (0.0007) -[2023-10-16 04:32:46,214][05219] Updated weights for policy 1, policy_version 44690 (0.0009) -[2023-10-16 04:32:46,379][05218] Updated weights for policy 0, policy_version 44842 (0.0008) -[2023-10-16 04:32:46,569][05219] Updated weights for policy 1, policy_version 44700 (0.0008) -[2023-10-16 04:32:46,751][05218] Updated weights for policy 0, policy_version 44852 (0.0008) -[2023-10-16 04:32:47,135][05218] Updated weights for policy 0, policy_version 44862 (0.0010) -[2023-10-16 04:32:47,350][03835] Fps is (10 sec: 19660.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 91717632. Throughput: 0: 1804.0, 1: 1799.3. Samples: 22932432. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:32:47,351][03835] Avg episode reward: [(0, '6.090'), (1, '6.700')] -[2023-10-16 04:32:50,451][05219] Updated weights for policy 1, policy_version 44710 (0.0008) -[2023-10-16 04:32:50,811][05219] Updated weights for policy 1, policy_version 44720 (0.0008) -[2023-10-16 04:32:50,910][05218] Updated weights for policy 0, policy_version 44872 (0.0009) -[2023-10-16 04:32:51,167][05219] Updated weights for policy 1, policy_version 44730 (0.0007) -[2023-10-16 04:32:51,284][05218] Updated weights for policy 0, policy_version 44882 (0.0009) -[2023-10-16 04:32:51,672][05218] Updated weights for policy 0, policy_version 44892 (0.0008) -[2023-10-16 04:32:52,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 91783168. Throughput: 0: 1789.9, 1: 1773.9. Samples: 22952794. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:32:52,351][03835] Avg episode reward: [(0, '6.970'), (1, '7.150')] -[2023-10-16 04:32:55,023][05219] Updated weights for policy 1, policy_version 44740 (0.0009) -[2023-10-16 04:32:55,368][05218] Updated weights for policy 0, policy_version 44902 (0.0010) -[2023-10-16 04:32:55,398][05219] Updated weights for policy 1, policy_version 44750 (0.0007) -[2023-10-16 04:32:55,735][05218] Updated weights for policy 0, policy_version 44912 (0.0010) -[2023-10-16 04:32:55,760][05219] Updated weights for policy 1, policy_version 44760 (0.0007) -[2023-10-16 04:32:56,107][05218] Updated weights for policy 0, policy_version 44922 (0.0009) -[2023-10-16 04:32:57,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 91848704. Throughput: 0: 1805.9, 1: 1794.1. Samples: 22964866. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:32:57,351][03835] Avg episode reward: [(0, '6.840'), (1, '6.040')] -[2023-10-16 04:32:59,427][05219] Updated weights for policy 1, policy_version 44770 (0.0009) -[2023-10-16 04:32:59,800][05219] Updated weights for policy 1, policy_version 44780 (0.0009) -[2023-10-16 04:32:59,898][05218] Updated weights for policy 0, policy_version 44932 (0.0009) -[2023-10-16 04:33:00,161][05219] Updated weights for policy 1, policy_version 44790 (0.0009) -[2023-10-16 04:33:00,268][05218] Updated weights for policy 0, policy_version 44942 (0.0008) -[2023-10-16 04:33:00,519][05219] Updated weights for policy 1, policy_version 44800 (0.0008) -[2023-10-16 04:33:00,642][05218] Updated weights for policy 0, policy_version 44952 (0.0009) -[2023-10-16 04:33:02,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 91914240. Throughput: 0: 1789.3, 1: 1766.7. Samples: 22984858. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:33:02,351][03835] Avg episode reward: [(0, '7.050'), (1, '6.230')] -[2023-10-16 04:33:04,221][05219] Updated weights for policy 1, policy_version 44810 (0.0008) -[2023-10-16 04:33:04,479][05218] Updated weights for policy 0, policy_version 44962 (0.0010) -[2023-10-16 04:33:04,577][05219] Updated weights for policy 1, policy_version 44820 (0.0007) -[2023-10-16 04:33:04,850][05218] Updated weights for policy 0, policy_version 44972 (0.0007) -[2023-10-16 04:33:04,944][05219] Updated weights for policy 1, policy_version 44830 (0.0007) -[2023-10-16 04:33:05,234][05218] Updated weights for policy 0, policy_version 44982 (0.0009) -[2023-10-16 04:33:05,602][05218] Updated weights for policy 0, policy_version 44992 (0.0010) -[2023-10-16 04:33:07,350][03835] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 91979776. Throughput: 0: 1778.5, 1: 1768.5. Samples: 23007246. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:33:07,352][03835] Avg episode reward: [(0, '6.820'), (1, '6.430')] -[2023-10-16 04:33:08,768][05219] Updated weights for policy 1, policy_version 44840 (0.0007) -[2023-10-16 04:33:09,139][05219] Updated weights for policy 1, policy_version 44850 (0.0008) -[2023-10-16 04:33:09,353][05218] Updated weights for policy 0, policy_version 45002 (0.0009) -[2023-10-16 04:33:09,509][05219] Updated weights for policy 1, policy_version 44860 (0.0007) -[2023-10-16 04:33:09,729][05218] Updated weights for policy 0, policy_version 45012 (0.0010) -[2023-10-16 04:33:10,105][05218] Updated weights for policy 0, policy_version 45022 (0.0010) -[2023-10-16 04:33:12,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 92045312. Throughput: 0: 1774.4, 1: 1769.9. Samples: 23016758. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 04:33:12,351][03835] Avg episode reward: [(0, '6.780'), (1, '5.900')] -[2023-10-16 04:33:13,086][05219] Updated weights for policy 1, policy_version 44870 (0.0008) -[2023-10-16 04:33:13,451][05219] Updated weights for policy 1, policy_version 44880 (0.0007) -[2023-10-16 04:33:13,819][05219] Updated weights for policy 1, policy_version 44890 (0.0007) -[2023-10-16 04:33:13,921][05218] Updated weights for policy 0, policy_version 45032 (0.0007) -[2023-10-16 04:33:14,293][05218] Updated weights for policy 0, policy_version 45042 (0.0008) -[2023-10-16 04:33:14,669][05218] Updated weights for policy 0, policy_version 45052 (0.0007) -[2023-10-16 04:33:17,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 92110848. Throughput: 0: 1777.1, 1: 1778.1. Samples: 23039368. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 04:33:17,352][03835] Avg episode reward: [(0, '6.140'), (1, '6.370')] -[2023-10-16 04:33:17,518][05219] Updated weights for policy 1, policy_version 44900 (0.0007) -[2023-10-16 04:33:17,889][05219] Updated weights for policy 1, policy_version 44910 (0.0008) -[2023-10-16 04:33:18,249][05219] Updated weights for policy 1, policy_version 44920 (0.0010) -[2023-10-16 04:33:18,538][05218] Updated weights for policy 0, policy_version 45062 (0.0009) -[2023-10-16 04:33:18,910][05218] Updated weights for policy 0, policy_version 45072 (0.0009) -[2023-10-16 04:33:19,286][05218] Updated weights for policy 0, policy_version 45082 (0.0009) -[2023-10-16 04:33:22,058][05219] Updated weights for policy 1, policy_version 44930 (0.0008) -[2023-10-16 04:33:22,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 92176384. Throughput: 0: 1785.3, 1: 1802.0. Samples: 23061398. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 04:33:22,351][03835] Avg episode reward: [(0, '6.680'), (1, '6.480')] -[2023-10-16 04:33:22,413][05219] Updated weights for policy 1, policy_version 44940 (0.0011) -[2023-10-16 04:33:22,781][05219] Updated weights for policy 1, policy_version 44950 (0.0009) -[2023-10-16 04:33:23,113][05218] Updated weights for policy 0, policy_version 45092 (0.0009) -[2023-10-16 04:33:23,135][05219] Updated weights for policy 1, policy_version 44960 (0.0009) -[2023-10-16 04:33:23,490][05218] Updated weights for policy 0, policy_version 45102 (0.0007) -[2023-10-16 04:33:23,878][05218] Updated weights for policy 0, policy_version 45112 (0.0007) -[2023-10-16 04:33:26,950][05219] Updated weights for policy 1, policy_version 44970 (0.0010) -[2023-10-16 04:33:27,322][05219] Updated weights for policy 1, policy_version 44980 (0.0008) -[2023-10-16 04:33:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 92241920. Throughput: 0: 1775.6, 1: 1787.8. Samples: 23071454. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 04:33:27,351][03835] Avg episode reward: [(0, '6.590'), (1, '7.000')] -[2023-10-16 04:33:27,537][05218] Updated weights for policy 0, policy_version 45122 (0.0008) -[2023-10-16 04:33:27,676][05219] Updated weights for policy 1, policy_version 44990 (0.0007) -[2023-10-16 04:33:27,915][05218] Updated weights for policy 0, policy_version 45132 (0.0008) -[2023-10-16 04:33:28,294][05218] Updated weights for policy 0, policy_version 45142 (0.0007) -[2023-10-16 04:33:28,679][05218] Updated weights for policy 0, policy_version 45152 (0.0007) -[2023-10-16 04:33:31,447][05219] Updated weights for policy 1, policy_version 45000 (0.0010) -[2023-10-16 04:33:31,818][05219] Updated weights for policy 1, policy_version 45010 (0.0007) -[2023-10-16 04:33:32,185][05219] Updated weights for policy 1, policy_version 45020 (0.0007) -[2023-10-16 04:33:32,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 92340224. Throughput: 0: 1781.5, 1: 1805.3. Samples: 23093836. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 04:33:32,351][03835] Avg episode reward: [(0, '5.860'), (1, '6.340')] -[2023-10-16 04:33:32,425][05218] Updated weights for policy 0, policy_version 45162 (0.0008) -[2023-10-16 04:33:32,803][05218] Updated weights for policy 0, policy_version 45172 (0.0007) -[2023-10-16 04:33:33,185][05218] Updated weights for policy 0, policy_version 45182 (0.0009) -[2023-10-16 04:33:35,999][05219] Updated weights for policy 1, policy_version 45030 (0.0008) -[2023-10-16 04:33:36,371][05219] Updated weights for policy 1, policy_version 45040 (0.0010) -[2023-10-16 04:33:36,738][05219] Updated weights for policy 1, policy_version 45050 (0.0008) -[2023-10-16 04:33:36,902][05218] Updated weights for policy 0, policy_version 45192 (0.0008) -[2023-10-16 04:33:37,277][05218] Updated weights for policy 0, policy_version 45202 (0.0010) -[2023-10-16 04:33:37,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 92405760. Throughput: 0: 1787.4, 1: 1794.0. Samples: 23113958. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 04:33:37,351][03835] Avg episode reward: [(0, '5.740'), (1, '6.250')] -[2023-10-16 04:33:37,360][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000045056_46137344.pth... -[2023-10-16 04:33:37,389][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000043392_44433408.pth -[2023-10-16 04:33:37,654][05218] Updated weights for policy 0, policy_version 45212 (0.0008) -[2023-10-16 04:33:37,808][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000045216_46301184.pth... -[2023-10-16 04:33:37,849][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000043520_44564480.pth -[2023-10-16 04:33:40,482][05219] Updated weights for policy 1, policy_version 45060 (0.0008) -[2023-10-16 04:33:40,843][05219] Updated weights for policy 1, policy_version 45070 (0.0009) -[2023-10-16 04:33:41,211][05219] Updated weights for policy 1, policy_version 45080 (0.0009) -[2023-10-16 04:33:41,411][05218] Updated weights for policy 0, policy_version 45222 (0.0008) -[2023-10-16 04:33:41,784][05218] Updated weights for policy 0, policy_version 45232 (0.0007) -[2023-10-16 04:33:42,157][05218] Updated weights for policy 0, policy_version 45242 (0.0007) -[2023-10-16 04:33:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 92471296. Throughput: 0: 1776.0, 1: 1805.0. Samples: 23126014. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 04:33:42,351][03835] Avg episode reward: [(0, '6.740'), (1, '6.540')] -[2023-10-16 04:33:44,935][05219] Updated weights for policy 1, policy_version 45090 (0.0008) -[2023-10-16 04:33:45,304][05219] Updated weights for policy 1, policy_version 45100 (0.0007) -[2023-10-16 04:33:45,673][05219] Updated weights for policy 1, policy_version 45110 (0.0007) -[2023-10-16 04:33:45,954][05218] Updated weights for policy 0, policy_version 45252 (0.0007) -[2023-10-16 04:33:46,034][05219] Updated weights for policy 1, policy_version 45120 (0.0009) -[2023-10-16 04:33:46,324][05218] Updated weights for policy 0, policy_version 45262 (0.0008) -[2023-10-16 04:33:46,692][05218] Updated weights for policy 0, policy_version 45272 (0.0009) -[2023-10-16 04:33:47,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 92569600. Throughput: 0: 1788.1, 1: 1794.1. Samples: 23146058. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 04:33:47,351][03835] Avg episode reward: [(0, '6.540'), (1, '5.740')] -[2023-10-16 04:33:49,806][05219] Updated weights for policy 1, policy_version 45130 (0.0010) -[2023-10-16 04:33:50,184][05219] Updated weights for policy 1, policy_version 45140 (0.0009) -[2023-10-16 04:33:50,297][05218] Updated weights for policy 0, policy_version 45282 (0.0007) -[2023-10-16 04:33:50,538][05219] Updated weights for policy 1, policy_version 45150 (0.0008) -[2023-10-16 04:33:50,671][05218] Updated weights for policy 0, policy_version 45292 (0.0010) -[2023-10-16 04:33:51,049][05218] Updated weights for policy 0, policy_version 45302 (0.0010) -[2023-10-16 04:33:51,422][05218] Updated weights for policy 0, policy_version 45312 (0.0007) -[2023-10-16 04:33:52,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 92635136. Throughput: 0: 1774.6, 1: 1793.3. Samples: 23167800. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 04:33:52,352][03835] Avg episode reward: [(0, '6.670'), (1, '6.680')] -[2023-10-16 04:33:54,486][05219] Updated weights for policy 1, policy_version 45160 (0.0009) -[2023-10-16 04:33:54,863][05219] Updated weights for policy 1, policy_version 45170 (0.0007) -[2023-10-16 04:33:55,100][05218] Updated weights for policy 0, policy_version 45322 (0.0009) -[2023-10-16 04:33:55,235][05219] Updated weights for policy 1, policy_version 45180 (0.0007) -[2023-10-16 04:33:55,471][05218] Updated weights for policy 0, policy_version 45332 (0.0008) -[2023-10-16 04:33:55,847][05218] Updated weights for policy 0, policy_version 45342 (0.0010) -[2023-10-16 04:33:57,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 92700672. Throughput: 0: 1796.4, 1: 1798.1. Samples: 23178508. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 04:33:57,351][03835] Avg episode reward: [(0, '7.090'), (1, '6.880')] -[2023-10-16 04:33:59,012][05219] Updated weights for policy 1, policy_version 45190 (0.0008) -[2023-10-16 04:33:59,370][05219] Updated weights for policy 1, policy_version 45200 (0.0008) -[2023-10-16 04:33:59,640][05218] Updated weights for policy 0, policy_version 45352 (0.0009) -[2023-10-16 04:33:59,733][05219] Updated weights for policy 1, policy_version 45210 (0.0008) -[2023-10-16 04:34:00,019][05218] Updated weights for policy 0, policy_version 45362 (0.0008) -[2023-10-16 04:34:00,394][05218] Updated weights for policy 0, policy_version 45372 (0.0008) -[2023-10-16 04:34:02,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 92766208. Throughput: 0: 1779.9, 1: 1780.0. Samples: 23199564. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 04:34:02,351][03835] Avg episode reward: [(0, '6.410'), (1, '6.370')] -[2023-10-16 04:34:03,512][05219] Updated weights for policy 1, policy_version 45220 (0.0007) -[2023-10-16 04:34:03,876][05219] Updated weights for policy 1, policy_version 45230 (0.0007) -[2023-10-16 04:34:04,054][05218] Updated weights for policy 0, policy_version 45382 (0.0009) -[2023-10-16 04:34:04,242][05219] Updated weights for policy 1, policy_version 45240 (0.0007) -[2023-10-16 04:34:04,435][05218] Updated weights for policy 0, policy_version 45392 (0.0009) -[2023-10-16 04:34:04,801][05218] Updated weights for policy 0, policy_version 45402 (0.0010) -[2023-10-16 04:34:07,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 92831744. Throughput: 0: 1786.3, 1: 1782.5. Samples: 23221996. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 04:34:07,351][03835] Avg episode reward: [(0, '6.600'), (1, '6.480')] -[2023-10-16 04:34:08,053][05219] Updated weights for policy 1, policy_version 45250 (0.0007) -[2023-10-16 04:34:08,415][05219] Updated weights for policy 1, policy_version 45260 (0.0009) -[2023-10-16 04:34:08,654][05218] Updated weights for policy 0, policy_version 45412 (0.0007) -[2023-10-16 04:34:08,779][05219] Updated weights for policy 1, policy_version 45270 (0.0008) -[2023-10-16 04:34:09,036][05218] Updated weights for policy 0, policy_version 45422 (0.0008) -[2023-10-16 04:34:09,147][05219] Updated weights for policy 1, policy_version 45280 (0.0008) -[2023-10-16 04:34:09,405][05218] Updated weights for policy 0, policy_version 45432 (0.0008) -[2023-10-16 04:34:12,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 92897280. Throughput: 0: 1785.2, 1: 1778.2. Samples: 23231804. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 04:34:12,351][03835] Avg episode reward: [(0, '6.640'), (1, '5.980')] -[2023-10-16 04:34:12,886][05219] Updated weights for policy 1, policy_version 45290 (0.0011) -[2023-10-16 04:34:13,163][05218] Updated weights for policy 0, policy_version 45442 (0.0008) -[2023-10-16 04:34:13,243][05219] Updated weights for policy 1, policy_version 45300 (0.0008) -[2023-10-16 04:34:13,541][05218] Updated weights for policy 0, policy_version 45452 (0.0007) -[2023-10-16 04:34:13,606][05219] Updated weights for policy 1, policy_version 45310 (0.0007) -[2023-10-16 04:34:13,908][05218] Updated weights for policy 0, policy_version 45462 (0.0008) -[2023-10-16 04:34:14,286][05218] Updated weights for policy 0, policy_version 45472 (0.0010) -[2023-10-16 04:34:17,220][05219] Updated weights for policy 1, policy_version 45320 (0.0007) -[2023-10-16 04:34:17,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 92962816. Throughput: 0: 1786.0, 1: 1782.0. Samples: 23254396. Policy #0 lag: (min: 8.0, avg: 23.9, max: 40.0) -[2023-10-16 04:34:17,351][03835] Avg episode reward: [(0, '6.320'), (1, '6.030')] -[2023-10-16 04:34:17,586][05219] Updated weights for policy 1, policy_version 45330 (0.0009) -[2023-10-16 04:34:17,962][05219] Updated weights for policy 1, policy_version 45340 (0.0008) -[2023-10-16 04:34:18,002][05218] Updated weights for policy 0, policy_version 45482 (0.0010) -[2023-10-16 04:34:18,369][05218] Updated weights for policy 0, policy_version 45492 (0.0007) -[2023-10-16 04:34:18,751][05218] Updated weights for policy 0, policy_version 45502 (0.0007) -[2023-10-16 04:34:21,765][05219] Updated weights for policy 1, policy_version 45350 (0.0009) -[2023-10-16 04:34:22,126][05219] Updated weights for policy 1, policy_version 45360 (0.0011) -[2023-10-16 04:34:22,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 93028352. Throughput: 0: 1803.8, 1: 1797.8. Samples: 23276032. Policy #0 lag: (min: 8.0, avg: 23.9, max: 40.0) -[2023-10-16 04:34:22,351][03835] Avg episode reward: [(0, '6.360'), (1, '6.250')] -[2023-10-16 04:34:22,503][05219] Updated weights for policy 1, policy_version 45370 (0.0007) -[2023-10-16 04:34:22,594][05218] Updated weights for policy 0, policy_version 45512 (0.0009) -[2023-10-16 04:34:22,965][05218] Updated weights for policy 0, policy_version 45522 (0.0008) -[2023-10-16 04:34:23,331][05218] Updated weights for policy 0, policy_version 45532 (0.0008) -[2023-10-16 04:34:26,249][05219] Updated weights for policy 1, policy_version 45380 (0.0007) -[2023-10-16 04:34:26,609][05219] Updated weights for policy 1, policy_version 45390 (0.0008) -[2023-10-16 04:34:26,980][05219] Updated weights for policy 1, policy_version 45400 (0.0009) -[2023-10-16 04:34:27,190][05218] Updated weights for policy 0, policy_version 45542 (0.0008) -[2023-10-16 04:34:27,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 93126656. Throughput: 0: 1785.3, 1: 1780.1. Samples: 23286458. Policy #0 lag: (min: 8.0, avg: 23.9, max: 40.0) -[2023-10-16 04:34:27,351][03835] Avg episode reward: [(0, '6.240'), (1, '5.960')] -[2023-10-16 04:34:27,572][05218] Updated weights for policy 0, policy_version 45552 (0.0007) -[2023-10-16 04:34:27,948][05218] Updated weights for policy 0, policy_version 45562 (0.0007) -[2023-10-16 04:34:30,952][05219] Updated weights for policy 1, policy_version 45410 (0.0008) -[2023-10-16 04:34:31,310][05219] Updated weights for policy 1, policy_version 45420 (0.0008) -[2023-10-16 04:34:31,677][05219] Updated weights for policy 1, policy_version 45430 (0.0007) -[2023-10-16 04:34:31,733][05218] Updated weights for policy 0, policy_version 45572 (0.0008) -[2023-10-16 04:34:32,039][05219] Updated weights for policy 1, policy_version 45440 (0.0007) -[2023-10-16 04:34:32,110][05218] Updated weights for policy 0, policy_version 45582 (0.0009) -[2023-10-16 04:34:32,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 93192192. Throughput: 0: 1799.7, 1: 1803.1. Samples: 23308184. Policy #0 lag: (min: 8.0, avg: 23.9, max: 40.0) -[2023-10-16 04:34:32,351][03835] Avg episode reward: [(0, '6.900'), (1, '6.660')] -[2023-10-16 04:34:32,482][05218] Updated weights for policy 0, policy_version 45592 (0.0007) -[2023-10-16 04:34:35,775][05219] Updated weights for policy 1, policy_version 45450 (0.0009) -[2023-10-16 04:34:36,137][05219] Updated weights for policy 1, policy_version 45460 (0.0007) -[2023-10-16 04:34:36,438][05218] Updated weights for policy 0, policy_version 45602 (0.0007) -[2023-10-16 04:34:36,518][05219] Updated weights for policy 1, policy_version 45470 (0.0008) -[2023-10-16 04:34:36,809][05218] Updated weights for policy 0, policy_version 45612 (0.0008) -[2023-10-16 04:34:37,181][05218] Updated weights for policy 0, policy_version 45622 (0.0011) -[2023-10-16 04:34:37,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 93257728. Throughput: 0: 1780.6, 1: 1778.2. Samples: 23327948. Policy #0 lag: (min: 8.0, avg: 23.9, max: 40.0) -[2023-10-16 04:34:37,351][03835] Avg episode reward: [(0, '6.350'), (1, '6.830')] -[2023-10-16 04:34:37,557][05218] Updated weights for policy 0, policy_version 45632 (0.0011) -[2023-10-16 04:34:40,284][05219] Updated weights for policy 1, policy_version 45480 (0.0009) -[2023-10-16 04:34:40,649][05219] Updated weights for policy 1, policy_version 45490 (0.0008) -[2023-10-16 04:34:41,009][05219] Updated weights for policy 1, policy_version 45500 (0.0007) -[2023-10-16 04:34:41,413][05218] Updated weights for policy 0, policy_version 45642 (0.0008) -[2023-10-16 04:34:41,798][05218] Updated weights for policy 0, policy_version 45652 (0.0009) -[2023-10-16 04:34:42,177][05218] Updated weights for policy 0, policy_version 45662 (0.0007) -[2023-10-16 04:34:42,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 93356032. Throughput: 0: 1789.6, 1: 1802.1. Samples: 23340134. Policy #0 lag: (min: 8.0, avg: 23.9, max: 40.0) -[2023-10-16 04:34:42,351][03835] Avg episode reward: [(0, '5.550'), (1, '6.370')] -[2023-10-16 04:34:44,810][05219] Updated weights for policy 1, policy_version 45510 (0.0008) -[2023-10-16 04:34:45,171][05219] Updated weights for policy 1, policy_version 45520 (0.0009) -[2023-10-16 04:34:45,542][05219] Updated weights for policy 1, policy_version 45530 (0.0008) -[2023-10-16 04:34:45,984][05218] Updated weights for policy 0, policy_version 45672 (0.0008) -[2023-10-16 04:34:46,362][05218] Updated weights for policy 0, policy_version 45682 (0.0009) -[2023-10-16 04:34:46,753][05218] Updated weights for policy 0, policy_version 45692 (0.0008) -[2023-10-16 04:34:47,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 93421568. Throughput: 0: 1785.4, 1: 1781.6. Samples: 23360078. Policy #0 lag: (min: 31.0, avg: 32.4, max: 56.0) -[2023-10-16 04:34:47,351][03835] Avg episode reward: [(0, '6.130'), (1, '7.100')] -[2023-10-16 04:34:49,327][05219] Updated weights for policy 1, policy_version 45540 (0.0008) -[2023-10-16 04:34:49,694][05219] Updated weights for policy 1, policy_version 45550 (0.0008) -[2023-10-16 04:34:50,068][05219] Updated weights for policy 1, policy_version 45560 (0.0008) -[2023-10-16 04:34:50,513][05218] Updated weights for policy 0, policy_version 45702 (0.0010) -[2023-10-16 04:34:50,889][05218] Updated weights for policy 0, policy_version 45712 (0.0008) -[2023-10-16 04:34:51,270][05218] Updated weights for policy 0, policy_version 45722 (0.0008) -[2023-10-16 04:34:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 93487104. Throughput: 0: 1765.0, 1: 1785.3. Samples: 23381758. Policy #0 lag: (min: 31.0, avg: 32.4, max: 56.0) -[2023-10-16 04:34:52,352][03835] Avg episode reward: [(0, '6.190'), (1, '6.720')] -[2023-10-16 04:34:53,739][05219] Updated weights for policy 1, policy_version 45570 (0.0009) -[2023-10-16 04:34:54,101][05219] Updated weights for policy 1, policy_version 45580 (0.0010) -[2023-10-16 04:34:54,464][05219] Updated weights for policy 1, policy_version 45590 (0.0010) -[2023-10-16 04:34:54,827][05219] Updated weights for policy 1, policy_version 45600 (0.0009) -[2023-10-16 04:34:55,015][05218] Updated weights for policy 0, policy_version 45732 (0.0009) -[2023-10-16 04:34:55,392][05218] Updated weights for policy 0, policy_version 45742 (0.0007) -[2023-10-16 04:34:55,771][05218] Updated weights for policy 0, policy_version 45752 (0.0007) -[2023-10-16 04:34:57,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 93552640. Throughput: 0: 1787.7, 1: 1783.9. Samples: 23392524. Policy #0 lag: (min: 31.0, avg: 32.4, max: 56.0) -[2023-10-16 04:34:57,351][03835] Avg episode reward: [(0, '6.670'), (1, '5.810')] -[2023-10-16 04:34:58,818][05219] Updated weights for policy 1, policy_version 45610 (0.0010) -[2023-10-16 04:34:59,193][05219] Updated weights for policy 1, policy_version 45620 (0.0008) -[2023-10-16 04:34:59,482][05218] Updated weights for policy 0, policy_version 45762 (0.0009) -[2023-10-16 04:34:59,558][05219] Updated weights for policy 1, policy_version 45630 (0.0008) -[2023-10-16 04:34:59,859][05218] Updated weights for policy 0, policy_version 45772 (0.0008) -[2023-10-16 04:35:00,241][05218] Updated weights for policy 0, policy_version 45782 (0.0008) -[2023-10-16 04:35:00,619][05218] Updated weights for policy 0, policy_version 45792 (0.0007) -[2023-10-16 04:35:02,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 93618176. Throughput: 0: 1771.2, 1: 1774.8. Samples: 23413970. Policy #0 lag: (min: 31.0, avg: 32.4, max: 56.0) -[2023-10-16 04:35:02,351][03835] Avg episode reward: [(0, '6.330'), (1, '6.740')] -[2023-10-16 04:35:03,161][05219] Updated weights for policy 1, policy_version 45640 (0.0007) -[2023-10-16 04:35:03,529][05219] Updated weights for policy 1, policy_version 45650 (0.0008) -[2023-10-16 04:35:03,888][05219] Updated weights for policy 1, policy_version 45660 (0.0008) -[2023-10-16 04:35:04,133][05218] Updated weights for policy 0, policy_version 45802 (0.0010) -[2023-10-16 04:35:04,514][05218] Updated weights for policy 0, policy_version 45812 (0.0010) -[2023-10-16 04:35:04,887][05218] Updated weights for policy 0, policy_version 45822 (0.0008) -[2023-10-16 04:35:07,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 93683712. Throughput: 0: 1775.9, 1: 1796.4. Samples: 23436788. Policy #0 lag: (min: 31.0, avg: 32.4, max: 56.0) -[2023-10-16 04:35:07,352][03835] Avg episode reward: [(0, '5.880'), (1, '6.680')] -[2023-10-16 04:35:07,746][05219] Updated weights for policy 1, policy_version 45670 (0.0008) -[2023-10-16 04:35:08,102][05219] Updated weights for policy 1, policy_version 45680 (0.0007) -[2023-10-16 04:35:08,471][05219] Updated weights for policy 1, policy_version 45690 (0.0007) -[2023-10-16 04:35:08,659][05218] Updated weights for policy 0, policy_version 45832 (0.0009) -[2023-10-16 04:35:09,036][05218] Updated weights for policy 0, policy_version 45842 (0.0009) -[2023-10-16 04:35:09,416][05218] Updated weights for policy 0, policy_version 45852 (0.0009) -[2023-10-16 04:35:12,276][05219] Updated weights for policy 1, policy_version 45700 (0.0007) -[2023-10-16 04:35:12,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 93749248. Throughput: 0: 1776.5, 1: 1777.0. Samples: 23446366. Policy #0 lag: (min: 31.0, avg: 32.4, max: 56.0) -[2023-10-16 04:35:12,351][03835] Avg episode reward: [(0, '5.790'), (1, '6.840')] -[2023-10-16 04:35:12,640][05219] Updated weights for policy 1, policy_version 45710 (0.0007) -[2023-10-16 04:35:13,011][05219] Updated weights for policy 1, policy_version 45720 (0.0007) -[2023-10-16 04:35:13,094][05218] Updated weights for policy 0, policy_version 45862 (0.0007) -[2023-10-16 04:35:13,463][05218] Updated weights for policy 0, policy_version 45872 (0.0008) -[2023-10-16 04:35:13,846][05218] Updated weights for policy 0, policy_version 45882 (0.0008) -[2023-10-16 04:35:16,853][05219] Updated weights for policy 1, policy_version 45730 (0.0007) -[2023-10-16 04:35:17,224][05219] Updated weights for policy 1, policy_version 45740 (0.0011) -[2023-10-16 04:35:17,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 93814784. Throughput: 0: 1776.1, 1: 1787.0. Samples: 23468524. Policy #0 lag: (min: 31.0, avg: 32.4, max: 56.0) -[2023-10-16 04:35:17,351][03835] Avg episode reward: [(0, '5.770'), (1, '6.860')] -[2023-10-16 04:35:17,555][05218] Updated weights for policy 0, policy_version 45892 (0.0007) -[2023-10-16 04:35:17,583][05219] Updated weights for policy 1, policy_version 45750 (0.0009) -[2023-10-16 04:35:17,939][05218] Updated weights for policy 0, policy_version 45902 (0.0009) -[2023-10-16 04:35:17,946][05219] Updated weights for policy 1, policy_version 45760 (0.0008) -[2023-10-16 04:35:18,313][05218] Updated weights for policy 0, policy_version 45912 (0.0007) -[2023-10-16 04:35:21,489][05219] Updated weights for policy 1, policy_version 45770 (0.0010) -[2023-10-16 04:35:21,856][05219] Updated weights for policy 1, policy_version 45780 (0.0010) -[2023-10-16 04:35:22,145][05218] Updated weights for policy 0, policy_version 45922 (0.0009) -[2023-10-16 04:35:22,214][05219] Updated weights for policy 1, policy_version 45790 (0.0008) -[2023-10-16 04:35:22,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 93913088. Throughput: 0: 1802.6, 1: 1788.1. Samples: 23489528. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:35:22,351][03835] Avg episode reward: [(0, '5.750'), (1, '6.060')] -[2023-10-16 04:35:22,518][05218] Updated weights for policy 0, policy_version 45932 (0.0007) -[2023-10-16 04:35:22,892][05218] Updated weights for policy 0, policy_version 45942 (0.0007) -[2023-10-16 04:35:23,267][05218] Updated weights for policy 0, policy_version 45952 (0.0008) -[2023-10-16 04:35:25,935][05219] Updated weights for policy 1, policy_version 45800 (0.0008) -[2023-10-16 04:35:26,314][05219] Updated weights for policy 1, policy_version 45810 (0.0008) -[2023-10-16 04:35:26,678][05219] Updated weights for policy 1, policy_version 45820 (0.0009) -[2023-10-16 04:35:27,034][05218] Updated weights for policy 0, policy_version 45962 (0.0010) -[2023-10-16 04:35:27,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 93978624. Throughput: 0: 1786.2, 1: 1790.3. Samples: 23501076. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:35:27,351][03835] Avg episode reward: [(0, '6.490'), (1, '6.520')] -[2023-10-16 04:35:27,410][05218] Updated weights for policy 0, policy_version 45972 (0.0009) -[2023-10-16 04:35:27,788][05218] Updated weights for policy 0, policy_version 45982 (0.0007) -[2023-10-16 04:35:30,425][05219] Updated weights for policy 1, policy_version 45830 (0.0008) -[2023-10-16 04:35:30,783][05219] Updated weights for policy 1, policy_version 45840 (0.0010) -[2023-10-16 04:35:31,144][05219] Updated weights for policy 1, policy_version 45850 (0.0008) -[2023-10-16 04:35:31,359][05218] Updated weights for policy 0, policy_version 45992 (0.0008) -[2023-10-16 04:35:31,724][05218] Updated weights for policy 0, policy_version 46002 (0.0008) -[2023-10-16 04:35:32,096][05218] Updated weights for policy 0, policy_version 46012 (0.0010) -[2023-10-16 04:35:32,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 94076928. Throughput: 0: 1801.6, 1: 1797.0. Samples: 23522016. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:35:32,352][03835] Avg episode reward: [(0, '6.990'), (1, '6.150')] -[2023-10-16 04:35:35,040][05219] Updated weights for policy 1, policy_version 45860 (0.0008) -[2023-10-16 04:35:35,411][05219] Updated weights for policy 1, policy_version 45870 (0.0007) -[2023-10-16 04:35:35,774][05219] Updated weights for policy 1, policy_version 45880 (0.0008) -[2023-10-16 04:35:35,805][05218] Updated weights for policy 0, policy_version 46022 (0.0009) -[2023-10-16 04:35:36,177][05218] Updated weights for policy 0, policy_version 46032 (0.0009) -[2023-10-16 04:35:36,556][05218] Updated weights for policy 0, policy_version 46042 (0.0007) -[2023-10-16 04:35:37,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 94142464. Throughput: 0: 1798.0, 1: 1784.8. Samples: 23542982. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:35:37,351][03835] Avg episode reward: [(0, '7.520'), (1, '6.530')] -[2023-10-16 04:35:37,361][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000046048_47153152.pth... -[2023-10-16 04:35:37,361][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000045888_46989312.pth... -[2023-10-16 04:35:37,399][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000044224_45285376.pth -[2023-10-16 04:35:37,400][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000044352_45416448.pth -[2023-10-16 04:35:37,406][04766] Saving new best policy, reward=7.520! -[2023-10-16 04:35:39,514][05219] Updated weights for policy 1, policy_version 45890 (0.0009) -[2023-10-16 04:35:39,879][05219] Updated weights for policy 1, policy_version 45900 (0.0010) -[2023-10-16 04:35:40,234][05219] Updated weights for policy 1, policy_version 45910 (0.0007) -[2023-10-16 04:35:40,342][05218] Updated weights for policy 0, policy_version 46052 (0.0007) -[2023-10-16 04:35:40,598][05219] Updated weights for policy 1, policy_version 45920 (0.0007) -[2023-10-16 04:35:40,723][05218] Updated weights for policy 0, policy_version 46062 (0.0009) -[2023-10-16 04:35:41,104][05218] Updated weights for policy 0, policy_version 46072 (0.0010) -[2023-10-16 04:35:42,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 94208000. Throughput: 0: 1807.1, 1: 1798.8. Samples: 23554788. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:35:42,351][03835] Avg episode reward: [(0, '6.800'), (1, '7.090')] -[2023-10-16 04:35:44,274][05219] Updated weights for policy 1, policy_version 45930 (0.0007) -[2023-10-16 04:35:44,639][05219] Updated weights for policy 1, policy_version 45940 (0.0007) -[2023-10-16 04:35:44,920][05218] Updated weights for policy 0, policy_version 46082 (0.0009) -[2023-10-16 04:35:45,013][05219] Updated weights for policy 1, policy_version 45950 (0.0008) -[2023-10-16 04:35:45,285][05218] Updated weights for policy 0, policy_version 46092 (0.0008) -[2023-10-16 04:35:45,664][05218] Updated weights for policy 0, policy_version 46102 (0.0010) -[2023-10-16 04:35:46,031][05218] Updated weights for policy 0, policy_version 46112 (0.0008) -[2023-10-16 04:35:47,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 94273536. Throughput: 0: 1796.1, 1: 1797.7. Samples: 23575690. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:35:47,351][03835] Avg episode reward: [(0, '6.760'), (1, '6.430')] -[2023-10-16 04:35:48,605][05219] Updated weights for policy 1, policy_version 45960 (0.0009) -[2023-10-16 04:35:48,985][05219] Updated weights for policy 1, policy_version 45970 (0.0009) -[2023-10-16 04:35:49,344][05219] Updated weights for policy 1, policy_version 45980 (0.0008) -[2023-10-16 04:35:49,688][05218] Updated weights for policy 0, policy_version 46122 (0.0008) -[2023-10-16 04:35:50,062][05218] Updated weights for policy 0, policy_version 46132 (0.0007) -[2023-10-16 04:35:50,438][05218] Updated weights for policy 0, policy_version 46142 (0.0009) -[2023-10-16 04:35:52,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 94339072. Throughput: 0: 1793.8, 1: 1794.0. Samples: 23598238. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-16 04:35:52,351][03835] Avg episode reward: [(0, '7.310'), (1, '6.580')] -[2023-10-16 04:35:53,081][05219] Updated weights for policy 1, policy_version 45990 (0.0008) -[2023-10-16 04:35:53,457][05219] Updated weights for policy 1, policy_version 46000 (0.0009) -[2023-10-16 04:35:53,815][05219] Updated weights for policy 1, policy_version 46010 (0.0008) -[2023-10-16 04:35:54,249][05218] Updated weights for policy 0, policy_version 46152 (0.0009) -[2023-10-16 04:35:54,619][05218] Updated weights for policy 0, policy_version 46162 (0.0008) -[2023-10-16 04:35:54,988][05218] Updated weights for policy 0, policy_version 46172 (0.0008) -[2023-10-16 04:35:57,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 94404608. Throughput: 0: 1792.8, 1: 1801.8. Samples: 23608120. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-16 04:35:57,351][03835] Avg episode reward: [(0, '6.770'), (1, '6.350')] -[2023-10-16 04:35:57,394][05219] Updated weights for policy 1, policy_version 46020 (0.0009) -[2023-10-16 04:35:57,756][05219] Updated weights for policy 1, policy_version 46030 (0.0010) -[2023-10-16 04:35:58,127][05219] Updated weights for policy 1, policy_version 46040 (0.0011) -[2023-10-16 04:35:58,758][05218] Updated weights for policy 0, policy_version 46182 (0.0008) -[2023-10-16 04:35:59,132][05218] Updated weights for policy 0, policy_version 46192 (0.0009) -[2023-10-16 04:35:59,500][05218] Updated weights for policy 0, policy_version 46202 (0.0009) -[2023-10-16 04:36:01,955][05219] Updated weights for policy 1, policy_version 46050 (0.0009) -[2023-10-16 04:36:02,318][05219] Updated weights for policy 1, policy_version 46060 (0.0008) -[2023-10-16 04:36:02,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 94470144. Throughput: 0: 1795.4, 1: 1805.2. Samples: 23630554. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-16 04:36:02,351][03835] Avg episode reward: [(0, '6.940'), (1, '6.120')] -[2023-10-16 04:36:02,694][05219] Updated weights for policy 1, policy_version 46070 (0.0008) -[2023-10-16 04:36:03,060][05219] Updated weights for policy 1, policy_version 46080 (0.0009) -[2023-10-16 04:36:03,207][05218] Updated weights for policy 0, policy_version 46212 (0.0009) -[2023-10-16 04:36:03,589][05218] Updated weights for policy 0, policy_version 46222 (0.0010) -[2023-10-16 04:36:03,954][05218] Updated weights for policy 0, policy_version 46232 (0.0009) -[2023-10-16 04:36:07,006][05219] Updated weights for policy 1, policy_version 46090 (0.0010) -[2023-10-16 04:36:07,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 94535680. Throughput: 0: 1804.0, 1: 1809.7. Samples: 23652144. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-16 04:36:07,351][03835] Avg episode reward: [(0, '6.270'), (1, '5.780')] -[2023-10-16 04:36:07,366][05219] Updated weights for policy 1, policy_version 46100 (0.0010) -[2023-10-16 04:36:07,621][05218] Updated weights for policy 0, policy_version 46242 (0.0010) -[2023-10-16 04:36:07,724][05219] Updated weights for policy 1, policy_version 46110 (0.0008) -[2023-10-16 04:36:07,984][05218] Updated weights for policy 0, policy_version 46252 (0.0009) -[2023-10-16 04:36:08,355][05218] Updated weights for policy 0, policy_version 46262 (0.0009) -[2023-10-16 04:36:08,729][05218] Updated weights for policy 0, policy_version 46272 (0.0009) -[2023-10-16 04:36:11,530][05219] Updated weights for policy 1, policy_version 46120 (0.0008) -[2023-10-16 04:36:11,893][05219] Updated weights for policy 1, policy_version 46130 (0.0007) -[2023-10-16 04:36:12,269][05219] Updated weights for policy 1, policy_version 46140 (0.0007) -[2023-10-16 04:36:12,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 94601216. Throughput: 0: 1786.4, 1: 1795.6. Samples: 23662262. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-16 04:36:12,351][03835] Avg episode reward: [(0, '6.100'), (1, '6.790')] -[2023-10-16 04:36:12,717][05218] Updated weights for policy 0, policy_version 46282 (0.0008) -[2023-10-16 04:36:13,099][05218] Updated weights for policy 0, policy_version 46292 (0.0007) -[2023-10-16 04:36:13,479][05218] Updated weights for policy 0, policy_version 46302 (0.0007) -[2023-10-16 04:36:16,072][05219] Updated weights for policy 1, policy_version 46150 (0.0007) -[2023-10-16 04:36:16,444][05219] Updated weights for policy 1, policy_version 46160 (0.0008) -[2023-10-16 04:36:16,812][05219] Updated weights for policy 1, policy_version 46170 (0.0007) -[2023-10-16 04:36:17,207][05218] Updated weights for policy 0, policy_version 46312 (0.0007) -[2023-10-16 04:36:17,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 94699520. Throughput: 0: 1793.3, 1: 1810.1. Samples: 23684168. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-16 04:36:17,351][03835] Avg episode reward: [(0, '6.070'), (1, '6.220')] -[2023-10-16 04:36:17,581][05218] Updated weights for policy 0, policy_version 46322 (0.0007) -[2023-10-16 04:36:17,957][05218] Updated weights for policy 0, policy_version 46332 (0.0007) -[2023-10-16 04:36:20,564][05219] Updated weights for policy 1, policy_version 46180 (0.0007) -[2023-10-16 04:36:20,932][05219] Updated weights for policy 1, policy_version 46190 (0.0007) -[2023-10-16 04:36:21,287][05219] Updated weights for policy 1, policy_version 46200 (0.0007) -[2023-10-16 04:36:21,706][05218] Updated weights for policy 0, policy_version 46342 (0.0009) -[2023-10-16 04:36:22,081][05218] Updated weights for policy 0, policy_version 46352 (0.0008) -[2023-10-16 04:36:22,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 94765056. Throughput: 0: 1796.9, 1: 1797.2. Samples: 23704714. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-16 04:36:22,351][03835] Avg episode reward: [(0, '6.300'), (1, '6.070')] -[2023-10-16 04:36:22,457][05218] Updated weights for policy 0, policy_version 46362 (0.0008) -[2023-10-16 04:36:24,787][05219] Updated weights for policy 1, policy_version 46210 (0.0008) -[2023-10-16 04:36:25,150][05219] Updated weights for policy 1, policy_version 46220 (0.0009) -[2023-10-16 04:36:25,516][05219] Updated weights for policy 1, policy_version 46230 (0.0009) -[2023-10-16 04:36:25,878][05219] Updated weights for policy 1, policy_version 46240 (0.0011) -[2023-10-16 04:36:26,172][05218] Updated weights for policy 0, policy_version 46372 (0.0009) -[2023-10-16 04:36:26,555][05218] Updated weights for policy 0, policy_version 46382 (0.0007) -[2023-10-16 04:36:26,936][05218] Updated weights for policy 0, policy_version 46392 (0.0007) -[2023-10-16 04:36:27,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 94863360. Throughput: 0: 1788.9, 1: 1809.1. Samples: 23716698. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:36:27,351][03835] Avg episode reward: [(0, '6.120'), (1, '6.740')] -[2023-10-16 04:36:29,797][05219] Updated weights for policy 1, policy_version 46250 (0.0008) -[2023-10-16 04:36:30,159][05219] Updated weights for policy 1, policy_version 46260 (0.0009) -[2023-10-16 04:36:30,522][05219] Updated weights for policy 1, policy_version 46270 (0.0010) -[2023-10-16 04:36:30,696][05218] Updated weights for policy 0, policy_version 46402 (0.0008) -[2023-10-16 04:36:31,068][05218] Updated weights for policy 0, policy_version 46412 (0.0009) -[2023-10-16 04:36:31,443][05218] Updated weights for policy 0, policy_version 46422 (0.0010) -[2023-10-16 04:36:31,823][05218] Updated weights for policy 0, policy_version 46432 (0.0008) -[2023-10-16 04:36:32,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 94928896. Throughput: 0: 1800.2, 1: 1791.0. Samples: 23737292. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:36:32,352][03835] Avg episode reward: [(0, '6.890'), (1, '6.250')] -[2023-10-16 04:36:34,305][05219] Updated weights for policy 1, policy_version 46280 (0.0008) -[2023-10-16 04:36:34,669][05219] Updated weights for policy 1, policy_version 46290 (0.0007) -[2023-10-16 04:36:35,028][05219] Updated weights for policy 1, policy_version 46300 (0.0007) -[2023-10-16 04:36:35,273][05218] Updated weights for policy 0, policy_version 46442 (0.0008) -[2023-10-16 04:36:35,641][05218] Updated weights for policy 0, policy_version 46452 (0.0007) -[2023-10-16 04:36:36,019][05218] Updated weights for policy 0, policy_version 46462 (0.0007) -[2023-10-16 04:36:37,351][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 94994432. Throughput: 0: 1791.5, 1: 1792.6. Samples: 23759524. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:36:37,352][03835] Avg episode reward: [(0, '7.180'), (1, '6.420')] -[2023-10-16 04:36:38,766][05219] Updated weights for policy 1, policy_version 46310 (0.0008) -[2023-10-16 04:36:39,140][05219] Updated weights for policy 1, policy_version 46320 (0.0009) -[2023-10-16 04:36:39,502][05219] Updated weights for policy 1, policy_version 46330 (0.0008) -[2023-10-16 04:36:39,779][05218] Updated weights for policy 0, policy_version 46472 (0.0008) -[2023-10-16 04:36:40,156][05218] Updated weights for policy 0, policy_version 46482 (0.0007) -[2023-10-16 04:36:40,530][05218] Updated weights for policy 0, policy_version 46492 (0.0009) -[2023-10-16 04:36:42,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 95059968. Throughput: 0: 1805.2, 1: 1791.7. Samples: 23769982. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:36:42,352][03835] Avg episode reward: [(0, '6.850'), (1, '7.320')] -[2023-10-16 04:36:43,506][05219] Updated weights for policy 1, policy_version 46340 (0.0010) -[2023-10-16 04:36:43,868][05219] Updated weights for policy 1, policy_version 46350 (0.0009) -[2023-10-16 04:36:44,230][05219] Updated weights for policy 1, policy_version 46360 (0.0008) -[2023-10-16 04:36:44,386][05218] Updated weights for policy 0, policy_version 46502 (0.0009) -[2023-10-16 04:36:44,757][05218] Updated weights for policy 0, policy_version 46512 (0.0009) -[2023-10-16 04:36:45,126][05218] Updated weights for policy 0, policy_version 46522 (0.0010) -[2023-10-16 04:36:47,351][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 95125504. Throughput: 0: 1793.0, 1: 1783.9. Samples: 23791514. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:36:47,352][03835] Avg episode reward: [(0, '7.190'), (1, '5.810')] -[2023-10-16 04:36:48,050][05219] Updated weights for policy 1, policy_version 46370 (0.0008) -[2023-10-16 04:36:48,419][05219] Updated weights for policy 1, policy_version 46380 (0.0010) -[2023-10-16 04:36:48,782][05219] Updated weights for policy 1, policy_version 46390 (0.0009) -[2023-10-16 04:36:48,946][05218] Updated weights for policy 0, policy_version 46532 (0.0009) -[2023-10-16 04:36:49,154][05219] Updated weights for policy 1, policy_version 46400 (0.0008) -[2023-10-16 04:36:49,324][05218] Updated weights for policy 0, policy_version 46542 (0.0008) -[2023-10-16 04:36:49,702][05218] Updated weights for policy 0, policy_version 46552 (0.0007) -[2023-10-16 04:36:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 95191040. Throughput: 0: 1787.0, 1: 1795.4. Samples: 23813354. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:36:52,352][03835] Avg episode reward: [(0, '6.870'), (1, '6.330')] -[2023-10-16 04:36:52,969][05219] Updated weights for policy 1, policy_version 46410 (0.0009) -[2023-10-16 04:36:53,328][05219] Updated weights for policy 1, policy_version 46420 (0.0010) -[2023-10-16 04:36:53,401][05218] Updated weights for policy 0, policy_version 46562 (0.0008) -[2023-10-16 04:36:53,697][05219] Updated weights for policy 1, policy_version 46430 (0.0008) -[2023-10-16 04:36:53,774][05218] Updated weights for policy 0, policy_version 46572 (0.0009) -[2023-10-16 04:36:54,149][05218] Updated weights for policy 0, policy_version 46582 (0.0007) -[2023-10-16 04:36:54,534][05218] Updated weights for policy 0, policy_version 46592 (0.0010) -[2023-10-16 04:36:57,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 95256576. Throughput: 0: 1793.6, 1: 1779.8. Samples: 23823066. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:36:57,351][03835] Avg episode reward: [(0, '6.750'), (1, '6.850')] -[2023-10-16 04:36:57,663][05219] Updated weights for policy 1, policy_version 46440 (0.0008) -[2023-10-16 04:36:58,032][05219] Updated weights for policy 1, policy_version 46450 (0.0007) -[2023-10-16 04:36:58,306][05218] Updated weights for policy 0, policy_version 46602 (0.0008) -[2023-10-16 04:36:58,393][05219] Updated weights for policy 1, policy_version 46460 (0.0008) -[2023-10-16 04:36:58,679][05218] Updated weights for policy 0, policy_version 46612 (0.0008) -[2023-10-16 04:36:59,062][05218] Updated weights for policy 0, policy_version 46622 (0.0007) -[2023-10-16 04:37:02,085][05219] Updated weights for policy 1, policy_version 46470 (0.0009) -[2023-10-16 04:37:02,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 95322112. Throughput: 0: 1793.9, 1: 1779.9. Samples: 23844988. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:37:02,351][03835] Avg episode reward: [(0, '6.790'), (1, '6.460')] -[2023-10-16 04:37:02,449][05219] Updated weights for policy 1, policy_version 46480 (0.0009) -[2023-10-16 04:37:02,709][05218] Updated weights for policy 0, policy_version 46632 (0.0008) -[2023-10-16 04:37:02,816][05219] Updated weights for policy 1, policy_version 46490 (0.0009) -[2023-10-16 04:37:03,087][05218] Updated weights for policy 0, policy_version 46642 (0.0008) -[2023-10-16 04:37:03,460][05218] Updated weights for policy 0, policy_version 46652 (0.0009) -[2023-10-16 04:37:06,554][05219] Updated weights for policy 1, policy_version 46500 (0.0008) -[2023-10-16 04:37:06,919][05219] Updated weights for policy 1, policy_version 46510 (0.0007) -[2023-10-16 04:37:07,132][05218] Updated weights for policy 0, policy_version 46662 (0.0010) -[2023-10-16 04:37:07,278][05219] Updated weights for policy 1, policy_version 46520 (0.0007) -[2023-10-16 04:37:07,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 95387648. Throughput: 0: 1807.0, 1: 1784.4. Samples: 23866326. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:37:07,351][03835] Avg episode reward: [(0, '6.510'), (1, '6.340')] -[2023-10-16 04:37:07,511][05218] Updated weights for policy 0, policy_version 46672 (0.0010) -[2023-10-16 04:37:07,892][05218] Updated weights for policy 0, policy_version 46682 (0.0008) -[2023-10-16 04:37:11,121][05219] Updated weights for policy 1, policy_version 46530 (0.0007) -[2023-10-16 04:37:11,481][05219] Updated weights for policy 1, policy_version 46540 (0.0009) -[2023-10-16 04:37:11,655][05218] Updated weights for policy 0, policy_version 46692 (0.0009) -[2023-10-16 04:37:11,850][05219] Updated weights for policy 1, policy_version 46550 (0.0007) -[2023-10-16 04:37:12,025][05218] Updated weights for policy 0, policy_version 46702 (0.0008) -[2023-10-16 04:37:12,204][05219] Updated weights for policy 1, policy_version 46560 (0.0007) -[2023-10-16 04:37:12,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 95485952. Throughput: 0: 1798.0, 1: 1778.5. Samples: 23877640. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:37:12,351][03835] Avg episode reward: [(0, '6.630'), (1, '6.950')] -[2023-10-16 04:37:12,406][05218] Updated weights for policy 0, policy_version 46712 (0.0007) -[2023-10-16 04:37:16,174][05219] Updated weights for policy 1, policy_version 46570 (0.0009) -[2023-10-16 04:37:16,214][05218] Updated weights for policy 0, policy_version 46722 (0.0007) -[2023-10-16 04:37:16,536][05219] Updated weights for policy 1, policy_version 46580 (0.0007) -[2023-10-16 04:37:16,576][05218] Updated weights for policy 0, policy_version 46732 (0.0009) -[2023-10-16 04:37:16,900][05219] Updated weights for policy 1, policy_version 46590 (0.0007) -[2023-10-16 04:37:16,950][05218] Updated weights for policy 0, policy_version 46742 (0.0009) -[2023-10-16 04:37:17,332][05218] Updated weights for policy 0, policy_version 46752 (0.0007) -[2023-10-16 04:37:17,350][03835] Fps is (10 sec: 19660.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 95584256. Throughput: 0: 1810.0, 1: 1789.0. Samples: 23899246. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:37:17,351][03835] Avg episode reward: [(0, '6.470'), (1, '6.840')] -[2023-10-16 04:37:20,492][05219] Updated weights for policy 1, policy_version 46600 (0.0008) -[2023-10-16 04:37:20,858][05219] Updated weights for policy 1, policy_version 46610 (0.0008) -[2023-10-16 04:37:21,012][05218] Updated weights for policy 0, policy_version 46762 (0.0009) -[2023-10-16 04:37:21,223][05219] Updated weights for policy 1, policy_version 46620 (0.0007) -[2023-10-16 04:37:21,380][05218] Updated weights for policy 0, policy_version 46772 (0.0009) -[2023-10-16 04:37:21,758][05218] Updated weights for policy 0, policy_version 46782 (0.0009) -[2023-10-16 04:37:22,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 95649792. Throughput: 0: 1790.3, 1: 1765.9. Samples: 23919552. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:37:22,351][03835] Avg episode reward: [(0, '6.480'), (1, '6.330')] -[2023-10-16 04:37:25,220][05219] Updated weights for policy 1, policy_version 46630 (0.0008) -[2023-10-16 04:37:25,418][05218] Updated weights for policy 0, policy_version 46792 (0.0008) -[2023-10-16 04:37:25,589][05219] Updated weights for policy 1, policy_version 46640 (0.0007) -[2023-10-16 04:37:25,781][05218] Updated weights for policy 0, policy_version 46802 (0.0009) -[2023-10-16 04:37:25,949][05219] Updated weights for policy 1, policy_version 46650 (0.0008) -[2023-10-16 04:37:26,160][05218] Updated weights for policy 0, policy_version 46812 (0.0008) -[2023-10-16 04:37:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 95715328. Throughput: 0: 1810.1, 1: 1785.0. Samples: 23931760. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:37:27,351][03835] Avg episode reward: [(0, '7.150'), (1, '6.220')] -[2023-10-16 04:37:29,594][05219] Updated weights for policy 1, policy_version 46660 (0.0008) -[2023-10-16 04:37:29,901][05218] Updated weights for policy 0, policy_version 46822 (0.0007) -[2023-10-16 04:37:29,950][05219] Updated weights for policy 1, policy_version 46670 (0.0008) -[2023-10-16 04:37:30,277][05218] Updated weights for policy 0, policy_version 46832 (0.0008) -[2023-10-16 04:37:30,312][05219] Updated weights for policy 1, policy_version 46680 (0.0009) -[2023-10-16 04:37:30,657][05218] Updated weights for policy 0, policy_version 46842 (0.0009) -[2023-10-16 04:37:32,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 95780864. Throughput: 0: 1797.5, 1: 1765.9. Samples: 23951864. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:37:32,351][03835] Avg episode reward: [(0, '6.050'), (1, '6.210')] -[2023-10-16 04:37:34,127][05219] Updated weights for policy 1, policy_version 46690 (0.0010) -[2023-10-16 04:37:34,395][05218] Updated weights for policy 0, policy_version 46852 (0.0009) -[2023-10-16 04:37:34,490][05219] Updated weights for policy 1, policy_version 46700 (0.0007) -[2023-10-16 04:37:34,759][05218] Updated weights for policy 0, policy_version 46862 (0.0008) -[2023-10-16 04:37:34,850][05219] Updated weights for policy 1, policy_version 46710 (0.0007) -[2023-10-16 04:37:35,132][05218] Updated weights for policy 0, policy_version 46872 (0.0010) -[2023-10-16 04:37:35,216][05219] Updated weights for policy 1, policy_version 46720 (0.0008) -[2023-10-16 04:37:37,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 95846400. Throughput: 0: 1803.0, 1: 1774.2. Samples: 23974326. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:37:37,351][03835] Avg episode reward: [(0, '6.760'), (1, '6.250')] -[2023-10-16 04:37:37,360][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000046720_47841280.pth... -[2023-10-16 04:37:37,360][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000046880_48005120.pth... -[2023-10-16 04:37:37,399][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000045056_46137344.pth -[2023-10-16 04:37:37,399][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000045216_46301184.pth -[2023-10-16 04:37:38,805][05218] Updated weights for policy 0, policy_version 46882 (0.0009) -[2023-10-16 04:37:38,822][05219] Updated weights for policy 1, policy_version 46730 (0.0007) -[2023-10-16 04:37:39,176][05218] Updated weights for policy 0, policy_version 46892 (0.0008) -[2023-10-16 04:37:39,188][05219] Updated weights for policy 1, policy_version 46740 (0.0007) -[2023-10-16 04:37:39,551][05219] Updated weights for policy 1, policy_version 46750 (0.0007) -[2023-10-16 04:37:39,551][05218] Updated weights for policy 0, policy_version 46902 (0.0009) -[2023-10-16 04:37:39,927][05218] Updated weights for policy 0, policy_version 46912 (0.0007) -[2023-10-16 04:37:42,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 95911936. Throughput: 0: 1803.4, 1: 1777.9. Samples: 23984224. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:37:42,352][03835] Avg episode reward: [(0, '6.850'), (1, '6.380')] -[2023-10-16 04:37:43,324][05219] Updated weights for policy 1, policy_version 46760 (0.0008) -[2023-10-16 04:37:43,695][05219] Updated weights for policy 1, policy_version 46770 (0.0007) -[2023-10-16 04:37:43,737][05218] Updated weights for policy 0, policy_version 46922 (0.0009) -[2023-10-16 04:37:44,053][05219] Updated weights for policy 1, policy_version 46780 (0.0007) -[2023-10-16 04:37:44,112][05218] Updated weights for policy 0, policy_version 46932 (0.0008) -[2023-10-16 04:37:44,477][05218] Updated weights for policy 0, policy_version 46942 (0.0007) -[2023-10-16 04:37:47,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 95977472. Throughput: 0: 1800.7, 1: 1787.4. Samples: 24006452. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:37:47,351][03835] Avg episode reward: [(0, '6.630'), (1, '6.840')] -[2023-10-16 04:37:47,824][05219] Updated weights for policy 1, policy_version 46790 (0.0009) -[2023-10-16 04:37:48,207][05219] Updated weights for policy 1, policy_version 46800 (0.0007) -[2023-10-16 04:37:48,326][05218] Updated weights for policy 0, policy_version 46952 (0.0008) -[2023-10-16 04:37:48,564][05219] Updated weights for policy 1, policy_version 46810 (0.0008) -[2023-10-16 04:37:48,705][05218] Updated weights for policy 0, policy_version 46962 (0.0008) -[2023-10-16 04:37:49,080][05218] Updated weights for policy 0, policy_version 46972 (0.0008) -[2023-10-16 04:37:52,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 96043008. Throughput: 0: 1802.1, 1: 1803.7. Samples: 24028588. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:37:52,351][03835] Avg episode reward: [(0, '6.540'), (1, '6.660')] -[2023-10-16 04:37:52,395][05219] Updated weights for policy 1, policy_version 46820 (0.0008) -[2023-10-16 04:37:52,755][05219] Updated weights for policy 1, policy_version 46830 (0.0010) -[2023-10-16 04:37:52,779][05218] Updated weights for policy 0, policy_version 46982 (0.0010) -[2023-10-16 04:37:53,112][05219] Updated weights for policy 1, policy_version 46840 (0.0008) -[2023-10-16 04:37:53,164][05218] Updated weights for policy 0, policy_version 46992 (0.0008) -[2023-10-16 04:37:53,537][05218] Updated weights for policy 0, policy_version 47002 (0.0009) -[2023-10-16 04:37:56,937][05219] Updated weights for policy 1, policy_version 46850 (0.0008) -[2023-10-16 04:37:57,295][05219] Updated weights for policy 1, policy_version 46860 (0.0007) -[2023-10-16 04:37:57,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 96108544. Throughput: 0: 1785.2, 1: 1784.2. Samples: 24038264. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:37:57,351][03835] Avg episode reward: [(0, '6.420'), (1, '6.160')] -[2023-10-16 04:37:57,371][05218] Updated weights for policy 0, policy_version 47012 (0.0009) -[2023-10-16 04:37:57,657][05219] Updated weights for policy 1, policy_version 46870 (0.0009) -[2023-10-16 04:37:57,738][05218] Updated weights for policy 0, policy_version 47022 (0.0007) -[2023-10-16 04:37:58,025][05219] Updated weights for policy 1, policy_version 46880 (0.0008) -[2023-10-16 04:37:58,109][05218] Updated weights for policy 0, policy_version 47032 (0.0009) -[2023-10-16 04:38:01,832][05219] Updated weights for policy 1, policy_version 46890 (0.0009) -[2023-10-16 04:38:01,837][05218] Updated weights for policy 0, policy_version 47042 (0.0009) -[2023-10-16 04:38:02,193][05219] Updated weights for policy 1, policy_version 46900 (0.0008) -[2023-10-16 04:38:02,200][05218] Updated weights for policy 0, policy_version 47052 (0.0007) -[2023-10-16 04:38:02,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 96174080. Throughput: 0: 1788.0, 1: 1793.6. Samples: 24060416. Policy #0 lag: (min: 31.0, avg: 31.3, max: 42.0) -[2023-10-16 04:38:02,351][03835] Avg episode reward: [(0, '6.600'), (1, '6.560')] -[2023-10-16 04:38:02,557][05219] Updated weights for policy 1, policy_version 46910 (0.0008) -[2023-10-16 04:38:02,570][05218] Updated weights for policy 0, policy_version 47062 (0.0008) -[2023-10-16 04:38:02,951][05218] Updated weights for policy 0, policy_version 47072 (0.0009) -[2023-10-16 04:38:06,278][05219] Updated weights for policy 1, policy_version 46920 (0.0008) -[2023-10-16 04:38:06,648][05219] Updated weights for policy 1, policy_version 46930 (0.0010) -[2023-10-16 04:38:06,863][05218] Updated weights for policy 0, policy_version 47082 (0.0009) -[2023-10-16 04:38:07,002][05219] Updated weights for policy 1, policy_version 46940 (0.0008) -[2023-10-16 04:38:07,246][05218] Updated weights for policy 0, policy_version 47092 (0.0009) -[2023-10-16 04:38:07,350][03835] Fps is (10 sec: 16383.4, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 96272384. Throughput: 0: 1789.9, 1: 1781.3. Samples: 24080258. Policy #0 lag: (min: 31.0, avg: 31.3, max: 42.0) -[2023-10-16 04:38:07,352][03835] Avg episode reward: [(0, '6.950'), (1, '6.180')] -[2023-10-16 04:38:07,636][05218] Updated weights for policy 0, policy_version 47102 (0.0008) -[2023-10-16 04:38:10,939][05219] Updated weights for policy 1, policy_version 46950 (0.0008) -[2023-10-16 04:38:11,300][05219] Updated weights for policy 1, policy_version 46960 (0.0007) -[2023-10-16 04:38:11,330][05218] Updated weights for policy 0, policy_version 47112 (0.0008) -[2023-10-16 04:38:11,667][05219] Updated weights for policy 1, policy_version 46970 (0.0008) -[2023-10-16 04:38:11,695][05218] Updated weights for policy 0, policy_version 47122 (0.0008) -[2023-10-16 04:38:12,078][05218] Updated weights for policy 0, policy_version 47132 (0.0009) -[2023-10-16 04:38:12,350][03835] Fps is (10 sec: 19661.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 96370688. Throughput: 0: 1779.9, 1: 1789.6. Samples: 24092384. Policy #0 lag: (min: 31.0, avg: 31.3, max: 42.0) -[2023-10-16 04:38:12,351][03835] Avg episode reward: [(0, '6.730'), (1, '6.260')] -[2023-10-16 04:38:15,467][05219] Updated weights for policy 1, policy_version 46980 (0.0007) -[2023-10-16 04:38:15,826][05218] Updated weights for policy 0, policy_version 47142 (0.0009) -[2023-10-16 04:38:15,834][05219] Updated weights for policy 1, policy_version 46990 (0.0008) -[2023-10-16 04:38:16,197][05219] Updated weights for policy 1, policy_version 47000 (0.0007) -[2023-10-16 04:38:16,201][05218] Updated weights for policy 0, policy_version 47152 (0.0008) -[2023-10-16 04:38:16,583][05218] Updated weights for policy 0, policy_version 47162 (0.0007) -[2023-10-16 04:38:17,350][03835] Fps is (10 sec: 16384.6, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 96436224. Throughput: 0: 1783.4, 1: 1792.4. Samples: 24112778. Policy #0 lag: (min: 31.0, avg: 31.3, max: 42.0) -[2023-10-16 04:38:17,351][03835] Avg episode reward: [(0, '5.620'), (1, '6.960')] -[2023-10-16 04:38:19,867][05219] Updated weights for policy 1, policy_version 47010 (0.0009) -[2023-10-16 04:38:20,233][05219] Updated weights for policy 1, policy_version 47020 (0.0010) -[2023-10-16 04:38:20,450][05218] Updated weights for policy 0, policy_version 47172 (0.0008) -[2023-10-16 04:38:20,593][05219] Updated weights for policy 1, policy_version 47030 (0.0008) -[2023-10-16 04:38:20,826][05218] Updated weights for policy 0, policy_version 47182 (0.0011) -[2023-10-16 04:38:20,953][05219] Updated weights for policy 1, policy_version 47040 (0.0008) -[2023-10-16 04:38:21,200][05218] Updated weights for policy 0, policy_version 47192 (0.0007) -[2023-10-16 04:38:22,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 96501760. Throughput: 0: 1763.7, 1: 1781.2. Samples: 24133844. Policy #0 lag: (min: 31.0, avg: 31.3, max: 42.0) -[2023-10-16 04:38:22,351][03835] Avg episode reward: [(0, '6.810'), (1, '6.440')] -[2023-10-16 04:38:24,819][05218] Updated weights for policy 0, policy_version 47202 (0.0011) -[2023-10-16 04:38:24,855][05219] Updated weights for policy 1, policy_version 47050 (0.0007) -[2023-10-16 04:38:25,189][05218] Updated weights for policy 0, policy_version 47212 (0.0008) -[2023-10-16 04:38:25,218][05219] Updated weights for policy 1, policy_version 47060 (0.0007) -[2023-10-16 04:38:25,568][05218] Updated weights for policy 0, policy_version 47222 (0.0009) -[2023-10-16 04:38:25,580][05219] Updated weights for policy 1, policy_version 47070 (0.0008) -[2023-10-16 04:38:25,936][05218] Updated weights for policy 0, policy_version 47232 (0.0010) -[2023-10-16 04:38:27,351][03835] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 96567296. Throughput: 0: 1783.6, 1: 1789.3. Samples: 24145006. Policy #0 lag: (min: 31.0, avg: 31.3, max: 42.0) -[2023-10-16 04:38:27,352][03835] Avg episode reward: [(0, '6.070'), (1, '6.570')] -[2023-10-16 04:38:29,351][05219] Updated weights for policy 1, policy_version 47080 (0.0008) -[2023-10-16 04:38:29,502][05218] Updated weights for policy 0, policy_version 47242 (0.0009) -[2023-10-16 04:38:29,712][05219] Updated weights for policy 1, policy_version 47090 (0.0008) -[2023-10-16 04:38:29,880][05218] Updated weights for policy 0, policy_version 47252 (0.0009) -[2023-10-16 04:38:30,078][05219] Updated weights for policy 1, policy_version 47100 (0.0007) -[2023-10-16 04:38:30,254][05218] Updated weights for policy 0, policy_version 47262 (0.0011) -[2023-10-16 04:38:32,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 96632832. Throughput: 0: 1772.6, 1: 1773.4. Samples: 24166020. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:38:32,351][03835] Avg episode reward: [(0, '6.370'), (1, '6.250')] -[2023-10-16 04:38:33,856][05219] Updated weights for policy 1, policy_version 47110 (0.0007) -[2023-10-16 04:38:34,120][05218] Updated weights for policy 0, policy_version 47272 (0.0008) -[2023-10-16 04:38:34,235][05219] Updated weights for policy 1, policy_version 47120 (0.0008) -[2023-10-16 04:38:34,495][05218] Updated weights for policy 0, policy_version 47282 (0.0007) -[2023-10-16 04:38:34,598][05219] Updated weights for policy 1, policy_version 47130 (0.0009) -[2023-10-16 04:38:34,878][05218] Updated weights for policy 0, policy_version 47292 (0.0007) -[2023-10-16 04:38:37,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 96698368. Throughput: 0: 1778.7, 1: 1768.3. Samples: 24188204. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:38:37,351][03835] Avg episode reward: [(0, '7.340'), (1, '5.730')] -[2023-10-16 04:38:38,385][05219] Updated weights for policy 1, policy_version 47140 (0.0008) -[2023-10-16 04:38:38,545][05218] Updated weights for policy 0, policy_version 47302 (0.0007) -[2023-10-16 04:38:38,751][05219] Updated weights for policy 1, policy_version 47150 (0.0008) -[2023-10-16 04:38:38,910][05218] Updated weights for policy 0, policy_version 47312 (0.0007) -[2023-10-16 04:38:39,121][05219] Updated weights for policy 1, policy_version 47160 (0.0008) -[2023-10-16 04:38:39,284][05218] Updated weights for policy 0, policy_version 47322 (0.0008) -[2023-10-16 04:38:42,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 96763904. Throughput: 0: 1783.9, 1: 1765.2. Samples: 24197972. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:38:42,351][03835] Avg episode reward: [(0, '6.520'), (1, '5.530')] -[2023-10-16 04:38:42,956][05219] Updated weights for policy 1, policy_version 47170 (0.0008) -[2023-10-16 04:38:43,166][05218] Updated weights for policy 0, policy_version 47332 (0.0008) -[2023-10-16 04:38:43,324][05219] Updated weights for policy 1, policy_version 47180 (0.0008) -[2023-10-16 04:38:43,542][05218] Updated weights for policy 0, policy_version 47342 (0.0008) -[2023-10-16 04:38:43,686][05219] Updated weights for policy 1, policy_version 47190 (0.0007) -[2023-10-16 04:38:43,913][05218] Updated weights for policy 0, policy_version 47352 (0.0008) -[2023-10-16 04:38:44,049][05219] Updated weights for policy 1, policy_version 47200 (0.0007) -[2023-10-16 04:38:47,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 96829440. Throughput: 0: 1782.7, 1: 1767.5. Samples: 24220180. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:38:47,351][03835] Avg episode reward: [(0, '6.130'), (1, '6.640')] -[2023-10-16 04:38:47,588][05218] Updated weights for policy 0, policy_version 47362 (0.0010) -[2023-10-16 04:38:47,821][05219] Updated weights for policy 1, policy_version 47210 (0.0007) -[2023-10-16 04:38:47,957][05218] Updated weights for policy 0, policy_version 47372 (0.0008) -[2023-10-16 04:38:48,179][05219] Updated weights for policy 1, policy_version 47220 (0.0008) -[2023-10-16 04:38:48,333][05218] Updated weights for policy 0, policy_version 47382 (0.0008) -[2023-10-16 04:38:48,548][05219] Updated weights for policy 1, policy_version 47230 (0.0010) -[2023-10-16 04:38:48,709][05218] Updated weights for policy 0, policy_version 47392 (0.0009) -[2023-10-16 04:38:52,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 96894976. Throughput: 0: 1796.9, 1: 1802.9. Samples: 24242248. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:38:52,351][03835] Avg episode reward: [(0, '6.800'), (1, '7.490')] -[2023-10-16 04:38:52,416][05219] Updated weights for policy 1, policy_version 47240 (0.0009) -[2023-10-16 04:38:52,481][05218] Updated weights for policy 0, policy_version 47402 (0.0008) -[2023-10-16 04:38:52,786][05219] Updated weights for policy 1, policy_version 47250 (0.0009) -[2023-10-16 04:38:52,853][05218] Updated weights for policy 0, policy_version 47412 (0.0009) -[2023-10-16 04:38:53,145][05219] Updated weights for policy 1, policy_version 47260 (0.0008) -[2023-10-16 04:38:53,227][05218] Updated weights for policy 0, policy_version 47422 (0.0008) -[2023-10-16 04:38:53,297][04891] Saving new best policy, reward=7.490! -[2023-10-16 04:38:56,913][05219] Updated weights for policy 1, policy_version 47270 (0.0009) -[2023-10-16 04:38:57,033][05218] Updated weights for policy 0, policy_version 47432 (0.0007) -[2023-10-16 04:38:57,264][05219] Updated weights for policy 1, policy_version 47280 (0.0007) -[2023-10-16 04:38:57,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 96960512. Throughput: 0: 1779.1, 1: 1772.0. Samples: 24252182. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:38:57,351][03835] Avg episode reward: [(0, '6.180'), (1, '6.480')] -[2023-10-16 04:38:57,398][05218] Updated weights for policy 0, policy_version 47442 (0.0008) -[2023-10-16 04:38:57,622][05219] Updated weights for policy 1, policy_version 47290 (0.0008) -[2023-10-16 04:38:57,774][05218] Updated weights for policy 0, policy_version 47452 (0.0008) -[2023-10-16 04:39:01,365][05219] Updated weights for policy 1, policy_version 47300 (0.0008) -[2023-10-16 04:39:01,639][05218] Updated weights for policy 0, policy_version 47462 (0.0008) -[2023-10-16 04:39:01,722][05219] Updated weights for policy 1, policy_version 47310 (0.0008) -[2023-10-16 04:39:02,006][05218] Updated weights for policy 0, policy_version 47472 (0.0007) -[2023-10-16 04:39:02,088][05219] Updated weights for policy 1, policy_version 47320 (0.0007) -[2023-10-16 04:39:02,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 97026048. Throughput: 0: 1798.2, 1: 1799.5. Samples: 24274674. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:39:02,351][03835] Avg episode reward: [(0, '6.070'), (1, '7.500')] -[2023-10-16 04:39:02,367][04891] Saving new best policy, reward=7.500! -[2023-10-16 04:39:02,386][05218] Updated weights for policy 0, policy_version 47482 (0.0008) -[2023-10-16 04:39:05,742][05219] Updated weights for policy 1, policy_version 47330 (0.0007) -[2023-10-16 04:39:06,076][05218] Updated weights for policy 0, policy_version 47492 (0.0008) -[2023-10-16 04:39:06,094][05219] Updated weights for policy 1, policy_version 47340 (0.0008) -[2023-10-16 04:39:06,444][05218] Updated weights for policy 0, policy_version 47502 (0.0009) -[2023-10-16 04:39:06,456][05219] Updated weights for policy 1, policy_version 47350 (0.0008) -[2023-10-16 04:39:06,811][05218] Updated weights for policy 0, policy_version 47512 (0.0007) -[2023-10-16 04:39:06,822][05219] Updated weights for policy 1, policy_version 47360 (0.0007) -[2023-10-16 04:39:07,350][03835] Fps is (10 sec: 19660.2, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 97157120. Throughput: 0: 1782.6, 1: 1777.0. Samples: 24294026. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-16 04:39:07,352][03835] Avg episode reward: [(0, '6.860'), (1, '6.520')] -[2023-10-16 04:39:10,636][05219] Updated weights for policy 1, policy_version 47370 (0.0008) -[2023-10-16 04:39:10,653][05218] Updated weights for policy 0, policy_version 47522 (0.0012) -[2023-10-16 04:39:11,001][05219] Updated weights for policy 1, policy_version 47380 (0.0010) -[2023-10-16 04:39:11,023][05218] Updated weights for policy 0, policy_version 47532 (0.0007) -[2023-10-16 04:39:11,358][05219] Updated weights for policy 1, policy_version 47390 (0.0008) -[2023-10-16 04:39:11,396][05218] Updated weights for policy 0, policy_version 47542 (0.0009) -[2023-10-16 04:39:11,776][05218] Updated weights for policy 0, policy_version 47552 (0.0008) -[2023-10-16 04:39:12,350][03835] Fps is (10 sec: 19660.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 97222656. Throughput: 0: 1794.9, 1: 1797.5. Samples: 24306662. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-16 04:39:12,351][03835] Avg episode reward: [(0, '6.610'), (1, '6.370')] -[2023-10-16 04:39:15,106][05219] Updated weights for policy 1, policy_version 47400 (0.0007) -[2023-10-16 04:39:15,481][05219] Updated weights for policy 1, policy_version 47410 (0.0008) -[2023-10-16 04:39:15,615][05218] Updated weights for policy 0, policy_version 47562 (0.0010) -[2023-10-16 04:39:15,837][05219] Updated weights for policy 1, policy_version 47420 (0.0007) -[2023-10-16 04:39:15,985][05218] Updated weights for policy 0, policy_version 47572 (0.0007) -[2023-10-16 04:39:16,360][05218] Updated weights for policy 0, policy_version 47582 (0.0008) -[2023-10-16 04:39:17,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 97288192. Throughput: 0: 1775.6, 1: 1781.3. Samples: 24326082. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-16 04:39:17,351][03835] Avg episode reward: [(0, '6.460'), (1, '6.560')] -[2023-10-16 04:39:19,610][05219] Updated weights for policy 1, policy_version 47430 (0.0007) -[2023-10-16 04:39:19,982][05219] Updated weights for policy 1, policy_version 47440 (0.0008) -[2023-10-16 04:39:20,286][05218] Updated weights for policy 0, policy_version 47592 (0.0008) -[2023-10-16 04:39:20,347][05219] Updated weights for policy 1, policy_version 47450 (0.0010) -[2023-10-16 04:39:20,666][05218] Updated weights for policy 0, policy_version 47602 (0.0008) -[2023-10-16 04:39:21,032][05218] Updated weights for policy 0, policy_version 47612 (0.0007) -[2023-10-16 04:39:22,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 97353728. Throughput: 0: 1772.7, 1: 1789.4. Samples: 24348498. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-16 04:39:22,351][03835] Avg episode reward: [(0, '5.780'), (1, '6.240')] -[2023-10-16 04:39:24,046][05219] Updated weights for policy 1, policy_version 47460 (0.0009) -[2023-10-16 04:39:24,417][05219] Updated weights for policy 1, policy_version 47470 (0.0008) -[2023-10-16 04:39:24,677][05218] Updated weights for policy 0, policy_version 47622 (0.0008) -[2023-10-16 04:39:24,784][05219] Updated weights for policy 1, policy_version 47480 (0.0007) -[2023-10-16 04:39:25,049][05218] Updated weights for policy 0, policy_version 47632 (0.0007) -[2023-10-16 04:39:25,416][05218] Updated weights for policy 0, policy_version 47642 (0.0008) -[2023-10-16 04:39:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 97419264. Throughput: 0: 1783.0, 1: 1789.9. Samples: 24358752. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-16 04:39:27,351][03835] Avg episode reward: [(0, '6.540'), (1, '6.190')] -[2023-10-16 04:39:28,483][05219] Updated weights for policy 1, policy_version 47490 (0.0007) -[2023-10-16 04:39:28,858][05219] Updated weights for policy 1, policy_version 47500 (0.0007) -[2023-10-16 04:39:29,219][05219] Updated weights for policy 1, policy_version 47510 (0.0009) -[2023-10-16 04:39:29,312][05218] Updated weights for policy 0, policy_version 47652 (0.0010) -[2023-10-16 04:39:29,585][05219] Updated weights for policy 1, policy_version 47520 (0.0008) -[2023-10-16 04:39:29,687][05218] Updated weights for policy 0, policy_version 47662 (0.0007) -[2023-10-16 04:39:30,073][05218] Updated weights for policy 0, policy_version 47672 (0.0008) -[2023-10-16 04:39:32,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 97484800. Throughput: 0: 1769.8, 1: 1790.0. Samples: 24380370. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-16 04:39:32,351][03835] Avg episode reward: [(0, '6.360'), (1, '6.760')] -[2023-10-16 04:39:33,298][05219] Updated weights for policy 1, policy_version 47530 (0.0009) -[2023-10-16 04:39:33,657][05219] Updated weights for policy 1, policy_version 47540 (0.0007) -[2023-10-16 04:39:33,669][05218] Updated weights for policy 0, policy_version 47682 (0.0008) -[2023-10-16 04:39:34,016][05219] Updated weights for policy 1, policy_version 47550 (0.0008) -[2023-10-16 04:39:34,052][05218] Updated weights for policy 0, policy_version 47692 (0.0008) -[2023-10-16 04:39:34,423][05218] Updated weights for policy 0, policy_version 47702 (0.0011) -[2023-10-16 04:39:34,792][05218] Updated weights for policy 0, policy_version 47712 (0.0011) -[2023-10-16 04:39:37,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 97550336. Throughput: 0: 1776.8, 1: 1787.6. Samples: 24402648. Policy #0 lag: (min: 9.0, avg: 25.8, max: 41.0) -[2023-10-16 04:39:37,351][03835] Avg episode reward: [(0, '6.260'), (1, '6.470')] -[2023-10-16 04:39:37,360][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000047712_48857088.pth... -[2023-10-16 04:39:37,360][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000047552_48693248.pth... -[2023-10-16 04:39:37,389][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000046048_47153152.pth -[2023-10-16 04:39:37,393][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000045888_46989312.pth -[2023-10-16 04:39:37,942][05219] Updated weights for policy 1, policy_version 47560 (0.0008) -[2023-10-16 04:39:38,304][05219] Updated weights for policy 1, policy_version 47570 (0.0008) -[2023-10-16 04:39:38,635][05218] Updated weights for policy 0, policy_version 47722 (0.0008) -[2023-10-16 04:39:38,669][05219] Updated weights for policy 1, policy_version 47580 (0.0007) -[2023-10-16 04:39:39,007][05218] Updated weights for policy 0, policy_version 47732 (0.0007) -[2023-10-16 04:39:39,395][05218] Updated weights for policy 0, policy_version 47742 (0.0007) -[2023-10-16 04:39:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 97615872. Throughput: 0: 1779.9, 1: 1788.2. Samples: 24412750. Policy #0 lag: (min: 9.0, avg: 25.8, max: 41.0) -[2023-10-16 04:39:42,351][03835] Avg episode reward: [(0, '6.100'), (1, '6.230')] -[2023-10-16 04:39:42,581][05219] Updated weights for policy 1, policy_version 47590 (0.0008) -[2023-10-16 04:39:42,942][05219] Updated weights for policy 1, policy_version 47600 (0.0007) -[2023-10-16 04:39:42,999][05218] Updated weights for policy 0, policy_version 47752 (0.0007) -[2023-10-16 04:39:43,305][05219] Updated weights for policy 1, policy_version 47610 (0.0007) -[2023-10-16 04:39:43,372][05218] Updated weights for policy 0, policy_version 47762 (0.0008) -[2023-10-16 04:39:43,752][05218] Updated weights for policy 0, policy_version 47772 (0.0009) -[2023-10-16 04:39:47,037][05219] Updated weights for policy 1, policy_version 47620 (0.0008) -[2023-10-16 04:39:47,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 97681408. Throughput: 0: 1778.4, 1: 1787.7. Samples: 24435150. Policy #0 lag: (min: 9.0, avg: 25.8, max: 41.0) -[2023-10-16 04:39:47,351][03835] Avg episode reward: [(0, '7.280'), (1, '6.700')] -[2023-10-16 04:39:47,415][05219] Updated weights for policy 1, policy_version 47630 (0.0009) -[2023-10-16 04:39:47,580][05218] Updated weights for policy 0, policy_version 47782 (0.0010) -[2023-10-16 04:39:47,774][05219] Updated weights for policy 1, policy_version 47640 (0.0008) -[2023-10-16 04:39:47,956][05218] Updated weights for policy 0, policy_version 47792 (0.0009) -[2023-10-16 04:39:48,326][05218] Updated weights for policy 0, policy_version 47802 (0.0010) -[2023-10-16 04:39:51,468][05219] Updated weights for policy 1, policy_version 47650 (0.0010) -[2023-10-16 04:39:51,821][05219] Updated weights for policy 1, policy_version 47660 (0.0007) -[2023-10-16 04:39:52,051][05218] Updated weights for policy 0, policy_version 47812 (0.0010) -[2023-10-16 04:39:52,194][05219] Updated weights for policy 1, policy_version 47670 (0.0007) -[2023-10-16 04:39:52,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 97746944. Throughput: 0: 1801.7, 1: 1801.1. Samples: 24456152. Policy #0 lag: (min: 9.0, avg: 25.8, max: 41.0) -[2023-10-16 04:39:52,351][03835] Avg episode reward: [(0, '6.720'), (1, '6.620')] -[2023-10-16 04:39:52,429][05218] Updated weights for policy 0, policy_version 47822 (0.0009) -[2023-10-16 04:39:52,550][05219] Updated weights for policy 1, policy_version 47680 (0.0008) -[2023-10-16 04:39:52,800][05218] Updated weights for policy 0, policy_version 47832 (0.0007) -[2023-10-16 04:39:56,362][05219] Updated weights for policy 1, policy_version 47690 (0.0010) -[2023-10-16 04:39:56,483][05218] Updated weights for policy 0, policy_version 47842 (0.0007) -[2023-10-16 04:39:56,715][05219] Updated weights for policy 1, policy_version 47700 (0.0007) -[2023-10-16 04:39:56,847][05218] Updated weights for policy 0, policy_version 47852 (0.0008) -[2023-10-16 04:39:57,078][05219] Updated weights for policy 1, policy_version 47710 (0.0007) -[2023-10-16 04:39:57,224][05218] Updated weights for policy 0, policy_version 47862 (0.0009) -[2023-10-16 04:39:57,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 97845248. Throughput: 0: 1783.9, 1: 1786.5. Samples: 24467330. Policy #0 lag: (min: 9.0, avg: 25.8, max: 41.0) -[2023-10-16 04:39:57,351][03835] Avg episode reward: [(0, '6.930'), (1, '6.700')] -[2023-10-16 04:39:57,596][05218] Updated weights for policy 0, policy_version 47872 (0.0009) -[2023-10-16 04:40:00,691][05219] Updated weights for policy 1, policy_version 47720 (0.0010) -[2023-10-16 04:40:01,049][05219] Updated weights for policy 1, policy_version 47730 (0.0009) -[2023-10-16 04:40:01,393][05218] Updated weights for policy 0, policy_version 47882 (0.0008) -[2023-10-16 04:40:01,418][05219] Updated weights for policy 1, policy_version 47740 (0.0009) -[2023-10-16 04:40:01,761][05218] Updated weights for policy 0, policy_version 47892 (0.0007) -[2023-10-16 04:40:02,146][05218] Updated weights for policy 0, policy_version 47902 (0.0008) -[2023-10-16 04:40:02,350][03835] Fps is (10 sec: 19660.4, 60 sec: 15291.7, 300 sec: 14440.1). Total num frames: 97943552. Throughput: 0: 1810.0, 1: 1803.8. Samples: 24488704. Policy #0 lag: (min: 9.0, avg: 25.8, max: 41.0) -[2023-10-16 04:40:02,351][03835] Avg episode reward: [(0, '7.290'), (1, '6.880')] -[2023-10-16 04:40:05,232][05219] Updated weights for policy 1, policy_version 47750 (0.0008) -[2023-10-16 04:40:05,616][05219] Updated weights for policy 1, policy_version 47760 (0.0009) -[2023-10-16 04:40:05,793][05218] Updated weights for policy 0, policy_version 47912 (0.0008) -[2023-10-16 04:40:05,979][05219] Updated weights for policy 1, policy_version 47770 (0.0007) -[2023-10-16 04:40:06,164][05218] Updated weights for policy 0, policy_version 47922 (0.0009) -[2023-10-16 04:40:06,548][05218] Updated weights for policy 0, policy_version 47932 (0.0008) -[2023-10-16 04:40:07,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 98009088. Throughput: 0: 1788.6, 1: 1785.8. Samples: 24509346. Policy #0 lag: (min: 31.0, avg: 32.4, max: 56.0) -[2023-10-16 04:40:07,351][03835] Avg episode reward: [(0, '6.090'), (1, '6.810')] -[2023-10-16 04:40:09,606][05219] Updated weights for policy 1, policy_version 47780 (0.0009) -[2023-10-16 04:40:09,969][05219] Updated weights for policy 1, policy_version 47790 (0.0008) -[2023-10-16 04:40:10,328][05219] Updated weights for policy 1, policy_version 47800 (0.0007) -[2023-10-16 04:40:10,383][05218] Updated weights for policy 0, policy_version 47942 (0.0008) -[2023-10-16 04:40:10,756][05218] Updated weights for policy 0, policy_version 47952 (0.0009) -[2023-10-16 04:40:11,139][05218] Updated weights for policy 0, policy_version 47962 (0.0009) -[2023-10-16 04:40:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 98074624. Throughput: 0: 1801.9, 1: 1805.1. Samples: 24521068. Policy #0 lag: (min: 31.0, avg: 32.4, max: 56.0) -[2023-10-16 04:40:12,352][03835] Avg episode reward: [(0, '6.390'), (1, '6.480')] -[2023-10-16 04:40:14,237][05219] Updated weights for policy 1, policy_version 47810 (0.0010) -[2023-10-16 04:40:14,607][05219] Updated weights for policy 1, policy_version 47820 (0.0009) -[2023-10-16 04:40:14,967][05219] Updated weights for policy 1, policy_version 47830 (0.0008) -[2023-10-16 04:40:15,069][05218] Updated weights for policy 0, policy_version 47972 (0.0010) -[2023-10-16 04:40:15,328][05219] Updated weights for policy 1, policy_version 47840 (0.0007) -[2023-10-16 04:40:15,444][05218] Updated weights for policy 0, policy_version 47982 (0.0007) -[2023-10-16 04:40:15,818][05218] Updated weights for policy 0, policy_version 47992 (0.0007) -[2023-10-16 04:40:17,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 98140160. Throughput: 0: 1790.2, 1: 1783.9. Samples: 24541206. Policy #0 lag: (min: 31.0, avg: 32.4, max: 56.0) -[2023-10-16 04:40:17,351][03835] Avg episode reward: [(0, '6.420'), (1, '6.570')] -[2023-10-16 04:40:19,167][05219] Updated weights for policy 1, policy_version 47850 (0.0010) -[2023-10-16 04:40:19,542][05219] Updated weights for policy 1, policy_version 47860 (0.0008) -[2023-10-16 04:40:19,597][05218] Updated weights for policy 0, policy_version 48002 (0.0009) -[2023-10-16 04:40:19,908][05219] Updated weights for policy 1, policy_version 47870 (0.0007) -[2023-10-16 04:40:19,973][05218] Updated weights for policy 0, policy_version 48012 (0.0009) -[2023-10-16 04:40:20,350][05218] Updated weights for policy 0, policy_version 48022 (0.0008) -[2023-10-16 04:40:20,727][05218] Updated weights for policy 0, policy_version 48032 (0.0008) -[2023-10-16 04:40:22,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 98205696. Throughput: 0: 1789.1, 1: 1789.4. Samples: 24563682. Policy #0 lag: (min: 31.0, avg: 32.4, max: 56.0) -[2023-10-16 04:40:22,351][03835] Avg episode reward: [(0, '6.850'), (1, '6.940')] -[2023-10-16 04:40:23,560][05219] Updated weights for policy 1, policy_version 47880 (0.0008) -[2023-10-16 04:40:23,917][05219] Updated weights for policy 1, policy_version 47890 (0.0008) -[2023-10-16 04:40:24,284][05219] Updated weights for policy 1, policy_version 47900 (0.0008) -[2023-10-16 04:40:24,367][05218] Updated weights for policy 0, policy_version 48042 (0.0007) -[2023-10-16 04:40:24,739][05218] Updated weights for policy 0, policy_version 48052 (0.0008) -[2023-10-16 04:40:25,112][05218] Updated weights for policy 0, policy_version 48062 (0.0007) -[2023-10-16 04:40:27,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 98271232. Throughput: 0: 1784.0, 1: 1786.9. Samples: 24573436. Policy #0 lag: (min: 31.0, avg: 32.4, max: 56.0) -[2023-10-16 04:40:27,351][03835] Avg episode reward: [(0, '6.040'), (1, '7.390')] -[2023-10-16 04:40:28,105][05219] Updated weights for policy 1, policy_version 47910 (0.0010) -[2023-10-16 04:40:28,465][05219] Updated weights for policy 1, policy_version 47920 (0.0009) -[2023-10-16 04:40:28,834][05219] Updated weights for policy 1, policy_version 47930 (0.0008) -[2023-10-16 04:40:28,880][05218] Updated weights for policy 0, policy_version 48072 (0.0008) -[2023-10-16 04:40:29,263][05218] Updated weights for policy 0, policy_version 48082 (0.0009) -[2023-10-16 04:40:29,633][05218] Updated weights for policy 0, policy_version 48092 (0.0007) -[2023-10-16 04:40:32,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 98336768. Throughput: 0: 1793.0, 1: 1780.8. Samples: 24595970. Policy #0 lag: (min: 31.0, avg: 32.4, max: 56.0) -[2023-10-16 04:40:32,352][03835] Avg episode reward: [(0, '6.100'), (1, '6.580')] -[2023-10-16 04:40:32,704][05219] Updated weights for policy 1, policy_version 47940 (0.0009) -[2023-10-16 04:40:33,069][05219] Updated weights for policy 1, policy_version 47950 (0.0008) -[2023-10-16 04:40:33,171][05218] Updated weights for policy 0, policy_version 48102 (0.0008) -[2023-10-16 04:40:33,434][05219] Updated weights for policy 1, policy_version 47960 (0.0009) -[2023-10-16 04:40:33,543][05218] Updated weights for policy 0, policy_version 48112 (0.0008) -[2023-10-16 04:40:33,913][05218] Updated weights for policy 0, policy_version 48122 (0.0008) -[2023-10-16 04:40:37,344][05219] Updated weights for policy 1, policy_version 47970 (0.0009) -[2023-10-16 04:40:37,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 98402304. Throughput: 0: 1805.6, 1: 1798.4. Samples: 24618336. Policy #0 lag: (min: 31.0, avg: 32.4, max: 56.0) -[2023-10-16 04:40:37,352][03835] Avg episode reward: [(0, '6.030'), (1, '6.310')] -[2023-10-16 04:40:37,662][05218] Updated weights for policy 0, policy_version 48132 (0.0010) -[2023-10-16 04:40:37,701][05219] Updated weights for policy 1, policy_version 47980 (0.0008) -[2023-10-16 04:40:38,038][05218] Updated weights for policy 0, policy_version 48142 (0.0009) -[2023-10-16 04:40:38,066][05219] Updated weights for policy 1, policy_version 47990 (0.0007) -[2023-10-16 04:40:38,409][05218] Updated weights for policy 0, policy_version 48152 (0.0009) -[2023-10-16 04:40:38,419][05219] Updated weights for policy 1, policy_version 48000 (0.0007) -[2023-10-16 04:40:42,144][05219] Updated weights for policy 1, policy_version 48010 (0.0008) -[2023-10-16 04:40:42,203][05218] Updated weights for policy 0, policy_version 48162 (0.0009) -[2023-10-16 04:40:42,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 98467840. Throughput: 0: 1791.6, 1: 1782.8. Samples: 24628178. Policy #0 lag: (min: 10.0, avg: 14.6, max: 42.0) -[2023-10-16 04:40:42,351][03835] Avg episode reward: [(0, '6.840'), (1, '6.380')] -[2023-10-16 04:40:42,513][05219] Updated weights for policy 1, policy_version 48020 (0.0008) -[2023-10-16 04:40:42,574][05218] Updated weights for policy 0, policy_version 48172 (0.0008) -[2023-10-16 04:40:42,879][05219] Updated weights for policy 1, policy_version 48030 (0.0007) -[2023-10-16 04:40:42,945][05218] Updated weights for policy 0, policy_version 48182 (0.0007) -[2023-10-16 04:40:43,319][05218] Updated weights for policy 0, policy_version 48192 (0.0008) -[2023-10-16 04:40:46,724][05219] Updated weights for policy 1, policy_version 48040 (0.0008) -[2023-10-16 04:40:47,015][05218] Updated weights for policy 0, policy_version 48202 (0.0008) -[2023-10-16 04:40:47,079][05219] Updated weights for policy 1, policy_version 48050 (0.0007) -[2023-10-16 04:40:47,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 98533376. Throughput: 0: 1802.2, 1: 1794.7. Samples: 24650564. Policy #0 lag: (min: 10.0, avg: 14.6, max: 42.0) -[2023-10-16 04:40:47,351][03835] Avg episode reward: [(0, '7.310'), (1, '6.310')] -[2023-10-16 04:40:47,388][05218] Updated weights for policy 0, policy_version 48212 (0.0008) -[2023-10-16 04:40:47,450][05219] Updated weights for policy 1, policy_version 48060 (0.0007) -[2023-10-16 04:40:47,762][05218] Updated weights for policy 0, policy_version 48222 (0.0008) -[2023-10-16 04:40:51,427][05219] Updated weights for policy 1, policy_version 48070 (0.0008) -[2023-10-16 04:40:51,545][05218] Updated weights for policy 0, policy_version 48232 (0.0008) -[2023-10-16 04:40:51,799][05219] Updated weights for policy 1, policy_version 48080 (0.0007) -[2023-10-16 04:40:51,927][05218] Updated weights for policy 0, policy_version 48242 (0.0007) -[2023-10-16 04:40:52,160][05219] Updated weights for policy 1, policy_version 48090 (0.0007) -[2023-10-16 04:40:52,294][05218] Updated weights for policy 0, policy_version 48252 (0.0008) -[2023-10-16 04:40:52,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 98598912. Throughput: 0: 1798.1, 1: 1779.8. Samples: 24670350. Policy #0 lag: (min: 10.0, avg: 14.6, max: 42.0) -[2023-10-16 04:40:52,351][03835] Avg episode reward: [(0, '7.020'), (1, '6.690')] -[2023-10-16 04:40:55,908][05219] Updated weights for policy 1, policy_version 48100 (0.0009) -[2023-10-16 04:40:56,073][05218] Updated weights for policy 0, policy_version 48262 (0.0007) -[2023-10-16 04:40:56,269][05219] Updated weights for policy 1, policy_version 48110 (0.0009) -[2023-10-16 04:40:56,452][05218] Updated weights for policy 0, policy_version 48272 (0.0009) -[2023-10-16 04:40:56,631][05219] Updated weights for policy 1, policy_version 48120 (0.0007) -[2023-10-16 04:40:56,822][05218] Updated weights for policy 0, policy_version 48282 (0.0008) -[2023-10-16 04:40:57,350][03835] Fps is (10 sec: 19660.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 98729984. Throughput: 0: 1802.0, 1: 1786.0. Samples: 24682528. Policy #0 lag: (min: 10.0, avg: 14.6, max: 42.0) -[2023-10-16 04:40:57,351][03835] Avg episode reward: [(0, '6.950'), (1, '6.490')] -[2023-10-16 04:41:00,387][05219] Updated weights for policy 1, policy_version 48130 (0.0008) -[2023-10-16 04:41:00,530][05218] Updated weights for policy 0, policy_version 48292 (0.0009) -[2023-10-16 04:41:00,759][05219] Updated weights for policy 1, policy_version 48140 (0.0008) -[2023-10-16 04:41:00,908][05218] Updated weights for policy 0, policy_version 48302 (0.0009) -[2023-10-16 04:41:01,125][05219] Updated weights for policy 1, policy_version 48150 (0.0008) -[2023-10-16 04:41:01,275][05218] Updated weights for policy 0, policy_version 48312 (0.0009) -[2023-10-16 04:41:01,484][05219] Updated weights for policy 1, policy_version 48160 (0.0008) -[2023-10-16 04:41:02,350][03835] Fps is (10 sec: 19660.8, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 98795520. Throughput: 0: 1805.1, 1: 1786.1. Samples: 24702810. Policy #0 lag: (min: 10.0, avg: 14.6, max: 42.0) -[2023-10-16 04:41:02,351][03835] Avg episode reward: [(0, '6.680'), (1, '7.040')] -[2023-10-16 04:41:05,019][05218] Updated weights for policy 0, policy_version 48322 (0.0011) -[2023-10-16 04:41:05,278][05219] Updated weights for policy 1, policy_version 48170 (0.0007) -[2023-10-16 04:41:05,391][05218] Updated weights for policy 0, policy_version 48332 (0.0009) -[2023-10-16 04:41:05,642][05219] Updated weights for policy 1, policy_version 48180 (0.0010) -[2023-10-16 04:41:05,758][05218] Updated weights for policy 0, policy_version 48342 (0.0008) -[2023-10-16 04:41:06,001][05219] Updated weights for policy 1, policy_version 48190 (0.0008) -[2023-10-16 04:41:06,132][05218] Updated weights for policy 0, policy_version 48352 (0.0009) -[2023-10-16 04:41:07,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 98861056. Throughput: 0: 1795.7, 1: 1764.1. Samples: 24723872. Policy #0 lag: (min: 10.0, avg: 14.6, max: 42.0) -[2023-10-16 04:41:07,351][03835] Avg episode reward: [(0, '6.530'), (1, '6.390')] -[2023-10-16 04:41:09,830][05219] Updated weights for policy 1, policy_version 48200 (0.0009) -[2023-10-16 04:41:10,067][05218] Updated weights for policy 0, policy_version 48362 (0.0008) -[2023-10-16 04:41:10,186][05219] Updated weights for policy 1, policy_version 48210 (0.0009) -[2023-10-16 04:41:10,438][05218] Updated weights for policy 0, policy_version 48372 (0.0009) -[2023-10-16 04:41:10,561][05219] Updated weights for policy 1, policy_version 48220 (0.0009) -[2023-10-16 04:41:10,816][05218] Updated weights for policy 0, policy_version 48382 (0.0009) -[2023-10-16 04:41:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 98926592. Throughput: 0: 1807.9, 1: 1780.6. Samples: 24734920. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:41:12,351][03835] Avg episode reward: [(0, '6.710'), (1, '6.690')] -[2023-10-16 04:41:14,440][05219] Updated weights for policy 1, policy_version 48230 (0.0010) -[2023-10-16 04:41:14,653][05218] Updated weights for policy 0, policy_version 48392 (0.0009) -[2023-10-16 04:41:14,811][05219] Updated weights for policy 1, policy_version 48240 (0.0008) -[2023-10-16 04:41:15,041][05218] Updated weights for policy 0, policy_version 48402 (0.0008) -[2023-10-16 04:41:15,176][05219] Updated weights for policy 1, policy_version 48250 (0.0009) -[2023-10-16 04:41:15,413][05218] Updated weights for policy 0, policy_version 48412 (0.0009) -[2023-10-16 04:41:17,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 98992128. Throughput: 0: 1778.7, 1: 1764.3. Samples: 24755406. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:41:17,352][03835] Avg episode reward: [(0, '6.840'), (1, '6.380')] -[2023-10-16 04:41:18,875][05219] Updated weights for policy 1, policy_version 48260 (0.0008) -[2023-10-16 04:41:19,137][05218] Updated weights for policy 0, policy_version 48422 (0.0009) -[2023-10-16 04:41:19,231][05219] Updated weights for policy 1, policy_version 48270 (0.0009) -[2023-10-16 04:41:19,505][05218] Updated weights for policy 0, policy_version 48432 (0.0008) -[2023-10-16 04:41:19,597][05219] Updated weights for policy 1, policy_version 48280 (0.0008) -[2023-10-16 04:41:19,884][05218] Updated weights for policy 0, policy_version 48442 (0.0008) -[2023-10-16 04:41:22,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 99057664. Throughput: 0: 1775.0, 1: 1764.5. Samples: 24777612. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:41:22,351][03835] Avg episode reward: [(0, '6.130'), (1, '6.260')] -[2023-10-16 04:41:23,371][05219] Updated weights for policy 1, policy_version 48290 (0.0007) -[2023-10-16 04:41:23,693][05218] Updated weights for policy 0, policy_version 48452 (0.0010) -[2023-10-16 04:41:23,730][05219] Updated weights for policy 1, policy_version 48300 (0.0007) -[2023-10-16 04:41:24,067][05218] Updated weights for policy 0, policy_version 48462 (0.0009) -[2023-10-16 04:41:24,093][05219] Updated weights for policy 1, policy_version 48310 (0.0007) -[2023-10-16 04:41:24,443][05218] Updated weights for policy 0, policy_version 48472 (0.0009) -[2023-10-16 04:41:24,459][05219] Updated weights for policy 1, policy_version 48320 (0.0008) -[2023-10-16 04:41:27,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 99123200. Throughput: 0: 1772.8, 1: 1764.1. Samples: 24787340. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:41:27,351][03835] Avg episode reward: [(0, '6.120'), (1, '6.410')] -[2023-10-16 04:41:28,276][05218] Updated weights for policy 0, policy_version 48482 (0.0009) -[2023-10-16 04:41:28,434][05219] Updated weights for policy 1, policy_version 48330 (0.0008) -[2023-10-16 04:41:28,650][05218] Updated weights for policy 0, policy_version 48492 (0.0008) -[2023-10-16 04:41:28,800][05219] Updated weights for policy 1, policy_version 48340 (0.0009) -[2023-10-16 04:41:29,026][05218] Updated weights for policy 0, policy_version 48502 (0.0009) -[2023-10-16 04:41:29,156][05219] Updated weights for policy 1, policy_version 48350 (0.0007) -[2023-10-16 04:41:29,405][05218] Updated weights for policy 0, policy_version 48512 (0.0010) -[2023-10-16 04:41:32,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 99188736. Throughput: 0: 1771.1, 1: 1760.8. Samples: 24809502. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:41:32,351][03835] Avg episode reward: [(0, '7.030'), (1, '6.670')] -[2023-10-16 04:41:33,030][05219] Updated weights for policy 1, policy_version 48360 (0.0007) -[2023-10-16 04:41:33,080][05218] Updated weights for policy 0, policy_version 48522 (0.0008) -[2023-10-16 04:41:33,388][05219] Updated weights for policy 1, policy_version 48370 (0.0008) -[2023-10-16 04:41:33,449][05218] Updated weights for policy 0, policy_version 48532 (0.0007) -[2023-10-16 04:41:33,745][05219] Updated weights for policy 1, policy_version 48380 (0.0007) -[2023-10-16 04:41:33,825][05218] Updated weights for policy 0, policy_version 48542 (0.0008) -[2023-10-16 04:41:37,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 99254272. Throughput: 0: 1792.8, 1: 1788.9. Samples: 24831528. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:41:37,351][03835] Avg episode reward: [(0, '6.580'), (1, '6.240')] -[2023-10-16 04:41:37,359][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000048384_49545216.pth... -[2023-10-16 04:41:37,395][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000046720_47841280.pth -[2023-10-16 04:41:37,629][05218] Updated weights for policy 0, policy_version 48552 (0.0009) -[2023-10-16 04:41:37,775][05219] Updated weights for policy 1, policy_version 48390 (0.0010) -[2023-10-16 04:41:38,005][05218] Updated weights for policy 0, policy_version 48562 (0.0009) -[2023-10-16 04:41:38,142][05219] Updated weights for policy 1, policy_version 48400 (0.0007) -[2023-10-16 04:41:38,382][05218] Updated weights for policy 0, policy_version 48572 (0.0007) -[2023-10-16 04:41:38,505][05219] Updated weights for policy 1, policy_version 48410 (0.0007) -[2023-10-16 04:41:38,530][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000048576_49741824.pth... -[2023-10-16 04:41:38,560][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000046880_48005120.pth -[2023-10-16 04:41:42,083][05218] Updated weights for policy 0, policy_version 48582 (0.0009) -[2023-10-16 04:41:42,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 99319808. Throughput: 0: 1764.7, 1: 1760.9. Samples: 24841178. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:41:42,351][03835] Avg episode reward: [(0, '6.910'), (1, '6.670')] -[2023-10-16 04:41:42,365][05219] Updated weights for policy 1, policy_version 48420 (0.0008) -[2023-10-16 04:41:42,458][05218] Updated weights for policy 0, policy_version 48592 (0.0008) -[2023-10-16 04:41:42,725][05219] Updated weights for policy 1, policy_version 48430 (0.0008) -[2023-10-16 04:41:42,828][05218] Updated weights for policy 0, policy_version 48602 (0.0009) -[2023-10-16 04:41:43,103][05219] Updated weights for policy 1, policy_version 48440 (0.0009) -[2023-10-16 04:41:46,534][05218] Updated weights for policy 0, policy_version 48612 (0.0009) -[2023-10-16 04:41:46,808][05219] Updated weights for policy 1, policy_version 48450 (0.0010) -[2023-10-16 04:41:46,914][05218] Updated weights for policy 0, policy_version 48622 (0.0008) -[2023-10-16 04:41:47,160][05219] Updated weights for policy 1, policy_version 48460 (0.0010) -[2023-10-16 04:41:47,294][05218] Updated weights for policy 0, policy_version 48632 (0.0009) -[2023-10-16 04:41:47,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 99385344. Throughput: 0: 1797.1, 1: 1774.6. Samples: 24863534. Policy #0 lag: (min: 26.0, avg: 27.0, max: 44.0) -[2023-10-16 04:41:47,351][03835] Avg episode reward: [(0, '6.880'), (1, '6.530')] -[2023-10-16 04:41:47,540][05219] Updated weights for policy 1, policy_version 48470 (0.0008) -[2023-10-16 04:41:47,900][05219] Updated weights for policy 1, policy_version 48480 (0.0010) -[2023-10-16 04:41:51,122][05218] Updated weights for policy 0, policy_version 48642 (0.0008) -[2023-10-16 04:41:51,487][05218] Updated weights for policy 0, policy_version 48652 (0.0008) -[2023-10-16 04:41:51,681][05219] Updated weights for policy 1, policy_version 48490 (0.0009) -[2023-10-16 04:41:51,860][05218] Updated weights for policy 0, policy_version 48662 (0.0007) -[2023-10-16 04:41:52,049][05219] Updated weights for policy 1, policy_version 48500 (0.0009) -[2023-10-16 04:41:52,243][05218] Updated weights for policy 0, policy_version 48672 (0.0009) -[2023-10-16 04:41:52,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 99483648. Throughput: 0: 1780.4, 1: 1767.9. Samples: 24883546. Policy #0 lag: (min: 26.0, avg: 27.0, max: 44.0) -[2023-10-16 04:41:52,351][03835] Avg episode reward: [(0, '6.360'), (1, '5.870')] -[2023-10-16 04:41:52,412][05219] Updated weights for policy 1, policy_version 48510 (0.0007) -[2023-10-16 04:41:55,979][05218] Updated weights for policy 0, policy_version 48682 (0.0009) -[2023-10-16 04:41:56,287][05219] Updated weights for policy 1, policy_version 48520 (0.0009) -[2023-10-16 04:41:56,358][05218] Updated weights for policy 0, policy_version 48692 (0.0009) -[2023-10-16 04:41:56,650][05219] Updated weights for policy 1, policy_version 48530 (0.0007) -[2023-10-16 04:41:56,724][05218] Updated weights for policy 0, policy_version 48702 (0.0008) -[2023-10-16 04:41:57,021][05219] Updated weights for policy 1, policy_version 48540 (0.0009) -[2023-10-16 04:41:57,350][03835] Fps is (10 sec: 19660.8, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 99581952. Throughput: 0: 1798.9, 1: 1771.6. Samples: 24895596. Policy #0 lag: (min: 26.0, avg: 27.0, max: 44.0) -[2023-10-16 04:41:57,351][03835] Avg episode reward: [(0, '5.700'), (1, '6.730')] -[2023-10-16 04:42:00,542][05218] Updated weights for policy 0, policy_version 48712 (0.0009) -[2023-10-16 04:42:00,830][05219] Updated weights for policy 1, policy_version 48550 (0.0009) -[2023-10-16 04:42:00,912][05218] Updated weights for policy 0, policy_version 48722 (0.0008) -[2023-10-16 04:42:01,205][05219] Updated weights for policy 1, policy_version 48560 (0.0007) -[2023-10-16 04:42:01,288][05218] Updated weights for policy 0, policy_version 48732 (0.0009) -[2023-10-16 04:42:01,560][05219] Updated weights for policy 1, policy_version 48570 (0.0008) -[2023-10-16 04:42:02,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 99647488. Throughput: 0: 1789.1, 1: 1775.9. Samples: 24915830. Policy #0 lag: (min: 26.0, avg: 27.0, max: 44.0) -[2023-10-16 04:42:02,351][03835] Avg episode reward: [(0, '7.310'), (1, '6.850')] -[2023-10-16 04:42:04,948][05218] Updated weights for policy 0, policy_version 48742 (0.0008) -[2023-10-16 04:42:05,319][05218] Updated weights for policy 0, policy_version 48752 (0.0008) -[2023-10-16 04:42:05,365][05219] Updated weights for policy 1, policy_version 48580 (0.0008) -[2023-10-16 04:42:05,703][05218] Updated weights for policy 0, policy_version 48762 (0.0009) -[2023-10-16 04:42:05,725][05219] Updated weights for policy 1, policy_version 48590 (0.0008) -[2023-10-16 04:42:06,089][05219] Updated weights for policy 1, policy_version 48600 (0.0010) -[2023-10-16 04:42:07,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 99713024. Throughput: 0: 1793.0, 1: 1755.2. Samples: 24937280. Policy #0 lag: (min: 26.0, avg: 27.0, max: 44.0) -[2023-10-16 04:42:07,351][03835] Avg episode reward: [(0, '6.810'), (1, '6.600')] -[2023-10-16 04:42:09,318][05218] Updated weights for policy 0, policy_version 48772 (0.0007) -[2023-10-16 04:42:09,696][05218] Updated weights for policy 0, policy_version 48782 (0.0008) -[2023-10-16 04:42:09,750][05219] Updated weights for policy 1, policy_version 48610 (0.0009) -[2023-10-16 04:42:10,072][05218] Updated weights for policy 0, policy_version 48792 (0.0008) -[2023-10-16 04:42:10,110][05219] Updated weights for policy 1, policy_version 48620 (0.0007) -[2023-10-16 04:42:10,478][05219] Updated weights for policy 1, policy_version 48630 (0.0009) -[2023-10-16 04:42:10,841][05219] Updated weights for policy 1, policy_version 48640 (0.0010) -[2023-10-16 04:42:12,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 99778560. Throughput: 0: 1791.6, 1: 1777.5. Samples: 24947950. Policy #0 lag: (min: 26.0, avg: 27.0, max: 44.0) -[2023-10-16 04:42:12,351][03835] Avg episode reward: [(0, '7.010'), (1, '7.120')] -[2023-10-16 04:42:13,994][05218] Updated weights for policy 0, policy_version 48802 (0.0008) -[2023-10-16 04:42:14,361][05218] Updated weights for policy 0, policy_version 48812 (0.0008) -[2023-10-16 04:42:14,662][05219] Updated weights for policy 1, policy_version 48650 (0.0008) -[2023-10-16 04:42:14,735][05218] Updated weights for policy 0, policy_version 48822 (0.0008) -[2023-10-16 04:42:15,027][05219] Updated weights for policy 1, policy_version 48660 (0.0007) -[2023-10-16 04:42:15,111][05218] Updated weights for policy 0, policy_version 48832 (0.0008) -[2023-10-16 04:42:15,380][05219] Updated weights for policy 1, policy_version 48670 (0.0007) -[2023-10-16 04:42:17,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 99844096. Throughput: 0: 1778.9, 1: 1760.4. Samples: 24968766. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-16 04:42:17,351][03835] Avg episode reward: [(0, '7.380'), (1, '6.940')] -[2023-10-16 04:42:18,814][05218] Updated weights for policy 0, policy_version 48842 (0.0009) -[2023-10-16 04:42:19,119][05219] Updated weights for policy 1, policy_version 48680 (0.0008) -[2023-10-16 04:42:19,188][05218] Updated weights for policy 0, policy_version 48852 (0.0009) -[2023-10-16 04:42:19,484][05219] Updated weights for policy 1, policy_version 48690 (0.0007) -[2023-10-16 04:42:19,572][05218] Updated weights for policy 0, policy_version 48862 (0.0010) -[2023-10-16 04:42:19,843][05219] Updated weights for policy 1, policy_version 48700 (0.0008) -[2023-10-16 04:42:22,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 99909632. Throughput: 0: 1785.9, 1: 1763.7. Samples: 24991262. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-16 04:42:22,352][03835] Avg episode reward: [(0, '6.770'), (1, '6.000')] -[2023-10-16 04:42:23,395][05218] Updated weights for policy 0, policy_version 48872 (0.0011) -[2023-10-16 04:42:23,764][05219] Updated weights for policy 1, policy_version 48710 (0.0008) -[2023-10-16 04:42:23,783][05218] Updated weights for policy 0, policy_version 48882 (0.0009) -[2023-10-16 04:42:24,139][05219] Updated weights for policy 1, policy_version 48720 (0.0008) -[2023-10-16 04:42:24,150][05218] Updated weights for policy 0, policy_version 48892 (0.0008) -[2023-10-16 04:42:24,506][05219] Updated weights for policy 1, policy_version 48730 (0.0009) -[2023-10-16 04:42:27,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 99975168. Throughput: 0: 1779.1, 1: 1766.8. Samples: 25000744. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-16 04:42:27,351][03835] Avg episode reward: [(0, '6.250'), (1, '6.470')] -[2023-10-16 04:42:27,891][05218] Updated weights for policy 0, policy_version 48902 (0.0008) -[2023-10-16 04:42:28,263][05218] Updated weights for policy 0, policy_version 48912 (0.0009) -[2023-10-16 04:42:28,378][05219] Updated weights for policy 1, policy_version 48740 (0.0008) -[2023-10-16 04:42:28,641][05218] Updated weights for policy 0, policy_version 48922 (0.0007) -[2023-10-16 04:42:28,743][05219] Updated weights for policy 1, policy_version 48750 (0.0007) -[2023-10-16 04:42:29,106][05219] Updated weights for policy 1, policy_version 48760 (0.0007) -[2023-10-16 04:42:32,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 100040704. Throughput: 0: 1776.4, 1: 1765.1. Samples: 25022898. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-16 04:42:32,351][03835] Avg episode reward: [(0, '6.740'), (1, '6.750')] -[2023-10-16 04:42:32,465][05218] Updated weights for policy 0, policy_version 48932 (0.0009) -[2023-10-16 04:42:32,833][05218] Updated weights for policy 0, policy_version 48942 (0.0009) -[2023-10-16 04:42:33,001][05219] Updated weights for policy 1, policy_version 48770 (0.0007) -[2023-10-16 04:42:33,217][05218] Updated weights for policy 0, policy_version 48952 (0.0008) -[2023-10-16 04:42:33,364][05219] Updated weights for policy 1, policy_version 48780 (0.0009) -[2023-10-16 04:42:33,728][05219] Updated weights for policy 1, policy_version 48790 (0.0008) -[2023-10-16 04:42:34,093][05219] Updated weights for policy 1, policy_version 48800 (0.0008) -[2023-10-16 04:42:36,900][05218] Updated weights for policy 0, policy_version 48962 (0.0007) -[2023-10-16 04:42:37,273][05218] Updated weights for policy 0, policy_version 48972 (0.0009) -[2023-10-16 04:42:37,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 100106240. Throughput: 0: 1794.6, 1: 1785.2. Samples: 25044636. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-16 04:42:37,351][03835] Avg episode reward: [(0, '6.670'), (1, '6.420')] -[2023-10-16 04:42:37,654][05218] Updated weights for policy 0, policy_version 48982 (0.0007) -[2023-10-16 04:42:37,835][05219] Updated weights for policy 1, policy_version 48810 (0.0009) -[2023-10-16 04:42:38,024][05218] Updated weights for policy 0, policy_version 48992 (0.0008) -[2023-10-16 04:42:38,190][05219] Updated weights for policy 1, policy_version 48820 (0.0008) -[2023-10-16 04:42:38,551][05219] Updated weights for policy 1, policy_version 48830 (0.0010) -[2023-10-16 04:42:41,691][05218] Updated weights for policy 0, policy_version 49002 (0.0009) -[2023-10-16 04:42:42,072][05218] Updated weights for policy 0, policy_version 49012 (0.0010) -[2023-10-16 04:42:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 100171776. Throughput: 0: 1778.5, 1: 1765.5. Samples: 25055074. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-16 04:42:42,351][03835] Avg episode reward: [(0, '6.720'), (1, '6.180')] -[2023-10-16 04:42:42,443][05218] Updated weights for policy 0, policy_version 49022 (0.0007) -[2023-10-16 04:42:42,460][05219] Updated weights for policy 1, policy_version 48840 (0.0008) -[2023-10-16 04:42:42,833][05219] Updated weights for policy 1, policy_version 48850 (0.0008) -[2023-10-16 04:42:43,200][05219] Updated weights for policy 1, policy_version 48860 (0.0008) -[2023-10-16 04:42:46,004][05218] Updated weights for policy 0, policy_version 49032 (0.0011) -[2023-10-16 04:42:46,383][05218] Updated weights for policy 0, policy_version 49042 (0.0008) -[2023-10-16 04:42:46,762][05218] Updated weights for policy 0, policy_version 49052 (0.0008) -[2023-10-16 04:42:47,090][05219] Updated weights for policy 1, policy_version 48870 (0.0009) -[2023-10-16 04:42:47,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 100270080. Throughput: 0: 1798.5, 1: 1774.8. Samples: 25076630. Policy #0 lag: (min: 27.0, avg: 27.0, max: 30.0) -[2023-10-16 04:42:47,351][03835] Avg episode reward: [(0, '6.720'), (1, '7.140')] -[2023-10-16 04:42:47,455][05219] Updated weights for policy 1, policy_version 48880 (0.0007) -[2023-10-16 04:42:47,821][05219] Updated weights for policy 1, policy_version 48890 (0.0007) -[2023-10-16 04:42:50,431][05218] Updated weights for policy 0, policy_version 49062 (0.0009) -[2023-10-16 04:42:50,808][05218] Updated weights for policy 0, policy_version 49072 (0.0011) -[2023-10-16 04:42:51,190][05218] Updated weights for policy 0, policy_version 49082 (0.0008) -[2023-10-16 04:42:51,585][05219] Updated weights for policy 1, policy_version 48900 (0.0008) -[2023-10-16 04:42:51,953][05219] Updated weights for policy 1, policy_version 48910 (0.0008) -[2023-10-16 04:42:52,313][05219] Updated weights for policy 1, policy_version 48920 (0.0007) -[2023-10-16 04:42:52,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 100335616. Throughput: 0: 1787.0, 1: 1783.9. Samples: 25097972. Policy #0 lag: (min: 27.0, avg: 27.0, max: 30.0) -[2023-10-16 04:42:52,351][03835] Avg episode reward: [(0, '6.900'), (1, '6.940')] -[2023-10-16 04:42:54,959][05218] Updated weights for policy 0, policy_version 49092 (0.0008) -[2023-10-16 04:42:55,333][05218] Updated weights for policy 0, policy_version 49102 (0.0008) -[2023-10-16 04:42:55,706][05218] Updated weights for policy 0, policy_version 49112 (0.0009) -[2023-10-16 04:42:56,147][05219] Updated weights for policy 1, policy_version 48930 (0.0007) -[2023-10-16 04:42:56,510][05219] Updated weights for policy 1, policy_version 48940 (0.0007) -[2023-10-16 04:42:56,873][05219] Updated weights for policy 1, policy_version 48950 (0.0007) -[2023-10-16 04:42:57,236][05219] Updated weights for policy 1, policy_version 48960 (0.0009) -[2023-10-16 04:42:57,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 100433920. Throughput: 0: 1804.6, 1: 1777.3. Samples: 25109136. Policy #0 lag: (min: 27.0, avg: 27.0, max: 30.0) -[2023-10-16 04:42:57,352][03835] Avg episode reward: [(0, '7.650'), (1, '6.660')] -[2023-10-16 04:42:57,353][04766] Saving new best policy, reward=7.650! -[2023-10-16 04:42:59,304][05218] Updated weights for policy 0, policy_version 49122 (0.0008) -[2023-10-16 04:42:59,681][05218] Updated weights for policy 0, policy_version 49132 (0.0007) -[2023-10-16 04:43:00,050][05218] Updated weights for policy 0, policy_version 49142 (0.0007) -[2023-10-16 04:43:00,422][05218] Updated weights for policy 0, policy_version 49152 (0.0009) -[2023-10-16 04:43:01,044][05219] Updated weights for policy 1, policy_version 48970 (0.0010) -[2023-10-16 04:43:01,408][05219] Updated weights for policy 1, policy_version 48980 (0.0008) -[2023-10-16 04:43:01,761][05219] Updated weights for policy 1, policy_version 48990 (0.0009) -[2023-10-16 04:43:02,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 100499456. Throughput: 0: 1803.4, 1: 1793.3. Samples: 25130620. Policy #0 lag: (min: 27.0, avg: 27.0, max: 30.0) -[2023-10-16 04:43:02,351][03835] Avg episode reward: [(0, '6.470'), (1, '5.890')] -[2023-10-16 04:43:04,234][05218] Updated weights for policy 0, policy_version 49162 (0.0009) -[2023-10-16 04:43:04,616][05218] Updated weights for policy 0, policy_version 49172 (0.0007) -[2023-10-16 04:43:04,990][05218] Updated weights for policy 0, policy_version 49182 (0.0007) -[2023-10-16 04:43:05,471][05219] Updated weights for policy 1, policy_version 49000 (0.0008) -[2023-10-16 04:43:05,849][05219] Updated weights for policy 1, policy_version 49010 (0.0009) -[2023-10-16 04:43:06,214][05219] Updated weights for policy 1, policy_version 49020 (0.0010) -[2023-10-16 04:43:07,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 100564992. Throughput: 0: 1802.2, 1: 1771.3. Samples: 25152068. Policy #0 lag: (min: 27.0, avg: 27.0, max: 30.0) -[2023-10-16 04:43:07,351][03835] Avg episode reward: [(0, '6.830'), (1, '6.580')] -[2023-10-16 04:43:08,843][05218] Updated weights for policy 0, policy_version 49192 (0.0008) -[2023-10-16 04:43:09,225][05218] Updated weights for policy 0, policy_version 49202 (0.0007) -[2023-10-16 04:43:09,598][05218] Updated weights for policy 0, policy_version 49212 (0.0007) -[2023-10-16 04:43:09,968][05219] Updated weights for policy 1, policy_version 49030 (0.0010) -[2023-10-16 04:43:10,355][05219] Updated weights for policy 1, policy_version 49040 (0.0008) -[2023-10-16 04:43:10,715][05219] Updated weights for policy 1, policy_version 49050 (0.0008) -[2023-10-16 04:43:12,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 100630528. Throughput: 0: 1804.8, 1: 1796.4. Samples: 25162800. Policy #0 lag: (min: 27.0, avg: 27.0, max: 30.0) -[2023-10-16 04:43:12,351][03835] Avg episode reward: [(0, '7.150'), (1, '6.480')] -[2023-10-16 04:43:13,232][05218] Updated weights for policy 0, policy_version 49222 (0.0009) -[2023-10-16 04:43:13,612][05218] Updated weights for policy 0, policy_version 49232 (0.0009) -[2023-10-16 04:43:13,994][05218] Updated weights for policy 0, policy_version 49242 (0.0007) -[2023-10-16 04:43:14,297][05219] Updated weights for policy 1, policy_version 49060 (0.0008) -[2023-10-16 04:43:14,655][05219] Updated weights for policy 1, policy_version 49070 (0.0009) -[2023-10-16 04:43:15,022][05219] Updated weights for policy 1, policy_version 49080 (0.0008) -[2023-10-16 04:43:17,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 100696064. Throughput: 0: 1803.8, 1: 1788.0. Samples: 25184532. Policy #0 lag: (min: 27.0, avg: 27.0, max: 30.0) -[2023-10-16 04:43:17,351][03835] Avg episode reward: [(0, '6.960'), (1, '6.830')] -[2023-10-16 04:43:17,752][05218] Updated weights for policy 0, policy_version 49252 (0.0008) -[2023-10-16 04:43:18,135][05218] Updated weights for policy 0, policy_version 49262 (0.0009) -[2023-10-16 04:43:18,510][05218] Updated weights for policy 0, policy_version 49272 (0.0009) -[2023-10-16 04:43:18,753][05219] Updated weights for policy 1, policy_version 49090 (0.0008) -[2023-10-16 04:43:19,102][05219] Updated weights for policy 1, policy_version 49100 (0.0008) -[2023-10-16 04:43:19,459][05219] Updated weights for policy 1, policy_version 49110 (0.0008) -[2023-10-16 04:43:19,832][05219] Updated weights for policy 1, policy_version 49120 (0.0009) -[2023-10-16 04:43:22,154][05218] Updated weights for policy 0, policy_version 49282 (0.0008) -[2023-10-16 04:43:22,351][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 100761600. Throughput: 0: 1809.3, 1: 1790.5. Samples: 25206630. Policy #0 lag: (min: 21.0, avg: 27.1, max: 53.0) -[2023-10-16 04:43:22,352][03835] Avg episode reward: [(0, '6.640'), (1, '6.520')] -[2023-10-16 04:43:22,531][05218] Updated weights for policy 0, policy_version 49292 (0.0008) -[2023-10-16 04:43:22,915][05218] Updated weights for policy 0, policy_version 49302 (0.0010) -[2023-10-16 04:43:23,282][05218] Updated weights for policy 0, policy_version 49312 (0.0010) -[2023-10-16 04:43:23,475][05219] Updated weights for policy 1, policy_version 49130 (0.0009) -[2023-10-16 04:43:23,846][05219] Updated weights for policy 1, policy_version 49140 (0.0008) -[2023-10-16 04:43:24,216][05219] Updated weights for policy 1, policy_version 49150 (0.0008) -[2023-10-16 04:43:27,025][05218] Updated weights for policy 0, policy_version 49322 (0.0009) -[2023-10-16 04:43:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 100827136. Throughput: 0: 1799.8, 1: 1791.2. Samples: 25216670. Policy #0 lag: (min: 21.0, avg: 27.1, max: 53.0) -[2023-10-16 04:43:27,351][03835] Avg episode reward: [(0, '6.640'), (1, '6.270')] -[2023-10-16 04:43:27,405][05218] Updated weights for policy 0, policy_version 49332 (0.0009) -[2023-10-16 04:43:27,793][05218] Updated weights for policy 0, policy_version 49342 (0.0009) -[2023-10-16 04:43:28,073][05219] Updated weights for policy 1, policy_version 49160 (0.0008) -[2023-10-16 04:43:28,429][05219] Updated weights for policy 1, policy_version 49170 (0.0008) -[2023-10-16 04:43:28,800][05219] Updated weights for policy 1, policy_version 49180 (0.0008) -[2023-10-16 04:43:31,438][05218] Updated weights for policy 0, policy_version 49352 (0.0008) -[2023-10-16 04:43:31,809][05218] Updated weights for policy 0, policy_version 49362 (0.0007) -[2023-10-16 04:43:32,190][05218] Updated weights for policy 0, policy_version 49372 (0.0007) -[2023-10-16 04:43:32,350][03835] Fps is (10 sec: 16384.7, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 100925440. Throughput: 0: 1810.4, 1: 1792.2. Samples: 25238748. Policy #0 lag: (min: 21.0, avg: 27.1, max: 53.0) -[2023-10-16 04:43:32,351][03835] Avg episode reward: [(0, '6.700'), (1, '7.700')] -[2023-10-16 04:43:32,558][05219] Updated weights for policy 1, policy_version 49190 (0.0008) -[2023-10-16 04:43:32,926][05219] Updated weights for policy 1, policy_version 49200 (0.0008) -[2023-10-16 04:43:33,295][05219] Updated weights for policy 1, policy_version 49210 (0.0009) -[2023-10-16 04:43:33,515][04891] Saving new best policy, reward=7.700! -[2023-10-16 04:43:35,936][05218] Updated weights for policy 0, policy_version 49382 (0.0008) -[2023-10-16 04:43:36,318][05218] Updated weights for policy 0, policy_version 49392 (0.0009) -[2023-10-16 04:43:36,699][05218] Updated weights for policy 0, policy_version 49402 (0.0009) -[2023-10-16 04:43:37,234][05219] Updated weights for policy 1, policy_version 49220 (0.0011) -[2023-10-16 04:43:37,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 100990976. Throughput: 0: 1789.8, 1: 1804.1. Samples: 25259696. Policy #0 lag: (min: 21.0, avg: 27.1, max: 53.0) -[2023-10-16 04:43:37,351][03835] Avg episode reward: [(0, '6.110'), (1, '7.040')] -[2023-10-16 04:43:37,360][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000049408_50593792.pth... -[2023-10-16 04:43:37,394][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000047712_48857088.pth -[2023-10-16 04:43:37,599][05219] Updated weights for policy 1, policy_version 49230 (0.0008) -[2023-10-16 04:43:37,960][05219] Updated weights for policy 1, policy_version 49240 (0.0010) -[2023-10-16 04:43:38,251][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000049248_50429952.pth... -[2023-10-16 04:43:38,291][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000047552_48693248.pth -[2023-10-16 04:43:40,630][05218] Updated weights for policy 0, policy_version 49412 (0.0010) -[2023-10-16 04:43:40,996][05218] Updated weights for policy 0, policy_version 49422 (0.0008) -[2023-10-16 04:43:41,382][05218] Updated weights for policy 0, policy_version 49432 (0.0009) -[2023-10-16 04:43:41,790][05219] Updated weights for policy 1, policy_version 49250 (0.0007) -[2023-10-16 04:43:42,166][05219] Updated weights for policy 1, policy_version 49260 (0.0009) -[2023-10-16 04:43:42,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 101056512. Throughput: 0: 1806.6, 1: 1787.1. Samples: 25270850. Policy #0 lag: (min: 21.0, avg: 27.1, max: 53.0) -[2023-10-16 04:43:42,351][03835] Avg episode reward: [(0, '6.470'), (1, '6.720')] -[2023-10-16 04:43:42,531][05219] Updated weights for policy 1, policy_version 49270 (0.0008) -[2023-10-16 04:43:42,906][05219] Updated weights for policy 1, policy_version 49280 (0.0011) -[2023-10-16 04:43:45,126][05218] Updated weights for policy 0, policy_version 49442 (0.0009) -[2023-10-16 04:43:45,508][05218] Updated weights for policy 0, policy_version 49452 (0.0007) -[2023-10-16 04:43:45,880][05218] Updated weights for policy 0, policy_version 49462 (0.0007) -[2023-10-16 04:43:46,251][05218] Updated weights for policy 0, policy_version 49472 (0.0007) -[2023-10-16 04:43:46,739][05219] Updated weights for policy 1, policy_version 49290 (0.0010) -[2023-10-16 04:43:47,097][05219] Updated weights for policy 1, policy_version 49300 (0.0008) -[2023-10-16 04:43:47,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 101122048. Throughput: 0: 1781.2, 1: 1792.6. Samples: 25291438. Policy #0 lag: (min: 21.0, avg: 27.1, max: 53.0) -[2023-10-16 04:43:47,351][03835] Avg episode reward: [(0, '6.920'), (1, '6.770')] -[2023-10-16 04:43:47,458][05219] Updated weights for policy 1, policy_version 49310 (0.0010) -[2023-10-16 04:43:49,992][05218] Updated weights for policy 0, policy_version 49482 (0.0009) -[2023-10-16 04:43:50,374][05218] Updated weights for policy 0, policy_version 49492 (0.0007) -[2023-10-16 04:43:50,741][05218] Updated weights for policy 0, policy_version 49502 (0.0007) -[2023-10-16 04:43:51,271][05219] Updated weights for policy 1, policy_version 49320 (0.0008) -[2023-10-16 04:43:51,638][05219] Updated weights for policy 1, policy_version 49330 (0.0007) -[2023-10-16 04:43:52,003][05219] Updated weights for policy 1, policy_version 49340 (0.0007) -[2023-10-16 04:43:52,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 101220352. Throughput: 0: 1784.4, 1: 1780.5. Samples: 25312486. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-16 04:43:52,351][03835] Avg episode reward: [(0, '6.820'), (1, '6.570')] -[2023-10-16 04:43:54,534][05218] Updated weights for policy 0, policy_version 49512 (0.0009) -[2023-10-16 04:43:54,913][05218] Updated weights for policy 0, policy_version 49522 (0.0009) -[2023-10-16 04:43:55,289][05218] Updated weights for policy 0, policy_version 49532 (0.0008) -[2023-10-16 04:43:55,621][05219] Updated weights for policy 1, policy_version 49350 (0.0009) -[2023-10-16 04:43:56,004][05219] Updated weights for policy 1, policy_version 49360 (0.0011) -[2023-10-16 04:43:56,368][05219] Updated weights for policy 1, policy_version 49370 (0.0011) -[2023-10-16 04:43:57,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 101285888. Throughput: 0: 1785.8, 1: 1788.7. Samples: 25323652. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-16 04:43:57,351][03835] Avg episode reward: [(0, '6.920'), (1, '6.900')] -[2023-10-16 04:43:58,966][05218] Updated weights for policy 0, policy_version 49542 (0.0008) -[2023-10-16 04:43:59,335][05218] Updated weights for policy 0, policy_version 49552 (0.0009) -[2023-10-16 04:43:59,709][05218] Updated weights for policy 0, policy_version 49562 (0.0008) -[2023-10-16 04:44:00,287][05219] Updated weights for policy 1, policy_version 49380 (0.0009) -[2023-10-16 04:44:00,660][05219] Updated weights for policy 1, policy_version 49390 (0.0009) -[2023-10-16 04:44:01,017][05219] Updated weights for policy 1, policy_version 49400 (0.0007) -[2023-10-16 04:44:02,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 101351424. Throughput: 0: 1783.5, 1: 1780.6. Samples: 25344916. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-16 04:44:02,351][03835] Avg episode reward: [(0, '6.780'), (1, '6.980')] -[2023-10-16 04:44:03,493][05218] Updated weights for policy 0, policy_version 49572 (0.0007) -[2023-10-16 04:44:03,869][05218] Updated weights for policy 0, policy_version 49582 (0.0009) -[2023-10-16 04:44:04,253][05218] Updated weights for policy 0, policy_version 49592 (0.0010) -[2023-10-16 04:44:04,698][05219] Updated weights for policy 1, policy_version 49410 (0.0007) -[2023-10-16 04:44:05,057][05219] Updated weights for policy 1, policy_version 49420 (0.0007) -[2023-10-16 04:44:05,430][05219] Updated weights for policy 1, policy_version 49430 (0.0009) -[2023-10-16 04:44:05,788][05219] Updated weights for policy 1, policy_version 49440 (0.0010) -[2023-10-16 04:44:07,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 101416960. Throughput: 0: 1788.7, 1: 1773.8. Samples: 25366944. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-16 04:44:07,351][03835] Avg episode reward: [(0, '6.680'), (1, '6.850')] -[2023-10-16 04:44:08,056][05218] Updated weights for policy 0, policy_version 49602 (0.0010) -[2023-10-16 04:44:08,432][05218] Updated weights for policy 0, policy_version 49612 (0.0010) -[2023-10-16 04:44:08,808][05218] Updated weights for policy 0, policy_version 49622 (0.0008) -[2023-10-16 04:44:09,179][05218] Updated weights for policy 0, policy_version 49632 (0.0009) -[2023-10-16 04:44:09,503][05219] Updated weights for policy 1, policy_version 49450 (0.0007) -[2023-10-16 04:44:09,872][05219] Updated weights for policy 1, policy_version 49460 (0.0010) -[2023-10-16 04:44:10,230][05219] Updated weights for policy 1, policy_version 49470 (0.0008) -[2023-10-16 04:44:12,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 101482496. Throughput: 0: 1781.3, 1: 1783.2. Samples: 25377074. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-16 04:44:12,352][03835] Avg episode reward: [(0, '6.520'), (1, '6.410')] -[2023-10-16 04:44:13,064][05218] Updated weights for policy 0, policy_version 49642 (0.0008) -[2023-10-16 04:44:13,441][05218] Updated weights for policy 0, policy_version 49652 (0.0008) -[2023-10-16 04:44:13,823][05218] Updated weights for policy 0, policy_version 49662 (0.0007) -[2023-10-16 04:44:14,121][05219] Updated weights for policy 1, policy_version 49480 (0.0009) -[2023-10-16 04:44:14,489][05219] Updated weights for policy 1, policy_version 49490 (0.0009) -[2023-10-16 04:44:14,850][05219] Updated weights for policy 1, policy_version 49500 (0.0010) -[2023-10-16 04:44:17,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 101548032. Throughput: 0: 1786.7, 1: 1777.3. Samples: 25399130. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-16 04:44:17,351][03835] Avg episode reward: [(0, '6.710'), (1, '5.880')] -[2023-10-16 04:44:17,440][05218] Updated weights for policy 0, policy_version 49672 (0.0008) -[2023-10-16 04:44:17,822][05218] Updated weights for policy 0, policy_version 49682 (0.0008) -[2023-10-16 04:44:18,206][05218] Updated weights for policy 0, policy_version 49692 (0.0008) -[2023-10-16 04:44:18,712][05219] Updated weights for policy 1, policy_version 49510 (0.0009) -[2023-10-16 04:44:19,073][05219] Updated weights for policy 1, policy_version 49520 (0.0007) -[2023-10-16 04:44:19,432][05219] Updated weights for policy 1, policy_version 49530 (0.0007) -[2023-10-16 04:44:21,872][05218] Updated weights for policy 0, policy_version 49702 (0.0007) -[2023-10-16 04:44:22,251][05218] Updated weights for policy 0, policy_version 49712 (0.0008) -[2023-10-16 04:44:22,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.6, 300 sec: 14218.0). Total num frames: 101613568. Throughput: 0: 1797.8, 1: 1782.0. Samples: 25420788. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-16 04:44:22,351][03835] Avg episode reward: [(0, '6.810'), (1, '6.690')] -[2023-10-16 04:44:22,625][05218] Updated weights for policy 0, policy_version 49722 (0.0008) -[2023-10-16 04:44:23,135][05219] Updated weights for policy 1, policy_version 49540 (0.0008) -[2023-10-16 04:44:23,495][05219] Updated weights for policy 1, policy_version 49550 (0.0011) -[2023-10-16 04:44:23,858][05219] Updated weights for policy 1, policy_version 49560 (0.0008) -[2023-10-16 04:44:26,200][05218] Updated weights for policy 0, policy_version 49732 (0.0009) -[2023-10-16 04:44:26,572][05218] Updated weights for policy 0, policy_version 49742 (0.0007) -[2023-10-16 04:44:26,954][05218] Updated weights for policy 0, policy_version 49752 (0.0009) -[2023-10-16 04:44:27,351][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 101711872. Throughput: 0: 1785.0, 1: 1781.0. Samples: 25431318. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-16 04:44:27,351][03835] Avg episode reward: [(0, '6.760'), (1, '6.240')] -[2023-10-16 04:44:27,703][05219] Updated weights for policy 1, policy_version 49570 (0.0009) -[2023-10-16 04:44:28,072][05219] Updated weights for policy 1, policy_version 49580 (0.0008) -[2023-10-16 04:44:28,436][05219] Updated weights for policy 1, policy_version 49590 (0.0007) -[2023-10-16 04:44:28,798][05219] Updated weights for policy 1, policy_version 49600 (0.0009) -[2023-10-16 04:44:30,786][05218] Updated weights for policy 0, policy_version 49762 (0.0010) -[2023-10-16 04:44:31,156][05218] Updated weights for policy 0, policy_version 49772 (0.0009) -[2023-10-16 04:44:31,533][05218] Updated weights for policy 0, policy_version 49782 (0.0009) -[2023-10-16 04:44:31,904][05218] Updated weights for policy 0, policy_version 49792 (0.0009) -[2023-10-16 04:44:32,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 101777408. Throughput: 0: 1806.2, 1: 1785.7. Samples: 25453076. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-16 04:44:32,351][03835] Avg episode reward: [(0, '6.160'), (1, '6.520')] -[2023-10-16 04:44:32,475][05219] Updated weights for policy 1, policy_version 49610 (0.0008) -[2023-10-16 04:44:32,847][05219] Updated weights for policy 1, policy_version 49620 (0.0007) -[2023-10-16 04:44:33,204][05219] Updated weights for policy 1, policy_version 49630 (0.0011) -[2023-10-16 04:44:35,668][05218] Updated weights for policy 0, policy_version 49802 (0.0009) -[2023-10-16 04:44:36,030][05218] Updated weights for policy 0, policy_version 49812 (0.0009) -[2023-10-16 04:44:36,404][05218] Updated weights for policy 0, policy_version 49822 (0.0008) -[2023-10-16 04:44:36,835][05219] Updated weights for policy 1, policy_version 49640 (0.0008) -[2023-10-16 04:44:37,209][05219] Updated weights for policy 1, policy_version 49650 (0.0008) -[2023-10-16 04:44:37,351][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 101842944. Throughput: 0: 1791.8, 1: 1807.3. Samples: 25474450. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-16 04:44:37,352][03835] Avg episode reward: [(0, '6.170'), (1, '6.330')] -[2023-10-16 04:44:37,574][05219] Updated weights for policy 1, policy_version 49660 (0.0008) -[2023-10-16 04:44:40,184][05218] Updated weights for policy 0, policy_version 49832 (0.0007) -[2023-10-16 04:44:40,558][05218] Updated weights for policy 0, policy_version 49842 (0.0009) -[2023-10-16 04:44:40,932][05218] Updated weights for policy 0, policy_version 49852 (0.0010) -[2023-10-16 04:44:41,340][05219] Updated weights for policy 1, policy_version 49670 (0.0008) -[2023-10-16 04:44:41,721][05219] Updated weights for policy 1, policy_version 49680 (0.0007) -[2023-10-16 04:44:42,083][05219] Updated weights for policy 1, policy_version 49690 (0.0007) -[2023-10-16 04:44:42,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 101941248. Throughput: 0: 1813.6, 1: 1792.7. Samples: 25485936. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-16 04:44:42,351][03835] Avg episode reward: [(0, '7.060'), (1, '6.960')] -[2023-10-16 04:44:44,602][05218] Updated weights for policy 0, policy_version 49862 (0.0007) -[2023-10-16 04:44:44,972][05218] Updated weights for policy 0, policy_version 49872 (0.0007) -[2023-10-16 04:44:45,354][05218] Updated weights for policy 0, policy_version 49882 (0.0007) -[2023-10-16 04:44:45,822][05219] Updated weights for policy 1, policy_version 49700 (0.0007) -[2023-10-16 04:44:46,190][05219] Updated weights for policy 1, policy_version 49710 (0.0008) -[2023-10-16 04:44:46,552][05219] Updated weights for policy 1, policy_version 49720 (0.0007) -[2023-10-16 04:44:47,350][03835] Fps is (10 sec: 16384.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 102006784. Throughput: 0: 1793.9, 1: 1801.7. Samples: 25506716. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-16 04:44:47,351][03835] Avg episode reward: [(0, '6.020'), (1, '6.660')] -[2023-10-16 04:44:49,058][05218] Updated weights for policy 0, policy_version 49892 (0.0009) -[2023-10-16 04:44:49,429][05218] Updated weights for policy 0, policy_version 49902 (0.0009) -[2023-10-16 04:44:49,806][05218] Updated weights for policy 0, policy_version 49912 (0.0009) -[2023-10-16 04:44:50,374][05219] Updated weights for policy 1, policy_version 49730 (0.0007) -[2023-10-16 04:44:50,735][05219] Updated weights for policy 1, policy_version 49740 (0.0008) -[2023-10-16 04:44:51,094][05219] Updated weights for policy 1, policy_version 49750 (0.0008) -[2023-10-16 04:44:51,465][05219] Updated weights for policy 1, policy_version 49760 (0.0007) -[2023-10-16 04:44:52,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 102072320. Throughput: 0: 1797.8, 1: 1790.0. Samples: 25528392. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-16 04:44:52,351][03835] Avg episode reward: [(0, '6.660'), (1, '6.730')] -[2023-10-16 04:44:53,514][05218] Updated weights for policy 0, policy_version 49922 (0.0008) -[2023-10-16 04:44:53,893][05218] Updated weights for policy 0, policy_version 49932 (0.0009) -[2023-10-16 04:44:54,257][05218] Updated weights for policy 0, policy_version 49942 (0.0010) -[2023-10-16 04:44:54,636][05218] Updated weights for policy 0, policy_version 49952 (0.0008) -[2023-10-16 04:44:55,202][05219] Updated weights for policy 1, policy_version 49770 (0.0007) -[2023-10-16 04:44:55,581][05219] Updated weights for policy 1, policy_version 49780 (0.0007) -[2023-10-16 04:44:55,945][05219] Updated weights for policy 1, policy_version 49790 (0.0007) -[2023-10-16 04:44:57,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 102137856. Throughput: 0: 1794.9, 1: 1807.4. Samples: 25539176. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:44:57,351][03835] Avg episode reward: [(0, '6.920'), (1, '7.020')] -[2023-10-16 04:44:58,491][05218] Updated weights for policy 0, policy_version 49962 (0.0008) -[2023-10-16 04:44:58,870][05218] Updated weights for policy 0, policy_version 49972 (0.0008) -[2023-10-16 04:44:59,242][05218] Updated weights for policy 0, policy_version 49982 (0.0009) -[2023-10-16 04:44:59,696][05219] Updated weights for policy 1, policy_version 49800 (0.0010) -[2023-10-16 04:45:00,059][05219] Updated weights for policy 1, policy_version 49810 (0.0010) -[2023-10-16 04:45:00,422][05219] Updated weights for policy 1, policy_version 49820 (0.0010) -[2023-10-16 04:45:02,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 102203392. Throughput: 0: 1788.7, 1: 1790.5. Samples: 25560194. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:45:02,351][03835] Avg episode reward: [(0, '6.770'), (1, '6.680')] -[2023-10-16 04:45:03,210][05218] Updated weights for policy 0, policy_version 49992 (0.0009) -[2023-10-16 04:45:03,575][05218] Updated weights for policy 0, policy_version 50002 (0.0007) -[2023-10-16 04:45:03,953][05218] Updated weights for policy 0, policy_version 50012 (0.0007) -[2023-10-16 04:45:04,247][05219] Updated weights for policy 1, policy_version 49830 (0.0010) -[2023-10-16 04:45:04,623][05219] Updated weights for policy 1, policy_version 49840 (0.0009) -[2023-10-16 04:45:04,985][05219] Updated weights for policy 1, policy_version 49850 (0.0009) -[2023-10-16 04:45:07,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 102268928. Throughput: 0: 1811.6, 1: 1787.4. Samples: 25582744. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:45:07,351][03835] Avg episode reward: [(0, '7.430'), (1, '7.310')] -[2023-10-16 04:45:07,620][05218] Updated weights for policy 0, policy_version 50022 (0.0008) -[2023-10-16 04:45:07,998][05218] Updated weights for policy 0, policy_version 50032 (0.0007) -[2023-10-16 04:45:08,374][05218] Updated weights for policy 0, policy_version 50042 (0.0009) -[2023-10-16 04:45:08,850][05219] Updated weights for policy 1, policy_version 49860 (0.0009) -[2023-10-16 04:45:09,218][05219] Updated weights for policy 1, policy_version 49870 (0.0010) -[2023-10-16 04:45:09,580][05219] Updated weights for policy 1, policy_version 49880 (0.0008) -[2023-10-16 04:45:12,003][05218] Updated weights for policy 0, policy_version 50052 (0.0008) -[2023-10-16 04:45:12,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 102334464. Throughput: 0: 1795.1, 1: 1787.3. Samples: 25592526. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:45:12,351][03835] Avg episode reward: [(0, '7.030'), (1, '6.990')] -[2023-10-16 04:45:12,382][05218] Updated weights for policy 0, policy_version 50062 (0.0008) -[2023-10-16 04:45:12,745][05218] Updated weights for policy 0, policy_version 50072 (0.0010) -[2023-10-16 04:45:13,384][05219] Updated weights for policy 1, policy_version 49890 (0.0007) -[2023-10-16 04:45:13,755][05219] Updated weights for policy 1, policy_version 49900 (0.0009) -[2023-10-16 04:45:14,117][05219] Updated weights for policy 1, policy_version 49910 (0.0008) -[2023-10-16 04:45:14,487][05219] Updated weights for policy 1, policy_version 49920 (0.0007) -[2023-10-16 04:45:16,458][05218] Updated weights for policy 0, policy_version 50082 (0.0008) -[2023-10-16 04:45:16,851][05218] Updated weights for policy 0, policy_version 50092 (0.0008) -[2023-10-16 04:45:17,213][05218] Updated weights for policy 0, policy_version 50102 (0.0009) -[2023-10-16 04:45:17,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 102400000. Throughput: 0: 1809.1, 1: 1785.2. Samples: 25614820. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:45:17,351][03835] Avg episode reward: [(0, '7.150'), (1, '7.320')] -[2023-10-16 04:45:17,593][05218] Updated weights for policy 0, policy_version 50112 (0.0008) -[2023-10-16 04:45:18,315][05219] Updated weights for policy 1, policy_version 49930 (0.0009) -[2023-10-16 04:45:18,676][05219] Updated weights for policy 1, policy_version 49940 (0.0009) -[2023-10-16 04:45:19,048][05219] Updated weights for policy 1, policy_version 49950 (0.0009) -[2023-10-16 04:45:21,367][05218] Updated weights for policy 0, policy_version 50122 (0.0007) -[2023-10-16 04:45:21,740][05218] Updated weights for policy 0, policy_version 50132 (0.0007) -[2023-10-16 04:45:22,131][05218] Updated weights for policy 0, policy_version 50142 (0.0008) -[2023-10-16 04:45:22,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 102498304. Throughput: 0: 1788.6, 1: 1799.1. Samples: 25635896. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:45:22,351][03835] Avg episode reward: [(0, '7.080'), (1, '6.800')] -[2023-10-16 04:45:22,603][05219] Updated weights for policy 1, policy_version 49960 (0.0007) -[2023-10-16 04:45:22,972][05219] Updated weights for policy 1, policy_version 49970 (0.0007) -[2023-10-16 04:45:23,327][05219] Updated weights for policy 1, policy_version 49980 (0.0008) -[2023-10-16 04:45:25,923][05218] Updated weights for policy 0, policy_version 50152 (0.0009) -[2023-10-16 04:45:26,303][05218] Updated weights for policy 0, policy_version 50162 (0.0008) -[2023-10-16 04:45:26,682][05218] Updated weights for policy 0, policy_version 50172 (0.0008) -[2023-10-16 04:45:27,131][05219] Updated weights for policy 1, policy_version 49990 (0.0008) -[2023-10-16 04:45:27,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 102563840. Throughput: 0: 1802.3, 1: 1782.6. Samples: 25647258. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:45:27,351][03835] Avg episode reward: [(0, '6.930'), (1, '6.660')] -[2023-10-16 04:45:27,513][05219] Updated weights for policy 1, policy_version 50000 (0.0008) -[2023-10-16 04:45:27,874][05219] Updated weights for policy 1, policy_version 50010 (0.0011) -[2023-10-16 04:45:30,455][05218] Updated weights for policy 0, policy_version 50182 (0.0010) -[2023-10-16 04:45:30,829][05218] Updated weights for policy 0, policy_version 50192 (0.0010) -[2023-10-16 04:45:31,218][05218] Updated weights for policy 0, policy_version 50202 (0.0007) -[2023-10-16 04:45:31,685][05219] Updated weights for policy 1, policy_version 50020 (0.0008) -[2023-10-16 04:45:32,052][05219] Updated weights for policy 1, policy_version 50030 (0.0008) -[2023-10-16 04:45:32,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 102629376. Throughput: 0: 1791.0, 1: 1794.1. Samples: 25668044. Policy #0 lag: (min: 16.0, avg: 42.0, max: 48.0) -[2023-10-16 04:45:32,351][03835] Avg episode reward: [(0, '6.620'), (1, '6.330')] -[2023-10-16 04:45:32,421][05219] Updated weights for policy 1, policy_version 50040 (0.0007) -[2023-10-16 04:45:34,827][05218] Updated weights for policy 0, policy_version 50212 (0.0008) -[2023-10-16 04:45:35,212][05218] Updated weights for policy 0, policy_version 50222 (0.0007) -[2023-10-16 04:45:35,587][05218] Updated weights for policy 0, policy_version 50232 (0.0009) -[2023-10-16 04:45:36,142][05219] Updated weights for policy 1, policy_version 50050 (0.0008) -[2023-10-16 04:45:36,500][05219] Updated weights for policy 1, policy_version 50060 (0.0007) -[2023-10-16 04:45:36,882][05219] Updated weights for policy 1, policy_version 50070 (0.0009) -[2023-10-16 04:45:37,240][05219] Updated weights for policy 1, policy_version 50080 (0.0008) -[2023-10-16 04:45:37,351][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 102727680. Throughput: 0: 1790.1, 1: 1790.0. Samples: 25689498. Policy #0 lag: (min: 16.0, avg: 42.0, max: 48.0) -[2023-10-16 04:45:37,352][03835] Avg episode reward: [(0, '7.240'), (1, '5.870')] -[2023-10-16 04:45:37,364][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000050240_51445760.pth... -[2023-10-16 04:45:37,364][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000050080_51281920.pth... -[2023-10-16 04:45:37,398][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000048384_49545216.pth -[2023-10-16 04:45:37,401][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000048576_49741824.pth -[2023-10-16 04:45:37,404][04891] Saving a milestone ./train_atari/atari_timepilot_APPO/checkpoint_p1/milestones/checkpoint_000050080_51281920.pth -[2023-10-16 04:45:37,405][04766] Saving a milestone ./train_atari/atari_timepilot_APPO/checkpoint_p0/milestones/checkpoint_000050240_51445760.pth -[2023-10-16 04:45:39,115][05218] Updated weights for policy 0, policy_version 50242 (0.0008) -[2023-10-16 04:45:39,486][05218] Updated weights for policy 0, policy_version 50252 (0.0008) -[2023-10-16 04:45:39,860][05218] Updated weights for policy 0, policy_version 50262 (0.0008) -[2023-10-16 04:45:40,227][05218] Updated weights for policy 0, policy_version 50272 (0.0007) -[2023-10-16 04:45:40,946][05219] Updated weights for policy 1, policy_version 50090 (0.0009) -[2023-10-16 04:45:41,307][05219] Updated weights for policy 1, policy_version 50100 (0.0010) -[2023-10-16 04:45:41,668][05219] Updated weights for policy 1, policy_version 50110 (0.0007) -[2023-10-16 04:45:42,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 102793216. Throughput: 0: 1794.4, 1: 1790.8. Samples: 25700510. Policy #0 lag: (min: 16.0, avg: 42.0, max: 48.0) -[2023-10-16 04:45:42,351][03835] Avg episode reward: [(0, '6.490'), (1, '6.070')] -[2023-10-16 04:45:43,949][05218] Updated weights for policy 0, policy_version 50282 (0.0009) -[2023-10-16 04:45:44,332][05218] Updated weights for policy 0, policy_version 50292 (0.0007) -[2023-10-16 04:45:44,698][05218] Updated weights for policy 0, policy_version 50302 (0.0008) -[2023-10-16 04:45:45,528][05219] Updated weights for policy 1, policy_version 50120 (0.0008) -[2023-10-16 04:45:45,887][05219] Updated weights for policy 1, policy_version 50130 (0.0009) -[2023-10-16 04:45:46,251][05219] Updated weights for policy 1, policy_version 50140 (0.0009) -[2023-10-16 04:45:47,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 102858752. Throughput: 0: 1796.6, 1: 1792.0. Samples: 25721678. Policy #0 lag: (min: 16.0, avg: 42.0, max: 48.0) -[2023-10-16 04:45:47,351][03835] Avg episode reward: [(0, '6.600'), (1, '6.650')] -[2023-10-16 04:45:48,565][05218] Updated weights for policy 0, policy_version 50312 (0.0008) -[2023-10-16 04:45:48,952][05218] Updated weights for policy 0, policy_version 50322 (0.0010) -[2023-10-16 04:45:49,327][05218] Updated weights for policy 0, policy_version 50332 (0.0010) -[2023-10-16 04:45:50,036][05219] Updated weights for policy 1, policy_version 50150 (0.0011) -[2023-10-16 04:45:50,404][05219] Updated weights for policy 1, policy_version 50160 (0.0009) -[2023-10-16 04:45:50,772][05219] Updated weights for policy 1, policy_version 50170 (0.0011) -[2023-10-16 04:45:52,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 102924288. Throughput: 0: 1794.5, 1: 1778.5. Samples: 25743530. Policy #0 lag: (min: 16.0, avg: 42.0, max: 48.0) -[2023-10-16 04:45:52,351][03835] Avg episode reward: [(0, '7.060'), (1, '6.400')] -[2023-10-16 04:45:53,031][05218] Updated weights for policy 0, policy_version 50342 (0.0008) -[2023-10-16 04:45:53,405][05218] Updated weights for policy 0, policy_version 50352 (0.0008) -[2023-10-16 04:45:53,777][05218] Updated weights for policy 0, policy_version 50362 (0.0009) -[2023-10-16 04:45:54,691][05219] Updated weights for policy 1, policy_version 50180 (0.0010) -[2023-10-16 04:45:55,057][05219] Updated weights for policy 1, policy_version 50190 (0.0010) -[2023-10-16 04:45:55,420][05219] Updated weights for policy 1, policy_version 50200 (0.0009) -[2023-10-16 04:45:57,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 102989824. Throughput: 0: 1794.5, 1: 1792.0. Samples: 25753918. Policy #0 lag: (min: 16.0, avg: 42.0, max: 48.0) -[2023-10-16 04:45:57,351][03835] Avg episode reward: [(0, '6.320'), (1, '6.490')] -[2023-10-16 04:45:57,625][05218] Updated weights for policy 0, policy_version 50372 (0.0007) -[2023-10-16 04:45:57,999][05218] Updated weights for policy 0, policy_version 50382 (0.0007) -[2023-10-16 04:45:58,361][05218] Updated weights for policy 0, policy_version 50392 (0.0008) -[2023-10-16 04:45:59,191][05219] Updated weights for policy 1, policy_version 50210 (0.0009) -[2023-10-16 04:45:59,559][05219] Updated weights for policy 1, policy_version 50220 (0.0008) -[2023-10-16 04:45:59,928][05219] Updated weights for policy 1, policy_version 50230 (0.0008) -[2023-10-16 04:46:00,297][05219] Updated weights for policy 1, policy_version 50240 (0.0007) -[2023-10-16 04:46:02,123][05218] Updated weights for policy 0, policy_version 50402 (0.0009) -[2023-10-16 04:46:02,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 103055360. Throughput: 0: 1797.8, 1: 1776.7. Samples: 25775672. Policy #0 lag: (min: 16.0, avg: 42.0, max: 48.0) -[2023-10-16 04:46:02,351][03835] Avg episode reward: [(0, '5.910'), (1, '7.030')] -[2023-10-16 04:46:02,492][05218] Updated weights for policy 0, policy_version 50412 (0.0008) -[2023-10-16 04:46:02,865][05218] Updated weights for policy 0, policy_version 50422 (0.0010) -[2023-10-16 04:46:03,245][05218] Updated weights for policy 0, policy_version 50432 (0.0009) -[2023-10-16 04:46:03,969][05219] Updated weights for policy 1, policy_version 50250 (0.0007) -[2023-10-16 04:46:04,335][05219] Updated weights for policy 1, policy_version 50260 (0.0007) -[2023-10-16 04:46:04,704][05219] Updated weights for policy 1, policy_version 50270 (0.0007) -[2023-10-16 04:46:06,957][05218] Updated weights for policy 0, policy_version 50442 (0.0010) -[2023-10-16 04:46:07,324][05218] Updated weights for policy 0, policy_version 50452 (0.0010) -[2023-10-16 04:46:07,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 103120896. Throughput: 0: 1809.5, 1: 1773.6. Samples: 25797134. Policy #0 lag: (min: 16.0, avg: 42.0, max: 48.0) -[2023-10-16 04:46:07,351][03835] Avg episode reward: [(0, '6.220'), (1, '6.250')] -[2023-10-16 04:46:07,703][05218] Updated weights for policy 0, policy_version 50462 (0.0009) -[2023-10-16 04:46:08,535][05219] Updated weights for policy 1, policy_version 50280 (0.0010) -[2023-10-16 04:46:08,898][05219] Updated weights for policy 1, policy_version 50290 (0.0008) -[2023-10-16 04:46:09,269][05219] Updated weights for policy 1, policy_version 50300 (0.0008) -[2023-10-16 04:46:11,373][05218] Updated weights for policy 0, policy_version 50472 (0.0009) -[2023-10-16 04:46:11,749][05218] Updated weights for policy 0, policy_version 50482 (0.0010) -[2023-10-16 04:46:12,124][05218] Updated weights for policy 0, policy_version 50492 (0.0009) -[2023-10-16 04:46:12,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 103219200. Throughput: 0: 1798.2, 1: 1774.1. Samples: 25808014. Policy #0 lag: (min: 3.0, avg: 3.8, max: 21.0) -[2023-10-16 04:46:12,351][03835] Avg episode reward: [(0, '7.090'), (1, '6.830')] -[2023-10-16 04:46:13,022][05219] Updated weights for policy 1, policy_version 50310 (0.0007) -[2023-10-16 04:46:13,396][05219] Updated weights for policy 1, policy_version 50320 (0.0009) -[2023-10-16 04:46:13,758][05219] Updated weights for policy 1, policy_version 50330 (0.0009) -[2023-10-16 04:46:15,817][05218] Updated weights for policy 0, policy_version 50502 (0.0010) -[2023-10-16 04:46:16,189][05218] Updated weights for policy 0, policy_version 50512 (0.0008) -[2023-10-16 04:46:16,563][05218] Updated weights for policy 0, policy_version 50522 (0.0007) -[2023-10-16 04:46:17,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 103284736. Throughput: 0: 1807.9, 1: 1778.0. Samples: 25829412. Policy #0 lag: (min: 3.0, avg: 3.8, max: 21.0) -[2023-10-16 04:46:17,351][03835] Avg episode reward: [(0, '6.870'), (1, '6.600')] -[2023-10-16 04:46:17,724][05219] Updated weights for policy 1, policy_version 50340 (0.0009) -[2023-10-16 04:46:18,111][05219] Updated weights for policy 1, policy_version 50350 (0.0009) -[2023-10-16 04:46:18,478][05219] Updated weights for policy 1, policy_version 50360 (0.0008) -[2023-10-16 04:46:20,236][05218] Updated weights for policy 0, policy_version 50532 (0.0009) -[2023-10-16 04:46:20,609][05218] Updated weights for policy 0, policy_version 50542 (0.0010) -[2023-10-16 04:46:20,982][05218] Updated weights for policy 0, policy_version 50552 (0.0009) -[2023-10-16 04:46:22,242][05219] Updated weights for policy 1, policy_version 50370 (0.0008) -[2023-10-16 04:46:22,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 103350272. Throughput: 0: 1797.7, 1: 1798.7. Samples: 25851332. Policy #0 lag: (min: 3.0, avg: 3.8, max: 21.0) -[2023-10-16 04:46:22,351][03835] Avg episode reward: [(0, '6.940'), (1, '6.250')] -[2023-10-16 04:46:22,597][05219] Updated weights for policy 1, policy_version 50380 (0.0008) -[2023-10-16 04:46:22,969][05219] Updated weights for policy 1, policy_version 50390 (0.0007) -[2023-10-16 04:46:23,328][05219] Updated weights for policy 1, policy_version 50400 (0.0008) -[2023-10-16 04:46:24,673][05218] Updated weights for policy 0, policy_version 50562 (0.0009) -[2023-10-16 04:46:25,051][05218] Updated weights for policy 0, policy_version 50572 (0.0011) -[2023-10-16 04:46:25,430][05218] Updated weights for policy 0, policy_version 50582 (0.0008) -[2023-10-16 04:46:25,808][05218] Updated weights for policy 0, policy_version 50592 (0.0008) -[2023-10-16 04:46:27,030][05219] Updated weights for policy 1, policy_version 50410 (0.0007) -[2023-10-16 04:46:27,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 103415808. Throughput: 0: 1814.0, 1: 1770.6. Samples: 25861818. Policy #0 lag: (min: 3.0, avg: 3.8, max: 21.0) -[2023-10-16 04:46:27,352][03835] Avg episode reward: [(0, '7.550'), (1, '7.190')] -[2023-10-16 04:46:27,391][05219] Updated weights for policy 1, policy_version 50420 (0.0009) -[2023-10-16 04:46:27,763][05219] Updated weights for policy 1, policy_version 50430 (0.0009) -[2023-10-16 04:46:29,420][05218] Updated weights for policy 0, policy_version 50602 (0.0009) -[2023-10-16 04:46:29,801][05218] Updated weights for policy 0, policy_version 50612 (0.0009) -[2023-10-16 04:46:30,173][05218] Updated weights for policy 0, policy_version 50622 (0.0008) -[2023-10-16 04:46:31,550][05219] Updated weights for policy 1, policy_version 50440 (0.0008) -[2023-10-16 04:46:31,919][05219] Updated weights for policy 1, policy_version 50450 (0.0008) -[2023-10-16 04:46:32,293][05219] Updated weights for policy 1, policy_version 50460 (0.0008) -[2023-10-16 04:46:32,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 103481344. Throughput: 0: 1807.0, 1: 1798.6. Samples: 25883930. Policy #0 lag: (min: 3.0, avg: 3.8, max: 21.0) -[2023-10-16 04:46:32,351][03835] Avg episode reward: [(0, '6.310'), (1, '7.210')] -[2023-10-16 04:46:33,725][05218] Updated weights for policy 0, policy_version 50632 (0.0008) -[2023-10-16 04:46:34,102][05218] Updated weights for policy 0, policy_version 50642 (0.0009) -[2023-10-16 04:46:34,488][05218] Updated weights for policy 0, policy_version 50652 (0.0009) -[2023-10-16 04:46:35,932][05219] Updated weights for policy 1, policy_version 50470 (0.0009) -[2023-10-16 04:46:36,286][05219] Updated weights for policy 1, policy_version 50480 (0.0010) -[2023-10-16 04:46:36,655][05219] Updated weights for policy 1, policy_version 50490 (0.0008) -[2023-10-16 04:46:37,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 103579648. Throughput: 0: 1811.3, 1: 1780.8. Samples: 25905174. Policy #0 lag: (min: 3.0, avg: 3.8, max: 21.0) -[2023-10-16 04:46:37,351][03835] Avg episode reward: [(0, '6.540'), (1, '7.020')] -[2023-10-16 04:46:38,157][05218] Updated weights for policy 0, policy_version 50662 (0.0009) -[2023-10-16 04:46:38,534][05218] Updated weights for policy 0, policy_version 50672 (0.0008) -[2023-10-16 04:46:38,915][05218] Updated weights for policy 0, policy_version 50682 (0.0008) -[2023-10-16 04:46:40,496][05219] Updated weights for policy 1, policy_version 50500 (0.0007) -[2023-10-16 04:46:40,857][05219] Updated weights for policy 1, policy_version 50510 (0.0010) -[2023-10-16 04:46:41,223][05219] Updated weights for policy 1, policy_version 50520 (0.0009) -[2023-10-16 04:46:42,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 103645184. Throughput: 0: 1810.5, 1: 1805.0. Samples: 25916614. Policy #0 lag: (min: 3.0, avg: 3.8, max: 21.0) -[2023-10-16 04:46:42,351][03835] Avg episode reward: [(0, '6.160'), (1, '6.880')] -[2023-10-16 04:46:42,690][05218] Updated weights for policy 0, policy_version 50692 (0.0008) -[2023-10-16 04:46:43,070][05218] Updated weights for policy 0, policy_version 50702 (0.0009) -[2023-10-16 04:46:43,451][05218] Updated weights for policy 0, policy_version 50712 (0.0009) -[2023-10-16 04:46:44,983][05219] Updated weights for policy 1, policy_version 50530 (0.0007) -[2023-10-16 04:46:45,342][05219] Updated weights for policy 1, policy_version 50540 (0.0010) -[2023-10-16 04:46:45,701][05219] Updated weights for policy 1, policy_version 50550 (0.0010) -[2023-10-16 04:46:46,061][05219] Updated weights for policy 1, policy_version 50560 (0.0010) -[2023-10-16 04:46:47,231][05218] Updated weights for policy 0, policy_version 50722 (0.0010) -[2023-10-16 04:46:47,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 103710720. Throughput: 0: 1809.2, 1: 1787.1. Samples: 25937506. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-16 04:46:47,351][03835] Avg episode reward: [(0, '6.210'), (1, '6.870')] -[2023-10-16 04:46:47,613][05218] Updated weights for policy 0, policy_version 50732 (0.0010) -[2023-10-16 04:46:47,993][05218] Updated weights for policy 0, policy_version 50742 (0.0008) -[2023-10-16 04:46:48,366][05218] Updated weights for policy 0, policy_version 50752 (0.0008) -[2023-10-16 04:46:49,868][05219] Updated weights for policy 1, policy_version 50570 (0.0007) -[2023-10-16 04:46:50,229][05219] Updated weights for policy 1, policy_version 50580 (0.0010) -[2023-10-16 04:46:50,593][05219] Updated weights for policy 1, policy_version 50590 (0.0010) -[2023-10-16 04:46:52,028][05218] Updated weights for policy 0, policy_version 50762 (0.0007) -[2023-10-16 04:46:52,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 103776256. Throughput: 0: 1814.3, 1: 1787.0. Samples: 25959194. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-16 04:46:52,351][03835] Avg episode reward: [(0, '6.360'), (1, '7.060')] -[2023-10-16 04:46:52,410][05218] Updated weights for policy 0, policy_version 50772 (0.0009) -[2023-10-16 04:46:52,786][05218] Updated weights for policy 0, policy_version 50782 (0.0008) -[2023-10-16 04:46:54,379][05219] Updated weights for policy 1, policy_version 50600 (0.0008) -[2023-10-16 04:46:54,747][05219] Updated weights for policy 1, policy_version 50610 (0.0009) -[2023-10-16 04:46:55,123][05219] Updated weights for policy 1, policy_version 50620 (0.0010) -[2023-10-16 04:46:56,503][05218] Updated weights for policy 0, policy_version 50792 (0.0010) -[2023-10-16 04:46:56,887][05218] Updated weights for policy 0, policy_version 50802 (0.0007) -[2023-10-16 04:46:57,262][05218] Updated weights for policy 0, policy_version 50812 (0.0007) -[2023-10-16 04:46:57,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 103841792. Throughput: 0: 1809.6, 1: 1790.8. Samples: 25970030. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-16 04:46:57,351][03835] Avg episode reward: [(0, '6.590'), (1, '7.290')] -[2023-10-16 04:46:58,768][05219] Updated weights for policy 1, policy_version 50630 (0.0009) -[2023-10-16 04:46:59,134][05219] Updated weights for policy 1, policy_version 50640 (0.0009) -[2023-10-16 04:46:59,499][05219] Updated weights for policy 1, policy_version 50650 (0.0009) -[2023-10-16 04:47:00,871][05218] Updated weights for policy 0, policy_version 50822 (0.0008) -[2023-10-16 04:47:01,247][05218] Updated weights for policy 0, policy_version 50832 (0.0008) -[2023-10-16 04:47:01,620][05218] Updated weights for policy 0, policy_version 50842 (0.0008) -[2023-10-16 04:47:02,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 103940096. Throughput: 0: 1818.1, 1: 1782.1. Samples: 25991420. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-16 04:47:02,351][03835] Avg episode reward: [(0, '6.900'), (1, '7.440')] -[2023-10-16 04:47:03,414][05219] Updated weights for policy 1, policy_version 50660 (0.0007) -[2023-10-16 04:47:03,815][05219] Updated weights for policy 1, policy_version 50670 (0.0007) -[2023-10-16 04:47:04,166][05219] Updated weights for policy 1, policy_version 50680 (0.0008) -[2023-10-16 04:47:05,247][05218] Updated weights for policy 0, policy_version 50852 (0.0008) -[2023-10-16 04:47:05,636][05218] Updated weights for policy 0, policy_version 50862 (0.0008) -[2023-10-16 04:47:06,018][05218] Updated weights for policy 0, policy_version 50872 (0.0010) -[2023-10-16 04:47:07,350][03835] Fps is (10 sec: 16383.5, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 104005632. Throughput: 0: 1813.2, 1: 1780.9. Samples: 26013070. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-16 04:47:07,352][03835] Avg episode reward: [(0, '6.320'), (1, '6.420')] -[2023-10-16 04:47:07,923][05219] Updated weights for policy 1, policy_version 50690 (0.0010) -[2023-10-16 04:47:08,293][05219] Updated weights for policy 1, policy_version 50700 (0.0009) -[2023-10-16 04:47:08,664][05219] Updated weights for policy 1, policy_version 50710 (0.0007) -[2023-10-16 04:47:09,027][05219] Updated weights for policy 1, policy_version 50720 (0.0008) -[2023-10-16 04:47:09,634][05218] Updated weights for policy 0, policy_version 50882 (0.0008) -[2023-10-16 04:47:10,006][05218] Updated weights for policy 0, policy_version 50892 (0.0010) -[2023-10-16 04:47:10,379][05218] Updated weights for policy 0, policy_version 50902 (0.0010) -[2023-10-16 04:47:10,752][05218] Updated weights for policy 0, policy_version 50912 (0.0012) -[2023-10-16 04:47:12,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 104071168. Throughput: 0: 1809.3, 1: 1782.5. Samples: 26023452. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-16 04:47:12,351][03835] Avg episode reward: [(0, '5.950'), (1, '6.140')] -[2023-10-16 04:47:12,834][05219] Updated weights for policy 1, policy_version 50730 (0.0010) -[2023-10-16 04:47:13,204][05219] Updated weights for policy 1, policy_version 50740 (0.0008) -[2023-10-16 04:47:13,559][05219] Updated weights for policy 1, policy_version 50750 (0.0010) -[2023-10-16 04:47:14,516][05218] Updated weights for policy 0, policy_version 50922 (0.0009) -[2023-10-16 04:47:14,892][05218] Updated weights for policy 0, policy_version 50932 (0.0009) -[2023-10-16 04:47:15,266][05218] Updated weights for policy 0, policy_version 50942 (0.0010) -[2023-10-16 04:47:17,207][05219] Updated weights for policy 1, policy_version 50760 (0.0009) -[2023-10-16 04:47:17,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 104136704. Throughput: 0: 1802.8, 1: 1786.9. Samples: 26045468. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-16 04:47:17,351][03835] Avg episode reward: [(0, '6.600'), (1, '6.980')] -[2023-10-16 04:47:17,568][05219] Updated weights for policy 1, policy_version 50770 (0.0010) -[2023-10-16 04:47:17,939][05219] Updated weights for policy 1, policy_version 50780 (0.0008) -[2023-10-16 04:47:19,024][05218] Updated weights for policy 0, policy_version 50952 (0.0010) -[2023-10-16 04:47:19,399][05218] Updated weights for policy 0, policy_version 50962 (0.0009) -[2023-10-16 04:47:19,774][05218] Updated weights for policy 0, policy_version 50972 (0.0009) -[2023-10-16 04:47:21,790][05219] Updated weights for policy 1, policy_version 50790 (0.0007) -[2023-10-16 04:47:22,156][05219] Updated weights for policy 1, policy_version 50800 (0.0009) -[2023-10-16 04:47:22,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 104202240. Throughput: 0: 1804.8, 1: 1797.4. Samples: 26067272. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-16 04:47:22,351][03835] Avg episode reward: [(0, '6.800'), (1, '6.560')] -[2023-10-16 04:47:22,528][05219] Updated weights for policy 1, policy_version 50810 (0.0008) -[2023-10-16 04:47:23,479][05218] Updated weights for policy 0, policy_version 50982 (0.0011) -[2023-10-16 04:47:23,858][05218] Updated weights for policy 0, policy_version 50992 (0.0011) -[2023-10-16 04:47:24,234][05218] Updated weights for policy 0, policy_version 51002 (0.0010) -[2023-10-16 04:47:26,323][05219] Updated weights for policy 1, policy_version 50820 (0.0007) -[2023-10-16 04:47:26,692][05219] Updated weights for policy 1, policy_version 50830 (0.0009) -[2023-10-16 04:47:27,057][05219] Updated weights for policy 1, policy_version 50840 (0.0008) -[2023-10-16 04:47:27,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 104300544. Throughput: 0: 1799.4, 1: 1781.9. Samples: 26077770. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-16 04:47:27,351][03835] Avg episode reward: [(0, '6.520'), (1, '6.210')] -[2023-10-16 04:47:27,955][05218] Updated weights for policy 0, policy_version 51012 (0.0009) -[2023-10-16 04:47:28,338][05218] Updated weights for policy 0, policy_version 51022 (0.0007) -[2023-10-16 04:47:28,708][05218] Updated weights for policy 0, policy_version 51032 (0.0007) -[2023-10-16 04:47:30,711][05219] Updated weights for policy 1, policy_version 50850 (0.0010) -[2023-10-16 04:47:31,074][05219] Updated weights for policy 1, policy_version 50860 (0.0009) -[2023-10-16 04:47:31,446][05219] Updated weights for policy 1, policy_version 50870 (0.0008) -[2023-10-16 04:47:31,819][05219] Updated weights for policy 1, policy_version 50880 (0.0009) -[2023-10-16 04:47:32,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 104366080. Throughput: 0: 1805.2, 1: 1799.7. Samples: 26099728. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-16 04:47:32,351][03835] Avg episode reward: [(0, '6.650'), (1, '6.580')] -[2023-10-16 04:47:32,504][05218] Updated weights for policy 0, policy_version 51042 (0.0008) -[2023-10-16 04:47:32,880][05218] Updated weights for policy 0, policy_version 51052 (0.0009) -[2023-10-16 04:47:33,247][05218] Updated weights for policy 0, policy_version 51062 (0.0010) -[2023-10-16 04:47:33,624][05218] Updated weights for policy 0, policy_version 51072 (0.0010) -[2023-10-16 04:47:35,653][05219] Updated weights for policy 1, policy_version 50890 (0.0007) -[2023-10-16 04:47:36,018][05219] Updated weights for policy 1, policy_version 50900 (0.0007) -[2023-10-16 04:47:36,391][05219] Updated weights for policy 1, policy_version 50910 (0.0007) -[2023-10-16 04:47:37,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 104431616. Throughput: 0: 1811.2, 1: 1784.3. Samples: 26120990. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-16 04:47:37,351][03835] Avg episode reward: [(0, '6.620'), (1, '6.390')] -[2023-10-16 04:47:37,360][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000050912_52133888.pth... -[2023-10-16 04:47:37,399][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000049248_50429952.pth -[2023-10-16 04:47:37,494][05218] Updated weights for policy 0, policy_version 51082 (0.0010) -[2023-10-16 04:47:37,873][05218] Updated weights for policy 0, policy_version 51092 (0.0007) -[2023-10-16 04:47:38,247][05218] Updated weights for policy 0, policy_version 51102 (0.0007) -[2023-10-16 04:47:38,322][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000051104_52330496.pth... -[2023-10-16 04:47:38,351][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000049408_50593792.pth -[2023-10-16 04:47:40,142][05219] Updated weights for policy 1, policy_version 50920 (0.0007) -[2023-10-16 04:47:40,498][05219] Updated weights for policy 1, policy_version 50930 (0.0008) -[2023-10-16 04:47:40,867][05219] Updated weights for policy 1, policy_version 50940 (0.0008) -[2023-10-16 04:47:42,036][05218] Updated weights for policy 0, policy_version 51112 (0.0009) -[2023-10-16 04:47:42,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 104497152. Throughput: 0: 1799.0, 1: 1803.6. Samples: 26132148. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-16 04:47:42,351][03835] Avg episode reward: [(0, '6.350'), (1, '6.760')] -[2023-10-16 04:47:42,411][05218] Updated weights for policy 0, policy_version 51122 (0.0008) -[2023-10-16 04:47:42,788][05218] Updated weights for policy 0, policy_version 51132 (0.0010) -[2023-10-16 04:47:44,451][05219] Updated weights for policy 1, policy_version 50950 (0.0008) -[2023-10-16 04:47:44,808][05219] Updated weights for policy 1, policy_version 50960 (0.0008) -[2023-10-16 04:47:45,165][05219] Updated weights for policy 1, policy_version 50970 (0.0010) -[2023-10-16 04:47:46,610][05218] Updated weights for policy 0, policy_version 51142 (0.0010) -[2023-10-16 04:47:46,985][05218] Updated weights for policy 0, policy_version 51152 (0.0008) -[2023-10-16 04:47:47,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 104562688. Throughput: 0: 1808.3, 1: 1794.6. Samples: 26153550. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-16 04:47:47,351][03835] Avg episode reward: [(0, '6.430'), (1, '6.320')] -[2023-10-16 04:47:47,360][05218] Updated weights for policy 0, policy_version 51162 (0.0008) -[2023-10-16 04:47:49,012][05219] Updated weights for policy 1, policy_version 50980 (0.0007) -[2023-10-16 04:47:49,395][05219] Updated weights for policy 1, policy_version 50990 (0.0007) -[2023-10-16 04:47:49,769][05219] Updated weights for policy 1, policy_version 51000 (0.0007) -[2023-10-16 04:47:51,126][05218] Updated weights for policy 0, policy_version 51172 (0.0010) -[2023-10-16 04:47:51,499][05218] Updated weights for policy 0, policy_version 51182 (0.0008) -[2023-10-16 04:47:51,872][05218] Updated weights for policy 0, policy_version 51192 (0.0008) -[2023-10-16 04:47:52,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 104660992. Throughput: 0: 1788.8, 1: 1799.5. Samples: 26174544. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-16 04:47:52,351][03835] Avg episode reward: [(0, '6.880'), (1, '7.000')] -[2023-10-16 04:47:53,474][05219] Updated weights for policy 1, policy_version 51010 (0.0008) -[2023-10-16 04:47:53,841][05219] Updated weights for policy 1, policy_version 51020 (0.0011) -[2023-10-16 04:47:54,205][05219] Updated weights for policy 1, policy_version 51030 (0.0010) -[2023-10-16 04:47:54,572][05219] Updated weights for policy 1, policy_version 51040 (0.0008) -[2023-10-16 04:47:55,621][05218] Updated weights for policy 0, policy_version 51202 (0.0008) -[2023-10-16 04:47:55,996][05218] Updated weights for policy 0, policy_version 51212 (0.0007) -[2023-10-16 04:47:56,381][05218] Updated weights for policy 0, policy_version 51222 (0.0009) -[2023-10-16 04:47:56,745][05218] Updated weights for policy 0, policy_version 51232 (0.0008) -[2023-10-16 04:47:57,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 104726528. Throughput: 0: 1809.3, 1: 1797.3. Samples: 26185750. Policy #0 lag: (min: 21.0, avg: 26.8, max: 53.0) -[2023-10-16 04:47:57,351][03835] Avg episode reward: [(0, '6.470'), (1, '6.390')] -[2023-10-16 04:47:58,420][05219] Updated weights for policy 1, policy_version 51050 (0.0008) -[2023-10-16 04:47:58,776][05219] Updated weights for policy 1, policy_version 51060 (0.0008) -[2023-10-16 04:47:59,139][05219] Updated weights for policy 1, policy_version 51070 (0.0007) -[2023-10-16 04:48:00,422][05218] Updated weights for policy 0, policy_version 51242 (0.0011) -[2023-10-16 04:48:00,797][05218] Updated weights for policy 0, policy_version 51252 (0.0010) -[2023-10-16 04:48:01,173][05218] Updated weights for policy 0, policy_version 51262 (0.0010) -[2023-10-16 04:48:02,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 104792064. Throughput: 0: 1794.3, 1: 1788.4. Samples: 26206690. Policy #0 lag: (min: 21.0, avg: 26.8, max: 53.0) -[2023-10-16 04:48:02,351][03835] Avg episode reward: [(0, '6.660'), (1, '6.400')] -[2023-10-16 04:48:03,011][05219] Updated weights for policy 1, policy_version 51080 (0.0007) -[2023-10-16 04:48:03,383][05219] Updated weights for policy 1, policy_version 51090 (0.0008) -[2023-10-16 04:48:03,744][05219] Updated weights for policy 1, policy_version 51100 (0.0010) -[2023-10-16 04:48:04,846][05218] Updated weights for policy 0, policy_version 51272 (0.0009) -[2023-10-16 04:48:05,214][05218] Updated weights for policy 0, policy_version 51282 (0.0007) -[2023-10-16 04:48:05,590][05218] Updated weights for policy 0, policy_version 51292 (0.0008) -[2023-10-16 04:48:07,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 104857600. Throughput: 0: 1787.6, 1: 1805.1. Samples: 26228942. Policy #0 lag: (min: 21.0, avg: 26.8, max: 53.0) -[2023-10-16 04:48:07,351][03835] Avg episode reward: [(0, '6.420'), (1, '7.220')] -[2023-10-16 04:48:07,593][05219] Updated weights for policy 1, policy_version 51110 (0.0008) -[2023-10-16 04:48:07,964][05219] Updated weights for policy 1, policy_version 51120 (0.0008) -[2023-10-16 04:48:08,339][05219] Updated weights for policy 1, policy_version 51130 (0.0007) -[2023-10-16 04:48:09,153][05218] Updated weights for policy 0, policy_version 51302 (0.0011) -[2023-10-16 04:48:09,533][05218] Updated weights for policy 0, policy_version 51312 (0.0008) -[2023-10-16 04:48:09,918][05218] Updated weights for policy 0, policy_version 51322 (0.0007) -[2023-10-16 04:48:12,248][05219] Updated weights for policy 1, policy_version 51140 (0.0007) -[2023-10-16 04:48:12,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 104923136. Throughput: 0: 1797.4, 1: 1782.3. Samples: 26238854. Policy #0 lag: (min: 21.0, avg: 26.8, max: 53.0) -[2023-10-16 04:48:12,351][03835] Avg episode reward: [(0, '6.320'), (1, '6.860')] -[2023-10-16 04:48:12,628][05219] Updated weights for policy 1, policy_version 51150 (0.0008) -[2023-10-16 04:48:12,987][05219] Updated weights for policy 1, policy_version 51160 (0.0010) -[2023-10-16 04:48:13,572][05218] Updated weights for policy 0, policy_version 51332 (0.0008) -[2023-10-16 04:48:13,940][05218] Updated weights for policy 0, policy_version 51342 (0.0009) -[2023-10-16 04:48:14,318][05218] Updated weights for policy 0, policy_version 51352 (0.0010) -[2023-10-16 04:48:16,673][05219] Updated weights for policy 1, policy_version 51170 (0.0008) -[2023-10-16 04:48:17,036][05219] Updated weights for policy 1, policy_version 51180 (0.0008) -[2023-10-16 04:48:17,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 104988672. Throughput: 0: 1790.5, 1: 1795.9. Samples: 26261116. Policy #0 lag: (min: 21.0, avg: 26.8, max: 53.0) -[2023-10-16 04:48:17,351][03835] Avg episode reward: [(0, '6.650'), (1, '7.100')] -[2023-10-16 04:48:17,398][05219] Updated weights for policy 1, policy_version 51190 (0.0009) -[2023-10-16 04:48:17,764][05219] Updated weights for policy 1, policy_version 51200 (0.0011) -[2023-10-16 04:48:18,162][05218] Updated weights for policy 0, policy_version 51362 (0.0009) -[2023-10-16 04:48:18,537][05218] Updated weights for policy 0, policy_version 51372 (0.0009) -[2023-10-16 04:48:18,926][05218] Updated weights for policy 0, policy_version 51382 (0.0007) -[2023-10-16 04:48:19,293][05218] Updated weights for policy 0, policy_version 51392 (0.0009) -[2023-10-16 04:48:21,601][05219] Updated weights for policy 1, policy_version 51210 (0.0008) -[2023-10-16 04:48:21,965][05219] Updated weights for policy 1, policy_version 51220 (0.0007) -[2023-10-16 04:48:22,319][05219] Updated weights for policy 1, policy_version 51230 (0.0008) -[2023-10-16 04:48:22,351][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 105054208. Throughput: 0: 1801.5, 1: 1789.5. Samples: 26282588. Policy #0 lag: (min: 21.0, avg: 26.8, max: 53.0) -[2023-10-16 04:48:22,352][03835] Avg episode reward: [(0, '6.570'), (1, '6.970')] -[2023-10-16 04:48:23,087][05218] Updated weights for policy 0, policy_version 51402 (0.0009) -[2023-10-16 04:48:23,461][05218] Updated weights for policy 0, policy_version 51412 (0.0011) -[2023-10-16 04:48:23,836][05218] Updated weights for policy 0, policy_version 51422 (0.0009) -[2023-10-16 04:48:25,911][05219] Updated weights for policy 1, policy_version 51240 (0.0012) -[2023-10-16 04:48:26,273][05219] Updated weights for policy 1, policy_version 51250 (0.0009) -[2023-10-16 04:48:26,637][05219] Updated weights for policy 1, policy_version 51260 (0.0007) -[2023-10-16 04:48:27,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 105152512. Throughput: 0: 1794.3, 1: 1792.7. Samples: 26293564. Policy #0 lag: (min: 21.0, avg: 26.8, max: 53.0) -[2023-10-16 04:48:27,351][03835] Avg episode reward: [(0, '6.560'), (1, '6.130')] -[2023-10-16 04:48:27,649][05218] Updated weights for policy 0, policy_version 51432 (0.0010) -[2023-10-16 04:48:28,026][05218] Updated weights for policy 0, policy_version 51442 (0.0008) -[2023-10-16 04:48:28,405][05218] Updated weights for policy 0, policy_version 51452 (0.0007) -[2023-10-16 04:48:30,459][05219] Updated weights for policy 1, policy_version 51270 (0.0008) -[2023-10-16 04:48:30,832][05219] Updated weights for policy 1, policy_version 51280 (0.0009) -[2023-10-16 04:48:31,195][05219] Updated weights for policy 1, policy_version 51290 (0.0009) -[2023-10-16 04:48:32,043][05218] Updated weights for policy 0, policy_version 51462 (0.0010) -[2023-10-16 04:48:32,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 105218048. Throughput: 0: 1802.2, 1: 1787.3. Samples: 26315078. Policy #0 lag: (min: 21.0, avg: 26.8, max: 53.0) -[2023-10-16 04:48:32,351][03835] Avg episode reward: [(0, '6.580'), (1, '6.050')] -[2023-10-16 04:48:32,420][05218] Updated weights for policy 0, policy_version 51472 (0.0010) -[2023-10-16 04:48:32,808][05218] Updated weights for policy 0, policy_version 51482 (0.0009) -[2023-10-16 04:48:35,057][05219] Updated weights for policy 1, policy_version 51300 (0.0007) -[2023-10-16 04:48:35,446][05219] Updated weights for policy 1, policy_version 51310 (0.0009) -[2023-10-16 04:48:35,811][05219] Updated weights for policy 1, policy_version 51320 (0.0011) -[2023-10-16 04:48:36,595][05218] Updated weights for policy 0, policy_version 51492 (0.0009) -[2023-10-16 04:48:36,975][05218] Updated weights for policy 0, policy_version 51502 (0.0009) -[2023-10-16 04:48:37,350][05218] Updated weights for policy 0, policy_version 51512 (0.0010) -[2023-10-16 04:48:37,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 105283584. Throughput: 0: 1808.5, 1: 1777.0. Samples: 26335890. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-16 04:48:37,351][03835] Avg episode reward: [(0, '5.860'), (1, '6.260')] -[2023-10-16 04:48:39,578][05219] Updated weights for policy 1, policy_version 51330 (0.0009) -[2023-10-16 04:48:39,944][05219] Updated weights for policy 1, policy_version 51340 (0.0008) -[2023-10-16 04:48:40,313][05219] Updated weights for policy 1, policy_version 51350 (0.0007) -[2023-10-16 04:48:40,680][05219] Updated weights for policy 1, policy_version 51360 (0.0008) -[2023-10-16 04:48:41,114][05218] Updated weights for policy 0, policy_version 51522 (0.0009) -[2023-10-16 04:48:41,498][05218] Updated weights for policy 0, policy_version 51532 (0.0008) -[2023-10-16 04:48:41,872][05218] Updated weights for policy 0, policy_version 51542 (0.0008) -[2023-10-16 04:48:42,245][05218] Updated weights for policy 0, policy_version 51552 (0.0010) -[2023-10-16 04:48:42,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 105381888. Throughput: 0: 1798.4, 1: 1797.0. Samples: 26347544. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-16 04:48:42,351][03835] Avg episode reward: [(0, '6.520'), (1, '5.930')] -[2023-10-16 04:48:44,530][05219] Updated weights for policy 1, policy_version 51370 (0.0009) -[2023-10-16 04:48:44,897][05219] Updated weights for policy 1, policy_version 51380 (0.0008) -[2023-10-16 04:48:45,267][05219] Updated weights for policy 1, policy_version 51390 (0.0009) -[2023-10-16 04:48:45,976][05218] Updated weights for policy 0, policy_version 51562 (0.0010) -[2023-10-16 04:48:46,356][05218] Updated weights for policy 0, policy_version 51572 (0.0009) -[2023-10-16 04:48:46,735][05218] Updated weights for policy 0, policy_version 51582 (0.0009) -[2023-10-16 04:48:47,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 105447424. Throughput: 0: 1806.2, 1: 1776.8. Samples: 26367924. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-16 04:48:47,351][03835] Avg episode reward: [(0, '6.370'), (1, '6.020')] -[2023-10-16 04:48:48,911][05219] Updated weights for policy 1, policy_version 51400 (0.0009) -[2023-10-16 04:48:49,271][05219] Updated weights for policy 1, policy_version 51410 (0.0007) -[2023-10-16 04:48:49,637][05219] Updated weights for policy 1, policy_version 51420 (0.0007) -[2023-10-16 04:48:50,535][05218] Updated weights for policy 0, policy_version 51592 (0.0007) -[2023-10-16 04:48:50,909][05218] Updated weights for policy 0, policy_version 51602 (0.0010) -[2023-10-16 04:48:51,274][05218] Updated weights for policy 0, policy_version 51612 (0.0010) -[2023-10-16 04:48:52,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 105512960. Throughput: 0: 1788.9, 1: 1782.7. Samples: 26389666. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-16 04:48:52,351][03835] Avg episode reward: [(0, '6.360'), (1, '6.030')] -[2023-10-16 04:48:53,359][05219] Updated weights for policy 1, policy_version 51430 (0.0008) -[2023-10-16 04:48:53,722][05219] Updated weights for policy 1, policy_version 51440 (0.0007) -[2023-10-16 04:48:54,089][05219] Updated weights for policy 1, policy_version 51450 (0.0008) -[2023-10-16 04:48:54,953][05218] Updated weights for policy 0, policy_version 51622 (0.0007) -[2023-10-16 04:48:55,323][05218] Updated weights for policy 0, policy_version 51632 (0.0007) -[2023-10-16 04:48:55,698][05218] Updated weights for policy 0, policy_version 51642 (0.0010) -[2023-10-16 04:48:57,351][03835] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 105578496. Throughput: 0: 1802.8, 1: 1785.8. Samples: 26400344. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-16 04:48:57,351][03835] Avg episode reward: [(0, '6.200'), (1, '5.540')] -[2023-10-16 04:48:57,908][05219] Updated weights for policy 1, policy_version 51460 (0.0008) -[2023-10-16 04:48:58,275][05219] Updated weights for policy 1, policy_version 51470 (0.0007) -[2023-10-16 04:48:58,637][05219] Updated weights for policy 1, policy_version 51480 (0.0007) -[2023-10-16 04:48:59,409][05218] Updated weights for policy 0, policy_version 51652 (0.0007) -[2023-10-16 04:48:59,791][05218] Updated weights for policy 0, policy_version 51662 (0.0007) -[2023-10-16 04:49:00,169][05218] Updated weights for policy 0, policy_version 51672 (0.0007) -[2023-10-16 04:49:02,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 105644032. Throughput: 0: 1789.9, 1: 1782.4. Samples: 26421872. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-16 04:49:02,351][03835] Avg episode reward: [(0, '6.280'), (1, '6.280')] -[2023-10-16 04:49:02,352][05219] Updated weights for policy 1, policy_version 51490 (0.0008) -[2023-10-16 04:49:02,714][05219] Updated weights for policy 1, policy_version 51500 (0.0010) -[2023-10-16 04:49:03,083][05219] Updated weights for policy 1, policy_version 51510 (0.0010) -[2023-10-16 04:49:03,444][05219] Updated weights for policy 1, policy_version 51520 (0.0010) -[2023-10-16 04:49:03,867][05218] Updated weights for policy 0, policy_version 51682 (0.0007) -[2023-10-16 04:49:04,239][05218] Updated weights for policy 0, policy_version 51692 (0.0009) -[2023-10-16 04:49:04,618][05218] Updated weights for policy 0, policy_version 51702 (0.0008) -[2023-10-16 04:49:04,995][05218] Updated weights for policy 0, policy_version 51712 (0.0009) -[2023-10-16 04:49:07,235][05219] Updated weights for policy 1, policy_version 51530 (0.0008) -[2023-10-16 04:49:07,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 105709568. Throughput: 0: 1783.6, 1: 1803.1. Samples: 26443988. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-16 04:49:07,351][03835] Avg episode reward: [(0, '6.980'), (1, '5.620')] -[2023-10-16 04:49:07,611][05219] Updated weights for policy 1, policy_version 51540 (0.0007) -[2023-10-16 04:49:07,970][05219] Updated weights for policy 1, policy_version 51550 (0.0008) -[2023-10-16 04:49:08,837][05218] Updated weights for policy 0, policy_version 51722 (0.0010) -[2023-10-16 04:49:09,213][05218] Updated weights for policy 0, policy_version 51732 (0.0010) -[2023-10-16 04:49:09,598][05218] Updated weights for policy 0, policy_version 51742 (0.0011) -[2023-10-16 04:49:11,662][05219] Updated weights for policy 1, policy_version 51560 (0.0009) -[2023-10-16 04:49:12,022][05219] Updated weights for policy 1, policy_version 51570 (0.0010) -[2023-10-16 04:49:12,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 105775104. Throughput: 0: 1784.8, 1: 1781.5. Samples: 26454046. Policy #0 lag: (min: 1.0, avg: 13.5, max: 33.0) -[2023-10-16 04:49:12,351][03835] Avg episode reward: [(0, '7.060'), (1, '6.270')] -[2023-10-16 04:49:12,392][05219] Updated weights for policy 1, policy_version 51580 (0.0010) -[2023-10-16 04:49:13,164][05218] Updated weights for policy 0, policy_version 51752 (0.0008) -[2023-10-16 04:49:13,545][05218] Updated weights for policy 0, policy_version 51762 (0.0008) -[2023-10-16 04:49:13,928][05218] Updated weights for policy 0, policy_version 51772 (0.0007) -[2023-10-16 04:49:16,143][05219] Updated weights for policy 1, policy_version 51590 (0.0011) -[2023-10-16 04:49:16,500][05219] Updated weights for policy 1, policy_version 51600 (0.0010) -[2023-10-16 04:49:16,859][05219] Updated weights for policy 1, policy_version 51610 (0.0010) -[2023-10-16 04:49:17,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 105873408. Throughput: 0: 1785.1, 1: 1799.9. Samples: 26476404. Policy #0 lag: (min: 1.0, avg: 13.5, max: 33.0) -[2023-10-16 04:49:17,351][03835] Avg episode reward: [(0, '6.400'), (1, '6.480')] -[2023-10-16 04:49:17,654][05218] Updated weights for policy 0, policy_version 51782 (0.0010) -[2023-10-16 04:49:18,044][05218] Updated weights for policy 0, policy_version 51792 (0.0009) -[2023-10-16 04:49:18,425][05218] Updated weights for policy 0, policy_version 51802 (0.0009) -[2023-10-16 04:49:20,703][05219] Updated weights for policy 1, policy_version 51620 (0.0010) -[2023-10-16 04:49:21,092][05219] Updated weights for policy 1, policy_version 51630 (0.0007) -[2023-10-16 04:49:21,455][05219] Updated weights for policy 1, policy_version 51640 (0.0007) -[2023-10-16 04:49:22,154][05218] Updated weights for policy 0, policy_version 51812 (0.0010) -[2023-10-16 04:49:22,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 105938944. Throughput: 0: 1802.2, 1: 1777.3. Samples: 26496970. Policy #0 lag: (min: 1.0, avg: 13.5, max: 33.0) -[2023-10-16 04:49:22,351][03835] Avg episode reward: [(0, '6.460'), (1, '6.430')] -[2023-10-16 04:49:22,527][05218] Updated weights for policy 0, policy_version 51822 (0.0010) -[2023-10-16 04:49:22,905][05218] Updated weights for policy 0, policy_version 51832 (0.0007) -[2023-10-16 04:49:25,196][05219] Updated weights for policy 1, policy_version 51650 (0.0009) -[2023-10-16 04:49:25,558][05219] Updated weights for policy 1, policy_version 51660 (0.0009) -[2023-10-16 04:49:25,930][05219] Updated weights for policy 1, policy_version 51670 (0.0010) -[2023-10-16 04:49:26,298][05219] Updated weights for policy 1, policy_version 51680 (0.0008) -[2023-10-16 04:49:26,798][05218] Updated weights for policy 0, policy_version 51842 (0.0008) -[2023-10-16 04:49:27,170][05218] Updated weights for policy 0, policy_version 51852 (0.0010) -[2023-10-16 04:49:27,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 106004480. Throughput: 0: 1783.6, 1: 1798.9. Samples: 26508756. Policy #0 lag: (min: 1.0, avg: 13.5, max: 33.0) -[2023-10-16 04:49:27,351][03835] Avg episode reward: [(0, '6.340'), (1, '6.670')] -[2023-10-16 04:49:27,542][05218] Updated weights for policy 0, policy_version 51862 (0.0009) -[2023-10-16 04:49:27,925][05218] Updated weights for policy 0, policy_version 51872 (0.0007) -[2023-10-16 04:49:30,082][05219] Updated weights for policy 1, policy_version 51690 (0.0010) -[2023-10-16 04:49:30,449][05219] Updated weights for policy 1, policy_version 51700 (0.0008) -[2023-10-16 04:49:30,810][05219] Updated weights for policy 1, policy_version 51710 (0.0010) -[2023-10-16 04:49:31,770][05218] Updated weights for policy 0, policy_version 51882 (0.0008) -[2023-10-16 04:49:32,140][05218] Updated weights for policy 0, policy_version 51892 (0.0007) -[2023-10-16 04:49:32,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 106070016. Throughput: 0: 1802.8, 1: 1789.3. Samples: 26529568. Policy #0 lag: (min: 1.0, avg: 13.5, max: 33.0) -[2023-10-16 04:49:32,351][03835] Avg episode reward: [(0, '6.590'), (1, '6.510')] -[2023-10-16 04:49:32,522][05218] Updated weights for policy 0, policy_version 51902 (0.0010) -[2023-10-16 04:49:34,752][05219] Updated weights for policy 1, policy_version 51720 (0.0008) -[2023-10-16 04:49:35,116][05219] Updated weights for policy 1, policy_version 51730 (0.0007) -[2023-10-16 04:49:35,481][05219] Updated weights for policy 1, policy_version 51740 (0.0007) -[2023-10-16 04:49:36,075][05218] Updated weights for policy 0, policy_version 51912 (0.0008) -[2023-10-16 04:49:36,452][05218] Updated weights for policy 0, policy_version 51922 (0.0009) -[2023-10-16 04:49:36,821][05218] Updated weights for policy 0, policy_version 51932 (0.0010) -[2023-10-16 04:49:37,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 106168320. Throughput: 0: 1787.0, 1: 1782.8. Samples: 26550306. Policy #0 lag: (min: 1.0, avg: 13.5, max: 33.0) -[2023-10-16 04:49:37,351][03835] Avg episode reward: [(0, '7.280'), (1, '6.760')] -[2023-10-16 04:49:37,360][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000051936_53182464.pth... -[2023-10-16 04:49:37,360][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000051744_52985856.pth... -[2023-10-16 04:49:37,390][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000050080_51281920.pth -[2023-10-16 04:49:37,399][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000050240_51445760.pth -[2023-10-16 04:49:39,217][05219] Updated weights for policy 1, policy_version 51750 (0.0009) -[2023-10-16 04:49:39,584][05219] Updated weights for policy 1, policy_version 51760 (0.0009) -[2023-10-16 04:49:39,952][05219] Updated weights for policy 1, policy_version 51770 (0.0010) -[2023-10-16 04:49:40,621][05218] Updated weights for policy 0, policy_version 51942 (0.0010) -[2023-10-16 04:49:41,003][05218] Updated weights for policy 0, policy_version 51952 (0.0011) -[2023-10-16 04:49:41,381][05218] Updated weights for policy 0, policy_version 51962 (0.0008) -[2023-10-16 04:49:42,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 106233856. Throughput: 0: 1808.0, 1: 1783.9. Samples: 26561978. Policy #0 lag: (min: 1.0, avg: 13.5, max: 33.0) -[2023-10-16 04:49:42,351][03835] Avg episode reward: [(0, '7.010'), (1, '7.250')] -[2023-10-16 04:49:43,684][05219] Updated weights for policy 1, policy_version 51780 (0.0010) -[2023-10-16 04:49:44,047][05219] Updated weights for policy 1, policy_version 51790 (0.0010) -[2023-10-16 04:49:44,418][05219] Updated weights for policy 1, policy_version 51800 (0.0007) -[2023-10-16 04:49:45,025][05218] Updated weights for policy 0, policy_version 51972 (0.0011) -[2023-10-16 04:49:45,396][05218] Updated weights for policy 0, policy_version 51982 (0.0010) -[2023-10-16 04:49:45,778][05218] Updated weights for policy 0, policy_version 51992 (0.0011) -[2023-10-16 04:49:47,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 106299392. Throughput: 0: 1789.6, 1: 1789.4. Samples: 26582926. Policy #0 lag: (min: 18.0, avg: 27.1, max: 50.0) -[2023-10-16 04:49:47,351][03835] Avg episode reward: [(0, '6.770'), (1, '6.550')] -[2023-10-16 04:49:48,130][05219] Updated weights for policy 1, policy_version 51810 (0.0007) -[2023-10-16 04:49:48,496][05219] Updated weights for policy 1, policy_version 51820 (0.0008) -[2023-10-16 04:49:48,867][05219] Updated weights for policy 1, policy_version 51830 (0.0009) -[2023-10-16 04:49:49,222][05219] Updated weights for policy 1, policy_version 51840 (0.0009) -[2023-10-16 04:49:49,377][05218] Updated weights for policy 0, policy_version 52002 (0.0008) -[2023-10-16 04:49:49,768][05218] Updated weights for policy 0, policy_version 52012 (0.0008) -[2023-10-16 04:49:50,133][05218] Updated weights for policy 0, policy_version 52022 (0.0008) -[2023-10-16 04:49:50,506][05218] Updated weights for policy 0, policy_version 52032 (0.0008) -[2023-10-16 04:49:52,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 106364928. Throughput: 0: 1798.7, 1: 1791.1. Samples: 26605528. Policy #0 lag: (min: 18.0, avg: 27.1, max: 50.0) -[2023-10-16 04:49:52,351][03835] Avg episode reward: [(0, '6.540'), (1, '7.090')] -[2023-10-16 04:49:52,953][05219] Updated weights for policy 1, policy_version 51850 (0.0009) -[2023-10-16 04:49:53,317][05219] Updated weights for policy 1, policy_version 51860 (0.0008) -[2023-10-16 04:49:53,691][05219] Updated weights for policy 1, policy_version 51870 (0.0007) -[2023-10-16 04:49:54,259][05218] Updated weights for policy 0, policy_version 52042 (0.0010) -[2023-10-16 04:49:54,634][05218] Updated weights for policy 0, policy_version 52052 (0.0010) -[2023-10-16 04:49:55,022][05218] Updated weights for policy 0, policy_version 52062 (0.0009) -[2023-10-16 04:49:57,344][05219] Updated weights for policy 1, policy_version 51880 (0.0010) -[2023-10-16 04:49:57,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 106430464. Throughput: 0: 1797.7, 1: 1787.8. Samples: 26615392. Policy #0 lag: (min: 18.0, avg: 27.1, max: 50.0) -[2023-10-16 04:49:57,351][03835] Avg episode reward: [(0, '6.940'), (1, '6.420')] -[2023-10-16 04:49:57,708][05219] Updated weights for policy 1, policy_version 51890 (0.0009) -[2023-10-16 04:49:58,070][05219] Updated weights for policy 1, policy_version 51900 (0.0011) -[2023-10-16 04:49:58,707][05218] Updated weights for policy 0, policy_version 52072 (0.0009) -[2023-10-16 04:49:59,083][05218] Updated weights for policy 0, policy_version 52082 (0.0008) -[2023-10-16 04:49:59,473][05218] Updated weights for policy 0, policy_version 52092 (0.0008) -[2023-10-16 04:50:01,789][05219] Updated weights for policy 1, policy_version 51910 (0.0010) -[2023-10-16 04:50:02,160][05219] Updated weights for policy 1, policy_version 51920 (0.0008) -[2023-10-16 04:50:02,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 106496000. Throughput: 0: 1794.3, 1: 1796.8. Samples: 26638006. Policy #0 lag: (min: 18.0, avg: 27.1, max: 50.0) -[2023-10-16 04:50:02,351][03835] Avg episode reward: [(0, '7.340'), (1, '6.370')] -[2023-10-16 04:50:02,539][05219] Updated weights for policy 1, policy_version 51930 (0.0007) -[2023-10-16 04:50:03,246][05218] Updated weights for policy 0, policy_version 52102 (0.0008) -[2023-10-16 04:50:03,620][05218] Updated weights for policy 0, policy_version 52112 (0.0008) -[2023-10-16 04:50:03,999][05218] Updated weights for policy 0, policy_version 52122 (0.0010) -[2023-10-16 04:50:06,583][05219] Updated weights for policy 1, policy_version 51940 (0.0009) -[2023-10-16 04:50:06,980][05219] Updated weights for policy 1, policy_version 51950 (0.0010) -[2023-10-16 04:50:07,344][05219] Updated weights for policy 1, policy_version 51960 (0.0008) -[2023-10-16 04:50:07,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 106561536. Throughput: 0: 1800.7, 1: 1802.5. Samples: 26659114. Policy #0 lag: (min: 18.0, avg: 27.1, max: 50.0) -[2023-10-16 04:50:07,351][03835] Avg episode reward: [(0, '6.940'), (1, '6.910')] -[2023-10-16 04:50:07,690][05218] Updated weights for policy 0, policy_version 52132 (0.0009) -[2023-10-16 04:50:08,069][05218] Updated weights for policy 0, policy_version 52142 (0.0009) -[2023-10-16 04:50:08,442][05218] Updated weights for policy 0, policy_version 52152 (0.0009) -[2023-10-16 04:50:10,841][05219] Updated weights for policy 1, policy_version 51970 (0.0008) -[2023-10-16 04:50:11,196][05219] Updated weights for policy 1, policy_version 51980 (0.0008) -[2023-10-16 04:50:11,565][05219] Updated weights for policy 1, policy_version 51990 (0.0008) -[2023-10-16 04:50:11,918][05219] Updated weights for policy 1, policy_version 52000 (0.0008) -[2023-10-16 04:50:12,180][05218] Updated weights for policy 0, policy_version 52162 (0.0009) -[2023-10-16 04:50:12,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 106659840. Throughput: 0: 1794.9, 1: 1785.4. Samples: 26669868. Policy #0 lag: (min: 18.0, avg: 27.1, max: 50.0) -[2023-10-16 04:50:12,351][03835] Avg episode reward: [(0, '7.060'), (1, '6.210')] -[2023-10-16 04:50:12,553][05218] Updated weights for policy 0, policy_version 52172 (0.0008) -[2023-10-16 04:50:12,929][05218] Updated weights for policy 0, policy_version 52182 (0.0009) -[2023-10-16 04:50:13,305][05218] Updated weights for policy 0, policy_version 52192 (0.0009) -[2023-10-16 04:50:15,628][05219] Updated weights for policy 1, policy_version 52010 (0.0007) -[2023-10-16 04:50:16,006][05219] Updated weights for policy 1, policy_version 52020 (0.0009) -[2023-10-16 04:50:16,366][05219] Updated weights for policy 1, policy_version 52030 (0.0007) -[2023-10-16 04:50:17,189][05218] Updated weights for policy 0, policy_version 52202 (0.0007) -[2023-10-16 04:50:17,351][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 106725376. Throughput: 0: 1798.7, 1: 1798.0. Samples: 26691420. Policy #0 lag: (min: 18.0, avg: 27.1, max: 50.0) -[2023-10-16 04:50:17,352][03835] Avg episode reward: [(0, '7.030'), (1, '6.540')] -[2023-10-16 04:50:17,557][05218] Updated weights for policy 0, policy_version 52212 (0.0007) -[2023-10-16 04:50:17,935][05218] Updated weights for policy 0, policy_version 52222 (0.0008) -[2023-10-16 04:50:20,103][05219] Updated weights for policy 1, policy_version 52040 (0.0008) -[2023-10-16 04:50:20,461][05219] Updated weights for policy 1, policy_version 52050 (0.0009) -[2023-10-16 04:50:20,827][05219] Updated weights for policy 1, policy_version 52060 (0.0010) -[2023-10-16 04:50:21,548][05218] Updated weights for policy 0, policy_version 52232 (0.0009) -[2023-10-16 04:50:21,921][05218] Updated weights for policy 0, policy_version 52242 (0.0010) -[2023-10-16 04:50:22,307][05218] Updated weights for policy 0, policy_version 52252 (0.0011) -[2023-10-16 04:50:22,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 106790912. Throughput: 0: 1808.0, 1: 1797.7. Samples: 26712562. Policy #0 lag: (min: 18.0, avg: 27.1, max: 50.0) -[2023-10-16 04:50:22,351][03835] Avg episode reward: [(0, '6.300'), (1, '6.780')] -[2023-10-16 04:50:24,736][05219] Updated weights for policy 1, policy_version 52070 (0.0008) -[2023-10-16 04:50:25,101][05219] Updated weights for policy 1, policy_version 52080 (0.0007) -[2023-10-16 04:50:25,466][05219] Updated weights for policy 1, policy_version 52090 (0.0008) -[2023-10-16 04:50:25,964][05218] Updated weights for policy 0, policy_version 52262 (0.0008) -[2023-10-16 04:50:26,328][05218] Updated weights for policy 0, policy_version 52272 (0.0009) -[2023-10-16 04:50:26,703][05218] Updated weights for policy 0, policy_version 52282 (0.0008) -[2023-10-16 04:50:27,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 106889216. Throughput: 0: 1799.6, 1: 1810.5. Samples: 26724430. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:50:27,351][03835] Avg episode reward: [(0, '6.750'), (1, '6.450')] -[2023-10-16 04:50:29,190][05219] Updated weights for policy 1, policy_version 52100 (0.0007) -[2023-10-16 04:50:29,549][05219] Updated weights for policy 1, policy_version 52110 (0.0007) -[2023-10-16 04:50:29,918][05219] Updated weights for policy 1, policy_version 52120 (0.0008) -[2023-10-16 04:50:30,265][05218] Updated weights for policy 0, policy_version 52292 (0.0009) -[2023-10-16 04:50:30,643][05218] Updated weights for policy 0, policy_version 52302 (0.0009) -[2023-10-16 04:50:31,009][05218] Updated weights for policy 0, policy_version 52312 (0.0008) -[2023-10-16 04:50:32,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 106954752. Throughput: 0: 1808.2, 1: 1797.9. Samples: 26745202. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:50:32,351][03835] Avg episode reward: [(0, '6.540'), (1, '7.530')] -[2023-10-16 04:50:33,662][05219] Updated weights for policy 1, policy_version 52130 (0.0009) -[2023-10-16 04:50:34,037][05219] Updated weights for policy 1, policy_version 52140 (0.0010) -[2023-10-16 04:50:34,391][05219] Updated weights for policy 1, policy_version 52150 (0.0011) -[2023-10-16 04:50:34,754][05219] Updated weights for policy 1, policy_version 52160 (0.0009) -[2023-10-16 04:50:34,803][05218] Updated weights for policy 0, policy_version 52322 (0.0007) -[2023-10-16 04:50:35,184][05218] Updated weights for policy 0, policy_version 52332 (0.0007) -[2023-10-16 04:50:35,568][05218] Updated weights for policy 0, policy_version 52342 (0.0008) -[2023-10-16 04:50:35,950][05218] Updated weights for policy 0, policy_version 52352 (0.0010) -[2023-10-16 04:50:37,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 107020288. Throughput: 0: 1802.8, 1: 1794.1. Samples: 26767388. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:50:37,351][03835] Avg episode reward: [(0, '6.490'), (1, '7.540')] -[2023-10-16 04:50:38,541][05219] Updated weights for policy 1, policy_version 52170 (0.0008) -[2023-10-16 04:50:38,912][05219] Updated weights for policy 1, policy_version 52180 (0.0008) -[2023-10-16 04:50:39,263][05219] Updated weights for policy 1, policy_version 52190 (0.0008) -[2023-10-16 04:50:39,518][05218] Updated weights for policy 0, policy_version 52362 (0.0007) -[2023-10-16 04:50:39,892][05218] Updated weights for policy 0, policy_version 52372 (0.0007) -[2023-10-16 04:50:40,272][05218] Updated weights for policy 0, policy_version 52382 (0.0007) -[2023-10-16 04:50:42,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 107085824. Throughput: 0: 1809.3, 1: 1791.0. Samples: 26777406. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:50:42,351][03835] Avg episode reward: [(0, '6.250'), (1, '6.690')] -[2023-10-16 04:50:42,972][05219] Updated weights for policy 1, policy_version 52200 (0.0010) -[2023-10-16 04:50:43,333][05219] Updated weights for policy 1, policy_version 52210 (0.0010) -[2023-10-16 04:50:43,691][05219] Updated weights for policy 1, policy_version 52220 (0.0010) -[2023-10-16 04:50:44,103][05218] Updated weights for policy 0, policy_version 52392 (0.0010) -[2023-10-16 04:50:44,481][05218] Updated weights for policy 0, policy_version 52402 (0.0010) -[2023-10-16 04:50:44,853][05218] Updated weights for policy 0, policy_version 52412 (0.0011) -[2023-10-16 04:50:47,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 107151360. Throughput: 0: 1798.8, 1: 1788.7. Samples: 26799440. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:50:47,351][03835] Avg episode reward: [(0, '6.400'), (1, '7.720')] -[2023-10-16 04:50:47,501][05219] Updated weights for policy 1, policy_version 52230 (0.0009) -[2023-10-16 04:50:47,870][05219] Updated weights for policy 1, policy_version 52240 (0.0008) -[2023-10-16 04:50:48,225][05219] Updated weights for policy 1, policy_version 52250 (0.0007) -[2023-10-16 04:50:48,445][04891] Saving new best policy, reward=7.720! -[2023-10-16 04:50:48,781][05218] Updated weights for policy 0, policy_version 52422 (0.0009) -[2023-10-16 04:50:49,163][05218] Updated weights for policy 0, policy_version 52432 (0.0009) -[2023-10-16 04:50:49,545][05218] Updated weights for policy 0, policy_version 52442 (0.0007) -[2023-10-16 04:50:52,009][05219] Updated weights for policy 1, policy_version 52260 (0.0007) -[2023-10-16 04:50:52,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 107216896. Throughput: 0: 1798.1, 1: 1808.2. Samples: 26821398. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:50:52,351][03835] Avg episode reward: [(0, '6.850'), (1, '7.170')] -[2023-10-16 04:50:52,403][05219] Updated weights for policy 1, policy_version 52270 (0.0008) -[2023-10-16 04:50:52,762][05219] Updated weights for policy 1, policy_version 52280 (0.0010) -[2023-10-16 04:50:53,264][05218] Updated weights for policy 0, policy_version 52452 (0.0009) -[2023-10-16 04:50:53,643][05218] Updated weights for policy 0, policy_version 52462 (0.0011) -[2023-10-16 04:50:54,021][05218] Updated weights for policy 0, policy_version 52472 (0.0011) -[2023-10-16 04:50:56,448][05219] Updated weights for policy 1, policy_version 52290 (0.0009) -[2023-10-16 04:50:56,823][05219] Updated weights for policy 1, policy_version 52300 (0.0008) -[2023-10-16 04:50:57,184][05219] Updated weights for policy 1, policy_version 52310 (0.0010) -[2023-10-16 04:50:57,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 107282432. Throughput: 0: 1796.4, 1: 1796.3. Samples: 26831540. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:50:57,351][03835] Avg episode reward: [(0, '6.410'), (1, '5.770')] -[2023-10-16 04:50:57,553][05219] Updated weights for policy 1, policy_version 52320 (0.0009) -[2023-10-16 04:50:57,616][05218] Updated weights for policy 0, policy_version 52482 (0.0011) -[2023-10-16 04:50:57,986][05218] Updated weights for policy 0, policy_version 52492 (0.0008) -[2023-10-16 04:50:58,358][05218] Updated weights for policy 0, policy_version 52502 (0.0007) -[2023-10-16 04:50:58,723][05218] Updated weights for policy 0, policy_version 52512 (0.0010) -[2023-10-16 04:51:01,261][05219] Updated weights for policy 1, policy_version 52330 (0.0007) -[2023-10-16 04:51:01,619][05219] Updated weights for policy 1, policy_version 52340 (0.0009) -[2023-10-16 04:51:01,990][05219] Updated weights for policy 1, policy_version 52350 (0.0009) -[2023-10-16 04:51:02,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 107380736. Throughput: 0: 1797.1, 1: 1810.3. Samples: 26853752. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-16 04:51:02,351][03835] Avg episode reward: [(0, '6.360'), (1, '6.450')] -[2023-10-16 04:51:02,394][05218] Updated weights for policy 0, policy_version 52522 (0.0009) -[2023-10-16 04:51:02,767][05218] Updated weights for policy 0, policy_version 52532 (0.0008) -[2023-10-16 04:51:03,137][05218] Updated weights for policy 0, policy_version 52542 (0.0007) -[2023-10-16 04:51:05,744][05219] Updated weights for policy 1, policy_version 52360 (0.0008) -[2023-10-16 04:51:06,111][05219] Updated weights for policy 1, policy_version 52370 (0.0009) -[2023-10-16 04:51:06,470][05219] Updated weights for policy 1, policy_version 52380 (0.0007) -[2023-10-16 04:51:06,976][05218] Updated weights for policy 0, policy_version 52552 (0.0009) -[2023-10-16 04:51:07,341][05218] Updated weights for policy 0, policy_version 52562 (0.0011) -[2023-10-16 04:51:07,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 107446272. Throughput: 0: 1804.5, 1: 1791.3. Samples: 26874374. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-16 04:51:07,351][03835] Avg episode reward: [(0, '6.780'), (1, '6.840')] -[2023-10-16 04:51:07,721][05218] Updated weights for policy 0, policy_version 52572 (0.0011) -[2023-10-16 04:51:10,202][05219] Updated weights for policy 1, policy_version 52390 (0.0009) -[2023-10-16 04:51:10,562][05219] Updated weights for policy 1, policy_version 52400 (0.0009) -[2023-10-16 04:51:10,930][05219] Updated weights for policy 1, policy_version 52410 (0.0010) -[2023-10-16 04:51:11,230][05218] Updated weights for policy 0, policy_version 52582 (0.0011) -[2023-10-16 04:51:11,604][05218] Updated weights for policy 0, policy_version 52592 (0.0011) -[2023-10-16 04:51:11,977][05218] Updated weights for policy 0, policy_version 52602 (0.0010) -[2023-10-16 04:51:12,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 107544576. Throughput: 0: 1795.9, 1: 1805.5. Samples: 26886492. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-16 04:51:12,351][03835] Avg episode reward: [(0, '6.440'), (1, '6.930')] -[2023-10-16 04:51:14,759][05219] Updated weights for policy 1, policy_version 52420 (0.0008) -[2023-10-16 04:51:15,125][05219] Updated weights for policy 1, policy_version 52430 (0.0008) -[2023-10-16 04:51:15,494][05219] Updated weights for policy 1, policy_version 52440 (0.0009) -[2023-10-16 04:51:15,734][05218] Updated weights for policy 0, policy_version 52612 (0.0009) -[2023-10-16 04:51:16,106][05218] Updated weights for policy 0, policy_version 52622 (0.0009) -[2023-10-16 04:51:16,480][05218] Updated weights for policy 0, policy_version 52632 (0.0009) -[2023-10-16 04:51:17,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 107610112. Throughput: 0: 1804.8, 1: 1789.4. Samples: 26906940. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-16 04:51:17,351][03835] Avg episode reward: [(0, '6.560'), (1, '7.250')] -[2023-10-16 04:51:19,129][05219] Updated weights for policy 1, policy_version 52450 (0.0008) -[2023-10-16 04:51:19,492][05219] Updated weights for policy 1, policy_version 52460 (0.0009) -[2023-10-16 04:51:19,865][05219] Updated weights for policy 1, policy_version 52470 (0.0010) -[2023-10-16 04:51:20,226][05218] Updated weights for policy 0, policy_version 52642 (0.0010) -[2023-10-16 04:51:20,228][05219] Updated weights for policy 1, policy_version 52480 (0.0010) -[2023-10-16 04:51:20,608][05218] Updated weights for policy 0, policy_version 52652 (0.0009) -[2023-10-16 04:51:20,984][05218] Updated weights for policy 0, policy_version 52662 (0.0008) -[2023-10-16 04:51:21,364][05218] Updated weights for policy 0, policy_version 52672 (0.0007) -[2023-10-16 04:51:22,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14745.6, 300 sec: 14440.2). Total num frames: 107675648. Throughput: 0: 1795.2, 1: 1791.7. Samples: 26928798. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-16 04:51:22,351][03835] Avg episode reward: [(0, '7.090'), (1, '7.110')] -[2023-10-16 04:51:24,145][05219] Updated weights for policy 1, policy_version 52490 (0.0009) -[2023-10-16 04:51:24,514][05219] Updated weights for policy 1, policy_version 52500 (0.0009) -[2023-10-16 04:51:24,892][05219] Updated weights for policy 1, policy_version 52510 (0.0007) -[2023-10-16 04:51:25,190][05218] Updated weights for policy 0, policy_version 52682 (0.0007) -[2023-10-16 04:51:25,556][05218] Updated weights for policy 0, policy_version 52692 (0.0007) -[2023-10-16 04:51:25,933][05218] Updated weights for policy 0, policy_version 52702 (0.0007) -[2023-10-16 04:51:27,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 107741184. Throughput: 0: 1807.3, 1: 1793.1. Samples: 26939426. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-16 04:51:27,351][03835] Avg episode reward: [(0, '6.300'), (1, '7.310')] -[2023-10-16 04:51:28,577][05219] Updated weights for policy 1, policy_version 52520 (0.0007) -[2023-10-16 04:51:28,947][05219] Updated weights for policy 1, policy_version 52530 (0.0009) -[2023-10-16 04:51:29,320][05219] Updated weights for policy 1, policy_version 52540 (0.0009) -[2023-10-16 04:51:29,620][05218] Updated weights for policy 0, policy_version 52712 (0.0009) -[2023-10-16 04:51:29,986][05218] Updated weights for policy 0, policy_version 52722 (0.0007) -[2023-10-16 04:51:30,368][05218] Updated weights for policy 0, policy_version 52732 (0.0008) -[2023-10-16 04:51:32,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 107806720. Throughput: 0: 1799.6, 1: 1794.1. Samples: 26961154. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-16 04:51:32,351][03835] Avg episode reward: [(0, '7.190'), (1, '7.240')] -[2023-10-16 04:51:32,887][05219] Updated weights for policy 1, policy_version 52550 (0.0008) -[2023-10-16 04:51:33,246][05219] Updated weights for policy 1, policy_version 52560 (0.0009) -[2023-10-16 04:51:33,615][05219] Updated weights for policy 1, policy_version 52570 (0.0010) -[2023-10-16 04:51:34,136][05218] Updated weights for policy 0, policy_version 52742 (0.0008) -[2023-10-16 04:51:34,523][05218] Updated weights for policy 0, policy_version 52752 (0.0009) -[2023-10-16 04:51:34,901][05218] Updated weights for policy 0, policy_version 52762 (0.0009) -[2023-10-16 04:51:37,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 107872256. Throughput: 0: 1794.7, 1: 1799.4. Samples: 26983132. Policy #0 lag: (min: 1.0, avg: 6.1, max: 33.0) -[2023-10-16 04:51:37,351][03835] Avg episode reward: [(0, '6.710'), (1, '6.490')] -[2023-10-16 04:51:37,361][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000052768_54034432.pth... -[2023-10-16 04:51:37,401][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000051104_52330496.pth -[2023-10-16 04:51:37,531][05219] Updated weights for policy 1, policy_version 52580 (0.0010) -[2023-10-16 04:51:37,894][05219] Updated weights for policy 1, policy_version 52590 (0.0011) -[2023-10-16 04:51:38,251][05219] Updated weights for policy 1, policy_version 52600 (0.0009) -[2023-10-16 04:51:38,541][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000052608_53870592.pth... -[2023-10-16 04:51:38,575][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000050912_52133888.pth -[2023-10-16 04:51:38,616][05218] Updated weights for policy 0, policy_version 52772 (0.0008) -[2023-10-16 04:51:38,995][05218] Updated weights for policy 0, policy_version 52782 (0.0008) -[2023-10-16 04:51:39,366][05218] Updated weights for policy 0, policy_version 52792 (0.0009) -[2023-10-16 04:51:42,185][05219] Updated weights for policy 1, policy_version 52610 (0.0008) -[2023-10-16 04:51:42,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 107937792. Throughput: 0: 1798.9, 1: 1787.2. Samples: 26992918. Policy #0 lag: (min: 1.0, avg: 6.1, max: 33.0) -[2023-10-16 04:51:42,351][03835] Avg episode reward: [(0, '7.440'), (1, '7.830')] -[2023-10-16 04:51:42,547][05219] Updated weights for policy 1, policy_version 52620 (0.0011) -[2023-10-16 04:51:42,914][05219] Updated weights for policy 1, policy_version 52630 (0.0007) -[2023-10-16 04:51:43,027][05218] Updated weights for policy 0, policy_version 52802 (0.0009) -[2023-10-16 04:51:43,269][04891] Saving new best policy, reward=7.830! -[2023-10-16 04:51:43,274][05219] Updated weights for policy 1, policy_version 52640 (0.0007) -[2023-10-16 04:51:43,406][05218] Updated weights for policy 0, policy_version 52812 (0.0009) -[2023-10-16 04:51:43,781][05218] Updated weights for policy 0, policy_version 52822 (0.0007) -[2023-10-16 04:51:44,159][05218] Updated weights for policy 0, policy_version 52832 (0.0009) -[2023-10-16 04:51:47,075][05219] Updated weights for policy 1, policy_version 52650 (0.0009) -[2023-10-16 04:51:47,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 108003328. Throughput: 0: 1802.4, 1: 1794.1. Samples: 27015592. Policy #0 lag: (min: 1.0, avg: 6.1, max: 33.0) -[2023-10-16 04:51:47,351][03835] Avg episode reward: [(0, '7.000'), (1, '7.270')] -[2023-10-16 04:51:47,436][05219] Updated weights for policy 1, policy_version 52660 (0.0009) -[2023-10-16 04:51:47,803][05219] Updated weights for policy 1, policy_version 52670 (0.0008) -[2023-10-16 04:51:47,812][05218] Updated weights for policy 0, policy_version 52842 (0.0009) -[2023-10-16 04:51:48,184][05218] Updated weights for policy 0, policy_version 52852 (0.0009) -[2023-10-16 04:51:48,564][05218] Updated weights for policy 0, policy_version 52862 (0.0011) -[2023-10-16 04:51:51,573][05219] Updated weights for policy 1, policy_version 52680 (0.0008) -[2023-10-16 04:51:51,944][05219] Updated weights for policy 1, policy_version 52690 (0.0009) -[2023-10-16 04:51:52,137][05218] Updated weights for policy 0, policy_version 52872 (0.0009) -[2023-10-16 04:51:52,305][05219] Updated weights for policy 1, policy_version 52700 (0.0009) -[2023-10-16 04:51:52,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 108068864. Throughput: 0: 1811.7, 1: 1793.3. Samples: 27036596. Policy #0 lag: (min: 1.0, avg: 6.1, max: 33.0) -[2023-10-16 04:51:52,351][03835] Avg episode reward: [(0, '6.750'), (1, '6.870')] -[2023-10-16 04:51:52,507][05218] Updated weights for policy 0, policy_version 52882 (0.0010) -[2023-10-16 04:51:52,882][05218] Updated weights for policy 0, policy_version 52892 (0.0008) -[2023-10-16 04:51:55,964][05219] Updated weights for policy 1, policy_version 52710 (0.0009) -[2023-10-16 04:51:56,323][05219] Updated weights for policy 1, policy_version 52720 (0.0009) -[2023-10-16 04:51:56,687][05219] Updated weights for policy 1, policy_version 52730 (0.0007) -[2023-10-16 04:51:56,749][05218] Updated weights for policy 0, policy_version 52902 (0.0007) -[2023-10-16 04:51:57,123][05218] Updated weights for policy 0, policy_version 52912 (0.0010) -[2023-10-16 04:51:57,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 108167168. Throughput: 0: 1799.2, 1: 1789.1. Samples: 27047968. Policy #0 lag: (min: 1.0, avg: 6.1, max: 33.0) -[2023-10-16 04:51:57,351][03835] Avg episode reward: [(0, '6.870'), (1, '7.060')] -[2023-10-16 04:51:57,503][05218] Updated weights for policy 0, policy_version 52922 (0.0008) -[2023-10-16 04:52:00,543][05219] Updated weights for policy 1, policy_version 52740 (0.0009) -[2023-10-16 04:52:00,908][05219] Updated weights for policy 1, policy_version 52750 (0.0008) -[2023-10-16 04:52:01,112][05218] Updated weights for policy 0, policy_version 52932 (0.0009) -[2023-10-16 04:52:01,264][05219] Updated weights for policy 1, policy_version 52760 (0.0008) -[2023-10-16 04:52:01,477][05218] Updated weights for policy 0, policy_version 52942 (0.0008) -[2023-10-16 04:52:01,846][05218] Updated weights for policy 0, policy_version 52952 (0.0008) -[2023-10-16 04:52:02,350][03835] Fps is (10 sec: 19660.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 108265472. Throughput: 0: 1809.6, 1: 1792.5. Samples: 27069034. Policy #0 lag: (min: 1.0, avg: 6.1, max: 33.0) -[2023-10-16 04:52:02,351][03835] Avg episode reward: [(0, '6.320'), (1, '5.920')] -[2023-10-16 04:52:05,163][05219] Updated weights for policy 1, policy_version 52770 (0.0007) -[2023-10-16 04:52:05,528][05219] Updated weights for policy 1, policy_version 52780 (0.0008) -[2023-10-16 04:52:05,654][05218] Updated weights for policy 0, policy_version 52962 (0.0008) -[2023-10-16 04:52:05,893][05219] Updated weights for policy 1, policy_version 52790 (0.0008) -[2023-10-16 04:52:06,026][05218] Updated weights for policy 0, policy_version 52972 (0.0008) -[2023-10-16 04:52:06,262][05219] Updated weights for policy 1, policy_version 52800 (0.0008) -[2023-10-16 04:52:06,406][05218] Updated weights for policy 0, policy_version 52982 (0.0008) -[2023-10-16 04:52:06,773][05218] Updated weights for policy 0, policy_version 52992 (0.0009) -[2023-10-16 04:52:07,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 108331008. Throughput: 0: 1796.9, 1: 1780.5. Samples: 27089782. Policy #0 lag: (min: 1.0, avg: 6.1, max: 33.0) -[2023-10-16 04:52:07,351][03835] Avg episode reward: [(0, '6.190'), (1, '7.160')] -[2023-10-16 04:52:09,889][05219] Updated weights for policy 1, policy_version 52810 (0.0011) -[2023-10-16 04:52:10,253][05219] Updated weights for policy 1, policy_version 52820 (0.0010) -[2023-10-16 04:52:10,598][05218] Updated weights for policy 0, policy_version 53002 (0.0009) -[2023-10-16 04:52:10,621][05219] Updated weights for policy 1, policy_version 52830 (0.0007) -[2023-10-16 04:52:10,972][05218] Updated weights for policy 0, policy_version 53012 (0.0008) -[2023-10-16 04:52:11,346][05218] Updated weights for policy 0, policy_version 53022 (0.0007) -[2023-10-16 04:52:12,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 108396544. Throughput: 0: 1809.7, 1: 1794.9. Samples: 27101632. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:52:12,351][03835] Avg episode reward: [(0, '6.270'), (1, '6.890')] -[2023-10-16 04:52:14,378][05219] Updated weights for policy 1, policy_version 52840 (0.0009) -[2023-10-16 04:52:14,749][05219] Updated weights for policy 1, policy_version 52850 (0.0007) -[2023-10-16 04:52:15,112][05219] Updated weights for policy 1, policy_version 52860 (0.0011) -[2023-10-16 04:52:15,122][05218] Updated weights for policy 0, policy_version 53032 (0.0009) -[2023-10-16 04:52:15,496][05218] Updated weights for policy 0, policy_version 53042 (0.0010) -[2023-10-16 04:52:15,871][05218] Updated weights for policy 0, policy_version 53052 (0.0009) -[2023-10-16 04:52:17,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 108462080. Throughput: 0: 1797.7, 1: 1781.3. Samples: 27122210. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:52:17,351][03835] Avg episode reward: [(0, '6.950'), (1, '6.870')] -[2023-10-16 04:52:18,949][05219] Updated weights for policy 1, policy_version 52870 (0.0007) -[2023-10-16 04:52:19,318][05219] Updated weights for policy 1, policy_version 52880 (0.0008) -[2023-10-16 04:52:19,679][05219] Updated weights for policy 1, policy_version 52890 (0.0007) -[2023-10-16 04:52:19,720][05218] Updated weights for policy 0, policy_version 53062 (0.0007) -[2023-10-16 04:52:20,104][05218] Updated weights for policy 0, policy_version 53072 (0.0010) -[2023-10-16 04:52:20,484][05218] Updated weights for policy 0, policy_version 53082 (0.0009) -[2023-10-16 04:52:22,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 108527616. Throughput: 0: 1810.1, 1: 1783.7. Samples: 27144854. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:52:22,351][03835] Avg episode reward: [(0, '7.250'), (1, '6.500')] -[2023-10-16 04:52:23,436][05219] Updated weights for policy 1, policy_version 52900 (0.0009) -[2023-10-16 04:52:23,808][05219] Updated weights for policy 1, policy_version 52910 (0.0010) -[2023-10-16 04:52:24,061][05218] Updated weights for policy 0, policy_version 53092 (0.0008) -[2023-10-16 04:52:24,169][05219] Updated weights for policy 1, policy_version 52920 (0.0008) -[2023-10-16 04:52:24,424][05218] Updated weights for policy 0, policy_version 53102 (0.0010) -[2023-10-16 04:52:24,801][05218] Updated weights for policy 0, policy_version 53112 (0.0009) -[2023-10-16 04:52:27,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 108593152. Throughput: 0: 1805.9, 1: 1783.3. Samples: 27154432. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:52:27,351][03835] Avg episode reward: [(0, '7.380'), (1, '6.540')] -[2023-10-16 04:52:28,048][05219] Updated weights for policy 1, policy_version 52930 (0.0008) -[2023-10-16 04:52:28,413][05219] Updated weights for policy 1, policy_version 52940 (0.0010) -[2023-10-16 04:52:28,535][05218] Updated weights for policy 0, policy_version 53122 (0.0007) -[2023-10-16 04:52:28,766][05219] Updated weights for policy 1, policy_version 52950 (0.0008) -[2023-10-16 04:52:28,913][05218] Updated weights for policy 0, policy_version 53132 (0.0007) -[2023-10-16 04:52:29,125][05219] Updated weights for policy 1, policy_version 52960 (0.0007) -[2023-10-16 04:52:29,293][05218] Updated weights for policy 0, policy_version 53142 (0.0009) -[2023-10-16 04:52:29,674][05218] Updated weights for policy 0, policy_version 53152 (0.0007) -[2023-10-16 04:52:32,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 108658688. Throughput: 0: 1797.1, 1: 1780.1. Samples: 27176568. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:52:32,352][03835] Avg episode reward: [(0, '7.680'), (1, '7.410')] -[2023-10-16 04:52:32,353][04766] Saving new best policy, reward=7.680! -[2023-10-16 04:52:32,839][05219] Updated weights for policy 1, policy_version 52970 (0.0008) -[2023-10-16 04:52:33,206][05219] Updated weights for policy 1, policy_version 52980 (0.0008) -[2023-10-16 04:52:33,568][05219] Updated weights for policy 1, policy_version 52990 (0.0009) -[2023-10-16 04:52:33,591][05218] Updated weights for policy 0, policy_version 53162 (0.0009) -[2023-10-16 04:52:33,968][05218] Updated weights for policy 0, policy_version 53172 (0.0010) -[2023-10-16 04:52:34,348][05218] Updated weights for policy 0, policy_version 53182 (0.0008) -[2023-10-16 04:52:37,313][05219] Updated weights for policy 1, policy_version 53000 (0.0007) -[2023-10-16 04:52:37,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 108724224. Throughput: 0: 1807.1, 1: 1798.7. Samples: 27198856. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:52:37,351][03835] Avg episode reward: [(0, '6.760'), (1, '6.950')] -[2023-10-16 04:52:37,678][05219] Updated weights for policy 1, policy_version 53010 (0.0007) -[2023-10-16 04:52:37,945][05218] Updated weights for policy 0, policy_version 53192 (0.0009) -[2023-10-16 04:52:38,037][05219] Updated weights for policy 1, policy_version 53020 (0.0007) -[2023-10-16 04:52:38,309][05218] Updated weights for policy 0, policy_version 53202 (0.0010) -[2023-10-16 04:52:38,685][05218] Updated weights for policy 0, policy_version 53212 (0.0008) -[2023-10-16 04:52:41,753][05219] Updated weights for policy 1, policy_version 53030 (0.0008) -[2023-10-16 04:52:42,124][05219] Updated weights for policy 1, policy_version 53040 (0.0007) -[2023-10-16 04:52:42,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 108789760. Throughput: 0: 1797.2, 1: 1779.0. Samples: 27208896. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:52:42,351][03835] Avg episode reward: [(0, '6.590'), (1, '6.290')] -[2023-10-16 04:52:42,437][05218] Updated weights for policy 0, policy_version 53222 (0.0008) -[2023-10-16 04:52:42,486][05219] Updated weights for policy 1, policy_version 53050 (0.0007) -[2023-10-16 04:52:42,813][05218] Updated weights for policy 0, policy_version 53232 (0.0008) -[2023-10-16 04:52:43,186][05218] Updated weights for policy 0, policy_version 53242 (0.0010) -[2023-10-16 04:52:46,018][05219] Updated weights for policy 1, policy_version 53060 (0.0009) -[2023-10-16 04:52:46,393][05219] Updated weights for policy 1, policy_version 53070 (0.0010) -[2023-10-16 04:52:46,758][05219] Updated weights for policy 1, policy_version 53080 (0.0010) -[2023-10-16 04:52:46,998][05218] Updated weights for policy 0, policy_version 53252 (0.0011) -[2023-10-16 04:52:47,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 108888064. Throughput: 0: 1803.6, 1: 1803.8. Samples: 27231366. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:52:47,351][03835] Avg episode reward: [(0, '6.760'), (1, '6.730')] -[2023-10-16 04:52:47,375][05218] Updated weights for policy 0, policy_version 53262 (0.0011) -[2023-10-16 04:52:47,748][05218] Updated weights for policy 0, policy_version 53272 (0.0009) -[2023-10-16 04:52:50,606][05219] Updated weights for policy 1, policy_version 53090 (0.0008) -[2023-10-16 04:52:50,987][05219] Updated weights for policy 1, policy_version 53100 (0.0011) -[2023-10-16 04:52:51,349][05219] Updated weights for policy 1, policy_version 53110 (0.0009) -[2023-10-16 04:52:51,350][05218] Updated weights for policy 0, policy_version 53282 (0.0010) -[2023-10-16 04:52:51,722][05219] Updated weights for policy 1, policy_version 53120 (0.0007) -[2023-10-16 04:52:51,722][05218] Updated weights for policy 0, policy_version 53292 (0.0009) -[2023-10-16 04:52:52,096][05218] Updated weights for policy 0, policy_version 53302 (0.0010) -[2023-10-16 04:52:52,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 108953600. Throughput: 0: 1801.1, 1: 1792.0. Samples: 27251474. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-16 04:52:52,351][03835] Avg episode reward: [(0, '6.490'), (1, '6.620')] -[2023-10-16 04:52:52,475][05218] Updated weights for policy 0, policy_version 53312 (0.0007) -[2023-10-16 04:52:55,388][05219] Updated weights for policy 1, policy_version 53130 (0.0010) -[2023-10-16 04:52:55,756][05219] Updated weights for policy 1, policy_version 53140 (0.0011) -[2023-10-16 04:52:56,116][05219] Updated weights for policy 1, policy_version 53150 (0.0008) -[2023-10-16 04:52:56,263][05218] Updated weights for policy 0, policy_version 53322 (0.0007) -[2023-10-16 04:52:56,630][05218] Updated weights for policy 0, policy_version 53332 (0.0008) -[2023-10-16 04:52:57,009][05218] Updated weights for policy 0, policy_version 53342 (0.0008) -[2023-10-16 04:52:57,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 109051904. Throughput: 0: 1797.5, 1: 1808.7. Samples: 27263912. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-16 04:52:57,351][03835] Avg episode reward: [(0, '6.460'), (1, '6.920')] -[2023-10-16 04:52:59,918][05219] Updated weights for policy 1, policy_version 53160 (0.0007) -[2023-10-16 04:53:00,291][05219] Updated weights for policy 1, policy_version 53170 (0.0007) -[2023-10-16 04:53:00,655][05219] Updated weights for policy 1, policy_version 53180 (0.0009) -[2023-10-16 04:53:00,808][05218] Updated weights for policy 0, policy_version 53352 (0.0009) -[2023-10-16 04:53:01,182][05218] Updated weights for policy 0, policy_version 53362 (0.0009) -[2023-10-16 04:53:01,560][05218] Updated weights for policy 0, policy_version 53372 (0.0010) -[2023-10-16 04:53:02,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 109117440. Throughput: 0: 1802.1, 1: 1793.3. Samples: 27284004. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-16 04:53:02,351][03835] Avg episode reward: [(0, '7.370'), (1, '7.320')] -[2023-10-16 04:53:04,478][05219] Updated weights for policy 1, policy_version 53190 (0.0009) -[2023-10-16 04:53:04,838][05219] Updated weights for policy 1, policy_version 53200 (0.0007) -[2023-10-16 04:53:05,198][05218] Updated weights for policy 0, policy_version 53382 (0.0009) -[2023-10-16 04:53:05,203][05219] Updated weights for policy 1, policy_version 53210 (0.0007) -[2023-10-16 04:53:05,576][05218] Updated weights for policy 0, policy_version 53392 (0.0008) -[2023-10-16 04:53:05,947][05218] Updated weights for policy 0, policy_version 53402 (0.0008) -[2023-10-16 04:53:07,351][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 109182976. Throughput: 0: 1786.5, 1: 1791.9. Samples: 27305882. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-16 04:53:07,352][03835] Avg episode reward: [(0, '7.420'), (1, '7.760')] -[2023-10-16 04:53:09,040][05219] Updated weights for policy 1, policy_version 53220 (0.0008) -[2023-10-16 04:53:09,433][05219] Updated weights for policy 1, policy_version 53230 (0.0009) -[2023-10-16 04:53:09,593][05218] Updated weights for policy 0, policy_version 53412 (0.0010) -[2023-10-16 04:53:09,796][05219] Updated weights for policy 1, policy_version 53240 (0.0008) -[2023-10-16 04:53:09,973][05218] Updated weights for policy 0, policy_version 53422 (0.0009) -[2023-10-16 04:53:10,334][05218] Updated weights for policy 0, policy_version 53432 (0.0010) -[2023-10-16 04:53:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 109248512. Throughput: 0: 1799.3, 1: 1792.1. Samples: 27316044. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-16 04:53:12,351][03835] Avg episode reward: [(0, '6.930'), (1, '7.060')] -[2023-10-16 04:53:13,715][05219] Updated weights for policy 1, policy_version 53250 (0.0007) -[2023-10-16 04:53:14,091][05219] Updated weights for policy 1, policy_version 53260 (0.0010) -[2023-10-16 04:53:14,177][05218] Updated weights for policy 0, policy_version 53442 (0.0010) -[2023-10-16 04:53:14,453][05219] Updated weights for policy 1, policy_version 53270 (0.0008) -[2023-10-16 04:53:14,554][05218] Updated weights for policy 0, policy_version 53452 (0.0007) -[2023-10-16 04:53:14,810][05219] Updated weights for policy 1, policy_version 53280 (0.0007) -[2023-10-16 04:53:14,930][05218] Updated weights for policy 0, policy_version 53462 (0.0007) -[2023-10-16 04:53:15,311][05218] Updated weights for policy 0, policy_version 53472 (0.0008) -[2023-10-16 04:53:17,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 109314048. Throughput: 0: 1785.9, 1: 1790.6. Samples: 27337512. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-16 04:53:17,351][03835] Avg episode reward: [(0, '6.840'), (1, '7.230')] -[2023-10-16 04:53:18,318][05219] Updated weights for policy 1, policy_version 53290 (0.0007) -[2023-10-16 04:53:18,677][05219] Updated weights for policy 1, policy_version 53300 (0.0007) -[2023-10-16 04:53:19,030][05218] Updated weights for policy 0, policy_version 53482 (0.0007) -[2023-10-16 04:53:19,037][05219] Updated weights for policy 1, policy_version 53310 (0.0007) -[2023-10-16 04:53:19,415][05218] Updated weights for policy 0, policy_version 53492 (0.0007) -[2023-10-16 04:53:19,783][05218] Updated weights for policy 0, policy_version 53502 (0.0008) -[2023-10-16 04:53:22,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 109379584. Throughput: 0: 1782.0, 1: 1800.0. Samples: 27360046. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-16 04:53:22,351][03835] Avg episode reward: [(0, '6.580'), (1, '7.580')] -[2023-10-16 04:53:22,943][05219] Updated weights for policy 1, policy_version 53320 (0.0007) -[2023-10-16 04:53:23,305][05219] Updated weights for policy 1, policy_version 53330 (0.0008) -[2023-10-16 04:53:23,608][05218] Updated weights for policy 0, policy_version 53512 (0.0009) -[2023-10-16 04:53:23,677][05219] Updated weights for policy 1, policy_version 53340 (0.0008) -[2023-10-16 04:53:23,981][05218] Updated weights for policy 0, policy_version 53522 (0.0008) -[2023-10-16 04:53:24,355][05218] Updated weights for policy 0, policy_version 53532 (0.0007) -[2023-10-16 04:53:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 109445120. Throughput: 0: 1779.9, 1: 1797.0. Samples: 27369856. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:53:27,351][03835] Avg episode reward: [(0, '7.040'), (1, '8.820')] -[2023-10-16 04:53:27,457][05219] Updated weights for policy 1, policy_version 53350 (0.0009) -[2023-10-16 04:53:27,821][05219] Updated weights for policy 1, policy_version 53360 (0.0008) -[2023-10-16 04:53:28,113][05218] Updated weights for policy 0, policy_version 53542 (0.0008) -[2023-10-16 04:53:28,187][05219] Updated weights for policy 1, policy_version 53370 (0.0007) -[2023-10-16 04:53:28,401][04891] Saving new best policy, reward=8.820! -[2023-10-16 04:53:28,494][05218] Updated weights for policy 0, policy_version 53552 (0.0009) -[2023-10-16 04:53:28,877][05218] Updated weights for policy 0, policy_version 53562 (0.0009) -[2023-10-16 04:53:32,033][05219] Updated weights for policy 1, policy_version 53380 (0.0009) -[2023-10-16 04:53:32,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 109510656. Throughput: 0: 1779.9, 1: 1792.2. Samples: 27392110. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:53:32,351][03835] Avg episode reward: [(0, '6.220'), (1, '8.180')] -[2023-10-16 04:53:32,402][05219] Updated weights for policy 1, policy_version 53390 (0.0009) -[2023-10-16 04:53:32,586][05218] Updated weights for policy 0, policy_version 53572 (0.0009) -[2023-10-16 04:53:32,769][05219] Updated weights for policy 1, policy_version 53400 (0.0009) -[2023-10-16 04:53:32,969][05218] Updated weights for policy 0, policy_version 53582 (0.0009) -[2023-10-16 04:53:33,344][05218] Updated weights for policy 0, policy_version 53592 (0.0008) -[2023-10-16 04:53:36,562][05219] Updated weights for policy 1, policy_version 53410 (0.0009) -[2023-10-16 04:53:36,920][05219] Updated weights for policy 1, policy_version 53420 (0.0009) -[2023-10-16 04:53:37,233][05218] Updated weights for policy 0, policy_version 53602 (0.0009) -[2023-10-16 04:53:37,290][05219] Updated weights for policy 1, policy_version 53430 (0.0009) -[2023-10-16 04:53:37,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 109576192. Throughput: 0: 1798.8, 1: 1794.8. Samples: 27413186. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:53:37,351][03835] Avg episode reward: [(0, '6.640'), (1, '7.150')] -[2023-10-16 04:53:37,604][05218] Updated weights for policy 0, policy_version 53612 (0.0008) -[2023-10-16 04:53:37,646][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000053440_54722560.pth... -[2023-10-16 04:53:37,646][05219] Updated weights for policy 1, policy_version 53440 (0.0008) -[2023-10-16 04:53:37,685][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000051744_52985856.pth -[2023-10-16 04:53:37,979][05218] Updated weights for policy 0, policy_version 53622 (0.0011) -[2023-10-16 04:53:38,350][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000053632_54919168.pth... -[2023-10-16 04:53:38,352][05218] Updated weights for policy 0, policy_version 53632 (0.0011) -[2023-10-16 04:53:38,386][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000051936_53182464.pth -[2023-10-16 04:53:41,354][05219] Updated weights for policy 1, policy_version 53450 (0.0007) -[2023-10-16 04:53:41,720][05219] Updated weights for policy 1, policy_version 53460 (0.0007) -[2023-10-16 04:53:42,062][05218] Updated weights for policy 0, policy_version 53642 (0.0008) -[2023-10-16 04:53:42,080][05219] Updated weights for policy 1, policy_version 53470 (0.0007) -[2023-10-16 04:53:42,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 109674496. Throughput: 0: 1773.2, 1: 1779.1. Samples: 27423766. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:53:42,351][03835] Avg episode reward: [(0, '7.410'), (1, '8.760')] -[2023-10-16 04:53:42,439][05218] Updated weights for policy 0, policy_version 53652 (0.0009) -[2023-10-16 04:53:42,822][05218] Updated weights for policy 0, policy_version 53662 (0.0008) -[2023-10-16 04:53:45,845][05219] Updated weights for policy 1, policy_version 53480 (0.0009) -[2023-10-16 04:53:46,210][05219] Updated weights for policy 1, policy_version 53490 (0.0008) -[2023-10-16 04:53:46,572][05219] Updated weights for policy 1, policy_version 53500 (0.0009) -[2023-10-16 04:53:46,602][05218] Updated weights for policy 0, policy_version 53672 (0.0009) -[2023-10-16 04:53:46,977][05218] Updated weights for policy 0, policy_version 53682 (0.0010) -[2023-10-16 04:53:47,347][05218] Updated weights for policy 0, policy_version 53692 (0.0009) -[2023-10-16 04:53:47,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 109740032. Throughput: 0: 1798.2, 1: 1791.0. Samples: 27445518. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:53:47,351][03835] Avg episode reward: [(0, '6.170'), (1, '7.420')] -[2023-10-16 04:53:50,319][05219] Updated weights for policy 1, policy_version 53510 (0.0007) -[2023-10-16 04:53:50,688][05219] Updated weights for policy 1, policy_version 53520 (0.0009) -[2023-10-16 04:53:51,042][05219] Updated weights for policy 1, policy_version 53530 (0.0009) -[2023-10-16 04:53:51,274][05218] Updated weights for policy 0, policy_version 53702 (0.0009) -[2023-10-16 04:53:51,655][05218] Updated weights for policy 0, policy_version 53712 (0.0008) -[2023-10-16 04:53:52,030][05218] Updated weights for policy 0, policy_version 53722 (0.0008) -[2023-10-16 04:53:52,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.7, 300 sec: 14440.2). Total num frames: 109838336. Throughput: 0: 1772.1, 1: 1775.3. Samples: 27465514. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:53:52,351][03835] Avg episode reward: [(0, '6.700'), (1, '7.000')] -[2023-10-16 04:53:55,147][05219] Updated weights for policy 1, policy_version 53540 (0.0008) -[2023-10-16 04:53:55,545][05219] Updated weights for policy 1, policy_version 53550 (0.0008) -[2023-10-16 04:53:55,658][05218] Updated weights for policy 0, policy_version 53732 (0.0007) -[2023-10-16 04:53:55,904][05219] Updated weights for policy 1, policy_version 53560 (0.0009) -[2023-10-16 04:53:56,033][05218] Updated weights for policy 0, policy_version 53742 (0.0009) -[2023-10-16 04:53:56,415][05218] Updated weights for policy 0, policy_version 53752 (0.0009) -[2023-10-16 04:53:57,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 109903872. Throughput: 0: 1796.8, 1: 1801.1. Samples: 27477950. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:53:57,351][03835] Avg episode reward: [(0, '6.720'), (1, '7.090')] -[2023-10-16 04:53:59,554][05219] Updated weights for policy 1, policy_version 53570 (0.0009) -[2023-10-16 04:53:59,927][05219] Updated weights for policy 1, policy_version 53580 (0.0010) -[2023-10-16 04:54:00,233][05218] Updated weights for policy 0, policy_version 53762 (0.0009) -[2023-10-16 04:54:00,289][05219] Updated weights for policy 1, policy_version 53590 (0.0009) -[2023-10-16 04:54:00,617][05218] Updated weights for policy 0, policy_version 53772 (0.0008) -[2023-10-16 04:54:00,653][05219] Updated weights for policy 1, policy_version 53600 (0.0009) -[2023-10-16 04:54:00,990][05218] Updated weights for policy 0, policy_version 53782 (0.0008) -[2023-10-16 04:54:01,361][05218] Updated weights for policy 0, policy_version 53792 (0.0009) -[2023-10-16 04:54:02,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 109969408. Throughput: 0: 1779.2, 1: 1776.8. Samples: 27497532. Policy #0 lag: (min: 31.0, avg: 32.1, max: 53.0) -[2023-10-16 04:54:02,351][03835] Avg episode reward: [(0, '6.610'), (1, '7.060')] -[2023-10-16 04:54:04,504][05219] Updated weights for policy 1, policy_version 53610 (0.0007) -[2023-10-16 04:54:04,858][05219] Updated weights for policy 1, policy_version 53620 (0.0007) -[2023-10-16 04:54:05,197][05218] Updated weights for policy 0, policy_version 53802 (0.0007) -[2023-10-16 04:54:05,231][05219] Updated weights for policy 1, policy_version 53630 (0.0008) -[2023-10-16 04:54:05,577][05218] Updated weights for policy 0, policy_version 53812 (0.0008) -[2023-10-16 04:54:05,955][05218] Updated weights for policy 0, policy_version 53822 (0.0007) -[2023-10-16 04:54:07,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 110034944. Throughput: 0: 1776.8, 1: 1766.9. Samples: 27519512. Policy #0 lag: (min: 31.0, avg: 32.1, max: 53.0) -[2023-10-16 04:54:07,351][03835] Avg episode reward: [(0, '7.020'), (1, '6.720')] -[2023-10-16 04:54:09,098][05219] Updated weights for policy 1, policy_version 53640 (0.0009) -[2023-10-16 04:54:09,459][05219] Updated weights for policy 1, policy_version 53650 (0.0007) -[2023-10-16 04:54:09,629][05218] Updated weights for policy 0, policy_version 53832 (0.0008) -[2023-10-16 04:54:09,841][05219] Updated weights for policy 1, policy_version 53660 (0.0010) -[2023-10-16 04:54:09,995][05218] Updated weights for policy 0, policy_version 53842 (0.0009) -[2023-10-16 04:54:10,370][05218] Updated weights for policy 0, policy_version 53852 (0.0010) -[2023-10-16 04:54:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 110100480. Throughput: 0: 1785.1, 1: 1765.4. Samples: 27529628. Policy #0 lag: (min: 31.0, avg: 32.1, max: 53.0) -[2023-10-16 04:54:12,351][03835] Avg episode reward: [(0, '6.750'), (1, '6.310')] -[2023-10-16 04:54:13,634][05219] Updated weights for policy 1, policy_version 53670 (0.0007) -[2023-10-16 04:54:14,009][05219] Updated weights for policy 1, policy_version 53680 (0.0008) -[2023-10-16 04:54:14,212][05218] Updated weights for policy 0, policy_version 53862 (0.0010) -[2023-10-16 04:54:14,362][05219] Updated weights for policy 1, policy_version 53690 (0.0008) -[2023-10-16 04:54:14,588][05218] Updated weights for policy 0, policy_version 53872 (0.0009) -[2023-10-16 04:54:14,959][05218] Updated weights for policy 0, policy_version 53882 (0.0010) -[2023-10-16 04:54:17,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 110166016. Throughput: 0: 1773.7, 1: 1770.0. Samples: 27551578. Policy #0 lag: (min: 31.0, avg: 32.1, max: 53.0) -[2023-10-16 04:54:17,351][03835] Avg episode reward: [(0, '7.260'), (1, '7.570')] -[2023-10-16 04:54:18,113][05219] Updated weights for policy 1, policy_version 53700 (0.0008) -[2023-10-16 04:54:18,490][05219] Updated weights for policy 1, policy_version 53710 (0.0010) -[2023-10-16 04:54:18,747][05218] Updated weights for policy 0, policy_version 53892 (0.0010) -[2023-10-16 04:54:18,861][05219] Updated weights for policy 1, policy_version 53720 (0.0009) -[2023-10-16 04:54:19,127][05218] Updated weights for policy 0, policy_version 53902 (0.0008) -[2023-10-16 04:54:19,505][05218] Updated weights for policy 0, policy_version 53912 (0.0009) -[2023-10-16 04:54:22,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 110231552. Throughput: 0: 1779.4, 1: 1788.7. Samples: 27573752. Policy #0 lag: (min: 31.0, avg: 32.1, max: 53.0) -[2023-10-16 04:54:22,351][03835] Avg episode reward: [(0, '7.290'), (1, '7.010')] -[2023-10-16 04:54:22,720][05219] Updated weights for policy 1, policy_version 53730 (0.0009) -[2023-10-16 04:54:23,084][05219] Updated weights for policy 1, policy_version 53740 (0.0009) -[2023-10-16 04:54:23,179][05218] Updated weights for policy 0, policy_version 53922 (0.0008) -[2023-10-16 04:54:23,437][05219] Updated weights for policy 1, policy_version 53750 (0.0009) -[2023-10-16 04:54:23,564][05218] Updated weights for policy 0, policy_version 53932 (0.0007) -[2023-10-16 04:54:23,802][05219] Updated weights for policy 1, policy_version 53760 (0.0008) -[2023-10-16 04:54:23,938][05218] Updated weights for policy 0, policy_version 53942 (0.0007) -[2023-10-16 04:54:24,312][05218] Updated weights for policy 0, policy_version 53952 (0.0010) -[2023-10-16 04:54:27,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 110297088. Throughput: 0: 1782.3, 1: 1769.8. Samples: 27583610. Policy #0 lag: (min: 31.0, avg: 32.1, max: 53.0) -[2023-10-16 04:54:27,351][03835] Avg episode reward: [(0, '6.660'), (1, '6.870')] -[2023-10-16 04:54:27,622][05219] Updated weights for policy 1, policy_version 53770 (0.0008) -[2023-10-16 04:54:27,989][05219] Updated weights for policy 1, policy_version 53780 (0.0008) -[2023-10-16 04:54:28,055][05218] Updated weights for policy 0, policy_version 53962 (0.0007) -[2023-10-16 04:54:28,349][05219] Updated weights for policy 1, policy_version 53790 (0.0009) -[2023-10-16 04:54:28,431][05218] Updated weights for policy 0, policy_version 53972 (0.0010) -[2023-10-16 04:54:28,810][05218] Updated weights for policy 0, policy_version 53982 (0.0007) -[2023-10-16 04:54:32,238][05219] Updated weights for policy 1, policy_version 53800 (0.0009) -[2023-10-16 04:54:32,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 110362624. Throughput: 0: 1783.0, 1: 1777.3. Samples: 27605730. Policy #0 lag: (min: 31.0, avg: 32.1, max: 53.0) -[2023-10-16 04:54:32,351][03835] Avg episode reward: [(0, '6.460'), (1, '7.830')] -[2023-10-16 04:54:32,524][05218] Updated weights for policy 0, policy_version 53992 (0.0007) -[2023-10-16 04:54:32,608][05219] Updated weights for policy 1, policy_version 53810 (0.0008) -[2023-10-16 04:54:32,905][05218] Updated weights for policy 0, policy_version 54002 (0.0009) -[2023-10-16 04:54:32,967][05219] Updated weights for policy 1, policy_version 53820 (0.0007) -[2023-10-16 04:54:33,277][05218] Updated weights for policy 0, policy_version 54012 (0.0009) -[2023-10-16 04:54:36,755][05219] Updated weights for policy 1, policy_version 53830 (0.0008) -[2023-10-16 04:54:37,065][05218] Updated weights for policy 0, policy_version 54022 (0.0010) -[2023-10-16 04:54:37,111][05219] Updated weights for policy 1, policy_version 53840 (0.0008) -[2023-10-16 04:54:37,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 110428160. Throughput: 0: 1805.4, 1: 1778.1. Samples: 27626772. Policy #0 lag: (min: 31.0, avg: 32.1, max: 53.0) -[2023-10-16 04:54:37,351][03835] Avg episode reward: [(0, '6.970'), (1, '7.380')] -[2023-10-16 04:54:37,445][05218] Updated weights for policy 0, policy_version 54032 (0.0007) -[2023-10-16 04:54:37,485][05219] Updated weights for policy 1, policy_version 53850 (0.0008) -[2023-10-16 04:54:37,811][05218] Updated weights for policy 0, policy_version 54042 (0.0009) -[2023-10-16 04:54:41,328][05219] Updated weights for policy 1, policy_version 53860 (0.0007) -[2023-10-16 04:54:41,564][05218] Updated weights for policy 0, policy_version 54052 (0.0009) -[2023-10-16 04:54:41,716][05219] Updated weights for policy 1, policy_version 53870 (0.0007) -[2023-10-16 04:54:41,935][05218] Updated weights for policy 0, policy_version 54062 (0.0009) -[2023-10-16 04:54:42,089][05219] Updated weights for policy 1, policy_version 53880 (0.0007) -[2023-10-16 04:54:42,312][05218] Updated weights for policy 0, policy_version 54072 (0.0008) -[2023-10-16 04:54:42,350][03835] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 14218.0). Total num frames: 110493696. Throughput: 0: 1781.6, 1: 1770.9. Samples: 27637816. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-10-16 04:54:42,351][03835] Avg episode reward: [(0, '6.470'), (1, '7.640')] -[2023-10-16 04:54:45,859][05219] Updated weights for policy 1, policy_version 53890 (0.0007) -[2023-10-16 04:54:46,131][05218] Updated weights for policy 0, policy_version 54082 (0.0008) -[2023-10-16 04:54:46,227][05219] Updated weights for policy 1, policy_version 53900 (0.0008) -[2023-10-16 04:54:46,507][05218] Updated weights for policy 0, policy_version 54092 (0.0008) -[2023-10-16 04:54:46,581][05219] Updated weights for policy 1, policy_version 53910 (0.0008) -[2023-10-16 04:54:46,880][05218] Updated weights for policy 0, policy_version 54102 (0.0007) -[2023-10-16 04:54:46,955][05219] Updated weights for policy 1, policy_version 53920 (0.0009) -[2023-10-16 04:54:47,256][05218] Updated weights for policy 0, policy_version 54112 (0.0008) -[2023-10-16 04:54:47,350][03835] Fps is (10 sec: 19660.3, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 110624768. Throughput: 0: 1804.7, 1: 1781.6. Samples: 27658916. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-10-16 04:54:47,352][03835] Avg episode reward: [(0, '6.470'), (1, '7.250')] -[2023-10-16 04:54:50,619][05219] Updated weights for policy 1, policy_version 53930 (0.0009) -[2023-10-16 04:54:50,983][05219] Updated weights for policy 1, policy_version 53940 (0.0008) -[2023-10-16 04:54:51,172][05218] Updated weights for policy 0, policy_version 54122 (0.0007) -[2023-10-16 04:54:51,343][05219] Updated weights for policy 1, policy_version 53950 (0.0008) -[2023-10-16 04:54:51,547][05218] Updated weights for policy 0, policy_version 54132 (0.0008) -[2023-10-16 04:54:51,924][05218] Updated weights for policy 0, policy_version 54142 (0.0011) -[2023-10-16 04:54:52,350][03835] Fps is (10 sec: 19661.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 110690304. Throughput: 0: 1778.1, 1: 1765.8. Samples: 27678988. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-10-16 04:54:52,351][03835] Avg episode reward: [(0, '7.230'), (1, '7.460')] -[2023-10-16 04:54:55,175][05219] Updated weights for policy 1, policy_version 53960 (0.0010) -[2023-10-16 04:54:55,536][05219] Updated weights for policy 1, policy_version 53970 (0.0010) -[2023-10-16 04:54:55,677][05218] Updated weights for policy 0, policy_version 54152 (0.0008) -[2023-10-16 04:54:55,896][05219] Updated weights for policy 1, policy_version 53980 (0.0007) -[2023-10-16 04:54:56,051][05218] Updated weights for policy 0, policy_version 54162 (0.0008) -[2023-10-16 04:54:56,426][05218] Updated weights for policy 0, policy_version 54172 (0.0010) -[2023-10-16 04:54:57,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 110755840. Throughput: 0: 1801.7, 1: 1790.4. Samples: 27691270. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-10-16 04:54:57,351][03835] Avg episode reward: [(0, '7.000'), (1, '7.460')] -[2023-10-16 04:54:59,677][05219] Updated weights for policy 1, policy_version 53990 (0.0009) -[2023-10-16 04:55:00,039][05219] Updated weights for policy 1, policy_version 54000 (0.0007) -[2023-10-16 04:55:00,074][05218] Updated weights for policy 0, policy_version 54182 (0.0008) -[2023-10-16 04:55:00,400][05219] Updated weights for policy 1, policy_version 54010 (0.0008) -[2023-10-16 04:55:00,446][05218] Updated weights for policy 0, policy_version 54192 (0.0009) -[2023-10-16 04:55:00,821][05218] Updated weights for policy 0, policy_version 54202 (0.0008) -[2023-10-16 04:55:02,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 110821376. Throughput: 0: 1781.0, 1: 1763.7. Samples: 27711090. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-10-16 04:55:02,352][03835] Avg episode reward: [(0, '6.100'), (1, '7.610')] -[2023-10-16 04:55:04,166][05219] Updated weights for policy 1, policy_version 54020 (0.0007) -[2023-10-16 04:55:04,530][05219] Updated weights for policy 1, policy_version 54030 (0.0010) -[2023-10-16 04:55:04,603][05218] Updated weights for policy 0, policy_version 54212 (0.0010) -[2023-10-16 04:55:04,905][05219] Updated weights for policy 1, policy_version 54040 (0.0010) -[2023-10-16 04:55:04,978][05218] Updated weights for policy 0, policy_version 54222 (0.0008) -[2023-10-16 04:55:05,355][05218] Updated weights for policy 0, policy_version 54232 (0.0008) -[2023-10-16 04:55:07,351][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 110886912. Throughput: 0: 1783.3, 1: 1770.0. Samples: 27733652. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-10-16 04:55:07,352][03835] Avg episode reward: [(0, '6.520'), (1, '7.590')] -[2023-10-16 04:55:08,628][05219] Updated weights for policy 1, policy_version 54050 (0.0007) -[2023-10-16 04:55:08,996][05219] Updated weights for policy 1, policy_version 54060 (0.0010) -[2023-10-16 04:55:09,028][05218] Updated weights for policy 0, policy_version 54242 (0.0008) -[2023-10-16 04:55:09,368][05219] Updated weights for policy 1, policy_version 54070 (0.0008) -[2023-10-16 04:55:09,398][05218] Updated weights for policy 0, policy_version 54252 (0.0009) -[2023-10-16 04:55:09,737][05219] Updated weights for policy 1, policy_version 54080 (0.0007) -[2023-10-16 04:55:09,770][05218] Updated weights for policy 0, policy_version 54262 (0.0008) -[2023-10-16 04:55:10,154][05218] Updated weights for policy 0, policy_version 54272 (0.0008) -[2023-10-16 04:55:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 110952448. Throughput: 0: 1779.1, 1: 1773.1. Samples: 27743460. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-10-16 04:55:12,351][03835] Avg episode reward: [(0, '6.360'), (1, '6.930')] -[2023-10-16 04:55:13,500][05219] Updated weights for policy 1, policy_version 54090 (0.0008) -[2023-10-16 04:55:13,857][05219] Updated weights for policy 1, policy_version 54100 (0.0009) -[2023-10-16 04:55:13,896][05218] Updated weights for policy 0, policy_version 54282 (0.0008) -[2023-10-16 04:55:14,226][05219] Updated weights for policy 1, policy_version 54110 (0.0008) -[2023-10-16 04:55:14,270][05218] Updated weights for policy 0, policy_version 54292 (0.0009) -[2023-10-16 04:55:14,641][05218] Updated weights for policy 0, policy_version 54302 (0.0010) -[2023-10-16 04:55:17,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 111017984. Throughput: 0: 1772.6, 1: 1776.6. Samples: 27765446. Policy #0 lag: (min: 19.0, avg: 19.9, max: 40.0) -[2023-10-16 04:55:17,351][03835] Avg episode reward: [(0, '7.080'), (1, '6.960')] -[2023-10-16 04:55:18,056][05219] Updated weights for policy 1, policy_version 54120 (0.0010) -[2023-10-16 04:55:18,404][05218] Updated weights for policy 0, policy_version 54312 (0.0008) -[2023-10-16 04:55:18,424][05219] Updated weights for policy 1, policy_version 54130 (0.0008) -[2023-10-16 04:55:18,768][05218] Updated weights for policy 0, policy_version 54322 (0.0007) -[2023-10-16 04:55:18,793][05219] Updated weights for policy 1, policy_version 54140 (0.0010) -[2023-10-16 04:55:19,148][05218] Updated weights for policy 0, policy_version 54332 (0.0009) -[2023-10-16 04:55:22,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 111083520. Throughput: 0: 1787.2, 1: 1793.6. Samples: 27787908. Policy #0 lag: (min: 19.0, avg: 19.9, max: 40.0) -[2023-10-16 04:55:22,351][03835] Avg episode reward: [(0, '7.290'), (1, '7.040')] -[2023-10-16 04:55:22,545][05219] Updated weights for policy 1, policy_version 54150 (0.0007) -[2023-10-16 04:55:22,916][05219] Updated weights for policy 1, policy_version 54160 (0.0008) -[2023-10-16 04:55:22,979][05218] Updated weights for policy 0, policy_version 54342 (0.0009) -[2023-10-16 04:55:23,273][05219] Updated weights for policy 1, policy_version 54170 (0.0008) -[2023-10-16 04:55:23,353][05218] Updated weights for policy 0, policy_version 54352 (0.0008) -[2023-10-16 04:55:23,729][05218] Updated weights for policy 0, policy_version 54362 (0.0008) -[2023-10-16 04:55:27,223][05219] Updated weights for policy 1, policy_version 54180 (0.0007) -[2023-10-16 04:55:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 111149056. Throughput: 0: 1770.2, 1: 1775.2. Samples: 27797358. Policy #0 lag: (min: 19.0, avg: 19.9, max: 40.0) -[2023-10-16 04:55:27,351][03835] Avg episode reward: [(0, '6.860'), (1, '6.720')] -[2023-10-16 04:55:27,608][05219] Updated weights for policy 1, policy_version 54190 (0.0008) -[2023-10-16 04:55:27,661][05218] Updated weights for policy 0, policy_version 54372 (0.0009) -[2023-10-16 04:55:27,977][05219] Updated weights for policy 1, policy_version 54200 (0.0011) -[2023-10-16 04:55:28,037][05218] Updated weights for policy 0, policy_version 54382 (0.0009) -[2023-10-16 04:55:28,408][05218] Updated weights for policy 0, policy_version 54392 (0.0008) -[2023-10-16 04:55:31,739][05219] Updated weights for policy 1, policy_version 54210 (0.0007) -[2023-10-16 04:55:32,091][05219] Updated weights for policy 1, policy_version 54220 (0.0009) -[2023-10-16 04:55:32,290][05218] Updated weights for policy 0, policy_version 54402 (0.0007) -[2023-10-16 04:55:32,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 111214592. Throughput: 0: 1773.6, 1: 1788.9. Samples: 27819228. Policy #0 lag: (min: 19.0, avg: 19.9, max: 40.0) -[2023-10-16 04:55:32,351][03835] Avg episode reward: [(0, '6.950'), (1, '7.550')] -[2023-10-16 04:55:32,462][05219] Updated weights for policy 1, policy_version 54230 (0.0008) -[2023-10-16 04:55:32,671][05218] Updated weights for policy 0, policy_version 54412 (0.0007) -[2023-10-16 04:55:32,818][05219] Updated weights for policy 1, policy_version 54240 (0.0008) -[2023-10-16 04:55:33,042][05218] Updated weights for policy 0, policy_version 54422 (0.0007) -[2023-10-16 04:55:33,414][05218] Updated weights for policy 0, policy_version 54432 (0.0010) -[2023-10-16 04:55:36,767][05219] Updated weights for policy 1, policy_version 54250 (0.0007) -[2023-10-16 04:55:37,129][05219] Updated weights for policy 1, policy_version 54260 (0.0008) -[2023-10-16 04:55:37,152][05218] Updated weights for policy 0, policy_version 54442 (0.0008) -[2023-10-16 04:55:37,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 111280128. Throughput: 0: 1790.9, 1: 1788.0. Samples: 27840038. Policy #0 lag: (min: 19.0, avg: 19.9, max: 40.0) -[2023-10-16 04:55:37,351][03835] Avg episode reward: [(0, '7.360'), (1, '7.210')] -[2023-10-16 04:55:37,487][05219] Updated weights for policy 1, policy_version 54270 (0.0007) -[2023-10-16 04:55:37,530][05218] Updated weights for policy 0, policy_version 54452 (0.0008) -[2023-10-16 04:55:37,559][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000054272_55574528.pth... -[2023-10-16 04:55:37,589][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000052608_53870592.pth -[2023-10-16 04:55:37,897][05218] Updated weights for policy 0, policy_version 54462 (0.0010) -[2023-10-16 04:55:37,973][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000054464_55771136.pth... -[2023-10-16 04:55:38,002][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000052768_54034432.pth -[2023-10-16 04:55:41,278][05219] Updated weights for policy 1, policy_version 54280 (0.0008) -[2023-10-16 04:55:41,640][05219] Updated weights for policy 1, policy_version 54290 (0.0008) -[2023-10-16 04:55:41,678][05218] Updated weights for policy 0, policy_version 54472 (0.0009) -[2023-10-16 04:55:42,008][05219] Updated weights for policy 1, policy_version 54300 (0.0009) -[2023-10-16 04:55:42,064][05218] Updated weights for policy 0, policy_version 54482 (0.0010) -[2023-10-16 04:55:42,350][03835] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 111378432. Throughput: 0: 1769.6, 1: 1782.3. Samples: 27851106. Policy #0 lag: (min: 19.0, avg: 19.9, max: 40.0) -[2023-10-16 04:55:42,351][03835] Avg episode reward: [(0, '6.600'), (1, '6.600')] -[2023-10-16 04:55:42,434][05218] Updated weights for policy 0, policy_version 54492 (0.0009) -[2023-10-16 04:55:45,669][05219] Updated weights for policy 1, policy_version 54310 (0.0008) -[2023-10-16 04:55:46,029][05219] Updated weights for policy 1, policy_version 54320 (0.0008) -[2023-10-16 04:55:46,294][05218] Updated weights for policy 0, policy_version 54502 (0.0009) -[2023-10-16 04:55:46,393][05219] Updated weights for policy 1, policy_version 54330 (0.0008) -[2023-10-16 04:55:46,655][05218] Updated weights for policy 0, policy_version 54512 (0.0009) -[2023-10-16 04:55:47,027][05218] Updated weights for policy 0, policy_version 54522 (0.0010) -[2023-10-16 04:55:47,350][03835] Fps is (10 sec: 19661.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 111476736. Throughput: 0: 1788.0, 1: 1793.3. Samples: 27872246. Policy #0 lag: (min: 19.0, avg: 19.9, max: 40.0) -[2023-10-16 04:55:47,351][03835] Avg episode reward: [(0, '6.910'), (1, '6.820')] -[2023-10-16 04:55:50,062][05219] Updated weights for policy 1, policy_version 54340 (0.0008) -[2023-10-16 04:55:50,421][05219] Updated weights for policy 1, policy_version 54350 (0.0009) -[2023-10-16 04:55:50,784][05219] Updated weights for policy 1, policy_version 54360 (0.0011) -[2023-10-16 04:55:50,807][05218] Updated weights for policy 0, policy_version 54532 (0.0010) -[2023-10-16 04:55:51,190][05218] Updated weights for policy 0, policy_version 54542 (0.0009) -[2023-10-16 04:55:51,567][05218] Updated weights for policy 0, policy_version 54552 (0.0011) -[2023-10-16 04:55:52,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 111542272. Throughput: 0: 1759.3, 1: 1778.5. Samples: 27892852. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-16 04:55:52,351][03835] Avg episode reward: [(0, '8.170'), (1, '6.810')] -[2023-10-16 04:55:52,362][04766] Saving new best policy, reward=8.170! -[2023-10-16 04:55:54,590][05219] Updated weights for policy 1, policy_version 54370 (0.0009) -[2023-10-16 04:55:54,944][05219] Updated weights for policy 1, policy_version 54380 (0.0010) -[2023-10-16 04:55:55,309][05219] Updated weights for policy 1, policy_version 54390 (0.0008) -[2023-10-16 04:55:55,342][05218] Updated weights for policy 0, policy_version 54562 (0.0008) -[2023-10-16 04:55:55,679][05219] Updated weights for policy 1, policy_version 54400 (0.0008) -[2023-10-16 04:55:55,716][05218] Updated weights for policy 0, policy_version 54572 (0.0007) -[2023-10-16 04:55:56,090][05218] Updated weights for policy 0, policy_version 54582 (0.0009) -[2023-10-16 04:55:56,473][05218] Updated weights for policy 0, policy_version 54592 (0.0011) -[2023-10-16 04:55:57,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 111607808. Throughput: 0: 1791.6, 1: 1794.1. Samples: 27904816. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-16 04:55:57,351][03835] Avg episode reward: [(0, '7.320'), (1, '7.020')] -[2023-10-16 04:55:59,424][05219] Updated weights for policy 1, policy_version 54410 (0.0007) -[2023-10-16 04:55:59,791][05219] Updated weights for policy 1, policy_version 54420 (0.0007) -[2023-10-16 04:56:00,143][05219] Updated weights for policy 1, policy_version 54430 (0.0007) -[2023-10-16 04:56:00,223][05218] Updated weights for policy 0, policy_version 54602 (0.0007) -[2023-10-16 04:56:00,605][05218] Updated weights for policy 0, policy_version 54612 (0.0008) -[2023-10-16 04:56:00,969][05218] Updated weights for policy 0, policy_version 54622 (0.0008) -[2023-10-16 04:56:02,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 111673344. Throughput: 0: 1764.3, 1: 1783.1. Samples: 27925080. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-16 04:56:02,351][03835] Avg episode reward: [(0, '6.420'), (1, '7.260')] -[2023-10-16 04:56:03,953][05219] Updated weights for policy 1, policy_version 54440 (0.0009) -[2023-10-16 04:56:04,318][05219] Updated weights for policy 1, policy_version 54450 (0.0008) -[2023-10-16 04:56:04,672][05218] Updated weights for policy 0, policy_version 54632 (0.0007) -[2023-10-16 04:56:04,681][05219] Updated weights for policy 1, policy_version 54460 (0.0007) -[2023-10-16 04:56:05,053][05218] Updated weights for policy 0, policy_version 54642 (0.0010) -[2023-10-16 04:56:05,428][05218] Updated weights for policy 0, policy_version 54652 (0.0009) -[2023-10-16 04:56:07,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 111738880. Throughput: 0: 1768.3, 1: 1778.9. Samples: 27947532. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-16 04:56:07,351][03835] Avg episode reward: [(0, '6.440'), (1, '7.340')] -[2023-10-16 04:56:08,479][05219] Updated weights for policy 1, policy_version 54470 (0.0009) -[2023-10-16 04:56:08,844][05219] Updated weights for policy 1, policy_version 54480 (0.0008) -[2023-10-16 04:56:09,196][05218] Updated weights for policy 0, policy_version 54662 (0.0008) -[2023-10-16 04:56:09,208][05219] Updated weights for policy 1, policy_version 54490 (0.0008) -[2023-10-16 04:56:09,580][05218] Updated weights for policy 0, policy_version 54672 (0.0008) -[2023-10-16 04:56:09,960][05218] Updated weights for policy 0, policy_version 54682 (0.0009) -[2023-10-16 04:56:12,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 111804416. Throughput: 0: 1772.5, 1: 1779.9. Samples: 27957214. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-16 04:56:12,351][03835] Avg episode reward: [(0, '6.440'), (1, '7.580')] -[2023-10-16 04:56:12,989][05219] Updated weights for policy 1, policy_version 54500 (0.0007) -[2023-10-16 04:56:13,350][05219] Updated weights for policy 1, policy_version 54510 (0.0008) -[2023-10-16 04:56:13,592][05218] Updated weights for policy 0, policy_version 54692 (0.0009) -[2023-10-16 04:56:13,708][05219] Updated weights for policy 1, policy_version 54520 (0.0007) -[2023-10-16 04:56:13,965][05218] Updated weights for policy 0, policy_version 54702 (0.0010) -[2023-10-16 04:56:14,339][05218] Updated weights for policy 0, policy_version 54712 (0.0009) -[2023-10-16 04:56:17,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 111869952. Throughput: 0: 1778.2, 1: 1782.9. Samples: 27979476. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-16 04:56:17,351][03835] Avg episode reward: [(0, '6.040'), (1, '6.870')] -[2023-10-16 04:56:17,510][05219] Updated weights for policy 1, policy_version 54530 (0.0008) -[2023-10-16 04:56:17,921][05219] Updated weights for policy 1, policy_version 54540 (0.0010) -[2023-10-16 04:56:18,126][05218] Updated weights for policy 0, policy_version 54722 (0.0009) -[2023-10-16 04:56:18,287][05219] Updated weights for policy 1, policy_version 54550 (0.0008) -[2023-10-16 04:56:18,504][05218] Updated weights for policy 0, policy_version 54732 (0.0008) -[2023-10-16 04:56:18,651][05219] Updated weights for policy 1, policy_version 54560 (0.0007) -[2023-10-16 04:56:18,877][05218] Updated weights for policy 0, policy_version 54742 (0.0009) -[2023-10-16 04:56:19,248][05218] Updated weights for policy 0, policy_version 54752 (0.0009) -[2023-10-16 04:56:22,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 111935488. Throughput: 0: 1789.5, 1: 1797.1. Samples: 28001434. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-16 04:56:22,352][03835] Avg episode reward: [(0, '6.060'), (1, '6.320')] -[2023-10-16 04:56:22,419][05219] Updated weights for policy 1, policy_version 54570 (0.0008) -[2023-10-16 04:56:22,780][05219] Updated weights for policy 1, policy_version 54580 (0.0007) -[2023-10-16 04:56:23,065][05218] Updated weights for policy 0, policy_version 54762 (0.0009) -[2023-10-16 04:56:23,146][05219] Updated weights for policy 1, policy_version 54590 (0.0007) -[2023-10-16 04:56:23,437][05218] Updated weights for policy 0, policy_version 54772 (0.0008) -[2023-10-16 04:56:23,823][05218] Updated weights for policy 0, policy_version 54782 (0.0009) -[2023-10-16 04:56:26,988][05219] Updated weights for policy 1, policy_version 54600 (0.0010) -[2023-10-16 04:56:27,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 112001024. Throughput: 0: 1776.7, 1: 1779.2. Samples: 28011120. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-16 04:56:27,351][03835] Avg episode reward: [(0, '5.360'), (1, '7.170')] -[2023-10-16 04:56:27,358][05219] Updated weights for policy 1, policy_version 54610 (0.0007) -[2023-10-16 04:56:27,546][05218] Updated weights for policy 0, policy_version 54792 (0.0008) -[2023-10-16 04:56:27,710][05219] Updated weights for policy 1, policy_version 54620 (0.0008) -[2023-10-16 04:56:27,926][05218] Updated weights for policy 0, policy_version 54802 (0.0009) -[2023-10-16 04:56:28,295][05218] Updated weights for policy 0, policy_version 54812 (0.0009) -[2023-10-16 04:56:31,476][05219] Updated weights for policy 1, policy_version 54630 (0.0009) -[2023-10-16 04:56:31,846][05219] Updated weights for policy 1, policy_version 54640 (0.0008) -[2023-10-16 04:56:32,105][05218] Updated weights for policy 0, policy_version 54822 (0.0008) -[2023-10-16 04:56:32,213][05219] Updated weights for policy 1, policy_version 54650 (0.0007) -[2023-10-16 04:56:32,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 112066560. Throughput: 0: 1788.0, 1: 1796.6. Samples: 28033554. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-16 04:56:32,351][03835] Avg episode reward: [(0, '6.200'), (1, '7.010')] -[2023-10-16 04:56:32,465][05218] Updated weights for policy 0, policy_version 54832 (0.0008) -[2023-10-16 04:56:32,842][05218] Updated weights for policy 0, policy_version 54842 (0.0009) -[2023-10-16 04:56:36,012][05219] Updated weights for policy 1, policy_version 54660 (0.0007) -[2023-10-16 04:56:36,374][05219] Updated weights for policy 1, policy_version 54670 (0.0008) -[2023-10-16 04:56:36,642][05218] Updated weights for policy 0, policy_version 54852 (0.0009) -[2023-10-16 04:56:36,740][05219] Updated weights for policy 1, policy_version 54680 (0.0007) -[2023-10-16 04:56:37,015][05218] Updated weights for policy 0, policy_version 54862 (0.0008) -[2023-10-16 04:56:37,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 112164864. Throughput: 0: 1788.9, 1: 1778.5. Samples: 28053384. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-16 04:56:37,351][03835] Avg episode reward: [(0, '6.170'), (1, '7.300')] -[2023-10-16 04:56:37,398][05218] Updated weights for policy 0, policy_version 54872 (0.0008) -[2023-10-16 04:56:40,560][05219] Updated weights for policy 1, policy_version 54690 (0.0009) -[2023-10-16 04:56:40,925][05219] Updated weights for policy 1, policy_version 54700 (0.0007) -[2023-10-16 04:56:41,102][05218] Updated weights for policy 0, policy_version 54882 (0.0007) -[2023-10-16 04:56:41,282][05219] Updated weights for policy 1, policy_version 54710 (0.0009) -[2023-10-16 04:56:41,477][05218] Updated weights for policy 0, policy_version 54892 (0.0007) -[2023-10-16 04:56:41,655][05219] Updated weights for policy 1, policy_version 54720 (0.0008) -[2023-10-16 04:56:41,851][05218] Updated weights for policy 0, policy_version 54902 (0.0010) -[2023-10-16 04:56:42,230][05218] Updated weights for policy 0, policy_version 54912 (0.0010) -[2023-10-16 04:56:42,350][03835] Fps is (10 sec: 19661.1, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 112263168. Throughput: 0: 1779.1, 1: 1798.1. Samples: 28065786. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-16 04:56:42,351][03835] Avg episode reward: [(0, '6.350'), (1, '7.020')] -[2023-10-16 04:56:45,393][05219] Updated weights for policy 1, policy_version 54730 (0.0010) -[2023-10-16 04:56:45,752][05219] Updated weights for policy 1, policy_version 54740 (0.0009) -[2023-10-16 04:56:46,071][05218] Updated weights for policy 0, policy_version 54922 (0.0008) -[2023-10-16 04:56:46,123][05219] Updated weights for policy 1, policy_version 54750 (0.0007) -[2023-10-16 04:56:46,453][05218] Updated weights for policy 0, policy_version 54932 (0.0011) -[2023-10-16 04:56:46,825][05218] Updated weights for policy 0, policy_version 54942 (0.0009) -[2023-10-16 04:56:47,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 112328704. Throughput: 0: 1794.1, 1: 1784.0. Samples: 28086092. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-16 04:56:47,351][03835] Avg episode reward: [(0, '7.540'), (1, '7.590')] -[2023-10-16 04:56:50,008][05219] Updated weights for policy 1, policy_version 54760 (0.0007) -[2023-10-16 04:56:50,365][05219] Updated weights for policy 1, policy_version 54770 (0.0009) -[2023-10-16 04:56:50,476][05218] Updated weights for policy 0, policy_version 54952 (0.0007) -[2023-10-16 04:56:50,724][05219] Updated weights for policy 1, policy_version 54780 (0.0009) -[2023-10-16 04:56:50,847][05218] Updated weights for policy 0, policy_version 54962 (0.0007) -[2023-10-16 04:56:51,227][05218] Updated weights for policy 0, policy_version 54972 (0.0007) -[2023-10-16 04:56:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 112394240. Throughput: 0: 1773.8, 1: 1788.8. Samples: 28107850. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-16 04:56:52,351][03835] Avg episode reward: [(0, '7.390'), (1, '7.280')] -[2023-10-16 04:56:54,299][05219] Updated weights for policy 1, policy_version 54790 (0.0009) -[2023-10-16 04:56:54,663][05219] Updated weights for policy 1, policy_version 54800 (0.0010) -[2023-10-16 04:56:55,033][05219] Updated weights for policy 1, policy_version 54810 (0.0007) -[2023-10-16 04:56:55,160][05218] Updated weights for policy 0, policy_version 54982 (0.0008) -[2023-10-16 04:56:55,540][05218] Updated weights for policy 0, policy_version 54992 (0.0008) -[2023-10-16 04:56:55,917][05218] Updated weights for policy 0, policy_version 55002 (0.0008) -[2023-10-16 04:56:57,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 112459776. Throughput: 0: 1795.2, 1: 1792.3. Samples: 28118648. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-16 04:56:57,351][03835] Avg episode reward: [(0, '6.630'), (1, '6.850')] -[2023-10-16 04:56:58,680][05219] Updated weights for policy 1, policy_version 54820 (0.0007) -[2023-10-16 04:56:59,043][05219] Updated weights for policy 1, policy_version 54830 (0.0008) -[2023-10-16 04:56:59,411][05219] Updated weights for policy 1, policy_version 54840 (0.0007) -[2023-10-16 04:56:59,482][05218] Updated weights for policy 0, policy_version 55012 (0.0007) -[2023-10-16 04:56:59,865][05218] Updated weights for policy 0, policy_version 55022 (0.0007) -[2023-10-16 04:57:00,229][05218] Updated weights for policy 0, policy_version 55032 (0.0010) -[2023-10-16 04:57:02,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 112525312. Throughput: 0: 1779.1, 1: 1786.9. Samples: 28139946. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-16 04:57:02,352][03835] Avg episode reward: [(0, '6.160'), (1, '7.240')] -[2023-10-16 04:57:03,225][05219] Updated weights for policy 1, policy_version 54850 (0.0008) -[2023-10-16 04:57:03,637][05219] Updated weights for policy 1, policy_version 54860 (0.0010) -[2023-10-16 04:57:03,936][05218] Updated weights for policy 0, policy_version 55042 (0.0009) -[2023-10-16 04:57:04,007][05219] Updated weights for policy 1, policy_version 54870 (0.0009) -[2023-10-16 04:57:04,308][05218] Updated weights for policy 0, policy_version 55052 (0.0008) -[2023-10-16 04:57:04,369][05219] Updated weights for policy 1, policy_version 54880 (0.0008) -[2023-10-16 04:57:04,689][05218] Updated weights for policy 0, policy_version 55062 (0.0008) -[2023-10-16 04:57:05,056][05218] Updated weights for policy 0, policy_version 55072 (0.0008) -[2023-10-16 04:57:07,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 112590848. Throughput: 0: 1784.1, 1: 1795.5. Samples: 28162512. Policy #0 lag: (min: 23.0, avg: 26.0, max: 55.0) -[2023-10-16 04:57:07,351][03835] Avg episode reward: [(0, '4.920'), (1, '6.870')] -[2023-10-16 04:57:08,076][05219] Updated weights for policy 1, policy_version 54890 (0.0010) -[2023-10-16 04:57:08,435][05219] Updated weights for policy 1, policy_version 54900 (0.0008) -[2023-10-16 04:57:08,687][05218] Updated weights for policy 0, policy_version 55082 (0.0008) -[2023-10-16 04:57:08,804][05219] Updated weights for policy 1, policy_version 54910 (0.0009) -[2023-10-16 04:57:09,067][05218] Updated weights for policy 0, policy_version 55092 (0.0008) -[2023-10-16 04:57:09,435][05218] Updated weights for policy 0, policy_version 55102 (0.0009) -[2023-10-16 04:57:12,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 112656384. Throughput: 0: 1787.2, 1: 1793.5. Samples: 28172248. Policy #0 lag: (min: 23.0, avg: 26.0, max: 55.0) -[2023-10-16 04:57:12,351][03835] Avg episode reward: [(0, '4.810'), (1, '6.350')] -[2023-10-16 04:57:12,508][05219] Updated weights for policy 1, policy_version 54920 (0.0007) -[2023-10-16 04:57:12,871][05219] Updated weights for policy 1, policy_version 54930 (0.0007) -[2023-10-16 04:57:13,237][05219] Updated weights for policy 1, policy_version 54940 (0.0007) -[2023-10-16 04:57:13,242][05218] Updated weights for policy 0, policy_version 55112 (0.0009) -[2023-10-16 04:57:13,622][05218] Updated weights for policy 0, policy_version 55122 (0.0008) -[2023-10-16 04:57:13,994][05218] Updated weights for policy 0, policy_version 55132 (0.0009) -[2023-10-16 04:57:16,921][05219] Updated weights for policy 1, policy_version 54950 (0.0008) -[2023-10-16 04:57:17,289][05219] Updated weights for policy 1, policy_version 54960 (0.0010) -[2023-10-16 04:57:17,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 112721920. Throughput: 0: 1787.9, 1: 1793.7. Samples: 28194726. Policy #0 lag: (min: 23.0, avg: 26.0, max: 55.0) -[2023-10-16 04:57:17,351][03835] Avg episode reward: [(0, '5.560'), (1, '7.020')] -[2023-10-16 04:57:17,648][05219] Updated weights for policy 1, policy_version 54970 (0.0010) -[2023-10-16 04:57:17,797][05218] Updated weights for policy 0, policy_version 55142 (0.0008) -[2023-10-16 04:57:18,173][05218] Updated weights for policy 0, policy_version 55152 (0.0007) -[2023-10-16 04:57:18,546][05218] Updated weights for policy 0, policy_version 55162 (0.0007) -[2023-10-16 04:57:21,430][05219] Updated weights for policy 1, policy_version 54980 (0.0008) -[2023-10-16 04:57:21,792][05219] Updated weights for policy 1, policy_version 54990 (0.0009) -[2023-10-16 04:57:22,153][05219] Updated weights for policy 1, policy_version 55000 (0.0007) -[2023-10-16 04:57:22,332][05218] Updated weights for policy 0, policy_version 55172 (0.0008) -[2023-10-16 04:57:22,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.6, 300 sec: 14218.0). Total num frames: 112787456. Throughput: 0: 1809.3, 1: 1800.4. Samples: 28215818. Policy #0 lag: (min: 23.0, avg: 26.0, max: 55.0) -[2023-10-16 04:57:22,351][03835] Avg episode reward: [(0, '5.190'), (1, '7.290')] -[2023-10-16 04:57:22,711][05218] Updated weights for policy 0, policy_version 55182 (0.0009) -[2023-10-16 04:57:23,074][05218] Updated weights for policy 0, policy_version 55192 (0.0011) -[2023-10-16 04:57:26,154][05219] Updated weights for policy 1, policy_version 55010 (0.0008) -[2023-10-16 04:57:26,523][05219] Updated weights for policy 1, policy_version 55020 (0.0008) -[2023-10-16 04:57:26,859][05218] Updated weights for policy 0, policy_version 55202 (0.0010) -[2023-10-16 04:57:26,884][05219] Updated weights for policy 1, policy_version 55030 (0.0008) -[2023-10-16 04:57:27,229][05218] Updated weights for policy 0, policy_version 55212 (0.0009) -[2023-10-16 04:57:27,253][05219] Updated weights for policy 1, policy_version 55040 (0.0008) -[2023-10-16 04:57:27,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 112885760. Throughput: 0: 1788.1, 1: 1789.7. Samples: 28226788. Policy #0 lag: (min: 23.0, avg: 26.0, max: 55.0) -[2023-10-16 04:57:27,351][03835] Avg episode reward: [(0, '4.770'), (1, '7.000')] -[2023-10-16 04:57:27,595][05218] Updated weights for policy 0, policy_version 55222 (0.0008) -[2023-10-16 04:57:27,973][05218] Updated weights for policy 0, policy_version 55232 (0.0009) -[2023-10-16 04:57:31,012][05219] Updated weights for policy 1, policy_version 55050 (0.0008) -[2023-10-16 04:57:31,379][05219] Updated weights for policy 1, policy_version 55060 (0.0008) -[2023-10-16 04:57:31,635][05218] Updated weights for policy 0, policy_version 55242 (0.0009) -[2023-10-16 04:57:31,746][05219] Updated weights for policy 1, policy_version 55070 (0.0007) -[2023-10-16 04:57:32,008][05218] Updated weights for policy 0, policy_version 55252 (0.0009) -[2023-10-16 04:57:32,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 112951296. Throughput: 0: 1805.0, 1: 1804.5. Samples: 28248522. Policy #0 lag: (min: 23.0, avg: 26.0, max: 55.0) -[2023-10-16 04:57:32,351][03835] Avg episode reward: [(0, '4.680'), (1, '7.130')] -[2023-10-16 04:57:32,388][05218] Updated weights for policy 0, policy_version 55262 (0.0008) -[2023-10-16 04:57:35,481][05219] Updated weights for policy 1, policy_version 55080 (0.0009) -[2023-10-16 04:57:35,843][05219] Updated weights for policy 1, policy_version 55090 (0.0009) -[2023-10-16 04:57:36,184][05218] Updated weights for policy 0, policy_version 55272 (0.0008) -[2023-10-16 04:57:36,205][05219] Updated weights for policy 1, policy_version 55100 (0.0007) -[2023-10-16 04:57:36,561][05218] Updated weights for policy 0, policy_version 55282 (0.0009) -[2023-10-16 04:57:36,935][05218] Updated weights for policy 0, policy_version 55292 (0.0008) -[2023-10-16 04:57:37,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 113049600. Throughput: 0: 1792.6, 1: 1784.0. Samples: 28268796. Policy #0 lag: (min: 23.0, avg: 26.0, max: 55.0) -[2023-10-16 04:57:37,351][03835] Avg episode reward: [(0, '5.320'), (1, '7.480')] -[2023-10-16 04:57:37,363][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000055296_56623104.pth... -[2023-10-16 04:57:37,363][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000055104_56426496.pth... -[2023-10-16 04:57:37,392][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000053632_54919168.pth -[2023-10-16 04:57:37,398][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000053440_54722560.pth -[2023-10-16 04:57:40,021][05219] Updated weights for policy 1, policy_version 55110 (0.0007) -[2023-10-16 04:57:40,379][05219] Updated weights for policy 1, policy_version 55120 (0.0007) -[2023-10-16 04:57:40,637][05218] Updated weights for policy 0, policy_version 55302 (0.0007) -[2023-10-16 04:57:40,750][05219] Updated weights for policy 1, policy_version 55130 (0.0008) -[2023-10-16 04:57:41,009][05218] Updated weights for policy 0, policy_version 55312 (0.0009) -[2023-10-16 04:57:41,390][05218] Updated weights for policy 0, policy_version 55322 (0.0009) -[2023-10-16 04:57:42,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 113115136. Throughput: 0: 1806.7, 1: 1803.1. Samples: 28281086. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:57:42,351][03835] Avg episode reward: [(0, '5.800'), (1, '6.510')] -[2023-10-16 04:57:44,467][05219] Updated weights for policy 1, policy_version 55140 (0.0008) -[2023-10-16 04:57:44,838][05219] Updated weights for policy 1, policy_version 55150 (0.0007) -[2023-10-16 04:57:45,177][05218] Updated weights for policy 0, policy_version 55332 (0.0008) -[2023-10-16 04:57:45,199][05219] Updated weights for policy 1, policy_version 55160 (0.0008) -[2023-10-16 04:57:45,548][05218] Updated weights for policy 0, policy_version 55342 (0.0009) -[2023-10-16 04:57:45,913][05218] Updated weights for policy 0, policy_version 55352 (0.0007) -[2023-10-16 04:57:47,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 113180672. Throughput: 0: 1788.5, 1: 1783.9. Samples: 28300704. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:57:47,351][03835] Avg episode reward: [(0, '6.350'), (1, '6.800')] -[2023-10-16 04:57:49,075][05219] Updated weights for policy 1, policy_version 55170 (0.0008) -[2023-10-16 04:57:49,494][05219] Updated weights for policy 1, policy_version 55180 (0.0009) -[2023-10-16 04:57:49,707][05218] Updated weights for policy 0, policy_version 55362 (0.0007) -[2023-10-16 04:57:49,853][05219] Updated weights for policy 1, policy_version 55190 (0.0008) -[2023-10-16 04:57:50,080][05218] Updated weights for policy 0, policy_version 55372 (0.0007) -[2023-10-16 04:57:50,215][05219] Updated weights for policy 1, policy_version 55200 (0.0008) -[2023-10-16 04:57:50,444][05218] Updated weights for policy 0, policy_version 55382 (0.0008) -[2023-10-16 04:57:50,819][05218] Updated weights for policy 0, policy_version 55392 (0.0009) -[2023-10-16 04:57:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 113246208. Throughput: 0: 1785.0, 1: 1775.6. Samples: 28322738. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:57:52,351][03835] Avg episode reward: [(0, '6.530'), (1, '7.110')] -[2023-10-16 04:57:54,012][05219] Updated weights for policy 1, policy_version 55210 (0.0010) -[2023-10-16 04:57:54,381][05219] Updated weights for policy 1, policy_version 55220 (0.0008) -[2023-10-16 04:57:54,488][05218] Updated weights for policy 0, policy_version 55402 (0.0008) -[2023-10-16 04:57:54,752][05219] Updated weights for policy 1, policy_version 55230 (0.0008) -[2023-10-16 04:57:54,869][05218] Updated weights for policy 0, policy_version 55412 (0.0007) -[2023-10-16 04:57:55,247][05218] Updated weights for policy 0, policy_version 55422 (0.0008) -[2023-10-16 04:57:57,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 113311744. Throughput: 0: 1783.2, 1: 1774.7. Samples: 28332354. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:57:57,351][03835] Avg episode reward: [(0, '5.950'), (1, '6.470')] -[2023-10-16 04:57:58,569][05219] Updated weights for policy 1, policy_version 55240 (0.0008) -[2023-10-16 04:57:58,863][05218] Updated weights for policy 0, policy_version 55432 (0.0009) -[2023-10-16 04:57:58,936][05219] Updated weights for policy 1, policy_version 55250 (0.0009) -[2023-10-16 04:57:59,233][05218] Updated weights for policy 0, policy_version 55442 (0.0008) -[2023-10-16 04:57:59,305][05219] Updated weights for policy 1, policy_version 55260 (0.0008) -[2023-10-16 04:57:59,606][05218] Updated weights for policy 0, policy_version 55452 (0.0009) -[2023-10-16 04:58:02,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 113377280. Throughput: 0: 1785.6, 1: 1775.6. Samples: 28354978. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:58:02,351][03835] Avg episode reward: [(0, '5.620'), (1, '7.350')] -[2023-10-16 04:58:03,120][05219] Updated weights for policy 1, policy_version 55270 (0.0008) -[2023-10-16 04:58:03,338][05218] Updated weights for policy 0, policy_version 55462 (0.0008) -[2023-10-16 04:58:03,483][05219] Updated weights for policy 1, policy_version 55280 (0.0008) -[2023-10-16 04:58:03,704][05218] Updated weights for policy 0, policy_version 55472 (0.0009) -[2023-10-16 04:58:03,852][05219] Updated weights for policy 1, policy_version 55290 (0.0007) -[2023-10-16 04:58:04,086][05218] Updated weights for policy 0, policy_version 55482 (0.0008) -[2023-10-16 04:58:07,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 113442816. Throughput: 0: 1793.4, 1: 1804.5. Samples: 28377724. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:58:07,351][03835] Avg episode reward: [(0, '5.950'), (1, '7.090')] -[2023-10-16 04:58:07,556][05219] Updated weights for policy 1, policy_version 55300 (0.0007) -[2023-10-16 04:58:07,775][05218] Updated weights for policy 0, policy_version 55492 (0.0007) -[2023-10-16 04:58:07,915][05219] Updated weights for policy 1, policy_version 55310 (0.0007) -[2023-10-16 04:58:08,150][05218] Updated weights for policy 0, policy_version 55502 (0.0008) -[2023-10-16 04:58:08,273][05219] Updated weights for policy 1, policy_version 55320 (0.0009) -[2023-10-16 04:58:08,533][05218] Updated weights for policy 0, policy_version 55512 (0.0008) -[2023-10-16 04:58:11,948][05219] Updated weights for policy 1, policy_version 55330 (0.0009) -[2023-10-16 04:58:12,311][05219] Updated weights for policy 1, policy_version 55340 (0.0007) -[2023-10-16 04:58:12,349][05218] Updated weights for policy 0, policy_version 55522 (0.0008) -[2023-10-16 04:58:12,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 113508352. Throughput: 0: 1790.0, 1: 1780.8. Samples: 28387476. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:58:12,351][03835] Avg episode reward: [(0, '5.680'), (1, '6.990')] -[2023-10-16 04:58:12,673][05219] Updated weights for policy 1, policy_version 55350 (0.0007) -[2023-10-16 04:58:12,730][05218] Updated weights for policy 0, policy_version 55532 (0.0008) -[2023-10-16 04:58:13,036][05219] Updated weights for policy 1, policy_version 55360 (0.0008) -[2023-10-16 04:58:13,111][05218] Updated weights for policy 0, policy_version 55542 (0.0009) -[2023-10-16 04:58:13,476][05218] Updated weights for policy 0, policy_version 55552 (0.0010) -[2023-10-16 04:58:16,834][05219] Updated weights for policy 1, policy_version 55370 (0.0008) -[2023-10-16 04:58:17,207][05219] Updated weights for policy 1, policy_version 55380 (0.0007) -[2023-10-16 04:58:17,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 113573888. Throughput: 0: 1789.5, 1: 1791.0. Samples: 28409642. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:58:17,351][03835] Avg episode reward: [(0, '6.120'), (1, '6.820')] -[2023-10-16 04:58:17,366][05218] Updated weights for policy 0, policy_version 55562 (0.0009) -[2023-10-16 04:58:17,574][05219] Updated weights for policy 1, policy_version 55390 (0.0008) -[2023-10-16 04:58:17,748][05218] Updated weights for policy 0, policy_version 55572 (0.0010) -[2023-10-16 04:58:18,125][05218] Updated weights for policy 0, policy_version 55582 (0.0010) -[2023-10-16 04:58:21,320][05219] Updated weights for policy 1, policy_version 55400 (0.0011) -[2023-10-16 04:58:21,672][05219] Updated weights for policy 1, policy_version 55410 (0.0009) -[2023-10-16 04:58:21,929][05218] Updated weights for policy 0, policy_version 55592 (0.0009) -[2023-10-16 04:58:22,036][05219] Updated weights for policy 1, policy_version 55420 (0.0009) -[2023-10-16 04:58:22,316][05218] Updated weights for policy 0, policy_version 55602 (0.0010) -[2023-10-16 04:58:22,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 113672192. Throughput: 0: 1798.7, 1: 1777.7. Samples: 28429732. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-16 04:58:22,351][03835] Avg episode reward: [(0, '6.110'), (1, '7.150')] -[2023-10-16 04:58:22,688][05218] Updated weights for policy 0, policy_version 55612 (0.0008) -[2023-10-16 04:58:25,775][05219] Updated weights for policy 1, policy_version 55430 (0.0008) -[2023-10-16 04:58:26,146][05219] Updated weights for policy 1, policy_version 55440 (0.0010) -[2023-10-16 04:58:26,508][05219] Updated weights for policy 1, policy_version 55450 (0.0009) -[2023-10-16 04:58:26,554][05218] Updated weights for policy 0, policy_version 55622 (0.0009) -[2023-10-16 04:58:26,926][05218] Updated weights for policy 0, policy_version 55632 (0.0007) -[2023-10-16 04:58:27,303][05218] Updated weights for policy 0, policy_version 55642 (0.0009) -[2023-10-16 04:58:27,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 113737728. Throughput: 0: 1782.9, 1: 1787.6. Samples: 28441762. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-16 04:58:27,351][03835] Avg episode reward: [(0, '5.760'), (1, '7.000')] -[2023-10-16 04:58:30,280][05219] Updated weights for policy 1, policy_version 55460 (0.0009) -[2023-10-16 04:58:30,649][05219] Updated weights for policy 1, policy_version 55470 (0.0009) -[2023-10-16 04:58:30,981][05218] Updated weights for policy 0, policy_version 55652 (0.0010) -[2023-10-16 04:58:31,011][05219] Updated weights for policy 1, policy_version 55480 (0.0008) -[2023-10-16 04:58:31,360][05218] Updated weights for policy 0, policy_version 55662 (0.0008) -[2023-10-16 04:58:31,738][05218] Updated weights for policy 0, policy_version 55672 (0.0008) -[2023-10-16 04:58:32,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 113836032. Throughput: 0: 1805.9, 1: 1786.9. Samples: 28462380. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-16 04:58:32,351][03835] Avg episode reward: [(0, '5.580'), (1, '6.850')] -[2023-10-16 04:58:34,954][05219] Updated weights for policy 1, policy_version 55490 (0.0008) -[2023-10-16 04:58:35,376][05219] Updated weights for policy 1, policy_version 55500 (0.0009) -[2023-10-16 04:58:35,455][05218] Updated weights for policy 0, policy_version 55682 (0.0008) -[2023-10-16 04:58:35,737][05219] Updated weights for policy 1, policy_version 55510 (0.0009) -[2023-10-16 04:58:35,825][05218] Updated weights for policy 0, policy_version 55692 (0.0010) -[2023-10-16 04:58:36,103][05219] Updated weights for policy 1, policy_version 55520 (0.0008) -[2023-10-16 04:58:36,196][05218] Updated weights for policy 0, policy_version 55702 (0.0008) -[2023-10-16 04:58:36,561][05218] Updated weights for policy 0, policy_version 55712 (0.0009) -[2023-10-16 04:58:37,351][03835] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 113901568. Throughput: 0: 1791.1, 1: 1783.1. Samples: 28483576. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-16 04:58:37,352][03835] Avg episode reward: [(0, '5.920'), (1, '6.630')] -[2023-10-16 04:58:39,947][05219] Updated weights for policy 1, policy_version 55530 (0.0008) -[2023-10-16 04:58:40,315][05219] Updated weights for policy 1, policy_version 55540 (0.0009) -[2023-10-16 04:58:40,395][05218] Updated weights for policy 0, policy_version 55722 (0.0009) -[2023-10-16 04:58:40,680][05219] Updated weights for policy 1, policy_version 55550 (0.0009) -[2023-10-16 04:58:40,757][05218] Updated weights for policy 0, policy_version 55732 (0.0008) -[2023-10-16 04:58:41,131][05218] Updated weights for policy 0, policy_version 55742 (0.0009) -[2023-10-16 04:58:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 113967104. Throughput: 0: 1818.3, 1: 1803.6. Samples: 28495340. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-16 04:58:42,351][03835] Avg episode reward: [(0, '6.200'), (1, '6.510')] -[2023-10-16 04:58:44,249][05219] Updated weights for policy 1, policy_version 55560 (0.0008) -[2023-10-16 04:58:44,615][05219] Updated weights for policy 1, policy_version 55570 (0.0008) -[2023-10-16 04:58:44,769][05218] Updated weights for policy 0, policy_version 55752 (0.0009) -[2023-10-16 04:58:44,979][05219] Updated weights for policy 1, policy_version 55580 (0.0008) -[2023-10-16 04:58:45,145][05218] Updated weights for policy 0, policy_version 55762 (0.0009) -[2023-10-16 04:58:45,520][05218] Updated weights for policy 0, policy_version 55772 (0.0008) -[2023-10-16 04:58:47,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 114032640. Throughput: 0: 1790.3, 1: 1788.2. Samples: 28516010. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-16 04:58:47,351][03835] Avg episode reward: [(0, '6.290'), (1, '7.110')] -[2023-10-16 04:58:48,826][05219] Updated weights for policy 1, policy_version 55590 (0.0010) -[2023-10-16 04:58:49,183][05219] Updated weights for policy 1, policy_version 55600 (0.0008) -[2023-10-16 04:58:49,401][05218] Updated weights for policy 0, policy_version 55782 (0.0010) -[2023-10-16 04:58:49,539][05219] Updated weights for policy 1, policy_version 55610 (0.0007) -[2023-10-16 04:58:49,774][05218] Updated weights for policy 0, policy_version 55792 (0.0007) -[2023-10-16 04:58:50,152][05218] Updated weights for policy 0, policy_version 55802 (0.0009) -[2023-10-16 04:58:52,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 114098176. Throughput: 0: 1779.5, 1: 1778.3. Samples: 28537824. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-16 04:58:52,351][03835] Avg episode reward: [(0, '7.010'), (1, '6.830')] -[2023-10-16 04:58:53,366][05219] Updated weights for policy 1, policy_version 55620 (0.0007) -[2023-10-16 04:58:53,729][05219] Updated weights for policy 1, policy_version 55630 (0.0007) -[2023-10-16 04:58:53,880][05218] Updated weights for policy 0, policy_version 55812 (0.0008) -[2023-10-16 04:58:54,099][05219] Updated weights for policy 1, policy_version 55640 (0.0007) -[2023-10-16 04:58:54,250][05218] Updated weights for policy 0, policy_version 55822 (0.0010) -[2023-10-16 04:58:54,630][05218] Updated weights for policy 0, policy_version 55832 (0.0008) -[2023-10-16 04:58:57,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 114163712. Throughput: 0: 1779.5, 1: 1779.9. Samples: 28547648. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-16 04:58:57,351][03835] Avg episode reward: [(0, '6.640'), (1, '6.850')] -[2023-10-16 04:58:57,734][05219] Updated weights for policy 1, policy_version 55650 (0.0008) -[2023-10-16 04:58:58,096][05219] Updated weights for policy 1, policy_version 55660 (0.0008) -[2023-10-16 04:58:58,454][05219] Updated weights for policy 1, policy_version 55670 (0.0010) -[2023-10-16 04:58:58,657][05218] Updated weights for policy 0, policy_version 55842 (0.0009) -[2023-10-16 04:58:58,822][05219] Updated weights for policy 1, policy_version 55680 (0.0010) -[2023-10-16 04:58:59,032][05218] Updated weights for policy 0, policy_version 55852 (0.0009) -[2023-10-16 04:58:59,411][05218] Updated weights for policy 0, policy_version 55862 (0.0009) -[2023-10-16 04:58:59,787][05218] Updated weights for policy 0, policy_version 55872 (0.0010) -[2023-10-16 04:59:02,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 114229248. Throughput: 0: 1776.6, 1: 1789.2. Samples: 28570102. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-16 04:59:02,351][03835] Avg episode reward: [(0, '6.030'), (1, '7.310')] -[2023-10-16 04:59:02,635][05219] Updated weights for policy 1, policy_version 55690 (0.0008) -[2023-10-16 04:59:03,006][05219] Updated weights for policy 1, policy_version 55700 (0.0009) -[2023-10-16 04:59:03,364][05219] Updated weights for policy 1, policy_version 55710 (0.0007) -[2023-10-16 04:59:03,631][05218] Updated weights for policy 0, policy_version 55882 (0.0009) -[2023-10-16 04:59:04,018][05218] Updated weights for policy 0, policy_version 55892 (0.0009) -[2023-10-16 04:59:04,393][05218] Updated weights for policy 0, policy_version 55902 (0.0008) -[2023-10-16 04:59:07,257][05219] Updated weights for policy 1, policy_version 55720 (0.0007) -[2023-10-16 04:59:07,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 114294784. Throughput: 0: 1791.5, 1: 1812.3. Samples: 28591900. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-16 04:59:07,351][03835] Avg episode reward: [(0, '5.820'), (1, '7.490')] -[2023-10-16 04:59:07,623][05219] Updated weights for policy 1, policy_version 55730 (0.0007) -[2023-10-16 04:59:07,957][05218] Updated weights for policy 0, policy_version 55912 (0.0008) -[2023-10-16 04:59:07,984][05219] Updated weights for policy 1, policy_version 55740 (0.0009) -[2023-10-16 04:59:08,326][05218] Updated weights for policy 0, policy_version 55922 (0.0010) -[2023-10-16 04:59:08,698][05218] Updated weights for policy 0, policy_version 55932 (0.0010) -[2023-10-16 04:59:11,831][05219] Updated weights for policy 1, policy_version 55750 (0.0008) -[2023-10-16 04:59:12,206][05219] Updated weights for policy 1, policy_version 55760 (0.0008) -[2023-10-16 04:59:12,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 114360320. Throughput: 0: 1775.4, 1: 1782.5. Samples: 28601870. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-16 04:59:12,351][03835] Avg episode reward: [(0, '6.010'), (1, '7.290')] -[2023-10-16 04:59:12,372][05218] Updated weights for policy 0, policy_version 55942 (0.0009) -[2023-10-16 04:59:12,568][05219] Updated weights for policy 1, policy_version 55770 (0.0008) -[2023-10-16 04:59:12,744][05218] Updated weights for policy 0, policy_version 55952 (0.0009) -[2023-10-16 04:59:13,122][05218] Updated weights for policy 0, policy_version 55962 (0.0009) -[2023-10-16 04:59:16,226][05219] Updated weights for policy 1, policy_version 55780 (0.0008) -[2023-10-16 04:59:16,595][05219] Updated weights for policy 1, policy_version 55790 (0.0007) -[2023-10-16 04:59:16,893][05218] Updated weights for policy 0, policy_version 55972 (0.0009) -[2023-10-16 04:59:16,964][05219] Updated weights for policy 1, policy_version 55800 (0.0009) -[2023-10-16 04:59:17,272][05218] Updated weights for policy 0, policy_version 55982 (0.0008) -[2023-10-16 04:59:17,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 114458624. Throughput: 0: 1784.3, 1: 1806.5. Samples: 28623964. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-16 04:59:17,351][03835] Avg episode reward: [(0, '5.910'), (1, '7.570')] -[2023-10-16 04:59:17,662][05218] Updated weights for policy 0, policy_version 55992 (0.0009) -[2023-10-16 04:59:20,843][05219] Updated weights for policy 1, policy_version 55810 (0.0007) -[2023-10-16 04:59:21,260][05219] Updated weights for policy 1, policy_version 55820 (0.0008) -[2023-10-16 04:59:21,448][05218] Updated weights for policy 0, policy_version 56002 (0.0008) -[2023-10-16 04:59:21,632][05219] Updated weights for policy 1, policy_version 55830 (0.0008) -[2023-10-16 04:59:21,827][05218] Updated weights for policy 0, policy_version 56012 (0.0009) -[2023-10-16 04:59:21,994][05219] Updated weights for policy 1, policy_version 55840 (0.0007) -[2023-10-16 04:59:22,196][05218] Updated weights for policy 0, policy_version 56022 (0.0009) -[2023-10-16 04:59:22,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 114524160. Throughput: 0: 1773.4, 1: 1781.9. Samples: 28643564. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-16 04:59:22,351][03835] Avg episode reward: [(0, '6.120'), (1, '7.430')] -[2023-10-16 04:59:22,577][05218] Updated weights for policy 0, policy_version 56032 (0.0010) -[2023-10-16 04:59:25,823][05219] Updated weights for policy 1, policy_version 55850 (0.0008) -[2023-10-16 04:59:26,180][05219] Updated weights for policy 1, policy_version 55860 (0.0008) -[2023-10-16 04:59:26,214][05218] Updated weights for policy 0, policy_version 56042 (0.0009) -[2023-10-16 04:59:26,539][05219] Updated weights for policy 1, policy_version 55870 (0.0008) -[2023-10-16 04:59:26,581][05218] Updated weights for policy 0, policy_version 56052 (0.0009) -[2023-10-16 04:59:26,958][05218] Updated weights for policy 0, policy_version 56062 (0.0008) -[2023-10-16 04:59:27,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 114622464. Throughput: 0: 1770.0, 1: 1790.2. Samples: 28655552. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-16 04:59:27,351][03835] Avg episode reward: [(0, '6.480'), (1, '8.090')] -[2023-10-16 04:59:30,419][05219] Updated weights for policy 1, policy_version 55880 (0.0009) -[2023-10-16 04:59:30,783][05219] Updated weights for policy 1, policy_version 55890 (0.0008) -[2023-10-16 04:59:30,818][05218] Updated weights for policy 0, policy_version 56072 (0.0008) -[2023-10-16 04:59:31,143][05219] Updated weights for policy 1, policy_version 55900 (0.0008) -[2023-10-16 04:59:31,192][05218] Updated weights for policy 0, policy_version 56082 (0.0008) -[2023-10-16 04:59:31,572][05218] Updated weights for policy 0, policy_version 56092 (0.0009) -[2023-10-16 04:59:32,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 114688000. Throughput: 0: 1770.0, 1: 1771.2. Samples: 28675364. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:59:32,351][03835] Avg episode reward: [(0, '5.020'), (1, '7.020')] -[2023-10-16 04:59:34,841][05219] Updated weights for policy 1, policy_version 55910 (0.0007) -[2023-10-16 04:59:35,213][05219] Updated weights for policy 1, policy_version 55920 (0.0009) -[2023-10-16 04:59:35,405][05218] Updated weights for policy 0, policy_version 56102 (0.0007) -[2023-10-16 04:59:35,571][05219] Updated weights for policy 1, policy_version 55930 (0.0008) -[2023-10-16 04:59:35,778][05218] Updated weights for policy 0, policy_version 56112 (0.0007) -[2023-10-16 04:59:36,158][05218] Updated weights for policy 0, policy_version 56122 (0.0009) -[2023-10-16 04:59:37,351][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 114753536. Throughput: 0: 1762.4, 1: 1771.4. Samples: 28696846. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:59:37,352][03835] Avg episode reward: [(0, '5.350'), (1, '7.360')] -[2023-10-16 04:59:37,363][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000055936_57278464.pth... -[2023-10-16 04:59:37,363][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000056128_57475072.pth... -[2023-10-16 04:59:37,396][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000054464_55771136.pth -[2023-10-16 04:59:37,403][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000054272_55574528.pth -[2023-10-16 04:59:39,379][05219] Updated weights for policy 1, policy_version 55940 (0.0008) -[2023-10-16 04:59:39,747][05219] Updated weights for policy 1, policy_version 55950 (0.0008) -[2023-10-16 04:59:40,055][05218] Updated weights for policy 0, policy_version 56132 (0.0008) -[2023-10-16 04:59:40,102][05219] Updated weights for policy 1, policy_version 55960 (0.0009) -[2023-10-16 04:59:40,421][05218] Updated weights for policy 0, policy_version 56142 (0.0009) -[2023-10-16 04:59:40,793][05218] Updated weights for policy 0, policy_version 56152 (0.0010) -[2023-10-16 04:59:42,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 114819072. Throughput: 0: 1786.0, 1: 1776.2. Samples: 28707946. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:59:42,351][03835] Avg episode reward: [(0, '5.440'), (1, '6.930')] -[2023-10-16 04:59:43,912][05219] Updated weights for policy 1, policy_version 55970 (0.0010) -[2023-10-16 04:59:44,269][05219] Updated weights for policy 1, policy_version 55980 (0.0009) -[2023-10-16 04:59:44,530][05218] Updated weights for policy 0, policy_version 56162 (0.0008) -[2023-10-16 04:59:44,641][05219] Updated weights for policy 1, policy_version 55990 (0.0008) -[2023-10-16 04:59:44,908][05218] Updated weights for policy 0, policy_version 56172 (0.0008) -[2023-10-16 04:59:45,000][05219] Updated weights for policy 1, policy_version 56000 (0.0007) -[2023-10-16 04:59:45,288][05218] Updated weights for policy 0, policy_version 56182 (0.0009) -[2023-10-16 04:59:45,666][05218] Updated weights for policy 0, policy_version 56192 (0.0011) -[2023-10-16 04:59:47,350][03835] Fps is (10 sec: 13107.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 114884608. Throughput: 0: 1767.6, 1: 1759.1. Samples: 28728806. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:59:47,351][03835] Avg episode reward: [(0, '6.160'), (1, '6.050')] -[2023-10-16 04:59:48,769][05219] Updated weights for policy 1, policy_version 56010 (0.0009) -[2023-10-16 04:59:49,135][05219] Updated weights for policy 1, policy_version 56020 (0.0009) -[2023-10-16 04:59:49,302][05218] Updated weights for policy 0, policy_version 56202 (0.0007) -[2023-10-16 04:59:49,507][05219] Updated weights for policy 1, policy_version 56030 (0.0009) -[2023-10-16 04:59:49,681][05218] Updated weights for policy 0, policy_version 56212 (0.0008) -[2023-10-16 04:59:50,058][05218] Updated weights for policy 0, policy_version 56222 (0.0009) -[2023-10-16 04:59:52,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 114950144. Throughput: 0: 1777.0, 1: 1769.0. Samples: 28751470. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:59:52,352][03835] Avg episode reward: [(0, '6.330'), (1, '6.610')] -[2023-10-16 04:59:53,247][05219] Updated weights for policy 1, policy_version 56040 (0.0009) -[2023-10-16 04:59:53,611][05219] Updated weights for policy 1, policy_version 56050 (0.0010) -[2023-10-16 04:59:53,890][05218] Updated weights for policy 0, policy_version 56232 (0.0008) -[2023-10-16 04:59:53,972][05219] Updated weights for policy 1, policy_version 56060 (0.0008) -[2023-10-16 04:59:54,269][05218] Updated weights for policy 0, policy_version 56242 (0.0008) -[2023-10-16 04:59:54,636][05218] Updated weights for policy 0, policy_version 56252 (0.0009) -[2023-10-16 04:59:57,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 115015680. Throughput: 0: 1776.2, 1: 1767.7. Samples: 28761344. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 04:59:57,351][03835] Avg episode reward: [(0, '6.220'), (1, '7.140')] -[2023-10-16 04:59:57,794][05219] Updated weights for policy 1, policy_version 56070 (0.0008) -[2023-10-16 04:59:58,161][05219] Updated weights for policy 1, policy_version 56080 (0.0008) -[2023-10-16 04:59:58,422][05218] Updated weights for policy 0, policy_version 56262 (0.0010) -[2023-10-16 04:59:58,519][05219] Updated weights for policy 1, policy_version 56090 (0.0008) -[2023-10-16 04:59:58,807][05218] Updated weights for policy 0, policy_version 56272 (0.0007) -[2023-10-16 04:59:59,179][05218] Updated weights for policy 0, policy_version 56282 (0.0008) -[2023-10-16 05:00:02,221][05219] Updated weights for policy 1, policy_version 56100 (0.0008) -[2023-10-16 05:00:02,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 115081216. Throughput: 0: 1782.4, 1: 1767.8. Samples: 28783726. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:00:02,351][03835] Avg episode reward: [(0, '7.090'), (1, '7.090')] -[2023-10-16 05:00:02,582][05219] Updated weights for policy 1, policy_version 56110 (0.0008) -[2023-10-16 05:00:02,868][05218] Updated weights for policy 0, policy_version 56292 (0.0009) -[2023-10-16 05:00:02,955][05219] Updated weights for policy 1, policy_version 56120 (0.0007) -[2023-10-16 05:00:03,244][05218] Updated weights for policy 0, policy_version 56302 (0.0007) -[2023-10-16 05:00:03,611][05218] Updated weights for policy 0, policy_version 56312 (0.0008) -[2023-10-16 05:00:06,786][05219] Updated weights for policy 1, policy_version 56130 (0.0007) -[2023-10-16 05:00:07,185][05219] Updated weights for policy 1, policy_version 56140 (0.0011) -[2023-10-16 05:00:07,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 115146752. Throughput: 0: 1811.5, 1: 1791.4. Samples: 28805696. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:00:07,351][03835] Avg episode reward: [(0, '6.340'), (1, '7.090')] -[2023-10-16 05:00:07,418][05218] Updated weights for policy 0, policy_version 56322 (0.0008) -[2023-10-16 05:00:07,542][05219] Updated weights for policy 1, policy_version 56150 (0.0008) -[2023-10-16 05:00:07,790][05218] Updated weights for policy 0, policy_version 56332 (0.0008) -[2023-10-16 05:00:07,904][05219] Updated weights for policy 1, policy_version 56160 (0.0007) -[2023-10-16 05:00:08,167][05218] Updated weights for policy 0, policy_version 56342 (0.0011) -[2023-10-16 05:00:08,543][05218] Updated weights for policy 0, policy_version 56352 (0.0010) -[2023-10-16 05:00:11,693][05219] Updated weights for policy 1, policy_version 56170 (0.0009) -[2023-10-16 05:00:12,064][05219] Updated weights for policy 1, policy_version 56180 (0.0007) -[2023-10-16 05:00:12,229][05218] Updated weights for policy 0, policy_version 56362 (0.0007) -[2023-10-16 05:00:12,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 115212288. Throughput: 0: 1786.4, 1: 1771.2. Samples: 28815644. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 05:00:12,351][03835] Avg episode reward: [(0, '6.330'), (1, '7.410')] -[2023-10-16 05:00:12,425][05219] Updated weights for policy 1, policy_version 56190 (0.0008) -[2023-10-16 05:00:12,592][05218] Updated weights for policy 0, policy_version 56372 (0.0009) -[2023-10-16 05:00:12,963][05218] Updated weights for policy 0, policy_version 56382 (0.0010) -[2023-10-16 05:00:16,362][05219] Updated weights for policy 1, policy_version 56200 (0.0008) -[2023-10-16 05:00:16,740][05219] Updated weights for policy 1, policy_version 56210 (0.0008) -[2023-10-16 05:00:16,831][05218] Updated weights for policy 0, policy_version 56392 (0.0009) -[2023-10-16 05:00:17,097][05219] Updated weights for policy 1, policy_version 56220 (0.0007) -[2023-10-16 05:00:17,215][05218] Updated weights for policy 0, policy_version 56402 (0.0007) -[2023-10-16 05:00:17,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 115310592. Throughput: 0: 1812.1, 1: 1795.3. Samples: 28837692. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 05:00:17,351][03835] Avg episode reward: [(0, '6.760'), (1, '6.490')] -[2023-10-16 05:00:17,590][05218] Updated weights for policy 0, policy_version 56412 (0.0008) -[2023-10-16 05:00:20,976][05219] Updated weights for policy 1, policy_version 56230 (0.0008) -[2023-10-16 05:00:21,311][05218] Updated weights for policy 0, policy_version 56422 (0.0008) -[2023-10-16 05:00:21,339][05219] Updated weights for policy 1, policy_version 56240 (0.0007) -[2023-10-16 05:00:21,681][05218] Updated weights for policy 0, policy_version 56432 (0.0008) -[2023-10-16 05:00:21,706][05219] Updated weights for policy 1, policy_version 56250 (0.0007) -[2023-10-16 05:00:22,053][05218] Updated weights for policy 0, policy_version 56442 (0.0008) -[2023-10-16 05:00:22,350][03835] Fps is (10 sec: 19660.9, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 115408896. Throughput: 0: 1791.5, 1: 1770.5. Samples: 28857136. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 05:00:22,351][03835] Avg episode reward: [(0, '6.860'), (1, '6.760')] -[2023-10-16 05:00:25,426][05219] Updated weights for policy 1, policy_version 56260 (0.0009) -[2023-10-16 05:00:25,738][05218] Updated weights for policy 0, policy_version 56452 (0.0009) -[2023-10-16 05:00:25,782][05219] Updated weights for policy 1, policy_version 56270 (0.0009) -[2023-10-16 05:00:26,120][05218] Updated weights for policy 0, policy_version 56462 (0.0009) -[2023-10-16 05:00:26,154][05219] Updated weights for policy 1, policy_version 56280 (0.0007) -[2023-10-16 05:00:26,489][05218] Updated weights for policy 0, policy_version 56472 (0.0009) -[2023-10-16 05:00:27,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 115474432. Throughput: 0: 1805.2, 1: 1797.2. Samples: 28870058. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 05:00:27,351][03835] Avg episode reward: [(0, '7.120'), (1, '7.160')] -[2023-10-16 05:00:29,893][05219] Updated weights for policy 1, policy_version 56290 (0.0007) -[2023-10-16 05:00:30,258][05219] Updated weights for policy 1, policy_version 56300 (0.0010) -[2023-10-16 05:00:30,395][05218] Updated weights for policy 0, policy_version 56482 (0.0009) -[2023-10-16 05:00:30,620][05219] Updated weights for policy 1, policy_version 56310 (0.0007) -[2023-10-16 05:00:30,766][05218] Updated weights for policy 0, policy_version 56492 (0.0008) -[2023-10-16 05:00:30,988][05219] Updated weights for policy 1, policy_version 56320 (0.0007) -[2023-10-16 05:00:31,136][05218] Updated weights for policy 0, policy_version 56502 (0.0009) -[2023-10-16 05:00:31,509][05218] Updated weights for policy 0, policy_version 56512 (0.0009) -[2023-10-16 05:00:32,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 115539968. Throughput: 0: 1798.4, 1: 1778.9. Samples: 28889788. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 05:00:32,351][03835] Avg episode reward: [(0, '5.930'), (1, '7.070')] -[2023-10-16 05:00:34,858][05219] Updated weights for policy 1, policy_version 56330 (0.0008) -[2023-10-16 05:00:35,170][05218] Updated weights for policy 0, policy_version 56522 (0.0009) -[2023-10-16 05:00:35,219][05219] Updated weights for policy 1, policy_version 56340 (0.0007) -[2023-10-16 05:00:35,546][05218] Updated weights for policy 0, policy_version 56532 (0.0009) -[2023-10-16 05:00:35,586][05219] Updated weights for policy 1, policy_version 56350 (0.0008) -[2023-10-16 05:00:35,923][05218] Updated weights for policy 0, policy_version 56542 (0.0008) -[2023-10-16 05:00:37,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.6, 300 sec: 14329.1). Total num frames: 115605504. Throughput: 0: 1788.0, 1: 1772.1. Samples: 28911672. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 05:00:37,351][03835] Avg episode reward: [(0, '6.430'), (1, '7.180')] -[2023-10-16 05:00:39,403][05219] Updated weights for policy 1, policy_version 56360 (0.0009) -[2023-10-16 05:00:39,714][05218] Updated weights for policy 0, policy_version 56552 (0.0008) -[2023-10-16 05:00:39,777][05219] Updated weights for policy 1, policy_version 56370 (0.0007) -[2023-10-16 05:00:40,091][05218] Updated weights for policy 0, policy_version 56562 (0.0009) -[2023-10-16 05:00:40,140][05219] Updated weights for policy 1, policy_version 56380 (0.0007) -[2023-10-16 05:00:40,464][05218] Updated weights for policy 0, policy_version 56572 (0.0008) -[2023-10-16 05:00:42,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 115671040. Throughput: 0: 1796.8, 1: 1776.3. Samples: 28922132. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 05:00:42,351][03835] Avg episode reward: [(0, '6.810'), (1, '8.340')] -[2023-10-16 05:00:44,046][05219] Updated weights for policy 1, policy_version 56390 (0.0009) -[2023-10-16 05:00:44,072][05218] Updated weights for policy 0, policy_version 56582 (0.0008) -[2023-10-16 05:00:44,415][05219] Updated weights for policy 1, policy_version 56400 (0.0008) -[2023-10-16 05:00:44,447][05218] Updated weights for policy 0, policy_version 56592 (0.0008) -[2023-10-16 05:00:44,774][05219] Updated weights for policy 1, policy_version 56410 (0.0007) -[2023-10-16 05:00:44,834][05218] Updated weights for policy 0, policy_version 56602 (0.0007) -[2023-10-16 05:00:47,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 115736576. Throughput: 0: 1787.5, 1: 1770.4. Samples: 28943836. Policy #0 lag: (min: 7.0, avg: 8.8, max: 36.0) -[2023-10-16 05:00:47,351][03835] Avg episode reward: [(0, '5.970'), (1, '7.100')] -[2023-10-16 05:00:48,497][05219] Updated weights for policy 1, policy_version 56420 (0.0008) -[2023-10-16 05:00:48,690][05218] Updated weights for policy 0, policy_version 56612 (0.0009) -[2023-10-16 05:00:48,857][05219] Updated weights for policy 1, policy_version 56430 (0.0007) -[2023-10-16 05:00:49,093][05218] Updated weights for policy 0, policy_version 56622 (0.0008) -[2023-10-16 05:00:49,225][05219] Updated weights for policy 1, policy_version 56440 (0.0010) -[2023-10-16 05:00:49,469][05218] Updated weights for policy 0, policy_version 56632 (0.0008) -[2023-10-16 05:00:52,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 115802112. Throughput: 0: 1780.0, 1: 1784.1. Samples: 28966080. Policy #0 lag: (min: 7.0, avg: 8.8, max: 36.0) -[2023-10-16 05:00:52,351][03835] Avg episode reward: [(0, '6.690'), (1, '7.040')] -[2023-10-16 05:00:53,019][05219] Updated weights for policy 1, policy_version 56450 (0.0010) -[2023-10-16 05:00:53,058][05218] Updated weights for policy 0, policy_version 56642 (0.0008) -[2023-10-16 05:00:53,410][05219] Updated weights for policy 1, policy_version 56460 (0.0009) -[2023-10-16 05:00:53,442][05218] Updated weights for policy 0, policy_version 56652 (0.0009) -[2023-10-16 05:00:53,781][05219] Updated weights for policy 1, policy_version 56470 (0.0008) -[2023-10-16 05:00:53,806][05218] Updated weights for policy 0, policy_version 56662 (0.0007) -[2023-10-16 05:00:54,137][05219] Updated weights for policy 1, policy_version 56480 (0.0008) -[2023-10-16 05:00:54,185][05218] Updated weights for policy 0, policy_version 56672 (0.0007) -[2023-10-16 05:00:57,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 115867648. Throughput: 0: 1782.9, 1: 1775.2. Samples: 28975760. Policy #0 lag: (min: 7.0, avg: 8.8, max: 36.0) -[2023-10-16 05:00:57,351][03835] Avg episode reward: [(0, '7.180'), (1, '7.400')] -[2023-10-16 05:00:57,705][05219] Updated weights for policy 1, policy_version 56490 (0.0009) -[2023-10-16 05:00:57,858][05218] Updated weights for policy 0, policy_version 56682 (0.0007) -[2023-10-16 05:00:58,084][05219] Updated weights for policy 1, policy_version 56500 (0.0007) -[2023-10-16 05:00:58,230][05218] Updated weights for policy 0, policy_version 56692 (0.0007) -[2023-10-16 05:00:58,452][05219] Updated weights for policy 1, policy_version 56510 (0.0007) -[2023-10-16 05:00:58,605][05218] Updated weights for policy 0, policy_version 56702 (0.0008) -[2023-10-16 05:01:02,296][05218] Updated weights for policy 0, policy_version 56712 (0.0008) -[2023-10-16 05:01:02,348][05219] Updated weights for policy 1, policy_version 56520 (0.0007) -[2023-10-16 05:01:02,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 115933184. Throughput: 0: 1789.8, 1: 1783.0. Samples: 28998466. Policy #0 lag: (min: 7.0, avg: 8.8, max: 36.0) -[2023-10-16 05:01:02,351][03835] Avg episode reward: [(0, '6.840'), (1, '6.390')] -[2023-10-16 05:01:02,676][05218] Updated weights for policy 0, policy_version 56722 (0.0008) -[2023-10-16 05:01:02,711][05219] Updated weights for policy 1, policy_version 56530 (0.0008) -[2023-10-16 05:01:03,042][05218] Updated weights for policy 0, policy_version 56732 (0.0007) -[2023-10-16 05:01:03,072][05219] Updated weights for policy 1, policy_version 56540 (0.0008) -[2023-10-16 05:01:06,764][05218] Updated weights for policy 0, policy_version 56742 (0.0008) -[2023-10-16 05:01:06,934][05219] Updated weights for policy 1, policy_version 56550 (0.0008) -[2023-10-16 05:01:07,145][05218] Updated weights for policy 0, policy_version 56752 (0.0008) -[2023-10-16 05:01:07,302][05219] Updated weights for policy 1, policy_version 56560 (0.0008) -[2023-10-16 05:01:07,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 115998720. Throughput: 0: 1807.0, 1: 1803.7. Samples: 29019616. Policy #0 lag: (min: 7.0, avg: 8.8, max: 36.0) -[2023-10-16 05:01:07,351][03835] Avg episode reward: [(0, '6.800'), (1, '6.720')] -[2023-10-16 05:01:07,532][05218] Updated weights for policy 0, policy_version 56762 (0.0009) -[2023-10-16 05:01:07,668][05219] Updated weights for policy 1, policy_version 56570 (0.0008) -[2023-10-16 05:01:11,349][05218] Updated weights for policy 0, policy_version 56772 (0.0007) -[2023-10-16 05:01:11,598][05219] Updated weights for policy 1, policy_version 56580 (0.0008) -[2023-10-16 05:01:11,711][05218] Updated weights for policy 0, policy_version 56782 (0.0009) -[2023-10-16 05:01:11,968][05219] Updated weights for policy 1, policy_version 56590 (0.0008) -[2023-10-16 05:01:12,090][05218] Updated weights for policy 0, policy_version 56792 (0.0008) -[2023-10-16 05:01:12,340][05219] Updated weights for policy 1, policy_version 56600 (0.0008) -[2023-10-16 05:01:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 116064256. Throughput: 0: 1788.2, 1: 1775.9. Samples: 29030442. Policy #0 lag: (min: 7.0, avg: 8.8, max: 36.0) -[2023-10-16 05:01:12,351][03835] Avg episode reward: [(0, '6.470'), (1, '6.030')] -[2023-10-16 05:01:15,815][05218] Updated weights for policy 0, policy_version 56802 (0.0008) -[2023-10-16 05:01:15,998][05219] Updated weights for policy 1, policy_version 56610 (0.0009) -[2023-10-16 05:01:16,186][05218] Updated weights for policy 0, policy_version 56812 (0.0008) -[2023-10-16 05:01:16,356][05219] Updated weights for policy 1, policy_version 56620 (0.0007) -[2023-10-16 05:01:16,565][05218] Updated weights for policy 0, policy_version 56822 (0.0007) -[2023-10-16 05:01:16,725][05219] Updated weights for policy 1, policy_version 56630 (0.0007) -[2023-10-16 05:01:16,938][05218] Updated weights for policy 0, policy_version 56832 (0.0008) -[2023-10-16 05:01:17,092][05219] Updated weights for policy 1, policy_version 56640 (0.0009) -[2023-10-16 05:01:17,350][03835] Fps is (10 sec: 19660.3, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 116195328. Throughput: 0: 1798.4, 1: 1797.8. Samples: 29051616. Policy #0 lag: (min: 7.0, avg: 8.8, max: 36.0) -[2023-10-16 05:01:17,351][03835] Avg episode reward: [(0, '6.850'), (1, '6.790')] -[2023-10-16 05:01:20,588][05219] Updated weights for policy 1, policy_version 56650 (0.0009) -[2023-10-16 05:01:20,638][05218] Updated weights for policy 0, policy_version 56842 (0.0008) -[2023-10-16 05:01:20,963][05219] Updated weights for policy 1, policy_version 56660 (0.0009) -[2023-10-16 05:01:21,009][05218] Updated weights for policy 0, policy_version 56852 (0.0010) -[2023-10-16 05:01:21,323][05219] Updated weights for policy 1, policy_version 56670 (0.0008) -[2023-10-16 05:01:21,386][05218] Updated weights for policy 0, policy_version 56862 (0.0009) -[2023-10-16 05:01:22,351][03835] Fps is (10 sec: 19660.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 116260864. Throughput: 0: 1790.5, 1: 1778.3. Samples: 29072270. Policy #0 lag: (min: 15.0, avg: 23.0, max: 47.0) -[2023-10-16 05:01:22,352][03835] Avg episode reward: [(0, '6.400'), (1, '6.590')] -[2023-10-16 05:01:25,115][05218] Updated weights for policy 0, policy_version 56872 (0.0010) -[2023-10-16 05:01:25,156][05219] Updated weights for policy 1, policy_version 56680 (0.0008) -[2023-10-16 05:01:25,492][05218] Updated weights for policy 0, policy_version 56882 (0.0009) -[2023-10-16 05:01:25,526][05219] Updated weights for policy 1, policy_version 56690 (0.0007) -[2023-10-16 05:01:25,862][05218] Updated weights for policy 0, policy_version 56892 (0.0008) -[2023-10-16 05:01:25,888][05219] Updated weights for policy 1, policy_version 56700 (0.0007) -[2023-10-16 05:01:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 116326400. Throughput: 0: 1796.3, 1: 1798.1. Samples: 29083880. Policy #0 lag: (min: 15.0, avg: 23.0, max: 47.0) -[2023-10-16 05:01:27,351][03835] Avg episode reward: [(0, '6.430'), (1, '7.440')] -[2023-10-16 05:01:29,661][05219] Updated weights for policy 1, policy_version 56710 (0.0008) -[2023-10-16 05:01:29,784][05218] Updated weights for policy 0, policy_version 56902 (0.0008) -[2023-10-16 05:01:30,020][05219] Updated weights for policy 1, policy_version 56720 (0.0007) -[2023-10-16 05:01:30,146][05218] Updated weights for policy 0, policy_version 56912 (0.0007) -[2023-10-16 05:01:30,381][05219] Updated weights for policy 1, policy_version 56730 (0.0008) -[2023-10-16 05:01:30,532][05218] Updated weights for policy 0, policy_version 56922 (0.0007) -[2023-10-16 05:01:32,350][03835] Fps is (10 sec: 13107.8, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 116391936. Throughput: 0: 1780.3, 1: 1781.2. Samples: 29104102. Policy #0 lag: (min: 15.0, avg: 23.0, max: 47.0) -[2023-10-16 05:01:32,351][03835] Avg episode reward: [(0, '6.920'), (1, '7.990')] -[2023-10-16 05:01:34,191][05219] Updated weights for policy 1, policy_version 56740 (0.0008) -[2023-10-16 05:01:34,287][05218] Updated weights for policy 0, policy_version 56932 (0.0007) -[2023-10-16 05:01:34,562][05219] Updated weights for policy 1, policy_version 56750 (0.0008) -[2023-10-16 05:01:34,672][05218] Updated weights for policy 0, policy_version 56942 (0.0008) -[2023-10-16 05:01:34,929][05219] Updated weights for policy 1, policy_version 56760 (0.0007) -[2023-10-16 05:01:35,051][05218] Updated weights for policy 0, policy_version 56952 (0.0009) -[2023-10-16 05:01:37,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 116457472. Throughput: 0: 1784.3, 1: 1774.2. Samples: 29126214. Policy #0 lag: (min: 15.0, avg: 23.0, max: 47.0) -[2023-10-16 05:01:37,351][03835] Avg episode reward: [(0, '6.580'), (1, '6.780')] -[2023-10-16 05:01:37,361][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000056768_58130432.pth... -[2023-10-16 05:01:37,361][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000056960_58327040.pth... -[2023-10-16 05:01:37,401][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000055296_56623104.pth -[2023-10-16 05:01:37,403][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000055104_56426496.pth -[2023-10-16 05:01:38,739][05219] Updated weights for policy 1, policy_version 56770 (0.0009) -[2023-10-16 05:01:38,846][05218] Updated weights for policy 0, policy_version 56962 (0.0008) -[2023-10-16 05:01:39,135][05219] Updated weights for policy 1, policy_version 56780 (0.0010) -[2023-10-16 05:01:39,217][05218] Updated weights for policy 0, policy_version 56972 (0.0007) -[2023-10-16 05:01:39,492][05219] Updated weights for policy 1, policy_version 56790 (0.0007) -[2023-10-16 05:01:39,599][05218] Updated weights for policy 0, policy_version 56982 (0.0007) -[2023-10-16 05:01:39,857][05219] Updated weights for policy 1, policy_version 56800 (0.0008) -[2023-10-16 05:01:39,966][05218] Updated weights for policy 0, policy_version 56992 (0.0008) -[2023-10-16 05:01:42,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 116523008. Throughput: 0: 1783.0, 1: 1773.9. Samples: 29135822. Policy #0 lag: (min: 15.0, avg: 23.0, max: 47.0) -[2023-10-16 05:01:42,351][03835] Avg episode reward: [(0, '6.600'), (1, '7.310')] -[2023-10-16 05:01:43,694][05218] Updated weights for policy 0, policy_version 57002 (0.0007) -[2023-10-16 05:01:43,732][05219] Updated weights for policy 1, policy_version 56810 (0.0009) -[2023-10-16 05:01:44,065][05218] Updated weights for policy 0, policy_version 57012 (0.0008) -[2023-10-16 05:01:44,088][05219] Updated weights for policy 1, policy_version 56820 (0.0007) -[2023-10-16 05:01:44,438][05218] Updated weights for policy 0, policy_version 57022 (0.0008) -[2023-10-16 05:01:44,447][05219] Updated weights for policy 1, policy_version 56830 (0.0008) -[2023-10-16 05:01:47,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 116588544. Throughput: 0: 1776.2, 1: 1769.9. Samples: 29158042. Policy #0 lag: (min: 15.0, avg: 23.0, max: 47.0) -[2023-10-16 05:01:47,351][03835] Avg episode reward: [(0, '6.170'), (1, '7.240')] -[2023-10-16 05:01:48,236][05219] Updated weights for policy 1, policy_version 56840 (0.0009) -[2023-10-16 05:01:48,374][05218] Updated weights for policy 0, policy_version 57032 (0.0008) -[2023-10-16 05:01:48,595][05219] Updated weights for policy 1, policy_version 56850 (0.0008) -[2023-10-16 05:01:48,739][05218] Updated weights for policy 0, policy_version 57042 (0.0010) -[2023-10-16 05:01:48,966][05219] Updated weights for policy 1, policy_version 56860 (0.0008) -[2023-10-16 05:01:49,125][05218] Updated weights for policy 0, policy_version 57052 (0.0010) -[2023-10-16 05:01:52,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 116654080. Throughput: 0: 1792.2, 1: 1782.9. Samples: 29180496. Policy #0 lag: (min: 15.0, avg: 23.0, max: 47.0) -[2023-10-16 05:01:52,351][03835] Avg episode reward: [(0, '6.350'), (1, '6.550')] -[2023-10-16 05:01:52,715][05219] Updated weights for policy 1, policy_version 56870 (0.0008) -[2023-10-16 05:01:52,824][05218] Updated weights for policy 0, policy_version 57062 (0.0008) -[2023-10-16 05:01:53,067][05219] Updated weights for policy 1, policy_version 56880 (0.0008) -[2023-10-16 05:01:53,196][05218] Updated weights for policy 0, policy_version 57072 (0.0009) -[2023-10-16 05:01:53,430][05219] Updated weights for policy 1, policy_version 56890 (0.0008) -[2023-10-16 05:01:53,574][05218] Updated weights for policy 0, policy_version 57082 (0.0007) -[2023-10-16 05:01:57,251][05219] Updated weights for policy 1, policy_version 56900 (0.0007) -[2023-10-16 05:01:57,295][05218] Updated weights for policy 0, policy_version 57092 (0.0007) -[2023-10-16 05:01:57,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 116719616. Throughput: 0: 1773.9, 1: 1774.9. Samples: 29190138. Policy #0 lag: (min: 15.0, avg: 23.0, max: 47.0) -[2023-10-16 05:01:57,351][03835] Avg episode reward: [(0, '6.240'), (1, '6.810')] -[2023-10-16 05:01:57,619][05219] Updated weights for policy 1, policy_version 56910 (0.0007) -[2023-10-16 05:01:57,668][05218] Updated weights for policy 0, policy_version 57102 (0.0008) -[2023-10-16 05:01:57,981][05219] Updated weights for policy 1, policy_version 56920 (0.0008) -[2023-10-16 05:01:58,048][05218] Updated weights for policy 0, policy_version 57112 (0.0007) -[2023-10-16 05:02:01,771][05219] Updated weights for policy 1, policy_version 56930 (0.0008) -[2023-10-16 05:02:01,771][05218] Updated weights for policy 0, policy_version 57122 (0.0010) -[2023-10-16 05:02:02,140][05219] Updated weights for policy 1, policy_version 56940 (0.0008) -[2023-10-16 05:02:02,141][05218] Updated weights for policy 0, policy_version 57132 (0.0008) -[2023-10-16 05:02:02,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 116785152. Throughput: 0: 1794.1, 1: 1784.4. Samples: 29212650. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:02:02,351][03835] Avg episode reward: [(0, '6.200'), (1, '6.790')] -[2023-10-16 05:02:02,497][05219] Updated weights for policy 1, policy_version 56950 (0.0007) -[2023-10-16 05:02:02,524][05218] Updated weights for policy 0, policy_version 57142 (0.0009) -[2023-10-16 05:02:02,863][05219] Updated weights for policy 1, policy_version 56960 (0.0008) -[2023-10-16 05:02:02,905][05218] Updated weights for policy 0, policy_version 57152 (0.0008) -[2023-10-16 05:02:06,614][05219] Updated weights for policy 1, policy_version 56970 (0.0007) -[2023-10-16 05:02:06,805][05218] Updated weights for policy 0, policy_version 57162 (0.0008) -[2023-10-16 05:02:06,985][05219] Updated weights for policy 1, policy_version 56980 (0.0008) -[2023-10-16 05:02:07,172][05218] Updated weights for policy 0, policy_version 57172 (0.0009) -[2023-10-16 05:02:07,341][05219] Updated weights for policy 1, policy_version 56990 (0.0008) -[2023-10-16 05:02:07,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 116850688. Throughput: 0: 1784.3, 1: 1785.8. Samples: 29232922. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:02:07,351][03835] Avg episode reward: [(0, '6.080'), (1, '6.450')] -[2023-10-16 05:02:07,546][05218] Updated weights for policy 0, policy_version 57182 (0.0009) -[2023-10-16 05:02:11,185][05219] Updated weights for policy 1, policy_version 57000 (0.0009) -[2023-10-16 05:02:11,398][05218] Updated weights for policy 0, policy_version 57192 (0.0008) -[2023-10-16 05:02:11,552][05219] Updated weights for policy 1, policy_version 57010 (0.0008) -[2023-10-16 05:02:11,762][05218] Updated weights for policy 0, policy_version 57202 (0.0007) -[2023-10-16 05:02:11,906][05219] Updated weights for policy 1, policy_version 57020 (0.0007) -[2023-10-16 05:02:12,143][05218] Updated weights for policy 0, policy_version 57212 (0.0007) -[2023-10-16 05:02:12,350][03835] Fps is (10 sec: 19661.2, 60 sec: 15291.7, 300 sec: 14440.1). Total num frames: 116981760. Throughput: 0: 1787.9, 1: 1781.8. Samples: 29244518. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:02:12,351][03835] Avg episode reward: [(0, '6.610'), (1, '7.110')] -[2023-10-16 05:02:15,755][05219] Updated weights for policy 1, policy_version 57030 (0.0009) -[2023-10-16 05:02:15,937][05218] Updated weights for policy 0, policy_version 57222 (0.0008) -[2023-10-16 05:02:16,117][05219] Updated weights for policy 1, policy_version 57040 (0.0009) -[2023-10-16 05:02:16,305][05218] Updated weights for policy 0, policy_version 57232 (0.0009) -[2023-10-16 05:02:16,482][05219] Updated weights for policy 1, policy_version 57050 (0.0007) -[2023-10-16 05:02:16,683][05218] Updated weights for policy 0, policy_version 57242 (0.0007) -[2023-10-16 05:02:17,350][03835] Fps is (10 sec: 19660.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 117047296. Throughput: 0: 1791.3, 1: 1789.1. Samples: 29265220. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:02:17,351][03835] Avg episode reward: [(0, '6.530'), (1, '7.150')] -[2023-10-16 05:02:20,281][05219] Updated weights for policy 1, policy_version 57060 (0.0008) -[2023-10-16 05:02:20,372][05218] Updated weights for policy 0, policy_version 57252 (0.0008) -[2023-10-16 05:02:20,652][05219] Updated weights for policy 1, policy_version 57070 (0.0008) -[2023-10-16 05:02:20,753][05218] Updated weights for policy 0, policy_version 57262 (0.0009) -[2023-10-16 05:02:21,016][05219] Updated weights for policy 1, policy_version 57080 (0.0009) -[2023-10-16 05:02:21,117][05218] Updated weights for policy 0, policy_version 57272 (0.0009) -[2023-10-16 05:02:22,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 117112832. Throughput: 0: 1775.8, 1: 1779.6. Samples: 29286206. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:02:22,351][03835] Avg episode reward: [(0, '6.140'), (1, '7.170')] -[2023-10-16 05:02:24,708][05218] Updated weights for policy 0, policy_version 57282 (0.0008) -[2023-10-16 05:02:24,908][05219] Updated weights for policy 1, policy_version 57090 (0.0009) -[2023-10-16 05:02:25,087][05218] Updated weights for policy 0, policy_version 57292 (0.0008) -[2023-10-16 05:02:25,305][05219] Updated weights for policy 1, policy_version 57100 (0.0008) -[2023-10-16 05:02:25,462][05218] Updated weights for policy 0, policy_version 57302 (0.0008) -[2023-10-16 05:02:25,669][05219] Updated weights for policy 1, policy_version 57110 (0.0008) -[2023-10-16 05:02:25,836][05218] Updated weights for policy 0, policy_version 57312 (0.0009) -[2023-10-16 05:02:26,042][05219] Updated weights for policy 1, policy_version 57120 (0.0008) -[2023-10-16 05:02:27,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 117178368. Throughput: 0: 1790.5, 1: 1800.9. Samples: 29297434. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:02:27,351][03835] Avg episode reward: [(0, '6.350'), (1, '7.740')] -[2023-10-16 05:02:29,557][05218] Updated weights for policy 0, policy_version 57322 (0.0007) -[2023-10-16 05:02:29,901][05219] Updated weights for policy 1, policy_version 57130 (0.0007) -[2023-10-16 05:02:29,935][05218] Updated weights for policy 0, policy_version 57332 (0.0008) -[2023-10-16 05:02:30,263][05219] Updated weights for policy 1, policy_version 57140 (0.0007) -[2023-10-16 05:02:30,307][05218] Updated weights for policy 0, policy_version 57342 (0.0008) -[2023-10-16 05:02:30,625][05219] Updated weights for policy 1, policy_version 57150 (0.0008) -[2023-10-16 05:02:32,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 117243904. Throughput: 0: 1770.5, 1: 1775.4. Samples: 29317606. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:02:32,351][03835] Avg episode reward: [(0, '6.940'), (1, '7.730')] -[2023-10-16 05:02:34,206][05218] Updated weights for policy 0, policy_version 57352 (0.0011) -[2023-10-16 05:02:34,521][05219] Updated weights for policy 1, policy_version 57160 (0.0007) -[2023-10-16 05:02:34,584][05218] Updated weights for policy 0, policy_version 57362 (0.0008) -[2023-10-16 05:02:34,887][05219] Updated weights for policy 1, policy_version 57170 (0.0007) -[2023-10-16 05:02:34,962][05218] Updated weights for policy 0, policy_version 57372 (0.0007) -[2023-10-16 05:02:35,258][05219] Updated weights for policy 1, policy_version 57180 (0.0009) -[2023-10-16 05:02:37,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 117309440. Throughput: 0: 1769.3, 1: 1768.3. Samples: 29339686. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:02:37,351][03835] Avg episode reward: [(0, '6.380'), (1, '7.430')] -[2023-10-16 05:02:38,698][05218] Updated weights for policy 0, policy_version 57382 (0.0009) -[2023-10-16 05:02:39,016][05219] Updated weights for policy 1, policy_version 57190 (0.0008) -[2023-10-16 05:02:39,077][05218] Updated weights for policy 0, policy_version 57392 (0.0008) -[2023-10-16 05:02:39,370][05219] Updated weights for policy 1, policy_version 57200 (0.0007) -[2023-10-16 05:02:39,438][05218] Updated weights for policy 0, policy_version 57402 (0.0009) -[2023-10-16 05:02:39,744][05219] Updated weights for policy 1, policy_version 57210 (0.0008) -[2023-10-16 05:02:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 117374976. Throughput: 0: 1770.9, 1: 1768.3. Samples: 29349402. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:02:42,351][03835] Avg episode reward: [(0, '5.990'), (1, '6.330')] -[2023-10-16 05:02:43,321][05218] Updated weights for policy 0, policy_version 57412 (0.0008) -[2023-10-16 05:02:43,598][05219] Updated weights for policy 1, policy_version 57220 (0.0008) -[2023-10-16 05:02:43,693][05218] Updated weights for policy 0, policy_version 57422 (0.0008) -[2023-10-16 05:02:43,955][05219] Updated weights for policy 1, policy_version 57230 (0.0008) -[2023-10-16 05:02:44,069][05218] Updated weights for policy 0, policy_version 57432 (0.0009) -[2023-10-16 05:02:44,324][05219] Updated weights for policy 1, policy_version 57240 (0.0008) -[2023-10-16 05:02:47,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 117440512. Throughput: 0: 1769.2, 1: 1768.1. Samples: 29371826. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:02:47,351][03835] Avg episode reward: [(0, '6.110'), (1, '6.410')] -[2023-10-16 05:02:47,862][05218] Updated weights for policy 0, policy_version 57442 (0.0008) -[2023-10-16 05:02:48,075][05219] Updated weights for policy 1, policy_version 57250 (0.0007) -[2023-10-16 05:02:48,239][05218] Updated weights for policy 0, policy_version 57452 (0.0007) -[2023-10-16 05:02:48,438][05219] Updated weights for policy 1, policy_version 57260 (0.0008) -[2023-10-16 05:02:48,607][05218] Updated weights for policy 0, policy_version 57462 (0.0008) -[2023-10-16 05:02:48,806][05219] Updated weights for policy 1, policy_version 57270 (0.0008) -[2023-10-16 05:02:48,985][05218] Updated weights for policy 0, policy_version 57472 (0.0008) -[2023-10-16 05:02:49,158][05219] Updated weights for policy 1, policy_version 57280 (0.0009) -[2023-10-16 05:02:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 117506048. Throughput: 0: 1795.0, 1: 1788.3. Samples: 29394168. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:02:52,351][03835] Avg episode reward: [(0, '6.370'), (1, '6.450')] -[2023-10-16 05:02:52,745][05218] Updated weights for policy 0, policy_version 57482 (0.0007) -[2023-10-16 05:02:52,955][05219] Updated weights for policy 1, policy_version 57290 (0.0008) -[2023-10-16 05:02:53,132][05218] Updated weights for policy 0, policy_version 57492 (0.0008) -[2023-10-16 05:02:53,313][05219] Updated weights for policy 1, policy_version 57300 (0.0008) -[2023-10-16 05:02:53,496][05218] Updated weights for policy 0, policy_version 57502 (0.0010) -[2023-10-16 05:02:53,686][05219] Updated weights for policy 1, policy_version 57310 (0.0009) -[2023-10-16 05:02:57,251][05218] Updated weights for policy 0, policy_version 57512 (0.0010) -[2023-10-16 05:02:57,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 117571584. Throughput: 0: 1779.8, 1: 1764.4. Samples: 29404004. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:02:57,351][03835] Avg episode reward: [(0, '5.740'), (1, '6.580')] -[2023-10-16 05:02:57,471][05219] Updated weights for policy 1, policy_version 57320 (0.0007) -[2023-10-16 05:02:57,625][05218] Updated weights for policy 0, policy_version 57522 (0.0009) -[2023-10-16 05:02:57,842][05219] Updated weights for policy 1, policy_version 57330 (0.0007) -[2023-10-16 05:02:57,999][05218] Updated weights for policy 0, policy_version 57532 (0.0008) -[2023-10-16 05:02:58,202][05219] Updated weights for policy 1, policy_version 57340 (0.0009) -[2023-10-16 05:03:01,748][05218] Updated weights for policy 0, policy_version 57542 (0.0008) -[2023-10-16 05:03:01,900][05219] Updated weights for policy 1, policy_version 57350 (0.0007) -[2023-10-16 05:03:02,117][05218] Updated weights for policy 0, policy_version 57552 (0.0008) -[2023-10-16 05:03:02,260][05219] Updated weights for policy 1, policy_version 57360 (0.0008) -[2023-10-16 05:03:02,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 117637120. Throughput: 0: 1791.3, 1: 1783.7. Samples: 29426096. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:03:02,351][03835] Avg episode reward: [(0, '6.480'), (1, '7.010')] -[2023-10-16 05:03:02,500][05218] Updated weights for policy 0, policy_version 57562 (0.0007) -[2023-10-16 05:03:02,628][05219] Updated weights for policy 1, policy_version 57370 (0.0008) -[2023-10-16 05:03:06,251][05218] Updated weights for policy 0, policy_version 57572 (0.0008) -[2023-10-16 05:03:06,588][05219] Updated weights for policy 1, policy_version 57380 (0.0011) -[2023-10-16 05:03:06,632][05218] Updated weights for policy 0, policy_version 57582 (0.0008) -[2023-10-16 05:03:06,951][05219] Updated weights for policy 1, policy_version 57390 (0.0008) -[2023-10-16 05:03:07,009][05218] Updated weights for policy 0, policy_version 57592 (0.0008) -[2023-10-16 05:03:07,313][05219] Updated weights for policy 1, policy_version 57400 (0.0010) -[2023-10-16 05:03:07,351][03835] Fps is (10 sec: 16383.4, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 117735424. Throughput: 0: 1770.0, 1: 1780.1. Samples: 29445964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:03:07,352][03835] Avg episode reward: [(0, '6.490'), (1, '7.200')] -[2023-10-16 05:03:10,905][05218] Updated weights for policy 0, policy_version 57602 (0.0009) -[2023-10-16 05:03:11,285][05218] Updated weights for policy 0, policy_version 57612 (0.0008) -[2023-10-16 05:03:11,289][05219] Updated weights for policy 1, policy_version 57410 (0.0008) -[2023-10-16 05:03:11,673][05218] Updated weights for policy 0, policy_version 57622 (0.0008) -[2023-10-16 05:03:11,689][05219] Updated weights for policy 1, policy_version 57420 (0.0007) -[2023-10-16 05:03:12,046][05218] Updated weights for policy 0, policy_version 57632 (0.0008) -[2023-10-16 05:03:12,055][05219] Updated weights for policy 1, policy_version 57430 (0.0008) -[2023-10-16 05:03:12,350][03835] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 14329.1). Total num frames: 117800960. Throughput: 0: 1788.9, 1: 1776.3. Samples: 29457870. Policy #0 lag: (min: 15.0, avg: 15.1, max: 20.0) -[2023-10-16 05:03:12,351][03835] Avg episode reward: [(0, '5.910'), (1, '6.960')] -[2023-10-16 05:03:12,415][05219] Updated weights for policy 1, policy_version 57440 (0.0008) -[2023-10-16 05:03:15,892][05218] Updated weights for policy 0, policy_version 57642 (0.0011) -[2023-10-16 05:03:16,261][05218] Updated weights for policy 0, policy_version 57652 (0.0008) -[2023-10-16 05:03:16,267][05219] Updated weights for policy 1, policy_version 57450 (0.0008) -[2023-10-16 05:03:16,634][05219] Updated weights for policy 1, policy_version 57460 (0.0008) -[2023-10-16 05:03:16,637][05218] Updated weights for policy 0, policy_version 57662 (0.0008) -[2023-10-16 05:03:17,001][05219] Updated weights for policy 1, policy_version 57470 (0.0007) -[2023-10-16 05:03:17,350][03835] Fps is (10 sec: 16384.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 117899264. Throughput: 0: 1783.3, 1: 1790.7. Samples: 29478434. Policy #0 lag: (min: 15.0, avg: 15.1, max: 20.0) -[2023-10-16 05:03:17,351][03835] Avg episode reward: [(0, '6.920'), (1, '6.810')] -[2023-10-16 05:03:20,357][05218] Updated weights for policy 0, policy_version 57672 (0.0009) -[2023-10-16 05:03:20,597][05219] Updated weights for policy 1, policy_version 57480 (0.0009) -[2023-10-16 05:03:20,726][05218] Updated weights for policy 0, policy_version 57682 (0.0009) -[2023-10-16 05:03:20,959][05219] Updated weights for policy 1, policy_version 57490 (0.0009) -[2023-10-16 05:03:21,102][05218] Updated weights for policy 0, policy_version 57692 (0.0008) -[2023-10-16 05:03:21,320][05219] Updated weights for policy 1, policy_version 57500 (0.0009) -[2023-10-16 05:03:22,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 117964800. Throughput: 0: 1777.2, 1: 1773.4. Samples: 29499466. Policy #0 lag: (min: 15.0, avg: 15.1, max: 20.0) -[2023-10-16 05:03:22,351][03835] Avg episode reward: [(0, '6.660'), (1, '6.850')] -[2023-10-16 05:03:24,843][05218] Updated weights for policy 0, policy_version 57702 (0.0007) -[2023-10-16 05:03:25,211][05218] Updated weights for policy 0, policy_version 57712 (0.0009) -[2023-10-16 05:03:25,212][05219] Updated weights for policy 1, policy_version 57510 (0.0008) -[2023-10-16 05:03:25,582][05219] Updated weights for policy 1, policy_version 57520 (0.0010) -[2023-10-16 05:03:25,591][05218] Updated weights for policy 0, policy_version 57722 (0.0008) -[2023-10-16 05:03:25,939][05219] Updated weights for policy 1, policy_version 57530 (0.0010) -[2023-10-16 05:03:27,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 118030336. Throughput: 0: 1792.4, 1: 1798.8. Samples: 29511008. Policy #0 lag: (min: 15.0, avg: 15.1, max: 20.0) -[2023-10-16 05:03:27,351][03835] Avg episode reward: [(0, '6.670'), (1, '7.130')] -[2023-10-16 05:03:29,238][05218] Updated weights for policy 0, policy_version 57732 (0.0009) -[2023-10-16 05:03:29,609][05218] Updated weights for policy 0, policy_version 57742 (0.0009) -[2023-10-16 05:03:29,779][05219] Updated weights for policy 1, policy_version 57540 (0.0009) -[2023-10-16 05:03:29,984][05218] Updated weights for policy 0, policy_version 57752 (0.0007) -[2023-10-16 05:03:30,144][05219] Updated weights for policy 1, policy_version 57550 (0.0007) -[2023-10-16 05:03:30,506][05219] Updated weights for policy 1, policy_version 57560 (0.0008) -[2023-10-16 05:03:32,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 118095872. Throughput: 0: 1782.9, 1: 1767.5. Samples: 29531598. Policy #0 lag: (min: 15.0, avg: 15.1, max: 20.0) -[2023-10-16 05:03:32,351][03835] Avg episode reward: [(0, '7.300'), (1, '6.990')] -[2023-10-16 05:03:33,763][05218] Updated weights for policy 0, policy_version 57762 (0.0009) -[2023-10-16 05:03:34,148][05218] Updated weights for policy 0, policy_version 57772 (0.0008) -[2023-10-16 05:03:34,292][05219] Updated weights for policy 1, policy_version 57570 (0.0009) -[2023-10-16 05:03:34,516][05218] Updated weights for policy 0, policy_version 57782 (0.0008) -[2023-10-16 05:03:34,649][05219] Updated weights for policy 1, policy_version 57580 (0.0009) -[2023-10-16 05:03:34,892][05218] Updated weights for policy 0, policy_version 57792 (0.0007) -[2023-10-16 05:03:35,019][05219] Updated weights for policy 1, policy_version 57590 (0.0008) -[2023-10-16 05:03:35,384][05219] Updated weights for policy 1, policy_version 57600 (0.0008) -[2023-10-16 05:03:37,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 118161408. Throughput: 0: 1780.9, 1: 1767.6. Samples: 29553850. Policy #0 lag: (min: 15.0, avg: 15.1, max: 20.0) -[2023-10-16 05:03:37,351][03835] Avg episode reward: [(0, '6.230'), (1, '7.200')] -[2023-10-16 05:03:37,363][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000057600_58982400.pth... -[2023-10-16 05:03:37,363][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000057792_59179008.pth... -[2023-10-16 05:03:37,394][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000055936_57278464.pth -[2023-10-16 05:03:37,402][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000056128_57475072.pth -[2023-10-16 05:03:38,601][05218] Updated weights for policy 0, policy_version 57802 (0.0009) -[2023-10-16 05:03:38,982][05218] Updated weights for policy 0, policy_version 57812 (0.0009) -[2023-10-16 05:03:39,133][05219] Updated weights for policy 1, policy_version 57610 (0.0009) -[2023-10-16 05:03:39,356][05218] Updated weights for policy 0, policy_version 57822 (0.0008) -[2023-10-16 05:03:39,496][05219] Updated weights for policy 1, policy_version 57620 (0.0008) -[2023-10-16 05:03:39,864][05219] Updated weights for policy 1, policy_version 57630 (0.0009) -[2023-10-16 05:03:42,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 118226944. Throughput: 0: 1778.3, 1: 1771.1. Samples: 29563726. Policy #0 lag: (min: 15.0, avg: 15.1, max: 20.0) -[2023-10-16 05:03:42,352][03835] Avg episode reward: [(0, '6.120'), (1, '7.820')] -[2023-10-16 05:03:43,140][05218] Updated weights for policy 0, policy_version 57832 (0.0010) -[2023-10-16 05:03:43,511][05219] Updated weights for policy 1, policy_version 57640 (0.0008) -[2023-10-16 05:03:43,520][05218] Updated weights for policy 0, policy_version 57842 (0.0007) -[2023-10-16 05:03:43,875][05219] Updated weights for policy 1, policy_version 57650 (0.0008) -[2023-10-16 05:03:43,894][05218] Updated weights for policy 0, policy_version 57852 (0.0007) -[2023-10-16 05:03:44,235][05219] Updated weights for policy 1, policy_version 57660 (0.0010) -[2023-10-16 05:03:47,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 118292480. Throughput: 0: 1785.1, 1: 1770.3. Samples: 29586090. Policy #0 lag: (min: 15.0, avg: 15.1, max: 20.0) -[2023-10-16 05:03:47,351][03835] Avg episode reward: [(0, '6.310'), (1, '6.780')] -[2023-10-16 05:03:47,732][05218] Updated weights for policy 0, policy_version 57862 (0.0008) -[2023-10-16 05:03:48,020][05219] Updated weights for policy 1, policy_version 57670 (0.0009) -[2023-10-16 05:03:48,107][05218] Updated weights for policy 0, policy_version 57872 (0.0009) -[2023-10-16 05:03:48,383][05219] Updated weights for policy 1, policy_version 57680 (0.0008) -[2023-10-16 05:03:48,475][05218] Updated weights for policy 0, policy_version 57882 (0.0009) -[2023-10-16 05:03:48,748][05219] Updated weights for policy 1, policy_version 57690 (0.0008) -[2023-10-16 05:03:52,295][05218] Updated weights for policy 0, policy_version 57892 (0.0008) -[2023-10-16 05:03:52,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 118358016. Throughput: 0: 1813.3, 1: 1785.4. Samples: 29607902. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-16 05:03:52,351][03835] Avg episode reward: [(0, '6.630'), (1, '7.010')] -[2023-10-16 05:03:52,596][05219] Updated weights for policy 1, policy_version 57700 (0.0008) -[2023-10-16 05:03:52,685][05218] Updated weights for policy 0, policy_version 57902 (0.0008) -[2023-10-16 05:03:52,965][05219] Updated weights for policy 1, policy_version 57710 (0.0008) -[2023-10-16 05:03:53,055][05218] Updated weights for policy 0, policy_version 57912 (0.0009) -[2023-10-16 05:03:53,334][05219] Updated weights for policy 1, policy_version 57720 (0.0009) -[2023-10-16 05:03:56,691][05218] Updated weights for policy 0, policy_version 57922 (0.0009) -[2023-10-16 05:03:57,061][05218] Updated weights for policy 0, policy_version 57932 (0.0010) -[2023-10-16 05:03:57,142][05219] Updated weights for policy 1, policy_version 57730 (0.0008) -[2023-10-16 05:03:57,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 118423552. Throughput: 0: 1787.1, 1: 1769.2. Samples: 29617900. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-16 05:03:57,351][03835] Avg episode reward: [(0, '6.860'), (1, '7.480')] -[2023-10-16 05:03:57,437][05218] Updated weights for policy 0, policy_version 57942 (0.0009) -[2023-10-16 05:03:57,541][05219] Updated weights for policy 1, policy_version 57740 (0.0007) -[2023-10-16 05:03:57,815][05218] Updated weights for policy 0, policy_version 57952 (0.0008) -[2023-10-16 05:03:57,905][05219] Updated weights for policy 1, policy_version 57750 (0.0007) -[2023-10-16 05:03:58,268][05219] Updated weights for policy 1, policy_version 57760 (0.0009) -[2023-10-16 05:04:01,650][05218] Updated weights for policy 0, policy_version 57962 (0.0008) -[2023-10-16 05:04:02,031][05218] Updated weights for policy 0, policy_version 57972 (0.0009) -[2023-10-16 05:04:02,091][05219] Updated weights for policy 1, policy_version 57770 (0.0007) -[2023-10-16 05:04:02,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 118489088. Throughput: 0: 1810.6, 1: 1774.2. Samples: 29639748. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-16 05:04:02,351][03835] Avg episode reward: [(0, '6.230'), (1, '7.160')] -[2023-10-16 05:04:02,402][05218] Updated weights for policy 0, policy_version 57982 (0.0010) -[2023-10-16 05:04:02,465][05219] Updated weights for policy 1, policy_version 57780 (0.0008) -[2023-10-16 05:04:02,830][05219] Updated weights for policy 1, policy_version 57790 (0.0010) -[2023-10-16 05:04:06,121][05218] Updated weights for policy 0, policy_version 57992 (0.0010) -[2023-10-16 05:04:06,484][05218] Updated weights for policy 0, policy_version 58002 (0.0009) -[2023-10-16 05:04:06,702][05219] Updated weights for policy 1, policy_version 57800 (0.0007) -[2023-10-16 05:04:06,862][05218] Updated weights for policy 0, policy_version 58012 (0.0008) -[2023-10-16 05:04:07,066][05219] Updated weights for policy 1, policy_version 57810 (0.0007) -[2023-10-16 05:04:07,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 118587392. Throughput: 0: 1787.3, 1: 1779.5. Samples: 29659972. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-16 05:04:07,351][03835] Avg episode reward: [(0, '6.490'), (1, '6.990')] -[2023-10-16 05:04:07,439][05219] Updated weights for policy 1, policy_version 57820 (0.0007) -[2023-10-16 05:04:10,545][05218] Updated weights for policy 0, policy_version 58022 (0.0007) -[2023-10-16 05:04:10,925][05218] Updated weights for policy 0, policy_version 58032 (0.0010) -[2023-10-16 05:04:11,304][05218] Updated weights for policy 0, policy_version 58042 (0.0009) -[2023-10-16 05:04:11,343][05219] Updated weights for policy 1, policy_version 57830 (0.0008) -[2023-10-16 05:04:11,702][05219] Updated weights for policy 1, policy_version 57840 (0.0009) -[2023-10-16 05:04:12,065][05219] Updated weights for policy 1, policy_version 57850 (0.0008) -[2023-10-16 05:04:12,350][03835] Fps is (10 sec: 19660.3, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 118685696. Throughput: 0: 1807.1, 1: 1771.4. Samples: 29672040. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-16 05:04:12,352][03835] Avg episode reward: [(0, '6.440'), (1, '6.900')] -[2023-10-16 05:04:15,072][05218] Updated weights for policy 0, policy_version 58052 (0.0009) -[2023-10-16 05:04:15,447][05218] Updated weights for policy 0, policy_version 58062 (0.0008) -[2023-10-16 05:04:15,746][05219] Updated weights for policy 1, policy_version 57860 (0.0008) -[2023-10-16 05:04:15,816][05218] Updated weights for policy 0, policy_version 58072 (0.0009) -[2023-10-16 05:04:16,109][05219] Updated weights for policy 1, policy_version 57870 (0.0008) -[2023-10-16 05:04:16,481][05219] Updated weights for policy 1, policy_version 57880 (0.0007) -[2023-10-16 05:04:17,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 118751232. Throughput: 0: 1785.6, 1: 1783.7. Samples: 29692216. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-16 05:04:17,351][03835] Avg episode reward: [(0, '6.440'), (1, '7.360')] -[2023-10-16 05:04:19,664][05218] Updated weights for policy 0, policy_version 58082 (0.0009) -[2023-10-16 05:04:20,044][05218] Updated weights for policy 0, policy_version 58092 (0.0010) -[2023-10-16 05:04:20,175][05219] Updated weights for policy 1, policy_version 57890 (0.0008) -[2023-10-16 05:04:20,425][05218] Updated weights for policy 0, policy_version 58102 (0.0008) -[2023-10-16 05:04:20,545][05219] Updated weights for policy 1, policy_version 57900 (0.0008) -[2023-10-16 05:04:20,802][05218] Updated weights for policy 0, policy_version 58112 (0.0008) -[2023-10-16 05:04:20,911][05219] Updated weights for policy 1, policy_version 57910 (0.0009) -[2023-10-16 05:04:21,283][05219] Updated weights for policy 1, policy_version 57920 (0.0010) -[2023-10-16 05:04:22,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 118816768. Throughput: 0: 1785.5, 1: 1764.4. Samples: 29713596. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-16 05:04:22,351][03835] Avg episode reward: [(0, '6.020'), (1, '7.090')] -[2023-10-16 05:04:24,523][05218] Updated weights for policy 0, policy_version 58122 (0.0009) -[2023-10-16 05:04:24,900][05218] Updated weights for policy 0, policy_version 58132 (0.0008) -[2023-10-16 05:04:25,153][05219] Updated weights for policy 1, policy_version 57930 (0.0008) -[2023-10-16 05:04:25,270][05218] Updated weights for policy 0, policy_version 58142 (0.0008) -[2023-10-16 05:04:25,516][05219] Updated weights for policy 1, policy_version 57940 (0.0009) -[2023-10-16 05:04:25,897][05219] Updated weights for policy 1, policy_version 57950 (0.0010) -[2023-10-16 05:04:27,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 118882304. Throughput: 0: 1781.0, 1: 1788.5. Samples: 29724356. Policy #0 lag: (min: 19.0, avg: 45.1, max: 48.0) -[2023-10-16 05:04:27,351][03835] Avg episode reward: [(0, '6.580'), (1, '7.640')] -[2023-10-16 05:04:29,037][05218] Updated weights for policy 0, policy_version 58152 (0.0007) -[2023-10-16 05:04:29,412][05218] Updated weights for policy 0, policy_version 58162 (0.0008) -[2023-10-16 05:04:29,631][05219] Updated weights for policy 1, policy_version 57960 (0.0009) -[2023-10-16 05:04:29,788][05218] Updated weights for policy 0, policy_version 58172 (0.0009) -[2023-10-16 05:04:29,994][05219] Updated weights for policy 1, policy_version 57970 (0.0007) -[2023-10-16 05:04:30,364][05219] Updated weights for policy 1, policy_version 57980 (0.0010) -[2023-10-16 05:04:32,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 118947840. Throughput: 0: 1781.6, 1: 1760.5. Samples: 29745486. Policy #0 lag: (min: 19.0, avg: 45.1, max: 48.0) -[2023-10-16 05:04:32,351][03835] Avg episode reward: [(0, '6.590'), (1, '8.190')] -[2023-10-16 05:04:33,422][05218] Updated weights for policy 0, policy_version 58182 (0.0011) -[2023-10-16 05:04:33,791][05218] Updated weights for policy 0, policy_version 58192 (0.0008) -[2023-10-16 05:04:34,165][05218] Updated weights for policy 0, policy_version 58202 (0.0008) -[2023-10-16 05:04:34,234][05219] Updated weights for policy 1, policy_version 57990 (0.0009) -[2023-10-16 05:04:34,601][05219] Updated weights for policy 1, policy_version 58000 (0.0007) -[2023-10-16 05:04:34,958][05219] Updated weights for policy 1, policy_version 58010 (0.0007) -[2023-10-16 05:04:37,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 119013376. Throughput: 0: 1792.5, 1: 1763.3. Samples: 29767916. Policy #0 lag: (min: 19.0, avg: 45.1, max: 48.0) -[2023-10-16 05:04:37,351][03835] Avg episode reward: [(0, '6.790'), (1, '6.840')] -[2023-10-16 05:04:37,904][05218] Updated weights for policy 0, policy_version 58212 (0.0008) -[2023-10-16 05:04:38,296][05218] Updated weights for policy 0, policy_version 58222 (0.0008) -[2023-10-16 05:04:38,676][05218] Updated weights for policy 0, policy_version 58232 (0.0008) -[2023-10-16 05:04:38,685][05219] Updated weights for policy 1, policy_version 58020 (0.0008) -[2023-10-16 05:04:39,051][05219] Updated weights for policy 1, policy_version 58030 (0.0009) -[2023-10-16 05:04:39,410][05219] Updated weights for policy 1, policy_version 58040 (0.0008) -[2023-10-16 05:04:42,326][05218] Updated weights for policy 0, policy_version 58242 (0.0009) -[2023-10-16 05:04:42,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.6, 300 sec: 14218.0). Total num frames: 119078912. Throughput: 0: 1787.1, 1: 1767.7. Samples: 29777868. Policy #0 lag: (min: 19.0, avg: 45.1, max: 48.0) -[2023-10-16 05:04:42,351][03835] Avg episode reward: [(0, '6.750'), (1, '6.250')] -[2023-10-16 05:04:42,704][05218] Updated weights for policy 0, policy_version 58252 (0.0009) -[2023-10-16 05:04:43,082][05218] Updated weights for policy 0, policy_version 58262 (0.0007) -[2023-10-16 05:04:43,151][05219] Updated weights for policy 1, policy_version 58050 (0.0009) -[2023-10-16 05:04:43,457][05218] Updated weights for policy 0, policy_version 58272 (0.0007) -[2023-10-16 05:04:43,514][05219] Updated weights for policy 1, policy_version 58060 (0.0008) -[2023-10-16 05:04:43,877][05219] Updated weights for policy 1, policy_version 58070 (0.0008) -[2023-10-16 05:04:44,238][05219] Updated weights for policy 1, policy_version 58080 (0.0007) -[2023-10-16 05:04:47,176][05218] Updated weights for policy 0, policy_version 58282 (0.0007) -[2023-10-16 05:04:47,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 119144448. Throughput: 0: 1786.3, 1: 1775.2. Samples: 29800014. Policy #0 lag: (min: 19.0, avg: 45.1, max: 48.0) -[2023-10-16 05:04:47,351][03835] Avg episode reward: [(0, '6.670'), (1, '7.470')] -[2023-10-16 05:04:47,556][05218] Updated weights for policy 0, policy_version 58292 (0.0008) -[2023-10-16 05:04:47,935][05218] Updated weights for policy 0, policy_version 58302 (0.0008) -[2023-10-16 05:04:48,061][05219] Updated weights for policy 1, policy_version 58090 (0.0008) -[2023-10-16 05:04:48,428][05219] Updated weights for policy 1, policy_version 58100 (0.0012) -[2023-10-16 05:04:48,786][05219] Updated weights for policy 1, policy_version 58110 (0.0011) -[2023-10-16 05:04:51,755][05218] Updated weights for policy 0, policy_version 58312 (0.0007) -[2023-10-16 05:04:52,123][05218] Updated weights for policy 0, policy_version 58322 (0.0008) -[2023-10-16 05:04:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 119209984. Throughput: 0: 1794.9, 1: 1792.6. Samples: 29821410. Policy #0 lag: (min: 19.0, avg: 45.1, max: 48.0) -[2023-10-16 05:04:52,351][03835] Avg episode reward: [(0, '6.090'), (1, '6.780')] -[2023-10-16 05:04:52,488][05218] Updated weights for policy 0, policy_version 58332 (0.0008) -[2023-10-16 05:04:52,547][05219] Updated weights for policy 1, policy_version 58120 (0.0007) -[2023-10-16 05:04:52,915][05219] Updated weights for policy 1, policy_version 58130 (0.0007) -[2023-10-16 05:04:53,278][05219] Updated weights for policy 1, policy_version 58140 (0.0008) -[2023-10-16 05:04:56,252][05218] Updated weights for policy 0, policy_version 58342 (0.0009) -[2023-10-16 05:04:56,630][05218] Updated weights for policy 0, policy_version 58352 (0.0010) -[2023-10-16 05:04:57,006][05218] Updated weights for policy 0, policy_version 58362 (0.0008) -[2023-10-16 05:04:57,093][05219] Updated weights for policy 1, policy_version 58150 (0.0007) -[2023-10-16 05:04:57,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 119308288. Throughput: 0: 1783.2, 1: 1778.0. Samples: 29832292. Policy #0 lag: (min: 19.0, avg: 45.1, max: 48.0) -[2023-10-16 05:04:57,351][03835] Avg episode reward: [(0, '6.040'), (1, '6.920')] -[2023-10-16 05:04:57,460][05219] Updated weights for policy 1, policy_version 58160 (0.0009) -[2023-10-16 05:04:57,827][05219] Updated weights for policy 1, policy_version 58170 (0.0008) -[2023-10-16 05:05:00,672][05218] Updated weights for policy 0, policy_version 58372 (0.0007) -[2023-10-16 05:05:01,050][05218] Updated weights for policy 0, policy_version 58382 (0.0008) -[2023-10-16 05:05:01,416][05218] Updated weights for policy 0, policy_version 58392 (0.0007) -[2023-10-16 05:05:01,615][05219] Updated weights for policy 1, policy_version 58180 (0.0009) -[2023-10-16 05:05:01,977][05219] Updated weights for policy 1, policy_version 58190 (0.0009) -[2023-10-16 05:05:02,346][05219] Updated weights for policy 1, policy_version 58200 (0.0008) -[2023-10-16 05:05:02,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 119373824. Throughput: 0: 1790.7, 1: 1796.1. Samples: 29853622. Policy #0 lag: (min: 19.0, avg: 45.1, max: 48.0) -[2023-10-16 05:05:02,351][03835] Avg episode reward: [(0, '6.560'), (1, '7.640')] -[2023-10-16 05:05:05,176][05218] Updated weights for policy 0, policy_version 58402 (0.0008) -[2023-10-16 05:05:05,557][05218] Updated weights for policy 0, policy_version 58412 (0.0010) -[2023-10-16 05:05:05,931][05218] Updated weights for policy 0, policy_version 58422 (0.0008) -[2023-10-16 05:05:06,056][05219] Updated weights for policy 1, policy_version 58210 (0.0008) -[2023-10-16 05:05:06,306][05218] Updated weights for policy 0, policy_version 58432 (0.0008) -[2023-10-16 05:05:06,410][05219] Updated weights for policy 1, policy_version 58220 (0.0008) -[2023-10-16 05:05:06,787][05219] Updated weights for policy 1, policy_version 58230 (0.0007) -[2023-10-16 05:05:07,145][05219] Updated weights for policy 1, policy_version 58240 (0.0011) -[2023-10-16 05:05:07,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 119472128. Throughput: 0: 1776.9, 1: 1787.2. Samples: 29873982. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-16 05:05:07,351][03835] Avg episode reward: [(0, '6.700'), (1, '7.140')] -[2023-10-16 05:05:10,148][05218] Updated weights for policy 0, policy_version 58442 (0.0008) -[2023-10-16 05:05:10,521][05218] Updated weights for policy 0, policy_version 58452 (0.0008) -[2023-10-16 05:05:10,894][05218] Updated weights for policy 0, policy_version 58462 (0.0008) -[2023-10-16 05:05:10,997][05219] Updated weights for policy 1, policy_version 58250 (0.0010) -[2023-10-16 05:05:11,361][05219] Updated weights for policy 1, policy_version 58260 (0.0007) -[2023-10-16 05:05:11,718][05219] Updated weights for policy 1, policy_version 58270 (0.0007) -[2023-10-16 05:05:12,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 119537664. Throughput: 0: 1796.1, 1: 1792.6. Samples: 29885848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-16 05:05:12,351][03835] Avg episode reward: [(0, '7.030'), (1, '6.480')] -[2023-10-16 05:05:14,671][05218] Updated weights for policy 0, policy_version 58472 (0.0009) -[2023-10-16 05:05:15,043][05218] Updated weights for policy 0, policy_version 58482 (0.0009) -[2023-10-16 05:05:15,424][05218] Updated weights for policy 0, policy_version 58492 (0.0009) -[2023-10-16 05:05:15,592][05219] Updated weights for policy 1, policy_version 58280 (0.0009) -[2023-10-16 05:05:15,969][05219] Updated weights for policy 1, policy_version 58290 (0.0009) -[2023-10-16 05:05:16,333][05219] Updated weights for policy 1, policy_version 58300 (0.0007) -[2023-10-16 05:05:17,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 119603200. Throughput: 0: 1785.8, 1: 1799.5. Samples: 29906824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-16 05:05:17,351][03835] Avg episode reward: [(0, '6.560'), (1, '7.500')] -[2023-10-16 05:05:19,146][05218] Updated weights for policy 0, policy_version 58502 (0.0008) -[2023-10-16 05:05:19,521][05218] Updated weights for policy 0, policy_version 58512 (0.0007) -[2023-10-16 05:05:19,905][05218] Updated weights for policy 0, policy_version 58522 (0.0009) -[2023-10-16 05:05:20,094][05219] Updated weights for policy 1, policy_version 58310 (0.0007) -[2023-10-16 05:05:20,460][05219] Updated weights for policy 1, policy_version 58320 (0.0008) -[2023-10-16 05:05:20,829][05219] Updated weights for policy 1, policy_version 58330 (0.0011) -[2023-10-16 05:05:22,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 119668736. Throughput: 0: 1787.2, 1: 1790.9. Samples: 29928928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-16 05:05:22,351][03835] Avg episode reward: [(0, '6.830'), (1, '7.420')] -[2023-10-16 05:05:23,609][05218] Updated weights for policy 0, policy_version 58532 (0.0008) -[2023-10-16 05:05:23,991][05218] Updated weights for policy 0, policy_version 58542 (0.0011) -[2023-10-16 05:05:24,374][05218] Updated weights for policy 0, policy_version 58552 (0.0009) -[2023-10-16 05:05:24,529][05219] Updated weights for policy 1, policy_version 58340 (0.0008) -[2023-10-16 05:05:24,897][05219] Updated weights for policy 1, policy_version 58350 (0.0008) -[2023-10-16 05:05:25,257][05219] Updated weights for policy 1, policy_version 58360 (0.0007) -[2023-10-16 05:05:27,351][03835] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 119734272. Throughput: 0: 1783.8, 1: 1798.9. Samples: 29939090. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-16 05:05:27,352][03835] Avg episode reward: [(0, '6.750'), (1, '7.480')] -[2023-10-16 05:05:27,910][05218] Updated weights for policy 0, policy_version 58562 (0.0009) -[2023-10-16 05:05:28,280][05218] Updated weights for policy 0, policy_version 58572 (0.0010) -[2023-10-16 05:05:28,664][05218] Updated weights for policy 0, policy_version 58582 (0.0007) -[2023-10-16 05:05:28,987][05219] Updated weights for policy 1, policy_version 58370 (0.0008) -[2023-10-16 05:05:29,031][05218] Updated weights for policy 0, policy_version 58592 (0.0008) -[2023-10-16 05:05:29,359][05219] Updated weights for policy 1, policy_version 58380 (0.0010) -[2023-10-16 05:05:29,723][05219] Updated weights for policy 1, policy_version 58390 (0.0008) -[2023-10-16 05:05:30,083][05219] Updated weights for policy 1, policy_version 58400 (0.0009) -[2023-10-16 05:05:32,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 119799808. Throughput: 0: 1796.2, 1: 1787.9. Samples: 29961296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-16 05:05:32,351][03835] Avg episode reward: [(0, '6.600'), (1, '7.110')] -[2023-10-16 05:05:32,684][05218] Updated weights for policy 0, policy_version 58602 (0.0007) -[2023-10-16 05:05:33,055][05218] Updated weights for policy 0, policy_version 58612 (0.0008) -[2023-10-16 05:05:33,434][05218] Updated weights for policy 0, policy_version 58622 (0.0009) -[2023-10-16 05:05:33,916][05219] Updated weights for policy 1, policy_version 58410 (0.0007) -[2023-10-16 05:05:34,281][05219] Updated weights for policy 1, policy_version 58420 (0.0008) -[2023-10-16 05:05:34,654][05219] Updated weights for policy 1, policy_version 58430 (0.0009) -[2023-10-16 05:05:37,202][05218] Updated weights for policy 0, policy_version 58632 (0.0009) -[2023-10-16 05:05:37,351][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 119865344. Throughput: 0: 1811.4, 1: 1786.7. Samples: 29983328. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-16 05:05:37,352][03835] Avg episode reward: [(0, '5.970'), (1, '7.330')] -[2023-10-16 05:05:37,364][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000058432_59834368.pth... -[2023-10-16 05:05:37,405][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000056768_58130432.pth -[2023-10-16 05:05:37,409][04891] Saving a milestone ./train_atari/atari_timepilot_APPO/checkpoint_p1/milestones/checkpoint_000058432_59834368.pth -[2023-10-16 05:05:37,571][05218] Updated weights for policy 0, policy_version 58642 (0.0009) -[2023-10-16 05:05:37,960][05218] Updated weights for policy 0, policy_version 58652 (0.0008) -[2023-10-16 05:05:38,101][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000058656_60063744.pth... -[2023-10-16 05:05:38,129][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000056960_58327040.pth -[2023-10-16 05:05:38,133][04766] Saving a milestone ./train_atari/atari_timepilot_APPO/checkpoint_p0/milestones/checkpoint_000058656_60063744.pth -[2023-10-16 05:05:38,220][05219] Updated weights for policy 1, policy_version 58440 (0.0008) -[2023-10-16 05:05:38,591][05219] Updated weights for policy 1, policy_version 58450 (0.0009) -[2023-10-16 05:05:38,959][05219] Updated weights for policy 1, policy_version 58460 (0.0009) -[2023-10-16 05:05:41,784][05218] Updated weights for policy 0, policy_version 58662 (0.0007) -[2023-10-16 05:05:42,168][05218] Updated weights for policy 0, policy_version 58672 (0.0008) -[2023-10-16 05:05:42,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 119930880. Throughput: 0: 1802.5, 1: 1783.5. Samples: 29993662. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-16 05:05:42,351][03835] Avg episode reward: [(0, '7.290'), (1, '7.920')] -[2023-10-16 05:05:42,541][05218] Updated weights for policy 0, policy_version 58682 (0.0008) -[2023-10-16 05:05:42,778][05219] Updated weights for policy 1, policy_version 58470 (0.0009) -[2023-10-16 05:05:43,133][05219] Updated weights for policy 1, policy_version 58480 (0.0008) -[2023-10-16 05:05:43,485][05219] Updated weights for policy 1, policy_version 58490 (0.0009) -[2023-10-16 05:05:46,200][05218] Updated weights for policy 0, policy_version 58692 (0.0010) -[2023-10-16 05:05:46,573][05218] Updated weights for policy 0, policy_version 58702 (0.0011) -[2023-10-16 05:05:46,953][05218] Updated weights for policy 0, policy_version 58712 (0.0008) -[2023-10-16 05:05:47,245][05219] Updated weights for policy 1, policy_version 58500 (0.0008) -[2023-10-16 05:05:47,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 120029184. Throughput: 0: 1818.6, 1: 1778.6. Samples: 30015494. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:05:47,351][03835] Avg episode reward: [(0, '6.910'), (1, '6.860')] -[2023-10-16 05:05:47,616][05219] Updated weights for policy 1, policy_version 58510 (0.0008) -[2023-10-16 05:05:47,978][05219] Updated weights for policy 1, policy_version 58520 (0.0008) -[2023-10-16 05:05:50,613][05218] Updated weights for policy 0, policy_version 58722 (0.0009) -[2023-10-16 05:05:50,973][05218] Updated weights for policy 0, policy_version 58732 (0.0010) -[2023-10-16 05:05:51,347][05218] Updated weights for policy 0, policy_version 58742 (0.0009) -[2023-10-16 05:05:51,726][05218] Updated weights for policy 0, policy_version 58752 (0.0010) -[2023-10-16 05:05:51,943][05219] Updated weights for policy 1, policy_version 58530 (0.0008) -[2023-10-16 05:05:52,310][05219] Updated weights for policy 1, policy_version 58540 (0.0010) -[2023-10-16 05:05:52,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 120094720. Throughput: 0: 1810.0, 1: 1799.4. Samples: 30036404. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:05:52,351][03835] Avg episode reward: [(0, '6.570'), (1, '7.220')] -[2023-10-16 05:05:52,669][05219] Updated weights for policy 1, policy_version 58550 (0.0008) -[2023-10-16 05:05:53,045][05219] Updated weights for policy 1, policy_version 58560 (0.0010) -[2023-10-16 05:05:55,436][05218] Updated weights for policy 0, policy_version 58762 (0.0009) -[2023-10-16 05:05:55,807][05218] Updated weights for policy 0, policy_version 58772 (0.0007) -[2023-10-16 05:05:56,177][05218] Updated weights for policy 0, policy_version 58782 (0.0010) -[2023-10-16 05:05:56,927][05219] Updated weights for policy 1, policy_version 58570 (0.0008) -[2023-10-16 05:05:57,306][05219] Updated weights for policy 1, policy_version 58580 (0.0008) -[2023-10-16 05:05:57,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 120160256. Throughput: 0: 1820.5, 1: 1774.6. Samples: 30047626. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:05:57,351][03835] Avg episode reward: [(0, '7.060'), (1, '7.290')] -[2023-10-16 05:05:57,675][05219] Updated weights for policy 1, policy_version 58590 (0.0008) -[2023-10-16 05:05:59,880][05218] Updated weights for policy 0, policy_version 58792 (0.0009) -[2023-10-16 05:06:00,252][05218] Updated weights for policy 0, policy_version 58802 (0.0007) -[2023-10-16 05:06:00,618][05218] Updated weights for policy 0, policy_version 58812 (0.0009) -[2023-10-16 05:06:01,521][05219] Updated weights for policy 1, policy_version 58600 (0.0010) -[2023-10-16 05:06:01,872][05219] Updated weights for policy 1, policy_version 58610 (0.0008) -[2023-10-16 05:06:02,232][05219] Updated weights for policy 1, policy_version 58620 (0.0008) -[2023-10-16 05:06:02,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 120225792. Throughput: 0: 1804.0, 1: 1797.7. Samples: 30068904. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:06:02,351][03835] Avg episode reward: [(0, '6.340'), (1, '6.250')] -[2023-10-16 05:06:04,358][05218] Updated weights for policy 0, policy_version 58822 (0.0008) -[2023-10-16 05:06:04,740][05218] Updated weights for policy 0, policy_version 58832 (0.0009) -[2023-10-16 05:06:05,118][05218] Updated weights for policy 0, policy_version 58842 (0.0007) -[2023-10-16 05:06:05,960][05219] Updated weights for policy 1, policy_version 58630 (0.0009) -[2023-10-16 05:06:06,328][05219] Updated weights for policy 1, policy_version 58640 (0.0009) -[2023-10-16 05:06:06,697][05219] Updated weights for policy 1, policy_version 58650 (0.0008) -[2023-10-16 05:06:07,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 120324096. Throughput: 0: 1806.5, 1: 1776.0. Samples: 30090142. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:06:07,351][03835] Avg episode reward: [(0, '7.130'), (1, '7.120')] -[2023-10-16 05:06:08,832][05218] Updated weights for policy 0, policy_version 58852 (0.0008) -[2023-10-16 05:06:09,214][05218] Updated weights for policy 0, policy_version 58862 (0.0010) -[2023-10-16 05:06:09,587][05218] Updated weights for policy 0, policy_version 58872 (0.0007) -[2023-10-16 05:06:10,316][05219] Updated weights for policy 1, policy_version 58660 (0.0009) -[2023-10-16 05:06:10,677][05219] Updated weights for policy 1, policy_version 58670 (0.0010) -[2023-10-16 05:06:11,055][05219] Updated weights for policy 1, policy_version 58680 (0.0010) -[2023-10-16 05:06:12,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 120389632. Throughput: 0: 1807.4, 1: 1802.2. Samples: 30101524. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:06:12,351][03835] Avg episode reward: [(0, '7.010'), (1, '6.910')] -[2023-10-16 05:06:13,340][05218] Updated weights for policy 0, policy_version 58882 (0.0009) -[2023-10-16 05:06:13,711][05218] Updated weights for policy 0, policy_version 58892 (0.0009) -[2023-10-16 05:06:14,083][05218] Updated weights for policy 0, policy_version 58902 (0.0011) -[2023-10-16 05:06:14,469][05218] Updated weights for policy 0, policy_version 58912 (0.0010) -[2023-10-16 05:06:14,855][05219] Updated weights for policy 1, policy_version 58690 (0.0009) -[2023-10-16 05:06:15,214][05219] Updated weights for policy 1, policy_version 58700 (0.0010) -[2023-10-16 05:06:15,576][05219] Updated weights for policy 1, policy_version 58710 (0.0009) -[2023-10-16 05:06:15,942][05219] Updated weights for policy 1, policy_version 58720 (0.0010) -[2023-10-16 05:06:17,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 120455168. Throughput: 0: 1799.7, 1: 1782.1. Samples: 30122480. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:06:17,351][03835] Avg episode reward: [(0, '6.710'), (1, '7.790')] -[2023-10-16 05:06:18,317][05218] Updated weights for policy 0, policy_version 58922 (0.0010) -[2023-10-16 05:06:18,687][05218] Updated weights for policy 0, policy_version 58932 (0.0011) -[2023-10-16 05:06:19,066][05218] Updated weights for policy 0, policy_version 58942 (0.0009) -[2023-10-16 05:06:19,675][05219] Updated weights for policy 1, policy_version 58730 (0.0007) -[2023-10-16 05:06:20,044][05219] Updated weights for policy 1, policy_version 58740 (0.0007) -[2023-10-16 05:06:20,413][05219] Updated weights for policy 1, policy_version 58750 (0.0009) -[2023-10-16 05:06:22,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 120520704. Throughput: 0: 1814.6, 1: 1784.8. Samples: 30145298. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:06:22,352][03835] Avg episode reward: [(0, '6.670'), (1, '7.820')] -[2023-10-16 05:06:22,687][05218] Updated weights for policy 0, policy_version 58952 (0.0008) -[2023-10-16 05:06:23,069][05218] Updated weights for policy 0, policy_version 58962 (0.0008) -[2023-10-16 05:06:23,451][05218] Updated weights for policy 0, policy_version 58972 (0.0011) -[2023-10-16 05:06:24,001][05219] Updated weights for policy 1, policy_version 58760 (0.0009) -[2023-10-16 05:06:24,373][05219] Updated weights for policy 1, policy_version 58770 (0.0008) -[2023-10-16 05:06:24,750][05219] Updated weights for policy 1, policy_version 58780 (0.0007) -[2023-10-16 05:06:27,170][05218] Updated weights for policy 0, policy_version 58982 (0.0009) -[2023-10-16 05:06:27,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 120586240. Throughput: 0: 1803.0, 1: 1787.4. Samples: 30155228. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-16 05:06:27,352][03835] Avg episode reward: [(0, '6.760'), (1, '7.610')] -[2023-10-16 05:06:27,539][05218] Updated weights for policy 0, policy_version 58992 (0.0007) -[2023-10-16 05:06:27,921][05218] Updated weights for policy 0, policy_version 59002 (0.0008) -[2023-10-16 05:06:28,421][05219] Updated weights for policy 1, policy_version 58790 (0.0008) -[2023-10-16 05:06:28,787][05219] Updated weights for policy 1, policy_version 58800 (0.0008) -[2023-10-16 05:06:29,154][05219] Updated weights for policy 1, policy_version 58810 (0.0008) -[2023-10-16 05:06:31,681][05218] Updated weights for policy 0, policy_version 59012 (0.0009) -[2023-10-16 05:06:32,074][05218] Updated weights for policy 0, policy_version 59022 (0.0008) -[2023-10-16 05:06:32,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 120651776. Throughput: 0: 1809.7, 1: 1795.6. Samples: 30177730. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-16 05:06:32,351][03835] Avg episode reward: [(0, '6.740'), (1, '8.210')] -[2023-10-16 05:06:32,445][05218] Updated weights for policy 0, policy_version 59032 (0.0008) -[2023-10-16 05:06:32,792][05219] Updated weights for policy 1, policy_version 58820 (0.0009) -[2023-10-16 05:06:33,155][05219] Updated weights for policy 1, policy_version 58830 (0.0007) -[2023-10-16 05:06:33,520][05219] Updated weights for policy 1, policy_version 58840 (0.0010) -[2023-10-16 05:06:36,216][05218] Updated weights for policy 0, policy_version 59042 (0.0008) -[2023-10-16 05:06:36,588][05218] Updated weights for policy 0, policy_version 59052 (0.0007) -[2023-10-16 05:06:36,977][05218] Updated weights for policy 0, policy_version 59062 (0.0007) -[2023-10-16 05:06:37,309][05219] Updated weights for policy 1, policy_version 58850 (0.0010) -[2023-10-16 05:06:37,351][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 120750080. Throughput: 0: 1797.6, 1: 1809.9. Samples: 30198742. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-16 05:06:37,351][05218] Updated weights for policy 0, policy_version 59072 (0.0009) -[2023-10-16 05:06:37,351][03835] Avg episode reward: [(0, '6.330'), (1, '7.330')] -[2023-10-16 05:06:37,668][05219] Updated weights for policy 1, policy_version 58860 (0.0009) -[2023-10-16 05:06:38,028][05219] Updated weights for policy 1, policy_version 58870 (0.0010) -[2023-10-16 05:06:38,396][05219] Updated weights for policy 1, policy_version 58880 (0.0010) -[2023-10-16 05:06:40,977][05218] Updated weights for policy 0, policy_version 59082 (0.0009) -[2023-10-16 05:06:41,350][05218] Updated weights for policy 0, policy_version 59092 (0.0010) -[2023-10-16 05:06:41,732][05218] Updated weights for policy 0, policy_version 59102 (0.0009) -[2023-10-16 05:06:42,265][05219] Updated weights for policy 1, policy_version 58890 (0.0008) -[2023-10-16 05:06:42,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 120815616. Throughput: 0: 1805.0, 1: 1803.4. Samples: 30210002. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-16 05:06:42,351][03835] Avg episode reward: [(0, '6.470'), (1, '7.730')] -[2023-10-16 05:06:42,632][05219] Updated weights for policy 1, policy_version 58900 (0.0007) -[2023-10-16 05:06:42,993][05219] Updated weights for policy 1, policy_version 58910 (0.0009) -[2023-10-16 05:06:45,434][05218] Updated weights for policy 0, policy_version 59112 (0.0009) -[2023-10-16 05:06:45,816][05218] Updated weights for policy 0, policy_version 59122 (0.0011) -[2023-10-16 05:06:46,192][05218] Updated weights for policy 0, policy_version 59132 (0.0010) -[2023-10-16 05:06:46,905][05219] Updated weights for policy 1, policy_version 58920 (0.0009) -[2023-10-16 05:06:47,271][05219] Updated weights for policy 1, policy_version 58930 (0.0008) -[2023-10-16 05:06:47,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 120881152. Throughput: 0: 1801.2, 1: 1795.4. Samples: 30230754. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-16 05:06:47,351][03835] Avg episode reward: [(0, '6.380'), (1, '8.000')] -[2023-10-16 05:06:47,636][05219] Updated weights for policy 1, policy_version 58940 (0.0009) -[2023-10-16 05:06:49,968][05218] Updated weights for policy 0, policy_version 59142 (0.0010) -[2023-10-16 05:06:50,347][05218] Updated weights for policy 0, policy_version 59152 (0.0010) -[2023-10-16 05:06:50,716][05218] Updated weights for policy 0, policy_version 59162 (0.0010) -[2023-10-16 05:06:51,333][05219] Updated weights for policy 1, policy_version 58950 (0.0010) -[2023-10-16 05:06:51,710][05219] Updated weights for policy 1, policy_version 58960 (0.0009) -[2023-10-16 05:06:52,071][05219] Updated weights for policy 1, policy_version 58970 (0.0009) -[2023-10-16 05:06:52,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 120979456. Throughput: 0: 1798.9, 1: 1802.5. Samples: 30252206. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-16 05:06:52,351][03835] Avg episode reward: [(0, '5.940'), (1, '7.010')] -[2023-10-16 05:06:54,428][05218] Updated weights for policy 0, policy_version 59172 (0.0008) -[2023-10-16 05:06:54,812][05218] Updated weights for policy 0, policy_version 59182 (0.0008) -[2023-10-16 05:06:55,189][05218] Updated weights for policy 0, policy_version 59192 (0.0008) -[2023-10-16 05:06:55,728][05219] Updated weights for policy 1, policy_version 58980 (0.0008) -[2023-10-16 05:06:56,097][05219] Updated weights for policy 1, policy_version 58990 (0.0007) -[2023-10-16 05:06:56,466][05219] Updated weights for policy 1, policy_version 59000 (0.0007) -[2023-10-16 05:06:57,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 121044992. Throughput: 0: 1806.4, 1: 1797.2. Samples: 30263688. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-16 05:06:57,351][03835] Avg episode reward: [(0, '6.490'), (1, '7.240')] -[2023-10-16 05:06:58,775][05218] Updated weights for policy 0, policy_version 59202 (0.0010) -[2023-10-16 05:06:59,151][05218] Updated weights for policy 0, policy_version 59212 (0.0008) -[2023-10-16 05:06:59,528][05218] Updated weights for policy 0, policy_version 59222 (0.0007) -[2023-10-16 05:06:59,902][05218] Updated weights for policy 0, policy_version 59232 (0.0007) -[2023-10-16 05:07:00,215][05219] Updated weights for policy 1, policy_version 59010 (0.0008) -[2023-10-16 05:07:00,577][05219] Updated weights for policy 1, policy_version 59020 (0.0010) -[2023-10-16 05:07:00,951][05219] Updated weights for policy 1, policy_version 59030 (0.0010) -[2023-10-16 05:07:01,310][05219] Updated weights for policy 1, policy_version 59040 (0.0009) -[2023-10-16 05:07:02,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 121110528. Throughput: 0: 1805.0, 1: 1810.2. Samples: 30285164. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-16 05:07:02,351][03835] Avg episode reward: [(0, '7.040'), (1, '7.930')] -[2023-10-16 05:07:03,684][05218] Updated weights for policy 0, policy_version 59242 (0.0007) -[2023-10-16 05:07:04,059][05218] Updated weights for policy 0, policy_version 59252 (0.0007) -[2023-10-16 05:07:04,437][05218] Updated weights for policy 0, policy_version 59262 (0.0007) -[2023-10-16 05:07:05,138][05219] Updated weights for policy 1, policy_version 59050 (0.0009) -[2023-10-16 05:07:05,496][05219] Updated weights for policy 1, policy_version 59060 (0.0009) -[2023-10-16 05:07:05,856][05219] Updated weights for policy 1, policy_version 59070 (0.0007) -[2023-10-16 05:07:07,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 121176064. Throughput: 0: 1800.9, 1: 1798.2. Samples: 30307256. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:07:07,351][03835] Avg episode reward: [(0, '6.160'), (1, '8.080')] -[2023-10-16 05:07:08,055][05218] Updated weights for policy 0, policy_version 59272 (0.0011) -[2023-10-16 05:07:08,436][05218] Updated weights for policy 0, policy_version 59282 (0.0007) -[2023-10-16 05:07:08,813][05218] Updated weights for policy 0, policy_version 59292 (0.0007) -[2023-10-16 05:07:09,566][05219] Updated weights for policy 1, policy_version 59080 (0.0008) -[2023-10-16 05:07:09,946][05219] Updated weights for policy 1, policy_version 59090 (0.0007) -[2023-10-16 05:07:10,301][05219] Updated weights for policy 1, policy_version 59100 (0.0007) -[2023-10-16 05:07:12,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 121241600. Throughput: 0: 1797.4, 1: 1811.3. Samples: 30317620. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:07:12,351][03835] Avg episode reward: [(0, '6.670'), (1, '8.030')] -[2023-10-16 05:07:12,554][05218] Updated weights for policy 0, policy_version 59302 (0.0007) -[2023-10-16 05:07:12,933][05218] Updated weights for policy 0, policy_version 59312 (0.0007) -[2023-10-16 05:07:13,300][05218] Updated weights for policy 0, policy_version 59322 (0.0007) -[2023-10-16 05:07:14,175][05219] Updated weights for policy 1, policy_version 59110 (0.0008) -[2023-10-16 05:07:14,536][05219] Updated weights for policy 1, policy_version 59120 (0.0009) -[2023-10-16 05:07:14,906][05219] Updated weights for policy 1, policy_version 59130 (0.0007) -[2023-10-16 05:07:16,950][05218] Updated weights for policy 0, policy_version 59332 (0.0008) -[2023-10-16 05:07:17,325][05218] Updated weights for policy 0, policy_version 59342 (0.0009) -[2023-10-16 05:07:17,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 121307136. Throughput: 0: 1801.6, 1: 1798.0. Samples: 30339708. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:07:17,351][03835] Avg episode reward: [(0, '6.460'), (1, '7.840')] -[2023-10-16 05:07:17,693][05218] Updated weights for policy 0, policy_version 59352 (0.0009) -[2023-10-16 05:07:18,711][05219] Updated weights for policy 1, policy_version 59140 (0.0007) -[2023-10-16 05:07:19,081][05219] Updated weights for policy 1, policy_version 59150 (0.0009) -[2023-10-16 05:07:19,446][05219] Updated weights for policy 1, policy_version 59160 (0.0009) -[2023-10-16 05:07:21,425][05218] Updated weights for policy 0, policy_version 59362 (0.0009) -[2023-10-16 05:07:21,794][05218] Updated weights for policy 0, policy_version 59372 (0.0010) -[2023-10-16 05:07:22,178][05218] Updated weights for policy 0, policy_version 59382 (0.0008) -[2023-10-16 05:07:22,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 121372672. Throughput: 0: 1810.6, 1: 1793.9. Samples: 30360944. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:07:22,351][03835] Avg episode reward: [(0, '6.370'), (1, '7.980')] -[2023-10-16 05:07:22,545][05218] Updated weights for policy 0, policy_version 59392 (0.0007) -[2023-10-16 05:07:23,166][05219] Updated weights for policy 1, policy_version 59170 (0.0007) -[2023-10-16 05:07:23,528][05219] Updated weights for policy 1, policy_version 59180 (0.0008) -[2023-10-16 05:07:23,889][05219] Updated weights for policy 1, policy_version 59190 (0.0011) -[2023-10-16 05:07:24,253][05219] Updated weights for policy 1, policy_version 59200 (0.0010) -[2023-10-16 05:07:26,336][05218] Updated weights for policy 0, policy_version 59402 (0.0007) -[2023-10-16 05:07:26,707][05218] Updated weights for policy 0, policy_version 59412 (0.0008) -[2023-10-16 05:07:27,084][05218] Updated weights for policy 0, policy_version 59422 (0.0008) -[2023-10-16 05:07:27,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 121470976. Throughput: 0: 1801.2, 1: 1797.2. Samples: 30371930. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:07:27,351][03835] Avg episode reward: [(0, '5.840'), (1, '7.080')] -[2023-10-16 05:07:27,924][05219] Updated weights for policy 1, policy_version 59210 (0.0008) -[2023-10-16 05:07:28,280][05219] Updated weights for policy 1, policy_version 59220 (0.0008) -[2023-10-16 05:07:28,646][05219] Updated weights for policy 1, policy_version 59230 (0.0008) -[2023-10-16 05:07:30,750][05218] Updated weights for policy 0, policy_version 59432 (0.0009) -[2023-10-16 05:07:31,122][05218] Updated weights for policy 0, policy_version 59442 (0.0009) -[2023-10-16 05:07:31,504][05218] Updated weights for policy 0, policy_version 59452 (0.0008) -[2023-10-16 05:07:32,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 121536512. Throughput: 0: 1815.5, 1: 1801.6. Samples: 30393524. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:07:32,351][03835] Avg episode reward: [(0, '6.810'), (1, '7.810')] -[2023-10-16 05:07:32,424][05219] Updated weights for policy 1, policy_version 59240 (0.0009) -[2023-10-16 05:07:32,786][05219] Updated weights for policy 1, policy_version 59250 (0.0008) -[2023-10-16 05:07:33,152][05219] Updated weights for policy 1, policy_version 59260 (0.0009) -[2023-10-16 05:07:35,177][05218] Updated weights for policy 0, policy_version 59462 (0.0008) -[2023-10-16 05:07:35,551][05218] Updated weights for policy 0, policy_version 59472 (0.0009) -[2023-10-16 05:07:35,929][05218] Updated weights for policy 0, policy_version 59482 (0.0011) -[2023-10-16 05:07:37,005][05219] Updated weights for policy 1, policy_version 59270 (0.0008) -[2023-10-16 05:07:37,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 121602048. Throughput: 0: 1808.6, 1: 1815.3. Samples: 30415280. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:07:37,351][03835] Avg episode reward: [(0, '6.700'), (1, '7.150')] -[2023-10-16 05:07:37,360][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000059488_60915712.pth... -[2023-10-16 05:07:37,364][05219] Updated weights for policy 1, policy_version 59280 (0.0008) -[2023-10-16 05:07:37,403][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000057792_59179008.pth -[2023-10-16 05:07:37,730][05219] Updated weights for policy 1, policy_version 59290 (0.0010) -[2023-10-16 05:07:37,942][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000059296_60719104.pth... -[2023-10-16 05:07:37,981][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000057600_58982400.pth -[2023-10-16 05:07:39,688][05218] Updated weights for policy 0, policy_version 59492 (0.0008) -[2023-10-16 05:07:40,070][05218] Updated weights for policy 0, policy_version 59502 (0.0007) -[2023-10-16 05:07:40,449][05218] Updated weights for policy 0, policy_version 59512 (0.0009) -[2023-10-16 05:07:41,428][05219] Updated weights for policy 1, policy_version 59300 (0.0009) -[2023-10-16 05:07:41,792][05219] Updated weights for policy 1, policy_version 59310 (0.0007) -[2023-10-16 05:07:42,159][05219] Updated weights for policy 1, policy_version 59320 (0.0007) -[2023-10-16 05:07:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 121667584. Throughput: 0: 1811.9, 1: 1791.4. Samples: 30425836. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:07:42,352][03835] Avg episode reward: [(0, '6.050'), (1, '8.360')] -[2023-10-16 05:07:44,053][05218] Updated weights for policy 0, policy_version 59522 (0.0011) -[2023-10-16 05:07:44,424][05218] Updated weights for policy 0, policy_version 59532 (0.0009) -[2023-10-16 05:07:44,799][05218] Updated weights for policy 0, policy_version 59542 (0.0008) -[2023-10-16 05:07:45,169][05218] Updated weights for policy 0, policy_version 59552 (0.0009) -[2023-10-16 05:07:45,794][05219] Updated weights for policy 1, policy_version 59330 (0.0008) -[2023-10-16 05:07:46,166][05219] Updated weights for policy 1, policy_version 59340 (0.0008) -[2023-10-16 05:07:46,531][05219] Updated weights for policy 1, policy_version 59350 (0.0009) -[2023-10-16 05:07:46,892][05219] Updated weights for policy 1, policy_version 59360 (0.0009) -[2023-10-16 05:07:47,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 121765888. Throughput: 0: 1804.5, 1: 1803.1. Samples: 30447506. Policy #0 lag: (min: 18.0, avg: 24.4, max: 50.0) -[2023-10-16 05:07:47,351][03835] Avg episode reward: [(0, '6.270'), (1, '7.560')] -[2023-10-16 05:07:48,910][05218] Updated weights for policy 0, policy_version 59562 (0.0009) -[2023-10-16 05:07:49,285][05218] Updated weights for policy 0, policy_version 59572 (0.0008) -[2023-10-16 05:07:49,668][05218] Updated weights for policy 0, policy_version 59582 (0.0009) -[2023-10-16 05:07:50,784][05219] Updated weights for policy 1, policy_version 59370 (0.0008) -[2023-10-16 05:07:51,157][05219] Updated weights for policy 1, policy_version 59380 (0.0007) -[2023-10-16 05:07:51,522][05219] Updated weights for policy 1, policy_version 59390 (0.0009) -[2023-10-16 05:07:52,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 121831424. Throughput: 0: 1806.7, 1: 1782.0. Samples: 30468746. Policy #0 lag: (min: 18.0, avg: 24.4, max: 50.0) -[2023-10-16 05:07:52,351][03835] Avg episode reward: [(0, '6.250'), (1, '7.690')] -[2023-10-16 05:07:53,242][05218] Updated weights for policy 0, policy_version 59592 (0.0008) -[2023-10-16 05:07:53,621][05218] Updated weights for policy 0, policy_version 59602 (0.0009) -[2023-10-16 05:07:53,990][05218] Updated weights for policy 0, policy_version 59612 (0.0008) -[2023-10-16 05:07:55,190][05219] Updated weights for policy 1, policy_version 59400 (0.0009) -[2023-10-16 05:07:55,552][05219] Updated weights for policy 1, policy_version 59410 (0.0008) -[2023-10-16 05:07:55,919][05219] Updated weights for policy 1, policy_version 59420 (0.0009) -[2023-10-16 05:07:57,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 121896960. Throughput: 0: 1810.4, 1: 1798.3. Samples: 30480010. Policy #0 lag: (min: 18.0, avg: 24.4, max: 50.0) -[2023-10-16 05:07:57,351][03835] Avg episode reward: [(0, '6.450'), (1, '7.730')] -[2023-10-16 05:07:57,715][05218] Updated weights for policy 0, policy_version 59622 (0.0007) -[2023-10-16 05:07:58,096][05218] Updated weights for policy 0, policy_version 59632 (0.0008) -[2023-10-16 05:07:58,469][05218] Updated weights for policy 0, policy_version 59642 (0.0010) -[2023-10-16 05:07:59,691][05219] Updated weights for policy 1, policy_version 59430 (0.0008) -[2023-10-16 05:08:00,058][05219] Updated weights for policy 1, policy_version 59440 (0.0009) -[2023-10-16 05:08:00,420][05219] Updated weights for policy 1, policy_version 59450 (0.0008) -[2023-10-16 05:08:02,271][05218] Updated weights for policy 0, policy_version 59652 (0.0008) -[2023-10-16 05:08:02,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 121962496. Throughput: 0: 1805.0, 1: 1782.6. Samples: 30501148. Policy #0 lag: (min: 18.0, avg: 24.4, max: 50.0) -[2023-10-16 05:08:02,352][03835] Avg episode reward: [(0, '5.970'), (1, '6.840')] -[2023-10-16 05:08:02,655][05218] Updated weights for policy 0, policy_version 59662 (0.0007) -[2023-10-16 05:08:03,027][05218] Updated weights for policy 0, policy_version 59672 (0.0007) -[2023-10-16 05:08:04,038][05219] Updated weights for policy 1, policy_version 59460 (0.0009) -[2023-10-16 05:08:04,403][05219] Updated weights for policy 1, policy_version 59470 (0.0009) -[2023-10-16 05:08:04,774][05219] Updated weights for policy 1, policy_version 59480 (0.0011) -[2023-10-16 05:08:06,580][05218] Updated weights for policy 0, policy_version 59682 (0.0008) -[2023-10-16 05:08:06,957][05218] Updated weights for policy 0, policy_version 59692 (0.0008) -[2023-10-16 05:08:07,339][05218] Updated weights for policy 0, policy_version 59702 (0.0007) -[2023-10-16 05:08:07,351][03835] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 122028032. Throughput: 0: 1814.8, 1: 1786.9. Samples: 30523022. Policy #0 lag: (min: 18.0, avg: 24.4, max: 50.0) -[2023-10-16 05:08:07,352][03835] Avg episode reward: [(0, '6.640'), (1, '6.960')] -[2023-10-16 05:08:07,728][05218] Updated weights for policy 0, policy_version 59712 (0.0007) -[2023-10-16 05:08:08,650][05219] Updated weights for policy 1, policy_version 59490 (0.0009) -[2023-10-16 05:08:09,018][05219] Updated weights for policy 1, policy_version 59500 (0.0009) -[2023-10-16 05:08:09,394][05219] Updated weights for policy 1, policy_version 59510 (0.0012) -[2023-10-16 05:08:09,754][05219] Updated weights for policy 1, policy_version 59520 (0.0007) -[2023-10-16 05:08:11,491][05218] Updated weights for policy 0, policy_version 59722 (0.0009) -[2023-10-16 05:08:11,861][05218] Updated weights for policy 0, policy_version 59732 (0.0009) -[2023-10-16 05:08:12,241][05218] Updated weights for policy 0, policy_version 59742 (0.0009) -[2023-10-16 05:08:12,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 122126336. Throughput: 0: 1812.8, 1: 1785.3. Samples: 30533844. Policy #0 lag: (min: 18.0, avg: 24.4, max: 50.0) -[2023-10-16 05:08:12,351][03835] Avg episode reward: [(0, '6.820'), (1, '6.290')] -[2023-10-16 05:08:13,604][05219] Updated weights for policy 1, policy_version 59530 (0.0010) -[2023-10-16 05:08:13,975][05219] Updated weights for policy 1, policy_version 59540 (0.0011) -[2023-10-16 05:08:14,328][05219] Updated weights for policy 1, policy_version 59550 (0.0009) -[2023-10-16 05:08:15,793][05218] Updated weights for policy 0, policy_version 59752 (0.0008) -[2023-10-16 05:08:16,175][05218] Updated weights for policy 0, policy_version 59762 (0.0007) -[2023-10-16 05:08:16,548][05218] Updated weights for policy 0, policy_version 59772 (0.0009) -[2023-10-16 05:08:17,350][03835] Fps is (10 sec: 16384.7, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 122191872. Throughput: 0: 1812.8, 1: 1783.6. Samples: 30555358. Policy #0 lag: (min: 18.0, avg: 24.4, max: 50.0) -[2023-10-16 05:08:17,351][03835] Avg episode reward: [(0, '5.950'), (1, '6.370')] -[2023-10-16 05:08:18,223][05219] Updated weights for policy 1, policy_version 59560 (0.0007) -[2023-10-16 05:08:18,590][05219] Updated weights for policy 1, policy_version 59570 (0.0007) -[2023-10-16 05:08:18,942][05219] Updated weights for policy 1, policy_version 59580 (0.0008) -[2023-10-16 05:08:20,355][05218] Updated weights for policy 0, policy_version 59782 (0.0008) -[2023-10-16 05:08:20,722][05218] Updated weights for policy 0, policy_version 59792 (0.0009) -[2023-10-16 05:08:21,102][05218] Updated weights for policy 0, policy_version 59802 (0.0009) -[2023-10-16 05:08:22,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 122257408. Throughput: 0: 1802.7, 1: 1794.9. Samples: 30577170. Policy #0 lag: (min: 18.0, avg: 24.4, max: 50.0) -[2023-10-16 05:08:22,351][03835] Avg episode reward: [(0, '7.100'), (1, '7.150')] -[2023-10-16 05:08:22,678][05219] Updated weights for policy 1, policy_version 59590 (0.0009) -[2023-10-16 05:08:23,035][05219] Updated weights for policy 1, policy_version 59600 (0.0008) -[2023-10-16 05:08:23,401][05219] Updated weights for policy 1, policy_version 59610 (0.0009) -[2023-10-16 05:08:24,936][05218] Updated weights for policy 0, policy_version 59812 (0.0010) -[2023-10-16 05:08:25,321][05218] Updated weights for policy 0, policy_version 59822 (0.0009) -[2023-10-16 05:08:25,700][05218] Updated weights for policy 0, policy_version 59832 (0.0010) -[2023-10-16 05:08:27,074][05219] Updated weights for policy 1, policy_version 59620 (0.0011) -[2023-10-16 05:08:27,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 122322944. Throughput: 0: 1810.3, 1: 1783.6. Samples: 30587560. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:08:27,351][03835] Avg episode reward: [(0, '7.160'), (1, '6.480')] -[2023-10-16 05:08:27,453][05219] Updated weights for policy 1, policy_version 59630 (0.0010) -[2023-10-16 05:08:27,821][05219] Updated weights for policy 1, policy_version 59640 (0.0008) -[2023-10-16 05:08:29,366][05218] Updated weights for policy 0, policy_version 59842 (0.0010) -[2023-10-16 05:08:29,749][05218] Updated weights for policy 0, policy_version 59852 (0.0009) -[2023-10-16 05:08:30,114][05218] Updated weights for policy 0, policy_version 59862 (0.0009) -[2023-10-16 05:08:30,489][05218] Updated weights for policy 0, policy_version 59872 (0.0008) -[2023-10-16 05:08:31,524][05219] Updated weights for policy 1, policy_version 59650 (0.0008) -[2023-10-16 05:08:31,889][05219] Updated weights for policy 1, policy_version 59660 (0.0008) -[2023-10-16 05:08:32,254][05219] Updated weights for policy 1, policy_version 59670 (0.0009) -[2023-10-16 05:08:32,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 122388480. Throughput: 0: 1797.0, 1: 1794.5. Samples: 30609122. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:08:32,351][03835] Avg episode reward: [(0, '6.310'), (1, '7.320')] -[2023-10-16 05:08:32,625][05219] Updated weights for policy 1, policy_version 59680 (0.0008) -[2023-10-16 05:08:34,238][05218] Updated weights for policy 0, policy_version 59882 (0.0008) -[2023-10-16 05:08:34,624][05218] Updated weights for policy 0, policy_version 59892 (0.0008) -[2023-10-16 05:08:35,003][05218] Updated weights for policy 0, policy_version 59902 (0.0008) -[2023-10-16 05:08:36,520][05219] Updated weights for policy 1, policy_version 59690 (0.0008) -[2023-10-16 05:08:36,890][05219] Updated weights for policy 1, policy_version 59700 (0.0007) -[2023-10-16 05:08:37,252][05219] Updated weights for policy 1, policy_version 59710 (0.0008) -[2023-10-16 05:08:37,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14440.2). Total num frames: 122486784. Throughput: 0: 1791.6, 1: 1796.1. Samples: 30630190. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:08:37,351][03835] Avg episode reward: [(0, '6.470'), (1, '6.680')] -[2023-10-16 05:08:38,797][05218] Updated weights for policy 0, policy_version 59912 (0.0008) -[2023-10-16 05:08:39,172][05218] Updated weights for policy 0, policy_version 59922 (0.0009) -[2023-10-16 05:08:39,552][05218] Updated weights for policy 0, policy_version 59932 (0.0010) -[2023-10-16 05:08:40,848][05219] Updated weights for policy 1, policy_version 59720 (0.0009) -[2023-10-16 05:08:41,211][05219] Updated weights for policy 1, policy_version 59730 (0.0007) -[2023-10-16 05:08:41,572][05219] Updated weights for policy 1, policy_version 59740 (0.0008) -[2023-10-16 05:08:42,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 122552320. Throughput: 0: 1786.0, 1: 1796.0. Samples: 30641204. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:08:42,351][03835] Avg episode reward: [(0, '6.560'), (1, '6.480')] -[2023-10-16 05:08:43,433][05218] Updated weights for policy 0, policy_version 59942 (0.0010) -[2023-10-16 05:08:43,815][05218] Updated weights for policy 0, policy_version 59952 (0.0010) -[2023-10-16 05:08:44,192][05218] Updated weights for policy 0, policy_version 59962 (0.0008) -[2023-10-16 05:08:45,311][05219] Updated weights for policy 1, policy_version 59750 (0.0007) -[2023-10-16 05:08:45,669][05219] Updated weights for policy 1, policy_version 59760 (0.0010) -[2023-10-16 05:08:46,027][05219] Updated weights for policy 1, policy_version 59770 (0.0007) -[2023-10-16 05:08:47,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 122617856. Throughput: 0: 1793.6, 1: 1797.1. Samples: 30662728. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:08:47,351][03835] Avg episode reward: [(0, '6.520'), (1, '6.130')] -[2023-10-16 05:08:47,877][05218] Updated weights for policy 0, policy_version 59972 (0.0008) -[2023-10-16 05:08:48,257][05218] Updated weights for policy 0, policy_version 59982 (0.0010) -[2023-10-16 05:08:48,625][05218] Updated weights for policy 0, policy_version 59992 (0.0011) -[2023-10-16 05:08:49,702][05219] Updated weights for policy 1, policy_version 59780 (0.0008) -[2023-10-16 05:08:50,060][05219] Updated weights for policy 1, policy_version 59790 (0.0007) -[2023-10-16 05:08:50,423][05219] Updated weights for policy 1, policy_version 59800 (0.0008) -[2023-10-16 05:08:52,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 122683392. Throughput: 0: 1808.1, 1: 1786.9. Samples: 30684794. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:08:52,351][03835] Avg episode reward: [(0, '6.110'), (1, '6.430')] -[2023-10-16 05:08:52,418][05218] Updated weights for policy 0, policy_version 60002 (0.0009) -[2023-10-16 05:08:52,789][05218] Updated weights for policy 0, policy_version 60012 (0.0007) -[2023-10-16 05:08:53,168][05218] Updated weights for policy 0, policy_version 60022 (0.0010) -[2023-10-16 05:08:53,539][05218] Updated weights for policy 0, policy_version 60032 (0.0009) -[2023-10-16 05:08:54,386][05219] Updated weights for policy 1, policy_version 59810 (0.0008) -[2023-10-16 05:08:54,757][05219] Updated weights for policy 1, policy_version 59820 (0.0007) -[2023-10-16 05:08:55,120][05219] Updated weights for policy 1, policy_version 59830 (0.0007) -[2023-10-16 05:08:55,479][05219] Updated weights for policy 1, policy_version 59840 (0.0008) -[2023-10-16 05:08:57,309][05218] Updated weights for policy 0, policy_version 60042 (0.0009) -[2023-10-16 05:08:57,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 122748928. Throughput: 0: 1786.8, 1: 1798.7. Samples: 30695194. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:08:57,351][03835] Avg episode reward: [(0, '6.570'), (1, '6.060')] -[2023-10-16 05:08:57,677][05218] Updated weights for policy 0, policy_version 60052 (0.0009) -[2023-10-16 05:08:58,049][05218] Updated weights for policy 0, policy_version 60062 (0.0007) -[2023-10-16 05:08:59,173][05219] Updated weights for policy 1, policy_version 59850 (0.0007) -[2023-10-16 05:08:59,541][05219] Updated weights for policy 1, policy_version 59860 (0.0010) -[2023-10-16 05:08:59,910][05219] Updated weights for policy 1, policy_version 59870 (0.0010) -[2023-10-16 05:09:01,839][05218] Updated weights for policy 0, policy_version 60072 (0.0011) -[2023-10-16 05:09:02,215][05218] Updated weights for policy 0, policy_version 60082 (0.0008) -[2023-10-16 05:09:02,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 122814464. Throughput: 0: 1806.7, 1: 1784.0. Samples: 30716938. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:09:02,351][03835] Avg episode reward: [(0, '7.360'), (1, '6.390')] -[2023-10-16 05:09:02,595][05218] Updated weights for policy 0, policy_version 60092 (0.0008) -[2023-10-16 05:09:03,712][05219] Updated weights for policy 1, policy_version 59880 (0.0010) -[2023-10-16 05:09:04,083][05219] Updated weights for policy 1, policy_version 59890 (0.0009) -[2023-10-16 05:09:04,455][05219] Updated weights for policy 1, policy_version 59900 (0.0010) -[2023-10-16 05:09:06,241][05218] Updated weights for policy 0, policy_version 60102 (0.0008) -[2023-10-16 05:09:06,612][05218] Updated weights for policy 0, policy_version 60112 (0.0007) -[2023-10-16 05:09:06,982][05218] Updated weights for policy 0, policy_version 60122 (0.0008) -[2023-10-16 05:09:07,351][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 122912768. Throughput: 0: 1791.7, 1: 1787.3. Samples: 30738228. Policy #0 lag: (min: 23.0, avg: 31.8, max: 55.0) -[2023-10-16 05:09:07,352][03835] Avg episode reward: [(0, '6.670'), (1, '6.780')] -[2023-10-16 05:09:08,241][05219] Updated weights for policy 1, policy_version 59910 (0.0010) -[2023-10-16 05:09:08,610][05219] Updated weights for policy 1, policy_version 59920 (0.0008) -[2023-10-16 05:09:08,978][05219] Updated weights for policy 1, policy_version 59930 (0.0008) -[2023-10-16 05:09:10,678][05218] Updated weights for policy 0, policy_version 60132 (0.0007) -[2023-10-16 05:09:11,063][05218] Updated weights for policy 0, policy_version 60142 (0.0008) -[2023-10-16 05:09:11,447][05218] Updated weights for policy 0, policy_version 60152 (0.0007) -[2023-10-16 05:09:12,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 122978304. Throughput: 0: 1812.2, 1: 1789.7. Samples: 30749644. Policy #0 lag: (min: 23.0, avg: 31.8, max: 55.0) -[2023-10-16 05:09:12,351][03835] Avg episode reward: [(0, '6.860'), (1, '7.200')] -[2023-10-16 05:09:12,837][05219] Updated weights for policy 1, policy_version 59940 (0.0010) -[2023-10-16 05:09:13,217][05219] Updated weights for policy 1, policy_version 59950 (0.0007) -[2023-10-16 05:09:13,583][05219] Updated weights for policy 1, policy_version 59960 (0.0007) -[2023-10-16 05:09:15,023][05218] Updated weights for policy 0, policy_version 60162 (0.0008) -[2023-10-16 05:09:15,394][05218] Updated weights for policy 0, policy_version 60172 (0.0008) -[2023-10-16 05:09:15,770][05218] Updated weights for policy 0, policy_version 60182 (0.0011) -[2023-10-16 05:09:16,144][05218] Updated weights for policy 0, policy_version 60192 (0.0009) -[2023-10-16 05:09:17,264][05219] Updated weights for policy 1, policy_version 59970 (0.0007) -[2023-10-16 05:09:17,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 123043840. Throughput: 0: 1801.3, 1: 1790.6. Samples: 30770760. Policy #0 lag: (min: 23.0, avg: 31.8, max: 55.0) -[2023-10-16 05:09:17,351][03835] Avg episode reward: [(0, '6.890'), (1, '7.320')] -[2023-10-16 05:09:17,629][05219] Updated weights for policy 1, policy_version 59980 (0.0007) -[2023-10-16 05:09:17,984][05219] Updated weights for policy 1, policy_version 59990 (0.0007) -[2023-10-16 05:09:18,357][05219] Updated weights for policy 1, policy_version 60000 (0.0008) -[2023-10-16 05:09:19,705][05218] Updated weights for policy 0, policy_version 60202 (0.0007) -[2023-10-16 05:09:20,080][05218] Updated weights for policy 0, policy_version 60212 (0.0008) -[2023-10-16 05:09:20,459][05218] Updated weights for policy 0, policy_version 60222 (0.0008) -[2023-10-16 05:09:22,219][05219] Updated weights for policy 1, policy_version 60010 (0.0007) -[2023-10-16 05:09:22,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 123109376. Throughput: 0: 1807.1, 1: 1807.2. Samples: 30792832. Policy #0 lag: (min: 23.0, avg: 31.8, max: 55.0) -[2023-10-16 05:09:22,351][03835] Avg episode reward: [(0, '5.850'), (1, '7.190')] -[2023-10-16 05:09:22,582][05219] Updated weights for policy 1, policy_version 60020 (0.0009) -[2023-10-16 05:09:22,954][05219] Updated weights for policy 1, policy_version 60030 (0.0009) -[2023-10-16 05:09:24,259][05218] Updated weights for policy 0, policy_version 60232 (0.0010) -[2023-10-16 05:09:24,641][05218] Updated weights for policy 0, policy_version 60242 (0.0010) -[2023-10-16 05:09:25,009][05218] Updated weights for policy 0, policy_version 60252 (0.0009) -[2023-10-16 05:09:26,564][05219] Updated weights for policy 1, policy_version 60040 (0.0009) -[2023-10-16 05:09:26,931][05219] Updated weights for policy 1, policy_version 60050 (0.0008) -[2023-10-16 05:09:27,295][05219] Updated weights for policy 1, policy_version 60060 (0.0007) -[2023-10-16 05:09:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 123174912. Throughput: 0: 1806.5, 1: 1784.4. Samples: 30802796. Policy #0 lag: (min: 23.0, avg: 31.8, max: 55.0) -[2023-10-16 05:09:27,351][03835] Avg episode reward: [(0, '6.190'), (1, '7.470')] -[2023-10-16 05:09:28,725][05218] Updated weights for policy 0, policy_version 60262 (0.0009) -[2023-10-16 05:09:29,098][05218] Updated weights for policy 0, policy_version 60272 (0.0009) -[2023-10-16 05:09:29,476][05218] Updated weights for policy 0, policy_version 60282 (0.0007) -[2023-10-16 05:09:31,096][05219] Updated weights for policy 1, policy_version 60070 (0.0007) -[2023-10-16 05:09:31,457][05219] Updated weights for policy 1, policy_version 60080 (0.0007) -[2023-10-16 05:09:31,828][05219] Updated weights for policy 1, policy_version 60090 (0.0009) -[2023-10-16 05:09:32,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 123273216. Throughput: 0: 1805.8, 1: 1807.6. Samples: 30825328. Policy #0 lag: (min: 23.0, avg: 31.8, max: 55.0) -[2023-10-16 05:09:32,351][03835] Avg episode reward: [(0, '7.200'), (1, '8.020')] -[2023-10-16 05:09:32,975][05218] Updated weights for policy 0, policy_version 60292 (0.0007) -[2023-10-16 05:09:33,359][05218] Updated weights for policy 0, policy_version 60302 (0.0010) -[2023-10-16 05:09:33,727][05218] Updated weights for policy 0, policy_version 60312 (0.0010) -[2023-10-16 05:09:35,760][05219] Updated weights for policy 1, policy_version 60100 (0.0008) -[2023-10-16 05:09:36,130][05219] Updated weights for policy 1, policy_version 60110 (0.0010) -[2023-10-16 05:09:36,495][05219] Updated weights for policy 1, policy_version 60120 (0.0008) -[2023-10-16 05:09:37,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 123338752. Throughput: 0: 1803.0, 1: 1790.4. Samples: 30846496. Policy #0 lag: (min: 23.0, avg: 31.8, max: 55.0) -[2023-10-16 05:09:37,351][03835] Avg episode reward: [(0, '7.070'), (1, '6.590')] -[2023-10-16 05:09:37,361][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000060320_61767680.pth... -[2023-10-16 05:09:37,361][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000060128_61571072.pth... -[2023-10-16 05:09:37,399][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000058432_59834368.pth -[2023-10-16 05:09:37,402][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000058656_60063744.pth -[2023-10-16 05:09:37,570][05218] Updated weights for policy 0, policy_version 60322 (0.0010) -[2023-10-16 05:09:37,941][05218] Updated weights for policy 0, policy_version 60332 (0.0007) -[2023-10-16 05:09:38,315][05218] Updated weights for policy 0, policy_version 60342 (0.0008) -[2023-10-16 05:09:38,695][05218] Updated weights for policy 0, policy_version 60352 (0.0007) -[2023-10-16 05:09:40,142][05219] Updated weights for policy 1, policy_version 60130 (0.0008) -[2023-10-16 05:09:40,509][05219] Updated weights for policy 1, policy_version 60140 (0.0007) -[2023-10-16 05:09:40,880][05219] Updated weights for policy 1, policy_version 60150 (0.0008) -[2023-10-16 05:09:41,234][05219] Updated weights for policy 1, policy_version 60160 (0.0008) -[2023-10-16 05:09:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 123404288. Throughput: 0: 1799.5, 1: 1808.6. Samples: 30857558. Policy #0 lag: (min: 23.0, avg: 31.8, max: 55.0) -[2023-10-16 05:09:42,351][03835] Avg episode reward: [(0, '6.900'), (1, '6.930')] -[2023-10-16 05:09:42,445][05218] Updated weights for policy 0, policy_version 60362 (0.0008) -[2023-10-16 05:09:42,826][05218] Updated weights for policy 0, policy_version 60372 (0.0009) -[2023-10-16 05:09:43,191][05218] Updated weights for policy 0, policy_version 60382 (0.0007) -[2023-10-16 05:09:44,958][05219] Updated weights for policy 1, policy_version 60170 (0.0007) -[2023-10-16 05:09:45,326][05219] Updated weights for policy 1, policy_version 60180 (0.0010) -[2023-10-16 05:09:45,696][05219] Updated weights for policy 1, policy_version 60190 (0.0007) -[2023-10-16 05:09:46,800][05218] Updated weights for policy 0, policy_version 60392 (0.0010) -[2023-10-16 05:09:47,180][05218] Updated weights for policy 0, policy_version 60402 (0.0010) -[2023-10-16 05:09:47,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 123469824. Throughput: 0: 1802.3, 1: 1793.7. Samples: 30878758. Policy #0 lag: (min: 23.0, avg: 31.8, max: 55.0) -[2023-10-16 05:09:47,351][03835] Avg episode reward: [(0, '6.330'), (1, '8.140')] -[2023-10-16 05:09:47,558][05218] Updated weights for policy 0, policy_version 60412 (0.0010) -[2023-10-16 05:09:49,441][05219] Updated weights for policy 1, policy_version 60200 (0.0009) -[2023-10-16 05:09:49,808][05219] Updated weights for policy 1, policy_version 60210 (0.0009) -[2023-10-16 05:09:50,183][05219] Updated weights for policy 1, policy_version 60220 (0.0010) -[2023-10-16 05:09:51,301][05218] Updated weights for policy 0, policy_version 60422 (0.0008) -[2023-10-16 05:09:51,672][05218] Updated weights for policy 0, policy_version 60432 (0.0010) -[2023-10-16 05:09:52,044][05218] Updated weights for policy 0, policy_version 60442 (0.0009) -[2023-10-16 05:09:52,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 123568128. Throughput: 0: 1795.6, 1: 1788.8. Samples: 30899528. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:09:52,352][03835] Avg episode reward: [(0, '6.660'), (1, '7.020')] -[2023-10-16 05:09:53,968][05219] Updated weights for policy 1, policy_version 60230 (0.0009) -[2023-10-16 05:09:54,333][05219] Updated weights for policy 1, policy_version 60240 (0.0008) -[2023-10-16 05:09:54,699][05219] Updated weights for policy 1, policy_version 60250 (0.0009) -[2023-10-16 05:09:55,944][05218] Updated weights for policy 0, policy_version 60452 (0.0009) -[2023-10-16 05:09:56,321][05218] Updated weights for policy 0, policy_version 60462 (0.0009) -[2023-10-16 05:09:56,703][05218] Updated weights for policy 0, policy_version 60472 (0.0009) -[2023-10-16 05:09:57,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 123633664. Throughput: 0: 1789.1, 1: 1788.3. Samples: 30910626. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:09:57,351][03835] Avg episode reward: [(0, '6.130'), (1, '7.340')] -[2023-10-16 05:09:58,436][05219] Updated weights for policy 1, policy_version 60260 (0.0009) -[2023-10-16 05:09:58,801][05219] Updated weights for policy 1, policy_version 60270 (0.0009) -[2023-10-16 05:09:59,157][05219] Updated weights for policy 1, policy_version 60280 (0.0008) -[2023-10-16 05:10:00,537][05218] Updated weights for policy 0, policy_version 60482 (0.0009) -[2023-10-16 05:10:00,911][05218] Updated weights for policy 0, policy_version 60492 (0.0008) -[2023-10-16 05:10:01,288][05218] Updated weights for policy 0, policy_version 60502 (0.0008) -[2023-10-16 05:10:01,667][05218] Updated weights for policy 0, policy_version 60512 (0.0008) -[2023-10-16 05:10:02,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 123699200. Throughput: 0: 1796.0, 1: 1787.4. Samples: 30932014. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:10:02,351][03835] Avg episode reward: [(0, '6.890'), (1, '6.800')] -[2023-10-16 05:10:02,851][05219] Updated weights for policy 1, policy_version 60290 (0.0007) -[2023-10-16 05:10:03,215][05219] Updated weights for policy 1, policy_version 60300 (0.0009) -[2023-10-16 05:10:03,572][05219] Updated weights for policy 1, policy_version 60310 (0.0010) -[2023-10-16 05:10:03,943][05219] Updated weights for policy 1, policy_version 60320 (0.0010) -[2023-10-16 05:10:05,447][05218] Updated weights for policy 0, policy_version 60522 (0.0009) -[2023-10-16 05:10:05,826][05218] Updated weights for policy 0, policy_version 60532 (0.0009) -[2023-10-16 05:10:06,199][05218] Updated weights for policy 0, policy_version 60542 (0.0009) -[2023-10-16 05:10:07,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 123764736. Throughput: 0: 1782.6, 1: 1800.5. Samples: 30954072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:10:07,351][03835] Avg episode reward: [(0, '7.530'), (1, '6.710')] -[2023-10-16 05:10:07,940][05219] Updated weights for policy 1, policy_version 60330 (0.0007) -[2023-10-16 05:10:08,310][05219] Updated weights for policy 1, policy_version 60340 (0.0007) -[2023-10-16 05:10:08,671][05219] Updated weights for policy 1, policy_version 60350 (0.0010) -[2023-10-16 05:10:09,744][05218] Updated weights for policy 0, policy_version 60552 (0.0008) -[2023-10-16 05:10:10,110][05218] Updated weights for policy 0, policy_version 60562 (0.0007) -[2023-10-16 05:10:10,489][05218] Updated weights for policy 0, policy_version 60572 (0.0008) -[2023-10-16 05:10:12,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 123830272. Throughput: 0: 1800.7, 1: 1790.3. Samples: 30964388. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:10:12,351][03835] Avg episode reward: [(0, '7.340'), (1, '7.060')] -[2023-10-16 05:10:12,417][05219] Updated weights for policy 1, policy_version 60360 (0.0010) -[2023-10-16 05:10:12,783][05219] Updated weights for policy 1, policy_version 60370 (0.0011) -[2023-10-16 05:10:13,145][05219] Updated weights for policy 1, policy_version 60380 (0.0010) -[2023-10-16 05:10:14,297][05218] Updated weights for policy 0, policy_version 60582 (0.0010) -[2023-10-16 05:10:14,684][05218] Updated weights for policy 0, policy_version 60592 (0.0010) -[2023-10-16 05:10:15,058][05218] Updated weights for policy 0, policy_version 60602 (0.0010) -[2023-10-16 05:10:16,978][05219] Updated weights for policy 1, policy_version 60390 (0.0010) -[2023-10-16 05:10:17,344][05219] Updated weights for policy 1, policy_version 60400 (0.0008) -[2023-10-16 05:10:17,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 123895808. Throughput: 0: 1782.6, 1: 1788.4. Samples: 30986022. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:10:17,351][03835] Avg episode reward: [(0, '6.840'), (1, '7.580')] -[2023-10-16 05:10:17,702][05219] Updated weights for policy 1, policy_version 60410 (0.0007) -[2023-10-16 05:10:18,793][05218] Updated weights for policy 0, policy_version 60612 (0.0010) -[2023-10-16 05:10:19,171][05218] Updated weights for policy 0, policy_version 60622 (0.0007) -[2023-10-16 05:10:19,549][05218] Updated weights for policy 0, policy_version 60632 (0.0007) -[2023-10-16 05:10:21,385][05219] Updated weights for policy 1, policy_version 60420 (0.0009) -[2023-10-16 05:10:21,751][05219] Updated weights for policy 1, policy_version 60430 (0.0007) -[2023-10-16 05:10:22,122][05219] Updated weights for policy 1, policy_version 60440 (0.0007) -[2023-10-16 05:10:22,350][03835] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 123961344. Throughput: 0: 1789.0, 1: 1790.8. Samples: 31007588. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:10:22,352][03835] Avg episode reward: [(0, '6.510'), (1, '7.060')] -[2023-10-16 05:10:23,282][05218] Updated weights for policy 0, policy_version 60642 (0.0008) -[2023-10-16 05:10:23,665][05218] Updated weights for policy 0, policy_version 60652 (0.0007) -[2023-10-16 05:10:24,045][05218] Updated weights for policy 0, policy_version 60662 (0.0007) -[2023-10-16 05:10:24,427][05218] Updated weights for policy 0, policy_version 60672 (0.0009) -[2023-10-16 05:10:25,761][05219] Updated weights for policy 1, policy_version 60450 (0.0010) -[2023-10-16 05:10:26,117][05219] Updated weights for policy 1, policy_version 60460 (0.0010) -[2023-10-16 05:10:26,490][05219] Updated weights for policy 1, policy_version 60470 (0.0007) -[2023-10-16 05:10:26,854][05219] Updated weights for policy 1, policy_version 60480 (0.0009) -[2023-10-16 05:10:27,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 124059648. Throughput: 0: 1788.0, 1: 1786.4. Samples: 31018406. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:10:27,352][03835] Avg episode reward: [(0, '7.250'), (1, '6.670')] -[2023-10-16 05:10:28,122][05218] Updated weights for policy 0, policy_version 60682 (0.0008) -[2023-10-16 05:10:28,494][05218] Updated weights for policy 0, policy_version 60692 (0.0007) -[2023-10-16 05:10:28,872][05218] Updated weights for policy 0, policy_version 60702 (0.0007) -[2023-10-16 05:10:30,553][05219] Updated weights for policy 1, policy_version 60490 (0.0008) -[2023-10-16 05:10:30,917][05219] Updated weights for policy 1, policy_version 60500 (0.0008) -[2023-10-16 05:10:31,278][05219] Updated weights for policy 1, policy_version 60510 (0.0009) -[2023-10-16 05:10:32,350][03835] Fps is (10 sec: 16384.6, 60 sec: 14199.5, 300 sec: 14440.2). Total num frames: 124125184. Throughput: 0: 1781.7, 1: 1797.9. Samples: 31039842. Policy #0 lag: (min: 3.0, avg: 7.8, max: 35.0) -[2023-10-16 05:10:32,351][03835] Avg episode reward: [(0, '6.550'), (1, '6.570')] -[2023-10-16 05:10:32,725][05218] Updated weights for policy 0, policy_version 60712 (0.0007) -[2023-10-16 05:10:33,104][05218] Updated weights for policy 0, policy_version 60722 (0.0007) -[2023-10-16 05:10:33,481][05218] Updated weights for policy 0, policy_version 60732 (0.0007) -[2023-10-16 05:10:35,119][05219] Updated weights for policy 1, policy_version 60520 (0.0009) -[2023-10-16 05:10:35,475][05219] Updated weights for policy 1, policy_version 60530 (0.0007) -[2023-10-16 05:10:35,838][05219] Updated weights for policy 1, policy_version 60540 (0.0007) -[2023-10-16 05:10:37,215][05218] Updated weights for policy 0, policy_version 60742 (0.0010) -[2023-10-16 05:10:37,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 124190720. Throughput: 0: 1812.0, 1: 1790.5. Samples: 31061638. Policy #0 lag: (min: 3.0, avg: 7.8, max: 35.0) -[2023-10-16 05:10:37,351][03835] Avg episode reward: [(0, '6.510'), (1, '7.000')] -[2023-10-16 05:10:37,591][05218] Updated weights for policy 0, policy_version 60752 (0.0010) -[2023-10-16 05:10:37,969][05218] Updated weights for policy 0, policy_version 60762 (0.0008) -[2023-10-16 05:10:39,494][05219] Updated weights for policy 1, policy_version 60550 (0.0007) -[2023-10-16 05:10:39,869][05219] Updated weights for policy 1, policy_version 60560 (0.0007) -[2023-10-16 05:10:40,229][05219] Updated weights for policy 1, policy_version 60570 (0.0008) -[2023-10-16 05:10:41,780][05218] Updated weights for policy 0, policy_version 60772 (0.0007) -[2023-10-16 05:10:42,166][05218] Updated weights for policy 0, policy_version 60782 (0.0011) -[2023-10-16 05:10:42,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 124256256. Throughput: 0: 1790.5, 1: 1803.3. Samples: 31072346. Policy #0 lag: (min: 3.0, avg: 7.8, max: 35.0) -[2023-10-16 05:10:42,351][03835] Avg episode reward: [(0, '6.230'), (1, '7.170')] -[2023-10-16 05:10:42,540][05218] Updated weights for policy 0, policy_version 60792 (0.0008) -[2023-10-16 05:10:44,088][05219] Updated weights for policy 1, policy_version 60580 (0.0009) -[2023-10-16 05:10:44,450][05219] Updated weights for policy 1, policy_version 60590 (0.0007) -[2023-10-16 05:10:44,819][05219] Updated weights for policy 1, policy_version 60600 (0.0007) -[2023-10-16 05:10:46,394][05218] Updated weights for policy 0, policy_version 60802 (0.0008) -[2023-10-16 05:10:46,778][05218] Updated weights for policy 0, policy_version 60812 (0.0007) -[2023-10-16 05:10:47,148][05218] Updated weights for policy 0, policy_version 60822 (0.0008) -[2023-10-16 05:10:47,351][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 124321792. Throughput: 0: 1807.5, 1: 1789.6. Samples: 31093882. Policy #0 lag: (min: 3.0, avg: 7.8, max: 35.0) -[2023-10-16 05:10:47,352][03835] Avg episode reward: [(0, '5.840'), (1, '7.240')] -[2023-10-16 05:10:47,535][05218] Updated weights for policy 0, policy_version 60832 (0.0009) -[2023-10-16 05:10:48,582][05219] Updated weights for policy 1, policy_version 60610 (0.0008) -[2023-10-16 05:10:48,937][05219] Updated weights for policy 1, policy_version 60620 (0.0009) -[2023-10-16 05:10:49,307][05219] Updated weights for policy 1, policy_version 60630 (0.0008) -[2023-10-16 05:10:49,662][05219] Updated weights for policy 1, policy_version 60640 (0.0008) -[2023-10-16 05:10:51,164][05218] Updated weights for policy 0, policy_version 60842 (0.0007) -[2023-10-16 05:10:51,545][05218] Updated weights for policy 0, policy_version 60852 (0.0009) -[2023-10-16 05:10:51,920][05218] Updated weights for policy 0, policy_version 60862 (0.0009) -[2023-10-16 05:10:52,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 124420096. Throughput: 0: 1786.9, 1: 1789.9. Samples: 31115028. Policy #0 lag: (min: 3.0, avg: 7.8, max: 35.0) -[2023-10-16 05:10:52,352][03835] Avg episode reward: [(0, '6.460'), (1, '7.580')] -[2023-10-16 05:10:53,454][05219] Updated weights for policy 1, policy_version 60650 (0.0010) -[2023-10-16 05:10:53,812][05219] Updated weights for policy 1, policy_version 60660 (0.0009) -[2023-10-16 05:10:54,183][05219] Updated weights for policy 1, policy_version 60670 (0.0010) -[2023-10-16 05:10:55,772][05218] Updated weights for policy 0, policy_version 60872 (0.0009) -[2023-10-16 05:10:56,156][05218] Updated weights for policy 0, policy_version 60882 (0.0009) -[2023-10-16 05:10:56,522][05218] Updated weights for policy 0, policy_version 60892 (0.0009) -[2023-10-16 05:10:57,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 124485632. Throughput: 0: 1801.7, 1: 1791.1. Samples: 31126064. Policy #0 lag: (min: 3.0, avg: 7.8, max: 35.0) -[2023-10-16 05:10:57,352][03835] Avg episode reward: [(0, '6.800'), (1, '8.010')] -[2023-10-16 05:10:57,844][05219] Updated weights for policy 1, policy_version 60680 (0.0008) -[2023-10-16 05:10:58,213][05219] Updated weights for policy 1, policy_version 60690 (0.0007) -[2023-10-16 05:10:58,571][05219] Updated weights for policy 1, policy_version 60700 (0.0008) -[2023-10-16 05:11:00,227][05218] Updated weights for policy 0, policy_version 60902 (0.0007) -[2023-10-16 05:11:00,603][05218] Updated weights for policy 0, policy_version 60912 (0.0009) -[2023-10-16 05:11:00,976][05218] Updated weights for policy 0, policy_version 60922 (0.0008) -[2023-10-16 05:11:02,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 124551168. Throughput: 0: 1782.7, 1: 1794.4. Samples: 31146990. Policy #0 lag: (min: 3.0, avg: 7.8, max: 35.0) -[2023-10-16 05:11:02,351][03835] Avg episode reward: [(0, '6.320'), (1, '7.770')] -[2023-10-16 05:11:02,458][05219] Updated weights for policy 1, policy_version 60710 (0.0008) -[2023-10-16 05:11:02,824][05219] Updated weights for policy 1, policy_version 60720 (0.0007) -[2023-10-16 05:11:03,189][05219] Updated weights for policy 1, policy_version 60730 (0.0008) -[2023-10-16 05:11:04,796][05218] Updated weights for policy 0, policy_version 60932 (0.0008) -[2023-10-16 05:11:05,182][05218] Updated weights for policy 0, policy_version 60942 (0.0010) -[2023-10-16 05:11:05,550][05218] Updated weights for policy 0, policy_version 60952 (0.0011) -[2023-10-16 05:11:06,850][05219] Updated weights for policy 1, policy_version 60740 (0.0009) -[2023-10-16 05:11:07,218][05219] Updated weights for policy 1, policy_version 60750 (0.0011) -[2023-10-16 05:11:07,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 124616704. Throughput: 0: 1776.4, 1: 1805.7. Samples: 31168786. Policy #0 lag: (min: 3.0, avg: 7.8, max: 35.0) -[2023-10-16 05:11:07,351][03835] Avg episode reward: [(0, '5.400'), (1, '6.740')] -[2023-10-16 05:11:07,592][05219] Updated weights for policy 1, policy_version 60760 (0.0008) -[2023-10-16 05:11:09,312][05218] Updated weights for policy 0, policy_version 60962 (0.0010) -[2023-10-16 05:11:09,690][05218] Updated weights for policy 0, policy_version 60972 (0.0011) -[2023-10-16 05:11:10,067][05218] Updated weights for policy 0, policy_version 60982 (0.0011) -[2023-10-16 05:11:10,444][05218] Updated weights for policy 0, policy_version 60992 (0.0009) -[2023-10-16 05:11:11,404][05219] Updated weights for policy 1, policy_version 60770 (0.0008) -[2023-10-16 05:11:11,774][05219] Updated weights for policy 1, policy_version 60780 (0.0008) -[2023-10-16 05:11:12,142][05219] Updated weights for policy 1, policy_version 60790 (0.0008) -[2023-10-16 05:11:12,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 124682240. Throughput: 0: 1786.2, 1: 1791.9. Samples: 31179418. Policy #0 lag: (min: 30.0, avg: 37.7, max: 62.0) -[2023-10-16 05:11:12,351][03835] Avg episode reward: [(0, '5.900'), (1, '6.980')] -[2023-10-16 05:11:12,502][05219] Updated weights for policy 1, policy_version 60800 (0.0008) -[2023-10-16 05:11:14,167][05218] Updated weights for policy 0, policy_version 61002 (0.0010) -[2023-10-16 05:11:14,538][05218] Updated weights for policy 0, policy_version 61012 (0.0011) -[2023-10-16 05:11:14,913][05218] Updated weights for policy 0, policy_version 61022 (0.0010) -[2023-10-16 05:11:16,298][05219] Updated weights for policy 1, policy_version 60810 (0.0008) -[2023-10-16 05:11:16,666][05219] Updated weights for policy 1, policy_version 60820 (0.0007) -[2023-10-16 05:11:17,029][05219] Updated weights for policy 1, policy_version 60830 (0.0007) -[2023-10-16 05:11:17,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 124780544. Throughput: 0: 1783.9, 1: 1806.2. Samples: 31201396. Policy #0 lag: (min: 30.0, avg: 37.7, max: 62.0) -[2023-10-16 05:11:17,351][03835] Avg episode reward: [(0, '6.050'), (1, '7.340')] -[2023-10-16 05:11:18,579][05218] Updated weights for policy 0, policy_version 61032 (0.0010) -[2023-10-16 05:11:18,953][05218] Updated weights for policy 0, policy_version 61042 (0.0008) -[2023-10-16 05:11:19,332][05218] Updated weights for policy 0, policy_version 61052 (0.0010) -[2023-10-16 05:11:20,761][05219] Updated weights for policy 1, policy_version 60840 (0.0010) -[2023-10-16 05:11:21,123][05219] Updated weights for policy 1, policy_version 60850 (0.0008) -[2023-10-16 05:11:21,494][05219] Updated weights for policy 1, policy_version 60860 (0.0007) -[2023-10-16 05:11:22,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 124846080. Throughput: 0: 1787.7, 1: 1789.6. Samples: 31222616. Policy #0 lag: (min: 30.0, avg: 37.7, max: 62.0) -[2023-10-16 05:11:22,351][03835] Avg episode reward: [(0, '6.510'), (1, '6.640')] -[2023-10-16 05:11:23,171][05218] Updated weights for policy 0, policy_version 61062 (0.0009) -[2023-10-16 05:11:23,546][05218] Updated weights for policy 0, policy_version 61072 (0.0008) -[2023-10-16 05:11:23,931][05218] Updated weights for policy 0, policy_version 61082 (0.0008) -[2023-10-16 05:11:25,141][05219] Updated weights for policy 1, policy_version 60870 (0.0009) -[2023-10-16 05:11:25,504][05219] Updated weights for policy 1, policy_version 60880 (0.0010) -[2023-10-16 05:11:25,876][05219] Updated weights for policy 1, policy_version 60890 (0.0007) -[2023-10-16 05:11:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 124911616. Throughput: 0: 1777.5, 1: 1811.2. Samples: 31233842. Policy #0 lag: (min: 30.0, avg: 37.7, max: 62.0) -[2023-10-16 05:11:27,351][03835] Avg episode reward: [(0, '6.530'), (1, '6.760')] -[2023-10-16 05:11:27,634][05218] Updated weights for policy 0, policy_version 61092 (0.0009) -[2023-10-16 05:11:28,006][05218] Updated weights for policy 0, policy_version 61102 (0.0009) -[2023-10-16 05:11:28,392][05218] Updated weights for policy 0, policy_version 61112 (0.0009) -[2023-10-16 05:11:29,629][05219] Updated weights for policy 1, policy_version 60900 (0.0007) -[2023-10-16 05:11:30,002][05219] Updated weights for policy 1, policy_version 60910 (0.0008) -[2023-10-16 05:11:30,368][05219] Updated weights for policy 1, policy_version 60920 (0.0007) -[2023-10-16 05:11:32,132][05218] Updated weights for policy 0, policy_version 61122 (0.0009) -[2023-10-16 05:11:32,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 124977152. Throughput: 0: 1785.9, 1: 1795.9. Samples: 31255062. Policy #0 lag: (min: 30.0, avg: 37.7, max: 62.0) -[2023-10-16 05:11:32,351][03835] Avg episode reward: [(0, '5.920'), (1, '6.920')] -[2023-10-16 05:11:32,512][05218] Updated weights for policy 0, policy_version 61132 (0.0009) -[2023-10-16 05:11:32,887][05218] Updated weights for policy 0, policy_version 61142 (0.0008) -[2023-10-16 05:11:33,271][05218] Updated weights for policy 0, policy_version 61152 (0.0009) -[2023-10-16 05:11:34,150][05219] Updated weights for policy 1, policy_version 60930 (0.0010) -[2023-10-16 05:11:34,515][05219] Updated weights for policy 1, policy_version 60940 (0.0009) -[2023-10-16 05:11:34,877][05219] Updated weights for policy 1, policy_version 60950 (0.0009) -[2023-10-16 05:11:35,246][05219] Updated weights for policy 1, policy_version 60960 (0.0008) -[2023-10-16 05:11:37,034][05218] Updated weights for policy 0, policy_version 61162 (0.0009) -[2023-10-16 05:11:37,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 125042688. Throughput: 0: 1796.3, 1: 1796.7. Samples: 31276710. Policy #0 lag: (min: 30.0, avg: 37.7, max: 62.0) -[2023-10-16 05:11:37,351][03835] Avg episode reward: [(0, '6.630'), (1, '7.020')] -[2023-10-16 05:11:37,357][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000060960_62423040.pth... -[2023-10-16 05:11:37,399][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000059296_60719104.pth -[2023-10-16 05:11:37,412][05218] Updated weights for policy 0, policy_version 61172 (0.0009) -[2023-10-16 05:11:37,791][05218] Updated weights for policy 0, policy_version 61182 (0.0008) -[2023-10-16 05:11:37,865][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000061184_62652416.pth... -[2023-10-16 05:11:37,905][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000059488_60915712.pth -[2023-10-16 05:11:38,940][05219] Updated weights for policy 1, policy_version 60970 (0.0009) -[2023-10-16 05:11:39,300][05219] Updated weights for policy 1, policy_version 60980 (0.0009) -[2023-10-16 05:11:39,667][05219] Updated weights for policy 1, policy_version 60990 (0.0009) -[2023-10-16 05:11:41,634][05218] Updated weights for policy 0, policy_version 61192 (0.0008) -[2023-10-16 05:11:42,009][05218] Updated weights for policy 0, policy_version 61202 (0.0008) -[2023-10-16 05:11:42,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 125108224. Throughput: 0: 1782.9, 1: 1799.7. Samples: 31287276. Policy #0 lag: (min: 30.0, avg: 37.7, max: 62.0) -[2023-10-16 05:11:42,351][03835] Avg episode reward: [(0, '6.110'), (1, '7.180')] -[2023-10-16 05:11:42,384][05218] Updated weights for policy 0, policy_version 61212 (0.0009) -[2023-10-16 05:11:43,394][05219] Updated weights for policy 1, policy_version 61000 (0.0009) -[2023-10-16 05:11:43,751][05219] Updated weights for policy 1, policy_version 61010 (0.0009) -[2023-10-16 05:11:44,122][05219] Updated weights for policy 1, policy_version 61020 (0.0007) -[2023-10-16 05:11:46,160][05218] Updated weights for policy 0, policy_version 61222 (0.0009) -[2023-10-16 05:11:46,533][05218] Updated weights for policy 0, policy_version 61232 (0.0007) -[2023-10-16 05:11:46,916][05218] Updated weights for policy 0, policy_version 61242 (0.0010) -[2023-10-16 05:11:47,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 125206528. Throughput: 0: 1802.3, 1: 1800.0. Samples: 31309090. Policy #0 lag: (min: 30.0, avg: 37.7, max: 62.0) -[2023-10-16 05:11:47,351][03835] Avg episode reward: [(0, '6.850'), (1, '7.700')] -[2023-10-16 05:11:47,972][05219] Updated weights for policy 1, policy_version 61030 (0.0009) -[2023-10-16 05:11:48,330][05219] Updated weights for policy 1, policy_version 61040 (0.0007) -[2023-10-16 05:11:48,693][05219] Updated weights for policy 1, policy_version 61050 (0.0008) -[2023-10-16 05:11:50,494][05218] Updated weights for policy 0, policy_version 61252 (0.0008) -[2023-10-16 05:11:50,869][05218] Updated weights for policy 0, policy_version 61262 (0.0011) -[2023-10-16 05:11:51,250][05218] Updated weights for policy 0, policy_version 61272 (0.0009) -[2023-10-16 05:11:52,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 125272064. Throughput: 0: 1786.6, 1: 1810.1. Samples: 31330640. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:11:52,351][03835] Avg episode reward: [(0, '6.500'), (1, '6.660')] -[2023-10-16 05:11:52,420][05219] Updated weights for policy 1, policy_version 61060 (0.0009) -[2023-10-16 05:11:52,788][05219] Updated weights for policy 1, policy_version 61070 (0.0009) -[2023-10-16 05:11:53,155][05219] Updated weights for policy 1, policy_version 61080 (0.0008) -[2023-10-16 05:11:55,014][05218] Updated weights for policy 0, policy_version 61282 (0.0011) -[2023-10-16 05:11:55,385][05218] Updated weights for policy 0, policy_version 61292 (0.0011) -[2023-10-16 05:11:55,763][05218] Updated weights for policy 0, policy_version 61302 (0.0008) -[2023-10-16 05:11:56,132][05218] Updated weights for policy 0, policy_version 61312 (0.0008) -[2023-10-16 05:11:56,925][05219] Updated weights for policy 1, policy_version 61090 (0.0008) -[2023-10-16 05:11:57,293][05219] Updated weights for policy 1, policy_version 61100 (0.0008) -[2023-10-16 05:11:57,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 125337600. Throughput: 0: 1802.1, 1: 1797.0. Samples: 31341376. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:11:57,351][03835] Avg episode reward: [(0, '6.270'), (1, '6.960')] -[2023-10-16 05:11:57,662][05219] Updated weights for policy 1, policy_version 61110 (0.0007) -[2023-10-16 05:11:58,023][05219] Updated weights for policy 1, policy_version 61120 (0.0008) -[2023-10-16 05:11:59,871][05218] Updated weights for policy 0, policy_version 61322 (0.0011) -[2023-10-16 05:12:00,259][05218] Updated weights for policy 0, policy_version 61332 (0.0007) -[2023-10-16 05:12:00,630][05218] Updated weights for policy 0, policy_version 61342 (0.0008) -[2023-10-16 05:12:01,753][05219] Updated weights for policy 1, policy_version 61130 (0.0009) -[2023-10-16 05:12:02,114][05219] Updated weights for policy 1, policy_version 61140 (0.0009) -[2023-10-16 05:12:02,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 125403136. Throughput: 0: 1777.3, 1: 1807.1. Samples: 31362692. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:12:02,351][03835] Avg episode reward: [(0, '6.490'), (1, '7.290')] -[2023-10-16 05:12:02,479][05219] Updated weights for policy 1, policy_version 61150 (0.0008) -[2023-10-16 05:12:04,485][05218] Updated weights for policy 0, policy_version 61352 (0.0008) -[2023-10-16 05:12:04,859][05218] Updated weights for policy 0, policy_version 61362 (0.0009) -[2023-10-16 05:12:05,240][05218] Updated weights for policy 0, policy_version 61372 (0.0009) -[2023-10-16 05:12:06,384][05219] Updated weights for policy 1, policy_version 61160 (0.0007) -[2023-10-16 05:12:06,755][05219] Updated weights for policy 1, policy_version 61170 (0.0007) -[2023-10-16 05:12:07,119][05219] Updated weights for policy 1, policy_version 61180 (0.0007) -[2023-10-16 05:12:07,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 125501440. Throughput: 0: 1780.8, 1: 1801.5. Samples: 31383820. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:12:07,351][03835] Avg episode reward: [(0, '6.520'), (1, '7.100')] -[2023-10-16 05:12:08,897][05218] Updated weights for policy 0, policy_version 61382 (0.0010) -[2023-10-16 05:12:09,277][05218] Updated weights for policy 0, policy_version 61392 (0.0009) -[2023-10-16 05:12:09,650][05218] Updated weights for policy 0, policy_version 61402 (0.0008) -[2023-10-16 05:12:10,733][05219] Updated weights for policy 1, policy_version 61190 (0.0008) -[2023-10-16 05:12:11,098][05219] Updated weights for policy 1, policy_version 61200 (0.0007) -[2023-10-16 05:12:11,463][05219] Updated weights for policy 1, policy_version 61210 (0.0009) -[2023-10-16 05:12:12,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 125566976. Throughput: 0: 1782.6, 1: 1795.9. Samples: 31394874. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:12:12,351][03835] Avg episode reward: [(0, '6.840'), (1, '7.230')] -[2023-10-16 05:12:13,402][05218] Updated weights for policy 0, policy_version 61412 (0.0007) -[2023-10-16 05:12:13,778][05218] Updated weights for policy 0, policy_version 61422 (0.0007) -[2023-10-16 05:12:14,161][05218] Updated weights for policy 0, policy_version 61432 (0.0010) -[2023-10-16 05:12:15,287][05219] Updated weights for policy 1, policy_version 61220 (0.0008) -[2023-10-16 05:12:15,649][05219] Updated weights for policy 1, policy_version 61230 (0.0010) -[2023-10-16 05:12:16,014][05219] Updated weights for policy 1, policy_version 61240 (0.0009) -[2023-10-16 05:12:17,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 125632512. Throughput: 0: 1782.4, 1: 1794.2. Samples: 31416008. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:12:17,351][03835] Avg episode reward: [(0, '6.990'), (1, '7.500')] -[2023-10-16 05:12:18,120][05218] Updated weights for policy 0, policy_version 61442 (0.0009) -[2023-10-16 05:12:18,514][05218] Updated weights for policy 0, policy_version 61452 (0.0009) -[2023-10-16 05:12:18,895][05218] Updated weights for policy 0, policy_version 61462 (0.0009) -[2023-10-16 05:12:19,266][05218] Updated weights for policy 0, policy_version 61472 (0.0009) -[2023-10-16 05:12:19,690][05219] Updated weights for policy 1, policy_version 61250 (0.0009) -[2023-10-16 05:12:20,055][05219] Updated weights for policy 1, policy_version 61260 (0.0007) -[2023-10-16 05:12:20,406][05219] Updated weights for policy 1, policy_version 61270 (0.0007) -[2023-10-16 05:12:20,771][05219] Updated weights for policy 1, policy_version 61280 (0.0008) -[2023-10-16 05:12:22,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 125698048. Throughput: 0: 1804.5, 1: 1785.2. Samples: 31438246. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:12:22,352][03835] Avg episode reward: [(0, '6.450'), (1, '7.740')] -[2023-10-16 05:12:22,803][05218] Updated weights for policy 0, policy_version 61482 (0.0007) -[2023-10-16 05:12:23,181][05218] Updated weights for policy 0, policy_version 61492 (0.0009) -[2023-10-16 05:12:23,552][05218] Updated weights for policy 0, policy_version 61502 (0.0008) -[2023-10-16 05:12:24,709][05219] Updated weights for policy 1, policy_version 61290 (0.0007) -[2023-10-16 05:12:25,081][05219] Updated weights for policy 1, policy_version 61300 (0.0008) -[2023-10-16 05:12:25,455][05219] Updated weights for policy 1, policy_version 61310 (0.0010) -[2023-10-16 05:12:27,311][05218] Updated weights for policy 0, policy_version 61512 (0.0009) -[2023-10-16 05:12:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 125763584. Throughput: 0: 1787.2, 1: 1791.2. Samples: 31448306. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:12:27,351][03835] Avg episode reward: [(0, '6.970'), (1, '7.330')] -[2023-10-16 05:12:27,681][05218] Updated weights for policy 0, policy_version 61522 (0.0008) -[2023-10-16 05:12:28,053][05218] Updated weights for policy 0, policy_version 61532 (0.0007) -[2023-10-16 05:12:29,189][05219] Updated weights for policy 1, policy_version 61320 (0.0010) -[2023-10-16 05:12:29,556][05219] Updated weights for policy 1, policy_version 61330 (0.0007) -[2023-10-16 05:12:29,920][05219] Updated weights for policy 1, policy_version 61340 (0.0007) -[2023-10-16 05:12:31,929][05218] Updated weights for policy 0, policy_version 61542 (0.0009) -[2023-10-16 05:12:32,308][05218] Updated weights for policy 0, policy_version 61552 (0.0010) -[2023-10-16 05:12:32,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 125829120. Throughput: 0: 1799.3, 1: 1778.3. Samples: 31470084. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:12:32,351][03835] Avg episode reward: [(0, '6.860'), (1, '7.010')] -[2023-10-16 05:12:32,672][05218] Updated weights for policy 0, policy_version 61562 (0.0007) -[2023-10-16 05:12:33,923][05219] Updated weights for policy 1, policy_version 61350 (0.0008) -[2023-10-16 05:12:34,297][05219] Updated weights for policy 1, policy_version 61360 (0.0008) -[2023-10-16 05:12:34,657][05219] Updated weights for policy 1, policy_version 61370 (0.0008) -[2023-10-16 05:12:36,472][05218] Updated weights for policy 0, policy_version 61572 (0.0007) -[2023-10-16 05:12:36,849][05218] Updated weights for policy 0, policy_version 61582 (0.0007) -[2023-10-16 05:12:37,216][05218] Updated weights for policy 0, policy_version 61592 (0.0007) -[2023-10-16 05:12:37,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 125894656. Throughput: 0: 1789.9, 1: 1778.3. Samples: 31491210. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:12:37,352][03835] Avg episode reward: [(0, '6.580'), (1, '7.510')] -[2023-10-16 05:12:38,225][05219] Updated weights for policy 1, policy_version 61380 (0.0008) -[2023-10-16 05:12:38,592][05219] Updated weights for policy 1, policy_version 61390 (0.0009) -[2023-10-16 05:12:38,955][05219] Updated weights for policy 1, policy_version 61400 (0.0009) -[2023-10-16 05:12:40,884][05218] Updated weights for policy 0, policy_version 61602 (0.0008) -[2023-10-16 05:12:41,262][05218] Updated weights for policy 0, policy_version 61612 (0.0009) -[2023-10-16 05:12:41,630][05218] Updated weights for policy 0, policy_version 61622 (0.0008) -[2023-10-16 05:12:42,006][05218] Updated weights for policy 0, policy_version 61632 (0.0008) -[2023-10-16 05:12:42,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 125992960. Throughput: 0: 1792.0, 1: 1780.8. Samples: 31502154. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:12:42,351][03835] Avg episode reward: [(0, '6.190'), (1, '8.040')] -[2023-10-16 05:12:42,801][05219] Updated weights for policy 1, policy_version 61410 (0.0007) -[2023-10-16 05:12:43,172][05219] Updated weights for policy 1, policy_version 61420 (0.0008) -[2023-10-16 05:12:43,526][05219] Updated weights for policy 1, policy_version 61430 (0.0009) -[2023-10-16 05:12:43,894][05219] Updated weights for policy 1, policy_version 61440 (0.0010) -[2023-10-16 05:12:45,727][05218] Updated weights for policy 0, policy_version 61642 (0.0007) -[2023-10-16 05:12:46,103][05218] Updated weights for policy 0, policy_version 61652 (0.0007) -[2023-10-16 05:12:46,482][05218] Updated weights for policy 0, policy_version 61662 (0.0009) -[2023-10-16 05:12:47,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 126058496. Throughput: 0: 1797.0, 1: 1778.4. Samples: 31523586. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:12:47,351][03835] Avg episode reward: [(0, '6.330'), (1, '7.640')] -[2023-10-16 05:12:47,669][05219] Updated weights for policy 1, policy_version 61450 (0.0009) -[2023-10-16 05:12:48,039][05219] Updated weights for policy 1, policy_version 61460 (0.0008) -[2023-10-16 05:12:48,397][05219] Updated weights for policy 1, policy_version 61470 (0.0008) -[2023-10-16 05:12:50,175][05218] Updated weights for policy 0, policy_version 61672 (0.0008) -[2023-10-16 05:12:50,550][05218] Updated weights for policy 0, policy_version 61682 (0.0008) -[2023-10-16 05:12:50,919][05218] Updated weights for policy 0, policy_version 61692 (0.0009) -[2023-10-16 05:12:52,155][05219] Updated weights for policy 1, policy_version 61480 (0.0007) -[2023-10-16 05:12:52,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 126124032. Throughput: 0: 1787.5, 1: 1803.1. Samples: 31545396. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:12:52,351][03835] Avg episode reward: [(0, '6.540'), (1, '7.520')] -[2023-10-16 05:12:52,522][05219] Updated weights for policy 1, policy_version 61490 (0.0007) -[2023-10-16 05:12:52,890][05219] Updated weights for policy 1, policy_version 61500 (0.0007) -[2023-10-16 05:12:54,663][05218] Updated weights for policy 0, policy_version 61702 (0.0009) -[2023-10-16 05:12:55,035][05218] Updated weights for policy 0, policy_version 61712 (0.0007) -[2023-10-16 05:12:55,414][05218] Updated weights for policy 0, policy_version 61722 (0.0008) -[2023-10-16 05:12:56,547][05219] Updated weights for policy 1, policy_version 61510 (0.0007) -[2023-10-16 05:12:56,921][05219] Updated weights for policy 1, policy_version 61520 (0.0008) -[2023-10-16 05:12:57,295][05219] Updated weights for policy 1, policy_version 61530 (0.0007) -[2023-10-16 05:12:57,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 126189568. Throughput: 0: 1796.8, 1: 1785.8. Samples: 31556092. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:12:57,351][03835] Avg episode reward: [(0, '6.640'), (1, '8.000')] -[2023-10-16 05:12:59,007][05218] Updated weights for policy 0, policy_version 61732 (0.0009) -[2023-10-16 05:12:59,384][05218] Updated weights for policy 0, policy_version 61742 (0.0010) -[2023-10-16 05:12:59,761][05218] Updated weights for policy 0, policy_version 61752 (0.0010) -[2023-10-16 05:13:01,080][05219] Updated weights for policy 1, policy_version 61540 (0.0008) -[2023-10-16 05:13:01,451][05219] Updated weights for policy 1, policy_version 61550 (0.0007) -[2023-10-16 05:13:01,811][05219] Updated weights for policy 1, policy_version 61560 (0.0008) -[2023-10-16 05:13:02,351][03835] Fps is (10 sec: 16383.3, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 126287872. Throughput: 0: 1788.7, 1: 1810.1. Samples: 31577952. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:13:02,352][03835] Avg episode reward: [(0, '7.500'), (1, '7.450')] -[2023-10-16 05:13:03,453][05218] Updated weights for policy 0, policy_version 61762 (0.0007) -[2023-10-16 05:13:03,849][05218] Updated weights for policy 0, policy_version 61772 (0.0010) -[2023-10-16 05:13:04,224][05218] Updated weights for policy 0, policy_version 61782 (0.0009) -[2023-10-16 05:13:04,600][05218] Updated weights for policy 0, policy_version 61792 (0.0007) -[2023-10-16 05:13:05,490][05219] Updated weights for policy 1, policy_version 61570 (0.0009) -[2023-10-16 05:13:05,856][05219] Updated weights for policy 1, policy_version 61580 (0.0008) -[2023-10-16 05:13:06,215][05219] Updated weights for policy 1, policy_version 61590 (0.0007) -[2023-10-16 05:13:06,584][05219] Updated weights for policy 1, policy_version 61600 (0.0010) -[2023-10-16 05:13:07,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 126353408. Throughput: 0: 1791.9, 1: 1791.4. Samples: 31599492. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:13:07,351][03835] Avg episode reward: [(0, '7.660'), (1, '7.280')] -[2023-10-16 05:13:08,207][05218] Updated weights for policy 0, policy_version 61802 (0.0010) -[2023-10-16 05:13:08,585][05218] Updated weights for policy 0, policy_version 61812 (0.0009) -[2023-10-16 05:13:08,968][05218] Updated weights for policy 0, policy_version 61822 (0.0008) -[2023-10-16 05:13:10,288][05219] Updated weights for policy 1, policy_version 61610 (0.0007) -[2023-10-16 05:13:10,650][05219] Updated weights for policy 1, policy_version 61620 (0.0007) -[2023-10-16 05:13:11,008][05219] Updated weights for policy 1, policy_version 61630 (0.0008) -[2023-10-16 05:13:12,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 126418944. Throughput: 0: 1792.6, 1: 1810.5. Samples: 31610446. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:13:12,351][03835] Avg episode reward: [(0, '6.730'), (1, '7.710')] -[2023-10-16 05:13:12,856][05218] Updated weights for policy 0, policy_version 61832 (0.0011) -[2023-10-16 05:13:13,232][05218] Updated weights for policy 0, policy_version 61842 (0.0009) -[2023-10-16 05:13:13,611][05218] Updated weights for policy 0, policy_version 61852 (0.0009) -[2023-10-16 05:13:14,605][05219] Updated weights for policy 1, policy_version 61640 (0.0008) -[2023-10-16 05:13:14,972][05219] Updated weights for policy 1, policy_version 61650 (0.0008) -[2023-10-16 05:13:15,344][05219] Updated weights for policy 1, policy_version 61660 (0.0007) -[2023-10-16 05:13:17,332][05218] Updated weights for policy 0, policy_version 61862 (0.0009) -[2023-10-16 05:13:17,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 126484480. Throughput: 0: 1793.1, 1: 1801.6. Samples: 31631846. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:13:17,351][03835] Avg episode reward: [(0, '6.810'), (1, '6.800')] -[2023-10-16 05:13:17,716][05218] Updated weights for policy 0, policy_version 61872 (0.0010) -[2023-10-16 05:13:18,080][05218] Updated weights for policy 0, policy_version 61882 (0.0007) -[2023-10-16 05:13:19,284][05219] Updated weights for policy 1, policy_version 61670 (0.0007) -[2023-10-16 05:13:19,652][05219] Updated weights for policy 1, policy_version 61680 (0.0010) -[2023-10-16 05:13:20,010][05219] Updated weights for policy 1, policy_version 61690 (0.0008) -[2023-10-16 05:13:21,815][05218] Updated weights for policy 0, policy_version 61892 (0.0008) -[2023-10-16 05:13:22,187][05218] Updated weights for policy 0, policy_version 61902 (0.0012) -[2023-10-16 05:13:22,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 126550016. Throughput: 0: 1805.2, 1: 1798.0. Samples: 31653352. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:13:22,351][03835] Avg episode reward: [(0, '6.890'), (1, '7.520')] -[2023-10-16 05:13:22,571][05218] Updated weights for policy 0, policy_version 61912 (0.0007) -[2023-10-16 05:13:23,807][05219] Updated weights for policy 1, policy_version 61700 (0.0011) -[2023-10-16 05:13:24,171][05219] Updated weights for policy 1, policy_version 61710 (0.0009) -[2023-10-16 05:13:24,535][05219] Updated weights for policy 1, policy_version 61720 (0.0008) -[2023-10-16 05:13:26,373][05218] Updated weights for policy 0, policy_version 61922 (0.0007) -[2023-10-16 05:13:26,753][05218] Updated weights for policy 0, policy_version 61932 (0.0009) -[2023-10-16 05:13:27,121][05218] Updated weights for policy 0, policy_version 61942 (0.0008) -[2023-10-16 05:13:27,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 126615552. Throughput: 0: 1796.5, 1: 1793.7. Samples: 31663716. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:13:27,351][03835] Avg episode reward: [(0, '6.920'), (1, '7.710')] -[2023-10-16 05:13:27,500][05218] Updated weights for policy 0, policy_version 61952 (0.0007) -[2023-10-16 05:13:28,305][05219] Updated weights for policy 1, policy_version 61730 (0.0010) -[2023-10-16 05:13:28,671][05219] Updated weights for policy 1, policy_version 61740 (0.0007) -[2023-10-16 05:13:29,036][05219] Updated weights for policy 1, policy_version 61750 (0.0008) -[2023-10-16 05:13:29,404][05219] Updated weights for policy 1, policy_version 61760 (0.0009) -[2023-10-16 05:13:31,275][05218] Updated weights for policy 0, policy_version 61962 (0.0011) -[2023-10-16 05:13:31,656][05218] Updated weights for policy 0, policy_version 61972 (0.0011) -[2023-10-16 05:13:32,029][05218] Updated weights for policy 0, policy_version 61982 (0.0010) -[2023-10-16 05:13:32,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 126713856. Throughput: 0: 1807.6, 1: 1793.1. Samples: 31685620. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:13:32,351][03835] Avg episode reward: [(0, '6.920'), (1, '7.100')] -[2023-10-16 05:13:33,116][05219] Updated weights for policy 1, policy_version 61770 (0.0009) -[2023-10-16 05:13:33,482][05219] Updated weights for policy 1, policy_version 61780 (0.0009) -[2023-10-16 05:13:33,859][05219] Updated weights for policy 1, policy_version 61790 (0.0010) -[2023-10-16 05:13:35,812][05218] Updated weights for policy 0, policy_version 61992 (0.0008) -[2023-10-16 05:13:36,193][05218] Updated weights for policy 0, policy_version 62002 (0.0009) -[2023-10-16 05:13:36,569][05218] Updated weights for policy 0, policy_version 62012 (0.0008) -[2023-10-16 05:13:37,351][03835] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 126779392. Throughput: 0: 1791.0, 1: 1798.9. Samples: 31706942. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:13:37,352][03835] Avg episode reward: [(0, '6.870'), (1, '7.320')] -[2023-10-16 05:13:37,364][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000062016_63504384.pth... -[2023-10-16 05:13:37,404][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000060320_61767680.pth -[2023-10-16 05:13:37,701][05219] Updated weights for policy 1, policy_version 61800 (0.0007) -[2023-10-16 05:13:38,062][05219] Updated weights for policy 1, policy_version 61810 (0.0007) -[2023-10-16 05:13:38,428][05219] Updated weights for policy 1, policy_version 61820 (0.0007) -[2023-10-16 05:13:38,569][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000061824_63307776.pth... -[2023-10-16 05:13:38,598][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000060128_61571072.pth -[2023-10-16 05:13:40,290][05218] Updated weights for policy 0, policy_version 62022 (0.0009) -[2023-10-16 05:13:40,660][05218] Updated weights for policy 0, policy_version 62032 (0.0009) -[2023-10-16 05:13:41,038][05218] Updated weights for policy 0, policy_version 62042 (0.0009) -[2023-10-16 05:13:42,118][05219] Updated weights for policy 1, policy_version 61830 (0.0009) -[2023-10-16 05:13:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 126844928. Throughput: 0: 1809.6, 1: 1791.0. Samples: 31718118. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:13:42,351][03835] Avg episode reward: [(0, '6.790'), (1, '7.970')] -[2023-10-16 05:13:42,477][05219] Updated weights for policy 1, policy_version 61840 (0.0008) -[2023-10-16 05:13:42,844][05219] Updated weights for policy 1, policy_version 61850 (0.0007) -[2023-10-16 05:13:44,815][05218] Updated weights for policy 0, policy_version 62052 (0.0010) -[2023-10-16 05:13:45,191][05218] Updated weights for policy 0, policy_version 62062 (0.0010) -[2023-10-16 05:13:45,574][05218] Updated weights for policy 0, policy_version 62072 (0.0010) -[2023-10-16 05:13:46,675][05219] Updated weights for policy 1, policy_version 61860 (0.0008) -[2023-10-16 05:13:47,035][05219] Updated weights for policy 1, policy_version 61870 (0.0007) -[2023-10-16 05:13:47,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 126910464. Throughput: 0: 1794.7, 1: 1796.7. Samples: 31739564. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:13:47,351][03835] Avg episode reward: [(0, '7.250'), (1, '7.330')] -[2023-10-16 05:13:47,412][05219] Updated weights for policy 1, policy_version 61880 (0.0010) -[2023-10-16 05:13:49,359][05218] Updated weights for policy 0, policy_version 62082 (0.0008) -[2023-10-16 05:13:49,757][05218] Updated weights for policy 0, policy_version 62092 (0.0009) -[2023-10-16 05:13:50,142][05218] Updated weights for policy 0, policy_version 62102 (0.0008) -[2023-10-16 05:13:50,510][05218] Updated weights for policy 0, policy_version 62112 (0.0008) -[2023-10-16 05:13:51,205][05219] Updated weights for policy 1, policy_version 61890 (0.0008) -[2023-10-16 05:13:51,572][05219] Updated weights for policy 1, policy_version 61900 (0.0009) -[2023-10-16 05:13:51,941][05219] Updated weights for policy 1, policy_version 61910 (0.0008) -[2023-10-16 05:13:52,308][05219] Updated weights for policy 1, policy_version 61920 (0.0009) -[2023-10-16 05:13:52,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 127008768. Throughput: 0: 1790.8, 1: 1795.5. Samples: 31760874. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:13:52,352][03835] Avg episode reward: [(0, '6.260'), (1, '7.300')] -[2023-10-16 05:13:54,086][05218] Updated weights for policy 0, policy_version 62122 (0.0008) -[2023-10-16 05:13:54,463][05218] Updated weights for policy 0, policy_version 62132 (0.0009) -[2023-10-16 05:13:54,835][05218] Updated weights for policy 0, policy_version 62142 (0.0010) -[2023-10-16 05:13:56,114][05219] Updated weights for policy 1, policy_version 61930 (0.0010) -[2023-10-16 05:13:56,481][05219] Updated weights for policy 1, policy_version 61940 (0.0009) -[2023-10-16 05:13:56,847][05219] Updated weights for policy 1, policy_version 61950 (0.0008) -[2023-10-16 05:13:57,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 127074304. Throughput: 0: 1789.6, 1: 1794.1. Samples: 31771712. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:13:57,351][03835] Avg episode reward: [(0, '7.170'), (1, '7.050')] -[2023-10-16 05:13:58,365][05218] Updated weights for policy 0, policy_version 62152 (0.0007) -[2023-10-16 05:13:58,738][05218] Updated weights for policy 0, policy_version 62162 (0.0010) -[2023-10-16 05:13:59,104][05218] Updated weights for policy 0, policy_version 62172 (0.0007) -[2023-10-16 05:14:00,648][05219] Updated weights for policy 1, policy_version 61960 (0.0009) -[2023-10-16 05:14:01,008][05219] Updated weights for policy 1, policy_version 61970 (0.0009) -[2023-10-16 05:14:01,386][05219] Updated weights for policy 1, policy_version 61980 (0.0008) -[2023-10-16 05:14:02,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.6, 300 sec: 14329.1). Total num frames: 127139840. Throughput: 0: 1793.7, 1: 1793.2. Samples: 31793260. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:14:02,351][03835] Avg episode reward: [(0, '6.630'), (1, '7.860')] -[2023-10-16 05:14:02,856][05218] Updated weights for policy 0, policy_version 62182 (0.0008) -[2023-10-16 05:14:03,229][05218] Updated weights for policy 0, policy_version 62192 (0.0009) -[2023-10-16 05:14:03,602][05218] Updated weights for policy 0, policy_version 62202 (0.0007) -[2023-10-16 05:14:04,980][05219] Updated weights for policy 1, policy_version 61990 (0.0008) -[2023-10-16 05:14:05,350][05219] Updated weights for policy 1, policy_version 62000 (0.0007) -[2023-10-16 05:14:05,720][05219] Updated weights for policy 1, policy_version 62010 (0.0008) -[2023-10-16 05:14:07,341][05218] Updated weights for policy 0, policy_version 62212 (0.0008) -[2023-10-16 05:14:07,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 127205376. Throughput: 0: 1810.4, 1: 1784.8. Samples: 31815136. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:14:07,351][03835] Avg episode reward: [(0, '6.280'), (1, '7.170')] -[2023-10-16 05:14:07,718][05218] Updated weights for policy 0, policy_version 62222 (0.0009) -[2023-10-16 05:14:08,096][05218] Updated weights for policy 0, policy_version 62232 (0.0009) -[2023-10-16 05:14:09,661][05219] Updated weights for policy 1, policy_version 62020 (0.0008) -[2023-10-16 05:14:10,028][05219] Updated weights for policy 1, policy_version 62030 (0.0008) -[2023-10-16 05:14:10,389][05219] Updated weights for policy 1, policy_version 62040 (0.0007) -[2023-10-16 05:14:11,671][05218] Updated weights for policy 0, policy_version 62242 (0.0007) -[2023-10-16 05:14:12,044][05218] Updated weights for policy 0, policy_version 62252 (0.0007) -[2023-10-16 05:14:12,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 127270912. Throughput: 0: 1803.2, 1: 1803.2. Samples: 31826008. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:14:12,351][03835] Avg episode reward: [(0, '6.370'), (1, '8.320')] -[2023-10-16 05:14:12,419][05218] Updated weights for policy 0, policy_version 62262 (0.0008) -[2023-10-16 05:14:12,796][05218] Updated weights for policy 0, policy_version 62272 (0.0007) -[2023-10-16 05:14:14,091][05219] Updated weights for policy 1, policy_version 62050 (0.0011) -[2023-10-16 05:14:14,453][05219] Updated weights for policy 1, policy_version 62060 (0.0010) -[2023-10-16 05:14:14,828][05219] Updated weights for policy 1, policy_version 62070 (0.0011) -[2023-10-16 05:14:15,187][05219] Updated weights for policy 1, policy_version 62080 (0.0009) -[2023-10-16 05:14:16,483][05218] Updated weights for policy 0, policy_version 62282 (0.0010) -[2023-10-16 05:14:16,859][05218] Updated weights for policy 0, policy_version 62292 (0.0010) -[2023-10-16 05:14:17,229][05218] Updated weights for policy 0, policy_version 62302 (0.0007) -[2023-10-16 05:14:17,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 127369216. Throughput: 0: 1810.1, 1: 1782.6. Samples: 31847292. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:14:17,351][03835] Avg episode reward: [(0, '6.890'), (1, '7.500')] -[2023-10-16 05:14:19,100][05219] Updated weights for policy 1, policy_version 62090 (0.0009) -[2023-10-16 05:14:19,453][05219] Updated weights for policy 1, policy_version 62100 (0.0008) -[2023-10-16 05:14:19,819][05219] Updated weights for policy 1, policy_version 62110 (0.0008) -[2023-10-16 05:14:21,026][05218] Updated weights for policy 0, policy_version 62312 (0.0007) -[2023-10-16 05:14:21,405][05218] Updated weights for policy 0, policy_version 62322 (0.0008) -[2023-10-16 05:14:21,783][05218] Updated weights for policy 0, policy_version 62332 (0.0007) -[2023-10-16 05:14:22,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 127434752. Throughput: 0: 1801.8, 1: 1782.1. Samples: 31868214. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:14:22,351][03835] Avg episode reward: [(0, '6.790'), (1, '7.000')] -[2023-10-16 05:14:23,590][05219] Updated weights for policy 1, policy_version 62120 (0.0008) -[2023-10-16 05:14:23,954][05219] Updated weights for policy 1, policy_version 62130 (0.0007) -[2023-10-16 05:14:24,319][05219] Updated weights for policy 1, policy_version 62140 (0.0010) -[2023-10-16 05:14:25,347][05218] Updated weights for policy 0, policy_version 62342 (0.0009) -[2023-10-16 05:14:25,715][05218] Updated weights for policy 0, policy_version 62352 (0.0010) -[2023-10-16 05:14:26,088][05218] Updated weights for policy 0, policy_version 62362 (0.0011) -[2023-10-16 05:14:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 127500288. Throughput: 0: 1806.7, 1: 1779.1. Samples: 31879480. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:14:27,351][03835] Avg episode reward: [(0, '7.210'), (1, '7.550')] -[2023-10-16 05:14:28,020][05219] Updated weights for policy 1, policy_version 62150 (0.0011) -[2023-10-16 05:14:28,384][05219] Updated weights for policy 1, policy_version 62160 (0.0007) -[2023-10-16 05:14:28,750][05219] Updated weights for policy 1, policy_version 62170 (0.0008) -[2023-10-16 05:14:29,911][05218] Updated weights for policy 0, policy_version 62372 (0.0009) -[2023-10-16 05:14:30,287][05218] Updated weights for policy 0, policy_version 62382 (0.0007) -[2023-10-16 05:14:30,664][05218] Updated weights for policy 0, policy_version 62392 (0.0007) -[2023-10-16 05:14:32,311][05219] Updated weights for policy 1, policy_version 62180 (0.0007) -[2023-10-16 05:14:32,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 127565824. Throughput: 0: 1798.5, 1: 1783.2. Samples: 31900740. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:14:32,351][03835] Avg episode reward: [(0, '7.030'), (1, '7.530')] -[2023-10-16 05:14:32,684][05219] Updated weights for policy 1, policy_version 62190 (0.0009) -[2023-10-16 05:14:33,043][05219] Updated weights for policy 1, policy_version 62200 (0.0007) -[2023-10-16 05:14:34,441][05218] Updated weights for policy 0, policy_version 62402 (0.0009) -[2023-10-16 05:14:34,842][05218] Updated weights for policy 0, policy_version 62412 (0.0007) -[2023-10-16 05:14:35,217][05218] Updated weights for policy 0, policy_version 62422 (0.0008) -[2023-10-16 05:14:35,593][05218] Updated weights for policy 0, policy_version 62432 (0.0008) -[2023-10-16 05:14:36,743][05219] Updated weights for policy 1, policy_version 62210 (0.0008) -[2023-10-16 05:14:37,104][05219] Updated weights for policy 1, policy_version 62220 (0.0008) -[2023-10-16 05:14:37,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 127631360. Throughput: 0: 1795.8, 1: 1803.0. Samples: 31922822. Policy #0 lag: (min: 8.0, avg: 23.9, max: 40.0) -[2023-10-16 05:14:37,352][03835] Avg episode reward: [(0, '6.490'), (1, '7.180')] -[2023-10-16 05:14:37,465][05219] Updated weights for policy 1, policy_version 62230 (0.0007) -[2023-10-16 05:14:37,827][05219] Updated weights for policy 1, policy_version 62240 (0.0008) -[2023-10-16 05:14:39,310][05218] Updated weights for policy 0, policy_version 62442 (0.0007) -[2023-10-16 05:14:39,683][05218] Updated weights for policy 0, policy_version 62452 (0.0008) -[2023-10-16 05:14:40,054][05218] Updated weights for policy 0, policy_version 62462 (0.0009) -[2023-10-16 05:14:41,625][05219] Updated weights for policy 1, policy_version 62250 (0.0008) -[2023-10-16 05:14:41,992][05219] Updated weights for policy 1, policy_version 62260 (0.0009) -[2023-10-16 05:14:42,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 127696896. Throughput: 0: 1798.2, 1: 1792.7. Samples: 31933304. Policy #0 lag: (min: 8.0, avg: 23.9, max: 40.0) -[2023-10-16 05:14:42,351][03835] Avg episode reward: [(0, '6.780'), (1, '6.860')] -[2023-10-16 05:14:42,361][05219] Updated weights for policy 1, policy_version 62270 (0.0011) -[2023-10-16 05:14:43,735][05218] Updated weights for policy 0, policy_version 62472 (0.0008) -[2023-10-16 05:14:44,119][05218] Updated weights for policy 0, policy_version 62482 (0.0010) -[2023-10-16 05:14:44,489][05218] Updated weights for policy 0, policy_version 62492 (0.0008) -[2023-10-16 05:14:46,111][05219] Updated weights for policy 1, policy_version 62280 (0.0007) -[2023-10-16 05:14:46,476][05219] Updated weights for policy 1, policy_version 62290 (0.0007) -[2023-10-16 05:14:46,837][05219] Updated weights for policy 1, policy_version 62300 (0.0007) -[2023-10-16 05:14:47,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 127795200. Throughput: 0: 1791.7, 1: 1800.9. Samples: 31954928. Policy #0 lag: (min: 8.0, avg: 23.9, max: 40.0) -[2023-10-16 05:14:47,351][03835] Avg episode reward: [(0, '6.700'), (1, '8.260')] -[2023-10-16 05:14:48,332][05218] Updated weights for policy 0, policy_version 62502 (0.0009) -[2023-10-16 05:14:48,700][05218] Updated weights for policy 0, policy_version 62512 (0.0009) -[2023-10-16 05:14:49,071][05218] Updated weights for policy 0, policy_version 62522 (0.0009) -[2023-10-16 05:14:50,508][05219] Updated weights for policy 1, policy_version 62310 (0.0008) -[2023-10-16 05:14:50,872][05219] Updated weights for policy 1, policy_version 62320 (0.0007) -[2023-10-16 05:14:51,233][05219] Updated weights for policy 1, policy_version 62330 (0.0007) -[2023-10-16 05:14:52,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 127860736. Throughput: 0: 1794.5, 1: 1791.1. Samples: 31976486. Policy #0 lag: (min: 8.0, avg: 23.9, max: 40.0) -[2023-10-16 05:14:52,351][03835] Avg episode reward: [(0, '6.710'), (1, '6.860')] -[2023-10-16 05:14:52,881][05218] Updated weights for policy 0, policy_version 62532 (0.0009) -[2023-10-16 05:14:53,246][05218] Updated weights for policy 0, policy_version 62542 (0.0010) -[2023-10-16 05:14:53,625][05218] Updated weights for policy 0, policy_version 62552 (0.0007) -[2023-10-16 05:14:54,971][05219] Updated weights for policy 1, policy_version 62340 (0.0009) -[2023-10-16 05:14:55,339][05219] Updated weights for policy 1, policy_version 62350 (0.0007) -[2023-10-16 05:14:55,717][05219] Updated weights for policy 1, policy_version 62360 (0.0009) -[2023-10-16 05:14:57,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 127926272. Throughput: 0: 1782.8, 1: 1801.1. Samples: 31987282. Policy #0 lag: (min: 8.0, avg: 23.9, max: 40.0) -[2023-10-16 05:14:57,351][03835] Avg episode reward: [(0, '6.800'), (1, '7.310')] -[2023-10-16 05:14:57,482][05218] Updated weights for policy 0, policy_version 62562 (0.0007) -[2023-10-16 05:14:57,853][05218] Updated weights for policy 0, policy_version 62572 (0.0009) -[2023-10-16 05:14:58,227][05218] Updated weights for policy 0, policy_version 62582 (0.0009) -[2023-10-16 05:14:58,611][05218] Updated weights for policy 0, policy_version 62592 (0.0009) -[2023-10-16 05:14:59,577][05219] Updated weights for policy 1, policy_version 62370 (0.0008) -[2023-10-16 05:14:59,939][05219] Updated weights for policy 1, policy_version 62380 (0.0007) -[2023-10-16 05:15:00,304][05219] Updated weights for policy 1, policy_version 62390 (0.0007) -[2023-10-16 05:15:00,668][05219] Updated weights for policy 1, policy_version 62400 (0.0010) -[2023-10-16 05:15:02,304][05218] Updated weights for policy 0, policy_version 62602 (0.0010) -[2023-10-16 05:15:02,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 127991808. Throughput: 0: 1787.0, 1: 1795.8. Samples: 32008518. Policy #0 lag: (min: 8.0, avg: 23.9, max: 40.0) -[2023-10-16 05:15:02,351][03835] Avg episode reward: [(0, '6.500'), (1, '8.580')] -[2023-10-16 05:15:02,680][05218] Updated weights for policy 0, policy_version 62612 (0.0009) -[2023-10-16 05:15:03,051][05218] Updated weights for policy 0, policy_version 62622 (0.0010) -[2023-10-16 05:15:04,467][05219] Updated weights for policy 1, policy_version 62410 (0.0007) -[2023-10-16 05:15:04,831][05219] Updated weights for policy 1, policy_version 62420 (0.0007) -[2023-10-16 05:15:05,200][05219] Updated weights for policy 1, policy_version 62430 (0.0007) -[2023-10-16 05:15:06,759][05218] Updated weights for policy 0, policy_version 62632 (0.0011) -[2023-10-16 05:15:07,145][05218] Updated weights for policy 0, policy_version 62642 (0.0009) -[2023-10-16 05:15:07,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 128057344. Throughput: 0: 1794.0, 1: 1794.5. Samples: 32029696. Policy #0 lag: (min: 8.0, avg: 23.9, max: 40.0) -[2023-10-16 05:15:07,351][03835] Avg episode reward: [(0, '6.720'), (1, '6.910')] -[2023-10-16 05:15:07,521][05218] Updated weights for policy 0, policy_version 62652 (0.0008) -[2023-10-16 05:15:09,048][05219] Updated weights for policy 1, policy_version 62440 (0.0009) -[2023-10-16 05:15:09,418][05219] Updated weights for policy 1, policy_version 62450 (0.0007) -[2023-10-16 05:15:09,789][05219] Updated weights for policy 1, policy_version 62460 (0.0007) -[2023-10-16 05:15:11,267][05218] Updated weights for policy 0, policy_version 62662 (0.0009) -[2023-10-16 05:15:11,639][05218] Updated weights for policy 0, policy_version 62672 (0.0007) -[2023-10-16 05:15:12,015][05218] Updated weights for policy 0, policy_version 62682 (0.0008) -[2023-10-16 05:15:12,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 128155648. Throughput: 0: 1783.9, 1: 1794.7. Samples: 32040516. Policy #0 lag: (min: 8.0, avg: 23.9, max: 40.0) -[2023-10-16 05:15:12,351][03835] Avg episode reward: [(0, '6.810'), (1, '7.630')] -[2023-10-16 05:15:13,550][05219] Updated weights for policy 1, policy_version 62470 (0.0009) -[2023-10-16 05:15:13,920][05219] Updated weights for policy 1, policy_version 62480 (0.0007) -[2023-10-16 05:15:14,291][05219] Updated weights for policy 1, policy_version 62490 (0.0009) -[2023-10-16 05:15:15,752][05218] Updated weights for policy 0, policy_version 62692 (0.0008) -[2023-10-16 05:15:16,139][05218] Updated weights for policy 0, policy_version 62702 (0.0010) -[2023-10-16 05:15:16,514][05218] Updated weights for policy 0, policy_version 62712 (0.0008) -[2023-10-16 05:15:17,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 128221184. Throughput: 0: 1797.9, 1: 1790.9. Samples: 32062234. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-16 05:15:17,351][03835] Avg episode reward: [(0, '6.660'), (1, '7.740')] -[2023-10-16 05:15:18,024][05219] Updated weights for policy 1, policy_version 62500 (0.0009) -[2023-10-16 05:15:18,403][05219] Updated weights for policy 1, policy_version 62510 (0.0007) -[2023-10-16 05:15:18,765][05219] Updated weights for policy 1, policy_version 62520 (0.0007) -[2023-10-16 05:15:20,295][05218] Updated weights for policy 0, policy_version 62722 (0.0008) -[2023-10-16 05:15:20,687][05218] Updated weights for policy 0, policy_version 62732 (0.0009) -[2023-10-16 05:15:21,057][05218] Updated weights for policy 0, policy_version 62742 (0.0011) -[2023-10-16 05:15:21,432][05218] Updated weights for policy 0, policy_version 62752 (0.0007) -[2023-10-16 05:15:22,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 128286720. Throughput: 0: 1784.9, 1: 1797.9. Samples: 32084050. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-16 05:15:22,352][03835] Avg episode reward: [(0, '6.640'), (1, '6.710')] -[2023-10-16 05:15:22,618][05219] Updated weights for policy 1, policy_version 62530 (0.0008) -[2023-10-16 05:15:22,982][05219] Updated weights for policy 1, policy_version 62540 (0.0007) -[2023-10-16 05:15:23,341][05219] Updated weights for policy 1, policy_version 62550 (0.0008) -[2023-10-16 05:15:23,701][05219] Updated weights for policy 1, policy_version 62560 (0.0009) -[2023-10-16 05:15:25,114][05218] Updated weights for policy 0, policy_version 62762 (0.0009) -[2023-10-16 05:15:25,495][05218] Updated weights for policy 0, policy_version 62772 (0.0008) -[2023-10-16 05:15:25,878][05218] Updated weights for policy 0, policy_version 62782 (0.0008) -[2023-10-16 05:15:27,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 128352256. Throughput: 0: 1803.7, 1: 1785.0. Samples: 32094792. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-16 05:15:27,351][03835] Avg episode reward: [(0, '6.410'), (1, '6.730')] -[2023-10-16 05:15:27,465][05219] Updated weights for policy 1, policy_version 62570 (0.0009) -[2023-10-16 05:15:27,827][05219] Updated weights for policy 1, policy_version 62580 (0.0007) -[2023-10-16 05:15:28,187][05219] Updated weights for policy 1, policy_version 62590 (0.0007) -[2023-10-16 05:15:29,763][05218] Updated weights for policy 0, policy_version 62792 (0.0009) -[2023-10-16 05:15:30,149][05218] Updated weights for policy 0, policy_version 62802 (0.0009) -[2023-10-16 05:15:30,525][05218] Updated weights for policy 0, policy_version 62812 (0.0010) -[2023-10-16 05:15:32,035][05219] Updated weights for policy 1, policy_version 62600 (0.0008) -[2023-10-16 05:15:32,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 128417792. Throughput: 0: 1788.6, 1: 1801.2. Samples: 32116470. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-16 05:15:32,351][03835] Avg episode reward: [(0, '6.860'), (1, '7.390')] -[2023-10-16 05:15:32,401][05219] Updated weights for policy 1, policy_version 62610 (0.0009) -[2023-10-16 05:15:32,762][05219] Updated weights for policy 1, policy_version 62620 (0.0010) -[2023-10-16 05:15:34,172][05218] Updated weights for policy 0, policy_version 62822 (0.0008) -[2023-10-16 05:15:34,545][05218] Updated weights for policy 0, policy_version 62832 (0.0010) -[2023-10-16 05:15:34,920][05218] Updated weights for policy 0, policy_version 62842 (0.0009) -[2023-10-16 05:15:36,587][05219] Updated weights for policy 1, policy_version 62630 (0.0009) -[2023-10-16 05:15:36,956][05219] Updated weights for policy 1, policy_version 62640 (0.0009) -[2023-10-16 05:15:37,318][05219] Updated weights for policy 1, policy_version 62650 (0.0009) -[2023-10-16 05:15:37,351][03835] Fps is (10 sec: 13106.5, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 128483328. Throughput: 0: 1789.4, 1: 1798.1. Samples: 32137924. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-16 05:15:37,352][03835] Avg episode reward: [(0, '6.370'), (1, '8.070')] -[2023-10-16 05:15:37,366][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000062848_64356352.pth... -[2023-10-16 05:15:37,400][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000061184_62652416.pth -[2023-10-16 05:15:37,534][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000062656_64159744.pth... -[2023-10-16 05:15:37,572][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000060960_62423040.pth -[2023-10-16 05:15:38,832][05218] Updated weights for policy 0, policy_version 62852 (0.0007) -[2023-10-16 05:15:39,212][05218] Updated weights for policy 0, policy_version 62862 (0.0008) -[2023-10-16 05:15:39,583][05218] Updated weights for policy 0, policy_version 62872 (0.0010) -[2023-10-16 05:15:41,189][05219] Updated weights for policy 1, policy_version 62660 (0.0009) -[2023-10-16 05:15:41,559][05219] Updated weights for policy 1, policy_version 62670 (0.0009) -[2023-10-16 05:15:41,917][05219] Updated weights for policy 1, policy_version 62680 (0.0007) -[2023-10-16 05:15:42,350][03835] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 128581632. Throughput: 0: 1788.8, 1: 1791.5. Samples: 32148396. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-16 05:15:42,351][03835] Avg episode reward: [(0, '6.310'), (1, '7.120')] -[2023-10-16 05:15:43,292][05218] Updated weights for policy 0, policy_version 62882 (0.0008) -[2023-10-16 05:15:43,674][05218] Updated weights for policy 0, policy_version 62892 (0.0009) -[2023-10-16 05:15:44,052][05218] Updated weights for policy 0, policy_version 62902 (0.0007) -[2023-10-16 05:15:44,425][05218] Updated weights for policy 0, policy_version 62912 (0.0007) -[2023-10-16 05:15:45,446][05219] Updated weights for policy 1, policy_version 62690 (0.0008) -[2023-10-16 05:15:45,805][05219] Updated weights for policy 1, policy_version 62700 (0.0011) -[2023-10-16 05:15:46,174][05219] Updated weights for policy 1, policy_version 62710 (0.0008) -[2023-10-16 05:15:46,544][05219] Updated weights for policy 1, policy_version 62720 (0.0008) -[2023-10-16 05:15:47,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 128647168. Throughput: 0: 1797.8, 1: 1801.7. Samples: 32170494. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-16 05:15:47,351][03835] Avg episode reward: [(0, '7.210'), (1, '7.560')] -[2023-10-16 05:15:48,028][05218] Updated weights for policy 0, policy_version 62922 (0.0007) -[2023-10-16 05:15:48,401][05218] Updated weights for policy 0, policy_version 62932 (0.0007) -[2023-10-16 05:15:48,774][05218] Updated weights for policy 0, policy_version 62942 (0.0009) -[2023-10-16 05:15:50,272][05219] Updated weights for policy 1, policy_version 62730 (0.0007) -[2023-10-16 05:15:50,645][05219] Updated weights for policy 1, policy_version 62740 (0.0011) -[2023-10-16 05:15:51,005][05219] Updated weights for policy 1, policy_version 62750 (0.0011) -[2023-10-16 05:15:52,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 128712704. Throughput: 0: 1820.1, 1: 1791.0. Samples: 32192196. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-16 05:15:52,351][03835] Avg episode reward: [(0, '6.750'), (1, '7.370')] -[2023-10-16 05:15:52,418][05218] Updated weights for policy 0, policy_version 62952 (0.0010) -[2023-10-16 05:15:52,795][05218] Updated weights for policy 0, policy_version 62962 (0.0010) -[2023-10-16 05:15:53,176][05218] Updated weights for policy 0, policy_version 62972 (0.0008) -[2023-10-16 05:15:54,507][05219] Updated weights for policy 1, policy_version 62760 (0.0008) -[2023-10-16 05:15:54,873][05219] Updated weights for policy 1, policy_version 62770 (0.0007) -[2023-10-16 05:15:55,233][05219] Updated weights for policy 1, policy_version 62780 (0.0007) -[2023-10-16 05:15:57,035][05218] Updated weights for policy 0, policy_version 62982 (0.0009) -[2023-10-16 05:15:57,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 128778240. Throughput: 0: 1801.3, 1: 1808.5. Samples: 32202960. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-16 05:15:57,351][03835] Avg episode reward: [(0, '6.780'), (1, '7.090')] -[2023-10-16 05:15:57,415][05218] Updated weights for policy 0, policy_version 62992 (0.0007) -[2023-10-16 05:15:57,782][05218] Updated weights for policy 0, policy_version 63002 (0.0009) -[2023-10-16 05:15:58,939][05219] Updated weights for policy 1, policy_version 62790 (0.0008) -[2023-10-16 05:15:59,303][05219] Updated weights for policy 1, policy_version 62800 (0.0009) -[2023-10-16 05:15:59,674][05219] Updated weights for policy 1, policy_version 62810 (0.0007) -[2023-10-16 05:16:01,498][05218] Updated weights for policy 0, policy_version 63012 (0.0008) -[2023-10-16 05:16:01,876][05218] Updated weights for policy 0, policy_version 63022 (0.0008) -[2023-10-16 05:16:02,246][05218] Updated weights for policy 0, policy_version 63032 (0.0008) -[2023-10-16 05:16:02,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 128843776. Throughput: 0: 1816.4, 1: 1797.6. Samples: 32224862. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-16 05:16:02,351][03835] Avg episode reward: [(0, '6.690'), (1, '8.220')] -[2023-10-16 05:16:03,625][05219] Updated weights for policy 1, policy_version 62820 (0.0008) -[2023-10-16 05:16:03,998][05219] Updated weights for policy 1, policy_version 62830 (0.0008) -[2023-10-16 05:16:04,358][05219] Updated weights for policy 1, policy_version 62840 (0.0008) -[2023-10-16 05:16:05,941][05218] Updated weights for policy 0, policy_version 63042 (0.0011) -[2023-10-16 05:16:06,325][05218] Updated weights for policy 0, policy_version 63052 (0.0007) -[2023-10-16 05:16:06,700][05218] Updated weights for policy 0, policy_version 63062 (0.0007) -[2023-10-16 05:16:07,063][05218] Updated weights for policy 0, policy_version 63072 (0.0008) -[2023-10-16 05:16:07,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 128942080. Throughput: 0: 1799.4, 1: 1796.9. Samples: 32245882. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-16 05:16:07,351][03835] Avg episode reward: [(0, '6.720'), (1, '7.290')] -[2023-10-16 05:16:08,017][05219] Updated weights for policy 1, policy_version 62850 (0.0010) -[2023-10-16 05:16:08,388][05219] Updated weights for policy 1, policy_version 62860 (0.0008) -[2023-10-16 05:16:08,743][05219] Updated weights for policy 1, policy_version 62870 (0.0010) -[2023-10-16 05:16:09,107][05219] Updated weights for policy 1, policy_version 62880 (0.0011) -[2023-10-16 05:16:10,544][05218] Updated weights for policy 0, policy_version 63082 (0.0008) -[2023-10-16 05:16:10,914][05218] Updated weights for policy 0, policy_version 63092 (0.0008) -[2023-10-16 05:16:11,281][05218] Updated weights for policy 0, policy_version 63102 (0.0007) -[2023-10-16 05:16:12,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 129007616. Throughput: 0: 1815.9, 1: 1792.9. Samples: 32257188. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-16 05:16:12,351][03835] Avg episode reward: [(0, '6.750'), (1, '8.420')] -[2023-10-16 05:16:13,102][05219] Updated weights for policy 1, policy_version 62890 (0.0009) -[2023-10-16 05:16:13,476][05219] Updated weights for policy 1, policy_version 62900 (0.0010) -[2023-10-16 05:16:13,843][05219] Updated weights for policy 1, policy_version 62910 (0.0008) -[2023-10-16 05:16:15,168][05218] Updated weights for policy 0, policy_version 63112 (0.0007) -[2023-10-16 05:16:15,538][05218] Updated weights for policy 0, policy_version 63122 (0.0007) -[2023-10-16 05:16:15,914][05218] Updated weights for policy 0, policy_version 63132 (0.0008) -[2023-10-16 05:16:17,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 129073152. Throughput: 0: 1807.5, 1: 1788.1. Samples: 32278270. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-16 05:16:17,352][03835] Avg episode reward: [(0, '6.830'), (1, '7.240')] -[2023-10-16 05:16:17,510][05219] Updated weights for policy 1, policy_version 62920 (0.0010) -[2023-10-16 05:16:17,875][05219] Updated weights for policy 1, policy_version 62930 (0.0007) -[2023-10-16 05:16:18,243][05219] Updated weights for policy 1, policy_version 62940 (0.0007) -[2023-10-16 05:16:19,652][05218] Updated weights for policy 0, policy_version 63142 (0.0009) -[2023-10-16 05:16:20,031][05218] Updated weights for policy 0, policy_version 63152 (0.0007) -[2023-10-16 05:16:20,409][05218] Updated weights for policy 0, policy_version 63162 (0.0011) -[2023-10-16 05:16:21,996][05219] Updated weights for policy 1, policy_version 62950 (0.0007) -[2023-10-16 05:16:22,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 129138688. Throughput: 0: 1811.3, 1: 1803.0. Samples: 32300566. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-16 05:16:22,351][03835] Avg episode reward: [(0, '6.620'), (1, '8.090')] -[2023-10-16 05:16:22,367][05219] Updated weights for policy 1, policy_version 62960 (0.0008) -[2023-10-16 05:16:22,736][05219] Updated weights for policy 1, policy_version 62970 (0.0008) -[2023-10-16 05:16:23,965][05218] Updated weights for policy 0, policy_version 63172 (0.0009) -[2023-10-16 05:16:24,334][05218] Updated weights for policy 0, policy_version 63182 (0.0009) -[2023-10-16 05:16:24,706][05218] Updated weights for policy 0, policy_version 63192 (0.0008) -[2023-10-16 05:16:26,459][05219] Updated weights for policy 1, policy_version 62980 (0.0009) -[2023-10-16 05:16:26,825][05219] Updated weights for policy 1, policy_version 62990 (0.0008) -[2023-10-16 05:16:27,203][05219] Updated weights for policy 1, policy_version 63000 (0.0007) -[2023-10-16 05:16:27,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 129204224. Throughput: 0: 1818.6, 1: 1793.8. Samples: 32310954. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-16 05:16:27,351][03835] Avg episode reward: [(0, '6.450'), (1, '7.220')] -[2023-10-16 05:16:28,248][05218] Updated weights for policy 0, policy_version 63202 (0.0007) -[2023-10-16 05:16:28,622][05218] Updated weights for policy 0, policy_version 63212 (0.0008) -[2023-10-16 05:16:28,998][05218] Updated weights for policy 0, policy_version 63222 (0.0010) -[2023-10-16 05:16:29,372][05218] Updated weights for policy 0, policy_version 63232 (0.0010) -[2023-10-16 05:16:30,980][05219] Updated weights for policy 1, policy_version 63010 (0.0008) -[2023-10-16 05:16:31,347][05219] Updated weights for policy 1, policy_version 63020 (0.0007) -[2023-10-16 05:16:31,719][05219] Updated weights for policy 1, policy_version 63030 (0.0010) -[2023-10-16 05:16:32,082][05219] Updated weights for policy 1, policy_version 63040 (0.0008) -[2023-10-16 05:16:32,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 129302528. Throughput: 0: 1818.9, 1: 1796.0. Samples: 32333160. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-16 05:16:32,351][03835] Avg episode reward: [(0, '6.650'), (1, '7.330')] -[2023-10-16 05:16:33,056][05218] Updated weights for policy 0, policy_version 63242 (0.0008) -[2023-10-16 05:16:33,425][05218] Updated weights for policy 0, policy_version 63252 (0.0008) -[2023-10-16 05:16:33,795][05218] Updated weights for policy 0, policy_version 63262 (0.0007) -[2023-10-16 05:16:35,843][05219] Updated weights for policy 1, policy_version 63050 (0.0010) -[2023-10-16 05:16:36,198][05219] Updated weights for policy 1, policy_version 63060 (0.0007) -[2023-10-16 05:16:36,572][05219] Updated weights for policy 1, policy_version 63070 (0.0009) -[2023-10-16 05:16:37,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 129368064. Throughput: 0: 1823.2, 1: 1782.8. Samples: 32354464. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-16 05:16:37,351][03835] Avg episode reward: [(0, '6.030'), (1, '6.750')] -[2023-10-16 05:16:37,419][05218] Updated weights for policy 0, policy_version 63272 (0.0008) -[2023-10-16 05:16:37,804][05218] Updated weights for policy 0, policy_version 63282 (0.0010) -[2023-10-16 05:16:38,185][05218] Updated weights for policy 0, policy_version 63292 (0.0009) -[2023-10-16 05:16:40,325][05219] Updated weights for policy 1, policy_version 63080 (0.0010) -[2023-10-16 05:16:40,693][05219] Updated weights for policy 1, policy_version 63090 (0.0010) -[2023-10-16 05:16:41,049][05219] Updated weights for policy 1, policy_version 63100 (0.0007) -[2023-10-16 05:16:41,945][05218] Updated weights for policy 0, policy_version 63302 (0.0009) -[2023-10-16 05:16:42,312][05218] Updated weights for policy 0, policy_version 63312 (0.0009) -[2023-10-16 05:16:42,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 129433600. Throughput: 0: 1822.6, 1: 1798.4. Samples: 32365908. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 05:16:42,351][03835] Avg episode reward: [(0, '6.690'), (1, '6.440')] -[2023-10-16 05:16:42,688][05218] Updated weights for policy 0, policy_version 63322 (0.0008) -[2023-10-16 05:16:44,667][05219] Updated weights for policy 1, policy_version 63110 (0.0007) -[2023-10-16 05:16:45,029][05219] Updated weights for policy 1, policy_version 63120 (0.0007) -[2023-10-16 05:16:45,392][05219] Updated weights for policy 1, policy_version 63130 (0.0008) -[2023-10-16 05:16:46,364][05218] Updated weights for policy 0, policy_version 63332 (0.0009) -[2023-10-16 05:16:46,743][05218] Updated weights for policy 0, policy_version 63342 (0.0009) -[2023-10-16 05:16:47,116][05218] Updated weights for policy 0, policy_version 63352 (0.0008) -[2023-10-16 05:16:47,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 129499136. Throughput: 0: 1819.6, 1: 1781.6. Samples: 32386918. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 05:16:47,351][03835] Avg episode reward: [(0, '6.320'), (1, '7.170')] -[2023-10-16 05:16:49,283][05219] Updated weights for policy 1, policy_version 63140 (0.0008) -[2023-10-16 05:16:49,655][05219] Updated weights for policy 1, policy_version 63150 (0.0009) -[2023-10-16 05:16:50,016][05219] Updated weights for policy 1, policy_version 63160 (0.0010) -[2023-10-16 05:16:50,992][05218] Updated weights for policy 0, policy_version 63362 (0.0008) -[2023-10-16 05:16:51,387][05218] Updated weights for policy 0, policy_version 63372 (0.0007) -[2023-10-16 05:16:51,764][05218] Updated weights for policy 0, policy_version 63382 (0.0008) -[2023-10-16 05:16:52,140][05218] Updated weights for policy 0, policy_version 63392 (0.0007) -[2023-10-16 05:16:52,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 129597440. Throughput: 0: 1814.8, 1: 1779.5. Samples: 32407624. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 05:16:52,351][03835] Avg episode reward: [(0, '6.710'), (1, '7.560')] -[2023-10-16 05:16:53,723][05219] Updated weights for policy 1, policy_version 63170 (0.0010) -[2023-10-16 05:16:54,087][05219] Updated weights for policy 1, policy_version 63180 (0.0008) -[2023-10-16 05:16:54,449][05219] Updated weights for policy 1, policy_version 63190 (0.0008) -[2023-10-16 05:16:54,819][05219] Updated weights for policy 1, policy_version 63200 (0.0010) -[2023-10-16 05:16:55,728][05218] Updated weights for policy 0, policy_version 63402 (0.0009) -[2023-10-16 05:16:56,099][05218] Updated weights for policy 0, policy_version 63412 (0.0009) -[2023-10-16 05:16:56,472][05218] Updated weights for policy 0, policy_version 63422 (0.0008) -[2023-10-16 05:16:57,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 129662976. Throughput: 0: 1814.6, 1: 1781.0. Samples: 32418992. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 05:16:57,351][03835] Avg episode reward: [(0, '7.010'), (1, '6.750')] -[2023-10-16 05:16:58,753][05219] Updated weights for policy 1, policy_version 63210 (0.0009) -[2023-10-16 05:16:59,126][05219] Updated weights for policy 1, policy_version 63220 (0.0007) -[2023-10-16 05:16:59,487][05219] Updated weights for policy 1, policy_version 63230 (0.0008) -[2023-10-16 05:17:00,235][05218] Updated weights for policy 0, policy_version 63432 (0.0008) -[2023-10-16 05:17:00,614][05218] Updated weights for policy 0, policy_version 63442 (0.0007) -[2023-10-16 05:17:00,987][05218] Updated weights for policy 0, policy_version 63452 (0.0007) -[2023-10-16 05:17:02,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 129728512. Throughput: 0: 1811.5, 1: 1783.1. Samples: 32440028. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 05:17:02,351][03835] Avg episode reward: [(0, '6.940'), (1, '6.820')] -[2023-10-16 05:17:03,119][05219] Updated weights for policy 1, policy_version 63240 (0.0008) -[2023-10-16 05:17:03,493][05219] Updated weights for policy 1, policy_version 63250 (0.0010) -[2023-10-16 05:17:03,856][05219] Updated weights for policy 1, policy_version 63260 (0.0011) -[2023-10-16 05:17:04,726][05218] Updated weights for policy 0, policy_version 63462 (0.0007) -[2023-10-16 05:17:05,101][05218] Updated weights for policy 0, policy_version 63472 (0.0009) -[2023-10-16 05:17:05,478][05218] Updated weights for policy 0, policy_version 63482 (0.0010) -[2023-10-16 05:17:07,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 129794048. Throughput: 0: 1804.6, 1: 1801.2. Samples: 32462828. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 05:17:07,351][03835] Avg episode reward: [(0, '6.950'), (1, '7.490')] -[2023-10-16 05:17:07,512][05219] Updated weights for policy 1, policy_version 63270 (0.0008) -[2023-10-16 05:17:07,884][05219] Updated weights for policy 1, policy_version 63280 (0.0009) -[2023-10-16 05:17:08,244][05219] Updated weights for policy 1, policy_version 63290 (0.0009) -[2023-10-16 05:17:09,184][05218] Updated weights for policy 0, policy_version 63492 (0.0009) -[2023-10-16 05:17:09,567][05218] Updated weights for policy 0, policy_version 63502 (0.0010) -[2023-10-16 05:17:09,939][05218] Updated weights for policy 0, policy_version 63512 (0.0009) -[2023-10-16 05:17:12,132][05219] Updated weights for policy 1, policy_version 63300 (0.0007) -[2023-10-16 05:17:12,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 129859584. Throughput: 0: 1801.9, 1: 1788.3. Samples: 32472514. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 05:17:12,351][03835] Avg episode reward: [(0, '6.780'), (1, '7.500')] -[2023-10-16 05:17:12,489][05219] Updated weights for policy 1, policy_version 63310 (0.0007) -[2023-10-16 05:17:12,857][05219] Updated weights for policy 1, policy_version 63320 (0.0007) -[2023-10-16 05:17:13,509][05218] Updated weights for policy 0, policy_version 63522 (0.0007) -[2023-10-16 05:17:13,892][05218] Updated weights for policy 0, policy_version 63532 (0.0009) -[2023-10-16 05:17:14,260][05218] Updated weights for policy 0, policy_version 63542 (0.0010) -[2023-10-16 05:17:14,649][05218] Updated weights for policy 0, policy_version 63552 (0.0009) -[2023-10-16 05:17:16,635][05219] Updated weights for policy 1, policy_version 63330 (0.0008) -[2023-10-16 05:17:17,006][05219] Updated weights for policy 1, policy_version 63340 (0.0009) -[2023-10-16 05:17:17,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 129925120. Throughput: 0: 1797.6, 1: 1800.3. Samples: 32495064. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 05:17:17,351][03835] Avg episode reward: [(0, '6.700'), (1, '7.590')] -[2023-10-16 05:17:17,380][05219] Updated weights for policy 1, policy_version 63350 (0.0009) -[2023-10-16 05:17:17,752][05219] Updated weights for policy 1, policy_version 63360 (0.0009) -[2023-10-16 05:17:18,252][05218] Updated weights for policy 0, policy_version 63562 (0.0008) -[2023-10-16 05:17:18,629][05218] Updated weights for policy 0, policy_version 63572 (0.0008) -[2023-10-16 05:17:18,993][05218] Updated weights for policy 0, policy_version 63582 (0.0009) -[2023-10-16 05:17:21,479][05219] Updated weights for policy 1, policy_version 63370 (0.0008) -[2023-10-16 05:17:21,845][05219] Updated weights for policy 1, policy_version 63380 (0.0007) -[2023-10-16 05:17:22,206][05219] Updated weights for policy 1, policy_version 63390 (0.0008) -[2023-10-16 05:17:22,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 130023424. Throughput: 0: 1801.9, 1: 1802.7. Samples: 32516670. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-16 05:17:22,351][03835] Avg episode reward: [(0, '6.910'), (1, '8.170')] -[2023-10-16 05:17:22,784][05218] Updated weights for policy 0, policy_version 63592 (0.0010) -[2023-10-16 05:17:23,159][05218] Updated weights for policy 0, policy_version 63602 (0.0008) -[2023-10-16 05:17:23,535][05218] Updated weights for policy 0, policy_version 63612 (0.0008) -[2023-10-16 05:17:25,991][05219] Updated weights for policy 1, policy_version 63400 (0.0009) -[2023-10-16 05:17:26,362][05219] Updated weights for policy 1, policy_version 63410 (0.0007) -[2023-10-16 05:17:26,721][05219] Updated weights for policy 1, policy_version 63420 (0.0007) -[2023-10-16 05:17:27,255][05218] Updated weights for policy 0, policy_version 63622 (0.0009) -[2023-10-16 05:17:27,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 130088960. Throughput: 0: 1798.7, 1: 1795.8. Samples: 32527660. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-16 05:17:27,352][03835] Avg episode reward: [(0, '6.750'), (1, '6.930')] -[2023-10-16 05:17:27,635][05218] Updated weights for policy 0, policy_version 63632 (0.0010) -[2023-10-16 05:17:28,014][05218] Updated weights for policy 0, policy_version 63642 (0.0010) -[2023-10-16 05:17:30,484][05219] Updated weights for policy 1, policy_version 63430 (0.0008) -[2023-10-16 05:17:30,838][05219] Updated weights for policy 1, policy_version 63440 (0.0010) -[2023-10-16 05:17:31,204][05219] Updated weights for policy 1, policy_version 63450 (0.0007) -[2023-10-16 05:17:31,946][05218] Updated weights for policy 0, policy_version 63652 (0.0009) -[2023-10-16 05:17:32,328][05218] Updated weights for policy 0, policy_version 63662 (0.0009) -[2023-10-16 05:17:32,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 130154496. Throughput: 0: 1798.4, 1: 1801.5. Samples: 32548916. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-16 05:17:32,351][03835] Avg episode reward: [(0, '6.850'), (1, '7.140')] -[2023-10-16 05:17:32,688][05218] Updated weights for policy 0, policy_version 63672 (0.0008) -[2023-10-16 05:17:34,934][05219] Updated weights for policy 1, policy_version 63460 (0.0009) -[2023-10-16 05:17:35,309][05219] Updated weights for policy 1, policy_version 63470 (0.0008) -[2023-10-16 05:17:35,664][05219] Updated weights for policy 1, policy_version 63480 (0.0008) -[2023-10-16 05:17:36,354][05218] Updated weights for policy 0, policy_version 63682 (0.0008) -[2023-10-16 05:17:36,751][05218] Updated weights for policy 0, policy_version 63692 (0.0011) -[2023-10-16 05:17:37,114][05218] Updated weights for policy 0, policy_version 63702 (0.0009) -[2023-10-16 05:17:37,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 130220032. Throughput: 0: 1802.4, 1: 1796.0. Samples: 32569550. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-16 05:17:37,351][03835] Avg episode reward: [(0, '7.020'), (1, '8.040')] -[2023-10-16 05:17:37,358][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000063488_65011712.pth... -[2023-10-16 05:17:37,387][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000061824_63307776.pth -[2023-10-16 05:17:37,488][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000063712_65241088.pth... -[2023-10-16 05:17:37,491][05218] Updated weights for policy 0, policy_version 63712 (0.0008) -[2023-10-16 05:17:37,529][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000062016_63504384.pth -[2023-10-16 05:17:39,301][05219] Updated weights for policy 1, policy_version 63490 (0.0008) -[2023-10-16 05:17:39,665][05219] Updated weights for policy 1, policy_version 63500 (0.0010) -[2023-10-16 05:17:40,030][05219] Updated weights for policy 1, policy_version 63510 (0.0007) -[2023-10-16 05:17:40,393][05219] Updated weights for policy 1, policy_version 63520 (0.0009) -[2023-10-16 05:17:41,122][05218] Updated weights for policy 0, policy_version 63722 (0.0007) -[2023-10-16 05:17:41,501][05218] Updated weights for policy 0, policy_version 63732 (0.0007) -[2023-10-16 05:17:41,893][05218] Updated weights for policy 0, policy_version 63742 (0.0009) -[2023-10-16 05:17:42,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 130318336. Throughput: 0: 1795.6, 1: 1808.8. Samples: 32581186. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-16 05:17:42,351][03835] Avg episode reward: [(0, '6.650'), (1, '7.510')] -[2023-10-16 05:17:44,241][05219] Updated weights for policy 1, policy_version 63530 (0.0010) -[2023-10-16 05:17:44,608][05219] Updated weights for policy 1, policy_version 63540 (0.0010) -[2023-10-16 05:17:44,970][05219] Updated weights for policy 1, policy_version 63550 (0.0009) -[2023-10-16 05:17:45,658][05218] Updated weights for policy 0, policy_version 63752 (0.0010) -[2023-10-16 05:17:46,044][05218] Updated weights for policy 0, policy_version 63762 (0.0008) -[2023-10-16 05:17:46,415][05218] Updated weights for policy 0, policy_version 63772 (0.0009) -[2023-10-16 05:17:47,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 130383872. Throughput: 0: 1802.4, 1: 1800.8. Samples: 32602174. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-16 05:17:47,352][03835] Avg episode reward: [(0, '6.020'), (1, '7.060')] -[2023-10-16 05:17:48,846][05219] Updated weights for policy 1, policy_version 63560 (0.0010) -[2023-10-16 05:17:49,226][05219] Updated weights for policy 1, policy_version 63570 (0.0009) -[2023-10-16 05:17:49,595][05219] Updated weights for policy 1, policy_version 63580 (0.0007) -[2023-10-16 05:17:50,159][05218] Updated weights for policy 0, policy_version 63782 (0.0009) -[2023-10-16 05:17:50,532][05218] Updated weights for policy 0, policy_version 63792 (0.0009) -[2023-10-16 05:17:50,908][05218] Updated weights for policy 0, policy_version 63802 (0.0010) -[2023-10-16 05:17:52,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 130449408. Throughput: 0: 1795.1, 1: 1785.8. Samples: 32623968. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-16 05:17:52,351][03835] Avg episode reward: [(0, '6.460'), (1, '7.050')] -[2023-10-16 05:17:53,289][05219] Updated weights for policy 1, policy_version 63590 (0.0008) -[2023-10-16 05:17:53,654][05219] Updated weights for policy 1, policy_version 63600 (0.0008) -[2023-10-16 05:17:54,027][05219] Updated weights for policy 1, policy_version 63610 (0.0009) -[2023-10-16 05:17:54,747][05218] Updated weights for policy 0, policy_version 63812 (0.0008) -[2023-10-16 05:17:55,132][05218] Updated weights for policy 0, policy_version 63822 (0.0007) -[2023-10-16 05:17:55,523][05218] Updated weights for policy 0, policy_version 63832 (0.0008) -[2023-10-16 05:17:57,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 130514944. Throughput: 0: 1806.7, 1: 1790.5. Samples: 32634388. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-16 05:17:57,351][03835] Avg episode reward: [(0, '6.290'), (1, '7.640')] -[2023-10-16 05:17:57,787][05219] Updated weights for policy 1, policy_version 63620 (0.0010) -[2023-10-16 05:17:58,149][05219] Updated weights for policy 1, policy_version 63630 (0.0010) -[2023-10-16 05:17:58,522][05219] Updated weights for policy 1, policy_version 63640 (0.0010) -[2023-10-16 05:17:59,325][05218] Updated weights for policy 0, policy_version 63842 (0.0010) -[2023-10-16 05:17:59,699][05218] Updated weights for policy 0, policy_version 63852 (0.0012) -[2023-10-16 05:18:00,076][05218] Updated weights for policy 0, policy_version 63862 (0.0011) -[2023-10-16 05:18:00,453][05218] Updated weights for policy 0, policy_version 63872 (0.0010) -[2023-10-16 05:18:02,339][05219] Updated weights for policy 1, policy_version 63650 (0.0009) -[2023-10-16 05:18:02,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 130580480. Throughput: 0: 1784.0, 1: 1785.6. Samples: 32655692. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-16 05:18:02,351][03835] Avg episode reward: [(0, '6.490'), (1, '7.010')] -[2023-10-16 05:18:02,711][05219] Updated weights for policy 1, policy_version 63660 (0.0008) -[2023-10-16 05:18:03,067][05219] Updated weights for policy 1, policy_version 63670 (0.0010) -[2023-10-16 05:18:03,438][05219] Updated weights for policy 1, policy_version 63680 (0.0009) -[2023-10-16 05:18:04,248][05218] Updated weights for policy 0, policy_version 63882 (0.0009) -[2023-10-16 05:18:04,634][05218] Updated weights for policy 0, policy_version 63892 (0.0008) -[2023-10-16 05:18:05,011][05218] Updated weights for policy 0, policy_version 63902 (0.0008) -[2023-10-16 05:18:07,308][05219] Updated weights for policy 1, policy_version 63690 (0.0008) -[2023-10-16 05:18:07,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 130646016. Throughput: 0: 1778.6, 1: 1799.9. Samples: 32677700. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-16 05:18:07,351][03835] Avg episode reward: [(0, '6.880'), (1, '8.090')] -[2023-10-16 05:18:07,684][05219] Updated weights for policy 1, policy_version 63700 (0.0008) -[2023-10-16 05:18:08,046][05219] Updated weights for policy 1, policy_version 63710 (0.0008) -[2023-10-16 05:18:08,741][05218] Updated weights for policy 0, policy_version 63912 (0.0007) -[2023-10-16 05:18:09,113][05218] Updated weights for policy 0, policy_version 63922 (0.0009) -[2023-10-16 05:18:09,494][05218] Updated weights for policy 0, policy_version 63932 (0.0007) -[2023-10-16 05:18:12,003][05219] Updated weights for policy 1, policy_version 63720 (0.0008) -[2023-10-16 05:18:12,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 130711552. Throughput: 0: 1776.8, 1: 1778.0. Samples: 32687626. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-16 05:18:12,351][03835] Avg episode reward: [(0, '7.190'), (1, '7.550')] -[2023-10-16 05:18:12,364][05219] Updated weights for policy 1, policy_version 63730 (0.0010) -[2023-10-16 05:18:12,734][05219] Updated weights for policy 1, policy_version 63740 (0.0011) -[2023-10-16 05:18:13,150][05218] Updated weights for policy 0, policy_version 63942 (0.0008) -[2023-10-16 05:18:13,525][05218] Updated weights for policy 0, policy_version 63952 (0.0009) -[2023-10-16 05:18:13,906][05218] Updated weights for policy 0, policy_version 63962 (0.0008) -[2023-10-16 05:18:16,495][05219] Updated weights for policy 1, policy_version 63750 (0.0010) -[2023-10-16 05:18:16,852][05219] Updated weights for policy 1, policy_version 63760 (0.0010) -[2023-10-16 05:18:17,219][05219] Updated weights for policy 1, policy_version 63770 (0.0011) -[2023-10-16 05:18:17,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 130777088. Throughput: 0: 1787.5, 1: 1796.1. Samples: 32710178. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-16 05:18:17,351][03835] Avg episode reward: [(0, '6.640'), (1, '8.080')] -[2023-10-16 05:18:17,554][05218] Updated weights for policy 0, policy_version 63972 (0.0009) -[2023-10-16 05:18:17,929][05218] Updated weights for policy 0, policy_version 63982 (0.0009) -[2023-10-16 05:18:18,310][05218] Updated weights for policy 0, policy_version 63992 (0.0009) -[2023-10-16 05:18:21,015][05219] Updated weights for policy 1, policy_version 63780 (0.0009) -[2023-10-16 05:18:21,386][05219] Updated weights for policy 1, policy_version 63790 (0.0009) -[2023-10-16 05:18:21,751][05219] Updated weights for policy 1, policy_version 63800 (0.0009) -[2023-10-16 05:18:22,077][05218] Updated weights for policy 0, policy_version 64002 (0.0008) -[2023-10-16 05:18:22,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 130875392. Throughput: 0: 1811.9, 1: 1767.6. Samples: 32730626. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-16 05:18:22,351][03835] Avg episode reward: [(0, '6.770'), (1, '7.570')] -[2023-10-16 05:18:22,473][05218] Updated weights for policy 0, policy_version 64012 (0.0008) -[2023-10-16 05:18:22,859][05218] Updated weights for policy 0, policy_version 64022 (0.0008) -[2023-10-16 05:18:23,228][05218] Updated weights for policy 0, policy_version 64032 (0.0009) -[2023-10-16 05:18:25,562][05219] Updated weights for policy 1, policy_version 63810 (0.0008) -[2023-10-16 05:18:25,926][05219] Updated weights for policy 1, policy_version 63820 (0.0007) -[2023-10-16 05:18:26,291][05219] Updated weights for policy 1, policy_version 63830 (0.0007) -[2023-10-16 05:18:26,657][05219] Updated weights for policy 1, policy_version 63840 (0.0010) -[2023-10-16 05:18:26,913][05218] Updated weights for policy 0, policy_version 64042 (0.0008) -[2023-10-16 05:18:27,293][05218] Updated weights for policy 0, policy_version 64052 (0.0009) -[2023-10-16 05:18:27,350][03835] Fps is (10 sec: 16383.5, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 130940928. Throughput: 0: 1791.4, 1: 1788.3. Samples: 32742272. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-16 05:18:27,351][03835] Avg episode reward: [(0, '5.760'), (1, '6.990')] -[2023-10-16 05:18:27,668][05218] Updated weights for policy 0, policy_version 64062 (0.0009) -[2023-10-16 05:18:30,475][05219] Updated weights for policy 1, policy_version 63850 (0.0010) -[2023-10-16 05:18:30,834][05219] Updated weights for policy 1, policy_version 63860 (0.0010) -[2023-10-16 05:18:31,210][05219] Updated weights for policy 1, policy_version 63870 (0.0007) -[2023-10-16 05:18:31,421][05218] Updated weights for policy 0, policy_version 64072 (0.0008) -[2023-10-16 05:18:31,802][05218] Updated weights for policy 0, policy_version 64082 (0.0007) -[2023-10-16 05:18:32,173][05218] Updated weights for policy 0, policy_version 64092 (0.0007) -[2023-10-16 05:18:32,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 131039232. Throughput: 0: 1809.0, 1: 1770.4. Samples: 32763246. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-16 05:18:32,351][03835] Avg episode reward: [(0, '5.860'), (1, '7.680')] -[2023-10-16 05:18:34,873][05219] Updated weights for policy 1, policy_version 63880 (0.0009) -[2023-10-16 05:18:35,247][05219] Updated weights for policy 1, policy_version 63890 (0.0009) -[2023-10-16 05:18:35,610][05219] Updated weights for policy 1, policy_version 63900 (0.0008) -[2023-10-16 05:18:35,999][05218] Updated weights for policy 0, policy_version 64102 (0.0009) -[2023-10-16 05:18:36,374][05218] Updated weights for policy 0, policy_version 64112 (0.0011) -[2023-10-16 05:18:36,767][05218] Updated weights for policy 0, policy_version 64122 (0.0010) -[2023-10-16 05:18:37,351][03835] Fps is (10 sec: 16383.5, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 131104768. Throughput: 0: 1787.6, 1: 1773.8. Samples: 32784230. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-16 05:18:37,352][03835] Avg episode reward: [(0, '6.710'), (1, '7.300')] -[2023-10-16 05:18:39,327][05219] Updated weights for policy 1, policy_version 63910 (0.0008) -[2023-10-16 05:18:39,699][05219] Updated weights for policy 1, policy_version 63920 (0.0009) -[2023-10-16 05:18:40,054][05219] Updated weights for policy 1, policy_version 63930 (0.0007) -[2023-10-16 05:18:40,362][05218] Updated weights for policy 0, policy_version 64132 (0.0008) -[2023-10-16 05:18:40,736][05218] Updated weights for policy 0, policy_version 64142 (0.0009) -[2023-10-16 05:18:41,111][05218] Updated weights for policy 0, policy_version 64152 (0.0009) -[2023-10-16 05:18:42,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 131170304. Throughput: 0: 1808.1, 1: 1778.3. Samples: 32795778. Policy #0 lag: (min: 26.0, avg: 28.0, max: 57.0) -[2023-10-16 05:18:42,352][03835] Avg episode reward: [(0, '7.030'), (1, '7.030')] -[2023-10-16 05:18:43,814][05219] Updated weights for policy 1, policy_version 63940 (0.0008) -[2023-10-16 05:18:44,178][05219] Updated weights for policy 1, policy_version 63950 (0.0009) -[2023-10-16 05:18:44,537][05219] Updated weights for policy 1, policy_version 63960 (0.0007) -[2023-10-16 05:18:44,954][05218] Updated weights for policy 0, policy_version 64162 (0.0009) -[2023-10-16 05:18:45,342][05218] Updated weights for policy 0, policy_version 64172 (0.0010) -[2023-10-16 05:18:45,712][05218] Updated weights for policy 0, policy_version 64182 (0.0010) -[2023-10-16 05:18:46,082][05218] Updated weights for policy 0, policy_version 64192 (0.0009) -[2023-10-16 05:18:47,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 131235840. Throughput: 0: 1793.0, 1: 1781.9. Samples: 32816562. Policy #0 lag: (min: 26.0, avg: 28.0, max: 57.0) -[2023-10-16 05:18:47,352][03835] Avg episode reward: [(0, '6.690'), (1, '7.660')] -[2023-10-16 05:18:48,209][05219] Updated weights for policy 1, policy_version 63970 (0.0008) -[2023-10-16 05:18:48,577][05219] Updated weights for policy 1, policy_version 63980 (0.0009) -[2023-10-16 05:18:48,951][05219] Updated weights for policy 1, policy_version 63990 (0.0009) -[2023-10-16 05:18:49,316][05219] Updated weights for policy 1, policy_version 64000 (0.0007) -[2023-10-16 05:18:49,835][05218] Updated weights for policy 0, policy_version 64202 (0.0009) -[2023-10-16 05:18:50,200][05218] Updated weights for policy 0, policy_version 64212 (0.0008) -[2023-10-16 05:18:50,587][05218] Updated weights for policy 0, policy_version 64222 (0.0011) -[2023-10-16 05:18:52,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 131301376. Throughput: 0: 1789.6, 1: 1794.8. Samples: 32838994. Policy #0 lag: (min: 26.0, avg: 28.0, max: 57.0) -[2023-10-16 05:18:52,351][03835] Avg episode reward: [(0, '7.310'), (1, '8.000')] -[2023-10-16 05:18:52,999][05219] Updated weights for policy 1, policy_version 64010 (0.0010) -[2023-10-16 05:18:53,361][05219] Updated weights for policy 1, policy_version 64020 (0.0008) -[2023-10-16 05:18:53,730][05219] Updated weights for policy 1, policy_version 64030 (0.0007) -[2023-10-16 05:18:54,267][05218] Updated weights for policy 0, policy_version 64232 (0.0011) -[2023-10-16 05:18:54,649][05218] Updated weights for policy 0, policy_version 64242 (0.0010) -[2023-10-16 05:18:55,016][05218] Updated weights for policy 0, policy_version 64252 (0.0011) -[2023-10-16 05:18:57,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 131366912. Throughput: 0: 1791.0, 1: 1789.2. Samples: 32848734. Policy #0 lag: (min: 26.0, avg: 28.0, max: 57.0) -[2023-10-16 05:18:57,351][03835] Avg episode reward: [(0, '6.780'), (1, '7.700')] -[2023-10-16 05:18:57,694][05219] Updated weights for policy 1, policy_version 64040 (0.0008) -[2023-10-16 05:18:58,065][05219] Updated weights for policy 1, policy_version 64050 (0.0007) -[2023-10-16 05:18:58,425][05219] Updated weights for policy 1, policy_version 64060 (0.0007) -[2023-10-16 05:18:58,869][05218] Updated weights for policy 0, policy_version 64262 (0.0009) -[2023-10-16 05:18:59,243][05218] Updated weights for policy 0, policy_version 64272 (0.0008) -[2023-10-16 05:18:59,619][05218] Updated weights for policy 0, policy_version 64282 (0.0009) -[2023-10-16 05:19:02,239][05219] Updated weights for policy 1, policy_version 64070 (0.0007) -[2023-10-16 05:19:02,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 131432448. Throughput: 0: 1783.1, 1: 1790.7. Samples: 32870998. Policy #0 lag: (min: 26.0, avg: 28.0, max: 57.0) -[2023-10-16 05:19:02,351][03835] Avg episode reward: [(0, '6.090'), (1, '7.450')] -[2023-10-16 05:19:02,600][05219] Updated weights for policy 1, policy_version 64080 (0.0008) -[2023-10-16 05:19:02,972][05219] Updated weights for policy 1, policy_version 64090 (0.0009) -[2023-10-16 05:19:03,321][05218] Updated weights for policy 0, policy_version 64292 (0.0009) -[2023-10-16 05:19:03,689][05218] Updated weights for policy 0, policy_version 64302 (0.0008) -[2023-10-16 05:19:04,064][05218] Updated weights for policy 0, policy_version 64312 (0.0009) -[2023-10-16 05:19:06,847][05219] Updated weights for policy 1, policy_version 64100 (0.0009) -[2023-10-16 05:19:07,212][05219] Updated weights for policy 1, policy_version 64110 (0.0007) -[2023-10-16 05:19:07,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 131497984. Throughput: 0: 1799.4, 1: 1810.0. Samples: 32893048. Policy #0 lag: (min: 26.0, avg: 28.0, max: 57.0) -[2023-10-16 05:19:07,351][03835] Avg episode reward: [(0, '6.970'), (1, '7.370')] -[2023-10-16 05:19:07,584][05219] Updated weights for policy 1, policy_version 64120 (0.0008) -[2023-10-16 05:19:07,676][05218] Updated weights for policy 0, policy_version 64322 (0.0010) -[2023-10-16 05:19:08,076][05218] Updated weights for policy 0, policy_version 64332 (0.0009) -[2023-10-16 05:19:08,447][05218] Updated weights for policy 0, policy_version 64342 (0.0011) -[2023-10-16 05:19:08,822][05218] Updated weights for policy 0, policy_version 64352 (0.0007) -[2023-10-16 05:19:11,197][05219] Updated weights for policy 1, policy_version 64130 (0.0007) -[2023-10-16 05:19:11,561][05219] Updated weights for policy 1, policy_version 64140 (0.0009) -[2023-10-16 05:19:11,928][05219] Updated weights for policy 1, policy_version 64150 (0.0007) -[2023-10-16 05:19:12,292][05219] Updated weights for policy 1, policy_version 64160 (0.0008) -[2023-10-16 05:19:12,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 131596288. Throughput: 0: 1789.7, 1: 1790.1. Samples: 32903366. Policy #0 lag: (min: 26.0, avg: 28.0, max: 57.0) -[2023-10-16 05:19:12,351][03835] Avg episode reward: [(0, '6.740'), (1, '8.030')] -[2023-10-16 05:19:12,526][05218] Updated weights for policy 0, policy_version 64362 (0.0011) -[2023-10-16 05:19:12,906][05218] Updated weights for policy 0, policy_version 64372 (0.0011) -[2023-10-16 05:19:13,288][05218] Updated weights for policy 0, policy_version 64382 (0.0009) -[2023-10-16 05:19:16,046][05219] Updated weights for policy 1, policy_version 64170 (0.0008) -[2023-10-16 05:19:16,412][05219] Updated weights for policy 1, policy_version 64180 (0.0008) -[2023-10-16 05:19:16,769][05219] Updated weights for policy 1, policy_version 64190 (0.0009) -[2023-10-16 05:19:17,048][05218] Updated weights for policy 0, policy_version 64392 (0.0007) -[2023-10-16 05:19:17,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 131661824. Throughput: 0: 1801.0, 1: 1802.5. Samples: 32925402. Policy #0 lag: (min: 26.0, avg: 28.0, max: 57.0) -[2023-10-16 05:19:17,351][03835] Avg episode reward: [(0, '6.320'), (1, '7.400')] -[2023-10-16 05:19:17,421][05218] Updated weights for policy 0, policy_version 64402 (0.0008) -[2023-10-16 05:19:17,798][05218] Updated weights for policy 0, policy_version 64412 (0.0007) -[2023-10-16 05:19:20,641][05219] Updated weights for policy 1, policy_version 64200 (0.0011) -[2023-10-16 05:19:21,011][05219] Updated weights for policy 1, policy_version 64210 (0.0009) -[2023-10-16 05:19:21,385][05219] Updated weights for policy 1, policy_version 64220 (0.0010) -[2023-10-16 05:19:21,426][05218] Updated weights for policy 0, policy_version 64422 (0.0007) -[2023-10-16 05:19:21,790][05218] Updated weights for policy 0, policy_version 64432 (0.0010) -[2023-10-16 05:19:22,157][05218] Updated weights for policy 0, policy_version 64442 (0.0010) -[2023-10-16 05:19:22,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 131727360. Throughput: 0: 1802.1, 1: 1783.1. Samples: 32945564. Policy #0 lag: (min: 26.0, avg: 28.0, max: 57.0) -[2023-10-16 05:19:22,351][03835] Avg episode reward: [(0, '6.470'), (1, '7.860')] -[2023-10-16 05:19:25,219][05219] Updated weights for policy 1, policy_version 64230 (0.0008) -[2023-10-16 05:19:25,581][05219] Updated weights for policy 1, policy_version 64240 (0.0007) -[2023-10-16 05:19:25,942][05219] Updated weights for policy 1, policy_version 64250 (0.0008) -[2023-10-16 05:19:26,076][05218] Updated weights for policy 0, policy_version 64452 (0.0009) -[2023-10-16 05:19:26,441][05218] Updated weights for policy 0, policy_version 64462 (0.0007) -[2023-10-16 05:19:26,822][05218] Updated weights for policy 0, policy_version 64472 (0.0008) -[2023-10-16 05:19:27,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 131825664. Throughput: 0: 1796.9, 1: 1807.3. Samples: 32957966. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:19:27,351][03835] Avg episode reward: [(0, '7.280'), (1, '7.840')] -[2023-10-16 05:19:29,757][05219] Updated weights for policy 1, policy_version 64260 (0.0010) -[2023-10-16 05:19:30,128][05219] Updated weights for policy 1, policy_version 64270 (0.0009) -[2023-10-16 05:19:30,396][05218] Updated weights for policy 0, policy_version 64482 (0.0007) -[2023-10-16 05:19:30,493][05219] Updated weights for policy 1, policy_version 64280 (0.0007) -[2023-10-16 05:19:30,764][05218] Updated weights for policy 0, policy_version 64492 (0.0009) -[2023-10-16 05:19:31,137][05218] Updated weights for policy 0, policy_version 64502 (0.0011) -[2023-10-16 05:19:31,511][05218] Updated weights for policy 0, policy_version 64512 (0.0007) -[2023-10-16 05:19:32,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14440.2). Total num frames: 131891200. Throughput: 0: 1809.6, 1: 1780.7. Samples: 32978126. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:19:32,351][03835] Avg episode reward: [(0, '6.490'), (1, '7.440')] -[2023-10-16 05:19:34,308][05219] Updated weights for policy 1, policy_version 64290 (0.0009) -[2023-10-16 05:19:34,682][05219] Updated weights for policy 1, policy_version 64300 (0.0011) -[2023-10-16 05:19:35,047][05219] Updated weights for policy 1, policy_version 64310 (0.0008) -[2023-10-16 05:19:35,215][05218] Updated weights for policy 0, policy_version 64522 (0.0009) -[2023-10-16 05:19:35,420][05219] Updated weights for policy 1, policy_version 64320 (0.0007) -[2023-10-16 05:19:35,583][05218] Updated weights for policy 0, policy_version 64532 (0.0009) -[2023-10-16 05:19:35,965][05218] Updated weights for policy 0, policy_version 64542 (0.0008) -[2023-10-16 05:19:37,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.6, 300 sec: 14440.1). Total num frames: 131956736. Throughput: 0: 1803.7, 1: 1776.0. Samples: 33000082. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:19:37,351][03835] Avg episode reward: [(0, '6.510'), (1, '6.800')] -[2023-10-16 05:19:37,362][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000064544_66093056.pth... -[2023-10-16 05:19:37,363][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000064320_65863680.pth... -[2023-10-16 05:19:37,397][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000062848_64356352.pth -[2023-10-16 05:19:37,398][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000062656_64159744.pth -[2023-10-16 05:19:39,019][05219] Updated weights for policy 1, policy_version 64330 (0.0008) -[2023-10-16 05:19:39,385][05219] Updated weights for policy 1, policy_version 64340 (0.0007) -[2023-10-16 05:19:39,750][05219] Updated weights for policy 1, policy_version 64350 (0.0009) -[2023-10-16 05:19:39,765][05218] Updated weights for policy 0, policy_version 64552 (0.0008) -[2023-10-16 05:19:40,137][05218] Updated weights for policy 0, policy_version 64562 (0.0007) -[2023-10-16 05:19:40,509][05218] Updated weights for policy 0, policy_version 64572 (0.0009) -[2023-10-16 05:19:42,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 132022272. Throughput: 0: 1810.8, 1: 1777.5. Samples: 33010210. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:19:42,351][03835] Avg episode reward: [(0, '6.860'), (1, '7.480')] -[2023-10-16 05:19:43,360][05219] Updated weights for policy 1, policy_version 64360 (0.0009) -[2023-10-16 05:19:43,731][05219] Updated weights for policy 1, policy_version 64370 (0.0010) -[2023-10-16 05:19:44,092][05219] Updated weights for policy 1, policy_version 64380 (0.0008) -[2023-10-16 05:19:44,237][05218] Updated weights for policy 0, policy_version 64582 (0.0009) -[2023-10-16 05:19:44,605][05218] Updated weights for policy 0, policy_version 64592 (0.0009) -[2023-10-16 05:19:44,975][05218] Updated weights for policy 0, policy_version 64602 (0.0007) -[2023-10-16 05:19:47,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 132087808. Throughput: 0: 1800.5, 1: 1783.0. Samples: 33032254. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:19:47,351][03835] Avg episode reward: [(0, '6.030'), (1, '7.830')] -[2023-10-16 05:19:47,751][05219] Updated weights for policy 1, policy_version 64390 (0.0009) -[2023-10-16 05:19:48,117][05219] Updated weights for policy 1, policy_version 64400 (0.0008) -[2023-10-16 05:19:48,491][05219] Updated weights for policy 1, policy_version 64410 (0.0009) -[2023-10-16 05:19:48,806][05218] Updated weights for policy 0, policy_version 64612 (0.0008) -[2023-10-16 05:19:49,171][05218] Updated weights for policy 0, policy_version 64622 (0.0009) -[2023-10-16 05:19:49,555][05218] Updated weights for policy 0, policy_version 64632 (0.0012) -[2023-10-16 05:19:52,205][05219] Updated weights for policy 1, policy_version 64420 (0.0009) -[2023-10-16 05:19:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 132153344. Throughput: 0: 1788.3, 1: 1799.6. Samples: 33054500. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:19:52,351][03835] Avg episode reward: [(0, '6.630'), (1, '7.380')] -[2023-10-16 05:19:52,568][05219] Updated weights for policy 1, policy_version 64430 (0.0011) -[2023-10-16 05:19:52,932][05219] Updated weights for policy 1, policy_version 64440 (0.0007) -[2023-10-16 05:19:53,410][05218] Updated weights for policy 0, policy_version 64642 (0.0009) -[2023-10-16 05:19:53,805][05218] Updated weights for policy 0, policy_version 64652 (0.0008) -[2023-10-16 05:19:54,176][05218] Updated weights for policy 0, policy_version 64662 (0.0010) -[2023-10-16 05:19:54,548][05218] Updated weights for policy 0, policy_version 64672 (0.0010) -[2023-10-16 05:19:56,686][05219] Updated weights for policy 1, policy_version 64450 (0.0007) -[2023-10-16 05:19:57,049][05219] Updated weights for policy 1, policy_version 64460 (0.0007) -[2023-10-16 05:19:57,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 132218880. Throughput: 0: 1786.1, 1: 1791.3. Samples: 33064352. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:19:57,351][03835] Avg episode reward: [(0, '6.880'), (1, '7.820')] -[2023-10-16 05:19:57,412][05219] Updated weights for policy 1, policy_version 64470 (0.0008) -[2023-10-16 05:19:57,774][05219] Updated weights for policy 1, policy_version 64480 (0.0010) -[2023-10-16 05:19:58,245][05218] Updated weights for policy 0, policy_version 64682 (0.0007) -[2023-10-16 05:19:58,634][05218] Updated weights for policy 0, policy_version 64692 (0.0009) -[2023-10-16 05:19:59,006][05218] Updated weights for policy 0, policy_version 64702 (0.0009) -[2023-10-16 05:20:01,649][05219] Updated weights for policy 1, policy_version 64490 (0.0008) -[2023-10-16 05:20:02,012][05219] Updated weights for policy 1, policy_version 64500 (0.0010) -[2023-10-16 05:20:02,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 132284416. Throughput: 0: 1787.1, 1: 1803.6. Samples: 33086984. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:20:02,351][03835] Avg episode reward: [(0, '6.960'), (1, '7.080')] -[2023-10-16 05:20:02,383][05219] Updated weights for policy 1, policy_version 64510 (0.0009) -[2023-10-16 05:20:02,560][05218] Updated weights for policy 0, policy_version 64712 (0.0008) -[2023-10-16 05:20:02,932][05218] Updated weights for policy 0, policy_version 64722 (0.0010) -[2023-10-16 05:20:03,302][05218] Updated weights for policy 0, policy_version 64732 (0.0008) -[2023-10-16 05:20:06,362][05219] Updated weights for policy 1, policy_version 64520 (0.0007) -[2023-10-16 05:20:06,722][05219] Updated weights for policy 1, policy_version 64530 (0.0007) -[2023-10-16 05:20:06,947][05218] Updated weights for policy 0, policy_version 64742 (0.0008) -[2023-10-16 05:20:07,083][05219] Updated weights for policy 1, policy_version 64540 (0.0007) -[2023-10-16 05:20:07,313][05218] Updated weights for policy 0, policy_version 64752 (0.0007) -[2023-10-16 05:20:07,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 132382720. Throughput: 0: 1805.8, 1: 1794.6. Samples: 33107580. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) -[2023-10-16 05:20:07,352][03835] Avg episode reward: [(0, '6.930'), (1, '6.430')] -[2023-10-16 05:20:07,693][05218] Updated weights for policy 0, policy_version 64762 (0.0010) -[2023-10-16 05:20:10,916][05219] Updated weights for policy 1, policy_version 64550 (0.0008) -[2023-10-16 05:20:11,283][05219] Updated weights for policy 1, policy_version 64560 (0.0008) -[2023-10-16 05:20:11,345][05218] Updated weights for policy 0, policy_version 64772 (0.0010) -[2023-10-16 05:20:11,644][05219] Updated weights for policy 1, policy_version 64570 (0.0008) -[2023-10-16 05:20:11,726][05218] Updated weights for policy 0, policy_version 64782 (0.0008) -[2023-10-16 05:20:12,091][05218] Updated weights for policy 0, policy_version 64792 (0.0009) -[2023-10-16 05:20:12,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 132448256. Throughput: 0: 1799.1, 1: 1792.2. Samples: 33119576. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) -[2023-10-16 05:20:12,351][03835] Avg episode reward: [(0, '6.330'), (1, '6.400')] -[2023-10-16 05:20:15,380][05219] Updated weights for policy 1, policy_version 64580 (0.0008) -[2023-10-16 05:20:15,743][05219] Updated weights for policy 1, policy_version 64590 (0.0009) -[2023-10-16 05:20:15,874][05218] Updated weights for policy 0, policy_version 64802 (0.0007) -[2023-10-16 05:20:16,106][05219] Updated weights for policy 1, policy_version 64600 (0.0009) -[2023-10-16 05:20:16,255][05218] Updated weights for policy 0, policy_version 64812 (0.0010) -[2023-10-16 05:20:16,615][05218] Updated weights for policy 0, policy_version 64822 (0.0009) -[2023-10-16 05:20:16,991][05218] Updated weights for policy 0, policy_version 64832 (0.0008) -[2023-10-16 05:20:17,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 132546560. Throughput: 0: 1804.3, 1: 1796.5. Samples: 33140160. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) -[2023-10-16 05:20:17,351][03835] Avg episode reward: [(0, '6.260'), (1, '7.910')] -[2023-10-16 05:20:19,896][05219] Updated weights for policy 1, policy_version 64610 (0.0010) -[2023-10-16 05:20:20,263][05219] Updated weights for policy 1, policy_version 64620 (0.0007) -[2023-10-16 05:20:20,633][05219] Updated weights for policy 1, policy_version 64630 (0.0009) -[2023-10-16 05:20:20,704][05218] Updated weights for policy 0, policy_version 64842 (0.0010) -[2023-10-16 05:20:20,992][05219] Updated weights for policy 1, policy_version 64640 (0.0008) -[2023-10-16 05:20:21,075][05218] Updated weights for policy 0, policy_version 64852 (0.0009) -[2023-10-16 05:20:21,447][05218] Updated weights for policy 0, policy_version 64862 (0.0008) -[2023-10-16 05:20:22,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 132612096. Throughput: 0: 1794.9, 1: 1792.8. Samples: 33161530. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) -[2023-10-16 05:20:22,351][03835] Avg episode reward: [(0, '6.470'), (1, '7.310')] -[2023-10-16 05:20:24,776][05219] Updated weights for policy 1, policy_version 64650 (0.0008) -[2023-10-16 05:20:25,075][05218] Updated weights for policy 0, policy_version 64872 (0.0008) -[2023-10-16 05:20:25,134][05219] Updated weights for policy 1, policy_version 64660 (0.0007) -[2023-10-16 05:20:25,449][05218] Updated weights for policy 0, policy_version 64882 (0.0007) -[2023-10-16 05:20:25,508][05219] Updated weights for policy 1, policy_version 64670 (0.0008) -[2023-10-16 05:20:25,819][05218] Updated weights for policy 0, policy_version 64892 (0.0007) -[2023-10-16 05:20:27,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 132677632. Throughput: 0: 1808.4, 1: 1805.8. Samples: 33172846. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) -[2023-10-16 05:20:27,351][03835] Avg episode reward: [(0, '6.750'), (1, '7.360')] -[2023-10-16 05:20:29,140][05219] Updated weights for policy 1, policy_version 64680 (0.0009) -[2023-10-16 05:20:29,500][05219] Updated weights for policy 1, policy_version 64690 (0.0008) -[2023-10-16 05:20:29,639][05218] Updated weights for policy 0, policy_version 64902 (0.0009) -[2023-10-16 05:20:29,868][05219] Updated weights for policy 1, policy_version 64700 (0.0007) -[2023-10-16 05:20:30,009][05218] Updated weights for policy 0, policy_version 64912 (0.0008) -[2023-10-16 05:20:30,397][05218] Updated weights for policy 0, policy_version 64922 (0.0010) -[2023-10-16 05:20:32,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14440.2). Total num frames: 132743168. Throughput: 0: 1798.3, 1: 1790.7. Samples: 33193760. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) -[2023-10-16 05:20:32,351][03835] Avg episode reward: [(0, '6.360'), (1, '7.560')] -[2023-10-16 05:20:33,555][05219] Updated weights for policy 1, policy_version 64710 (0.0007) -[2023-10-16 05:20:33,920][05219] Updated weights for policy 1, policy_version 64720 (0.0007) -[2023-10-16 05:20:34,136][05218] Updated weights for policy 0, policy_version 64932 (0.0009) -[2023-10-16 05:20:34,283][05219] Updated weights for policy 1, policy_version 64730 (0.0009) -[2023-10-16 05:20:34,511][05218] Updated weights for policy 0, policy_version 64942 (0.0008) -[2023-10-16 05:20:34,891][05218] Updated weights for policy 0, policy_version 64952 (0.0009) -[2023-10-16 05:20:37,351][03835] Fps is (10 sec: 13106.6, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 132808704. Throughput: 0: 1799.7, 1: 1791.1. Samples: 33216086. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) -[2023-10-16 05:20:37,352][03835] Avg episode reward: [(0, '6.870'), (1, '7.010')] -[2023-10-16 05:20:38,103][05219] Updated weights for policy 1, policy_version 64740 (0.0008) -[2023-10-16 05:20:38,470][05219] Updated weights for policy 1, policy_version 64750 (0.0009) -[2023-10-16 05:20:38,676][05218] Updated weights for policy 0, policy_version 64962 (0.0010) -[2023-10-16 05:20:38,835][05219] Updated weights for policy 1, policy_version 64760 (0.0007) -[2023-10-16 05:20:39,067][05218] Updated weights for policy 0, policy_version 64972 (0.0010) -[2023-10-16 05:20:39,437][05218] Updated weights for policy 0, policy_version 64982 (0.0008) -[2023-10-16 05:20:39,818][05218] Updated weights for policy 0, policy_version 64992 (0.0008) -[2023-10-16 05:20:42,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 132874240. Throughput: 0: 1802.3, 1: 1787.5. Samples: 33225890. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) -[2023-10-16 05:20:42,351][03835] Avg episode reward: [(0, '6.850'), (1, '7.100')] -[2023-10-16 05:20:42,664][05219] Updated weights for policy 1, policy_version 64770 (0.0009) -[2023-10-16 05:20:43,031][05219] Updated weights for policy 1, policy_version 64780 (0.0007) -[2023-10-16 05:20:43,392][05219] Updated weights for policy 1, policy_version 64790 (0.0007) -[2023-10-16 05:20:43,599][05218] Updated weights for policy 0, policy_version 65002 (0.0010) -[2023-10-16 05:20:43,750][05219] Updated weights for policy 1, policy_version 64800 (0.0007) -[2023-10-16 05:20:43,976][05218] Updated weights for policy 0, policy_version 65012 (0.0009) -[2023-10-16 05:20:44,351][05218] Updated weights for policy 0, policy_version 65022 (0.0009) -[2023-10-16 05:20:47,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 132939776. Throughput: 0: 1794.6, 1: 1787.2. Samples: 33248164. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-16 05:20:47,351][03835] Avg episode reward: [(0, '7.020'), (1, '7.130')] -[2023-10-16 05:20:47,400][05219] Updated weights for policy 1, policy_version 64810 (0.0008) -[2023-10-16 05:20:47,766][05219] Updated weights for policy 1, policy_version 64820 (0.0008) -[2023-10-16 05:20:48,097][05218] Updated weights for policy 0, policy_version 65032 (0.0008) -[2023-10-16 05:20:48,126][05219] Updated weights for policy 1, policy_version 64830 (0.0007) -[2023-10-16 05:20:48,471][05218] Updated weights for policy 0, policy_version 65042 (0.0009) -[2023-10-16 05:20:48,843][05218] Updated weights for policy 0, policy_version 65052 (0.0008) -[2023-10-16 05:20:52,044][05219] Updated weights for policy 1, policy_version 64840 (0.0007) -[2023-10-16 05:20:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 133005312. Throughput: 0: 1800.3, 1: 1805.3. Samples: 33269832. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-16 05:20:52,352][03835] Avg episode reward: [(0, '6.810'), (1, '7.190')] -[2023-10-16 05:20:52,420][05219] Updated weights for policy 1, policy_version 64850 (0.0008) -[2023-10-16 05:20:52,751][05218] Updated weights for policy 0, policy_version 65062 (0.0009) -[2023-10-16 05:20:52,784][05219] Updated weights for policy 1, policy_version 64860 (0.0008) -[2023-10-16 05:20:53,122][05218] Updated weights for policy 0, policy_version 65072 (0.0008) -[2023-10-16 05:20:53,500][05218] Updated weights for policy 0, policy_version 65082 (0.0009) -[2023-10-16 05:20:56,400][05219] Updated weights for policy 1, policy_version 64870 (0.0009) -[2023-10-16 05:20:56,770][05219] Updated weights for policy 1, policy_version 64880 (0.0008) -[2023-10-16 05:20:57,136][05219] Updated weights for policy 1, policy_version 64890 (0.0007) -[2023-10-16 05:20:57,236][05218] Updated weights for policy 0, policy_version 65092 (0.0008) -[2023-10-16 05:20:57,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 133070848. Throughput: 0: 1776.8, 1: 1787.3. Samples: 33279960. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-16 05:20:57,351][03835] Avg episode reward: [(0, '6.910'), (1, '7.670')] -[2023-10-16 05:20:57,615][05218] Updated weights for policy 0, policy_version 65102 (0.0009) -[2023-10-16 05:20:57,998][05218] Updated weights for policy 0, policy_version 65112 (0.0010) -[2023-10-16 05:21:00,825][05219] Updated weights for policy 1, policy_version 64900 (0.0008) -[2023-10-16 05:21:01,196][05219] Updated weights for policy 1, policy_version 64910 (0.0008) -[2023-10-16 05:21:01,560][05219] Updated weights for policy 1, policy_version 64920 (0.0009) -[2023-10-16 05:21:01,695][05218] Updated weights for policy 0, policy_version 65122 (0.0009) -[2023-10-16 05:21:02,060][05218] Updated weights for policy 0, policy_version 65132 (0.0008) -[2023-10-16 05:21:02,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 133169152. Throughput: 0: 1796.6, 1: 1800.4. Samples: 33302022. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-16 05:21:02,351][03835] Avg episode reward: [(0, '6.560'), (1, '7.140')] -[2023-10-16 05:21:02,437][05218] Updated weights for policy 0, policy_version 65142 (0.0009) -[2023-10-16 05:21:02,815][05218] Updated weights for policy 0, policy_version 65152 (0.0009) -[2023-10-16 05:21:05,295][05219] Updated weights for policy 1, policy_version 64930 (0.0008) -[2023-10-16 05:21:05,662][05219] Updated weights for policy 1, policy_version 64940 (0.0008) -[2023-10-16 05:21:06,026][05219] Updated weights for policy 1, policy_version 64950 (0.0008) -[2023-10-16 05:21:06,390][05219] Updated weights for policy 1, policy_version 64960 (0.0008) -[2023-10-16 05:21:06,536][05218] Updated weights for policy 0, policy_version 65162 (0.0008) -[2023-10-16 05:21:06,913][05218] Updated weights for policy 0, policy_version 65172 (0.0008) -[2023-10-16 05:21:07,296][05218] Updated weights for policy 0, policy_version 65182 (0.0009) -[2023-10-16 05:21:07,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 133234688. Throughput: 0: 1783.8, 1: 1781.3. Samples: 33321960. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-16 05:21:07,351][03835] Avg episode reward: [(0, '6.900'), (1, '6.710')] -[2023-10-16 05:21:10,209][05219] Updated weights for policy 1, policy_version 64970 (0.0010) -[2023-10-16 05:21:10,581][05219] Updated weights for policy 1, policy_version 64980 (0.0009) -[2023-10-16 05:21:10,941][05219] Updated weights for policy 1, policy_version 64990 (0.0009) -[2023-10-16 05:21:11,053][05218] Updated weights for policy 0, policy_version 65192 (0.0009) -[2023-10-16 05:21:11,440][05218] Updated weights for policy 0, policy_version 65202 (0.0009) -[2023-10-16 05:21:11,809][05218] Updated weights for policy 0, policy_version 65212 (0.0010) -[2023-10-16 05:21:12,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 133332992. Throughput: 0: 1795.6, 1: 1794.8. Samples: 33334410. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-16 05:21:12,351][03835] Avg episode reward: [(0, '6.670'), (1, '6.540')] -[2023-10-16 05:21:14,651][05219] Updated weights for policy 1, policy_version 65000 (0.0010) -[2023-10-16 05:21:15,026][05219] Updated weights for policy 1, policy_version 65010 (0.0012) -[2023-10-16 05:21:15,398][05219] Updated weights for policy 1, policy_version 65020 (0.0009) -[2023-10-16 05:21:15,589][05218] Updated weights for policy 0, policy_version 65222 (0.0010) -[2023-10-16 05:21:15,965][05218] Updated weights for policy 0, policy_version 65232 (0.0011) -[2023-10-16 05:21:16,343][05218] Updated weights for policy 0, policy_version 65242 (0.0010) -[2023-10-16 05:21:17,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 133398528. Throughput: 0: 1790.1, 1: 1781.6. Samples: 33354488. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-16 05:21:17,352][03835] Avg episode reward: [(0, '6.460'), (1, '6.580')] -[2023-10-16 05:21:19,244][05219] Updated weights for policy 1, policy_version 65030 (0.0008) -[2023-10-16 05:21:19,612][05219] Updated weights for policy 1, policy_version 65040 (0.0007) -[2023-10-16 05:21:19,971][05219] Updated weights for policy 1, policy_version 65050 (0.0007) -[2023-10-16 05:21:20,063][05218] Updated weights for policy 0, policy_version 65252 (0.0009) -[2023-10-16 05:21:20,437][05218] Updated weights for policy 0, policy_version 65262 (0.0009) -[2023-10-16 05:21:20,808][05218] Updated weights for policy 0, policy_version 65272 (0.0009) -[2023-10-16 05:21:22,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 133464064. Throughput: 0: 1788.9, 1: 1782.2. Samples: 33376782. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-16 05:21:22,351][03835] Avg episode reward: [(0, '6.620'), (1, '7.090')] -[2023-10-16 05:21:23,731][05219] Updated weights for policy 1, policy_version 65060 (0.0010) -[2023-10-16 05:21:24,100][05219] Updated weights for policy 1, policy_version 65070 (0.0009) -[2023-10-16 05:21:24,408][05218] Updated weights for policy 0, policy_version 65282 (0.0007) -[2023-10-16 05:21:24,464][05219] Updated weights for policy 1, policy_version 65080 (0.0009) -[2023-10-16 05:21:24,798][05218] Updated weights for policy 0, policy_version 65292 (0.0007) -[2023-10-16 05:21:25,167][05218] Updated weights for policy 0, policy_version 65302 (0.0007) -[2023-10-16 05:21:25,551][05218] Updated weights for policy 0, policy_version 65312 (0.0008) -[2023-10-16 05:21:27,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 133529600. Throughput: 0: 1794.7, 1: 1780.3. Samples: 33386766. Policy #0 lag: (min: 27.0, avg: 27.1, max: 33.0) -[2023-10-16 05:21:27,351][03835] Avg episode reward: [(0, '6.090'), (1, '7.510')] -[2023-10-16 05:21:28,159][05219] Updated weights for policy 1, policy_version 65090 (0.0008) -[2023-10-16 05:21:28,525][05219] Updated weights for policy 1, policy_version 65100 (0.0007) -[2023-10-16 05:21:28,886][05219] Updated weights for policy 1, policy_version 65110 (0.0008) -[2023-10-16 05:21:29,253][05219] Updated weights for policy 1, policy_version 65120 (0.0007) -[2023-10-16 05:21:29,419][05218] Updated weights for policy 0, policy_version 65322 (0.0009) -[2023-10-16 05:21:29,796][05218] Updated weights for policy 0, policy_version 65332 (0.0007) -[2023-10-16 05:21:30,176][05218] Updated weights for policy 0, policy_version 65342 (0.0008) -[2023-10-16 05:21:32,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 133595136. Throughput: 0: 1789.0, 1: 1785.4. Samples: 33409012. Policy #0 lag: (min: 27.0, avg: 27.1, max: 33.0) -[2023-10-16 05:21:32,351][03835] Avg episode reward: [(0, '6.190'), (1, '7.150')] -[2023-10-16 05:21:33,030][05219] Updated weights for policy 1, policy_version 65130 (0.0011) -[2023-10-16 05:21:33,397][05219] Updated weights for policy 1, policy_version 65140 (0.0009) -[2023-10-16 05:21:33,769][05219] Updated weights for policy 1, policy_version 65150 (0.0008) -[2023-10-16 05:21:33,868][05218] Updated weights for policy 0, policy_version 65352 (0.0007) -[2023-10-16 05:21:34,253][05218] Updated weights for policy 0, policy_version 65362 (0.0009) -[2023-10-16 05:21:34,627][05218] Updated weights for policy 0, policy_version 65372 (0.0009) -[2023-10-16 05:21:37,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.6, 300 sec: 14329.1). Total num frames: 133660672. Throughput: 0: 1791.6, 1: 1798.8. Samples: 33431398. Policy #0 lag: (min: 27.0, avg: 27.1, max: 33.0) -[2023-10-16 05:21:37,351][03835] Avg episode reward: [(0, '6.740'), (1, '8.390')] -[2023-10-16 05:21:37,359][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000065376_66945024.pth... -[2023-10-16 05:21:37,395][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000063712_65241088.pth -[2023-10-16 05:21:37,713][05219] Updated weights for policy 1, policy_version 65160 (0.0009) -[2023-10-16 05:21:38,089][05219] Updated weights for policy 1, policy_version 65170 (0.0008) -[2023-10-16 05:21:38,315][05218] Updated weights for policy 0, policy_version 65382 (0.0008) -[2023-10-16 05:21:38,455][05219] Updated weights for policy 1, policy_version 65180 (0.0008) -[2023-10-16 05:21:38,592][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000065184_66748416.pth... -[2023-10-16 05:21:38,620][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000063488_65011712.pth -[2023-10-16 05:21:38,693][05218] Updated weights for policy 0, policy_version 65392 (0.0009) -[2023-10-16 05:21:39,066][05218] Updated weights for policy 0, policy_version 65402 (0.0008) -[2023-10-16 05:21:42,319][05219] Updated weights for policy 1, policy_version 65190 (0.0009) -[2023-10-16 05:21:42,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 133726208. Throughput: 0: 1796.7, 1: 1783.7. Samples: 33441078. Policy #0 lag: (min: 27.0, avg: 27.1, max: 33.0) -[2023-10-16 05:21:42,351][03835] Avg episode reward: [(0, '6.690'), (1, '8.150')] -[2023-10-16 05:21:42,682][05219] Updated weights for policy 1, policy_version 65200 (0.0007) -[2023-10-16 05:21:42,806][05218] Updated weights for policy 0, policy_version 65412 (0.0007) -[2023-10-16 05:21:43,058][05219] Updated weights for policy 1, policy_version 65210 (0.0009) -[2023-10-16 05:21:43,179][05218] Updated weights for policy 0, policy_version 65422 (0.0008) -[2023-10-16 05:21:43,562][05218] Updated weights for policy 0, policy_version 65432 (0.0007) -[2023-10-16 05:21:46,855][05219] Updated weights for policy 1, policy_version 65220 (0.0007) -[2023-10-16 05:21:47,212][05218] Updated weights for policy 0, policy_version 65442 (0.0011) -[2023-10-16 05:21:47,215][05219] Updated weights for policy 1, policy_version 65230 (0.0007) -[2023-10-16 05:21:47,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 133791744. Throughput: 0: 1795.1, 1: 1790.8. Samples: 33463384. Policy #0 lag: (min: 27.0, avg: 27.1, max: 33.0) -[2023-10-16 05:21:47,351][03835] Avg episode reward: [(0, '6.330'), (1, '7.360')] -[2023-10-16 05:21:47,578][05218] Updated weights for policy 0, policy_version 65452 (0.0011) -[2023-10-16 05:21:47,585][05219] Updated weights for policy 1, policy_version 65240 (0.0009) -[2023-10-16 05:21:47,947][05218] Updated weights for policy 0, policy_version 65462 (0.0008) -[2023-10-16 05:21:48,329][05218] Updated weights for policy 0, policy_version 65472 (0.0007) -[2023-10-16 05:21:51,465][05219] Updated weights for policy 1, policy_version 65250 (0.0009) -[2023-10-16 05:21:51,836][05219] Updated weights for policy 1, policy_version 65260 (0.0008) -[2023-10-16 05:21:52,018][05218] Updated weights for policy 0, policy_version 65482 (0.0007) -[2023-10-16 05:21:52,200][05219] Updated weights for policy 1, policy_version 65270 (0.0008) -[2023-10-16 05:21:52,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 133857280. Throughput: 0: 1806.7, 1: 1794.7. Samples: 33484020. Policy #0 lag: (min: 27.0, avg: 27.1, max: 33.0) -[2023-10-16 05:21:52,351][03835] Avg episode reward: [(0, '5.800'), (1, '8.160')] -[2023-10-16 05:21:52,390][05218] Updated weights for policy 0, policy_version 65492 (0.0008) -[2023-10-16 05:21:52,558][05219] Updated weights for policy 1, policy_version 65280 (0.0009) -[2023-10-16 05:21:52,765][05218] Updated weights for policy 0, policy_version 65502 (0.0010) -[2023-10-16 05:21:56,297][05219] Updated weights for policy 1, policy_version 65290 (0.0008) -[2023-10-16 05:21:56,610][05218] Updated weights for policy 0, policy_version 65512 (0.0008) -[2023-10-16 05:21:56,662][05219] Updated weights for policy 1, policy_version 65300 (0.0007) -[2023-10-16 05:21:56,983][05218] Updated weights for policy 0, policy_version 65522 (0.0007) -[2023-10-16 05:21:57,027][05219] Updated weights for policy 1, policy_version 65310 (0.0008) -[2023-10-16 05:21:57,349][05218] Updated weights for policy 0, policy_version 65532 (0.0009) -[2023-10-16 05:21:57,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 133955584. Throughput: 0: 1791.3, 1: 1788.6. Samples: 33495506. Policy #0 lag: (min: 27.0, avg: 27.1, max: 33.0) -[2023-10-16 05:21:57,351][03835] Avg episode reward: [(0, '5.990'), (1, '7.780')] -[2023-10-16 05:22:00,972][05219] Updated weights for policy 1, policy_version 65320 (0.0008) -[2023-10-16 05:22:01,013][05218] Updated weights for policy 0, policy_version 65542 (0.0009) -[2023-10-16 05:22:01,329][05219] Updated weights for policy 1, policy_version 65330 (0.0008) -[2023-10-16 05:22:01,384][05218] Updated weights for policy 0, policy_version 65552 (0.0008) -[2023-10-16 05:22:01,694][05219] Updated weights for policy 1, policy_version 65340 (0.0008) -[2023-10-16 05:22:01,755][05218] Updated weights for policy 0, policy_version 65562 (0.0008) -[2023-10-16 05:22:02,350][03835] Fps is (10 sec: 19660.5, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 134053888. Throughput: 0: 1810.1, 1: 1799.5. Samples: 33516920. Policy #0 lag: (min: 27.0, avg: 27.1, max: 33.0) -[2023-10-16 05:22:02,351][03835] Avg episode reward: [(0, '6.330'), (1, '7.900')] -[2023-10-16 05:22:05,354][05218] Updated weights for policy 0, policy_version 65572 (0.0008) -[2023-10-16 05:22:05,574][05219] Updated weights for policy 1, policy_version 65350 (0.0008) -[2023-10-16 05:22:05,725][05218] Updated weights for policy 0, policy_version 65582 (0.0008) -[2023-10-16 05:22:05,937][05219] Updated weights for policy 1, policy_version 65360 (0.0010) -[2023-10-16 05:22:06,112][05218] Updated weights for policy 0, policy_version 65592 (0.0007) -[2023-10-16 05:22:06,306][05219] Updated weights for policy 1, policy_version 65370 (0.0008) -[2023-10-16 05:22:07,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 134119424. Throughput: 0: 1800.1, 1: 1773.7. Samples: 33537604. Policy #0 lag: (min: 27.0, avg: 27.1, max: 33.0) -[2023-10-16 05:22:07,351][03835] Avg episode reward: [(0, '6.960'), (1, '8.070')] -[2023-10-16 05:22:09,817][05218] Updated weights for policy 0, policy_version 65602 (0.0009) -[2023-10-16 05:22:10,116][05219] Updated weights for policy 1, policy_version 65380 (0.0008) -[2023-10-16 05:22:10,207][05218] Updated weights for policy 0, policy_version 65612 (0.0008) -[2023-10-16 05:22:10,483][05219] Updated weights for policy 1, policy_version 65390 (0.0008) -[2023-10-16 05:22:10,575][05218] Updated weights for policy 0, policy_version 65622 (0.0008) -[2023-10-16 05:22:10,842][05219] Updated weights for policy 1, policy_version 65400 (0.0009) -[2023-10-16 05:22:10,949][05218] Updated weights for policy 0, policy_version 65632 (0.0007) -[2023-10-16 05:22:12,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 134184960. Throughput: 0: 1811.7, 1: 1801.4. Samples: 33549356. Policy #0 lag: (min: 24.0, avg: 45.3, max: 56.0) -[2023-10-16 05:22:12,351][03835] Avg episode reward: [(0, '6.680'), (1, '6.900')] -[2023-10-16 05:22:14,593][05218] Updated weights for policy 0, policy_version 65642 (0.0007) -[2023-10-16 05:22:14,628][05219] Updated weights for policy 1, policy_version 65410 (0.0010) -[2023-10-16 05:22:14,970][05218] Updated weights for policy 0, policy_version 65652 (0.0007) -[2023-10-16 05:22:14,996][05219] Updated weights for policy 1, policy_version 65420 (0.0008) -[2023-10-16 05:22:15,352][05218] Updated weights for policy 0, policy_version 65662 (0.0008) -[2023-10-16 05:22:15,352][05219] Updated weights for policy 1, policy_version 65430 (0.0008) -[2023-10-16 05:22:15,714][05219] Updated weights for policy 1, policy_version 65440 (0.0007) -[2023-10-16 05:22:17,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 134250496. Throughput: 0: 1803.3, 1: 1771.7. Samples: 33569888. Policy #0 lag: (min: 24.0, avg: 45.3, max: 56.0) -[2023-10-16 05:22:17,351][03835] Avg episode reward: [(0, '6.260'), (1, '6.750')] -[2023-10-16 05:22:19,123][05218] Updated weights for policy 0, policy_version 65672 (0.0009) -[2023-10-16 05:22:19,351][05219] Updated weights for policy 1, policy_version 65450 (0.0007) -[2023-10-16 05:22:19,494][05218] Updated weights for policy 0, policy_version 65682 (0.0008) -[2023-10-16 05:22:19,717][05219] Updated weights for policy 1, policy_version 65460 (0.0008) -[2023-10-16 05:22:19,873][05218] Updated weights for policy 0, policy_version 65692 (0.0007) -[2023-10-16 05:22:20,080][05219] Updated weights for policy 1, policy_version 65470 (0.0007) -[2023-10-16 05:22:22,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 134316032. Throughput: 0: 1802.4, 1: 1768.0. Samples: 33592068. Policy #0 lag: (min: 24.0, avg: 45.3, max: 56.0) -[2023-10-16 05:22:22,351][03835] Avg episode reward: [(0, '6.600'), (1, '7.400')] -[2023-10-16 05:22:23,606][05218] Updated weights for policy 0, policy_version 65702 (0.0008) -[2023-10-16 05:22:23,787][05219] Updated weights for policy 1, policy_version 65480 (0.0009) -[2023-10-16 05:22:23,984][05218] Updated weights for policy 0, policy_version 65712 (0.0008) -[2023-10-16 05:22:24,143][05219] Updated weights for policy 1, policy_version 65490 (0.0007) -[2023-10-16 05:22:24,345][05218] Updated weights for policy 0, policy_version 65722 (0.0008) -[2023-10-16 05:22:24,510][05219] Updated weights for policy 1, policy_version 65500 (0.0008) -[2023-10-16 05:22:27,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 134381568. Throughput: 0: 1798.6, 1: 1773.6. Samples: 33601828. Policy #0 lag: (min: 24.0, avg: 45.3, max: 56.0) -[2023-10-16 05:22:27,352][03835] Avg episode reward: [(0, '6.160'), (1, '6.640')] -[2023-10-16 05:22:28,196][05218] Updated weights for policy 0, policy_version 65732 (0.0007) -[2023-10-16 05:22:28,295][05219] Updated weights for policy 1, policy_version 65510 (0.0009) -[2023-10-16 05:22:28,569][05218] Updated weights for policy 0, policy_version 65742 (0.0007) -[2023-10-16 05:22:28,653][05219] Updated weights for policy 1, policy_version 65520 (0.0007) -[2023-10-16 05:22:28,946][05218] Updated weights for policy 0, policy_version 65752 (0.0009) -[2023-10-16 05:22:29,020][05219] Updated weights for policy 1, policy_version 65530 (0.0009) -[2023-10-16 05:22:32,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 134447104. Throughput: 0: 1792.3, 1: 1772.3. Samples: 33623788. Policy #0 lag: (min: 24.0, avg: 45.3, max: 56.0) -[2023-10-16 05:22:32,351][03835] Avg episode reward: [(0, '7.020'), (1, '7.250')] -[2023-10-16 05:22:32,755][05218] Updated weights for policy 0, policy_version 65762 (0.0009) -[2023-10-16 05:22:32,917][05219] Updated weights for policy 1, policy_version 65540 (0.0007) -[2023-10-16 05:22:33,130][05218] Updated weights for policy 0, policy_version 65772 (0.0010) -[2023-10-16 05:22:33,277][05219] Updated weights for policy 1, policy_version 65550 (0.0008) -[2023-10-16 05:22:33,511][05218] Updated weights for policy 0, policy_version 65782 (0.0009) -[2023-10-16 05:22:33,641][05219] Updated weights for policy 1, policy_version 65560 (0.0008) -[2023-10-16 05:22:33,880][05218] Updated weights for policy 0, policy_version 65792 (0.0009) -[2023-10-16 05:22:37,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 134512640. Throughput: 0: 1807.0, 1: 1791.4. Samples: 33645950. Policy #0 lag: (min: 24.0, avg: 45.3, max: 56.0) -[2023-10-16 05:22:37,352][03835] Avg episode reward: [(0, '7.410'), (1, '7.470')] -[2023-10-16 05:22:37,422][05219] Updated weights for policy 1, policy_version 65570 (0.0008) -[2023-10-16 05:22:37,656][05218] Updated weights for policy 0, policy_version 65802 (0.0007) -[2023-10-16 05:22:37,788][05219] Updated weights for policy 1, policy_version 65580 (0.0008) -[2023-10-16 05:22:38,027][05218] Updated weights for policy 0, policy_version 65812 (0.0007) -[2023-10-16 05:22:38,144][05219] Updated weights for policy 1, policy_version 65590 (0.0008) -[2023-10-16 05:22:38,409][05218] Updated weights for policy 0, policy_version 65822 (0.0009) -[2023-10-16 05:22:38,506][05219] Updated weights for policy 1, policy_version 65600 (0.0008) -[2023-10-16 05:22:42,174][05218] Updated weights for policy 0, policy_version 65832 (0.0007) -[2023-10-16 05:22:42,291][05219] Updated weights for policy 1, policy_version 65610 (0.0007) -[2023-10-16 05:22:42,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 134578176. Throughput: 0: 1792.2, 1: 1766.4. Samples: 33655640. Policy #0 lag: (min: 24.0, avg: 45.3, max: 56.0) -[2023-10-16 05:22:42,351][03835] Avg episode reward: [(0, '6.530'), (1, '7.470')] -[2023-10-16 05:22:42,556][05218] Updated weights for policy 0, policy_version 65842 (0.0008) -[2023-10-16 05:22:42,660][05219] Updated weights for policy 1, policy_version 65620 (0.0009) -[2023-10-16 05:22:42,930][05218] Updated weights for policy 0, policy_version 65852 (0.0008) -[2023-10-16 05:22:43,020][05219] Updated weights for policy 1, policy_version 65630 (0.0007) -[2023-10-16 05:22:46,601][05218] Updated weights for policy 0, policy_version 65862 (0.0009) -[2023-10-16 05:22:46,953][05219] Updated weights for policy 1, policy_version 65640 (0.0009) -[2023-10-16 05:22:46,963][05218] Updated weights for policy 0, policy_version 65872 (0.0009) -[2023-10-16 05:22:47,307][05219] Updated weights for policy 1, policy_version 65650 (0.0008) -[2023-10-16 05:22:47,337][05218] Updated weights for policy 0, policy_version 65882 (0.0007) -[2023-10-16 05:22:47,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 134643712. Throughput: 0: 1804.4, 1: 1775.1. Samples: 33677994. Policy #0 lag: (min: 24.0, avg: 45.3, max: 56.0) -[2023-10-16 05:22:47,351][03835] Avg episode reward: [(0, '7.060'), (1, '8.710')] -[2023-10-16 05:22:47,677][05219] Updated weights for policy 1, policy_version 65660 (0.0007) -[2023-10-16 05:22:51,140][05218] Updated weights for policy 0, policy_version 65892 (0.0008) -[2023-10-16 05:22:51,508][05219] Updated weights for policy 1, policy_version 65670 (0.0009) -[2023-10-16 05:22:51,509][05218] Updated weights for policy 0, policy_version 65902 (0.0008) -[2023-10-16 05:22:51,864][05219] Updated weights for policy 1, policy_version 65680 (0.0008) -[2023-10-16 05:22:51,886][05218] Updated weights for policy 0, policy_version 65912 (0.0008) -[2023-10-16 05:22:52,227][05219] Updated weights for policy 1, policy_version 65690 (0.0009) -[2023-10-16 05:22:52,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 134742016. Throughput: 0: 1781.2, 1: 1773.4. Samples: 33697560. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-16 05:22:52,351][03835] Avg episode reward: [(0, '6.730'), (1, '7.810')] -[2023-10-16 05:22:55,717][05218] Updated weights for policy 0, policy_version 65922 (0.0008) -[2023-10-16 05:22:56,089][05218] Updated weights for policy 0, policy_version 65932 (0.0010) -[2023-10-16 05:22:56,150][05219] Updated weights for policy 1, policy_version 65700 (0.0008) -[2023-10-16 05:22:56,468][05218] Updated weights for policy 0, policy_version 65942 (0.0007) -[2023-10-16 05:22:56,523][05219] Updated weights for policy 1, policy_version 65710 (0.0007) -[2023-10-16 05:22:56,848][05218] Updated weights for policy 0, policy_version 65952 (0.0007) -[2023-10-16 05:22:56,892][05219] Updated weights for policy 1, policy_version 65720 (0.0010) -[2023-10-16 05:22:57,350][03835] Fps is (10 sec: 19660.8, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 134840320. Throughput: 0: 1794.0, 1: 1764.5. Samples: 33709492. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-16 05:22:57,351][03835] Avg episode reward: [(0, '6.080'), (1, '7.820')] -[2023-10-16 05:23:00,551][05219] Updated weights for policy 1, policy_version 65730 (0.0009) -[2023-10-16 05:23:00,613][05218] Updated weights for policy 0, policy_version 65962 (0.0008) -[2023-10-16 05:23:00,920][05219] Updated weights for policy 1, policy_version 65740 (0.0008) -[2023-10-16 05:23:00,983][05218] Updated weights for policy 0, policy_version 65972 (0.0007) -[2023-10-16 05:23:01,283][05219] Updated weights for policy 1, policy_version 65750 (0.0008) -[2023-10-16 05:23:01,350][05218] Updated weights for policy 0, policy_version 65982 (0.0008) -[2023-10-16 05:23:01,653][05219] Updated weights for policy 1, policy_version 65760 (0.0009) -[2023-10-16 05:23:02,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 134905856. Throughput: 0: 1779.2, 1: 1777.9. Samples: 33729960. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-16 05:23:02,351][03835] Avg episode reward: [(0, '6.260'), (1, '8.050')] -[2023-10-16 05:23:05,032][05218] Updated weights for policy 0, policy_version 65992 (0.0010) -[2023-10-16 05:23:05,404][05218] Updated weights for policy 0, policy_version 66002 (0.0010) -[2023-10-16 05:23:05,456][05219] Updated weights for policy 1, policy_version 65770 (0.0008) -[2023-10-16 05:23:05,785][05218] Updated weights for policy 0, policy_version 66012 (0.0008) -[2023-10-16 05:23:05,820][05219] Updated weights for policy 1, policy_version 65780 (0.0008) -[2023-10-16 05:23:06,190][05219] Updated weights for policy 1, policy_version 65790 (0.0009) -[2023-10-16 05:23:07,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 134971392. Throughput: 0: 1781.3, 1: 1762.5. Samples: 33751542. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-16 05:23:07,351][03835] Avg episode reward: [(0, '6.650'), (1, '8.150')] -[2023-10-16 05:23:09,449][05218] Updated weights for policy 0, policy_version 66022 (0.0008) -[2023-10-16 05:23:09,813][05218] Updated weights for policy 0, policy_version 66032 (0.0008) -[2023-10-16 05:23:10,061][05219] Updated weights for policy 1, policy_version 65800 (0.0008) -[2023-10-16 05:23:10,183][05218] Updated weights for policy 0, policy_version 66042 (0.0009) -[2023-10-16 05:23:10,433][05219] Updated weights for policy 1, policy_version 65810 (0.0008) -[2023-10-16 05:23:10,801][05219] Updated weights for policy 1, policy_version 65820 (0.0010) -[2023-10-16 05:23:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 135036928. Throughput: 0: 1786.4, 1: 1785.4. Samples: 33762558. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-16 05:23:12,351][03835] Avg episode reward: [(0, '6.990'), (1, '6.690')] -[2023-10-16 05:23:13,907][05218] Updated weights for policy 0, policy_version 66052 (0.0010) -[2023-10-16 05:23:14,279][05218] Updated weights for policy 0, policy_version 66062 (0.0007) -[2023-10-16 05:23:14,651][05218] Updated weights for policy 0, policy_version 66072 (0.0007) -[2023-10-16 05:23:14,692][05219] Updated weights for policy 1, policy_version 65830 (0.0009) -[2023-10-16 05:23:15,061][05219] Updated weights for policy 1, policy_version 65840 (0.0010) -[2023-10-16 05:23:15,425][05219] Updated weights for policy 1, policy_version 65850 (0.0010) -[2023-10-16 05:23:17,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 135102464. Throughput: 0: 1789.6, 1: 1760.9. Samples: 33783564. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-16 05:23:17,351][03835] Avg episode reward: [(0, '6.880'), (1, '6.900')] -[2023-10-16 05:23:18,533][05218] Updated weights for policy 0, policy_version 66082 (0.0007) -[2023-10-16 05:23:18,911][05218] Updated weights for policy 0, policy_version 66092 (0.0009) -[2023-10-16 05:23:19,243][05219] Updated weights for policy 1, policy_version 65860 (0.0009) -[2023-10-16 05:23:19,285][05218] Updated weights for policy 0, policy_version 66102 (0.0009) -[2023-10-16 05:23:19,612][05219] Updated weights for policy 1, policy_version 65870 (0.0007) -[2023-10-16 05:23:19,659][05218] Updated weights for policy 0, policy_version 66112 (0.0009) -[2023-10-16 05:23:19,971][05219] Updated weights for policy 1, policy_version 65880 (0.0010) -[2023-10-16 05:23:22,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 135168000. Throughput: 0: 1794.2, 1: 1761.5. Samples: 33805956. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-16 05:23:22,351][03835] Avg episode reward: [(0, '6.640'), (1, '6.740')] -[2023-10-16 05:23:23,450][05218] Updated weights for policy 0, policy_version 66122 (0.0007) -[2023-10-16 05:23:23,724][05219] Updated weights for policy 1, policy_version 65890 (0.0009) -[2023-10-16 05:23:23,817][05218] Updated weights for policy 0, policy_version 66132 (0.0007) -[2023-10-16 05:23:24,089][05219] Updated weights for policy 1, policy_version 65900 (0.0009) -[2023-10-16 05:23:24,186][05218] Updated weights for policy 0, policy_version 66142 (0.0008) -[2023-10-16 05:23:24,449][05219] Updated weights for policy 1, policy_version 65910 (0.0011) -[2023-10-16 05:23:24,815][05219] Updated weights for policy 1, policy_version 65920 (0.0008) -[2023-10-16 05:23:27,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 135233536. Throughput: 0: 1795.2, 1: 1765.9. Samples: 33815890. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-16 05:23:27,351][03835] Avg episode reward: [(0, '6.510'), (1, '6.620')] -[2023-10-16 05:23:27,926][05218] Updated weights for policy 0, policy_version 66152 (0.0011) -[2023-10-16 05:23:28,309][05218] Updated weights for policy 0, policy_version 66162 (0.0009) -[2023-10-16 05:23:28,545][05219] Updated weights for policy 1, policy_version 65930 (0.0009) -[2023-10-16 05:23:28,682][05218] Updated weights for policy 0, policy_version 66172 (0.0007) -[2023-10-16 05:23:28,910][05219] Updated weights for policy 1, policy_version 65940 (0.0008) -[2023-10-16 05:23:29,274][05219] Updated weights for policy 1, policy_version 65950 (0.0009) -[2023-10-16 05:23:32,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 135299072. Throughput: 0: 1787.5, 1: 1770.7. Samples: 33838114. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-16 05:23:32,351][03835] Avg episode reward: [(0, '6.530'), (1, '6.820')] -[2023-10-16 05:23:32,484][05218] Updated weights for policy 0, policy_version 66182 (0.0008) -[2023-10-16 05:23:32,854][05218] Updated weights for policy 0, policy_version 66192 (0.0008) -[2023-10-16 05:23:32,977][05219] Updated weights for policy 1, policy_version 65960 (0.0009) -[2023-10-16 05:23:33,229][05218] Updated weights for policy 0, policy_version 66202 (0.0008) -[2023-10-16 05:23:33,335][05219] Updated weights for policy 1, policy_version 65970 (0.0009) -[2023-10-16 05:23:33,708][05219] Updated weights for policy 1, policy_version 65980 (0.0008) -[2023-10-16 05:23:37,038][05218] Updated weights for policy 0, policy_version 66212 (0.0007) -[2023-10-16 05:23:37,351][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 135364608. Throughput: 0: 1808.9, 1: 1795.3. Samples: 33859750. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-16 05:23:37,352][03835] Avg episode reward: [(0, '6.550'), (1, '7.940')] -[2023-10-16 05:23:37,417][05218] Updated weights for policy 0, policy_version 66222 (0.0009) -[2023-10-16 05:23:37,593][05219] Updated weights for policy 1, policy_version 65990 (0.0009) -[2023-10-16 05:23:37,783][05218] Updated weights for policy 0, policy_version 66232 (0.0009) -[2023-10-16 05:23:37,951][05219] Updated weights for policy 1, policy_version 66000 (0.0007) -[2023-10-16 05:23:38,074][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000066240_67829760.pth... -[2023-10-16 05:23:38,113][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000064544_66093056.pth -[2023-10-16 05:23:38,313][05219] Updated weights for policy 1, policy_version 66010 (0.0008) -[2023-10-16 05:23:38,518][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000066016_67600384.pth... -[2023-10-16 05:23:38,551][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000064320_65863680.pth -[2023-10-16 05:23:41,379][05218] Updated weights for policy 0, policy_version 66242 (0.0008) -[2023-10-16 05:23:41,767][05218] Updated weights for policy 0, policy_version 66252 (0.0011) -[2023-10-16 05:23:42,098][05219] Updated weights for policy 1, policy_version 66020 (0.0009) -[2023-10-16 05:23:42,138][05218] Updated weights for policy 0, policy_version 66262 (0.0007) -[2023-10-16 05:23:42,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 135430144. Throughput: 0: 1794.7, 1: 1778.5. Samples: 33870284. Policy #0 lag: (min: 12.0, avg: 20.4, max: 44.0) -[2023-10-16 05:23:42,351][03835] Avg episode reward: [(0, '6.670'), (1, '7.210')] -[2023-10-16 05:23:42,464][05219] Updated weights for policy 1, policy_version 66030 (0.0009) -[2023-10-16 05:23:42,514][05218] Updated weights for policy 0, policy_version 66272 (0.0008) -[2023-10-16 05:23:42,818][05219] Updated weights for policy 1, policy_version 66040 (0.0007) -[2023-10-16 05:23:46,246][05218] Updated weights for policy 0, policy_version 66282 (0.0008) -[2023-10-16 05:23:46,627][05218] Updated weights for policy 0, policy_version 66292 (0.0009) -[2023-10-16 05:23:46,697][05219] Updated weights for policy 1, policy_version 66050 (0.0009) -[2023-10-16 05:23:46,996][05218] Updated weights for policy 0, policy_version 66302 (0.0009) -[2023-10-16 05:23:47,058][05219] Updated weights for policy 1, policy_version 66060 (0.0008) -[2023-10-16 05:23:47,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 135528448. Throughput: 0: 1811.7, 1: 1788.8. Samples: 33891986. Policy #0 lag: (min: 12.0, avg: 20.4, max: 44.0) -[2023-10-16 05:23:47,351][03835] Avg episode reward: [(0, '6.380'), (1, '7.240')] -[2023-10-16 05:23:47,432][05219] Updated weights for policy 1, policy_version 66070 (0.0010) -[2023-10-16 05:23:47,798][05219] Updated weights for policy 1, policy_version 66080 (0.0009) -[2023-10-16 05:23:50,649][05218] Updated weights for policy 0, policy_version 66312 (0.0008) -[2023-10-16 05:23:51,022][05218] Updated weights for policy 0, policy_version 66322 (0.0008) -[2023-10-16 05:23:51,403][05218] Updated weights for policy 0, policy_version 66332 (0.0009) -[2023-10-16 05:23:51,494][05219] Updated weights for policy 1, policy_version 66090 (0.0008) -[2023-10-16 05:23:51,855][05219] Updated weights for policy 1, policy_version 66100 (0.0010) -[2023-10-16 05:23:52,224][05219] Updated weights for policy 1, policy_version 66110 (0.0009) -[2023-10-16 05:23:52,350][03835] Fps is (10 sec: 19660.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 135626752. Throughput: 0: 1792.7, 1: 1778.0. Samples: 33912222. Policy #0 lag: (min: 12.0, avg: 20.4, max: 44.0) -[2023-10-16 05:23:52,351][03835] Avg episode reward: [(0, '4.760'), (1, '8.470')] -[2023-10-16 05:23:55,132][05218] Updated weights for policy 0, policy_version 66342 (0.0007) -[2023-10-16 05:23:55,507][05218] Updated weights for policy 0, policy_version 66352 (0.0007) -[2023-10-16 05:23:55,889][05218] Updated weights for policy 0, policy_version 66362 (0.0007) -[2023-10-16 05:23:56,181][05219] Updated weights for policy 1, policy_version 66120 (0.0010) -[2023-10-16 05:23:56,545][05219] Updated weights for policy 1, policy_version 66130 (0.0008) -[2023-10-16 05:23:56,905][05219] Updated weights for policy 1, policy_version 66140 (0.0008) -[2023-10-16 05:23:57,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 135692288. Throughput: 0: 1812.4, 1: 1778.8. Samples: 33924166. Policy #0 lag: (min: 12.0, avg: 20.4, max: 44.0) -[2023-10-16 05:23:57,351][03835] Avg episode reward: [(0, '4.330'), (1, '6.590')] -[2023-10-16 05:23:59,459][05218] Updated weights for policy 0, policy_version 66372 (0.0009) -[2023-10-16 05:23:59,822][05218] Updated weights for policy 0, policy_version 66382 (0.0008) -[2023-10-16 05:24:00,200][05218] Updated weights for policy 0, policy_version 66392 (0.0009) -[2023-10-16 05:24:00,699][05219] Updated weights for policy 1, policy_version 66150 (0.0010) -[2023-10-16 05:24:01,073][05219] Updated weights for policy 1, policy_version 66160 (0.0009) -[2023-10-16 05:24:01,435][05219] Updated weights for policy 1, policy_version 66170 (0.0009) -[2023-10-16 05:24:02,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 135757824. Throughput: 0: 1797.0, 1: 1791.2. Samples: 33945036. Policy #0 lag: (min: 12.0, avg: 20.4, max: 44.0) -[2023-10-16 05:24:02,351][03835] Avg episode reward: [(0, '4.040'), (1, '6.880')] -[2023-10-16 05:24:04,096][05218] Updated weights for policy 0, policy_version 66402 (0.0007) -[2023-10-16 05:24:04,469][05218] Updated weights for policy 0, policy_version 66412 (0.0009) -[2023-10-16 05:24:04,852][05218] Updated weights for policy 0, policy_version 66422 (0.0009) -[2023-10-16 05:24:05,218][05218] Updated weights for policy 0, policy_version 66432 (0.0008) -[2023-10-16 05:24:05,221][05219] Updated weights for policy 1, policy_version 66180 (0.0009) -[2023-10-16 05:24:05,583][05219] Updated weights for policy 1, policy_version 66190 (0.0009) -[2023-10-16 05:24:05,952][05219] Updated weights for policy 1, policy_version 66200 (0.0009) -[2023-10-16 05:24:07,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 135823360. Throughput: 0: 1791.7, 1: 1775.0. Samples: 33966458. Policy #0 lag: (min: 12.0, avg: 20.4, max: 44.0) -[2023-10-16 05:24:07,352][03835] Avg episode reward: [(0, '4.140'), (1, '8.080')] -[2023-10-16 05:24:09,066][05218] Updated weights for policy 0, policy_version 66442 (0.0010) -[2023-10-16 05:24:09,446][05218] Updated weights for policy 0, policy_version 66452 (0.0009) -[2023-10-16 05:24:09,564][05219] Updated weights for policy 1, policy_version 66210 (0.0009) -[2023-10-16 05:24:09,829][05218] Updated weights for policy 0, policy_version 66462 (0.0009) -[2023-10-16 05:24:09,929][05219] Updated weights for policy 1, policy_version 66220 (0.0008) -[2023-10-16 05:24:10,297][05219] Updated weights for policy 1, policy_version 66230 (0.0011) -[2023-10-16 05:24:10,663][05219] Updated weights for policy 1, policy_version 66240 (0.0010) -[2023-10-16 05:24:12,351][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 135888896. Throughput: 0: 1784.9, 1: 1793.2. Samples: 33976902. Policy #0 lag: (min: 12.0, avg: 20.4, max: 44.0) -[2023-10-16 05:24:12,352][03835] Avg episode reward: [(0, '4.420'), (1, '7.230')] -[2023-10-16 05:24:13,658][05218] Updated weights for policy 0, policy_version 66472 (0.0009) -[2023-10-16 05:24:14,034][05218] Updated weights for policy 0, policy_version 66482 (0.0008) -[2023-10-16 05:24:14,394][05218] Updated weights for policy 0, policy_version 66492 (0.0011) -[2023-10-16 05:24:14,519][05219] Updated weights for policy 1, policy_version 66250 (0.0008) -[2023-10-16 05:24:14,883][05219] Updated weights for policy 1, policy_version 66260 (0.0008) -[2023-10-16 05:24:15,254][05219] Updated weights for policy 1, policy_version 66270 (0.0007) -[2023-10-16 05:24:17,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 135954432. Throughput: 0: 1786.0, 1: 1772.2. Samples: 33998232. Policy #0 lag: (min: 12.0, avg: 20.4, max: 44.0) -[2023-10-16 05:24:17,351][03835] Avg episode reward: [(0, '5.180'), (1, '7.730')] -[2023-10-16 05:24:18,206][05218] Updated weights for policy 0, policy_version 66502 (0.0007) -[2023-10-16 05:24:18,583][05218] Updated weights for policy 0, policy_version 66512 (0.0007) -[2023-10-16 05:24:18,955][05218] Updated weights for policy 0, policy_version 66522 (0.0008) -[2023-10-16 05:24:18,986][05219] Updated weights for policy 1, policy_version 66280 (0.0008) -[2023-10-16 05:24:19,357][05219] Updated weights for policy 1, policy_version 66290 (0.0008) -[2023-10-16 05:24:19,722][05219] Updated weights for policy 1, policy_version 66300 (0.0010) -[2023-10-16 05:24:22,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 136019968. Throughput: 0: 1800.0, 1: 1781.7. Samples: 34020926. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-16 05:24:22,351][03835] Avg episode reward: [(0, '5.090'), (1, '7.430')] -[2023-10-16 05:24:22,580][05218] Updated weights for policy 0, policy_version 66532 (0.0007) -[2023-10-16 05:24:22,954][05218] Updated weights for policy 0, policy_version 66542 (0.0009) -[2023-10-16 05:24:23,331][05218] Updated weights for policy 0, policy_version 66552 (0.0009) -[2023-10-16 05:24:23,390][05219] Updated weights for policy 1, policy_version 66310 (0.0008) -[2023-10-16 05:24:23,751][05219] Updated weights for policy 1, policy_version 66320 (0.0009) -[2023-10-16 05:24:24,118][05219] Updated weights for policy 1, policy_version 66330 (0.0009) -[2023-10-16 05:24:27,177][05218] Updated weights for policy 0, policy_version 66562 (0.0009) -[2023-10-16 05:24:27,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 136085504. Throughput: 0: 1781.6, 1: 1781.9. Samples: 34030642. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-16 05:24:27,352][03835] Avg episode reward: [(0, '5.060'), (1, '7.030')] -[2023-10-16 05:24:27,595][05218] Updated weights for policy 0, policy_version 66572 (0.0009) -[2023-10-16 05:24:27,965][05218] Updated weights for policy 0, policy_version 66582 (0.0009) -[2023-10-16 05:24:28,037][05219] Updated weights for policy 1, policy_version 66340 (0.0010) -[2023-10-16 05:24:28,338][05218] Updated weights for policy 0, policy_version 66592 (0.0010) -[2023-10-16 05:24:28,397][05219] Updated weights for policy 1, policy_version 66350 (0.0007) -[2023-10-16 05:24:28,759][05219] Updated weights for policy 1, policy_version 66360 (0.0007) -[2023-10-16 05:24:31,999][05218] Updated weights for policy 0, policy_version 66602 (0.0008) -[2023-10-16 05:24:32,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 136151040. Throughput: 0: 1796.9, 1: 1778.9. Samples: 34052896. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-16 05:24:32,351][03835] Avg episode reward: [(0, '5.210'), (1, '7.260')] -[2023-10-16 05:24:32,381][05218] Updated weights for policy 0, policy_version 66612 (0.0008) -[2023-10-16 05:24:32,663][05219] Updated weights for policy 1, policy_version 66370 (0.0008) -[2023-10-16 05:24:32,745][05218] Updated weights for policy 0, policy_version 66622 (0.0011) -[2023-10-16 05:24:33,019][05219] Updated weights for policy 1, policy_version 66380 (0.0008) -[2023-10-16 05:24:33,382][05219] Updated weights for policy 1, policy_version 66390 (0.0009) -[2023-10-16 05:24:33,754][05219] Updated weights for policy 1, policy_version 66400 (0.0010) -[2023-10-16 05:24:36,663][05218] Updated weights for policy 0, policy_version 66632 (0.0011) -[2023-10-16 05:24:37,037][05218] Updated weights for policy 0, policy_version 66642 (0.0010) -[2023-10-16 05:24:37,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 136216576. Throughput: 0: 1783.4, 1: 1808.5. Samples: 34073856. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-16 05:24:37,351][03835] Avg episode reward: [(0, '4.530'), (1, '8.280')] -[2023-10-16 05:24:37,413][05218] Updated weights for policy 0, policy_version 66652 (0.0008) -[2023-10-16 05:24:37,434][05219] Updated weights for policy 1, policy_version 66410 (0.0008) -[2023-10-16 05:24:37,799][05219] Updated weights for policy 1, policy_version 66420 (0.0008) -[2023-10-16 05:24:38,165][05219] Updated weights for policy 1, policy_version 66430 (0.0009) -[2023-10-16 05:24:41,218][05218] Updated weights for policy 0, policy_version 66662 (0.0009) -[2023-10-16 05:24:41,602][05218] Updated weights for policy 0, policy_version 66672 (0.0009) -[2023-10-16 05:24:41,925][05219] Updated weights for policy 1, policy_version 66440 (0.0008) -[2023-10-16 05:24:41,972][05218] Updated weights for policy 0, policy_version 66682 (0.0009) -[2023-10-16 05:24:42,293][05219] Updated weights for policy 1, policy_version 66450 (0.0008) -[2023-10-16 05:24:42,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 136314880. Throughput: 0: 1785.4, 1: 1787.3. Samples: 34084938. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-16 05:24:42,351][03835] Avg episode reward: [(0, '4.760'), (1, '7.320')] -[2023-10-16 05:24:42,667][05219] Updated weights for policy 1, policy_version 66460 (0.0011) -[2023-10-16 05:24:45,708][05218] Updated weights for policy 0, policy_version 66692 (0.0008) -[2023-10-16 05:24:46,093][05218] Updated weights for policy 0, policy_version 66702 (0.0008) -[2023-10-16 05:24:46,445][05219] Updated weights for policy 1, policy_version 66470 (0.0010) -[2023-10-16 05:24:46,465][05218] Updated weights for policy 0, policy_version 66712 (0.0007) -[2023-10-16 05:24:46,807][05219] Updated weights for policy 1, policy_version 66480 (0.0009) -[2023-10-16 05:24:47,169][05219] Updated weights for policy 1, policy_version 66490 (0.0010) -[2023-10-16 05:24:47,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 136380416. Throughput: 0: 1780.5, 1: 1797.3. Samples: 34106040. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-16 05:24:47,351][03835] Avg episode reward: [(0, '5.210'), (1, '7.200')] -[2023-10-16 05:24:50,215][05218] Updated weights for policy 0, policy_version 66722 (0.0008) -[2023-10-16 05:24:50,581][05218] Updated weights for policy 0, policy_version 66732 (0.0009) -[2023-10-16 05:24:50,957][05218] Updated weights for policy 0, policy_version 66742 (0.0010) -[2023-10-16 05:24:51,092][05219] Updated weights for policy 1, policy_version 66500 (0.0010) -[2023-10-16 05:24:51,339][05218] Updated weights for policy 0, policy_version 66752 (0.0008) -[2023-10-16 05:24:51,458][05219] Updated weights for policy 1, policy_version 66510 (0.0008) -[2023-10-16 05:24:51,828][05219] Updated weights for policy 1, policy_version 66520 (0.0007) -[2023-10-16 05:24:52,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 136478720. Throughput: 0: 1773.3, 1: 1780.9. Samples: 34126398. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-16 05:24:52,351][03835] Avg episode reward: [(0, '5.250'), (1, '8.430')] -[2023-10-16 05:24:55,125][05218] Updated weights for policy 0, policy_version 66762 (0.0007) -[2023-10-16 05:24:55,510][05218] Updated weights for policy 0, policy_version 66772 (0.0007) -[2023-10-16 05:24:55,619][05219] Updated weights for policy 1, policy_version 66530 (0.0008) -[2023-10-16 05:24:55,880][05218] Updated weights for policy 0, policy_version 66782 (0.0007) -[2023-10-16 05:24:55,979][05219] Updated weights for policy 1, policy_version 66540 (0.0008) -[2023-10-16 05:24:56,343][05219] Updated weights for policy 1, policy_version 66550 (0.0007) -[2023-10-16 05:24:56,699][05219] Updated weights for policy 1, policy_version 66560 (0.0008) -[2023-10-16 05:24:57,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 136544256. Throughput: 0: 1793.2, 1: 1791.5. Samples: 34138210. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-16 05:24:57,351][03835] Avg episode reward: [(0, '5.570'), (1, '7.720')] -[2023-10-16 05:24:59,581][05218] Updated weights for policy 0, policy_version 66792 (0.0009) -[2023-10-16 05:24:59,953][05218] Updated weights for policy 0, policy_version 66802 (0.0010) -[2023-10-16 05:25:00,326][05218] Updated weights for policy 0, policy_version 66812 (0.0007) -[2023-10-16 05:25:00,378][05219] Updated weights for policy 1, policy_version 66570 (0.0007) -[2023-10-16 05:25:00,740][05219] Updated weights for policy 1, policy_version 66580 (0.0008) -[2023-10-16 05:25:01,096][05219] Updated weights for policy 1, policy_version 66590 (0.0007) -[2023-10-16 05:25:02,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 136609792. Throughput: 0: 1780.1, 1: 1785.1. Samples: 34158668. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-16 05:25:02,351][03835] Avg episode reward: [(0, '5.770'), (1, '7.120')] -[2023-10-16 05:25:04,057][05218] Updated weights for policy 0, policy_version 66822 (0.0009) -[2023-10-16 05:25:04,438][05218] Updated weights for policy 0, policy_version 66832 (0.0010) -[2023-10-16 05:25:04,815][05218] Updated weights for policy 0, policy_version 66842 (0.0009) -[2023-10-16 05:25:04,842][05219] Updated weights for policy 1, policy_version 66600 (0.0009) -[2023-10-16 05:25:05,211][05219] Updated weights for policy 1, policy_version 66610 (0.0009) -[2023-10-16 05:25:05,574][05219] Updated weights for policy 1, policy_version 66620 (0.0007) -[2023-10-16 05:25:07,351][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 136675328. Throughput: 0: 1778.9, 1: 1775.4. Samples: 34180870. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:25:07,352][03835] Avg episode reward: [(0, '5.800'), (1, '7.860')] -[2023-10-16 05:25:08,633][05218] Updated weights for policy 0, policy_version 66852 (0.0008) -[2023-10-16 05:25:09,005][05218] Updated weights for policy 0, policy_version 66862 (0.0009) -[2023-10-16 05:25:09,362][05219] Updated weights for policy 1, policy_version 66630 (0.0008) -[2023-10-16 05:25:09,387][05218] Updated weights for policy 0, policy_version 66872 (0.0008) -[2023-10-16 05:25:09,720][05219] Updated weights for policy 1, policy_version 66640 (0.0009) -[2023-10-16 05:25:10,088][05219] Updated weights for policy 1, policy_version 66650 (0.0010) -[2023-10-16 05:25:12,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 136740864. Throughput: 0: 1780.2, 1: 1778.5. Samples: 34190784. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:25:12,351][03835] Avg episode reward: [(0, '5.820'), (1, '7.240')] -[2023-10-16 05:25:13,114][05218] Updated weights for policy 0, policy_version 66882 (0.0009) -[2023-10-16 05:25:13,490][05218] Updated weights for policy 0, policy_version 66892 (0.0011) -[2023-10-16 05:25:13,866][05218] Updated weights for policy 0, policy_version 66902 (0.0009) -[2023-10-16 05:25:13,943][05219] Updated weights for policy 1, policy_version 66660 (0.0009) -[2023-10-16 05:25:14,242][05218] Updated weights for policy 0, policy_version 66912 (0.0008) -[2023-10-16 05:25:14,310][05219] Updated weights for policy 1, policy_version 66670 (0.0008) -[2023-10-16 05:25:14,675][05219] Updated weights for policy 1, policy_version 66680 (0.0008) -[2023-10-16 05:25:17,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 136806400. Throughput: 0: 1777.3, 1: 1774.7. Samples: 34212738. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:25:17,351][03835] Avg episode reward: [(0, '5.780'), (1, '7.050')] -[2023-10-16 05:25:18,064][05218] Updated weights for policy 0, policy_version 66922 (0.0011) -[2023-10-16 05:25:18,291][05219] Updated weights for policy 1, policy_version 66690 (0.0008) -[2023-10-16 05:25:18,435][05218] Updated weights for policy 0, policy_version 66932 (0.0009) -[2023-10-16 05:25:18,656][05219] Updated weights for policy 1, policy_version 66700 (0.0008) -[2023-10-16 05:25:18,808][05218] Updated weights for policy 0, policy_version 66942 (0.0007) -[2023-10-16 05:25:19,016][05219] Updated weights for policy 1, policy_version 66710 (0.0008) -[2023-10-16 05:25:19,379][05219] Updated weights for policy 1, policy_version 66720 (0.0007) -[2023-10-16 05:25:22,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 136871936. Throughput: 0: 1799.7, 1: 1775.8. Samples: 34234756. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:25:22,351][03835] Avg episode reward: [(0, '5.930'), (1, '6.830')] -[2023-10-16 05:25:22,569][05218] Updated weights for policy 0, policy_version 66952 (0.0008) -[2023-10-16 05:25:22,941][05218] Updated weights for policy 0, policy_version 66962 (0.0008) -[2023-10-16 05:25:23,183][05219] Updated weights for policy 1, policy_version 66730 (0.0007) -[2023-10-16 05:25:23,312][05218] Updated weights for policy 0, policy_version 66972 (0.0009) -[2023-10-16 05:25:23,555][05219] Updated weights for policy 1, policy_version 66740 (0.0010) -[2023-10-16 05:25:23,919][05219] Updated weights for policy 1, policy_version 66750 (0.0009) -[2023-10-16 05:25:27,152][05218] Updated weights for policy 0, policy_version 66982 (0.0009) -[2023-10-16 05:25:27,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 136937472. Throughput: 0: 1775.2, 1: 1771.8. Samples: 34244554. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:25:27,351][03835] Avg episode reward: [(0, '6.190'), (1, '6.210')] -[2023-10-16 05:25:27,526][05218] Updated weights for policy 0, policy_version 66992 (0.0010) -[2023-10-16 05:25:27,827][05219] Updated weights for policy 1, policy_version 66760 (0.0007) -[2023-10-16 05:25:27,904][05218] Updated weights for policy 0, policy_version 67002 (0.0009) -[2023-10-16 05:25:28,205][05219] Updated weights for policy 1, policy_version 66770 (0.0008) -[2023-10-16 05:25:28,562][05219] Updated weights for policy 1, policy_version 66780 (0.0009) -[2023-10-16 05:25:31,626][05218] Updated weights for policy 0, policy_version 67012 (0.0009) -[2023-10-16 05:25:32,004][05218] Updated weights for policy 0, policy_version 67022 (0.0010) -[2023-10-16 05:25:32,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 137003008. Throughput: 0: 1794.5, 1: 1775.5. Samples: 34266688. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:25:32,351][03835] Avg episode reward: [(0, '6.140'), (1, '5.560')] -[2023-10-16 05:25:32,367][05219] Updated weights for policy 1, policy_version 66790 (0.0009) -[2023-10-16 05:25:32,368][05218] Updated weights for policy 0, policy_version 67032 (0.0008) -[2023-10-16 05:25:32,732][05219] Updated weights for policy 1, policy_version 66800 (0.0010) -[2023-10-16 05:25:33,102][05219] Updated weights for policy 1, policy_version 66810 (0.0009) -[2023-10-16 05:25:36,199][05218] Updated weights for policy 0, policy_version 67042 (0.0008) -[2023-10-16 05:25:36,573][05218] Updated weights for policy 0, policy_version 67052 (0.0009) -[2023-10-16 05:25:36,873][05219] Updated weights for policy 1, policy_version 66820 (0.0010) -[2023-10-16 05:25:36,958][05218] Updated weights for policy 0, policy_version 67062 (0.0009) -[2023-10-16 05:25:37,241][05219] Updated weights for policy 1, policy_version 66830 (0.0009) -[2023-10-16 05:25:37,328][05218] Updated weights for policy 0, policy_version 67072 (0.0007) -[2023-10-16 05:25:37,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 137101312. Throughput: 0: 1771.4, 1: 1801.8. Samples: 34287192. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:25:37,351][03835] Avg episode reward: [(0, '6.050'), (1, '6.000')] -[2023-10-16 05:25:37,359][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000067072_68681728.pth... -[2023-10-16 05:25:37,399][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000065376_66945024.pth -[2023-10-16 05:25:37,404][04766] Saving a milestone ./train_atari/atari_timepilot_APPO/checkpoint_p0/milestones/checkpoint_000067072_68681728.pth -[2023-10-16 05:25:37,604][05219] Updated weights for policy 1, policy_version 66840 (0.0007) -[2023-10-16 05:25:37,892][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000066848_68452352.pth... -[2023-10-16 05:25:37,922][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000065184_66748416.pth -[2023-10-16 05:25:37,926][04891] Saving a milestone ./train_atari/atari_timepilot_APPO/checkpoint_p1/milestones/checkpoint_000066848_68452352.pth -[2023-10-16 05:25:41,029][05218] Updated weights for policy 0, policy_version 67082 (0.0009) -[2023-10-16 05:25:41,300][05219] Updated weights for policy 1, policy_version 66850 (0.0007) -[2023-10-16 05:25:41,403][05218] Updated weights for policy 0, policy_version 67092 (0.0009) -[2023-10-16 05:25:41,660][05219] Updated weights for policy 1, policy_version 66860 (0.0007) -[2023-10-16 05:25:41,776][05218] Updated weights for policy 0, policy_version 67102 (0.0007) -[2023-10-16 05:25:42,022][05219] Updated weights for policy 1, policy_version 66870 (0.0007) -[2023-10-16 05:25:42,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 137166848. Throughput: 0: 1790.5, 1: 1785.1. Samples: 34299114. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:25:42,351][03835] Avg episode reward: [(0, '6.450'), (1, '6.370')] -[2023-10-16 05:25:42,386][05219] Updated weights for policy 1, policy_version 66880 (0.0009) -[2023-10-16 05:25:45,499][05218] Updated weights for policy 0, policy_version 67112 (0.0010) -[2023-10-16 05:25:45,863][05218] Updated weights for policy 0, policy_version 67122 (0.0008) -[2023-10-16 05:25:46,044][05219] Updated weights for policy 1, policy_version 66890 (0.0010) -[2023-10-16 05:25:46,238][05218] Updated weights for policy 0, policy_version 67132 (0.0008) -[2023-10-16 05:25:46,406][05219] Updated weights for policy 1, policy_version 66900 (0.0008) -[2023-10-16 05:25:46,776][05219] Updated weights for policy 1, policy_version 66910 (0.0009) -[2023-10-16 05:25:47,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 137265152. Throughput: 0: 1776.0, 1: 1802.9. Samples: 34319718. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:25:47,351][03835] Avg episode reward: [(0, '6.420'), (1, '5.990')] -[2023-10-16 05:25:49,992][05218] Updated weights for policy 0, policy_version 67142 (0.0008) -[2023-10-16 05:25:50,370][05218] Updated weights for policy 0, policy_version 67152 (0.0009) -[2023-10-16 05:25:50,704][05219] Updated weights for policy 1, policy_version 66920 (0.0008) -[2023-10-16 05:25:50,743][05218] Updated weights for policy 0, policy_version 67162 (0.0008) -[2023-10-16 05:25:51,070][05219] Updated weights for policy 1, policy_version 66930 (0.0009) -[2023-10-16 05:25:51,432][05219] Updated weights for policy 1, policy_version 66940 (0.0008) -[2023-10-16 05:25:52,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 137330688. Throughput: 0: 1776.0, 1: 1781.2. Samples: 34340942. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:25:52,351][03835] Avg episode reward: [(0, '6.330'), (1, '5.990')] -[2023-10-16 05:25:54,388][05218] Updated weights for policy 0, policy_version 67172 (0.0008) -[2023-10-16 05:25:54,769][05218] Updated weights for policy 0, policy_version 67182 (0.0010) -[2023-10-16 05:25:55,144][05218] Updated weights for policy 0, policy_version 67192 (0.0009) -[2023-10-16 05:25:55,161][05219] Updated weights for policy 1, policy_version 66950 (0.0009) -[2023-10-16 05:25:55,535][05219] Updated weights for policy 1, policy_version 66960 (0.0008) -[2023-10-16 05:25:55,898][05219] Updated weights for policy 1, policy_version 66970 (0.0008) -[2023-10-16 05:25:57,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 137396224. Throughput: 0: 1782.2, 1: 1803.1. Samples: 34352124. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:25:57,351][03835] Avg episode reward: [(0, '6.330'), (1, '6.180')] -[2023-10-16 05:25:58,934][05218] Updated weights for policy 0, policy_version 67202 (0.0008) -[2023-10-16 05:25:59,305][05218] Updated weights for policy 0, policy_version 67212 (0.0009) -[2023-10-16 05:25:59,681][05218] Updated weights for policy 0, policy_version 67222 (0.0008) -[2023-10-16 05:25:59,718][05219] Updated weights for policy 1, policy_version 66980 (0.0009) -[2023-10-16 05:26:00,046][05218] Updated weights for policy 0, policy_version 67232 (0.0009) -[2023-10-16 05:26:00,084][05219] Updated weights for policy 1, policy_version 66990 (0.0007) -[2023-10-16 05:26:00,448][05219] Updated weights for policy 1, policy_version 67000 (0.0007) -[2023-10-16 05:26:02,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 137461760. Throughput: 0: 1781.4, 1: 1786.5. Samples: 34373294. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:26:02,351][03835] Avg episode reward: [(0, '6.340'), (1, '6.470')] -[2023-10-16 05:26:03,792][05218] Updated weights for policy 0, policy_version 67242 (0.0008) -[2023-10-16 05:26:04,156][05218] Updated weights for policy 0, policy_version 67252 (0.0010) -[2023-10-16 05:26:04,313][05219] Updated weights for policy 1, policy_version 67010 (0.0009) -[2023-10-16 05:26:04,529][05218] Updated weights for policy 0, policy_version 67262 (0.0007) -[2023-10-16 05:26:04,682][05219] Updated weights for policy 1, policy_version 67020 (0.0008) -[2023-10-16 05:26:05,048][05219] Updated weights for policy 1, policy_version 67030 (0.0008) -[2023-10-16 05:26:05,401][05219] Updated weights for policy 1, policy_version 67040 (0.0008) -[2023-10-16 05:26:07,350][03835] Fps is (10 sec: 13106.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 137527296. Throughput: 0: 1791.4, 1: 1779.0. Samples: 34395424. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:26:07,352][03835] Avg episode reward: [(0, '6.500'), (1, '6.980')] -[2023-10-16 05:26:08,195][05218] Updated weights for policy 0, policy_version 67272 (0.0007) -[2023-10-16 05:26:08,561][05218] Updated weights for policy 0, policy_version 67282 (0.0007) -[2023-10-16 05:26:08,942][05218] Updated weights for policy 0, policy_version 67292 (0.0007) -[2023-10-16 05:26:09,239][05219] Updated weights for policy 1, policy_version 67050 (0.0008) -[2023-10-16 05:26:09,609][05219] Updated weights for policy 1, policy_version 67060 (0.0009) -[2023-10-16 05:26:09,967][05219] Updated weights for policy 1, policy_version 67070 (0.0007) -[2023-10-16 05:26:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 137592832. Throughput: 0: 1792.6, 1: 1782.8. Samples: 34405446. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:26:12,351][03835] Avg episode reward: [(0, '6.900'), (1, '6.560')] -[2023-10-16 05:26:12,623][05218] Updated weights for policy 0, policy_version 67302 (0.0008) -[2023-10-16 05:26:12,997][05218] Updated weights for policy 0, policy_version 67312 (0.0007) -[2023-10-16 05:26:13,382][05218] Updated weights for policy 0, policy_version 67322 (0.0009) -[2023-10-16 05:26:13,863][05219] Updated weights for policy 1, policy_version 67080 (0.0007) -[2023-10-16 05:26:14,225][05219] Updated weights for policy 1, policy_version 67090 (0.0008) -[2023-10-16 05:26:14,597][05219] Updated weights for policy 1, policy_version 67100 (0.0008) -[2023-10-16 05:26:17,097][05218] Updated weights for policy 0, policy_version 67332 (0.0009) -[2023-10-16 05:26:17,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 137658368. Throughput: 0: 1798.4, 1: 1781.9. Samples: 34427802. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:26:17,351][03835] Avg episode reward: [(0, '6.490'), (1, '6.570')] -[2023-10-16 05:26:17,471][05218] Updated weights for policy 0, policy_version 67342 (0.0007) -[2023-10-16 05:26:17,852][05218] Updated weights for policy 0, policy_version 67352 (0.0007) -[2023-10-16 05:26:18,284][05219] Updated weights for policy 1, policy_version 67110 (0.0007) -[2023-10-16 05:26:18,663][05219] Updated weights for policy 1, policy_version 67120 (0.0007) -[2023-10-16 05:26:19,037][05219] Updated weights for policy 1, policy_version 67130 (0.0010) -[2023-10-16 05:26:21,514][05218] Updated weights for policy 0, policy_version 67362 (0.0008) -[2023-10-16 05:26:21,896][05218] Updated weights for policy 0, policy_version 67372 (0.0010) -[2023-10-16 05:26:22,267][05218] Updated weights for policy 0, policy_version 67382 (0.0010) -[2023-10-16 05:26:22,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 137723904. Throughput: 0: 1808.6, 1: 1788.1. Samples: 34449042. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:26:22,351][03835] Avg episode reward: [(0, '6.170'), (1, '5.960')] -[2023-10-16 05:26:22,646][05218] Updated weights for policy 0, policy_version 67392 (0.0010) -[2023-10-16 05:26:22,663][05219] Updated weights for policy 1, policy_version 67140 (0.0008) -[2023-10-16 05:26:23,036][05219] Updated weights for policy 1, policy_version 67150 (0.0009) -[2023-10-16 05:26:23,398][05219] Updated weights for policy 1, policy_version 67160 (0.0010) -[2023-10-16 05:26:26,431][05218] Updated weights for policy 0, policy_version 67402 (0.0009) -[2023-10-16 05:26:26,803][05218] Updated weights for policy 0, policy_version 67412 (0.0009) -[2023-10-16 05:26:27,183][05218] Updated weights for policy 0, policy_version 67422 (0.0007) -[2023-10-16 05:26:27,190][05219] Updated weights for policy 1, policy_version 67170 (0.0011) -[2023-10-16 05:26:27,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 137822208. Throughput: 0: 1798.0, 1: 1778.8. Samples: 34460066. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:26:27,351][03835] Avg episode reward: [(0, '6.200'), (1, '6.010')] -[2023-10-16 05:26:27,544][05219] Updated weights for policy 1, policy_version 67180 (0.0009) -[2023-10-16 05:26:27,907][05219] Updated weights for policy 1, policy_version 67190 (0.0007) -[2023-10-16 05:26:28,269][05219] Updated weights for policy 1, policy_version 67200 (0.0009) -[2023-10-16 05:26:30,893][05218] Updated weights for policy 0, policy_version 67432 (0.0009) -[2023-10-16 05:26:31,281][05218] Updated weights for policy 0, policy_version 67442 (0.0008) -[2023-10-16 05:26:31,647][05218] Updated weights for policy 0, policy_version 67452 (0.0009) -[2023-10-16 05:26:31,969][05219] Updated weights for policy 1, policy_version 67210 (0.0007) -[2023-10-16 05:26:32,339][05219] Updated weights for policy 1, policy_version 67220 (0.0008) -[2023-10-16 05:26:32,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 137887744. Throughput: 0: 1814.1, 1: 1793.5. Samples: 34482060. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:26:32,351][03835] Avg episode reward: [(0, '6.360'), (1, '6.960')] -[2023-10-16 05:26:32,707][05219] Updated weights for policy 1, policy_version 67230 (0.0009) -[2023-10-16 05:26:35,367][05218] Updated weights for policy 0, policy_version 67462 (0.0008) -[2023-10-16 05:26:35,743][05218] Updated weights for policy 0, policy_version 67472 (0.0010) -[2023-10-16 05:26:36,116][05218] Updated weights for policy 0, policy_version 67482 (0.0008) -[2023-10-16 05:26:36,530][05219] Updated weights for policy 1, policy_version 67240 (0.0009) -[2023-10-16 05:26:36,898][05219] Updated weights for policy 1, policy_version 67250 (0.0008) -[2023-10-16 05:26:37,266][05219] Updated weights for policy 1, policy_version 67260 (0.0009) -[2023-10-16 05:26:37,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 137953280. Throughput: 0: 1800.9, 1: 1796.0. Samples: 34502800. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-16 05:26:37,351][03835] Avg episode reward: [(0, '6.490'), (1, '6.720')] -[2023-10-16 05:26:39,950][05218] Updated weights for policy 0, policy_version 67492 (0.0009) -[2023-10-16 05:26:40,327][05218] Updated weights for policy 0, policy_version 67502 (0.0011) -[2023-10-16 05:26:40,698][05218] Updated weights for policy 0, policy_version 67512 (0.0010) -[2023-10-16 05:26:40,992][05219] Updated weights for policy 1, policy_version 67270 (0.0007) -[2023-10-16 05:26:41,356][05219] Updated weights for policy 1, policy_version 67280 (0.0008) -[2023-10-16 05:26:41,721][05219] Updated weights for policy 1, policy_version 67290 (0.0009) -[2023-10-16 05:26:42,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 138051584. Throughput: 0: 1810.8, 1: 1791.0. Samples: 34514202. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-16 05:26:42,351][03835] Avg episode reward: [(0, '6.660'), (1, '6.440')] -[2023-10-16 05:26:44,332][05218] Updated weights for policy 0, policy_version 67522 (0.0008) -[2023-10-16 05:26:44,722][05218] Updated weights for policy 0, policy_version 67532 (0.0009) -[2023-10-16 05:26:45,093][05218] Updated weights for policy 0, policy_version 67542 (0.0008) -[2023-10-16 05:26:45,468][05218] Updated weights for policy 0, policy_version 67552 (0.0007) -[2023-10-16 05:26:45,631][05219] Updated weights for policy 1, policy_version 67300 (0.0009) -[2023-10-16 05:26:45,994][05219] Updated weights for policy 1, policy_version 67310 (0.0007) -[2023-10-16 05:26:46,360][05219] Updated weights for policy 1, policy_version 67320 (0.0008) -[2023-10-16 05:26:47,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 138117120. Throughput: 0: 1796.4, 1: 1802.9. Samples: 34535262. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-16 05:26:47,351][03835] Avg episode reward: [(0, '6.770'), (1, '6.930')] -[2023-10-16 05:26:49,333][05218] Updated weights for policy 0, policy_version 67562 (0.0009) -[2023-10-16 05:26:49,719][05218] Updated weights for policy 0, policy_version 67572 (0.0009) -[2023-10-16 05:26:50,071][05219] Updated weights for policy 1, policy_version 67330 (0.0008) -[2023-10-16 05:26:50,099][05218] Updated weights for policy 0, policy_version 67582 (0.0009) -[2023-10-16 05:26:50,441][05219] Updated weights for policy 1, policy_version 67340 (0.0010) -[2023-10-16 05:26:50,812][05219] Updated weights for policy 1, policy_version 67350 (0.0010) -[2023-10-16 05:26:51,168][05219] Updated weights for policy 1, policy_version 67360 (0.0009) -[2023-10-16 05:26:52,351][03835] Fps is (10 sec: 13106.6, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 138182656. Throughput: 0: 1794.3, 1: 1794.7. Samples: 34556928. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-16 05:26:52,352][03835] Avg episode reward: [(0, '7.330'), (1, '7.050')] -[2023-10-16 05:26:53,876][05218] Updated weights for policy 0, policy_version 67592 (0.0009) -[2023-10-16 05:26:54,252][05218] Updated weights for policy 0, policy_version 67602 (0.0009) -[2023-10-16 05:26:54,627][05218] Updated weights for policy 0, policy_version 67612 (0.0007) -[2023-10-16 05:26:54,873][05219] Updated weights for policy 1, policy_version 67370 (0.0007) -[2023-10-16 05:26:55,227][05219] Updated weights for policy 1, policy_version 67380 (0.0009) -[2023-10-16 05:26:55,587][05219] Updated weights for policy 1, policy_version 67390 (0.0008) -[2023-10-16 05:26:57,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 138248192. Throughput: 0: 1792.1, 1: 1809.8. Samples: 34567530. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-16 05:26:57,351][03835] Avg episode reward: [(0, '6.870'), (1, '7.020')] -[2023-10-16 05:26:58,417][05218] Updated weights for policy 0, policy_version 67622 (0.0009) -[2023-10-16 05:26:58,789][05218] Updated weights for policy 0, policy_version 67632 (0.0008) -[2023-10-16 05:26:59,159][05218] Updated weights for policy 0, policy_version 67642 (0.0008) -[2023-10-16 05:26:59,230][05219] Updated weights for policy 1, policy_version 67400 (0.0010) -[2023-10-16 05:26:59,600][05219] Updated weights for policy 1, policy_version 67410 (0.0008) -[2023-10-16 05:26:59,964][05219] Updated weights for policy 1, policy_version 67420 (0.0009) -[2023-10-16 05:27:02,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 138313728. Throughput: 0: 1784.3, 1: 1802.8. Samples: 34589218. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-16 05:27:02,351][03835] Avg episode reward: [(0, '7.150'), (1, '7.210')] -[2023-10-16 05:27:02,892][05218] Updated weights for policy 0, policy_version 67652 (0.0008) -[2023-10-16 05:27:03,275][05218] Updated weights for policy 0, policy_version 67662 (0.0009) -[2023-10-16 05:27:03,652][05218] Updated weights for policy 0, policy_version 67672 (0.0009) -[2023-10-16 05:27:03,822][05219] Updated weights for policy 1, policy_version 67430 (0.0007) -[2023-10-16 05:27:04,204][05219] Updated weights for policy 1, policy_version 67440 (0.0008) -[2023-10-16 05:27:04,573][05219] Updated weights for policy 1, policy_version 67450 (0.0007) -[2023-10-16 05:27:07,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 138379264. Throughput: 0: 1805.4, 1: 1800.8. Samples: 34611320. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-16 05:27:07,351][03835] Avg episode reward: [(0, '6.710'), (1, '7.360')] -[2023-10-16 05:27:07,551][05218] Updated weights for policy 0, policy_version 67682 (0.0010) -[2023-10-16 05:27:07,930][05218] Updated weights for policy 0, policy_version 67692 (0.0008) -[2023-10-16 05:27:08,302][05218] Updated weights for policy 0, policy_version 67702 (0.0008) -[2023-10-16 05:27:08,307][05219] Updated weights for policy 1, policy_version 67460 (0.0008) -[2023-10-16 05:27:08,670][05219] Updated weights for policy 1, policy_version 67470 (0.0007) -[2023-10-16 05:27:08,678][05218] Updated weights for policy 0, policy_version 67712 (0.0007) -[2023-10-16 05:27:09,044][05219] Updated weights for policy 1, policy_version 67480 (0.0008) -[2023-10-16 05:27:12,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 138444800. Throughput: 0: 1778.0, 1: 1796.4. Samples: 34620916. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-16 05:27:12,351][03835] Avg episode reward: [(0, '6.510'), (1, '6.460')] -[2023-10-16 05:27:12,538][05218] Updated weights for policy 0, policy_version 67722 (0.0009) -[2023-10-16 05:27:12,648][05219] Updated weights for policy 1, policy_version 67490 (0.0009) -[2023-10-16 05:27:12,911][05218] Updated weights for policy 0, policy_version 67732 (0.0009) -[2023-10-16 05:27:13,018][05219] Updated weights for policy 1, policy_version 67500 (0.0007) -[2023-10-16 05:27:13,288][05218] Updated weights for policy 0, policy_version 67742 (0.0008) -[2023-10-16 05:27:13,384][05219] Updated weights for policy 1, policy_version 67510 (0.0009) -[2023-10-16 05:27:13,746][05219] Updated weights for policy 1, policy_version 67520 (0.0010) -[2023-10-16 05:27:17,098][05218] Updated weights for policy 0, policy_version 67752 (0.0008) -[2023-10-16 05:27:17,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 138510336. Throughput: 0: 1789.1, 1: 1788.1. Samples: 34643036. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-16 05:27:17,351][03835] Avg episode reward: [(0, '7.080'), (1, '6.620')] -[2023-10-16 05:27:17,474][05218] Updated weights for policy 0, policy_version 67762 (0.0008) -[2023-10-16 05:27:17,622][05219] Updated weights for policy 1, policy_version 67530 (0.0007) -[2023-10-16 05:27:17,845][05218] Updated weights for policy 0, policy_version 67772 (0.0008) -[2023-10-16 05:27:17,988][05219] Updated weights for policy 1, policy_version 67540 (0.0010) -[2023-10-16 05:27:18,349][05219] Updated weights for policy 1, policy_version 67550 (0.0011) -[2023-10-16 05:27:21,726][05218] Updated weights for policy 0, policy_version 67782 (0.0008) -[2023-10-16 05:27:22,096][05218] Updated weights for policy 0, policy_version 67792 (0.0009) -[2023-10-16 05:27:22,140][05219] Updated weights for policy 1, policy_version 67560 (0.0007) -[2023-10-16 05:27:22,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 138575872. Throughput: 0: 1776.7, 1: 1802.3. Samples: 34663854. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-16 05:27:22,351][03835] Avg episode reward: [(0, '7.220'), (1, '6.860')] -[2023-10-16 05:27:22,467][05218] Updated weights for policy 0, policy_version 67802 (0.0008) -[2023-10-16 05:27:22,504][05219] Updated weights for policy 1, policy_version 67570 (0.0007) -[2023-10-16 05:27:22,871][05219] Updated weights for policy 1, policy_version 67580 (0.0008) -[2023-10-16 05:27:26,154][05218] Updated weights for policy 0, policy_version 67812 (0.0010) -[2023-10-16 05:27:26,520][05219] Updated weights for policy 1, policy_version 67590 (0.0007) -[2023-10-16 05:27:26,521][05218] Updated weights for policy 0, policy_version 67822 (0.0008) -[2023-10-16 05:27:26,884][05219] Updated weights for policy 1, policy_version 67600 (0.0009) -[2023-10-16 05:27:26,897][05218] Updated weights for policy 0, policy_version 67832 (0.0009) -[2023-10-16 05:27:27,253][05219] Updated weights for policy 1, policy_version 67610 (0.0007) -[2023-10-16 05:27:27,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 138674176. Throughput: 0: 1785.1, 1: 1792.1. Samples: 34675178. Policy #0 lag: (min: 10.0, avg: 37.9, max: 40.0) -[2023-10-16 05:27:27,351][03835] Avg episode reward: [(0, '7.510'), (1, '6.940')] -[2023-10-16 05:27:30,604][05218] Updated weights for policy 0, policy_version 67842 (0.0007) -[2023-10-16 05:27:30,979][05218] Updated weights for policy 0, policy_version 67852 (0.0008) -[2023-10-16 05:27:31,000][05219] Updated weights for policy 1, policy_version 67620 (0.0007) -[2023-10-16 05:27:31,352][05218] Updated weights for policy 0, policy_version 67862 (0.0009) -[2023-10-16 05:27:31,365][05219] Updated weights for policy 1, policy_version 67630 (0.0009) -[2023-10-16 05:27:31,729][05219] Updated weights for policy 1, policy_version 67640 (0.0008) -[2023-10-16 05:27:31,729][05218] Updated weights for policy 0, policy_version 67872 (0.0008) -[2023-10-16 05:27:32,350][03835] Fps is (10 sec: 19660.5, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 138772480. Throughput: 0: 1782.2, 1: 1794.6. Samples: 34696220. Policy #0 lag: (min: 10.0, avg: 37.9, max: 40.0) -[2023-10-16 05:27:32,351][03835] Avg episode reward: [(0, '6.950'), (1, '6.730')] -[2023-10-16 05:27:35,404][05218] Updated weights for policy 0, policy_version 67882 (0.0009) -[2023-10-16 05:27:35,601][05219] Updated weights for policy 1, policy_version 67650 (0.0010) -[2023-10-16 05:27:35,774][05218] Updated weights for policy 0, policy_version 67892 (0.0008) -[2023-10-16 05:27:35,966][05219] Updated weights for policy 1, policy_version 67660 (0.0007) -[2023-10-16 05:27:36,146][05218] Updated weights for policy 0, policy_version 67902 (0.0009) -[2023-10-16 05:27:36,330][05219] Updated weights for policy 1, policy_version 67670 (0.0008) -[2023-10-16 05:27:36,692][05219] Updated weights for policy 1, policy_version 67680 (0.0007) -[2023-10-16 05:27:37,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 138838016. Throughput: 0: 1775.8, 1: 1782.1. Samples: 34717030. Policy #0 lag: (min: 10.0, avg: 37.9, max: 40.0) -[2023-10-16 05:27:37,351][03835] Avg episode reward: [(0, '6.530'), (1, '7.570')] -[2023-10-16 05:27:37,357][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000067680_69304320.pth... -[2023-10-16 05:27:37,357][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000067904_69533696.pth... -[2023-10-16 05:27:37,394][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000066240_67829760.pth -[2023-10-16 05:27:37,395][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000066016_67600384.pth -[2023-10-16 05:27:39,646][05218] Updated weights for policy 0, policy_version 67912 (0.0008) -[2023-10-16 05:27:40,033][05218] Updated weights for policy 0, policy_version 67922 (0.0007) -[2023-10-16 05:27:40,407][05218] Updated weights for policy 0, policy_version 67932 (0.0007) -[2023-10-16 05:27:40,408][05219] Updated weights for policy 1, policy_version 67690 (0.0008) -[2023-10-16 05:27:40,771][05219] Updated weights for policy 1, policy_version 67700 (0.0008) -[2023-10-16 05:27:41,131][05219] Updated weights for policy 1, policy_version 67710 (0.0009) -[2023-10-16 05:27:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 138903552. Throughput: 0: 1787.2, 1: 1794.8. Samples: 34728722. Policy #0 lag: (min: 10.0, avg: 37.9, max: 40.0) -[2023-10-16 05:27:42,351][03835] Avg episode reward: [(0, '7.070'), (1, '7.070')] -[2023-10-16 05:27:44,052][05218] Updated weights for policy 0, policy_version 67942 (0.0008) -[2023-10-16 05:27:44,425][05218] Updated weights for policy 0, policy_version 67952 (0.0009) -[2023-10-16 05:27:44,804][05218] Updated weights for policy 0, policy_version 67962 (0.0009) -[2023-10-16 05:27:44,987][05219] Updated weights for policy 1, policy_version 67720 (0.0007) -[2023-10-16 05:27:45,350][05219] Updated weights for policy 1, policy_version 67730 (0.0007) -[2023-10-16 05:27:45,729][05219] Updated weights for policy 1, policy_version 67740 (0.0007) -[2023-10-16 05:27:47,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 138969088. Throughput: 0: 1788.4, 1: 1778.1. Samples: 34749712. Policy #0 lag: (min: 10.0, avg: 37.9, max: 40.0) -[2023-10-16 05:27:47,352][03835] Avg episode reward: [(0, '7.020'), (1, '6.800')] -[2023-10-16 05:27:48,501][05218] Updated weights for policy 0, policy_version 67972 (0.0008) -[2023-10-16 05:27:48,880][05218] Updated weights for policy 0, policy_version 67982 (0.0009) -[2023-10-16 05:27:49,254][05218] Updated weights for policy 0, policy_version 67992 (0.0010) -[2023-10-16 05:27:49,620][05219] Updated weights for policy 1, policy_version 67750 (0.0008) -[2023-10-16 05:27:49,988][05219] Updated weights for policy 1, policy_version 67760 (0.0011) -[2023-10-16 05:27:50,356][05219] Updated weights for policy 1, policy_version 67770 (0.0009) -[2023-10-16 05:27:52,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 139034624. Throughput: 0: 1791.9, 1: 1775.4. Samples: 34771850. Policy #0 lag: (min: 10.0, avg: 37.9, max: 40.0) -[2023-10-16 05:27:52,351][03835] Avg episode reward: [(0, '6.210'), (1, '6.610')] -[2023-10-16 05:27:53,035][05218] Updated weights for policy 0, policy_version 68002 (0.0009) -[2023-10-16 05:27:53,408][05218] Updated weights for policy 0, policy_version 68012 (0.0009) -[2023-10-16 05:27:53,782][05218] Updated weights for policy 0, policy_version 68022 (0.0009) -[2023-10-16 05:27:54,060][05219] Updated weights for policy 1, policy_version 67780 (0.0008) -[2023-10-16 05:27:54,155][05218] Updated weights for policy 0, policy_version 68032 (0.0008) -[2023-10-16 05:27:54,426][05219] Updated weights for policy 1, policy_version 67790 (0.0008) -[2023-10-16 05:27:54,805][05219] Updated weights for policy 1, policy_version 67800 (0.0008) -[2023-10-16 05:27:57,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 139100160. Throughput: 0: 1798.3, 1: 1784.0. Samples: 34782118. Policy #0 lag: (min: 10.0, avg: 37.9, max: 40.0) -[2023-10-16 05:27:57,351][03835] Avg episode reward: [(0, '7.080'), (1, '6.450')] -[2023-10-16 05:27:57,851][05218] Updated weights for policy 0, policy_version 68042 (0.0007) -[2023-10-16 05:27:58,228][05218] Updated weights for policy 0, policy_version 68052 (0.0007) -[2023-10-16 05:27:58,599][05218] Updated weights for policy 0, policy_version 68062 (0.0007) -[2023-10-16 05:27:58,614][05219] Updated weights for policy 1, policy_version 67810 (0.0008) -[2023-10-16 05:27:58,977][05219] Updated weights for policy 1, policy_version 67820 (0.0008) -[2023-10-16 05:27:59,347][05219] Updated weights for policy 1, policy_version 67830 (0.0008) -[2023-10-16 05:27:59,715][05219] Updated weights for policy 1, policy_version 67840 (0.0007) -[2023-10-16 05:28:02,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 139165696. Throughput: 0: 1801.0, 1: 1790.0. Samples: 34804632. Policy #0 lag: (min: 10.0, avg: 37.9, max: 40.0) -[2023-10-16 05:28:02,351][03835] Avg episode reward: [(0, '6.900'), (1, '6.550')] -[2023-10-16 05:28:02,419][05218] Updated weights for policy 0, policy_version 68072 (0.0008) -[2023-10-16 05:28:02,794][05218] Updated weights for policy 0, policy_version 68082 (0.0008) -[2023-10-16 05:28:03,162][05218] Updated weights for policy 0, policy_version 68092 (0.0009) -[2023-10-16 05:28:03,305][05219] Updated weights for policy 1, policy_version 67850 (0.0007) -[2023-10-16 05:28:03,677][05219] Updated weights for policy 1, policy_version 67860 (0.0010) -[2023-10-16 05:28:04,052][05219] Updated weights for policy 1, policy_version 67870 (0.0009) -[2023-10-16 05:28:06,838][05218] Updated weights for policy 0, policy_version 68102 (0.0009) -[2023-10-16 05:28:07,218][05218] Updated weights for policy 0, policy_version 68112 (0.0010) -[2023-10-16 05:28:07,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 139231232. Throughput: 0: 1811.5, 1: 1802.8. Samples: 34826498. Policy #0 lag: (min: 10.0, avg: 37.9, max: 40.0) -[2023-10-16 05:28:07,351][03835] Avg episode reward: [(0, '6.350'), (1, '7.550')] -[2023-10-16 05:28:07,587][05218] Updated weights for policy 0, policy_version 68122 (0.0007) -[2023-10-16 05:28:07,636][05219] Updated weights for policy 1, policy_version 67880 (0.0008) -[2023-10-16 05:28:08,011][05219] Updated weights for policy 1, policy_version 67890 (0.0009) -[2023-10-16 05:28:08,377][05219] Updated weights for policy 1, policy_version 67900 (0.0008) -[2023-10-16 05:28:11,263][05218] Updated weights for policy 0, policy_version 68132 (0.0007) -[2023-10-16 05:28:11,640][05218] Updated weights for policy 0, policy_version 68142 (0.0008) -[2023-10-16 05:28:11,969][05219] Updated weights for policy 1, policy_version 67910 (0.0008) -[2023-10-16 05:28:12,010][05218] Updated weights for policy 0, policy_version 68152 (0.0009) -[2023-10-16 05:28:12,325][05219] Updated weights for policy 1, policy_version 67920 (0.0008) -[2023-10-16 05:28:12,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 139329536. Throughput: 0: 1810.0, 1: 1793.8. Samples: 34837350. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-16 05:28:12,351][03835] Avg episode reward: [(0, '6.810'), (1, '6.410')] -[2023-10-16 05:28:12,695][05219] Updated weights for policy 1, policy_version 67930 (0.0009) -[2023-10-16 05:28:15,819][05218] Updated weights for policy 0, policy_version 68162 (0.0008) -[2023-10-16 05:28:16,199][05218] Updated weights for policy 0, policy_version 68172 (0.0010) -[2023-10-16 05:28:16,499][05219] Updated weights for policy 1, policy_version 67940 (0.0008) -[2023-10-16 05:28:16,575][05218] Updated weights for policy 0, policy_version 68182 (0.0009) -[2023-10-16 05:28:16,878][05219] Updated weights for policy 1, policy_version 67950 (0.0008) -[2023-10-16 05:28:16,958][05218] Updated weights for policy 0, policy_version 68192 (0.0009) -[2023-10-16 05:28:17,232][05219] Updated weights for policy 1, policy_version 67960 (0.0010) -[2023-10-16 05:28:17,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 139395072. Throughput: 0: 1807.1, 1: 1804.6. Samples: 34858746. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-16 05:28:17,351][03835] Avg episode reward: [(0, '7.080'), (1, '7.510')] -[2023-10-16 05:28:20,785][05218] Updated weights for policy 0, policy_version 68202 (0.0008) -[2023-10-16 05:28:20,993][05219] Updated weights for policy 1, policy_version 67970 (0.0009) -[2023-10-16 05:28:21,164][05218] Updated weights for policy 0, policy_version 68212 (0.0007) -[2023-10-16 05:28:21,364][05219] Updated weights for policy 1, policy_version 67980 (0.0007) -[2023-10-16 05:28:21,528][05218] Updated weights for policy 0, policy_version 68222 (0.0009) -[2023-10-16 05:28:21,726][05219] Updated weights for policy 1, policy_version 67990 (0.0008) -[2023-10-16 05:28:22,094][05219] Updated weights for policy 1, policy_version 68000 (0.0009) -[2023-10-16 05:28:22,350][03835] Fps is (10 sec: 16383.8, 60 sec: 15291.7, 300 sec: 14440.1). Total num frames: 139493376. Throughput: 0: 1794.1, 1: 1802.0. Samples: 34878852. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-16 05:28:22,351][03835] Avg episode reward: [(0, '6.740'), (1, '6.950')] -[2023-10-16 05:28:25,199][05218] Updated weights for policy 0, policy_version 68232 (0.0008) -[2023-10-16 05:28:25,569][05218] Updated weights for policy 0, policy_version 68242 (0.0009) -[2023-10-16 05:28:25,942][05218] Updated weights for policy 0, policy_version 68252 (0.0008) -[2023-10-16 05:28:25,950][05219] Updated weights for policy 1, policy_version 68010 (0.0008) -[2023-10-16 05:28:26,308][05219] Updated weights for policy 1, policy_version 68020 (0.0007) -[2023-10-16 05:28:26,676][05219] Updated weights for policy 1, policy_version 68030 (0.0009) -[2023-10-16 05:28:27,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 139558912. Throughput: 0: 1802.9, 1: 1804.3. Samples: 34891048. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-16 05:28:27,351][03835] Avg episode reward: [(0, '6.170'), (1, '6.410')] -[2023-10-16 05:28:29,703][05218] Updated weights for policy 0, policy_version 68262 (0.0008) -[2023-10-16 05:28:30,081][05218] Updated weights for policy 0, policy_version 68272 (0.0007) -[2023-10-16 05:28:30,460][05218] Updated weights for policy 0, policy_version 68282 (0.0008) -[2023-10-16 05:28:30,542][05219] Updated weights for policy 1, policy_version 68040 (0.0008) -[2023-10-16 05:28:30,910][05219] Updated weights for policy 1, policy_version 68050 (0.0008) -[2023-10-16 05:28:31,279][05219] Updated weights for policy 1, policy_version 68060 (0.0008) -[2023-10-16 05:28:32,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.2). Total num frames: 139624448. Throughput: 0: 1786.8, 1: 1808.2. Samples: 34911484. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-16 05:28:32,351][03835] Avg episode reward: [(0, '6.410'), (1, '7.780')] -[2023-10-16 05:28:34,304][05218] Updated weights for policy 0, policy_version 68292 (0.0008) -[2023-10-16 05:28:34,675][05218] Updated weights for policy 0, policy_version 68302 (0.0007) -[2023-10-16 05:28:35,035][05219] Updated weights for policy 1, policy_version 68070 (0.0010) -[2023-10-16 05:28:35,055][05218] Updated weights for policy 0, policy_version 68312 (0.0008) -[2023-10-16 05:28:35,415][05219] Updated weights for policy 1, policy_version 68080 (0.0009) -[2023-10-16 05:28:35,789][05219] Updated weights for policy 1, policy_version 68090 (0.0010) -[2023-10-16 05:28:37,351][03835] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 139689984. Throughput: 0: 1781.9, 1: 1801.4. Samples: 34933102. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-16 05:28:37,352][03835] Avg episode reward: [(0, '6.800'), (1, '6.580')] -[2023-10-16 05:28:38,765][05218] Updated weights for policy 0, policy_version 68322 (0.0009) -[2023-10-16 05:28:39,133][05218] Updated weights for policy 0, policy_version 68332 (0.0010) -[2023-10-16 05:28:39,510][05218] Updated weights for policy 0, policy_version 68342 (0.0008) -[2023-10-16 05:28:39,540][05219] Updated weights for policy 1, policy_version 68100 (0.0007) -[2023-10-16 05:28:39,883][05218] Updated weights for policy 0, policy_version 68352 (0.0011) -[2023-10-16 05:28:39,906][05219] Updated weights for policy 1, policy_version 68110 (0.0007) -[2023-10-16 05:28:40,276][05219] Updated weights for policy 1, policy_version 68120 (0.0007) -[2023-10-16 05:28:42,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 139755520. Throughput: 0: 1776.3, 1: 1809.9. Samples: 34943498. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-16 05:28:42,351][03835] Avg episode reward: [(0, '6.660'), (1, '7.040')] -[2023-10-16 05:28:43,657][05218] Updated weights for policy 0, policy_version 68362 (0.0011) -[2023-10-16 05:28:44,036][05218] Updated weights for policy 0, policy_version 68372 (0.0010) -[2023-10-16 05:28:44,066][05219] Updated weights for policy 1, policy_version 68130 (0.0008) -[2023-10-16 05:28:44,398][05218] Updated weights for policy 0, policy_version 68382 (0.0008) -[2023-10-16 05:28:44,431][05219] Updated weights for policy 1, policy_version 68140 (0.0008) -[2023-10-16 05:28:44,783][05219] Updated weights for policy 1, policy_version 68150 (0.0008) -[2023-10-16 05:28:45,151][05219] Updated weights for policy 1, policy_version 68160 (0.0009) -[2023-10-16 05:28:47,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 139821056. Throughput: 0: 1780.8, 1: 1792.9. Samples: 34965450. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-16 05:28:47,351][03835] Avg episode reward: [(0, '7.350'), (1, '8.050')] -[2023-10-16 05:28:48,203][05218] Updated weights for policy 0, policy_version 68392 (0.0009) -[2023-10-16 05:28:48,566][05218] Updated weights for policy 0, policy_version 68402 (0.0010) -[2023-10-16 05:28:48,914][05219] Updated weights for policy 1, policy_version 68170 (0.0008) -[2023-10-16 05:28:48,942][05218] Updated weights for policy 0, policy_version 68412 (0.0010) -[2023-10-16 05:28:49,281][05219] Updated weights for policy 1, policy_version 68180 (0.0010) -[2023-10-16 05:28:49,645][05219] Updated weights for policy 1, policy_version 68190 (0.0008) -[2023-10-16 05:28:52,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 139886592. Throughput: 0: 1795.7, 1: 1785.4. Samples: 34987648. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-16 05:28:52,351][03835] Avg episode reward: [(0, '7.050'), (1, '7.720')] -[2023-10-16 05:28:52,747][05218] Updated weights for policy 0, policy_version 68422 (0.0009) -[2023-10-16 05:28:53,123][05218] Updated weights for policy 0, policy_version 68432 (0.0007) -[2023-10-16 05:28:53,440][05219] Updated weights for policy 1, policy_version 68200 (0.0007) -[2023-10-16 05:28:53,507][05218] Updated weights for policy 0, policy_version 68442 (0.0008) -[2023-10-16 05:28:53,800][05219] Updated weights for policy 1, policy_version 68210 (0.0007) -[2023-10-16 05:28:54,170][05219] Updated weights for policy 1, policy_version 68220 (0.0007) -[2023-10-16 05:28:57,264][05218] Updated weights for policy 0, policy_version 68452 (0.0009) -[2023-10-16 05:28:57,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 139952128. Throughput: 0: 1774.6, 1: 1783.4. Samples: 34997462. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:28:57,351][03835] Avg episode reward: [(0, '6.640'), (1, '6.790')] -[2023-10-16 05:28:57,644][05218] Updated weights for policy 0, policy_version 68462 (0.0007) -[2023-10-16 05:28:58,000][05219] Updated weights for policy 1, policy_version 68230 (0.0008) -[2023-10-16 05:28:58,011][05218] Updated weights for policy 0, policy_version 68472 (0.0008) -[2023-10-16 05:28:58,368][05219] Updated weights for policy 1, policy_version 68240 (0.0007) -[2023-10-16 05:28:58,732][05219] Updated weights for policy 1, policy_version 68250 (0.0007) -[2023-10-16 05:29:01,665][05218] Updated weights for policy 0, policy_version 68482 (0.0008) -[2023-10-16 05:29:02,039][05218] Updated weights for policy 0, policy_version 68492 (0.0007) -[2023-10-16 05:29:02,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 140017664. Throughput: 0: 1797.6, 1: 1783.7. Samples: 35019908. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:29:02,351][03835] Avg episode reward: [(0, '6.620'), (1, '7.180')] -[2023-10-16 05:29:02,411][05218] Updated weights for policy 0, policy_version 68502 (0.0007) -[2023-10-16 05:29:02,427][05219] Updated weights for policy 1, policy_version 68260 (0.0008) -[2023-10-16 05:29:02,780][05218] Updated weights for policy 0, policy_version 68512 (0.0007) -[2023-10-16 05:29:02,791][05219] Updated weights for policy 1, policy_version 68270 (0.0008) -[2023-10-16 05:29:03,149][05219] Updated weights for policy 1, policy_version 68280 (0.0007) -[2023-10-16 05:29:06,719][05218] Updated weights for policy 0, policy_version 68522 (0.0008) -[2023-10-16 05:29:06,905][05219] Updated weights for policy 1, policy_version 68290 (0.0008) -[2023-10-16 05:29:07,094][05218] Updated weights for policy 0, policy_version 68532 (0.0009) -[2023-10-16 05:29:07,278][05219] Updated weights for policy 1, policy_version 68300 (0.0007) -[2023-10-16 05:29:07,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 140083200. Throughput: 0: 1789.1, 1: 1808.0. Samples: 35040718. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:29:07,351][03835] Avg episode reward: [(0, '6.840'), (1, '7.330')] -[2023-10-16 05:29:07,471][05218] Updated weights for policy 0, policy_version 68542 (0.0009) -[2023-10-16 05:29:07,646][05219] Updated weights for policy 1, policy_version 68310 (0.0009) -[2023-10-16 05:29:08,018][05219] Updated weights for policy 1, policy_version 68320 (0.0008) -[2023-10-16 05:29:11,162][05218] Updated weights for policy 0, policy_version 68552 (0.0009) -[2023-10-16 05:29:11,535][05218] Updated weights for policy 0, policy_version 68562 (0.0010) -[2023-10-16 05:29:11,681][05219] Updated weights for policy 1, policy_version 68330 (0.0009) -[2023-10-16 05:29:11,910][05218] Updated weights for policy 0, policy_version 68572 (0.0009) -[2023-10-16 05:29:12,049][05219] Updated weights for policy 1, policy_version 68340 (0.0008) -[2023-10-16 05:29:12,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 140181504. Throughput: 0: 1795.3, 1: 1783.3. Samples: 35052084. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:29:12,351][03835] Avg episode reward: [(0, '6.550'), (1, '6.750')] -[2023-10-16 05:29:12,411][05219] Updated weights for policy 1, policy_version 68350 (0.0008) -[2023-10-16 05:29:15,677][05218] Updated weights for policy 0, policy_version 68582 (0.0007) -[2023-10-16 05:29:16,057][05218] Updated weights for policy 0, policy_version 68592 (0.0008) -[2023-10-16 05:29:16,206][05219] Updated weights for policy 1, policy_version 68360 (0.0007) -[2023-10-16 05:29:16,419][05218] Updated weights for policy 0, policy_version 68602 (0.0007) -[2023-10-16 05:29:16,571][05219] Updated weights for policy 1, policy_version 68370 (0.0007) -[2023-10-16 05:29:16,944][05219] Updated weights for policy 1, policy_version 68380 (0.0010) -[2023-10-16 05:29:17,350][03835] Fps is (10 sec: 19661.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 140279808. Throughput: 0: 1790.3, 1: 1797.2. Samples: 35072920. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:29:17,351][03835] Avg episode reward: [(0, '7.170'), (1, '7.190')] -[2023-10-16 05:29:20,045][05218] Updated weights for policy 0, policy_version 68612 (0.0008) -[2023-10-16 05:29:20,420][05218] Updated weights for policy 0, policy_version 68622 (0.0007) -[2023-10-16 05:29:20,793][05218] Updated weights for policy 0, policy_version 68632 (0.0009) -[2023-10-16 05:29:20,901][05219] Updated weights for policy 1, policy_version 68390 (0.0009) -[2023-10-16 05:29:21,289][05219] Updated weights for policy 1, policy_version 68400 (0.0008) -[2023-10-16 05:29:21,648][05219] Updated weights for policy 1, policy_version 68410 (0.0007) -[2023-10-16 05:29:22,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 140345344. Throughput: 0: 1792.3, 1: 1780.6. Samples: 35093880. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:29:22,351][03835] Avg episode reward: [(0, '6.650'), (1, '7.880')] -[2023-10-16 05:29:24,332][05218] Updated weights for policy 0, policy_version 68642 (0.0009) -[2023-10-16 05:29:24,709][05218] Updated weights for policy 0, policy_version 68652 (0.0008) -[2023-10-16 05:29:25,100][05218] Updated weights for policy 0, policy_version 68662 (0.0009) -[2023-10-16 05:29:25,442][05219] Updated weights for policy 1, policy_version 68420 (0.0009) -[2023-10-16 05:29:25,466][05218] Updated weights for policy 0, policy_version 68672 (0.0008) -[2023-10-16 05:29:25,809][05219] Updated weights for policy 1, policy_version 68430 (0.0008) -[2023-10-16 05:29:26,170][05219] Updated weights for policy 1, policy_version 68440 (0.0008) -[2023-10-16 05:29:27,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 140410880. Throughput: 0: 1799.7, 1: 1797.8. Samples: 35105384. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:29:27,351][03835] Avg episode reward: [(0, '6.250'), (1, '7.390')] -[2023-10-16 05:29:29,288][05218] Updated weights for policy 0, policy_version 68682 (0.0008) -[2023-10-16 05:29:29,663][05218] Updated weights for policy 0, policy_version 68692 (0.0008) -[2023-10-16 05:29:30,042][05218] Updated weights for policy 0, policy_version 68702 (0.0007) -[2023-10-16 05:29:30,056][05219] Updated weights for policy 1, policy_version 68450 (0.0008) -[2023-10-16 05:29:30,426][05219] Updated weights for policy 1, policy_version 68460 (0.0007) -[2023-10-16 05:29:30,789][05219] Updated weights for policy 1, policy_version 68470 (0.0008) -[2023-10-16 05:29:31,143][05219] Updated weights for policy 1, policy_version 68480 (0.0007) -[2023-10-16 05:29:32,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 140476416. Throughput: 0: 1787.7, 1: 1784.0. Samples: 35126178. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:29:32,351][03835] Avg episode reward: [(0, '6.670'), (1, '6.620')] -[2023-10-16 05:29:33,845][05218] Updated weights for policy 0, policy_version 68712 (0.0010) -[2023-10-16 05:29:34,212][05218] Updated weights for policy 0, policy_version 68722 (0.0008) -[2023-10-16 05:29:34,590][05218] Updated weights for policy 0, policy_version 68732 (0.0007) -[2023-10-16 05:29:34,943][05219] Updated weights for policy 1, policy_version 68490 (0.0011) -[2023-10-16 05:29:35,301][05219] Updated weights for policy 1, policy_version 68500 (0.0007) -[2023-10-16 05:29:35,663][05219] Updated weights for policy 1, policy_version 68510 (0.0008) -[2023-10-16 05:29:37,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.6, 300 sec: 14329.1). Total num frames: 140541952. Throughput: 0: 1791.7, 1: 1781.0. Samples: 35148418. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:29:37,351][03835] Avg episode reward: [(0, '6.370'), (1, '7.190')] -[2023-10-16 05:29:37,358][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000068512_70156288.pth... -[2023-10-16 05:29:37,358][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000068736_70385664.pth... -[2023-10-16 05:29:37,397][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000066848_68452352.pth -[2023-10-16 05:29:37,401][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000067072_68681728.pth -[2023-10-16 05:29:38,388][05218] Updated weights for policy 0, policy_version 68742 (0.0009) -[2023-10-16 05:29:38,757][05218] Updated weights for policy 0, policy_version 68752 (0.0009) -[2023-10-16 05:29:39,132][05218] Updated weights for policy 0, policy_version 68762 (0.0009) -[2023-10-16 05:29:39,437][05219] Updated weights for policy 1, policy_version 68520 (0.0008) -[2023-10-16 05:29:39,798][05219] Updated weights for policy 1, policy_version 68530 (0.0010) -[2023-10-16 05:29:40,163][05219] Updated weights for policy 1, policy_version 68540 (0.0010) -[2023-10-16 05:29:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 140607488. Throughput: 0: 1789.9, 1: 1788.2. Samples: 35158476. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-16 05:29:42,351][03835] Avg episode reward: [(0, '6.250'), (1, '7.500')] -[2023-10-16 05:29:42,891][05218] Updated weights for policy 0, policy_version 68772 (0.0009) -[2023-10-16 05:29:43,262][05218] Updated weights for policy 0, policy_version 68782 (0.0010) -[2023-10-16 05:29:43,632][05218] Updated weights for policy 0, policy_version 68792 (0.0008) -[2023-10-16 05:29:43,908][05219] Updated weights for policy 1, policy_version 68550 (0.0010) -[2023-10-16 05:29:44,268][05219] Updated weights for policy 1, policy_version 68560 (0.0010) -[2023-10-16 05:29:44,631][05219] Updated weights for policy 1, policy_version 68570 (0.0009) -[2023-10-16 05:29:47,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 140673024. Throughput: 0: 1788.7, 1: 1778.7. Samples: 35180446. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-16 05:29:47,351][03835] Avg episode reward: [(0, '7.040'), (1, '6.670')] -[2023-10-16 05:29:47,401][05218] Updated weights for policy 0, policy_version 68802 (0.0008) -[2023-10-16 05:29:47,783][05218] Updated weights for policy 0, policy_version 68812 (0.0007) -[2023-10-16 05:29:48,165][05218] Updated weights for policy 0, policy_version 68822 (0.0007) -[2023-10-16 05:29:48,339][05219] Updated weights for policy 1, policy_version 68580 (0.0008) -[2023-10-16 05:29:48,544][05218] Updated weights for policy 0, policy_version 68832 (0.0009) -[2023-10-16 05:29:48,707][05219] Updated weights for policy 1, policy_version 68590 (0.0007) -[2023-10-16 05:29:49,062][05219] Updated weights for policy 1, policy_version 68600 (0.0010) -[2023-10-16 05:29:52,300][05218] Updated weights for policy 0, policy_version 68842 (0.0008) -[2023-10-16 05:29:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 140738560. Throughput: 0: 1807.3, 1: 1786.0. Samples: 35202418. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-16 05:29:52,351][03835] Avg episode reward: [(0, '7.270'), (1, '7.890')] -[2023-10-16 05:29:52,680][05218] Updated weights for policy 0, policy_version 68852 (0.0009) -[2023-10-16 05:29:52,707][05219] Updated weights for policy 1, policy_version 68610 (0.0009) -[2023-10-16 05:29:53,058][05218] Updated weights for policy 0, policy_version 68862 (0.0007) -[2023-10-16 05:29:53,073][05219] Updated weights for policy 1, policy_version 68620 (0.0008) -[2023-10-16 05:29:53,436][05219] Updated weights for policy 1, policy_version 68630 (0.0008) -[2023-10-16 05:29:53,798][05219] Updated weights for policy 1, policy_version 68640 (0.0008) -[2023-10-16 05:29:56,713][05218] Updated weights for policy 0, policy_version 68872 (0.0007) -[2023-10-16 05:29:57,099][05218] Updated weights for policy 0, policy_version 68882 (0.0008) -[2023-10-16 05:29:57,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 140804096. Throughput: 0: 1792.3, 1: 1777.9. Samples: 35212742. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-16 05:29:57,351][03835] Avg episode reward: [(0, '6.770'), (1, '8.200')] -[2023-10-16 05:29:57,464][05218] Updated weights for policy 0, policy_version 68892 (0.0010) -[2023-10-16 05:29:57,656][05219] Updated weights for policy 1, policy_version 68650 (0.0008) -[2023-10-16 05:29:58,019][05219] Updated weights for policy 1, policy_version 68660 (0.0007) -[2023-10-16 05:29:58,380][05219] Updated weights for policy 1, policy_version 68670 (0.0007) -[2023-10-16 05:30:01,110][05218] Updated weights for policy 0, policy_version 68902 (0.0008) -[2023-10-16 05:30:01,483][05218] Updated weights for policy 0, policy_version 68912 (0.0007) -[2023-10-16 05:30:01,864][05218] Updated weights for policy 0, policy_version 68922 (0.0008) -[2023-10-16 05:30:02,152][05219] Updated weights for policy 1, policy_version 68680 (0.0009) -[2023-10-16 05:30:02,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 140902400. Throughput: 0: 1805.9, 1: 1790.0. Samples: 35234734. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-16 05:30:02,351][03835] Avg episode reward: [(0, '6.480'), (1, '6.420')] -[2023-10-16 05:30:02,516][05219] Updated weights for policy 1, policy_version 68690 (0.0007) -[2023-10-16 05:30:02,888][05219] Updated weights for policy 1, policy_version 68700 (0.0007) -[2023-10-16 05:30:05,718][05218] Updated weights for policy 0, policy_version 68932 (0.0008) -[2023-10-16 05:30:06,090][05218] Updated weights for policy 0, policy_version 68942 (0.0008) -[2023-10-16 05:30:06,466][05218] Updated weights for policy 0, policy_version 68952 (0.0007) -[2023-10-16 05:30:06,845][05219] Updated weights for policy 1, policy_version 68710 (0.0008) -[2023-10-16 05:30:07,223][05219] Updated weights for policy 1, policy_version 68720 (0.0007) -[2023-10-16 05:30:07,350][03835] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 140967936. Throughput: 0: 1784.1, 1: 1799.8. Samples: 35255154. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-16 05:30:07,352][03835] Avg episode reward: [(0, '6.460'), (1, '6.390')] -[2023-10-16 05:30:07,586][05219] Updated weights for policy 1, policy_version 68730 (0.0008) -[2023-10-16 05:30:10,161][05218] Updated weights for policy 0, policy_version 68962 (0.0007) -[2023-10-16 05:30:10,538][05218] Updated weights for policy 0, policy_version 68972 (0.0007) -[2023-10-16 05:30:10,903][05218] Updated weights for policy 0, policy_version 68982 (0.0009) -[2023-10-16 05:30:11,192][05219] Updated weights for policy 1, policy_version 68740 (0.0009) -[2023-10-16 05:30:11,278][05218] Updated weights for policy 0, policy_version 68992 (0.0009) -[2023-10-16 05:30:11,559][05219] Updated weights for policy 1, policy_version 68750 (0.0007) -[2023-10-16 05:30:11,921][05219] Updated weights for policy 1, policy_version 68760 (0.0007) -[2023-10-16 05:30:12,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 141066240. Throughput: 0: 1805.8, 1: 1780.5. Samples: 35266766. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-16 05:30:12,351][03835] Avg episode reward: [(0, '6.450'), (1, '6.930')] -[2023-10-16 05:30:14,871][05218] Updated weights for policy 0, policy_version 69002 (0.0008) -[2023-10-16 05:30:15,251][05218] Updated weights for policy 0, policy_version 69012 (0.0008) -[2023-10-16 05:30:15,636][05218] Updated weights for policy 0, policy_version 69022 (0.0009) -[2023-10-16 05:30:15,939][05219] Updated weights for policy 1, policy_version 68770 (0.0007) -[2023-10-16 05:30:16,307][05219] Updated weights for policy 1, policy_version 68780 (0.0009) -[2023-10-16 05:30:16,664][05219] Updated weights for policy 1, policy_version 68790 (0.0009) -[2023-10-16 05:30:17,030][05219] Updated weights for policy 1, policy_version 68800 (0.0010) -[2023-10-16 05:30:17,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 141131776. Throughput: 0: 1789.5, 1: 1797.6. Samples: 35287598. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-16 05:30:17,351][03835] Avg episode reward: [(0, '6.600'), (1, '7.020')] -[2023-10-16 05:30:19,408][05218] Updated weights for policy 0, policy_version 69032 (0.0009) -[2023-10-16 05:30:19,789][05218] Updated weights for policy 0, policy_version 69042 (0.0009) -[2023-10-16 05:30:20,172][05218] Updated weights for policy 0, policy_version 69052 (0.0010) -[2023-10-16 05:30:20,750][05219] Updated weights for policy 1, policy_version 68810 (0.0008) -[2023-10-16 05:30:21,108][05219] Updated weights for policy 1, policy_version 68820 (0.0009) -[2023-10-16 05:30:21,476][05219] Updated weights for policy 1, policy_version 68830 (0.0008) -[2023-10-16 05:30:22,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 141197312. Throughput: 0: 1788.9, 1: 1775.4. Samples: 35308810. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-16 05:30:22,352][03835] Avg episode reward: [(0, '6.840'), (1, '6.900')] -[2023-10-16 05:30:23,889][05218] Updated weights for policy 0, policy_version 69062 (0.0008) -[2023-10-16 05:30:24,266][05218] Updated weights for policy 0, policy_version 69072 (0.0010) -[2023-10-16 05:30:24,650][05218] Updated weights for policy 0, policy_version 69082 (0.0009) -[2023-10-16 05:30:25,368][05219] Updated weights for policy 1, policy_version 68840 (0.0008) -[2023-10-16 05:30:25,732][05219] Updated weights for policy 1, policy_version 68850 (0.0010) -[2023-10-16 05:30:26,100][05219] Updated weights for policy 1, policy_version 68860 (0.0008) -[2023-10-16 05:30:27,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 141262848. Throughput: 0: 1788.4, 1: 1795.4. Samples: 35319748. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-10-16 05:30:27,351][03835] Avg episode reward: [(0, '6.960'), (1, '6.830')] -[2023-10-16 05:30:28,442][05218] Updated weights for policy 0, policy_version 69092 (0.0008) -[2023-10-16 05:30:28,810][05218] Updated weights for policy 0, policy_version 69102 (0.0009) -[2023-10-16 05:30:29,178][05218] Updated weights for policy 0, policy_version 69112 (0.0011) -[2023-10-16 05:30:29,785][05219] Updated weights for policy 1, policy_version 68870 (0.0009) -[2023-10-16 05:30:30,150][05219] Updated weights for policy 1, policy_version 68880 (0.0008) -[2023-10-16 05:30:30,527][05219] Updated weights for policy 1, policy_version 68890 (0.0009) -[2023-10-16 05:30:32,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 141328384. Throughput: 0: 1788.6, 1: 1774.1. Samples: 35340770. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-10-16 05:30:32,351][03835] Avg episode reward: [(0, '6.700'), (1, '7.440')] -[2023-10-16 05:30:33,011][05218] Updated weights for policy 0, policy_version 69122 (0.0009) -[2023-10-16 05:30:33,374][05218] Updated weights for policy 0, policy_version 69132 (0.0011) -[2023-10-16 05:30:33,751][05218] Updated weights for policy 0, policy_version 69142 (0.0010) -[2023-10-16 05:30:34,115][05218] Updated weights for policy 0, policy_version 69152 (0.0010) -[2023-10-16 05:30:34,386][05219] Updated weights for policy 1, policy_version 68900 (0.0009) -[2023-10-16 05:30:34,752][05219] Updated weights for policy 1, policy_version 68910 (0.0007) -[2023-10-16 05:30:35,120][05219] Updated weights for policy 1, policy_version 68920 (0.0008) -[2023-10-16 05:30:37,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 141393920. Throughput: 0: 1799.2, 1: 1770.8. Samples: 35363064. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-10-16 05:30:37,351][03835] Avg episode reward: [(0, '7.020'), (1, '7.250')] -[2023-10-16 05:30:37,922][05218] Updated weights for policy 0, policy_version 69162 (0.0010) -[2023-10-16 05:30:38,304][05218] Updated weights for policy 0, policy_version 69172 (0.0007) -[2023-10-16 05:30:38,671][05218] Updated weights for policy 0, policy_version 69182 (0.0009) -[2023-10-16 05:30:38,831][05219] Updated weights for policy 1, policy_version 68930 (0.0009) -[2023-10-16 05:30:39,199][05219] Updated weights for policy 1, policy_version 68940 (0.0009) -[2023-10-16 05:30:39,566][05219] Updated weights for policy 1, policy_version 68950 (0.0007) -[2023-10-16 05:30:39,931][05219] Updated weights for policy 1, policy_version 68960 (0.0007) -[2023-10-16 05:30:42,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 141459456. Throughput: 0: 1791.3, 1: 1770.3. Samples: 35373014. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-10-16 05:30:42,351][03835] Avg episode reward: [(0, '6.710'), (1, '8.010')] -[2023-10-16 05:30:42,376][05218] Updated weights for policy 0, policy_version 69192 (0.0009) -[2023-10-16 05:30:42,757][05218] Updated weights for policy 0, policy_version 69202 (0.0009) -[2023-10-16 05:30:43,139][05218] Updated weights for policy 0, policy_version 69212 (0.0008) -[2023-10-16 05:30:43,725][05219] Updated weights for policy 1, policy_version 68970 (0.0008) -[2023-10-16 05:30:44,086][05219] Updated weights for policy 1, policy_version 68980 (0.0007) -[2023-10-16 05:30:44,448][05219] Updated weights for policy 1, policy_version 68990 (0.0007) -[2023-10-16 05:30:46,762][05218] Updated weights for policy 0, policy_version 69222 (0.0009) -[2023-10-16 05:30:47,136][05218] Updated weights for policy 0, policy_version 69232 (0.0009) -[2023-10-16 05:30:47,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 141524992. Throughput: 0: 1802.6, 1: 1774.0. Samples: 35395678. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-10-16 05:30:47,351][03835] Avg episode reward: [(0, '6.810'), (1, '7.740')] -[2023-10-16 05:30:47,520][05218] Updated weights for policy 0, policy_version 69242 (0.0009) -[2023-10-16 05:30:48,141][05219] Updated weights for policy 1, policy_version 69000 (0.0008) -[2023-10-16 05:30:48,513][05219] Updated weights for policy 1, policy_version 69010 (0.0009) -[2023-10-16 05:30:48,877][05219] Updated weights for policy 1, policy_version 69020 (0.0010) -[2023-10-16 05:30:51,257][05218] Updated weights for policy 0, policy_version 69252 (0.0009) -[2023-10-16 05:30:51,628][05218] Updated weights for policy 0, policy_version 69262 (0.0008) -[2023-10-16 05:30:52,002][05218] Updated weights for policy 0, policy_version 69272 (0.0008) -[2023-10-16 05:30:52,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 141623296. Throughput: 0: 1796.0, 1: 1796.6. Samples: 35416820. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-10-16 05:30:52,351][03835] Avg episode reward: [(0, '7.340'), (1, '6.790')] -[2023-10-16 05:30:52,672][05219] Updated weights for policy 1, policy_version 69030 (0.0007) -[2023-10-16 05:30:53,063][05219] Updated weights for policy 1, policy_version 69040 (0.0008) -[2023-10-16 05:30:53,427][05219] Updated weights for policy 1, policy_version 69050 (0.0009) -[2023-10-16 05:30:55,768][05218] Updated weights for policy 0, policy_version 69282 (0.0010) -[2023-10-16 05:30:56,154][05218] Updated weights for policy 0, policy_version 69292 (0.0011) -[2023-10-16 05:30:56,519][05218] Updated weights for policy 0, policy_version 69302 (0.0008) -[2023-10-16 05:30:56,899][05218] Updated weights for policy 0, policy_version 69312 (0.0008) -[2023-10-16 05:30:57,184][05219] Updated weights for policy 1, policy_version 69060 (0.0009) -[2023-10-16 05:30:57,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 141688832. Throughput: 0: 1805.5, 1: 1778.8. Samples: 35428060. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-10-16 05:30:57,351][03835] Avg episode reward: [(0, '6.220'), (1, '7.200')] -[2023-10-16 05:30:57,554][05219] Updated weights for policy 1, policy_version 69070 (0.0008) -[2023-10-16 05:30:57,932][05219] Updated weights for policy 1, policy_version 69080 (0.0009) -[2023-10-16 05:31:00,504][05218] Updated weights for policy 0, policy_version 69322 (0.0009) -[2023-10-16 05:31:00,885][05218] Updated weights for policy 0, policy_version 69332 (0.0008) -[2023-10-16 05:31:01,256][05218] Updated weights for policy 0, policy_version 69342 (0.0008) -[2023-10-16 05:31:01,640][05219] Updated weights for policy 1, policy_version 69090 (0.0009) -[2023-10-16 05:31:02,007][05219] Updated weights for policy 1, policy_version 69100 (0.0010) -[2023-10-16 05:31:02,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 141754368. Throughput: 0: 1802.5, 1: 1789.5. Samples: 35449234. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-10-16 05:31:02,351][03835] Avg episode reward: [(0, '6.260'), (1, '7.300')] -[2023-10-16 05:31:02,365][05219] Updated weights for policy 1, policy_version 69110 (0.0011) -[2023-10-16 05:31:02,726][05219] Updated weights for policy 1, policy_version 69120 (0.0009) -[2023-10-16 05:31:04,830][05218] Updated weights for policy 0, policy_version 69352 (0.0008) -[2023-10-16 05:31:05,207][05218] Updated weights for policy 0, policy_version 69362 (0.0009) -[2023-10-16 05:31:05,580][05218] Updated weights for policy 0, policy_version 69372 (0.0008) -[2023-10-16 05:31:06,444][05219] Updated weights for policy 1, policy_version 69130 (0.0008) -[2023-10-16 05:31:06,817][05219] Updated weights for policy 1, policy_version 69140 (0.0008) -[2023-10-16 05:31:07,182][05219] Updated weights for policy 1, policy_version 69150 (0.0009) -[2023-10-16 05:31:07,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 141852672. Throughput: 0: 1804.0, 1: 1790.1. Samples: 35470542. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-10-16 05:31:07,351][03835] Avg episode reward: [(0, '6.980'), (1, '7.200')] -[2023-10-16 05:31:09,417][05218] Updated weights for policy 0, policy_version 69382 (0.0010) -[2023-10-16 05:31:09,794][05218] Updated weights for policy 0, policy_version 69392 (0.0010) -[2023-10-16 05:31:10,174][05218] Updated weights for policy 0, policy_version 69402 (0.0008) -[2023-10-16 05:31:10,963][05219] Updated weights for policy 1, policy_version 69160 (0.0009) -[2023-10-16 05:31:11,333][05219] Updated weights for policy 1, policy_version 69170 (0.0008) -[2023-10-16 05:31:11,710][05219] Updated weights for policy 1, policy_version 69180 (0.0009) -[2023-10-16 05:31:12,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 141918208. Throughput: 0: 1803.2, 1: 1792.9. Samples: 35481574. Policy #0 lag: (min: 9.0, avg: 16.4, max: 41.0) -[2023-10-16 05:31:12,351][03835] Avg episode reward: [(0, '5.830'), (1, '7.530')] -[2023-10-16 05:31:14,037][05218] Updated weights for policy 0, policy_version 69412 (0.0008) -[2023-10-16 05:31:14,417][05218] Updated weights for policy 0, policy_version 69422 (0.0009) -[2023-10-16 05:31:14,792][05218] Updated weights for policy 0, policy_version 69432 (0.0007) -[2023-10-16 05:31:15,526][05219] Updated weights for policy 1, policy_version 69190 (0.0008) -[2023-10-16 05:31:15,885][05219] Updated weights for policy 1, policy_version 69200 (0.0007) -[2023-10-16 05:31:16,250][05219] Updated weights for policy 1, policy_version 69210 (0.0008) -[2023-10-16 05:31:17,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 141983744. Throughput: 0: 1801.3, 1: 1799.6. Samples: 35502814. Policy #0 lag: (min: 9.0, avg: 16.4, max: 41.0) -[2023-10-16 05:31:17,351][03835] Avg episode reward: [(0, '6.650'), (1, '7.840')] -[2023-10-16 05:31:18,430][05218] Updated weights for policy 0, policy_version 69442 (0.0007) -[2023-10-16 05:31:18,816][05218] Updated weights for policy 0, policy_version 69452 (0.0008) -[2023-10-16 05:31:19,190][05218] Updated weights for policy 0, policy_version 69462 (0.0008) -[2023-10-16 05:31:19,573][05218] Updated weights for policy 0, policy_version 69472 (0.0007) -[2023-10-16 05:31:19,898][05219] Updated weights for policy 1, policy_version 69220 (0.0009) -[2023-10-16 05:31:20,276][05219] Updated weights for policy 1, policy_version 69230 (0.0008) -[2023-10-16 05:31:20,629][05219] Updated weights for policy 1, policy_version 69240 (0.0010) -[2023-10-16 05:31:22,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 142049280. Throughput: 0: 1807.2, 1: 1794.8. Samples: 35525152. Policy #0 lag: (min: 9.0, avg: 16.4, max: 41.0) -[2023-10-16 05:31:22,351][03835] Avg episode reward: [(0, '6.710'), (1, '7.670')] -[2023-10-16 05:31:23,252][05218] Updated weights for policy 0, policy_version 69482 (0.0009) -[2023-10-16 05:31:23,615][05218] Updated weights for policy 0, policy_version 69492 (0.0008) -[2023-10-16 05:31:23,996][05218] Updated weights for policy 0, policy_version 69502 (0.0009) -[2023-10-16 05:31:24,388][05219] Updated weights for policy 1, policy_version 69250 (0.0011) -[2023-10-16 05:31:24,761][05219] Updated weights for policy 1, policy_version 69260 (0.0009) -[2023-10-16 05:31:25,130][05219] Updated weights for policy 1, policy_version 69270 (0.0009) -[2023-10-16 05:31:25,498][05219] Updated weights for policy 1, policy_version 69280 (0.0008) -[2023-10-16 05:31:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 142114816. Throughput: 0: 1805.9, 1: 1807.4. Samples: 35535612. Policy #0 lag: (min: 9.0, avg: 16.4, max: 41.0) -[2023-10-16 05:31:27,351][03835] Avg episode reward: [(0, '6.520'), (1, '7.650')] -[2023-10-16 05:31:27,714][05218] Updated weights for policy 0, policy_version 69512 (0.0010) -[2023-10-16 05:31:28,096][05218] Updated weights for policy 0, policy_version 69522 (0.0008) -[2023-10-16 05:31:28,484][05218] Updated weights for policy 0, policy_version 69532 (0.0007) -[2023-10-16 05:31:29,150][05219] Updated weights for policy 1, policy_version 69290 (0.0010) -[2023-10-16 05:31:29,517][05219] Updated weights for policy 1, policy_version 69300 (0.0010) -[2023-10-16 05:31:29,875][05219] Updated weights for policy 1, policy_version 69310 (0.0009) -[2023-10-16 05:31:32,114][05218] Updated weights for policy 0, policy_version 69542 (0.0007) -[2023-10-16 05:31:32,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 142180352. Throughput: 0: 1805.3, 1: 1792.3. Samples: 35557572. Policy #0 lag: (min: 9.0, avg: 16.4, max: 41.0) -[2023-10-16 05:31:32,351][03835] Avg episode reward: [(0, '6.610'), (1, '7.480')] -[2023-10-16 05:31:32,495][05218] Updated weights for policy 0, policy_version 69552 (0.0010) -[2023-10-16 05:31:32,864][05218] Updated weights for policy 0, policy_version 69562 (0.0009) -[2023-10-16 05:31:33,652][05219] Updated weights for policy 1, policy_version 69320 (0.0008) -[2023-10-16 05:31:34,017][05219] Updated weights for policy 1, policy_version 69330 (0.0007) -[2023-10-16 05:31:34,386][05219] Updated weights for policy 1, policy_version 69340 (0.0007) -[2023-10-16 05:31:36,610][05218] Updated weights for policy 0, policy_version 69572 (0.0008) -[2023-10-16 05:31:36,987][05218] Updated weights for policy 0, policy_version 69582 (0.0010) -[2023-10-16 05:31:37,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 142245888. Throughput: 0: 1812.4, 1: 1790.0. Samples: 35578930. Policy #0 lag: (min: 9.0, avg: 16.4, max: 41.0) -[2023-10-16 05:31:37,351][03835] Avg episode reward: [(0, '6.750'), (1, '8.050')] -[2023-10-16 05:31:37,361][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000069344_71008256.pth... -[2023-10-16 05:31:37,368][05218] Updated weights for policy 0, policy_version 69592 (0.0010) -[2023-10-16 05:31:37,401][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000067680_69304320.pth -[2023-10-16 05:31:37,674][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000069600_71270400.pth... -[2023-10-16 05:31:37,711][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000067904_69533696.pth -[2023-10-16 05:31:38,300][05219] Updated weights for policy 1, policy_version 69350 (0.0009) -[2023-10-16 05:31:38,670][05219] Updated weights for policy 1, policy_version 69360 (0.0009) -[2023-10-16 05:31:39,034][05219] Updated weights for policy 1, policy_version 69370 (0.0009) -[2023-10-16 05:31:41,043][05218] Updated weights for policy 0, policy_version 69602 (0.0009) -[2023-10-16 05:31:41,419][05218] Updated weights for policy 0, policy_version 69612 (0.0009) -[2023-10-16 05:31:41,788][05218] Updated weights for policy 0, policy_version 69622 (0.0010) -[2023-10-16 05:31:42,162][05218] Updated weights for policy 0, policy_version 69632 (0.0008) -[2023-10-16 05:31:42,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 142344192. Throughput: 0: 1801.0, 1: 1789.6. Samples: 35589638. Policy #0 lag: (min: 9.0, avg: 16.4, max: 41.0) -[2023-10-16 05:31:42,351][03835] Avg episode reward: [(0, '6.610'), (1, '6.960')] -[2023-10-16 05:31:42,817][05219] Updated weights for policy 1, policy_version 69380 (0.0009) -[2023-10-16 05:31:43,191][05219] Updated weights for policy 1, policy_version 69390 (0.0008) -[2023-10-16 05:31:43,559][05219] Updated weights for policy 1, policy_version 69400 (0.0007) -[2023-10-16 05:31:45,939][05218] Updated weights for policy 0, policy_version 69642 (0.0009) -[2023-10-16 05:31:46,321][05218] Updated weights for policy 0, policy_version 69652 (0.0011) -[2023-10-16 05:31:46,696][05218] Updated weights for policy 0, policy_version 69662 (0.0011) -[2023-10-16 05:31:47,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 142409728. Throughput: 0: 1807.5, 1: 1785.3. Samples: 35610910. Policy #0 lag: (min: 9.0, avg: 16.4, max: 41.0) -[2023-10-16 05:31:47,351][03835] Avg episode reward: [(0, '6.800'), (1, '8.030')] -[2023-10-16 05:31:47,427][05219] Updated weights for policy 1, policy_version 69410 (0.0009) -[2023-10-16 05:31:47,803][05219] Updated weights for policy 1, policy_version 69420 (0.0009) -[2023-10-16 05:31:48,163][05219] Updated weights for policy 1, policy_version 69430 (0.0007) -[2023-10-16 05:31:48,526][05219] Updated weights for policy 1, policy_version 69440 (0.0008) -[2023-10-16 05:31:50,306][05218] Updated weights for policy 0, policy_version 69672 (0.0009) -[2023-10-16 05:31:50,688][05218] Updated weights for policy 0, policy_version 69682 (0.0009) -[2023-10-16 05:31:51,065][05218] Updated weights for policy 0, policy_version 69692 (0.0008) -[2023-10-16 05:31:52,277][05219] Updated weights for policy 1, policy_version 69450 (0.0009) -[2023-10-16 05:31:52,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 142475264. Throughput: 0: 1794.7, 1: 1803.4. Samples: 35632458. Policy #0 lag: (min: 9.0, avg: 16.4, max: 41.0) -[2023-10-16 05:31:52,351][03835] Avg episode reward: [(0, '6.770'), (1, '8.100')] -[2023-10-16 05:31:52,652][05219] Updated weights for policy 1, policy_version 69460 (0.0010) -[2023-10-16 05:31:53,017][05219] Updated weights for policy 1, policy_version 69470 (0.0008) -[2023-10-16 05:31:54,767][05218] Updated weights for policy 0, policy_version 69702 (0.0007) -[2023-10-16 05:31:55,141][05218] Updated weights for policy 0, policy_version 69712 (0.0007) -[2023-10-16 05:31:55,506][05218] Updated weights for policy 0, policy_version 69722 (0.0009) -[2023-10-16 05:31:56,746][05219] Updated weights for policy 1, policy_version 69480 (0.0008) -[2023-10-16 05:31:57,115][05219] Updated weights for policy 1, policy_version 69490 (0.0010) -[2023-10-16 05:31:57,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 142540800. Throughput: 0: 1813.9, 1: 1776.1. Samples: 35643124. Policy #0 lag: (min: 14.0, avg: 16.1, max: 44.0) -[2023-10-16 05:31:57,351][03835] Avg episode reward: [(0, '6.770'), (1, '7.190')] -[2023-10-16 05:31:57,474][05219] Updated weights for policy 1, policy_version 69500 (0.0009) -[2023-10-16 05:31:59,398][05218] Updated weights for policy 0, policy_version 69732 (0.0010) -[2023-10-16 05:31:59,762][05218] Updated weights for policy 0, policy_version 69742 (0.0009) -[2023-10-16 05:32:00,139][05218] Updated weights for policy 0, policy_version 69752 (0.0009) -[2023-10-16 05:32:01,329][05219] Updated weights for policy 1, policy_version 69510 (0.0009) -[2023-10-16 05:32:01,688][05219] Updated weights for policy 1, policy_version 69520 (0.0009) -[2023-10-16 05:32:02,057][05219] Updated weights for policy 1, policy_version 69530 (0.0007) -[2023-10-16 05:32:02,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 142639104. Throughput: 0: 1800.7, 1: 1801.4. Samples: 35664910. Policy #0 lag: (min: 14.0, avg: 16.1, max: 44.0) -[2023-10-16 05:32:02,351][03835] Avg episode reward: [(0, '6.690'), (1, '7.920')] -[2023-10-16 05:32:03,784][05218] Updated weights for policy 0, policy_version 69762 (0.0011) -[2023-10-16 05:32:04,151][05218] Updated weights for policy 0, policy_version 69772 (0.0009) -[2023-10-16 05:32:04,529][05218] Updated weights for policy 0, policy_version 69782 (0.0009) -[2023-10-16 05:32:04,900][05218] Updated weights for policy 0, policy_version 69792 (0.0008) -[2023-10-16 05:32:05,667][05219] Updated weights for policy 1, policy_version 69540 (0.0008) -[2023-10-16 05:32:06,035][05219] Updated weights for policy 1, policy_version 69550 (0.0007) -[2023-10-16 05:32:06,397][05219] Updated weights for policy 1, policy_version 69560 (0.0007) -[2023-10-16 05:32:07,351][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 142704640. Throughput: 0: 1801.7, 1: 1779.9. Samples: 35686324. Policy #0 lag: (min: 14.0, avg: 16.1, max: 44.0) -[2023-10-16 05:32:07,352][03835] Avg episode reward: [(0, '6.530'), (1, '7.620')] -[2023-10-16 05:32:08,634][05218] Updated weights for policy 0, policy_version 69802 (0.0010) -[2023-10-16 05:32:09,014][05218] Updated weights for policy 0, policy_version 69812 (0.0010) -[2023-10-16 05:32:09,396][05218] Updated weights for policy 0, policy_version 69822 (0.0010) -[2023-10-16 05:32:10,260][05219] Updated weights for policy 1, policy_version 69570 (0.0009) -[2023-10-16 05:32:10,614][05219] Updated weights for policy 1, policy_version 69580 (0.0009) -[2023-10-16 05:32:10,989][05219] Updated weights for policy 1, policy_version 69590 (0.0011) -[2023-10-16 05:32:11,351][05219] Updated weights for policy 1, policy_version 69600 (0.0010) -[2023-10-16 05:32:12,351][03835] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 142770176. Throughput: 0: 1796.6, 1: 1798.6. Samples: 35697402. Policy #0 lag: (min: 14.0, avg: 16.1, max: 44.0) -[2023-10-16 05:32:12,352][03835] Avg episode reward: [(0, '6.750'), (1, '6.380')] -[2023-10-16 05:32:13,075][05218] Updated weights for policy 0, policy_version 69832 (0.0008) -[2023-10-16 05:32:13,454][05218] Updated weights for policy 0, policy_version 69842 (0.0011) -[2023-10-16 05:32:13,831][05218] Updated weights for policy 0, policy_version 69852 (0.0011) -[2023-10-16 05:32:15,020][05219] Updated weights for policy 1, policy_version 69610 (0.0008) -[2023-10-16 05:32:15,389][05219] Updated weights for policy 1, policy_version 69620 (0.0007) -[2023-10-16 05:32:15,755][05219] Updated weights for policy 1, policy_version 69630 (0.0008) -[2023-10-16 05:32:17,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 142835712. Throughput: 0: 1799.5, 1: 1776.4. Samples: 35718484. Policy #0 lag: (min: 14.0, avg: 16.1, max: 44.0) -[2023-10-16 05:32:17,351][03835] Avg episode reward: [(0, '6.610'), (1, '7.120')] -[2023-10-16 05:32:17,605][05218] Updated weights for policy 0, policy_version 69862 (0.0009) -[2023-10-16 05:32:17,990][05218] Updated weights for policy 0, policy_version 69872 (0.0008) -[2023-10-16 05:32:18,373][05218] Updated weights for policy 0, policy_version 69882 (0.0007) -[2023-10-16 05:32:19,743][05219] Updated weights for policy 1, policy_version 69640 (0.0007) -[2023-10-16 05:32:20,110][05219] Updated weights for policy 1, policy_version 69650 (0.0008) -[2023-10-16 05:32:20,483][05219] Updated weights for policy 1, policy_version 69660 (0.0009) -[2023-10-16 05:32:22,032][05218] Updated weights for policy 0, policy_version 69892 (0.0008) -[2023-10-16 05:32:22,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 142901248. Throughput: 0: 1815.1, 1: 1774.0. Samples: 35740440. Policy #0 lag: (min: 14.0, avg: 16.1, max: 44.0) -[2023-10-16 05:32:22,351][03835] Avg episode reward: [(0, '7.150'), (1, '6.780')] -[2023-10-16 05:32:22,400][05218] Updated weights for policy 0, policy_version 69902 (0.0009) -[2023-10-16 05:32:22,774][05218] Updated weights for policy 0, policy_version 69912 (0.0009) -[2023-10-16 05:32:24,178][05219] Updated weights for policy 1, policy_version 69670 (0.0008) -[2023-10-16 05:32:24,558][05219] Updated weights for policy 1, policy_version 69680 (0.0008) -[2023-10-16 05:32:24,919][05219] Updated weights for policy 1, policy_version 69690 (0.0007) -[2023-10-16 05:32:26,526][05218] Updated weights for policy 0, policy_version 69922 (0.0009) -[2023-10-16 05:32:26,905][05218] Updated weights for policy 0, policy_version 69932 (0.0011) -[2023-10-16 05:32:27,286][05218] Updated weights for policy 0, policy_version 69942 (0.0009) -[2023-10-16 05:32:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 142966784. Throughput: 0: 1798.4, 1: 1782.7. Samples: 35750784. Policy #0 lag: (min: 14.0, avg: 16.1, max: 44.0) -[2023-10-16 05:32:27,351][03835] Avg episode reward: [(0, '6.840'), (1, '7.080')] -[2023-10-16 05:32:27,663][05218] Updated weights for policy 0, policy_version 69952 (0.0008) -[2023-10-16 05:32:28,619][05219] Updated weights for policy 1, policy_version 69700 (0.0008) -[2023-10-16 05:32:28,976][05219] Updated weights for policy 1, policy_version 69710 (0.0010) -[2023-10-16 05:32:29,347][05219] Updated weights for policy 1, policy_version 69720 (0.0010) -[2023-10-16 05:32:31,430][05218] Updated weights for policy 0, policy_version 69962 (0.0011) -[2023-10-16 05:32:31,812][05218] Updated weights for policy 0, policy_version 69972 (0.0009) -[2023-10-16 05:32:32,184][05218] Updated weights for policy 0, policy_version 69982 (0.0007) -[2023-10-16 05:32:32,351][03835] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 143065088. Throughput: 0: 1812.8, 1: 1785.4. Samples: 35772828. Policy #0 lag: (min: 14.0, avg: 16.1, max: 44.0) -[2023-10-16 05:32:32,352][03835] Avg episode reward: [(0, '7.070'), (1, '7.090')] -[2023-10-16 05:32:33,129][05219] Updated weights for policy 1, policy_version 69730 (0.0009) -[2023-10-16 05:32:33,492][05219] Updated weights for policy 1, policy_version 69740 (0.0009) -[2023-10-16 05:32:33,852][05219] Updated weights for policy 1, policy_version 69750 (0.0011) -[2023-10-16 05:32:34,215][05219] Updated weights for policy 1, policy_version 69760 (0.0008) -[2023-10-16 05:32:35,755][05218] Updated weights for policy 0, policy_version 69992 (0.0010) -[2023-10-16 05:32:36,122][05218] Updated weights for policy 0, policy_version 70002 (0.0009) -[2023-10-16 05:32:36,501][05218] Updated weights for policy 0, policy_version 70012 (0.0009) -[2023-10-16 05:32:37,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 143130624. Throughput: 0: 1802.8, 1: 1795.5. Samples: 35794382. Policy #0 lag: (min: 14.0, avg: 16.1, max: 44.0) -[2023-10-16 05:32:37,351][03835] Avg episode reward: [(0, '7.290'), (1, '7.370')] -[2023-10-16 05:32:38,025][05219] Updated weights for policy 1, policy_version 69770 (0.0008) -[2023-10-16 05:32:38,382][05219] Updated weights for policy 1, policy_version 69780 (0.0010) -[2023-10-16 05:32:38,765][05219] Updated weights for policy 1, policy_version 69790 (0.0010) -[2023-10-16 05:32:40,286][05218] Updated weights for policy 0, policy_version 70022 (0.0008) -[2023-10-16 05:32:40,657][05218] Updated weights for policy 0, policy_version 70032 (0.0009) -[2023-10-16 05:32:41,037][05218] Updated weights for policy 0, policy_version 70042 (0.0008) -[2023-10-16 05:32:42,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 143196160. Throughput: 0: 1811.6, 1: 1788.1. Samples: 35805110. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:32:42,351][03835] Avg episode reward: [(0, '6.580'), (1, '7.500')] -[2023-10-16 05:32:42,527][05219] Updated weights for policy 1, policy_version 69800 (0.0008) -[2023-10-16 05:32:42,903][05219] Updated weights for policy 1, policy_version 69810 (0.0008) -[2023-10-16 05:32:43,268][05219] Updated weights for policy 1, policy_version 69820 (0.0009) -[2023-10-16 05:32:44,804][05218] Updated weights for policy 0, policy_version 70052 (0.0009) -[2023-10-16 05:32:45,171][05218] Updated weights for policy 0, policy_version 70062 (0.0010) -[2023-10-16 05:32:45,548][05218] Updated weights for policy 0, policy_version 70072 (0.0007) -[2023-10-16 05:32:46,969][05219] Updated weights for policy 1, policy_version 69830 (0.0010) -[2023-10-16 05:32:47,331][05219] Updated weights for policy 1, policy_version 69840 (0.0010) -[2023-10-16 05:32:47,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 143261696. Throughput: 0: 1799.1, 1: 1788.0. Samples: 35826330. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:32:47,351][03835] Avg episode reward: [(0, '6.630'), (1, '7.020')] -[2023-10-16 05:32:47,703][05219] Updated weights for policy 1, policy_version 69850 (0.0008) -[2023-10-16 05:32:49,174][05218] Updated weights for policy 0, policy_version 70082 (0.0008) -[2023-10-16 05:32:49,559][05218] Updated weights for policy 0, policy_version 70092 (0.0009) -[2023-10-16 05:32:49,933][05218] Updated weights for policy 0, policy_version 70102 (0.0009) -[2023-10-16 05:32:50,304][05218] Updated weights for policy 0, policy_version 70112 (0.0009) -[2023-10-16 05:32:51,614][05219] Updated weights for policy 1, policy_version 69860 (0.0008) -[2023-10-16 05:32:51,984][05219] Updated weights for policy 1, policy_version 69870 (0.0008) -[2023-10-16 05:32:52,346][05219] Updated weights for policy 1, policy_version 69880 (0.0007) -[2023-10-16 05:32:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 143327232. Throughput: 0: 1794.0, 1: 1796.3. Samples: 35847884. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:32:52,352][03835] Avg episode reward: [(0, '6.940'), (1, '6.770')] -[2023-10-16 05:32:54,215][05218] Updated weights for policy 0, policy_version 70122 (0.0008) -[2023-10-16 05:32:54,591][05218] Updated weights for policy 0, policy_version 70132 (0.0009) -[2023-10-16 05:32:54,974][05218] Updated weights for policy 0, policy_version 70142 (0.0007) -[2023-10-16 05:32:56,100][05219] Updated weights for policy 1, policy_version 69890 (0.0008) -[2023-10-16 05:32:56,464][05219] Updated weights for policy 1, policy_version 69900 (0.0011) -[2023-10-16 05:32:56,839][05219] Updated weights for policy 1, policy_version 69910 (0.0008) -[2023-10-16 05:32:57,200][05219] Updated weights for policy 1, policy_version 69920 (0.0007) -[2023-10-16 05:32:57,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 143425536. Throughput: 0: 1792.8, 1: 1783.9. Samples: 35858354. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:32:57,352][03835] Avg episode reward: [(0, '6.710'), (1, '7.650')] -[2023-10-16 05:32:58,634][05218] Updated weights for policy 0, policy_version 70152 (0.0008) -[2023-10-16 05:32:59,005][05218] Updated weights for policy 0, policy_version 70162 (0.0008) -[2023-10-16 05:32:59,380][05218] Updated weights for policy 0, policy_version 70172 (0.0008) -[2023-10-16 05:33:00,852][05219] Updated weights for policy 1, policy_version 69930 (0.0008) -[2023-10-16 05:33:01,213][05219] Updated weights for policy 1, policy_version 69940 (0.0010) -[2023-10-16 05:33:01,582][05219] Updated weights for policy 1, policy_version 69950 (0.0009) -[2023-10-16 05:33:02,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 143491072. Throughput: 0: 1794.4, 1: 1800.1. Samples: 35880232. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:33:02,351][03835] Avg episode reward: [(0, '7.290'), (1, '7.060')] -[2023-10-16 05:33:03,210][05218] Updated weights for policy 0, policy_version 70182 (0.0007) -[2023-10-16 05:33:03,580][05218] Updated weights for policy 0, policy_version 70192 (0.0010) -[2023-10-16 05:33:03,958][05218] Updated weights for policy 0, policy_version 70202 (0.0009) -[2023-10-16 05:33:05,469][05219] Updated weights for policy 1, policy_version 69960 (0.0008) -[2023-10-16 05:33:05,836][05219] Updated weights for policy 1, policy_version 69970 (0.0011) -[2023-10-16 05:33:06,209][05219] Updated weights for policy 1, policy_version 69980 (0.0010) -[2023-10-16 05:33:07,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 143556608. Throughput: 0: 1804.9, 1: 1785.5. Samples: 35902010. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:33:07,351][03835] Avg episode reward: [(0, '7.180'), (1, '6.300')] -[2023-10-16 05:33:07,746][05218] Updated weights for policy 0, policy_version 70212 (0.0010) -[2023-10-16 05:33:08,128][05218] Updated weights for policy 0, policy_version 70222 (0.0009) -[2023-10-16 05:33:08,492][05218] Updated weights for policy 0, policy_version 70232 (0.0010) -[2023-10-16 05:33:10,048][05219] Updated weights for policy 1, policy_version 69990 (0.0008) -[2023-10-16 05:33:10,428][05219] Updated weights for policy 1, policy_version 70000 (0.0008) -[2023-10-16 05:33:10,790][05219] Updated weights for policy 1, policy_version 70010 (0.0010) -[2023-10-16 05:33:12,285][05218] Updated weights for policy 0, policy_version 70242 (0.0010) -[2023-10-16 05:33:12,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 143622144. Throughput: 0: 1791.1, 1: 1804.5. Samples: 35912582. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:33:12,351][03835] Avg episode reward: [(0, '6.670'), (1, '7.060')] -[2023-10-16 05:33:12,664][05218] Updated weights for policy 0, policy_version 70252 (0.0008) -[2023-10-16 05:33:13,035][05218] Updated weights for policy 0, policy_version 70262 (0.0007) -[2023-10-16 05:33:13,406][05218] Updated weights for policy 0, policy_version 70272 (0.0008) -[2023-10-16 05:33:14,372][05219] Updated weights for policy 1, policy_version 70020 (0.0009) -[2023-10-16 05:33:14,732][05219] Updated weights for policy 1, policy_version 70030 (0.0009) -[2023-10-16 05:33:15,102][05219] Updated weights for policy 1, policy_version 70040 (0.0007) -[2023-10-16 05:33:16,966][05218] Updated weights for policy 0, policy_version 70282 (0.0011) -[2023-10-16 05:33:17,340][05218] Updated weights for policy 0, policy_version 70292 (0.0009) -[2023-10-16 05:33:17,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 143687680. Throughput: 0: 1803.7, 1: 1782.7. Samples: 35934216. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:33:17,351][03835] Avg episode reward: [(0, '7.550'), (1, '7.260')] -[2023-10-16 05:33:17,723][05218] Updated weights for policy 0, policy_version 70302 (0.0008) -[2023-10-16 05:33:18,776][05219] Updated weights for policy 1, policy_version 70050 (0.0007) -[2023-10-16 05:33:19,125][05219] Updated weights for policy 1, policy_version 70060 (0.0008) -[2023-10-16 05:33:19,486][05219] Updated weights for policy 1, policy_version 70070 (0.0008) -[2023-10-16 05:33:19,849][05219] Updated weights for policy 1, policy_version 70080 (0.0007) -[2023-10-16 05:33:21,462][05218] Updated weights for policy 0, policy_version 70312 (0.0007) -[2023-10-16 05:33:21,841][05218] Updated weights for policy 0, policy_version 70322 (0.0007) -[2023-10-16 05:33:22,230][05218] Updated weights for policy 0, policy_version 70332 (0.0007) -[2023-10-16 05:33:22,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 143753216. Throughput: 0: 1794.5, 1: 1781.3. Samples: 35955296. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:33:22,352][03835] Avg episode reward: [(0, '7.180'), (1, '7.000')] -[2023-10-16 05:33:23,732][05219] Updated weights for policy 1, policy_version 70090 (0.0008) -[2023-10-16 05:33:24,103][05219] Updated weights for policy 1, policy_version 70100 (0.0010) -[2023-10-16 05:33:24,473][05219] Updated weights for policy 1, policy_version 70110 (0.0009) -[2023-10-16 05:33:25,933][05218] Updated weights for policy 0, policy_version 70342 (0.0009) -[2023-10-16 05:33:26,314][05218] Updated weights for policy 0, policy_version 70352 (0.0010) -[2023-10-16 05:33:26,678][05218] Updated weights for policy 0, policy_version 70362 (0.0008) -[2023-10-16 05:33:27,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 143851520. Throughput: 0: 1802.0, 1: 1782.3. Samples: 35966402. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:33:27,351][03835] Avg episode reward: [(0, '6.750'), (1, '7.210')] -[2023-10-16 05:33:28,193][05219] Updated weights for policy 1, policy_version 70120 (0.0008) -[2023-10-16 05:33:28,565][05219] Updated weights for policy 1, policy_version 70130 (0.0008) -[2023-10-16 05:33:28,923][05219] Updated weights for policy 1, policy_version 70140 (0.0008) -[2023-10-16 05:33:30,407][05218] Updated weights for policy 0, policy_version 70372 (0.0010) -[2023-10-16 05:33:30,779][05218] Updated weights for policy 0, policy_version 70382 (0.0010) -[2023-10-16 05:33:31,153][05218] Updated weights for policy 0, policy_version 70392 (0.0011) -[2023-10-16 05:33:32,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 143917056. Throughput: 0: 1798.7, 1: 1783.5. Samples: 35987530. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:33:32,351][03835] Avg episode reward: [(0, '7.240'), (1, '6.790')] -[2023-10-16 05:33:32,673][05219] Updated weights for policy 1, policy_version 70150 (0.0010) -[2023-10-16 05:33:33,037][05219] Updated weights for policy 1, policy_version 70160 (0.0008) -[2023-10-16 05:33:33,407][05219] Updated weights for policy 1, policy_version 70170 (0.0009) -[2023-10-16 05:33:34,826][05218] Updated weights for policy 0, policy_version 70402 (0.0008) -[2023-10-16 05:33:35,211][05218] Updated weights for policy 0, policy_version 70412 (0.0011) -[2023-10-16 05:33:35,584][05218] Updated weights for policy 0, policy_version 70422 (0.0010) -[2023-10-16 05:33:35,955][05218] Updated weights for policy 0, policy_version 70432 (0.0010) -[2023-10-16 05:33:37,284][05219] Updated weights for policy 1, policy_version 70180 (0.0009) -[2023-10-16 05:33:37,351][03835] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 143982592. Throughput: 0: 1798.1, 1: 1808.0. Samples: 36010160. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:33:37,352][03835] Avg episode reward: [(0, '6.740'), (1, '6.000')] -[2023-10-16 05:33:37,362][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000070432_72122368.pth... -[2023-10-16 05:33:37,406][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000068736_70385664.pth -[2023-10-16 05:33:37,653][05219] Updated weights for policy 1, policy_version 70190 (0.0008) -[2023-10-16 05:33:38,008][05219] Updated weights for policy 1, policy_version 70200 (0.0007) -[2023-10-16 05:33:38,306][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000070208_71892992.pth... -[2023-10-16 05:33:38,346][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000068512_70156288.pth -[2023-10-16 05:33:39,702][05218] Updated weights for policy 0, policy_version 70442 (0.0008) -[2023-10-16 05:33:40,075][05218] Updated weights for policy 0, policy_version 70452 (0.0007) -[2023-10-16 05:33:40,457][05218] Updated weights for policy 0, policy_version 70462 (0.0008) -[2023-10-16 05:33:41,763][05219] Updated weights for policy 1, policy_version 70210 (0.0009) -[2023-10-16 05:33:42,125][05219] Updated weights for policy 1, policy_version 70220 (0.0007) -[2023-10-16 05:33:42,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 144048128. Throughput: 0: 1808.9, 1: 1789.1. Samples: 36020262. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:33:42,352][03835] Avg episode reward: [(0, '6.250'), (1, '6.850')] -[2023-10-16 05:33:42,510][05219] Updated weights for policy 1, policy_version 70230 (0.0010) -[2023-10-16 05:33:42,870][05219] Updated weights for policy 1, policy_version 70240 (0.0010) -[2023-10-16 05:33:44,261][05218] Updated weights for policy 0, policy_version 70472 (0.0011) -[2023-10-16 05:33:44,641][05218] Updated weights for policy 0, policy_version 70482 (0.0008) -[2023-10-16 05:33:45,013][05218] Updated weights for policy 0, policy_version 70492 (0.0007) -[2023-10-16 05:33:46,596][05219] Updated weights for policy 1, policy_version 70250 (0.0010) -[2023-10-16 05:33:46,958][05219] Updated weights for policy 1, policy_version 70260 (0.0009) -[2023-10-16 05:33:47,332][05219] Updated weights for policy 1, policy_version 70270 (0.0007) -[2023-10-16 05:33:47,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 144113664. Throughput: 0: 1795.1, 1: 1808.3. Samples: 36042382. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:33:47,351][03835] Avg episode reward: [(0, '7.090'), (1, '6.800')] -[2023-10-16 05:33:48,769][05218] Updated weights for policy 0, policy_version 70502 (0.0010) -[2023-10-16 05:33:49,137][05218] Updated weights for policy 0, policy_version 70512 (0.0008) -[2023-10-16 05:33:49,522][05218] Updated weights for policy 0, policy_version 70522 (0.0008) -[2023-10-16 05:33:51,115][05219] Updated weights for policy 1, policy_version 70280 (0.0009) -[2023-10-16 05:33:51,481][05219] Updated weights for policy 1, policy_version 70290 (0.0008) -[2023-10-16 05:33:51,843][05219] Updated weights for policy 1, policy_version 70300 (0.0008) -[2023-10-16 05:33:52,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 144211968. Throughput: 0: 1794.8, 1: 1788.0. Samples: 36063236. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:33:52,351][03835] Avg episode reward: [(0, '6.080'), (1, '7.600')] -[2023-10-16 05:33:53,082][05218] Updated weights for policy 0, policy_version 70532 (0.0008) -[2023-10-16 05:33:53,460][05218] Updated weights for policy 0, policy_version 70542 (0.0007) -[2023-10-16 05:33:53,838][05218] Updated weights for policy 0, policy_version 70552 (0.0007) -[2023-10-16 05:33:55,536][05219] Updated weights for policy 1, policy_version 70310 (0.0009) -[2023-10-16 05:33:55,914][05219] Updated weights for policy 1, policy_version 70320 (0.0008) -[2023-10-16 05:33:56,272][05219] Updated weights for policy 1, policy_version 70330 (0.0010) -[2023-10-16 05:33:57,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 144277504. Throughput: 0: 1798.9, 1: 1800.2. Samples: 36074540. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:33:57,351][03835] Avg episode reward: [(0, '6.430'), (1, '7.430')] -[2023-10-16 05:33:57,427][05218] Updated weights for policy 0, policy_version 70562 (0.0008) -[2023-10-16 05:33:57,801][05218] Updated weights for policy 0, policy_version 70572 (0.0009) -[2023-10-16 05:33:58,171][05218] Updated weights for policy 0, policy_version 70582 (0.0007) -[2023-10-16 05:33:58,541][05218] Updated weights for policy 0, policy_version 70592 (0.0009) -[2023-10-16 05:33:59,990][05219] Updated weights for policy 1, policy_version 70340 (0.0010) -[2023-10-16 05:34:00,346][05219] Updated weights for policy 1, policy_version 70350 (0.0007) -[2023-10-16 05:34:00,714][05219] Updated weights for policy 1, policy_version 70360 (0.0008) -[2023-10-16 05:34:02,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 144343040. Throughput: 0: 1794.2, 1: 1787.3. Samples: 36095384. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:34:02,351][03835] Avg episode reward: [(0, '7.370'), (1, '6.530')] -[2023-10-16 05:34:02,504][05218] Updated weights for policy 0, policy_version 70602 (0.0007) -[2023-10-16 05:34:02,884][05218] Updated weights for policy 0, policy_version 70612 (0.0007) -[2023-10-16 05:34:03,251][05218] Updated weights for policy 0, policy_version 70622 (0.0007) -[2023-10-16 05:34:04,382][05219] Updated weights for policy 1, policy_version 70370 (0.0010) -[2023-10-16 05:34:04,752][05219] Updated weights for policy 1, policy_version 70380 (0.0007) -[2023-10-16 05:34:05,115][05219] Updated weights for policy 1, policy_version 70390 (0.0007) -[2023-10-16 05:34:05,482][05219] Updated weights for policy 1, policy_version 70400 (0.0009) -[2023-10-16 05:34:06,880][05218] Updated weights for policy 0, policy_version 70632 (0.0007) -[2023-10-16 05:34:07,262][05218] Updated weights for policy 0, policy_version 70642 (0.0007) -[2023-10-16 05:34:07,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 144408576. Throughput: 0: 1808.9, 1: 1792.9. Samples: 36117376. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:34:07,351][03835] Avg episode reward: [(0, '6.670'), (1, '7.310')] -[2023-10-16 05:34:07,634][05218] Updated weights for policy 0, policy_version 70652 (0.0009) -[2023-10-16 05:34:09,263][05219] Updated weights for policy 1, policy_version 70410 (0.0009) -[2023-10-16 05:34:09,627][05219] Updated weights for policy 1, policy_version 70420 (0.0008) -[2023-10-16 05:34:09,984][05219] Updated weights for policy 1, policy_version 70430 (0.0010) -[2023-10-16 05:34:11,445][05218] Updated weights for policy 0, policy_version 70662 (0.0009) -[2023-10-16 05:34:11,828][05218] Updated weights for policy 0, policy_version 70672 (0.0007) -[2023-10-16 05:34:12,205][05218] Updated weights for policy 0, policy_version 70682 (0.0007) -[2023-10-16 05:34:12,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 144474112. Throughput: 0: 1797.0, 1: 1795.5. Samples: 36128062. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:34:12,351][03835] Avg episode reward: [(0, '6.740'), (1, '6.300')] -[2023-10-16 05:34:13,932][05219] Updated weights for policy 1, policy_version 70440 (0.0010) -[2023-10-16 05:34:14,300][05219] Updated weights for policy 1, policy_version 70450 (0.0011) -[2023-10-16 05:34:14,665][05219] Updated weights for policy 1, policy_version 70460 (0.0009) -[2023-10-16 05:34:15,951][05218] Updated weights for policy 0, policy_version 70692 (0.0010) -[2023-10-16 05:34:16,322][05218] Updated weights for policy 0, policy_version 70702 (0.0010) -[2023-10-16 05:34:16,699][05218] Updated weights for policy 0, policy_version 70712 (0.0008) -[2023-10-16 05:34:17,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 144572416. Throughput: 0: 1809.4, 1: 1789.8. Samples: 36149492. Policy #0 lag: (min: 23.0, avg: 30.2, max: 55.0) -[2023-10-16 05:34:17,351][03835] Avg episode reward: [(0, '6.930'), (1, '7.110')] -[2023-10-16 05:34:18,448][05219] Updated weights for policy 1, policy_version 70470 (0.0008) -[2023-10-16 05:34:18,815][05219] Updated weights for policy 1, policy_version 70480 (0.0008) -[2023-10-16 05:34:19,177][05219] Updated weights for policy 1, policy_version 70490 (0.0009) -[2023-10-16 05:34:20,340][05218] Updated weights for policy 0, policy_version 70722 (0.0010) -[2023-10-16 05:34:20,724][05218] Updated weights for policy 0, policy_version 70732 (0.0010) -[2023-10-16 05:34:21,090][05218] Updated weights for policy 0, policy_version 70742 (0.0007) -[2023-10-16 05:34:21,461][05218] Updated weights for policy 0, policy_version 70752 (0.0009) -[2023-10-16 05:34:22,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 144637952. Throughput: 0: 1796.1, 1: 1788.4. Samples: 36171466. Policy #0 lag: (min: 23.0, avg: 30.2, max: 55.0) -[2023-10-16 05:34:22,351][03835] Avg episode reward: [(0, '6.590'), (1, '7.400')] -[2023-10-16 05:34:22,944][05219] Updated weights for policy 1, policy_version 70500 (0.0009) -[2023-10-16 05:34:23,297][05219] Updated weights for policy 1, policy_version 70510 (0.0012) -[2023-10-16 05:34:23,659][05219] Updated weights for policy 1, policy_version 70520 (0.0011) -[2023-10-16 05:34:25,196][05218] Updated weights for policy 0, policy_version 70762 (0.0007) -[2023-10-16 05:34:25,562][05218] Updated weights for policy 0, policy_version 70772 (0.0008) -[2023-10-16 05:34:25,938][05218] Updated weights for policy 0, policy_version 70782 (0.0009) -[2023-10-16 05:34:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 144703488. Throughput: 0: 1809.2, 1: 1784.3. Samples: 36181966. Policy #0 lag: (min: 23.0, avg: 30.2, max: 55.0) -[2023-10-16 05:34:27,351][03835] Avg episode reward: [(0, '6.390'), (1, '7.440')] -[2023-10-16 05:34:27,460][05219] Updated weights for policy 1, policy_version 70530 (0.0009) -[2023-10-16 05:34:27,829][05219] Updated weights for policy 1, policy_version 70540 (0.0009) -[2023-10-16 05:34:28,201][05219] Updated weights for policy 1, policy_version 70550 (0.0008) -[2023-10-16 05:34:28,571][05219] Updated weights for policy 1, policy_version 70560 (0.0008) -[2023-10-16 05:34:29,656][05218] Updated weights for policy 0, policy_version 70792 (0.0008) -[2023-10-16 05:34:30,031][05218] Updated weights for policy 0, policy_version 70802 (0.0007) -[2023-10-16 05:34:30,416][05218] Updated weights for policy 0, policy_version 70812 (0.0007) -[2023-10-16 05:34:32,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 144769024. Throughput: 0: 1797.3, 1: 1780.8. Samples: 36203396. Policy #0 lag: (min: 23.0, avg: 30.2, max: 55.0) -[2023-10-16 05:34:32,351][03835] Avg episode reward: [(0, '6.550'), (1, '7.080')] -[2023-10-16 05:34:32,403][05219] Updated weights for policy 1, policy_version 70570 (0.0007) -[2023-10-16 05:34:32,774][05219] Updated weights for policy 1, policy_version 70580 (0.0009) -[2023-10-16 05:34:33,135][05219] Updated weights for policy 1, policy_version 70590 (0.0007) -[2023-10-16 05:34:34,018][05218] Updated weights for policy 0, policy_version 70822 (0.0009) -[2023-10-16 05:34:34,381][05218] Updated weights for policy 0, policy_version 70832 (0.0007) -[2023-10-16 05:34:34,766][05218] Updated weights for policy 0, policy_version 70842 (0.0008) -[2023-10-16 05:34:37,047][05219] Updated weights for policy 1, policy_version 70600 (0.0007) -[2023-10-16 05:34:37,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 144834560. Throughput: 0: 1801.3, 1: 1804.7. Samples: 36225504. Policy #0 lag: (min: 23.0, avg: 30.2, max: 55.0) -[2023-10-16 05:34:37,351][03835] Avg episode reward: [(0, '7.180'), (1, '6.820')] -[2023-10-16 05:34:37,411][05219] Updated weights for policy 1, policy_version 70610 (0.0007) -[2023-10-16 05:34:37,779][05219] Updated weights for policy 1, policy_version 70620 (0.0008) -[2023-10-16 05:34:38,503][05218] Updated weights for policy 0, policy_version 70852 (0.0008) -[2023-10-16 05:34:38,868][05218] Updated weights for policy 0, policy_version 70862 (0.0007) -[2023-10-16 05:34:39,248][05218] Updated weights for policy 0, policy_version 70872 (0.0010) -[2023-10-16 05:34:41,708][05219] Updated weights for policy 1, policy_version 70630 (0.0009) -[2023-10-16 05:34:42,102][05219] Updated weights for policy 1, policy_version 70640 (0.0007) -[2023-10-16 05:34:42,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 144900096. Throughput: 0: 1800.0, 1: 1776.6. Samples: 36235488. Policy #0 lag: (min: 23.0, avg: 30.2, max: 55.0) -[2023-10-16 05:34:42,351][03835] Avg episode reward: [(0, '6.550'), (1, '7.470')] -[2023-10-16 05:34:42,468][05219] Updated weights for policy 1, policy_version 70650 (0.0009) -[2023-10-16 05:34:43,037][05218] Updated weights for policy 0, policy_version 70882 (0.0010) -[2023-10-16 05:34:43,408][05218] Updated weights for policy 0, policy_version 70892 (0.0009) -[2023-10-16 05:34:43,795][05218] Updated weights for policy 0, policy_version 70902 (0.0007) -[2023-10-16 05:34:44,162][05218] Updated weights for policy 0, policy_version 70912 (0.0010) -[2023-10-16 05:34:46,144][05219] Updated weights for policy 1, policy_version 70660 (0.0009) -[2023-10-16 05:34:46,508][05219] Updated weights for policy 1, policy_version 70670 (0.0009) -[2023-10-16 05:34:46,867][05219] Updated weights for policy 1, policy_version 70680 (0.0010) -[2023-10-16 05:34:47,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 144998400. Throughput: 0: 1795.8, 1: 1800.9. Samples: 36257236. Policy #0 lag: (min: 23.0, avg: 30.2, max: 55.0) -[2023-10-16 05:34:47,351][03835] Avg episode reward: [(0, '6.390'), (1, '7.290')] -[2023-10-16 05:34:47,922][05218] Updated weights for policy 0, policy_version 70922 (0.0009) -[2023-10-16 05:34:48,296][05218] Updated weights for policy 0, policy_version 70932 (0.0007) -[2023-10-16 05:34:48,684][05218] Updated weights for policy 0, policy_version 70942 (0.0010) -[2023-10-16 05:34:50,785][05219] Updated weights for policy 1, policy_version 70690 (0.0010) -[2023-10-16 05:34:51,149][05219] Updated weights for policy 1, policy_version 70700 (0.0009) -[2023-10-16 05:34:51,508][05219] Updated weights for policy 1, policy_version 70710 (0.0007) -[2023-10-16 05:34:51,876][05219] Updated weights for policy 1, policy_version 70720 (0.0008) -[2023-10-16 05:34:52,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 145063936. Throughput: 0: 1809.0, 1: 1760.6. Samples: 36278010. Policy #0 lag: (min: 23.0, avg: 30.2, max: 55.0) -[2023-10-16 05:34:52,352][03835] Avg episode reward: [(0, '7.440'), (1, '6.930')] -[2023-10-16 05:34:52,392][05218] Updated weights for policy 0, policy_version 70952 (0.0008) -[2023-10-16 05:34:52,772][05218] Updated weights for policy 0, policy_version 70962 (0.0012) -[2023-10-16 05:34:53,154][05218] Updated weights for policy 0, policy_version 70972 (0.0010) -[2023-10-16 05:34:55,698][05219] Updated weights for policy 1, policy_version 70730 (0.0008) -[2023-10-16 05:34:56,057][05219] Updated weights for policy 1, policy_version 70740 (0.0009) -[2023-10-16 05:34:56,433][05219] Updated weights for policy 1, policy_version 70750 (0.0010) -[2023-10-16 05:34:57,054][05218] Updated weights for policy 0, policy_version 70982 (0.0011) -[2023-10-16 05:34:57,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 145129472. Throughput: 0: 1790.2, 1: 1794.7. Samples: 36289382. Policy #0 lag: (min: 23.0, avg: 30.2, max: 55.0) -[2023-10-16 05:34:57,351][03835] Avg episode reward: [(0, '7.200'), (1, '7.010')] -[2023-10-16 05:34:57,435][05218] Updated weights for policy 0, policy_version 70992 (0.0008) -[2023-10-16 05:34:57,812][05218] Updated weights for policy 0, policy_version 71002 (0.0010) -[2023-10-16 05:35:00,148][05219] Updated weights for policy 1, policy_version 70760 (0.0007) -[2023-10-16 05:35:00,513][05219] Updated weights for policy 1, policy_version 70770 (0.0009) -[2023-10-16 05:35:00,884][05219] Updated weights for policy 1, policy_version 70780 (0.0009) -[2023-10-16 05:35:01,484][05218] Updated weights for policy 0, policy_version 71012 (0.0009) -[2023-10-16 05:35:01,858][05218] Updated weights for policy 0, policy_version 71022 (0.0007) -[2023-10-16 05:35:02,242][05218] Updated weights for policy 0, policy_version 71032 (0.0007) -[2023-10-16 05:35:02,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 145195008. Throughput: 0: 1803.3, 1: 1768.4. Samples: 36310220. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-16 05:35:02,351][03835] Avg episode reward: [(0, '6.920'), (1, '7.120')] -[2023-10-16 05:35:04,695][05219] Updated weights for policy 1, policy_version 70790 (0.0010) -[2023-10-16 05:35:05,059][05219] Updated weights for policy 1, policy_version 70800 (0.0009) -[2023-10-16 05:35:05,429][05219] Updated weights for policy 1, policy_version 70810 (0.0007) -[2023-10-16 05:35:05,980][05218] Updated weights for policy 0, policy_version 71042 (0.0008) -[2023-10-16 05:35:06,357][05218] Updated weights for policy 0, policy_version 71052 (0.0008) -[2023-10-16 05:35:06,736][05218] Updated weights for policy 0, policy_version 71062 (0.0008) -[2023-10-16 05:35:07,106][05218] Updated weights for policy 0, policy_version 71072 (0.0008) -[2023-10-16 05:35:07,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 145293312. Throughput: 0: 1783.7, 1: 1765.4. Samples: 36331174. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-16 05:35:07,351][03835] Avg episode reward: [(0, '7.560'), (1, '7.390')] -[2023-10-16 05:35:09,254][05219] Updated weights for policy 1, policy_version 70820 (0.0008) -[2023-10-16 05:35:09,618][05219] Updated weights for policy 1, policy_version 70830 (0.0008) -[2023-10-16 05:35:09,983][05219] Updated weights for policy 1, policy_version 70840 (0.0008) -[2023-10-16 05:35:11,054][05218] Updated weights for policy 0, policy_version 71082 (0.0010) -[2023-10-16 05:35:11,427][05218] Updated weights for policy 0, policy_version 71092 (0.0009) -[2023-10-16 05:35:11,803][05218] Updated weights for policy 0, policy_version 71102 (0.0011) -[2023-10-16 05:35:12,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 145358848. Throughput: 0: 1797.8, 1: 1774.2. Samples: 36342708. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-16 05:35:12,351][03835] Avg episode reward: [(0, '7.540'), (1, '7.360')] -[2023-10-16 05:35:13,583][05219] Updated weights for policy 1, policy_version 70850 (0.0008) -[2023-10-16 05:35:13,940][05219] Updated weights for policy 1, policy_version 70860 (0.0007) -[2023-10-16 05:35:14,311][05219] Updated weights for policy 1, policy_version 70870 (0.0008) -[2023-10-16 05:35:14,682][05219] Updated weights for policy 1, policy_version 70880 (0.0008) -[2023-10-16 05:35:15,614][05218] Updated weights for policy 0, policy_version 71112 (0.0009) -[2023-10-16 05:35:15,982][05218] Updated weights for policy 0, policy_version 71122 (0.0009) -[2023-10-16 05:35:16,360][05218] Updated weights for policy 0, policy_version 71132 (0.0009) -[2023-10-16 05:35:17,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 145424384. Throughput: 0: 1786.3, 1: 1769.3. Samples: 36363400. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-16 05:35:17,351][03835] Avg episode reward: [(0, '6.470'), (1, '7.410')] -[2023-10-16 05:35:18,456][05219] Updated weights for policy 1, policy_version 70890 (0.0009) -[2023-10-16 05:35:18,821][05219] Updated weights for policy 1, policy_version 70900 (0.0008) -[2023-10-16 05:35:19,185][05219] Updated weights for policy 1, policy_version 70910 (0.0009) -[2023-10-16 05:35:20,014][05218] Updated weights for policy 0, policy_version 71142 (0.0008) -[2023-10-16 05:35:20,392][05218] Updated weights for policy 0, policy_version 71152 (0.0008) -[2023-10-16 05:35:20,769][05218] Updated weights for policy 0, policy_version 71162 (0.0009) -[2023-10-16 05:35:22,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 145489920. Throughput: 0: 1777.2, 1: 1782.4. Samples: 36385686. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-16 05:35:22,351][03835] Avg episode reward: [(0, '7.110'), (1, '7.280')] -[2023-10-16 05:35:22,841][05219] Updated weights for policy 1, policy_version 70920 (0.0010) -[2023-10-16 05:35:23,212][05219] Updated weights for policy 1, policy_version 70930 (0.0008) -[2023-10-16 05:35:23,569][05219] Updated weights for policy 1, policy_version 70940 (0.0007) -[2023-10-16 05:35:24,365][05218] Updated weights for policy 0, policy_version 71172 (0.0009) -[2023-10-16 05:35:24,736][05218] Updated weights for policy 0, policy_version 71182 (0.0008) -[2023-10-16 05:35:25,112][05218] Updated weights for policy 0, policy_version 71192 (0.0011) -[2023-10-16 05:35:27,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 145555456. Throughput: 0: 1785.0, 1: 1776.9. Samples: 36395772. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-16 05:35:27,351][03835] Avg episode reward: [(0, '7.740'), (1, '7.090')] -[2023-10-16 05:35:27,487][05219] Updated weights for policy 1, policy_version 70950 (0.0009) -[2023-10-16 05:35:27,862][05219] Updated weights for policy 1, policy_version 70960 (0.0008) -[2023-10-16 05:35:28,233][05219] Updated weights for policy 1, policy_version 70970 (0.0008) -[2023-10-16 05:35:28,743][05218] Updated weights for policy 0, policy_version 71202 (0.0009) -[2023-10-16 05:35:29,114][05218] Updated weights for policy 0, policy_version 71212 (0.0010) -[2023-10-16 05:35:29,484][05218] Updated weights for policy 0, policy_version 71222 (0.0010) -[2023-10-16 05:35:29,860][05218] Updated weights for policy 0, policy_version 71232 (0.0009) -[2023-10-16 05:35:31,930][05219] Updated weights for policy 1, policy_version 70980 (0.0010) -[2023-10-16 05:35:32,299][05219] Updated weights for policy 1, policy_version 70990 (0.0009) -[2023-10-16 05:35:32,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 145620992. Throughput: 0: 1783.2, 1: 1790.6. Samples: 36418056. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-16 05:35:32,351][03835] Avg episode reward: [(0, '7.170'), (1, '6.930')] -[2023-10-16 05:35:32,659][05219] Updated weights for policy 1, policy_version 71000 (0.0007) -[2023-10-16 05:35:33,734][05218] Updated weights for policy 0, policy_version 71242 (0.0008) -[2023-10-16 05:35:34,112][05218] Updated weights for policy 0, policy_version 71252 (0.0008) -[2023-10-16 05:35:34,492][05218] Updated weights for policy 0, policy_version 71262 (0.0011) -[2023-10-16 05:35:36,451][05219] Updated weights for policy 1, policy_version 71010 (0.0007) -[2023-10-16 05:35:36,817][05219] Updated weights for policy 1, policy_version 71020 (0.0012) -[2023-10-16 05:35:37,187][05219] Updated weights for policy 1, policy_version 71030 (0.0009) -[2023-10-16 05:35:37,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 145686528. Throughput: 0: 1782.8, 1: 1805.4. Samples: 36439480. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-16 05:35:37,351][03835] Avg episode reward: [(0, '7.150'), (1, '7.650')] -[2023-10-16 05:35:37,364][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000071264_72974336.pth... -[2023-10-16 05:35:37,404][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000069600_71270400.pth -[2023-10-16 05:35:37,549][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000071040_72744960.pth... -[2023-10-16 05:35:37,554][05219] Updated weights for policy 1, policy_version 71040 (0.0007) -[2023-10-16 05:35:37,581][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000069344_71008256.pth -[2023-10-16 05:35:38,220][05218] Updated weights for policy 0, policy_version 71272 (0.0009) -[2023-10-16 05:35:38,597][05218] Updated weights for policy 0, policy_version 71282 (0.0009) -[2023-10-16 05:35:38,976][05218] Updated weights for policy 0, policy_version 71292 (0.0008) -[2023-10-16 05:35:41,480][05219] Updated weights for policy 1, policy_version 71050 (0.0008) -[2023-10-16 05:35:41,854][05219] Updated weights for policy 1, policy_version 71060 (0.0008) -[2023-10-16 05:35:42,215][05219] Updated weights for policy 1, policy_version 71070 (0.0010) -[2023-10-16 05:35:42,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 145784832. Throughput: 0: 1777.8, 1: 1789.1. Samples: 36449890. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-16 05:35:42,351][03835] Avg episode reward: [(0, '6.700'), (1, '7.630')] -[2023-10-16 05:35:42,720][05218] Updated weights for policy 0, policy_version 71302 (0.0008) -[2023-10-16 05:35:43,086][05218] Updated weights for policy 0, policy_version 71312 (0.0011) -[2023-10-16 05:35:43,458][05218] Updated weights for policy 0, policy_version 71322 (0.0011) -[2023-10-16 05:35:45,796][05219] Updated weights for policy 1, policy_version 71080 (0.0009) -[2023-10-16 05:35:46,158][05219] Updated weights for policy 1, policy_version 71090 (0.0010) -[2023-10-16 05:35:46,529][05219] Updated weights for policy 1, policy_version 71100 (0.0009) -[2023-10-16 05:35:47,161][05218] Updated weights for policy 0, policy_version 71332 (0.0009) -[2023-10-16 05:35:47,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 145850368. Throughput: 0: 1782.2, 1: 1805.1. Samples: 36471646. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-16 05:35:47,352][03835] Avg episode reward: [(0, '6.560'), (1, '7.410')] -[2023-10-16 05:35:47,537][05218] Updated weights for policy 0, policy_version 71342 (0.0007) -[2023-10-16 05:35:47,915][05218] Updated weights for policy 0, policy_version 71352 (0.0008) -[2023-10-16 05:35:50,236][05219] Updated weights for policy 1, policy_version 71110 (0.0009) -[2023-10-16 05:35:50,606][05219] Updated weights for policy 1, policy_version 71120 (0.0008) -[2023-10-16 05:35:50,961][05219] Updated weights for policy 1, policy_version 71130 (0.0009) -[2023-10-16 05:35:51,652][05218] Updated weights for policy 0, policy_version 71362 (0.0009) -[2023-10-16 05:35:52,032][05218] Updated weights for policy 0, policy_version 71372 (0.0009) -[2023-10-16 05:35:52,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 145915904. Throughput: 0: 1796.2, 1: 1789.6. Samples: 36492534. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-16 05:35:52,351][03835] Avg episode reward: [(0, '7.280'), (1, '7.800')] -[2023-10-16 05:35:52,410][05218] Updated weights for policy 0, policy_version 71382 (0.0010) -[2023-10-16 05:35:52,784][05218] Updated weights for policy 0, policy_version 71392 (0.0009) -[2023-10-16 05:35:54,569][05219] Updated weights for policy 1, policy_version 71140 (0.0009) -[2023-10-16 05:35:54,937][05219] Updated weights for policy 1, policy_version 71150 (0.0009) -[2023-10-16 05:35:55,302][05219] Updated weights for policy 1, policy_version 71160 (0.0008) -[2023-10-16 05:35:56,803][05218] Updated weights for policy 0, policy_version 71402 (0.0008) -[2023-10-16 05:35:57,182][05218] Updated weights for policy 0, policy_version 71412 (0.0008) -[2023-10-16 05:35:57,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 145981440. Throughput: 0: 1779.7, 1: 1800.9. Samples: 36503834. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-16 05:35:57,351][03835] Avg episode reward: [(0, '7.130'), (1, '7.540')] -[2023-10-16 05:35:57,554][05218] Updated weights for policy 0, policy_version 71422 (0.0007) -[2023-10-16 05:35:58,918][05219] Updated weights for policy 1, policy_version 71170 (0.0009) -[2023-10-16 05:35:59,276][05219] Updated weights for policy 1, policy_version 71180 (0.0012) -[2023-10-16 05:35:59,647][05219] Updated weights for policy 1, policy_version 71190 (0.0010) -[2023-10-16 05:36:00,001][05219] Updated weights for policy 1, policy_version 71200 (0.0010) -[2023-10-16 05:36:01,324][05218] Updated weights for policy 0, policy_version 71432 (0.0009) -[2023-10-16 05:36:01,693][05218] Updated weights for policy 0, policy_version 71442 (0.0008) -[2023-10-16 05:36:02,065][05218] Updated weights for policy 0, policy_version 71452 (0.0007) -[2023-10-16 05:36:02,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 146079744. Throughput: 0: 1799.5, 1: 1797.5. Samples: 36525266. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-16 05:36:02,351][03835] Avg episode reward: [(0, '6.730'), (1, '7.530')] -[2023-10-16 05:36:03,850][05219] Updated weights for policy 1, policy_version 71210 (0.0008) -[2023-10-16 05:36:04,219][05219] Updated weights for policy 1, policy_version 71220 (0.0008) -[2023-10-16 05:36:04,579][05219] Updated weights for policy 1, policy_version 71230 (0.0008) -[2023-10-16 05:36:05,704][05218] Updated weights for policy 0, policy_version 71462 (0.0008) -[2023-10-16 05:36:06,080][05218] Updated weights for policy 0, policy_version 71472 (0.0010) -[2023-10-16 05:36:06,456][05218] Updated weights for policy 0, policy_version 71482 (0.0007) -[2023-10-16 05:36:07,350][03835] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 146145280. Throughput: 0: 1783.2, 1: 1797.2. Samples: 36546806. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-16 05:36:07,352][03835] Avg episode reward: [(0, '7.410'), (1, '8.050')] -[2023-10-16 05:36:08,369][05219] Updated weights for policy 1, policy_version 71240 (0.0008) -[2023-10-16 05:36:08,741][05219] Updated weights for policy 1, policy_version 71250 (0.0009) -[2023-10-16 05:36:09,108][05219] Updated weights for policy 1, policy_version 71260 (0.0008) -[2023-10-16 05:36:10,156][05218] Updated weights for policy 0, policy_version 71492 (0.0008) -[2023-10-16 05:36:10,535][05218] Updated weights for policy 0, policy_version 71502 (0.0008) -[2023-10-16 05:36:10,902][05218] Updated weights for policy 0, policy_version 71512 (0.0009) -[2023-10-16 05:36:12,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 146210816. Throughput: 0: 1805.2, 1: 1797.2. Samples: 36557882. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-16 05:36:12,351][03835] Avg episode reward: [(0, '7.650'), (1, '7.070')] -[2023-10-16 05:36:12,928][05219] Updated weights for policy 1, policy_version 71270 (0.0008) -[2023-10-16 05:36:13,297][05219] Updated weights for policy 1, policy_version 71280 (0.0008) -[2023-10-16 05:36:13,659][05219] Updated weights for policy 1, policy_version 71290 (0.0007) -[2023-10-16 05:36:14,613][05218] Updated weights for policy 0, policy_version 71522 (0.0008) -[2023-10-16 05:36:14,978][05218] Updated weights for policy 0, policy_version 71532 (0.0010) -[2023-10-16 05:36:15,362][05218] Updated weights for policy 0, policy_version 71542 (0.0007) -[2023-10-16 05:36:15,724][05218] Updated weights for policy 0, policy_version 71552 (0.0010) -[2023-10-16 05:36:17,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 146276352. Throughput: 0: 1788.5, 1: 1794.4. Samples: 36579288. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-16 05:36:17,351][03835] Avg episode reward: [(0, '6.590'), (1, '7.390')] -[2023-10-16 05:36:17,545][05219] Updated weights for policy 1, policy_version 71300 (0.0007) -[2023-10-16 05:36:17,942][05219] Updated weights for policy 1, policy_version 71310 (0.0010) -[2023-10-16 05:36:18,294][05219] Updated weights for policy 1, policy_version 71320 (0.0010) -[2023-10-16 05:36:19,366][05218] Updated weights for policy 0, policy_version 71562 (0.0010) -[2023-10-16 05:36:19,746][05218] Updated weights for policy 0, policy_version 71572 (0.0009) -[2023-10-16 05:36:20,127][05218] Updated weights for policy 0, policy_version 71582 (0.0009) -[2023-10-16 05:36:22,087][05219] Updated weights for policy 1, policy_version 71330 (0.0009) -[2023-10-16 05:36:22,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 146341888. Throughput: 0: 1790.4, 1: 1804.0. Samples: 36601226. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-16 05:36:22,351][03835] Avg episode reward: [(0, '7.110'), (1, '7.470')] -[2023-10-16 05:36:22,450][05219] Updated weights for policy 1, policy_version 71340 (0.0011) -[2023-10-16 05:36:22,819][05219] Updated weights for policy 1, policy_version 71350 (0.0008) -[2023-10-16 05:36:23,180][05219] Updated weights for policy 1, policy_version 71360 (0.0009) -[2023-10-16 05:36:23,890][05218] Updated weights for policy 0, policy_version 71592 (0.0008) -[2023-10-16 05:36:24,261][05218] Updated weights for policy 0, policy_version 71602 (0.0009) -[2023-10-16 05:36:24,647][05218] Updated weights for policy 0, policy_version 71612 (0.0007) -[2023-10-16 05:36:26,994][05219] Updated weights for policy 1, policy_version 71370 (0.0009) -[2023-10-16 05:36:27,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 146407424. Throughput: 0: 1795.3, 1: 1792.0. Samples: 36611320. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-16 05:36:27,351][03835] Avg episode reward: [(0, '7.410'), (1, '8.290')] -[2023-10-16 05:36:27,353][05219] Updated weights for policy 1, policy_version 71380 (0.0007) -[2023-10-16 05:36:27,719][05219] Updated weights for policy 1, policy_version 71390 (0.0008) -[2023-10-16 05:36:28,530][05218] Updated weights for policy 0, policy_version 71622 (0.0008) -[2023-10-16 05:36:28,905][05218] Updated weights for policy 0, policy_version 71632 (0.0010) -[2023-10-16 05:36:29,278][05218] Updated weights for policy 0, policy_version 71642 (0.0010) -[2023-10-16 05:36:31,389][05219] Updated weights for policy 1, policy_version 71400 (0.0011) -[2023-10-16 05:36:31,753][05219] Updated weights for policy 1, policy_version 71410 (0.0011) -[2023-10-16 05:36:32,116][05219] Updated weights for policy 1, policy_version 71420 (0.0010) -[2023-10-16 05:36:32,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 146505728. Throughput: 0: 1793.8, 1: 1802.9. Samples: 36633498. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:36:32,351][03835] Avg episode reward: [(0, '7.190'), (1, '7.360')] -[2023-10-16 05:36:32,806][05218] Updated weights for policy 0, policy_version 71652 (0.0008) -[2023-10-16 05:36:33,184][05218] Updated weights for policy 0, policy_version 71662 (0.0008) -[2023-10-16 05:36:33,560][05218] Updated weights for policy 0, policy_version 71672 (0.0008) -[2023-10-16 05:36:36,113][05219] Updated weights for policy 1, policy_version 71430 (0.0009) -[2023-10-16 05:36:36,488][05219] Updated weights for policy 1, policy_version 71440 (0.0008) -[2023-10-16 05:36:36,856][05219] Updated weights for policy 1, policy_version 71450 (0.0008) -[2023-10-16 05:36:37,232][05218] Updated weights for policy 0, policy_version 71682 (0.0008) -[2023-10-16 05:36:37,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 146571264. Throughput: 0: 1811.1, 1: 1784.5. Samples: 36654338. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:36:37,351][03835] Avg episode reward: [(0, '7.300'), (1, '7.150')] -[2023-10-16 05:36:37,610][05218] Updated weights for policy 0, policy_version 71692 (0.0010) -[2023-10-16 05:36:37,981][05218] Updated weights for policy 0, policy_version 71702 (0.0010) -[2023-10-16 05:36:38,365][05218] Updated weights for policy 0, policy_version 71712 (0.0008) -[2023-10-16 05:36:40,465][05219] Updated weights for policy 1, policy_version 71460 (0.0009) -[2023-10-16 05:36:40,834][05219] Updated weights for policy 1, policy_version 71470 (0.0008) -[2023-10-16 05:36:41,186][05219] Updated weights for policy 1, policy_version 71480 (0.0010) -[2023-10-16 05:36:42,220][05218] Updated weights for policy 0, policy_version 71722 (0.0010) -[2023-10-16 05:36:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 146636800. Throughput: 0: 1794.2, 1: 1802.1. Samples: 36665670. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:36:42,351][03835] Avg episode reward: [(0, '7.340'), (1, '7.920')] -[2023-10-16 05:36:42,606][05218] Updated weights for policy 0, policy_version 71732 (0.0007) -[2023-10-16 05:36:42,975][05218] Updated weights for policy 0, policy_version 71742 (0.0007) -[2023-10-16 05:36:44,824][05219] Updated weights for policy 1, policy_version 71490 (0.0010) -[2023-10-16 05:36:45,190][05219] Updated weights for policy 1, policy_version 71500 (0.0011) -[2023-10-16 05:36:45,564][05219] Updated weights for policy 1, policy_version 71510 (0.0011) -[2023-10-16 05:36:45,936][05219] Updated weights for policy 1, policy_version 71520 (0.0008) -[2023-10-16 05:36:46,711][05218] Updated weights for policy 0, policy_version 71752 (0.0008) -[2023-10-16 05:36:47,092][05218] Updated weights for policy 0, policy_version 71762 (0.0009) -[2023-10-16 05:36:47,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 146702336. Throughput: 0: 1813.6, 1: 1780.5. Samples: 36687002. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:36:47,351][03835] Avg episode reward: [(0, '7.610'), (1, '6.950')] -[2023-10-16 05:36:47,472][05218] Updated weights for policy 0, policy_version 71772 (0.0009) -[2023-10-16 05:36:49,565][05219] Updated weights for policy 1, policy_version 71530 (0.0010) -[2023-10-16 05:36:49,925][05219] Updated weights for policy 1, policy_version 71540 (0.0010) -[2023-10-16 05:36:50,285][05219] Updated weights for policy 1, policy_version 71550 (0.0010) -[2023-10-16 05:36:51,176][05218] Updated weights for policy 0, policy_version 71782 (0.0009) -[2023-10-16 05:36:51,541][05218] Updated weights for policy 0, policy_version 71792 (0.0008) -[2023-10-16 05:36:51,919][05218] Updated weights for policy 0, policy_version 71802 (0.0007) -[2023-10-16 05:36:52,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 146800640. Throughput: 0: 1799.5, 1: 1780.5. Samples: 36707904. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:36:52,351][03835] Avg episode reward: [(0, '6.740'), (1, '7.080')] -[2023-10-16 05:36:54,142][05219] Updated weights for policy 1, policy_version 71560 (0.0008) -[2023-10-16 05:36:54,511][05219] Updated weights for policy 1, policy_version 71570 (0.0009) -[2023-10-16 05:36:54,885][05219] Updated weights for policy 1, policy_version 71580 (0.0009) -[2023-10-16 05:36:55,583][05218] Updated weights for policy 0, policy_version 71812 (0.0008) -[2023-10-16 05:36:55,966][05218] Updated weights for policy 0, policy_version 71822 (0.0009) -[2023-10-16 05:36:56,339][05218] Updated weights for policy 0, policy_version 71832 (0.0010) -[2023-10-16 05:36:57,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 146866176. Throughput: 0: 1808.5, 1: 1782.3. Samples: 36719468. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:36:57,351][03835] Avg episode reward: [(0, '6.900'), (1, '7.820')] -[2023-10-16 05:36:58,604][05219] Updated weights for policy 1, policy_version 71590 (0.0009) -[2023-10-16 05:36:58,973][05219] Updated weights for policy 1, policy_version 71600 (0.0009) -[2023-10-16 05:36:59,329][05219] Updated weights for policy 1, policy_version 71610 (0.0009) -[2023-10-16 05:36:59,919][05218] Updated weights for policy 0, policy_version 71842 (0.0009) -[2023-10-16 05:37:00,299][05218] Updated weights for policy 0, policy_version 71852 (0.0009) -[2023-10-16 05:37:00,680][05218] Updated weights for policy 0, policy_version 71862 (0.0009) -[2023-10-16 05:37:01,051][05218] Updated weights for policy 0, policy_version 71872 (0.0009) -[2023-10-16 05:37:02,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 146931712. Throughput: 0: 1803.9, 1: 1785.9. Samples: 36740826. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:37:02,351][03835] Avg episode reward: [(0, '7.130'), (1, '7.190')] -[2023-10-16 05:37:03,244][05219] Updated weights for policy 1, policy_version 71620 (0.0007) -[2023-10-16 05:37:03,640][05219] Updated weights for policy 1, policy_version 71630 (0.0007) -[2023-10-16 05:37:04,009][05219] Updated weights for policy 1, policy_version 71640 (0.0007) -[2023-10-16 05:37:04,787][05218] Updated weights for policy 0, policy_version 71882 (0.0007) -[2023-10-16 05:37:05,167][05218] Updated weights for policy 0, policy_version 71892 (0.0008) -[2023-10-16 05:37:05,543][05218] Updated weights for policy 0, policy_version 71902 (0.0011) -[2023-10-16 05:37:07,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 146997248. Throughput: 0: 1806.6, 1: 1792.2. Samples: 36763174. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:37:07,351][03835] Avg episode reward: [(0, '7.060'), (1, '7.560')] -[2023-10-16 05:37:07,791][05219] Updated weights for policy 1, policy_version 71650 (0.0009) -[2023-10-16 05:37:08,164][05219] Updated weights for policy 1, policy_version 71660 (0.0009) -[2023-10-16 05:37:08,532][05219] Updated weights for policy 1, policy_version 71670 (0.0008) -[2023-10-16 05:37:08,897][05219] Updated weights for policy 1, policy_version 71680 (0.0010) -[2023-10-16 05:37:09,402][05218] Updated weights for policy 0, policy_version 71912 (0.0010) -[2023-10-16 05:37:09,774][05218] Updated weights for policy 0, policy_version 71922 (0.0008) -[2023-10-16 05:37:10,145][05218] Updated weights for policy 0, policy_version 71932 (0.0009) -[2023-10-16 05:37:12,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 147062784. Throughput: 0: 1804.4, 1: 1789.9. Samples: 36773064. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:37:12,351][03835] Avg episode reward: [(0, '7.030'), (1, '7.300')] -[2023-10-16 05:37:12,644][05219] Updated weights for policy 1, policy_version 71690 (0.0007) -[2023-10-16 05:37:13,021][05219] Updated weights for policy 1, policy_version 71700 (0.0009) -[2023-10-16 05:37:13,382][05219] Updated weights for policy 1, policy_version 71710 (0.0010) -[2023-10-16 05:37:13,812][05218] Updated weights for policy 0, policy_version 71942 (0.0010) -[2023-10-16 05:37:14,186][05218] Updated weights for policy 0, policy_version 71952 (0.0008) -[2023-10-16 05:37:14,563][05218] Updated weights for policy 0, policy_version 71962 (0.0008) -[2023-10-16 05:37:16,955][05219] Updated weights for policy 1, policy_version 71720 (0.0008) -[2023-10-16 05:37:17,320][05219] Updated weights for policy 1, policy_version 71730 (0.0007) -[2023-10-16 05:37:17,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 147128320. Throughput: 0: 1804.4, 1: 1796.6. Samples: 36795544. Policy #0 lag: (min: 11.0, avg: 17.5, max: 43.0) -[2023-10-16 05:37:17,351][03835] Avg episode reward: [(0, '6.650'), (1, '8.090')] -[2023-10-16 05:37:17,690][05219] Updated weights for policy 1, policy_version 71740 (0.0007) -[2023-10-16 05:37:18,364][05218] Updated weights for policy 0, policy_version 71972 (0.0009) -[2023-10-16 05:37:18,732][05218] Updated weights for policy 0, policy_version 71982 (0.0009) -[2023-10-16 05:37:19,109][05218] Updated weights for policy 0, policy_version 71992 (0.0008) -[2023-10-16 05:37:21,463][05219] Updated weights for policy 1, policy_version 71750 (0.0008) -[2023-10-16 05:37:21,839][05219] Updated weights for policy 1, policy_version 71760 (0.0008) -[2023-10-16 05:37:22,199][05219] Updated weights for policy 1, policy_version 71770 (0.0008) -[2023-10-16 05:37:22,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 147193856. Throughput: 0: 1809.6, 1: 1807.4. Samples: 36817100. Policy #0 lag: (min: 11.0, avg: 17.5, max: 43.0) -[2023-10-16 05:37:22,351][03835] Avg episode reward: [(0, '7.150'), (1, '8.170')] -[2023-10-16 05:37:22,790][05218] Updated weights for policy 0, policy_version 72002 (0.0009) -[2023-10-16 05:37:23,169][05218] Updated weights for policy 0, policy_version 72012 (0.0008) -[2023-10-16 05:37:23,545][05218] Updated weights for policy 0, policy_version 72022 (0.0011) -[2023-10-16 05:37:23,923][05218] Updated weights for policy 0, policy_version 72032 (0.0009) -[2023-10-16 05:37:25,963][05219] Updated weights for policy 1, policy_version 71780 (0.0008) -[2023-10-16 05:37:26,329][05219] Updated weights for policy 1, policy_version 71790 (0.0008) -[2023-10-16 05:37:26,699][05219] Updated weights for policy 1, policy_version 71800 (0.0009) -[2023-10-16 05:37:27,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 147292160. Throughput: 0: 1804.6, 1: 1799.9. Samples: 36827872. Policy #0 lag: (min: 11.0, avg: 17.5, max: 43.0) -[2023-10-16 05:37:27,351][03835] Avg episode reward: [(0, '6.980'), (1, '8.030')] -[2023-10-16 05:37:27,750][05218] Updated weights for policy 0, policy_version 72042 (0.0008) -[2023-10-16 05:37:28,125][05218] Updated weights for policy 0, policy_version 72052 (0.0008) -[2023-10-16 05:37:28,503][05218] Updated weights for policy 0, policy_version 72062 (0.0007) -[2023-10-16 05:37:30,509][05219] Updated weights for policy 1, policy_version 71810 (0.0007) -[2023-10-16 05:37:30,882][05219] Updated weights for policy 1, policy_version 71820 (0.0009) -[2023-10-16 05:37:31,237][05219] Updated weights for policy 1, policy_version 71830 (0.0008) -[2023-10-16 05:37:31,602][05219] Updated weights for policy 1, policy_version 71840 (0.0010) -[2023-10-16 05:37:32,285][05218] Updated weights for policy 0, policy_version 72072 (0.0008) -[2023-10-16 05:37:32,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 147357696. Throughput: 0: 1795.1, 1: 1810.4. Samples: 36849246. Policy #0 lag: (min: 11.0, avg: 17.5, max: 43.0) -[2023-10-16 05:37:32,351][03835] Avg episode reward: [(0, '6.330'), (1, '7.610')] -[2023-10-16 05:37:32,660][05218] Updated weights for policy 0, policy_version 72082 (0.0008) -[2023-10-16 05:37:33,038][05218] Updated weights for policy 0, policy_version 72092 (0.0007) -[2023-10-16 05:37:35,421][05219] Updated weights for policy 1, policy_version 71850 (0.0008) -[2023-10-16 05:37:35,783][05219] Updated weights for policy 1, policy_version 71860 (0.0009) -[2023-10-16 05:37:36,158][05219] Updated weights for policy 1, policy_version 71870 (0.0007) -[2023-10-16 05:37:36,592][05218] Updated weights for policy 0, policy_version 72102 (0.0009) -[2023-10-16 05:37:36,965][05218] Updated weights for policy 0, policy_version 72112 (0.0011) -[2023-10-16 05:37:37,340][05218] Updated weights for policy 0, policy_version 72122 (0.0010) -[2023-10-16 05:37:37,351][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 147423232. Throughput: 0: 1806.8, 1: 1794.6. Samples: 36869966. Policy #0 lag: (min: 11.0, avg: 17.5, max: 43.0) -[2023-10-16 05:37:37,352][03835] Avg episode reward: [(0, '7.210'), (1, '7.380')] -[2023-10-16 05:37:37,362][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000071872_73596928.pth... -[2023-10-16 05:37:37,402][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000070208_71892992.pth -[2023-10-16 05:37:37,565][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000072128_73859072.pth... -[2023-10-16 05:37:37,594][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000070432_72122368.pth -[2023-10-16 05:37:40,025][05219] Updated weights for policy 1, policy_version 71880 (0.0008) -[2023-10-16 05:37:40,397][05219] Updated weights for policy 1, policy_version 71890 (0.0009) -[2023-10-16 05:37:40,763][05219] Updated weights for policy 1, policy_version 71900 (0.0009) -[2023-10-16 05:37:40,910][05218] Updated weights for policy 0, policy_version 72132 (0.0010) -[2023-10-16 05:37:41,279][05218] Updated weights for policy 0, policy_version 72142 (0.0008) -[2023-10-16 05:37:41,651][05218] Updated weights for policy 0, policy_version 72152 (0.0007) -[2023-10-16 05:37:42,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 147521536. Throughput: 0: 1799.8, 1: 1809.5. Samples: 36881888. Policy #0 lag: (min: 11.0, avg: 17.5, max: 43.0) -[2023-10-16 05:37:42,351][03835] Avg episode reward: [(0, '6.910'), (1, '6.560')] -[2023-10-16 05:37:44,587][05219] Updated weights for policy 1, policy_version 71910 (0.0008) -[2023-10-16 05:37:44,956][05219] Updated weights for policy 1, policy_version 71920 (0.0007) -[2023-10-16 05:37:45,318][05219] Updated weights for policy 1, policy_version 71930 (0.0008) -[2023-10-16 05:37:45,427][05218] Updated weights for policy 0, policy_version 72162 (0.0007) -[2023-10-16 05:37:45,802][05218] Updated weights for policy 0, policy_version 72172 (0.0008) -[2023-10-16 05:37:46,178][05218] Updated weights for policy 0, policy_version 72182 (0.0010) -[2023-10-16 05:37:46,552][05218] Updated weights for policy 0, policy_version 72192 (0.0009) -[2023-10-16 05:37:47,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 147587072. Throughput: 0: 1802.2, 1: 1786.6. Samples: 36902324. Policy #0 lag: (min: 11.0, avg: 17.5, max: 43.0) -[2023-10-16 05:37:47,351][03835] Avg episode reward: [(0, '6.440'), (1, '6.950')] -[2023-10-16 05:37:49,025][05219] Updated weights for policy 1, policy_version 71940 (0.0009) -[2023-10-16 05:37:49,414][05219] Updated weights for policy 1, policy_version 71950 (0.0010) -[2023-10-16 05:37:49,767][05219] Updated weights for policy 1, policy_version 71960 (0.0008) -[2023-10-16 05:37:50,322][05218] Updated weights for policy 0, policy_version 72202 (0.0009) -[2023-10-16 05:37:50,696][05218] Updated weights for policy 0, policy_version 72212 (0.0009) -[2023-10-16 05:37:51,061][05218] Updated weights for policy 0, policy_version 72222 (0.0007) -[2023-10-16 05:37:52,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 147652608. Throughput: 0: 1794.2, 1: 1788.4. Samples: 36924390. Policy #0 lag: (min: 11.0, avg: 17.5, max: 43.0) -[2023-10-16 05:37:52,351][03835] Avg episode reward: [(0, '6.520'), (1, '7.920')] -[2023-10-16 05:37:53,468][05219] Updated weights for policy 1, policy_version 71970 (0.0008) -[2023-10-16 05:37:53,837][05219] Updated weights for policy 1, policy_version 71980 (0.0007) -[2023-10-16 05:37:54,201][05219] Updated weights for policy 1, policy_version 71990 (0.0008) -[2023-10-16 05:37:54,569][05219] Updated weights for policy 1, policy_version 72000 (0.0007) -[2023-10-16 05:37:54,833][05218] Updated weights for policy 0, policy_version 72232 (0.0010) -[2023-10-16 05:37:55,213][05218] Updated weights for policy 0, policy_version 72242 (0.0008) -[2023-10-16 05:37:55,595][05218] Updated weights for policy 0, policy_version 72252 (0.0010) -[2023-10-16 05:37:57,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 147718144. Throughput: 0: 1807.1, 1: 1784.9. Samples: 36934704. Policy #0 lag: (min: 11.0, avg: 17.5, max: 43.0) -[2023-10-16 05:37:57,351][03835] Avg episode reward: [(0, '6.970'), (1, '7.500')] -[2023-10-16 05:37:58,378][05219] Updated weights for policy 1, policy_version 72010 (0.0010) -[2023-10-16 05:37:58,744][05219] Updated weights for policy 1, policy_version 72020 (0.0009) -[2023-10-16 05:37:59,110][05219] Updated weights for policy 1, policy_version 72030 (0.0007) -[2023-10-16 05:37:59,229][05218] Updated weights for policy 0, policy_version 72262 (0.0010) -[2023-10-16 05:37:59,601][05218] Updated weights for policy 0, policy_version 72272 (0.0008) -[2023-10-16 05:37:59,983][05218] Updated weights for policy 0, policy_version 72282 (0.0008) -[2023-10-16 05:38:02,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 147783680. Throughput: 0: 1793.8, 1: 1786.0. Samples: 36956634. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 05:38:02,351][03835] Avg episode reward: [(0, '7.030'), (1, '8.430')] -[2023-10-16 05:38:02,860][05219] Updated weights for policy 1, policy_version 72040 (0.0008) -[2023-10-16 05:38:03,229][05219] Updated weights for policy 1, policy_version 72050 (0.0009) -[2023-10-16 05:38:03,592][05219] Updated weights for policy 1, policy_version 72060 (0.0008) -[2023-10-16 05:38:03,960][05218] Updated weights for policy 0, policy_version 72292 (0.0008) -[2023-10-16 05:38:04,335][05218] Updated weights for policy 0, policy_version 72302 (0.0009) -[2023-10-16 05:38:04,706][05218] Updated weights for policy 0, policy_version 72312 (0.0010) -[2023-10-16 05:38:07,290][05219] Updated weights for policy 1, policy_version 72070 (0.0008) -[2023-10-16 05:38:07,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 147849216. Throughput: 0: 1787.1, 1: 1805.6. Samples: 36978774. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 05:38:07,351][03835] Avg episode reward: [(0, '6.400'), (1, '8.350')] -[2023-10-16 05:38:07,649][05219] Updated weights for policy 1, policy_version 72080 (0.0009) -[2023-10-16 05:38:08,023][05219] Updated weights for policy 1, policy_version 72090 (0.0009) -[2023-10-16 05:38:08,446][05218] Updated weights for policy 0, policy_version 72322 (0.0008) -[2023-10-16 05:38:08,815][05218] Updated weights for policy 0, policy_version 72332 (0.0008) -[2023-10-16 05:38:09,206][05218] Updated weights for policy 0, policy_version 72342 (0.0008) -[2023-10-16 05:38:09,577][05218] Updated weights for policy 0, policy_version 72352 (0.0010) -[2023-10-16 05:38:11,771][05219] Updated weights for policy 1, policy_version 72100 (0.0010) -[2023-10-16 05:38:12,125][05219] Updated weights for policy 1, policy_version 72110 (0.0008) -[2023-10-16 05:38:12,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 147914752. Throughput: 0: 1791.5, 1: 1784.9. Samples: 36988810. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 05:38:12,351][03835] Avg episode reward: [(0, '7.330'), (1, '8.220')] -[2023-10-16 05:38:12,497][05219] Updated weights for policy 1, policy_version 72120 (0.0008) -[2023-10-16 05:38:13,085][05218] Updated weights for policy 0, policy_version 72362 (0.0010) -[2023-10-16 05:38:13,463][05218] Updated weights for policy 0, policy_version 72372 (0.0010) -[2023-10-16 05:38:13,844][05218] Updated weights for policy 0, policy_version 72382 (0.0009) -[2023-10-16 05:38:16,286][05219] Updated weights for policy 1, policy_version 72130 (0.0008) -[2023-10-16 05:38:16,654][05219] Updated weights for policy 1, policy_version 72140 (0.0011) -[2023-10-16 05:38:17,018][05219] Updated weights for policy 1, policy_version 72150 (0.0010) -[2023-10-16 05:38:17,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 147980288. Throughput: 0: 1803.0, 1: 1803.3. Samples: 37011530. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 05:38:17,351][03835] Avg episode reward: [(0, '7.690'), (1, '7.330')] -[2023-10-16 05:38:17,380][05219] Updated weights for policy 1, policy_version 72160 (0.0008) -[2023-10-16 05:38:17,595][05218] Updated weights for policy 0, policy_version 72392 (0.0009) -[2023-10-16 05:38:17,979][05218] Updated weights for policy 0, policy_version 72402 (0.0008) -[2023-10-16 05:38:18,342][05218] Updated weights for policy 0, policy_version 72412 (0.0008) -[2023-10-16 05:38:21,057][05219] Updated weights for policy 1, policy_version 72170 (0.0008) -[2023-10-16 05:38:21,425][05219] Updated weights for policy 1, policy_version 72180 (0.0009) -[2023-10-16 05:38:21,805][05219] Updated weights for policy 1, policy_version 72190 (0.0008) -[2023-10-16 05:38:22,172][05218] Updated weights for policy 0, policy_version 72422 (0.0009) -[2023-10-16 05:38:22,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 148078592. Throughput: 0: 1806.7, 1: 1787.0. Samples: 37031684. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 05:38:22,351][03835] Avg episode reward: [(0, '7.520'), (1, '7.820')] -[2023-10-16 05:38:22,537][05218] Updated weights for policy 0, policy_version 72432 (0.0008) -[2023-10-16 05:38:22,911][05218] Updated weights for policy 0, policy_version 72442 (0.0008) -[2023-10-16 05:38:25,455][05219] Updated weights for policy 1, policy_version 72200 (0.0008) -[2023-10-16 05:38:25,833][05219] Updated weights for policy 1, policy_version 72210 (0.0009) -[2023-10-16 05:38:26,194][05219] Updated weights for policy 1, policy_version 72220 (0.0008) -[2023-10-16 05:38:26,659][05218] Updated weights for policy 0, policy_version 72452 (0.0009) -[2023-10-16 05:38:27,046][05218] Updated weights for policy 0, policy_version 72462 (0.0009) -[2023-10-16 05:38:27,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 148144128. Throughput: 0: 1784.5, 1: 1806.3. Samples: 37043476. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 05:38:27,351][03835] Avg episode reward: [(0, '7.670'), (1, '8.290')] -[2023-10-16 05:38:27,415][05218] Updated weights for policy 0, policy_version 72472 (0.0010) -[2023-10-16 05:38:30,068][05219] Updated weights for policy 1, policy_version 72230 (0.0008) -[2023-10-16 05:38:30,446][05219] Updated weights for policy 1, policy_version 72240 (0.0008) -[2023-10-16 05:38:30,815][05219] Updated weights for policy 1, policy_version 72250 (0.0009) -[2023-10-16 05:38:31,114][05218] Updated weights for policy 0, policy_version 72482 (0.0008) -[2023-10-16 05:38:31,494][05218] Updated weights for policy 0, policy_version 72492 (0.0009) -[2023-10-16 05:38:31,870][05218] Updated weights for policy 0, policy_version 72502 (0.0009) -[2023-10-16 05:38:32,248][05218] Updated weights for policy 0, policy_version 72512 (0.0009) -[2023-10-16 05:38:32,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.2). Total num frames: 148242432. Throughput: 0: 1803.2, 1: 1786.9. Samples: 37063880. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 05:38:32,351][03835] Avg episode reward: [(0, '8.180'), (1, '7.390')] -[2023-10-16 05:38:32,352][04766] Saving new best policy, reward=8.180! -[2023-10-16 05:38:34,402][05219] Updated weights for policy 1, policy_version 72260 (0.0008) -[2023-10-16 05:38:34,787][05219] Updated weights for policy 1, policy_version 72270 (0.0007) -[2023-10-16 05:38:35,151][05219] Updated weights for policy 1, policy_version 72280 (0.0009) -[2023-10-16 05:38:36,017][05218] Updated weights for policy 0, policy_version 72522 (0.0009) -[2023-10-16 05:38:36,393][05218] Updated weights for policy 0, policy_version 72532 (0.0009) -[2023-10-16 05:38:36,761][05218] Updated weights for policy 0, policy_version 72542 (0.0010) -[2023-10-16 05:38:37,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 148307968. Throughput: 0: 1781.0, 1: 1791.1. Samples: 37085132. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 05:38:37,351][03835] Avg episode reward: [(0, '7.290'), (1, '7.860')] -[2023-10-16 05:38:38,812][05219] Updated weights for policy 1, policy_version 72290 (0.0008) -[2023-10-16 05:38:39,182][05219] Updated weights for policy 1, policy_version 72300 (0.0008) -[2023-10-16 05:38:39,543][05219] Updated weights for policy 1, policy_version 72310 (0.0008) -[2023-10-16 05:38:39,905][05219] Updated weights for policy 1, policy_version 72320 (0.0008) -[2023-10-16 05:38:40,450][05218] Updated weights for policy 0, policy_version 72552 (0.0009) -[2023-10-16 05:38:40,815][05218] Updated weights for policy 0, policy_version 72562 (0.0011) -[2023-10-16 05:38:41,188][05218] Updated weights for policy 0, policy_version 72572 (0.0008) -[2023-10-16 05:38:42,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 148373504. Throughput: 0: 1800.8, 1: 1792.2. Samples: 37096386. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-16 05:38:42,351][03835] Avg episode reward: [(0, '7.430'), (1, '7.970')] -[2023-10-16 05:38:43,752][05219] Updated weights for policy 1, policy_version 72330 (0.0011) -[2023-10-16 05:38:44,112][05219] Updated weights for policy 1, policy_version 72340 (0.0009) -[2023-10-16 05:38:44,479][05219] Updated weights for policy 1, policy_version 72350 (0.0008) -[2023-10-16 05:38:45,046][05218] Updated weights for policy 0, policy_version 72582 (0.0008) -[2023-10-16 05:38:45,413][05218] Updated weights for policy 0, policy_version 72592 (0.0010) -[2023-10-16 05:38:45,793][05218] Updated weights for policy 0, policy_version 72602 (0.0011) -[2023-10-16 05:38:47,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 148439040. Throughput: 0: 1785.1, 1: 1793.0. Samples: 37117650. Policy #0 lag: (min: 0.0, avg: 22.8, max: 32.0) -[2023-10-16 05:38:47,351][03835] Avg episode reward: [(0, '7.650'), (1, '7.470')] -[2023-10-16 05:38:48,262][05219] Updated weights for policy 1, policy_version 72360 (0.0007) -[2023-10-16 05:38:48,628][05219] Updated weights for policy 1, policy_version 72370 (0.0008) -[2023-10-16 05:38:48,994][05219] Updated weights for policy 1, policy_version 72380 (0.0008) -[2023-10-16 05:38:49,487][05218] Updated weights for policy 0, policy_version 72612 (0.0009) -[2023-10-16 05:38:49,868][05218] Updated weights for policy 0, policy_version 72622 (0.0007) -[2023-10-16 05:38:50,242][05218] Updated weights for policy 0, policy_version 72632 (0.0008) -[2023-10-16 05:38:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 148504576. Throughput: 0: 1788.0, 1: 1798.7. Samples: 37140174. Policy #0 lag: (min: 0.0, avg: 22.8, max: 32.0) -[2023-10-16 05:38:52,352][03835] Avg episode reward: [(0, '6.740'), (1, '8.230')] -[2023-10-16 05:38:52,811][05219] Updated weights for policy 1, policy_version 72390 (0.0008) -[2023-10-16 05:38:53,193][05219] Updated weights for policy 1, policy_version 72400 (0.0008) -[2023-10-16 05:38:53,554][05219] Updated weights for policy 1, policy_version 72410 (0.0007) -[2023-10-16 05:38:53,953][05218] Updated weights for policy 0, policy_version 72642 (0.0008) -[2023-10-16 05:38:54,335][05218] Updated weights for policy 0, policy_version 72652 (0.0009) -[2023-10-16 05:38:54,707][05218] Updated weights for policy 0, policy_version 72662 (0.0009) -[2023-10-16 05:38:55,080][05218] Updated weights for policy 0, policy_version 72672 (0.0011) -[2023-10-16 05:38:57,167][05219] Updated weights for policy 1, policy_version 72420 (0.0008) -[2023-10-16 05:38:57,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 148570112. Throughput: 0: 1790.0, 1: 1796.9. Samples: 37150218. Policy #0 lag: (min: 0.0, avg: 22.8, max: 32.0) -[2023-10-16 05:38:57,351][03835] Avg episode reward: [(0, '7.220'), (1, '8.750')] -[2023-10-16 05:38:57,540][05219] Updated weights for policy 1, policy_version 72430 (0.0011) -[2023-10-16 05:38:57,902][05219] Updated weights for policy 1, policy_version 72440 (0.0008) -[2023-10-16 05:38:58,951][05218] Updated weights for policy 0, policy_version 72682 (0.0008) -[2023-10-16 05:38:59,326][05218] Updated weights for policy 0, policy_version 72692 (0.0008) -[2023-10-16 05:38:59,711][05218] Updated weights for policy 0, policy_version 72702 (0.0008) -[2023-10-16 05:39:01,726][05219] Updated weights for policy 1, policy_version 72450 (0.0009) -[2023-10-16 05:39:02,087][05219] Updated weights for policy 1, policy_version 72460 (0.0008) -[2023-10-16 05:39:02,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 148635648. Throughput: 0: 1778.4, 1: 1795.4. Samples: 37172352. Policy #0 lag: (min: 0.0, avg: 22.8, max: 32.0) -[2023-10-16 05:39:02,351][03835] Avg episode reward: [(0, '7.480'), (1, '8.220')] -[2023-10-16 05:39:02,462][05219] Updated weights for policy 1, policy_version 72470 (0.0009) -[2023-10-16 05:39:02,828][05219] Updated weights for policy 1, policy_version 72480 (0.0007) -[2023-10-16 05:39:03,471][05218] Updated weights for policy 0, policy_version 72712 (0.0010) -[2023-10-16 05:39:03,860][05218] Updated weights for policy 0, policy_version 72722 (0.0008) -[2023-10-16 05:39:04,225][05218] Updated weights for policy 0, policy_version 72732 (0.0009) -[2023-10-16 05:39:06,691][05219] Updated weights for policy 1, policy_version 72490 (0.0008) -[2023-10-16 05:39:07,053][05219] Updated weights for policy 1, policy_version 72500 (0.0007) -[2023-10-16 05:39:07,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 148701184. Throughput: 0: 1797.0, 1: 1803.5. Samples: 37193708. Policy #0 lag: (min: 0.0, avg: 22.8, max: 32.0) -[2023-10-16 05:39:07,352][03835] Avg episode reward: [(0, '6.900'), (1, '7.560')] -[2023-10-16 05:39:07,424][05219] Updated weights for policy 1, policy_version 72510 (0.0008) -[2023-10-16 05:39:07,975][05218] Updated weights for policy 0, policy_version 72742 (0.0008) -[2023-10-16 05:39:08,348][05218] Updated weights for policy 0, policy_version 72752 (0.0009) -[2023-10-16 05:39:08,726][05218] Updated weights for policy 0, policy_version 72762 (0.0008) -[2023-10-16 05:39:11,099][05219] Updated weights for policy 1, policy_version 72520 (0.0009) -[2023-10-16 05:39:11,452][05219] Updated weights for policy 1, policy_version 72530 (0.0011) -[2023-10-16 05:39:11,815][05219] Updated weights for policy 1, policy_version 72540 (0.0010) -[2023-10-16 05:39:12,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 148799488. Throughput: 0: 1792.6, 1: 1790.1. Samples: 37204700. Policy #0 lag: (min: 0.0, avg: 22.8, max: 32.0) -[2023-10-16 05:39:12,351][03835] Avg episode reward: [(0, '6.530'), (1, '8.310')] -[2023-10-16 05:39:12,363][05218] Updated weights for policy 0, policy_version 72772 (0.0008) -[2023-10-16 05:39:12,749][05218] Updated weights for policy 0, policy_version 72782 (0.0008) -[2023-10-16 05:39:13,117][05218] Updated weights for policy 0, policy_version 72792 (0.0008) -[2023-10-16 05:39:15,601][05219] Updated weights for policy 1, policy_version 72550 (0.0009) -[2023-10-16 05:39:15,967][05219] Updated weights for policy 1, policy_version 72560 (0.0010) -[2023-10-16 05:39:16,340][05219] Updated weights for policy 1, policy_version 72570 (0.0010) -[2023-10-16 05:39:16,770][05218] Updated weights for policy 0, policy_version 72802 (0.0008) -[2023-10-16 05:39:17,145][05218] Updated weights for policy 0, policy_version 72812 (0.0007) -[2023-10-16 05:39:17,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 148865024. Throughput: 0: 1798.7, 1: 1805.6. Samples: 37226076. Policy #0 lag: (min: 0.0, avg: 22.8, max: 32.0) -[2023-10-16 05:39:17,351][03835] Avg episode reward: [(0, '6.300'), (1, '8.670')] -[2023-10-16 05:39:17,525][05218] Updated weights for policy 0, policy_version 72822 (0.0007) -[2023-10-16 05:39:17,901][05218] Updated weights for policy 0, policy_version 72832 (0.0007) -[2023-10-16 05:39:20,219][05219] Updated weights for policy 1, policy_version 72580 (0.0009) -[2023-10-16 05:39:20,605][05219] Updated weights for policy 1, policy_version 72590 (0.0008) -[2023-10-16 05:39:20,963][05219] Updated weights for policy 1, policy_version 72600 (0.0007) -[2023-10-16 05:39:21,511][05218] Updated weights for policy 0, policy_version 72842 (0.0010) -[2023-10-16 05:39:21,888][05218] Updated weights for policy 0, policy_version 72852 (0.0009) -[2023-10-16 05:39:22,267][05218] Updated weights for policy 0, policy_version 72862 (0.0008) -[2023-10-16 05:39:22,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 148963328. Throughput: 0: 1795.1, 1: 1789.2. Samples: 37246428. Policy #0 lag: (min: 0.0, avg: 22.8, max: 32.0) -[2023-10-16 05:39:22,351][03835] Avg episode reward: [(0, '6.860'), (1, '7.520')] -[2023-10-16 05:39:24,698][05219] Updated weights for policy 1, policy_version 72610 (0.0008) -[2023-10-16 05:39:25,064][05219] Updated weights for policy 1, policy_version 72620 (0.0008) -[2023-10-16 05:39:25,436][05219] Updated weights for policy 1, policy_version 72630 (0.0008) -[2023-10-16 05:39:25,793][05219] Updated weights for policy 1, policy_version 72640 (0.0008) -[2023-10-16 05:39:25,971][05218] Updated weights for policy 0, policy_version 72872 (0.0010) -[2023-10-16 05:39:26,342][05218] Updated weights for policy 0, policy_version 72882 (0.0011) -[2023-10-16 05:39:26,716][05218] Updated weights for policy 0, policy_version 72892 (0.0008) -[2023-10-16 05:39:27,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 149028864. Throughput: 0: 1797.3, 1: 1806.9. Samples: 37258574. Policy #0 lag: (min: 0.0, avg: 22.8, max: 32.0) -[2023-10-16 05:39:27,351][03835] Avg episode reward: [(0, '7.630'), (1, '7.640')] -[2023-10-16 05:39:29,444][05219] Updated weights for policy 1, policy_version 72650 (0.0008) -[2023-10-16 05:39:29,803][05219] Updated weights for policy 1, policy_version 72660 (0.0007) -[2023-10-16 05:39:30,172][05219] Updated weights for policy 1, policy_version 72670 (0.0009) -[2023-10-16 05:39:30,517][05218] Updated weights for policy 0, policy_version 72902 (0.0011) -[2023-10-16 05:39:30,894][05218] Updated weights for policy 0, policy_version 72912 (0.0011) -[2023-10-16 05:39:31,274][05218] Updated weights for policy 0, policy_version 72922 (0.0009) -[2023-10-16 05:39:32,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 149094400. Throughput: 0: 1799.4, 1: 1787.4. Samples: 37279056. Policy #0 lag: (min: 26.0, avg: 29.8, max: 58.0) -[2023-10-16 05:39:32,351][03835] Avg episode reward: [(0, '7.200'), (1, '8.330')] -[2023-10-16 05:39:33,908][05219] Updated weights for policy 1, policy_version 72680 (0.0008) -[2023-10-16 05:39:34,263][05219] Updated weights for policy 1, policy_version 72690 (0.0008) -[2023-10-16 05:39:34,642][05219] Updated weights for policy 1, policy_version 72700 (0.0009) -[2023-10-16 05:39:35,038][05218] Updated weights for policy 0, policy_version 72932 (0.0010) -[2023-10-16 05:39:35,416][05218] Updated weights for policy 0, policy_version 72942 (0.0008) -[2023-10-16 05:39:35,788][05218] Updated weights for policy 0, policy_version 72952 (0.0007) -[2023-10-16 05:39:37,351][03835] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 149159936. Throughput: 0: 1793.8, 1: 1787.2. Samples: 37301318. Policy #0 lag: (min: 26.0, avg: 29.8, max: 58.0) -[2023-10-16 05:39:37,352][03835] Avg episode reward: [(0, '7.060'), (1, '6.810')] -[2023-10-16 05:39:37,363][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000072960_74711040.pth... -[2023-10-16 05:39:37,363][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000072704_74448896.pth... -[2023-10-16 05:39:37,398][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000071040_72744960.pth -[2023-10-16 05:39:37,402][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000071264_72974336.pth -[2023-10-16 05:39:38,414][05219] Updated weights for policy 1, policy_version 72710 (0.0008) -[2023-10-16 05:39:38,766][05219] Updated weights for policy 1, policy_version 72720 (0.0010) -[2023-10-16 05:39:39,131][05219] Updated weights for policy 1, policy_version 72730 (0.0009) -[2023-10-16 05:39:39,491][05218] Updated weights for policy 0, policy_version 72962 (0.0010) -[2023-10-16 05:39:39,859][05218] Updated weights for policy 0, policy_version 72972 (0.0008) -[2023-10-16 05:39:40,244][05218] Updated weights for policy 0, policy_version 72982 (0.0009) -[2023-10-16 05:39:40,613][05218] Updated weights for policy 0, policy_version 72992 (0.0011) -[2023-10-16 05:39:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 149225472. Throughput: 0: 1799.8, 1: 1785.8. Samples: 37311570. Policy #0 lag: (min: 26.0, avg: 29.8, max: 58.0) -[2023-10-16 05:39:42,351][03835] Avg episode reward: [(0, '7.440'), (1, '8.010')] -[2023-10-16 05:39:42,824][05219] Updated weights for policy 1, policy_version 72740 (0.0008) -[2023-10-16 05:39:43,187][05219] Updated weights for policy 1, policy_version 72750 (0.0009) -[2023-10-16 05:39:43,557][05219] Updated weights for policy 1, policy_version 72760 (0.0011) -[2023-10-16 05:39:44,297][05218] Updated weights for policy 0, policy_version 73002 (0.0009) -[2023-10-16 05:39:44,680][05218] Updated weights for policy 0, policy_version 73012 (0.0009) -[2023-10-16 05:39:45,044][05218] Updated weights for policy 0, policy_version 73022 (0.0009) -[2023-10-16 05:39:47,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 149291008. Throughput: 0: 1796.9, 1: 1793.2. Samples: 37333908. Policy #0 lag: (min: 26.0, avg: 29.8, max: 58.0) -[2023-10-16 05:39:47,351][03835] Avg episode reward: [(0, '6.780'), (1, '8.610')] -[2023-10-16 05:39:47,371][05219] Updated weights for policy 1, policy_version 72770 (0.0010) -[2023-10-16 05:39:47,733][05219] Updated weights for policy 1, policy_version 72780 (0.0008) -[2023-10-16 05:39:48,104][05219] Updated weights for policy 1, policy_version 72790 (0.0008) -[2023-10-16 05:39:48,472][05219] Updated weights for policy 1, policy_version 72800 (0.0007) -[2023-10-16 05:39:48,836][05218] Updated weights for policy 0, policy_version 73032 (0.0008) -[2023-10-16 05:39:49,216][05218] Updated weights for policy 0, policy_version 73042 (0.0009) -[2023-10-16 05:39:49,587][05218] Updated weights for policy 0, policy_version 73052 (0.0010) -[2023-10-16 05:39:52,245][05219] Updated weights for policy 1, policy_version 72810 (0.0007) -[2023-10-16 05:39:52,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 149356544. Throughput: 0: 1794.0, 1: 1807.4. Samples: 37355768. Policy #0 lag: (min: 26.0, avg: 29.8, max: 58.0) -[2023-10-16 05:39:52,351][03835] Avg episode reward: [(0, '6.430'), (1, '9.050')] -[2023-10-16 05:39:52,620][05219] Updated weights for policy 1, policy_version 72820 (0.0008) -[2023-10-16 05:39:52,987][05219] Updated weights for policy 1, policy_version 72830 (0.0008) -[2023-10-16 05:39:53,058][04891] Saving new best policy, reward=9.050! -[2023-10-16 05:39:53,422][05218] Updated weights for policy 0, policy_version 73062 (0.0009) -[2023-10-16 05:39:53,793][05218] Updated weights for policy 0, policy_version 73072 (0.0009) -[2023-10-16 05:39:54,168][05218] Updated weights for policy 0, policy_version 73082 (0.0008) -[2023-10-16 05:39:56,710][05219] Updated weights for policy 1, policy_version 72840 (0.0007) -[2023-10-16 05:39:57,079][05219] Updated weights for policy 1, policy_version 72850 (0.0010) -[2023-10-16 05:39:57,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 149422080. Throughput: 0: 1791.4, 1: 1789.2. Samples: 37365828. Policy #0 lag: (min: 26.0, avg: 29.8, max: 58.0) -[2023-10-16 05:39:57,351][03835] Avg episode reward: [(0, '6.670'), (1, '7.640')] -[2023-10-16 05:39:57,445][05219] Updated weights for policy 1, policy_version 72860 (0.0007) -[2023-10-16 05:39:57,861][05218] Updated weights for policy 0, policy_version 73092 (0.0009) -[2023-10-16 05:39:58,243][05218] Updated weights for policy 0, policy_version 73102 (0.0007) -[2023-10-16 05:39:58,624][05218] Updated weights for policy 0, policy_version 73112 (0.0007) -[2023-10-16 05:40:01,049][05219] Updated weights for policy 1, policy_version 72870 (0.0011) -[2023-10-16 05:40:01,414][05219] Updated weights for policy 1, policy_version 72880 (0.0008) -[2023-10-16 05:40:01,789][05219] Updated weights for policy 1, policy_version 72890 (0.0007) -[2023-10-16 05:40:02,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 149520384. Throughput: 0: 1787.3, 1: 1808.0. Samples: 37387862. Policy #0 lag: (min: 26.0, avg: 29.8, max: 58.0) -[2023-10-16 05:40:02,351][03835] Avg episode reward: [(0, '7.270'), (1, '8.160')] -[2023-10-16 05:40:02,401][05218] Updated weights for policy 0, policy_version 73122 (0.0007) -[2023-10-16 05:40:02,772][05218] Updated weights for policy 0, policy_version 73132 (0.0009) -[2023-10-16 05:40:03,149][05218] Updated weights for policy 0, policy_version 73142 (0.0010) -[2023-10-16 05:40:03,524][05218] Updated weights for policy 0, policy_version 73152 (0.0008) -[2023-10-16 05:40:05,728][05219] Updated weights for policy 1, policy_version 72900 (0.0008) -[2023-10-16 05:40:06,121][05219] Updated weights for policy 1, policy_version 72910 (0.0010) -[2023-10-16 05:40:06,488][05219] Updated weights for policy 1, policy_version 72920 (0.0008) -[2023-10-16 05:40:07,167][05218] Updated weights for policy 0, policy_version 73162 (0.0007) -[2023-10-16 05:40:07,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 149585920. Throughput: 0: 1808.5, 1: 1789.1. Samples: 37408320. Policy #0 lag: (min: 26.0, avg: 29.8, max: 58.0) -[2023-10-16 05:40:07,351][03835] Avg episode reward: [(0, '6.820'), (1, '7.880')] -[2023-10-16 05:40:07,547][05218] Updated weights for policy 0, policy_version 73172 (0.0007) -[2023-10-16 05:40:07,922][05218] Updated weights for policy 0, policy_version 73182 (0.0007) -[2023-10-16 05:40:10,445][05219] Updated weights for policy 1, policy_version 72930 (0.0008) -[2023-10-16 05:40:10,803][05219] Updated weights for policy 1, policy_version 72940 (0.0009) -[2023-10-16 05:40:11,175][05219] Updated weights for policy 1, policy_version 72950 (0.0008) -[2023-10-16 05:40:11,545][05219] Updated weights for policy 1, policy_version 72960 (0.0008) -[2023-10-16 05:40:11,731][05218] Updated weights for policy 0, policy_version 73192 (0.0008) -[2023-10-16 05:40:12,101][05218] Updated weights for policy 0, policy_version 73202 (0.0008) -[2023-10-16 05:40:12,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 149651456. Throughput: 0: 1786.7, 1: 1800.6. Samples: 37420002. Policy #0 lag: (min: 26.0, avg: 29.8, max: 58.0) -[2023-10-16 05:40:12,351][03835] Avg episode reward: [(0, '6.090'), (1, '6.800')] -[2023-10-16 05:40:12,472][05218] Updated weights for policy 0, policy_version 73212 (0.0008) -[2023-10-16 05:40:15,168][05219] Updated weights for policy 1, policy_version 72970 (0.0009) -[2023-10-16 05:40:15,532][05219] Updated weights for policy 1, policy_version 72980 (0.0009) -[2023-10-16 05:40:15,899][05219] Updated weights for policy 1, policy_version 72990 (0.0009) -[2023-10-16 05:40:16,158][05218] Updated weights for policy 0, policy_version 73222 (0.0008) -[2023-10-16 05:40:16,532][05218] Updated weights for policy 0, policy_version 73232 (0.0007) -[2023-10-16 05:40:16,915][05218] Updated weights for policy 0, policy_version 73242 (0.0008) -[2023-10-16 05:40:17,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 149749760. Throughput: 0: 1809.7, 1: 1788.4. Samples: 37440968. Policy #0 lag: (min: 10.0, avg: 16.0, max: 42.0) -[2023-10-16 05:40:17,351][03835] Avg episode reward: [(0, '6.880'), (1, '8.290')] -[2023-10-16 05:40:19,706][05219] Updated weights for policy 1, policy_version 73000 (0.0011) -[2023-10-16 05:40:20,068][05219] Updated weights for policy 1, policy_version 73010 (0.0011) -[2023-10-16 05:40:20,436][05219] Updated weights for policy 1, policy_version 73020 (0.0010) -[2023-10-16 05:40:20,840][05218] Updated weights for policy 0, policy_version 73252 (0.0010) -[2023-10-16 05:40:21,224][05218] Updated weights for policy 0, policy_version 73262 (0.0008) -[2023-10-16 05:40:21,592][05218] Updated weights for policy 0, policy_version 73272 (0.0010) -[2023-10-16 05:40:22,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 149815296. Throughput: 0: 1790.6, 1: 1787.5. Samples: 37462332. Policy #0 lag: (min: 10.0, avg: 16.0, max: 42.0) -[2023-10-16 05:40:22,351][03835] Avg episode reward: [(0, '6.610'), (1, '8.150')] -[2023-10-16 05:40:24,159][05219] Updated weights for policy 1, policy_version 73030 (0.0010) -[2023-10-16 05:40:24,517][05219] Updated weights for policy 1, policy_version 73040 (0.0010) -[2023-10-16 05:40:24,888][05219] Updated weights for policy 1, policy_version 73050 (0.0009) -[2023-10-16 05:40:25,224][05218] Updated weights for policy 0, policy_version 73282 (0.0009) -[2023-10-16 05:40:25,605][05218] Updated weights for policy 0, policy_version 73292 (0.0010) -[2023-10-16 05:40:25,976][05218] Updated weights for policy 0, policy_version 73302 (0.0008) -[2023-10-16 05:40:26,354][05218] Updated weights for policy 0, policy_version 73312 (0.0007) -[2023-10-16 05:40:27,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 149880832. Throughput: 0: 1811.1, 1: 1786.4. Samples: 37473454. Policy #0 lag: (min: 10.0, avg: 16.0, max: 42.0) -[2023-10-16 05:40:27,351][03835] Avg episode reward: [(0, '6.460'), (1, '7.030')] -[2023-10-16 05:40:28,715][05219] Updated weights for policy 1, policy_version 73060 (0.0007) -[2023-10-16 05:40:29,082][05219] Updated weights for policy 1, policy_version 73070 (0.0009) -[2023-10-16 05:40:29,454][05219] Updated weights for policy 1, policy_version 73080 (0.0009) -[2023-10-16 05:40:30,042][05218] Updated weights for policy 0, policy_version 73322 (0.0009) -[2023-10-16 05:40:30,421][05218] Updated weights for policy 0, policy_version 73332 (0.0010) -[2023-10-16 05:40:30,792][05218] Updated weights for policy 0, policy_version 73342 (0.0009) -[2023-10-16 05:40:32,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 149946368. Throughput: 0: 1790.3, 1: 1777.9. Samples: 37494478. Policy #0 lag: (min: 10.0, avg: 16.0, max: 42.0) -[2023-10-16 05:40:32,352][03835] Avg episode reward: [(0, '7.190'), (1, '7.940')] -[2023-10-16 05:40:33,338][05219] Updated weights for policy 1, policy_version 73090 (0.0008) -[2023-10-16 05:40:33,713][05219] Updated weights for policy 1, policy_version 73100 (0.0008) -[2023-10-16 05:40:34,073][05219] Updated weights for policy 1, policy_version 73110 (0.0008) -[2023-10-16 05:40:34,434][05219] Updated weights for policy 1, policy_version 73120 (0.0007) -[2023-10-16 05:40:34,631][05218] Updated weights for policy 0, policy_version 73352 (0.0008) -[2023-10-16 05:40:35,004][05218] Updated weights for policy 0, policy_version 73362 (0.0010) -[2023-10-16 05:40:35,382][05218] Updated weights for policy 0, policy_version 73372 (0.0008) -[2023-10-16 05:40:37,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 150011904. Throughput: 0: 1793.1, 1: 1782.2. Samples: 37516654. Policy #0 lag: (min: 10.0, avg: 16.0, max: 42.0) -[2023-10-16 05:40:37,351][03835] Avg episode reward: [(0, '6.040'), (1, '7.830')] -[2023-10-16 05:40:38,155][05219] Updated weights for policy 1, policy_version 73130 (0.0009) -[2023-10-16 05:40:38,522][05219] Updated weights for policy 1, policy_version 73140 (0.0007) -[2023-10-16 05:40:38,878][05219] Updated weights for policy 1, policy_version 73150 (0.0008) -[2023-10-16 05:40:39,049][05218] Updated weights for policy 0, policy_version 73382 (0.0008) -[2023-10-16 05:40:39,428][05218] Updated weights for policy 0, policy_version 73392 (0.0009) -[2023-10-16 05:40:39,798][05218] Updated weights for policy 0, policy_version 73402 (0.0009) -[2023-10-16 05:40:42,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 150077440. Throughput: 0: 1793.6, 1: 1779.1. Samples: 37526600. Policy #0 lag: (min: 10.0, avg: 16.0, max: 42.0) -[2023-10-16 05:40:42,351][03835] Avg episode reward: [(0, '7.080'), (1, '7.470')] -[2023-10-16 05:40:42,631][05219] Updated weights for policy 1, policy_version 73160 (0.0008) -[2023-10-16 05:40:43,000][05219] Updated weights for policy 1, policy_version 73170 (0.0007) -[2023-10-16 05:40:43,362][05219] Updated weights for policy 1, policy_version 73180 (0.0008) -[2023-10-16 05:40:43,527][05218] Updated weights for policy 0, policy_version 73412 (0.0008) -[2023-10-16 05:40:43,908][05218] Updated weights for policy 0, policy_version 73422 (0.0008) -[2023-10-16 05:40:44,274][05218] Updated weights for policy 0, policy_version 73432 (0.0009) -[2023-10-16 05:40:47,110][05219] Updated weights for policy 1, policy_version 73190 (0.0008) -[2023-10-16 05:40:47,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 150142976. Throughput: 0: 1795.6, 1: 1786.0. Samples: 37549032. Policy #0 lag: (min: 10.0, avg: 16.0, max: 42.0) -[2023-10-16 05:40:47,351][03835] Avg episode reward: [(0, '7.310'), (1, '8.200')] -[2023-10-16 05:40:47,467][05219] Updated weights for policy 1, policy_version 73200 (0.0008) -[2023-10-16 05:40:47,836][05219] Updated weights for policy 1, policy_version 73210 (0.0010) -[2023-10-16 05:40:47,986][05218] Updated weights for policy 0, policy_version 73442 (0.0010) -[2023-10-16 05:40:48,363][05218] Updated weights for policy 0, policy_version 73452 (0.0009) -[2023-10-16 05:40:48,743][05218] Updated weights for policy 0, policy_version 73462 (0.0008) -[2023-10-16 05:40:49,111][05218] Updated weights for policy 0, policy_version 73472 (0.0009) -[2023-10-16 05:40:51,669][05219] Updated weights for policy 1, policy_version 73220 (0.0008) -[2023-10-16 05:40:52,060][05219] Updated weights for policy 1, policy_version 73230 (0.0009) -[2023-10-16 05:40:52,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 150208512. Throughput: 0: 1807.5, 1: 1802.9. Samples: 37570788. Policy #0 lag: (min: 10.0, avg: 16.0, max: 42.0) -[2023-10-16 05:40:52,351][03835] Avg episode reward: [(0, '6.900'), (1, '7.570')] -[2023-10-16 05:40:52,430][05219] Updated weights for policy 1, policy_version 73240 (0.0011) -[2023-10-16 05:40:52,968][05218] Updated weights for policy 0, policy_version 73482 (0.0009) -[2023-10-16 05:40:53,348][05218] Updated weights for policy 0, policy_version 73492 (0.0009) -[2023-10-16 05:40:53,719][05218] Updated weights for policy 0, policy_version 73502 (0.0008) -[2023-10-16 05:40:56,226][05219] Updated weights for policy 1, policy_version 73250 (0.0007) -[2023-10-16 05:40:56,599][05219] Updated weights for policy 1, policy_version 73260 (0.0009) -[2023-10-16 05:40:56,970][05219] Updated weights for policy 1, policy_version 73270 (0.0007) -[2023-10-16 05:40:57,329][05219] Updated weights for policy 1, policy_version 73280 (0.0009) -[2023-10-16 05:40:57,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 150306816. Throughput: 0: 1794.4, 1: 1788.5. Samples: 37581230. Policy #0 lag: (min: 10.0, avg: 16.0, max: 42.0) -[2023-10-16 05:40:57,351][03835] Avg episode reward: [(0, '7.480'), (1, '7.390')] -[2023-10-16 05:40:57,482][05218] Updated weights for policy 0, policy_version 73512 (0.0008) -[2023-10-16 05:40:57,867][05218] Updated weights for policy 0, policy_version 73522 (0.0007) -[2023-10-16 05:40:58,239][05218] Updated weights for policy 0, policy_version 73532 (0.0009) -[2023-10-16 05:41:01,072][05219] Updated weights for policy 1, policy_version 73290 (0.0008) -[2023-10-16 05:41:01,427][05219] Updated weights for policy 1, policy_version 73300 (0.0007) -[2023-10-16 05:41:01,791][05219] Updated weights for policy 1, policy_version 73310 (0.0009) -[2023-10-16 05:41:01,944][05218] Updated weights for policy 0, policy_version 73542 (0.0011) -[2023-10-16 05:41:02,309][05218] Updated weights for policy 0, policy_version 73552 (0.0010) -[2023-10-16 05:41:02,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 150372352. Throughput: 0: 1802.4, 1: 1801.5. Samples: 37603142. Policy #0 lag: (min: 10.0, avg: 16.0, max: 42.0) -[2023-10-16 05:41:02,351][03835] Avg episode reward: [(0, '6.990'), (1, '7.630')] -[2023-10-16 05:41:02,680][05218] Updated weights for policy 0, policy_version 73562 (0.0008) -[2023-10-16 05:41:05,543][05219] Updated weights for policy 1, policy_version 73320 (0.0008) -[2023-10-16 05:41:05,913][05219] Updated weights for policy 1, policy_version 73330 (0.0009) -[2023-10-16 05:41:06,264][05218] Updated weights for policy 0, policy_version 73572 (0.0007) -[2023-10-16 05:41:06,281][05219] Updated weights for policy 1, policy_version 73340 (0.0007) -[2023-10-16 05:41:06,644][05218] Updated weights for policy 0, policy_version 73582 (0.0007) -[2023-10-16 05:41:07,013][05218] Updated weights for policy 0, policy_version 73592 (0.0009) -[2023-10-16 05:41:07,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 150470656. Throughput: 0: 1797.2, 1: 1777.6. Samples: 37623200. Policy #0 lag: (min: 1.0, avg: 12.7, max: 33.0) -[2023-10-16 05:41:07,351][03835] Avg episode reward: [(0, '6.610'), (1, '7.500')] -[2023-10-16 05:41:10,141][05219] Updated weights for policy 1, policy_version 73350 (0.0007) -[2023-10-16 05:41:10,519][05219] Updated weights for policy 1, policy_version 73360 (0.0009) -[2023-10-16 05:41:10,740][05218] Updated weights for policy 0, policy_version 73602 (0.0010) -[2023-10-16 05:41:10,879][05219] Updated weights for policy 1, policy_version 73370 (0.0008) -[2023-10-16 05:41:11,115][05218] Updated weights for policy 0, policy_version 73612 (0.0010) -[2023-10-16 05:41:11,488][05218] Updated weights for policy 0, policy_version 73622 (0.0009) -[2023-10-16 05:41:11,854][05218] Updated weights for policy 0, policy_version 73632 (0.0009) -[2023-10-16 05:41:12,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 150536192. Throughput: 0: 1801.4, 1: 1799.4. Samples: 37635492. Policy #0 lag: (min: 1.0, avg: 12.7, max: 33.0) -[2023-10-16 05:41:12,351][03835] Avg episode reward: [(0, '6.880'), (1, '7.660')] -[2023-10-16 05:41:14,586][05219] Updated weights for policy 1, policy_version 73380 (0.0008) -[2023-10-16 05:41:14,954][05219] Updated weights for policy 1, policy_version 73390 (0.0009) -[2023-10-16 05:41:15,322][05219] Updated weights for policy 1, policy_version 73400 (0.0007) -[2023-10-16 05:41:15,580][05218] Updated weights for policy 0, policy_version 73642 (0.0007) -[2023-10-16 05:41:15,953][05218] Updated weights for policy 0, policy_version 73652 (0.0008) -[2023-10-16 05:41:16,327][05218] Updated weights for policy 0, policy_version 73662 (0.0009) -[2023-10-16 05:41:17,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 150601728. Throughput: 0: 1798.0, 1: 1778.0. Samples: 37655400. Policy #0 lag: (min: 1.0, avg: 12.7, max: 33.0) -[2023-10-16 05:41:17,352][03835] Avg episode reward: [(0, '6.900'), (1, '8.150')] -[2023-10-16 05:41:19,309][05219] Updated weights for policy 1, policy_version 73410 (0.0009) -[2023-10-16 05:41:19,685][05219] Updated weights for policy 1, policy_version 73420 (0.0010) -[2023-10-16 05:41:20,048][05219] Updated weights for policy 1, policy_version 73430 (0.0007) -[2023-10-16 05:41:20,053][05218] Updated weights for policy 0, policy_version 73672 (0.0008) -[2023-10-16 05:41:20,412][05219] Updated weights for policy 1, policy_version 73440 (0.0007) -[2023-10-16 05:41:20,439][05218] Updated weights for policy 0, policy_version 73682 (0.0008) -[2023-10-16 05:41:20,818][05218] Updated weights for policy 0, policy_version 73692 (0.0010) -[2023-10-16 05:41:22,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 150667264. Throughput: 0: 1797.9, 1: 1779.7. Samples: 37677646. Policy #0 lag: (min: 1.0, avg: 12.7, max: 33.0) -[2023-10-16 05:41:22,351][03835] Avg episode reward: [(0, '7.300'), (1, '7.880')] -[2023-10-16 05:41:24,237][05219] Updated weights for policy 1, policy_version 73450 (0.0010) -[2023-10-16 05:41:24,454][05218] Updated weights for policy 0, policy_version 73702 (0.0008) -[2023-10-16 05:41:24,607][05219] Updated weights for policy 1, policy_version 73460 (0.0008) -[2023-10-16 05:41:24,835][05218] Updated weights for policy 0, policy_version 73712 (0.0008) -[2023-10-16 05:41:24,975][05219] Updated weights for policy 1, policy_version 73470 (0.0009) -[2023-10-16 05:41:25,204][05218] Updated weights for policy 0, policy_version 73722 (0.0007) -[2023-10-16 05:41:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 150732800. Throughput: 0: 1800.7, 1: 1774.3. Samples: 37687476. Policy #0 lag: (min: 1.0, avg: 12.7, max: 33.0) -[2023-10-16 05:41:27,352][03835] Avg episode reward: [(0, '7.210'), (1, '7.420')] -[2023-10-16 05:41:28,717][05219] Updated weights for policy 1, policy_version 73480 (0.0009) -[2023-10-16 05:41:29,010][05218] Updated weights for policy 0, policy_version 73732 (0.0010) -[2023-10-16 05:41:29,087][05219] Updated weights for policy 1, policy_version 73490 (0.0008) -[2023-10-16 05:41:29,396][05218] Updated weights for policy 0, policy_version 73742 (0.0010) -[2023-10-16 05:41:29,459][05219] Updated weights for policy 1, policy_version 73500 (0.0008) -[2023-10-16 05:41:29,777][05218] Updated weights for policy 0, policy_version 73752 (0.0009) -[2023-10-16 05:41:32,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 150798336. Throughput: 0: 1795.7, 1: 1775.6. Samples: 37709742. Policy #0 lag: (min: 1.0, avg: 12.7, max: 33.0) -[2023-10-16 05:41:32,351][03835] Avg episode reward: [(0, '6.980'), (1, '8.360')] -[2023-10-16 05:41:33,204][05219] Updated weights for policy 1, policy_version 73510 (0.0008) -[2023-10-16 05:41:33,579][05219] Updated weights for policy 1, policy_version 73520 (0.0009) -[2023-10-16 05:41:33,618][05218] Updated weights for policy 0, policy_version 73762 (0.0009) -[2023-10-16 05:41:33,944][05219] Updated weights for policy 1, policy_version 73530 (0.0009) -[2023-10-16 05:41:33,999][05218] Updated weights for policy 0, policy_version 73772 (0.0008) -[2023-10-16 05:41:34,360][05218] Updated weights for policy 0, policy_version 73782 (0.0007) -[2023-10-16 05:41:34,741][05218] Updated weights for policy 0, policy_version 73792 (0.0009) -[2023-10-16 05:41:37,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 150863872. Throughput: 0: 1796.9, 1: 1787.6. Samples: 37732092. Policy #0 lag: (min: 1.0, avg: 12.7, max: 33.0) -[2023-10-16 05:41:37,351][03835] Avg episode reward: [(0, '7.070'), (1, '8.060')] -[2023-10-16 05:41:37,360][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000073792_75563008.pth... -[2023-10-16 05:41:37,360][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000073536_75300864.pth... -[2023-10-16 05:41:37,396][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000071872_73596928.pth -[2023-10-16 05:41:37,402][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000072128_73859072.pth -[2023-10-16 05:41:37,716][05219] Updated weights for policy 1, policy_version 73540 (0.0008) -[2023-10-16 05:41:38,100][05219] Updated weights for policy 1, policy_version 73550 (0.0008) -[2023-10-16 05:41:38,397][05218] Updated weights for policy 0, policy_version 73802 (0.0009) -[2023-10-16 05:41:38,466][05219] Updated weights for policy 1, policy_version 73560 (0.0008) -[2023-10-16 05:41:38,769][05218] Updated weights for policy 0, policy_version 73812 (0.0008) -[2023-10-16 05:41:39,144][05218] Updated weights for policy 0, policy_version 73822 (0.0008) -[2023-10-16 05:41:42,177][05219] Updated weights for policy 1, policy_version 73570 (0.0008) -[2023-10-16 05:41:42,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 150929408. Throughput: 0: 1794.7, 1: 1772.3. Samples: 37741744. Policy #0 lag: (min: 1.0, avg: 12.7, max: 33.0) -[2023-10-16 05:41:42,351][03835] Avg episode reward: [(0, '6.600'), (1, '7.640')] -[2023-10-16 05:41:42,541][05219] Updated weights for policy 1, policy_version 73580 (0.0008) -[2023-10-16 05:41:42,895][05218] Updated weights for policy 0, policy_version 73832 (0.0009) -[2023-10-16 05:41:42,903][05219] Updated weights for policy 1, policy_version 73590 (0.0007) -[2023-10-16 05:41:43,267][05218] Updated weights for policy 0, policy_version 73842 (0.0009) -[2023-10-16 05:41:43,273][05219] Updated weights for policy 1, policy_version 73600 (0.0007) -[2023-10-16 05:41:43,650][05218] Updated weights for policy 0, policy_version 73852 (0.0009) -[2023-10-16 05:41:47,058][05219] Updated weights for policy 1, policy_version 73610 (0.0008) -[2023-10-16 05:41:47,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 150994944. Throughput: 0: 1794.7, 1: 1790.0. Samples: 37764452. Policy #0 lag: (min: 1.0, avg: 12.7, max: 33.0) -[2023-10-16 05:41:47,351][03835] Avg episode reward: [(0, '5.980'), (1, '7.360')] -[2023-10-16 05:41:47,425][05219] Updated weights for policy 1, policy_version 73620 (0.0008) -[2023-10-16 05:41:47,425][05218] Updated weights for policy 0, policy_version 73862 (0.0010) -[2023-10-16 05:41:47,789][05219] Updated weights for policy 1, policy_version 73630 (0.0007) -[2023-10-16 05:41:47,791][05218] Updated weights for policy 0, policy_version 73872 (0.0008) -[2023-10-16 05:41:48,168][05218] Updated weights for policy 0, policy_version 73882 (0.0007) -[2023-10-16 05:41:51,467][05219] Updated weights for policy 1, policy_version 73640 (0.0009) -[2023-10-16 05:41:51,807][05218] Updated weights for policy 0, policy_version 73892 (0.0008) -[2023-10-16 05:41:51,835][05219] Updated weights for policy 1, policy_version 73650 (0.0007) -[2023-10-16 05:41:52,185][05218] Updated weights for policy 0, policy_version 73902 (0.0009) -[2023-10-16 05:41:52,204][05219] Updated weights for policy 1, policy_version 73660 (0.0007) -[2023-10-16 05:41:52,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 151093248. Throughput: 0: 1803.9, 1: 1787.3. Samples: 37784802. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-16 05:41:52,351][03835] Avg episode reward: [(0, '6.440'), (1, '7.100')] -[2023-10-16 05:41:52,557][05218] Updated weights for policy 0, policy_version 73912 (0.0009) -[2023-10-16 05:41:55,855][05219] Updated weights for policy 1, policy_version 73670 (0.0008) -[2023-10-16 05:41:56,222][05219] Updated weights for policy 1, policy_version 73680 (0.0008) -[2023-10-16 05:41:56,301][05218] Updated weights for policy 0, policy_version 73922 (0.0008) -[2023-10-16 05:41:56,589][05219] Updated weights for policy 1, policy_version 73690 (0.0008) -[2023-10-16 05:41:56,678][05218] Updated weights for policy 0, policy_version 73932 (0.0008) -[2023-10-16 05:41:57,049][05218] Updated weights for policy 0, policy_version 73942 (0.0007) -[2023-10-16 05:41:57,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 151158784. Throughput: 0: 1789.7, 1: 1792.4. Samples: 37796684. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-16 05:41:57,351][03835] Avg episode reward: [(0, '7.100'), (1, '7.170')] -[2023-10-16 05:41:57,413][05218] Updated weights for policy 0, policy_version 73952 (0.0009) -[2023-10-16 05:42:00,355][05219] Updated weights for policy 1, policy_version 73700 (0.0009) -[2023-10-16 05:42:00,719][05219] Updated weights for policy 1, policy_version 73710 (0.0008) -[2023-10-16 05:42:01,089][05219] Updated weights for policy 1, policy_version 73720 (0.0008) -[2023-10-16 05:42:01,161][05218] Updated weights for policy 0, policy_version 73962 (0.0010) -[2023-10-16 05:42:01,536][05218] Updated weights for policy 0, policy_version 73972 (0.0010) -[2023-10-16 05:42:01,918][05218] Updated weights for policy 0, policy_version 73982 (0.0011) -[2023-10-16 05:42:02,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 151257088. Throughput: 0: 1804.3, 1: 1796.0. Samples: 37817412. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-16 05:42:02,351][03835] Avg episode reward: [(0, '7.340'), (1, '8.080')] -[2023-10-16 05:42:04,848][05219] Updated weights for policy 1, policy_version 73730 (0.0008) -[2023-10-16 05:42:05,218][05219] Updated weights for policy 1, policy_version 73740 (0.0007) -[2023-10-16 05:42:05,588][05219] Updated weights for policy 1, policy_version 73750 (0.0009) -[2023-10-16 05:42:05,735][05218] Updated weights for policy 0, policy_version 73992 (0.0008) -[2023-10-16 05:42:05,950][05219] Updated weights for policy 1, policy_version 73760 (0.0008) -[2023-10-16 05:42:06,109][05218] Updated weights for policy 0, policy_version 74002 (0.0008) -[2023-10-16 05:42:06,483][05218] Updated weights for policy 0, policy_version 74012 (0.0007) -[2023-10-16 05:42:07,351][03835] Fps is (10 sec: 16383.4, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 151322624. Throughput: 0: 1787.5, 1: 1792.3. Samples: 37838736. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-16 05:42:07,352][03835] Avg episode reward: [(0, '7.340'), (1, '6.730')] -[2023-10-16 05:42:09,633][05219] Updated weights for policy 1, policy_version 73770 (0.0010) -[2023-10-16 05:42:09,998][05219] Updated weights for policy 1, policy_version 73780 (0.0008) -[2023-10-16 05:42:10,227][05218] Updated weights for policy 0, policy_version 74022 (0.0009) -[2023-10-16 05:42:10,372][05219] Updated weights for policy 1, policy_version 73790 (0.0009) -[2023-10-16 05:42:10,590][05218] Updated weights for policy 0, policy_version 74032 (0.0009) -[2023-10-16 05:42:10,973][05218] Updated weights for policy 0, policy_version 74042 (0.0009) -[2023-10-16 05:42:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 151388160. Throughput: 0: 1808.5, 1: 1802.7. Samples: 37849980. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-16 05:42:12,351][03835] Avg episode reward: [(0, '6.960'), (1, '7.430')] -[2023-10-16 05:42:14,232][05219] Updated weights for policy 1, policy_version 73800 (0.0008) -[2023-10-16 05:42:14,586][05218] Updated weights for policy 0, policy_version 74052 (0.0009) -[2023-10-16 05:42:14,596][05219] Updated weights for policy 1, policy_version 73810 (0.0007) -[2023-10-16 05:42:14,966][05219] Updated weights for policy 1, policy_version 73820 (0.0007) -[2023-10-16 05:42:14,966][05218] Updated weights for policy 0, policy_version 74062 (0.0009) -[2023-10-16 05:42:15,331][05218] Updated weights for policy 0, policy_version 74072 (0.0008) -[2023-10-16 05:42:17,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 151453696. Throughput: 0: 1789.9, 1: 1787.0. Samples: 37870702. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-16 05:42:17,351][03835] Avg episode reward: [(0, '7.310'), (1, '8.460')] -[2023-10-16 05:42:18,666][05219] Updated weights for policy 1, policy_version 73830 (0.0010) -[2023-10-16 05:42:18,993][05218] Updated weights for policy 0, policy_version 74082 (0.0010) -[2023-10-16 05:42:19,034][05219] Updated weights for policy 1, policy_version 73840 (0.0009) -[2023-10-16 05:42:19,359][05218] Updated weights for policy 0, policy_version 74092 (0.0008) -[2023-10-16 05:42:19,406][05219] Updated weights for policy 1, policy_version 73850 (0.0008) -[2023-10-16 05:42:19,739][05218] Updated weights for policy 0, policy_version 74102 (0.0010) -[2023-10-16 05:42:20,111][05218] Updated weights for policy 0, policy_version 74112 (0.0007) -[2023-10-16 05:42:22,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 151519232. Throughput: 0: 1792.3, 1: 1788.7. Samples: 37893238. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-16 05:42:22,351][03835] Avg episode reward: [(0, '6.120'), (1, '7.410')] -[2023-10-16 05:42:23,219][05219] Updated weights for policy 1, policy_version 73860 (0.0008) -[2023-10-16 05:42:23,601][05219] Updated weights for policy 1, policy_version 73870 (0.0008) -[2023-10-16 05:42:23,862][05218] Updated weights for policy 0, policy_version 74122 (0.0007) -[2023-10-16 05:42:23,964][05219] Updated weights for policy 1, policy_version 73880 (0.0008) -[2023-10-16 05:42:24,234][05218] Updated weights for policy 0, policy_version 74132 (0.0009) -[2023-10-16 05:42:24,606][05218] Updated weights for policy 0, policy_version 74142 (0.0008) -[2023-10-16 05:42:27,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 151584768. Throughput: 0: 1797.6, 1: 1787.1. Samples: 37903052. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-16 05:42:27,351][03835] Avg episode reward: [(0, '6.680'), (1, '7.860')] -[2023-10-16 05:42:27,666][05219] Updated weights for policy 1, policy_version 73890 (0.0008) -[2023-10-16 05:42:28,040][05219] Updated weights for policy 1, policy_version 73900 (0.0011) -[2023-10-16 05:42:28,310][05218] Updated weights for policy 0, policy_version 74152 (0.0008) -[2023-10-16 05:42:28,406][05219] Updated weights for policy 1, policy_version 73910 (0.0008) -[2023-10-16 05:42:28,684][05218] Updated weights for policy 0, policy_version 74162 (0.0009) -[2023-10-16 05:42:28,769][05219] Updated weights for policy 1, policy_version 73920 (0.0008) -[2023-10-16 05:42:29,058][05218] Updated weights for policy 0, policy_version 74172 (0.0009) -[2023-10-16 05:42:32,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 151650304. Throughput: 0: 1796.7, 1: 1782.4. Samples: 37925512. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-16 05:42:32,351][03835] Avg episode reward: [(0, '6.930'), (1, '8.650')] -[2023-10-16 05:42:32,680][05219] Updated weights for policy 1, policy_version 73930 (0.0008) -[2023-10-16 05:42:32,757][05218] Updated weights for policy 0, policy_version 74182 (0.0009) -[2023-10-16 05:42:33,058][05219] Updated weights for policy 1, policy_version 73940 (0.0009) -[2023-10-16 05:42:33,137][05218] Updated weights for policy 0, policy_version 74192 (0.0007) -[2023-10-16 05:42:33,419][05219] Updated weights for policy 1, policy_version 73950 (0.0009) -[2023-10-16 05:42:33,501][05218] Updated weights for policy 0, policy_version 74202 (0.0008) -[2023-10-16 05:42:37,227][05218] Updated weights for policy 0, policy_version 74212 (0.0010) -[2023-10-16 05:42:37,310][05219] Updated weights for policy 1, policy_version 73960 (0.0007) -[2023-10-16 05:42:37,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 151715840. Throughput: 0: 1811.3, 1: 1806.4. Samples: 37947598. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-10-16 05:42:37,351][03835] Avg episode reward: [(0, '7.110'), (1, '7.630')] -[2023-10-16 05:42:37,605][05218] Updated weights for policy 0, policy_version 74222 (0.0008) -[2023-10-16 05:42:37,675][05219] Updated weights for policy 1, policy_version 73970 (0.0008) -[2023-10-16 05:42:37,986][05218] Updated weights for policy 0, policy_version 74232 (0.0009) -[2023-10-16 05:42:38,041][05219] Updated weights for policy 1, policy_version 73980 (0.0008) -[2023-10-16 05:42:41,927][05219] Updated weights for policy 1, policy_version 73990 (0.0008) -[2023-10-16 05:42:41,953][05218] Updated weights for policy 0, policy_version 74242 (0.0007) -[2023-10-16 05:42:42,292][05219] Updated weights for policy 1, policy_version 74000 (0.0008) -[2023-10-16 05:42:42,320][05218] Updated weights for policy 0, policy_version 74252 (0.0007) -[2023-10-16 05:42:42,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 151781376. Throughput: 0: 1796.9, 1: 1781.0. Samples: 37957692. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-16 05:42:42,351][03835] Avg episode reward: [(0, '7.100'), (1, '7.910')] -[2023-10-16 05:42:42,661][05219] Updated weights for policy 1, policy_version 74010 (0.0008) -[2023-10-16 05:42:42,697][05218] Updated weights for policy 0, policy_version 74262 (0.0007) -[2023-10-16 05:42:43,069][05218] Updated weights for policy 0, policy_version 74272 (0.0009) -[2023-10-16 05:42:46,431][05219] Updated weights for policy 1, policy_version 74020 (0.0009) -[2023-10-16 05:42:46,787][05219] Updated weights for policy 1, policy_version 74030 (0.0008) -[2023-10-16 05:42:46,848][05218] Updated weights for policy 0, policy_version 74282 (0.0008) -[2023-10-16 05:42:47,148][05219] Updated weights for policy 1, policy_version 74040 (0.0008) -[2023-10-16 05:42:47,218][05218] Updated weights for policy 0, policy_version 74292 (0.0008) -[2023-10-16 05:42:47,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 151846912. Throughput: 0: 1809.9, 1: 1802.8. Samples: 37979984. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-16 05:42:47,351][03835] Avg episode reward: [(0, '7.720'), (1, '8.150')] -[2023-10-16 05:42:47,601][05218] Updated weights for policy 0, policy_version 74302 (0.0007) -[2023-10-16 05:42:50,951][05219] Updated weights for policy 1, policy_version 74050 (0.0008) -[2023-10-16 05:42:51,315][05219] Updated weights for policy 1, policy_version 74060 (0.0008) -[2023-10-16 05:42:51,355][05218] Updated weights for policy 0, policy_version 74312 (0.0008) -[2023-10-16 05:42:51,674][05219] Updated weights for policy 1, policy_version 74070 (0.0008) -[2023-10-16 05:42:51,734][05218] Updated weights for policy 0, policy_version 74322 (0.0008) -[2023-10-16 05:42:52,038][05219] Updated weights for policy 1, policy_version 74080 (0.0008) -[2023-10-16 05:42:52,106][05218] Updated weights for policy 0, policy_version 74332 (0.0007) -[2023-10-16 05:42:52,350][03835] Fps is (10 sec: 19660.6, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 151977984. Throughput: 0: 1791.6, 1: 1773.6. Samples: 37999172. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-16 05:42:52,351][03835] Avg episode reward: [(0, '8.270'), (1, '7.500')] -[2023-10-16 05:42:52,362][04766] Saving new best policy, reward=8.270! -[2023-10-16 05:42:55,792][05219] Updated weights for policy 1, policy_version 74090 (0.0007) -[2023-10-16 05:42:55,798][05218] Updated weights for policy 0, policy_version 74342 (0.0009) -[2023-10-16 05:42:56,159][05219] Updated weights for policy 1, policy_version 74100 (0.0009) -[2023-10-16 05:42:56,166][05218] Updated weights for policy 0, policy_version 74352 (0.0009) -[2023-10-16 05:42:56,530][05219] Updated weights for policy 1, policy_version 74110 (0.0008) -[2023-10-16 05:42:56,549][05218] Updated weights for policy 0, policy_version 74362 (0.0009) -[2023-10-16 05:42:57,350][03835] Fps is (10 sec: 19660.5, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 152043520. Throughput: 0: 1799.9, 1: 1797.9. Samples: 38011886. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-16 05:42:57,351][03835] Avg episode reward: [(0, '6.950'), (1, '7.400')] -[2023-10-16 05:43:00,182][05219] Updated weights for policy 1, policy_version 74120 (0.0009) -[2023-10-16 05:43:00,255][05218] Updated weights for policy 0, policy_version 74372 (0.0009) -[2023-10-16 05:43:00,550][05219] Updated weights for policy 1, policy_version 74130 (0.0008) -[2023-10-16 05:43:00,628][05218] Updated weights for policy 0, policy_version 74382 (0.0009) -[2023-10-16 05:43:00,908][05219] Updated weights for policy 1, policy_version 74140 (0.0009) -[2023-10-16 05:43:00,991][05218] Updated weights for policy 0, policy_version 74392 (0.0009) -[2023-10-16 05:43:02,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 152109056. Throughput: 0: 1790.8, 1: 1779.3. Samples: 38031358. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-16 05:43:02,351][03835] Avg episode reward: [(0, '6.800'), (1, '7.840')] -[2023-10-16 05:43:04,715][05219] Updated weights for policy 1, policy_version 74150 (0.0008) -[2023-10-16 05:43:04,853][05218] Updated weights for policy 0, policy_version 74402 (0.0009) -[2023-10-16 05:43:05,089][05219] Updated weights for policy 1, policy_version 74160 (0.0007) -[2023-10-16 05:43:05,226][05218] Updated weights for policy 0, policy_version 74412 (0.0007) -[2023-10-16 05:43:05,449][05219] Updated weights for policy 1, policy_version 74170 (0.0008) -[2023-10-16 05:43:05,599][05218] Updated weights for policy 0, policy_version 74422 (0.0007) -[2023-10-16 05:43:05,977][05218] Updated weights for policy 0, policy_version 74432 (0.0009) -[2023-10-16 05:43:07,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 152174592. Throughput: 0: 1778.5, 1: 1784.2. Samples: 38053560. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-16 05:43:07,351][03835] Avg episode reward: [(0, '6.500'), (1, '7.370')] -[2023-10-16 05:43:09,236][05219] Updated weights for policy 1, policy_version 74180 (0.0009) -[2023-10-16 05:43:09,627][05219] Updated weights for policy 1, policy_version 74190 (0.0009) -[2023-10-16 05:43:09,808][05218] Updated weights for policy 0, policy_version 74442 (0.0009) -[2023-10-16 05:43:09,985][05219] Updated weights for policy 1, policy_version 74200 (0.0008) -[2023-10-16 05:43:10,178][05218] Updated weights for policy 0, policy_version 74452 (0.0009) -[2023-10-16 05:43:10,548][05218] Updated weights for policy 0, policy_version 74462 (0.0009) -[2023-10-16 05:43:12,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 152240128. Throughput: 0: 1784.6, 1: 1790.5. Samples: 38063932. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-16 05:43:12,351][03835] Avg episode reward: [(0, '7.200'), (1, '7.330')] -[2023-10-16 05:43:13,744][05219] Updated weights for policy 1, policy_version 74210 (0.0007) -[2023-10-16 05:43:14,115][05219] Updated weights for policy 1, policy_version 74220 (0.0008) -[2023-10-16 05:43:14,258][05218] Updated weights for policy 0, policy_version 74472 (0.0008) -[2023-10-16 05:43:14,487][05219] Updated weights for policy 1, policy_version 74230 (0.0009) -[2023-10-16 05:43:14,629][05218] Updated weights for policy 0, policy_version 74482 (0.0009) -[2023-10-16 05:43:14,851][05219] Updated weights for policy 1, policy_version 74240 (0.0009) -[2023-10-16 05:43:14,999][05218] Updated weights for policy 0, policy_version 74492 (0.0007) -[2023-10-16 05:43:17,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 152305664. Throughput: 0: 1776.7, 1: 1786.0. Samples: 38085834. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-16 05:43:17,351][03835] Avg episode reward: [(0, '6.980'), (1, '7.720')] -[2023-10-16 05:43:18,488][05219] Updated weights for policy 1, policy_version 74250 (0.0008) -[2023-10-16 05:43:18,615][05218] Updated weights for policy 0, policy_version 74502 (0.0007) -[2023-10-16 05:43:18,856][05219] Updated weights for policy 1, policy_version 74260 (0.0007) -[2023-10-16 05:43:18,988][05218] Updated weights for policy 0, policy_version 74512 (0.0008) -[2023-10-16 05:43:19,213][05219] Updated weights for policy 1, policy_version 74270 (0.0007) -[2023-10-16 05:43:19,358][05218] Updated weights for policy 0, policy_version 74522 (0.0008) -[2023-10-16 05:43:22,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 152371200. Throughput: 0: 1781.2, 1: 1791.4. Samples: 38108366. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-16 05:43:22,351][03835] Avg episode reward: [(0, '7.490'), (1, '7.880')] -[2023-10-16 05:43:22,981][05219] Updated weights for policy 1, policy_version 74280 (0.0007) -[2023-10-16 05:43:23,198][05218] Updated weights for policy 0, policy_version 74532 (0.0008) -[2023-10-16 05:43:23,341][05219] Updated weights for policy 1, policy_version 74290 (0.0008) -[2023-10-16 05:43:23,573][05218] Updated weights for policy 0, policy_version 74542 (0.0009) -[2023-10-16 05:43:23,704][05219] Updated weights for policy 1, policy_version 74300 (0.0007) -[2023-10-16 05:43:23,944][05218] Updated weights for policy 0, policy_version 74552 (0.0010) -[2023-10-16 05:43:27,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 152436736. Throughput: 0: 1777.9, 1: 1788.7. Samples: 38118188. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-16 05:43:27,351][03835] Avg episode reward: [(0, '8.070'), (1, '7.240')] -[2023-10-16 05:43:27,569][05219] Updated weights for policy 1, policy_version 74310 (0.0008) -[2023-10-16 05:43:27,622][05218] Updated weights for policy 0, policy_version 74562 (0.0009) -[2023-10-16 05:43:27,932][05219] Updated weights for policy 1, policy_version 74320 (0.0009) -[2023-10-16 05:43:27,988][05218] Updated weights for policy 0, policy_version 74572 (0.0007) -[2023-10-16 05:43:28,288][05219] Updated weights for policy 1, policy_version 74330 (0.0009) -[2023-10-16 05:43:28,368][05218] Updated weights for policy 0, policy_version 74582 (0.0010) -[2023-10-16 05:43:28,738][05218] Updated weights for policy 0, policy_version 74592 (0.0007) -[2023-10-16 05:43:31,969][05219] Updated weights for policy 1, policy_version 74340 (0.0007) -[2023-10-16 05:43:32,327][05219] Updated weights for policy 1, policy_version 74350 (0.0007) -[2023-10-16 05:43:32,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 152502272. Throughput: 0: 1777.7, 1: 1784.8. Samples: 38140300. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) -[2023-10-16 05:43:32,351][03835] Avg episode reward: [(0, '7.030'), (1, '8.160')] -[2023-10-16 05:43:32,520][05218] Updated weights for policy 0, policy_version 74602 (0.0007) -[2023-10-16 05:43:32,699][05219] Updated weights for policy 1, policy_version 74360 (0.0008) -[2023-10-16 05:43:32,893][05218] Updated weights for policy 0, policy_version 74612 (0.0007) -[2023-10-16 05:43:33,265][05218] Updated weights for policy 0, policy_version 74622 (0.0007) -[2023-10-16 05:43:36,481][05219] Updated weights for policy 1, policy_version 74370 (0.0008) -[2023-10-16 05:43:36,852][05219] Updated weights for policy 1, policy_version 74380 (0.0008) -[2023-10-16 05:43:37,032][05218] Updated weights for policy 0, policy_version 74632 (0.0009) -[2023-10-16 05:43:37,226][05219] Updated weights for policy 1, policy_version 74390 (0.0008) -[2023-10-16 05:43:37,351][03835] Fps is (10 sec: 13106.6, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 152567808. Throughput: 0: 1798.3, 1: 1796.5. Samples: 38160938. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) -[2023-10-16 05:43:37,352][03835] Avg episode reward: [(0, '6.990'), (1, '8.970')] -[2023-10-16 05:43:37,404][05218] Updated weights for policy 0, policy_version 74642 (0.0008) -[2023-10-16 05:43:37,583][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000074400_76185600.pth... -[2023-10-16 05:43:37,588][05219] Updated weights for policy 1, policy_version 74400 (0.0008) -[2023-10-16 05:43:37,616][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000072704_74448896.pth -[2023-10-16 05:43:37,782][05218] Updated weights for policy 0, policy_version 74652 (0.0008) -[2023-10-16 05:43:37,933][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000074656_76447744.pth... -[2023-10-16 05:43:37,962][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000072960_74711040.pth -[2023-10-16 05:43:41,238][05219] Updated weights for policy 1, policy_version 74410 (0.0010) -[2023-10-16 05:43:41,599][05218] Updated weights for policy 0, policy_version 74662 (0.0007) -[2023-10-16 05:43:41,607][05219] Updated weights for policy 1, policy_version 74420 (0.0008) -[2023-10-16 05:43:41,967][05218] Updated weights for policy 0, policy_version 74672 (0.0007) -[2023-10-16 05:43:41,981][05219] Updated weights for policy 1, policy_version 74430 (0.0008) -[2023-10-16 05:43:42,339][05218] Updated weights for policy 0, policy_version 74682 (0.0008) -[2023-10-16 05:43:42,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 152666112. Throughput: 0: 1779.7, 1: 1786.8. Samples: 38172378. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) -[2023-10-16 05:43:42,352][03835] Avg episode reward: [(0, '7.320'), (1, '8.020')] -[2023-10-16 05:43:45,720][05219] Updated weights for policy 1, policy_version 74440 (0.0008) -[2023-10-16 05:43:46,077][05219] Updated weights for policy 1, policy_version 74450 (0.0007) -[2023-10-16 05:43:46,101][05218] Updated weights for policy 0, policy_version 74692 (0.0008) -[2023-10-16 05:43:46,450][05219] Updated weights for policy 1, policy_version 74460 (0.0008) -[2023-10-16 05:43:46,465][05218] Updated weights for policy 0, policy_version 74702 (0.0009) -[2023-10-16 05:43:46,838][05218] Updated weights for policy 0, policy_version 74712 (0.0009) -[2023-10-16 05:43:47,350][03835] Fps is (10 sec: 19661.6, 60 sec: 15291.8, 300 sec: 14440.1). Total num frames: 152764416. Throughput: 0: 1803.9, 1: 1804.2. Samples: 38193722. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) -[2023-10-16 05:43:47,351][03835] Avg episode reward: [(0, '7.510'), (1, '7.550')] -[2023-10-16 05:43:50,418][05219] Updated weights for policy 1, policy_version 74470 (0.0008) -[2023-10-16 05:43:50,603][05218] Updated weights for policy 0, policy_version 74722 (0.0008) -[2023-10-16 05:43:50,778][05219] Updated weights for policy 1, policy_version 74480 (0.0008) -[2023-10-16 05:43:50,977][05218] Updated weights for policy 0, policy_version 74732 (0.0007) -[2023-10-16 05:43:51,143][05219] Updated weights for policy 1, policy_version 74490 (0.0008) -[2023-10-16 05:43:51,360][05218] Updated weights for policy 0, policy_version 74742 (0.0008) -[2023-10-16 05:43:51,734][05218] Updated weights for policy 0, policy_version 74752 (0.0007) -[2023-10-16 05:43:52,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 152829952. Throughput: 0: 1790.1, 1: 1787.4. Samples: 38214548. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) -[2023-10-16 05:43:52,351][03835] Avg episode reward: [(0, '6.620'), (1, '8.090')] -[2023-10-16 05:43:54,986][05219] Updated weights for policy 1, policy_version 74500 (0.0008) -[2023-10-16 05:43:55,323][05218] Updated weights for policy 0, policy_version 74762 (0.0007) -[2023-10-16 05:43:55,370][05219] Updated weights for policy 1, policy_version 74510 (0.0007) -[2023-10-16 05:43:55,693][05218] Updated weights for policy 0, policy_version 74772 (0.0008) -[2023-10-16 05:43:55,730][05219] Updated weights for policy 1, policy_version 74520 (0.0009) -[2023-10-16 05:43:56,065][05218] Updated weights for policy 0, policy_version 74782 (0.0008) -[2023-10-16 05:43:57,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 152895488. Throughput: 0: 1809.7, 1: 1806.4. Samples: 38226658. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) -[2023-10-16 05:43:57,351][03835] Avg episode reward: [(0, '6.920'), (1, '7.580')] -[2023-10-16 05:43:59,369][05219] Updated weights for policy 1, policy_version 74530 (0.0008) -[2023-10-16 05:43:59,730][05218] Updated weights for policy 0, policy_version 74792 (0.0007) -[2023-10-16 05:43:59,738][05219] Updated weights for policy 1, policy_version 74540 (0.0007) -[2023-10-16 05:44:00,097][05219] Updated weights for policy 1, policy_version 74550 (0.0008) -[2023-10-16 05:44:00,105][05218] Updated weights for policy 0, policy_version 74802 (0.0008) -[2023-10-16 05:44:00,467][05219] Updated weights for policy 1, policy_version 74560 (0.0008) -[2023-10-16 05:44:00,484][05218] Updated weights for policy 0, policy_version 74812 (0.0009) -[2023-10-16 05:44:02,351][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 152961024. Throughput: 0: 1796.7, 1: 1788.8. Samples: 38247178. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) -[2023-10-16 05:44:02,352][03835] Avg episode reward: [(0, '7.070'), (1, '7.740')] -[2023-10-16 05:44:04,227][05219] Updated weights for policy 1, policy_version 74570 (0.0008) -[2023-10-16 05:44:04,352][05218] Updated weights for policy 0, policy_version 74822 (0.0010) -[2023-10-16 05:44:04,595][05219] Updated weights for policy 1, policy_version 74580 (0.0007) -[2023-10-16 05:44:04,721][05218] Updated weights for policy 0, policy_version 74832 (0.0010) -[2023-10-16 05:44:04,967][05219] Updated weights for policy 1, policy_version 74590 (0.0008) -[2023-10-16 05:44:05,089][05218] Updated weights for policy 0, policy_version 74842 (0.0007) -[2023-10-16 05:44:07,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 153026560. Throughput: 0: 1793.8, 1: 1787.1. Samples: 38269506. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) -[2023-10-16 05:44:07,351][03835] Avg episode reward: [(0, '6.830'), (1, '7.230')] -[2023-10-16 05:44:08,694][05219] Updated weights for policy 1, policy_version 74600 (0.0009) -[2023-10-16 05:44:08,958][05218] Updated weights for policy 0, policy_version 74852 (0.0008) -[2023-10-16 05:44:09,056][05219] Updated weights for policy 1, policy_version 74610 (0.0008) -[2023-10-16 05:44:09,331][05218] Updated weights for policy 0, policy_version 74862 (0.0009) -[2023-10-16 05:44:09,411][05219] Updated weights for policy 1, policy_version 74620 (0.0008) -[2023-10-16 05:44:09,701][05218] Updated weights for policy 0, policy_version 74872 (0.0007) -[2023-10-16 05:44:12,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 153092096. Throughput: 0: 1790.8, 1: 1788.5. Samples: 38279258. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) -[2023-10-16 05:44:12,351][03835] Avg episode reward: [(0, '6.830'), (1, '8.110')] -[2023-10-16 05:44:13,226][05219] Updated weights for policy 1, policy_version 74630 (0.0007) -[2023-10-16 05:44:13,444][05218] Updated weights for policy 0, policy_version 74882 (0.0008) -[2023-10-16 05:44:13,593][05219] Updated weights for policy 1, policy_version 74640 (0.0009) -[2023-10-16 05:44:13,815][05218] Updated weights for policy 0, policy_version 74892 (0.0009) -[2023-10-16 05:44:13,952][05219] Updated weights for policy 1, policy_version 74650 (0.0008) -[2023-10-16 05:44:14,186][05218] Updated weights for policy 0, policy_version 74902 (0.0009) -[2023-10-16 05:44:14,566][05218] Updated weights for policy 0, policy_version 74912 (0.0008) -[2023-10-16 05:44:17,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 153157632. Throughput: 0: 1789.9, 1: 1784.4. Samples: 38301144. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) -[2023-10-16 05:44:17,351][03835] Avg episode reward: [(0, '7.040'), (1, '7.520')] -[2023-10-16 05:44:17,772][05219] Updated weights for policy 1, policy_version 74660 (0.0009) -[2023-10-16 05:44:18,137][05219] Updated weights for policy 1, policy_version 74670 (0.0008) -[2023-10-16 05:44:18,390][05218] Updated weights for policy 0, policy_version 74922 (0.0008) -[2023-10-16 05:44:18,500][05219] Updated weights for policy 1, policy_version 74680 (0.0008) -[2023-10-16 05:44:18,766][05218] Updated weights for policy 0, policy_version 74932 (0.0009) -[2023-10-16 05:44:19,153][05218] Updated weights for policy 0, policy_version 74942 (0.0009) -[2023-10-16 05:44:22,226][05219] Updated weights for policy 1, policy_version 74690 (0.0008) -[2023-10-16 05:44:22,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 153223168. Throughput: 0: 1807.8, 1: 1806.7. Samples: 38323590. Policy #0 lag: (min: 17.0, avg: 24.9, max: 49.0) -[2023-10-16 05:44:22,352][03835] Avg episode reward: [(0, '7.050'), (1, '7.970')] -[2023-10-16 05:44:22,595][05219] Updated weights for policy 1, policy_version 74700 (0.0007) -[2023-10-16 05:44:22,912][05218] Updated weights for policy 0, policy_version 74952 (0.0007) -[2023-10-16 05:44:22,953][05219] Updated weights for policy 1, policy_version 74710 (0.0007) -[2023-10-16 05:44:23,277][05218] Updated weights for policy 0, policy_version 74962 (0.0008) -[2023-10-16 05:44:23,309][05219] Updated weights for policy 1, policy_version 74720 (0.0009) -[2023-10-16 05:44:23,655][05218] Updated weights for policy 0, policy_version 74972 (0.0007) -[2023-10-16 05:44:27,165][05219] Updated weights for policy 1, policy_version 74730 (0.0007) -[2023-10-16 05:44:27,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 153288704. Throughput: 0: 1789.5, 1: 1784.5. Samples: 38333208. Policy #0 lag: (min: 17.0, avg: 24.9, max: 49.0) -[2023-10-16 05:44:27,351][03835] Avg episode reward: [(0, '6.940'), (1, '8.150')] -[2023-10-16 05:44:27,472][05218] Updated weights for policy 0, policy_version 74982 (0.0008) -[2023-10-16 05:44:27,531][05219] Updated weights for policy 1, policy_version 74740 (0.0007) -[2023-10-16 05:44:27,845][05218] Updated weights for policy 0, policy_version 74992 (0.0007) -[2023-10-16 05:44:27,892][05219] Updated weights for policy 1, policy_version 74750 (0.0008) -[2023-10-16 05:44:28,230][05218] Updated weights for policy 0, policy_version 75002 (0.0008) -[2023-10-16 05:44:31,788][05219] Updated weights for policy 1, policy_version 74760 (0.0007) -[2023-10-16 05:44:31,910][05218] Updated weights for policy 0, policy_version 75012 (0.0009) -[2023-10-16 05:44:32,156][05219] Updated weights for policy 1, policy_version 74770 (0.0007) -[2023-10-16 05:44:32,298][05218] Updated weights for policy 0, policy_version 75022 (0.0009) -[2023-10-16 05:44:32,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 153354240. Throughput: 0: 1802.1, 1: 1792.9. Samples: 38355496. Policy #0 lag: (min: 17.0, avg: 24.9, max: 49.0) -[2023-10-16 05:44:32,351][03835] Avg episode reward: [(0, '6.410'), (1, '7.950')] -[2023-10-16 05:44:32,520][05219] Updated weights for policy 1, policy_version 74780 (0.0008) -[2023-10-16 05:44:32,675][05218] Updated weights for policy 0, policy_version 75032 (0.0008) -[2023-10-16 05:44:36,398][05219] Updated weights for policy 1, policy_version 74790 (0.0009) -[2023-10-16 05:44:36,465][05218] Updated weights for policy 0, policy_version 75042 (0.0007) -[2023-10-16 05:44:36,768][05219] Updated weights for policy 1, policy_version 74800 (0.0008) -[2023-10-16 05:44:36,833][05218] Updated weights for policy 0, policy_version 75052 (0.0007) -[2023-10-16 05:44:37,133][05219] Updated weights for policy 1, policy_version 74810 (0.0008) -[2023-10-16 05:44:37,204][05218] Updated weights for policy 0, policy_version 75062 (0.0007) -[2023-10-16 05:44:37,351][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 153419776. Throughput: 0: 1799.3, 1: 1777.9. Samples: 38375524. Policy #0 lag: (min: 17.0, avg: 24.9, max: 49.0) -[2023-10-16 05:44:37,352][03835] Avg episode reward: [(0, '6.190'), (1, '7.150')] -[2023-10-16 05:44:37,582][05218] Updated weights for policy 0, policy_version 75072 (0.0007) -[2023-10-16 05:44:40,853][05219] Updated weights for policy 1, policy_version 74820 (0.0009) -[2023-10-16 05:44:41,219][05218] Updated weights for policy 0, policy_version 75082 (0.0008) -[2023-10-16 05:44:41,238][05219] Updated weights for policy 1, policy_version 74830 (0.0007) -[2023-10-16 05:44:41,593][05218] Updated weights for policy 0, policy_version 75092 (0.0007) -[2023-10-16 05:44:41,600][05219] Updated weights for policy 1, policy_version 74840 (0.0008) -[2023-10-16 05:44:41,966][05218] Updated weights for policy 0, policy_version 75102 (0.0010) -[2023-10-16 05:44:42,350][03835] Fps is (10 sec: 19660.9, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 153550848. Throughput: 0: 1800.4, 1: 1779.4. Samples: 38387748. Policy #0 lag: (min: 17.0, avg: 24.9, max: 49.0) -[2023-10-16 05:44:42,351][03835] Avg episode reward: [(0, '7.270'), (1, '6.710')] -[2023-10-16 05:44:45,421][05219] Updated weights for policy 1, policy_version 74850 (0.0007) -[2023-10-16 05:44:45,763][05218] Updated weights for policy 0, policy_version 75112 (0.0007) -[2023-10-16 05:44:45,788][05219] Updated weights for policy 1, policy_version 74860 (0.0007) -[2023-10-16 05:44:46,137][05218] Updated weights for policy 0, policy_version 75122 (0.0007) -[2023-10-16 05:44:46,143][05219] Updated weights for policy 1, policy_version 74870 (0.0007) -[2023-10-16 05:44:46,504][05218] Updated weights for policy 0, policy_version 75132 (0.0008) -[2023-10-16 05:44:46,511][05219] Updated weights for policy 1, policy_version 74880 (0.0008) -[2023-10-16 05:44:47,350][03835] Fps is (10 sec: 19661.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 153616384. Throughput: 0: 1793.0, 1: 1777.0. Samples: 38407830. Policy #0 lag: (min: 17.0, avg: 24.9, max: 49.0) -[2023-10-16 05:44:47,351][03835] Avg episode reward: [(0, '6.490'), (1, '7.200')] -[2023-10-16 05:44:50,249][05218] Updated weights for policy 0, policy_version 75142 (0.0008) -[2023-10-16 05:44:50,386][05219] Updated weights for policy 1, policy_version 74890 (0.0007) -[2023-10-16 05:44:50,626][05218] Updated weights for policy 0, policy_version 75152 (0.0007) -[2023-10-16 05:44:50,754][05219] Updated weights for policy 1, policy_version 74900 (0.0008) -[2023-10-16 05:44:50,991][05218] Updated weights for policy 0, policy_version 75162 (0.0007) -[2023-10-16 05:44:51,111][05219] Updated weights for policy 1, policy_version 74910 (0.0007) -[2023-10-16 05:44:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 153681920. Throughput: 0: 1787.7, 1: 1763.8. Samples: 38429324. Policy #0 lag: (min: 17.0, avg: 24.9, max: 49.0) -[2023-10-16 05:44:52,351][03835] Avg episode reward: [(0, '6.640'), (1, '6.450')] -[2023-10-16 05:44:54,728][05219] Updated weights for policy 1, policy_version 74920 (0.0007) -[2023-10-16 05:44:54,785][05218] Updated weights for policy 0, policy_version 75172 (0.0008) -[2023-10-16 05:44:55,098][05219] Updated weights for policy 1, policy_version 74930 (0.0008) -[2023-10-16 05:44:55,157][05218] Updated weights for policy 0, policy_version 75182 (0.0008) -[2023-10-16 05:44:55,454][05219] Updated weights for policy 1, policy_version 74940 (0.0008) -[2023-10-16 05:44:55,538][05218] Updated weights for policy 0, policy_version 75192 (0.0008) -[2023-10-16 05:44:57,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 153747456. Throughput: 0: 1802.4, 1: 1781.4. Samples: 38440528. Policy #0 lag: (min: 17.0, avg: 24.9, max: 49.0) -[2023-10-16 05:44:57,351][03835] Avg episode reward: [(0, '7.260'), (1, '7.390')] -[2023-10-16 05:44:59,221][05219] Updated weights for policy 1, policy_version 74950 (0.0007) -[2023-10-16 05:44:59,307][05218] Updated weights for policy 0, policy_version 75202 (0.0008) -[2023-10-16 05:44:59,589][05219] Updated weights for policy 1, policy_version 74960 (0.0008) -[2023-10-16 05:44:59,685][05218] Updated weights for policy 0, policy_version 75212 (0.0007) -[2023-10-16 05:44:59,949][05219] Updated weights for policy 1, policy_version 74970 (0.0009) -[2023-10-16 05:45:00,050][05218] Updated weights for policy 0, policy_version 75222 (0.0008) -[2023-10-16 05:45:00,428][05218] Updated weights for policy 0, policy_version 75232 (0.0009) -[2023-10-16 05:45:02,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 153812992. Throughput: 0: 1790.8, 1: 1774.9. Samples: 38461602. Policy #0 lag: (min: 17.0, avg: 24.9, max: 49.0) -[2023-10-16 05:45:02,351][03835] Avg episode reward: [(0, '7.060'), (1, '7.690')] -[2023-10-16 05:45:03,681][05219] Updated weights for policy 1, policy_version 74980 (0.0009) -[2023-10-16 05:45:04,041][05219] Updated weights for policy 1, policy_version 74990 (0.0008) -[2023-10-16 05:45:04,292][05218] Updated weights for policy 0, policy_version 75242 (0.0008) -[2023-10-16 05:45:04,407][05219] Updated weights for policy 1, policy_version 75000 (0.0009) -[2023-10-16 05:45:04,668][05218] Updated weights for policy 0, policy_version 75252 (0.0009) -[2023-10-16 05:45:05,032][05218] Updated weights for policy 0, policy_version 75262 (0.0011) -[2023-10-16 05:45:07,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 153878528. Throughput: 0: 1783.5, 1: 1775.7. Samples: 38483756. Policy #0 lag: (min: 17.0, avg: 24.9, max: 49.0) -[2023-10-16 05:45:07,352][03835] Avg episode reward: [(0, '6.150'), (1, '7.550')] -[2023-10-16 05:45:08,309][05219] Updated weights for policy 1, policy_version 75010 (0.0007) -[2023-10-16 05:45:08,672][05219] Updated weights for policy 1, policy_version 75020 (0.0007) -[2023-10-16 05:45:08,770][05218] Updated weights for policy 0, policy_version 75272 (0.0008) -[2023-10-16 05:45:09,034][05219] Updated weights for policy 1, policy_version 75030 (0.0007) -[2023-10-16 05:45:09,143][05218] Updated weights for policy 0, policy_version 75282 (0.0009) -[2023-10-16 05:45:09,404][05219] Updated weights for policy 1, policy_version 75040 (0.0008) -[2023-10-16 05:45:09,533][05218] Updated weights for policy 0, policy_version 75292 (0.0008) -[2023-10-16 05:45:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 153944064. Throughput: 0: 1788.7, 1: 1776.0. Samples: 38493618. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) -[2023-10-16 05:45:12,351][03835] Avg episode reward: [(0, '7.170'), (1, '8.050')] -[2023-10-16 05:45:13,198][05219] Updated weights for policy 1, policy_version 75050 (0.0008) -[2023-10-16 05:45:13,238][05218] Updated weights for policy 0, policy_version 75302 (0.0009) -[2023-10-16 05:45:13,566][05219] Updated weights for policy 1, policy_version 75060 (0.0010) -[2023-10-16 05:45:13,610][05218] Updated weights for policy 0, policy_version 75312 (0.0007) -[2023-10-16 05:45:13,921][05219] Updated weights for policy 1, policy_version 75070 (0.0007) -[2023-10-16 05:45:13,976][05218] Updated weights for policy 0, policy_version 75322 (0.0009) -[2023-10-16 05:45:17,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 154009600. Throughput: 0: 1787.7, 1: 1778.5. Samples: 38515974. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) -[2023-10-16 05:45:17,352][03835] Avg episode reward: [(0, '6.840'), (1, '7.630')] -[2023-10-16 05:45:17,623][05218] Updated weights for policy 0, policy_version 75332 (0.0007) -[2023-10-16 05:45:17,760][05219] Updated weights for policy 1, policy_version 75080 (0.0007) -[2023-10-16 05:45:18,002][05218] Updated weights for policy 0, policy_version 75342 (0.0007) -[2023-10-16 05:45:18,122][05219] Updated weights for policy 1, policy_version 75090 (0.0008) -[2023-10-16 05:45:18,371][05218] Updated weights for policy 0, policy_version 75352 (0.0007) -[2023-10-16 05:45:18,485][05219] Updated weights for policy 1, policy_version 75100 (0.0007) -[2023-10-16 05:45:22,250][05219] Updated weights for policy 1, policy_version 75110 (0.0008) -[2023-10-16 05:45:22,286][05218] Updated weights for policy 0, policy_version 75362 (0.0007) -[2023-10-16 05:45:22,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 154075136. Throughput: 0: 1804.9, 1: 1799.1. Samples: 38537702. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) -[2023-10-16 05:45:22,351][03835] Avg episode reward: [(0, '6.530'), (1, '8.140')] -[2023-10-16 05:45:22,613][05219] Updated weights for policy 1, policy_version 75120 (0.0007) -[2023-10-16 05:45:22,651][05218] Updated weights for policy 0, policy_version 75372 (0.0007) -[2023-10-16 05:45:22,977][05219] Updated weights for policy 1, policy_version 75130 (0.0007) -[2023-10-16 05:45:23,023][05218] Updated weights for policy 0, policy_version 75382 (0.0007) -[2023-10-16 05:45:23,394][05218] Updated weights for policy 0, policy_version 75392 (0.0010) -[2023-10-16 05:45:26,860][05219] Updated weights for policy 1, policy_version 75140 (0.0007) -[2023-10-16 05:45:27,021][05218] Updated weights for policy 0, policy_version 75402 (0.0009) -[2023-10-16 05:45:27,246][05219] Updated weights for policy 1, policy_version 75150 (0.0007) -[2023-10-16 05:45:27,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 154140672. Throughput: 0: 1780.8, 1: 1774.9. Samples: 38547758. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) -[2023-10-16 05:45:27,351][03835] Avg episode reward: [(0, '7.140'), (1, '8.460')] -[2023-10-16 05:45:27,394][05218] Updated weights for policy 0, policy_version 75412 (0.0007) -[2023-10-16 05:45:27,616][05219] Updated weights for policy 1, policy_version 75160 (0.0009) -[2023-10-16 05:45:27,773][05218] Updated weights for policy 0, policy_version 75422 (0.0007) -[2023-10-16 05:45:31,395][05218] Updated weights for policy 0, policy_version 75432 (0.0008) -[2023-10-16 05:45:31,426][05219] Updated weights for policy 1, policy_version 75170 (0.0008) -[2023-10-16 05:45:31,779][05218] Updated weights for policy 0, policy_version 75442 (0.0009) -[2023-10-16 05:45:31,794][05219] Updated weights for policy 1, policy_version 75180 (0.0008) -[2023-10-16 05:45:32,150][05219] Updated weights for policy 1, policy_version 75190 (0.0008) -[2023-10-16 05:45:32,158][05218] Updated weights for policy 0, policy_version 75452 (0.0007) -[2023-10-16 05:45:32,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 154238976. Throughput: 0: 1800.5, 1: 1794.3. Samples: 38569598. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) -[2023-10-16 05:45:32,351][03835] Avg episode reward: [(0, '7.430'), (1, '6.850')] -[2023-10-16 05:45:32,515][05219] Updated weights for policy 1, policy_version 75200 (0.0007) -[2023-10-16 05:45:35,945][05218] Updated weights for policy 0, policy_version 75462 (0.0011) -[2023-10-16 05:45:36,326][05218] Updated weights for policy 0, policy_version 75472 (0.0007) -[2023-10-16 05:45:36,405][05219] Updated weights for policy 1, policy_version 75210 (0.0007) -[2023-10-16 05:45:36,694][05218] Updated weights for policy 0, policy_version 75482 (0.0009) -[2023-10-16 05:45:36,768][05219] Updated weights for policy 1, policy_version 75220 (0.0008) -[2023-10-16 05:45:37,124][05219] Updated weights for policy 1, policy_version 75230 (0.0008) -[2023-10-16 05:45:37,351][03835] Fps is (10 sec: 19660.1, 60 sec: 15291.7, 300 sec: 14440.1). Total num frames: 154337280. Throughput: 0: 1777.4, 1: 1773.0. Samples: 38589092. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) -[2023-10-16 05:45:37,352][03835] Avg episode reward: [(0, '6.890'), (1, '8.030')] -[2023-10-16 05:45:37,362][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000075488_77299712.pth... -[2023-10-16 05:45:37,362][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000075232_77037568.pth... -[2023-10-16 05:45:37,399][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000073536_75300864.pth -[2023-10-16 05:45:37,401][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000073792_75563008.pth -[2023-10-16 05:45:37,403][04891] Saving a milestone ./train_atari/atari_timepilot_APPO/checkpoint_p1/milestones/checkpoint_000075232_77037568.pth -[2023-10-16 05:45:37,405][04766] Saving a milestone ./train_atari/atari_timepilot_APPO/checkpoint_p0/milestones/checkpoint_000075488_77299712.pth -[2023-10-16 05:45:40,544][05218] Updated weights for policy 0, policy_version 75492 (0.0009) -[2023-10-16 05:45:40,919][05218] Updated weights for policy 0, policy_version 75502 (0.0009) -[2023-10-16 05:45:40,993][05219] Updated weights for policy 1, policy_version 75240 (0.0009) -[2023-10-16 05:45:41,283][05218] Updated weights for policy 0, policy_version 75512 (0.0009) -[2023-10-16 05:45:41,362][05219] Updated weights for policy 1, policy_version 75250 (0.0008) -[2023-10-16 05:45:41,729][05219] Updated weights for policy 1, policy_version 75260 (0.0010) -[2023-10-16 05:45:42,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 154402816. Throughput: 0: 1794.5, 1: 1783.0. Samples: 38601516. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) -[2023-10-16 05:45:42,351][03835] Avg episode reward: [(0, '6.670'), (1, '7.300')] -[2023-10-16 05:45:45,025][05218] Updated weights for policy 0, policy_version 75522 (0.0008) -[2023-10-16 05:45:45,379][05219] Updated weights for policy 1, policy_version 75270 (0.0011) -[2023-10-16 05:45:45,411][05218] Updated weights for policy 0, policy_version 75532 (0.0010) -[2023-10-16 05:45:45,743][05219] Updated weights for policy 1, policy_version 75280 (0.0007) -[2023-10-16 05:45:45,786][05218] Updated weights for policy 0, policy_version 75542 (0.0010) -[2023-10-16 05:45:46,100][05219] Updated weights for policy 1, policy_version 75290 (0.0008) -[2023-10-16 05:45:46,150][05218] Updated weights for policy 0, policy_version 75552 (0.0009) -[2023-10-16 05:45:47,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 154468352. Throughput: 0: 1773.4, 1: 1769.8. Samples: 38621046. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) -[2023-10-16 05:45:47,352][03835] Avg episode reward: [(0, '6.990'), (1, '6.370')] -[2023-10-16 05:45:49,864][05219] Updated weights for policy 1, policy_version 75300 (0.0007) -[2023-10-16 05:45:50,020][05218] Updated weights for policy 0, policy_version 75562 (0.0007) -[2023-10-16 05:45:50,228][05219] Updated weights for policy 1, policy_version 75310 (0.0007) -[2023-10-16 05:45:50,402][05218] Updated weights for policy 0, policy_version 75572 (0.0007) -[2023-10-16 05:45:50,585][05219] Updated weights for policy 1, policy_version 75320 (0.0008) -[2023-10-16 05:45:50,775][05218] Updated weights for policy 0, policy_version 75582 (0.0010) -[2023-10-16 05:45:52,351][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 154533888. Throughput: 0: 1772.8, 1: 1763.8. Samples: 38642904. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) -[2023-10-16 05:45:52,352][03835] Avg episode reward: [(0, '7.030'), (1, '7.450')] -[2023-10-16 05:45:54,286][05219] Updated weights for policy 1, policy_version 75330 (0.0008) -[2023-10-16 05:45:54,656][05219] Updated weights for policy 1, policy_version 75340 (0.0008) -[2023-10-16 05:45:54,735][05218] Updated weights for policy 0, policy_version 75592 (0.0008) -[2023-10-16 05:45:55,017][05219] Updated weights for policy 1, policy_version 75350 (0.0007) -[2023-10-16 05:45:55,120][05218] Updated weights for policy 0, policy_version 75602 (0.0008) -[2023-10-16 05:45:55,386][05219] Updated weights for policy 1, policy_version 75360 (0.0007) -[2023-10-16 05:45:55,489][05218] Updated weights for policy 0, policy_version 75612 (0.0010) -[2023-10-16 05:45:57,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 154599424. Throughput: 0: 1778.2, 1: 1771.6. Samples: 38653356. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) -[2023-10-16 05:45:57,351][03835] Avg episode reward: [(0, '6.570'), (1, '8.080')] -[2023-10-16 05:45:59,263][05219] Updated weights for policy 1, policy_version 75370 (0.0009) -[2023-10-16 05:45:59,338][05218] Updated weights for policy 0, policy_version 75622 (0.0009) -[2023-10-16 05:45:59,628][05219] Updated weights for policy 1, policy_version 75380 (0.0007) -[2023-10-16 05:45:59,710][05218] Updated weights for policy 0, policy_version 75632 (0.0010) -[2023-10-16 05:45:59,992][05219] Updated weights for policy 1, policy_version 75390 (0.0008) -[2023-10-16 05:46:00,088][05218] Updated weights for policy 0, policy_version 75642 (0.0008) -[2023-10-16 05:46:02,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 154664960. Throughput: 0: 1759.6, 1: 1763.6. Samples: 38674516. Policy #0 lag: (min: 19.0, avg: 22.3, max: 51.0) -[2023-10-16 05:46:02,351][03835] Avg episode reward: [(0, '7.420'), (1, '7.170')] -[2023-10-16 05:46:03,766][05218] Updated weights for policy 0, policy_version 75652 (0.0010) -[2023-10-16 05:46:03,877][05219] Updated weights for policy 1, policy_version 75400 (0.0008) -[2023-10-16 05:46:04,150][05218] Updated weights for policy 0, policy_version 75662 (0.0009) -[2023-10-16 05:46:04,234][05219] Updated weights for policy 1, policy_version 75410 (0.0008) -[2023-10-16 05:46:04,520][05218] Updated weights for policy 0, policy_version 75672 (0.0008) -[2023-10-16 05:46:04,597][05219] Updated weights for policy 1, policy_version 75420 (0.0008) -[2023-10-16 05:46:07,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 154730496. Throughput: 0: 1768.4, 1: 1765.9. Samples: 38696746. Policy #0 lag: (min: 19.0, avg: 22.3, max: 51.0) -[2023-10-16 05:46:07,352][03835] Avg episode reward: [(0, '7.630'), (1, '7.470')] -[2023-10-16 05:46:08,394][05218] Updated weights for policy 0, policy_version 75682 (0.0007) -[2023-10-16 05:46:08,521][05219] Updated weights for policy 1, policy_version 75430 (0.0008) -[2023-10-16 05:46:08,770][05218] Updated weights for policy 0, policy_version 75692 (0.0009) -[2023-10-16 05:46:08,883][05219] Updated weights for policy 1, policy_version 75440 (0.0007) -[2023-10-16 05:46:09,142][05218] Updated weights for policy 0, policy_version 75702 (0.0009) -[2023-10-16 05:46:09,251][05219] Updated weights for policy 1, policy_version 75450 (0.0007) -[2023-10-16 05:46:09,521][05218] Updated weights for policy 0, policy_version 75712 (0.0008) -[2023-10-16 05:46:12,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 154796032. Throughput: 0: 1760.9, 1: 1765.2. Samples: 38706434. Policy #0 lag: (min: 19.0, avg: 22.3, max: 51.0) -[2023-10-16 05:46:12,352][03835] Avg episode reward: [(0, '7.080'), (1, '8.120')] -[2023-10-16 05:46:13,069][05219] Updated weights for policy 1, policy_version 75460 (0.0008) -[2023-10-16 05:46:13,360][05218] Updated weights for policy 0, policy_version 75722 (0.0007) -[2023-10-16 05:46:13,421][05219] Updated weights for policy 1, policy_version 75470 (0.0008) -[2023-10-16 05:46:13,731][05218] Updated weights for policy 0, policy_version 75732 (0.0009) -[2023-10-16 05:46:13,786][05219] Updated weights for policy 1, policy_version 75480 (0.0007) -[2023-10-16 05:46:14,105][05218] Updated weights for policy 0, policy_version 75742 (0.0009) -[2023-10-16 05:46:17,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 154861568. Throughput: 0: 1768.8, 1: 1771.6. Samples: 38728916. Policy #0 lag: (min: 19.0, avg: 22.3, max: 51.0) -[2023-10-16 05:46:17,351][03835] Avg episode reward: [(0, '6.780'), (1, '7.100')] -[2023-10-16 05:46:17,529][05219] Updated weights for policy 1, policy_version 75490 (0.0007) -[2023-10-16 05:46:17,649][05218] Updated weights for policy 0, policy_version 75752 (0.0009) -[2023-10-16 05:46:17,907][05219] Updated weights for policy 1, policy_version 75500 (0.0008) -[2023-10-16 05:46:18,019][05218] Updated weights for policy 0, policy_version 75762 (0.0008) -[2023-10-16 05:46:18,273][05219] Updated weights for policy 1, policy_version 75510 (0.0008) -[2023-10-16 05:46:18,397][05218] Updated weights for policy 0, policy_version 75772 (0.0009) -[2023-10-16 05:46:18,636][05219] Updated weights for policy 1, policy_version 75520 (0.0009) -[2023-10-16 05:46:21,968][05218] Updated weights for policy 0, policy_version 75782 (0.0008) -[2023-10-16 05:46:22,341][05218] Updated weights for policy 0, policy_version 75792 (0.0007) -[2023-10-16 05:46:22,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 154927104. Throughput: 0: 1783.4, 1: 1799.2. Samples: 38750310. Policy #0 lag: (min: 19.0, avg: 22.3, max: 51.0) -[2023-10-16 05:46:22,351][03835] Avg episode reward: [(0, '6.190'), (1, '7.420')] -[2023-10-16 05:46:22,360][05219] Updated weights for policy 1, policy_version 75530 (0.0007) -[2023-10-16 05:46:22,718][05218] Updated weights for policy 0, policy_version 75802 (0.0008) -[2023-10-16 05:46:22,724][05219] Updated weights for policy 1, policy_version 75540 (0.0007) -[2023-10-16 05:46:23,090][05219] Updated weights for policy 1, policy_version 75550 (0.0008) -[2023-10-16 05:46:26,524][05218] Updated weights for policy 0, policy_version 75812 (0.0010) -[2023-10-16 05:46:26,831][05219] Updated weights for policy 1, policy_version 75560 (0.0008) -[2023-10-16 05:46:26,893][05218] Updated weights for policy 0, policy_version 75822 (0.0008) -[2023-10-16 05:46:27,187][05219] Updated weights for policy 1, policy_version 75570 (0.0007) -[2023-10-16 05:46:27,265][05218] Updated weights for policy 0, policy_version 75832 (0.0009) -[2023-10-16 05:46:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 154992640. Throughput: 0: 1766.3, 1: 1776.1. Samples: 38760920. Policy #0 lag: (min: 19.0, avg: 22.3, max: 51.0) -[2023-10-16 05:46:27,351][03835] Avg episode reward: [(0, '5.780'), (1, '8.270')] -[2023-10-16 05:46:27,556][05219] Updated weights for policy 1, policy_version 75580 (0.0007) -[2023-10-16 05:46:30,901][05218] Updated weights for policy 0, policy_version 75842 (0.0010) -[2023-10-16 05:46:31,279][05218] Updated weights for policy 0, policy_version 75852 (0.0008) -[2023-10-16 05:46:31,423][05219] Updated weights for policy 1, policy_version 75590 (0.0009) -[2023-10-16 05:46:31,659][05218] Updated weights for policy 0, policy_version 75862 (0.0008) -[2023-10-16 05:46:31,783][05219] Updated weights for policy 1, policy_version 75600 (0.0009) -[2023-10-16 05:46:32,024][05218] Updated weights for policy 0, policy_version 75872 (0.0008) -[2023-10-16 05:46:32,160][05219] Updated weights for policy 1, policy_version 75610 (0.0008) -[2023-10-16 05:46:32,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 155090944. Throughput: 0: 1792.3, 1: 1802.3. Samples: 38782802. Policy #0 lag: (min: 19.0, avg: 22.3, max: 51.0) -[2023-10-16 05:46:32,351][03835] Avg episode reward: [(0, '6.380'), (1, '7.340')] -[2023-10-16 05:46:35,890][05218] Updated weights for policy 0, policy_version 75882 (0.0008) -[2023-10-16 05:46:36,079][05219] Updated weights for policy 1, policy_version 75620 (0.0008) -[2023-10-16 05:46:36,255][05218] Updated weights for policy 0, policy_version 75892 (0.0009) -[2023-10-16 05:46:36,440][05219] Updated weights for policy 1, policy_version 75630 (0.0009) -[2023-10-16 05:46:36,636][05218] Updated weights for policy 0, policy_version 75902 (0.0007) -[2023-10-16 05:46:36,801][05219] Updated weights for policy 1, policy_version 75640 (0.0009) -[2023-10-16 05:46:37,350][03835] Fps is (10 sec: 19660.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 155189248. Throughput: 0: 1780.1, 1: 1774.4. Samples: 38802856. Policy #0 lag: (min: 19.0, avg: 22.3, max: 51.0) -[2023-10-16 05:46:37,352][03835] Avg episode reward: [(0, '7.470'), (1, '7.710')] -[2023-10-16 05:46:40,474][05219] Updated weights for policy 1, policy_version 75650 (0.0008) -[2023-10-16 05:46:40,490][05218] Updated weights for policy 0, policy_version 75912 (0.0009) -[2023-10-16 05:46:40,842][05219] Updated weights for policy 1, policy_version 75660 (0.0009) -[2023-10-16 05:46:40,866][05218] Updated weights for policy 0, policy_version 75922 (0.0010) -[2023-10-16 05:46:41,195][05219] Updated weights for policy 1, policy_version 75670 (0.0008) -[2023-10-16 05:46:41,231][05218] Updated weights for policy 0, policy_version 75932 (0.0008) -[2023-10-16 05:46:41,562][05219] Updated weights for policy 1, policy_version 75680 (0.0009) -[2023-10-16 05:46:42,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 155254784. Throughput: 0: 1802.8, 1: 1798.6. Samples: 38815418. Policy #0 lag: (min: 19.0, avg: 22.3, max: 51.0) -[2023-10-16 05:46:42,351][03835] Avg episode reward: [(0, '7.200'), (1, '8.410')] -[2023-10-16 05:46:44,930][05218] Updated weights for policy 0, policy_version 75942 (0.0009) -[2023-10-16 05:46:45,305][05218] Updated weights for policy 0, policy_version 75952 (0.0008) -[2023-10-16 05:46:45,378][05219] Updated weights for policy 1, policy_version 75690 (0.0008) -[2023-10-16 05:46:45,681][05218] Updated weights for policy 0, policy_version 75962 (0.0008) -[2023-10-16 05:46:45,746][05219] Updated weights for policy 1, policy_version 75700 (0.0007) -[2023-10-16 05:46:46,115][05219] Updated weights for policy 1, policy_version 75710 (0.0008) -[2023-10-16 05:46:47,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 155320320. Throughput: 0: 1794.1, 1: 1778.5. Samples: 38835284. Policy #0 lag: (min: 19.0, avg: 22.3, max: 51.0) -[2023-10-16 05:46:47,351][03835] Avg episode reward: [(0, '6.780'), (1, '6.660')] -[2023-10-16 05:46:49,469][05218] Updated weights for policy 0, policy_version 75972 (0.0009) -[2023-10-16 05:46:49,834][05218] Updated weights for policy 0, policy_version 75982 (0.0008) -[2023-10-16 05:46:49,991][05219] Updated weights for policy 1, policy_version 75720 (0.0008) -[2023-10-16 05:46:50,214][05218] Updated weights for policy 0, policy_version 75992 (0.0007) -[2023-10-16 05:46:50,362][05219] Updated weights for policy 1, policy_version 75730 (0.0008) -[2023-10-16 05:46:50,726][05219] Updated weights for policy 1, policy_version 75740 (0.0009) -[2023-10-16 05:46:52,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 155385856. Throughput: 0: 1792.9, 1: 1775.4. Samples: 38857318. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:46:52,351][03835] Avg episode reward: [(0, '6.800'), (1, '7.390')] -[2023-10-16 05:46:53,973][05218] Updated weights for policy 0, policy_version 76002 (0.0009) -[2023-10-16 05:46:54,335][05218] Updated weights for policy 0, policy_version 76012 (0.0008) -[2023-10-16 05:46:54,496][05219] Updated weights for policy 1, policy_version 75750 (0.0009) -[2023-10-16 05:46:54,711][05218] Updated weights for policy 0, policy_version 76022 (0.0009) -[2023-10-16 05:46:54,854][05219] Updated weights for policy 1, policy_version 75760 (0.0008) -[2023-10-16 05:46:55,088][05218] Updated weights for policy 0, policy_version 76032 (0.0008) -[2023-10-16 05:46:55,224][05219] Updated weights for policy 1, policy_version 75770 (0.0008) -[2023-10-16 05:46:57,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 155451392. Throughput: 0: 1794.6, 1: 1782.7. Samples: 38867412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:46:57,351][03835] Avg episode reward: [(0, '6.110'), (1, '7.950')] -[2023-10-16 05:46:58,777][05218] Updated weights for policy 0, policy_version 76042 (0.0008) -[2023-10-16 05:46:59,077][05219] Updated weights for policy 1, policy_version 75780 (0.0009) -[2023-10-16 05:46:59,145][05218] Updated weights for policy 0, policy_version 76052 (0.0007) -[2023-10-16 05:46:59,456][05219] Updated weights for policy 1, policy_version 75790 (0.0008) -[2023-10-16 05:46:59,533][05218] Updated weights for policy 0, policy_version 76062 (0.0008) -[2023-10-16 05:46:59,833][05219] Updated weights for policy 1, policy_version 75800 (0.0009) -[2023-10-16 05:47:02,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 155516928. Throughput: 0: 1798.0, 1: 1767.4. Samples: 38889362. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:47:02,351][03835] Avg episode reward: [(0, '7.090'), (1, '7.760')] -[2023-10-16 05:47:03,256][05218] Updated weights for policy 0, policy_version 76072 (0.0007) -[2023-10-16 05:47:03,627][05218] Updated weights for policy 0, policy_version 76082 (0.0007) -[2023-10-16 05:47:03,695][05219] Updated weights for policy 1, policy_version 75810 (0.0010) -[2023-10-16 05:47:04,015][05218] Updated weights for policy 0, policy_version 76092 (0.0010) -[2023-10-16 05:47:04,098][05219] Updated weights for policy 1, policy_version 75820 (0.0010) -[2023-10-16 05:47:04,465][05219] Updated weights for policy 1, policy_version 75830 (0.0010) -[2023-10-16 05:47:04,831][05219] Updated weights for policy 1, policy_version 75840 (0.0009) -[2023-10-16 05:47:07,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 155582464. Throughput: 0: 1814.7, 1: 1767.1. Samples: 38911494. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:47:07,352][03835] Avg episode reward: [(0, '6.950'), (1, '8.210')] -[2023-10-16 05:47:07,678][05218] Updated weights for policy 0, policy_version 76102 (0.0007) -[2023-10-16 05:47:08,044][05218] Updated weights for policy 0, policy_version 76112 (0.0009) -[2023-10-16 05:47:08,425][05218] Updated weights for policy 0, policy_version 76122 (0.0008) -[2023-10-16 05:47:08,580][05219] Updated weights for policy 1, policy_version 75850 (0.0007) -[2023-10-16 05:47:08,938][05219] Updated weights for policy 1, policy_version 75860 (0.0010) -[2023-10-16 05:47:09,311][05219] Updated weights for policy 1, policy_version 75870 (0.0010) -[2023-10-16 05:47:12,268][05218] Updated weights for policy 0, policy_version 76132 (0.0009) -[2023-10-16 05:47:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 155648000. Throughput: 0: 1802.1, 1: 1761.1. Samples: 38921264. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:47:12,351][03835] Avg episode reward: [(0, '7.490'), (1, '8.730')] -[2023-10-16 05:47:12,645][05218] Updated weights for policy 0, policy_version 76142 (0.0010) -[2023-10-16 05:47:13,024][05218] Updated weights for policy 0, policy_version 76152 (0.0009) -[2023-10-16 05:47:13,038][05219] Updated weights for policy 1, policy_version 75880 (0.0008) -[2023-10-16 05:47:13,399][05219] Updated weights for policy 1, policy_version 75890 (0.0008) -[2023-10-16 05:47:13,760][05219] Updated weights for policy 1, policy_version 75900 (0.0008) -[2023-10-16 05:47:16,654][05218] Updated weights for policy 0, policy_version 76162 (0.0008) -[2023-10-16 05:47:17,034][05218] Updated weights for policy 0, policy_version 76172 (0.0009) -[2023-10-16 05:47:17,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 155713536. Throughput: 0: 1813.8, 1: 1761.6. Samples: 38943694. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:47:17,351][03835] Avg episode reward: [(0, '7.970'), (1, '7.130')] -[2023-10-16 05:47:17,412][05218] Updated weights for policy 0, policy_version 76182 (0.0009) -[2023-10-16 05:47:17,561][05219] Updated weights for policy 1, policy_version 75910 (0.0010) -[2023-10-16 05:47:17,779][05218] Updated weights for policy 0, policy_version 76192 (0.0007) -[2023-10-16 05:47:17,927][05219] Updated weights for policy 1, policy_version 75920 (0.0009) -[2023-10-16 05:47:18,304][05219] Updated weights for policy 1, policy_version 75930 (0.0011) -[2023-10-16 05:47:21,676][05218] Updated weights for policy 0, policy_version 76202 (0.0011) -[2023-10-16 05:47:22,048][05218] Updated weights for policy 0, policy_version 76212 (0.0011) -[2023-10-16 05:47:22,297][05219] Updated weights for policy 1, policy_version 75940 (0.0009) -[2023-10-16 05:47:22,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 155779072. Throughput: 0: 1801.0, 1: 1796.3. Samples: 38964734. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:47:22,351][03835] Avg episode reward: [(0, '7.140'), (1, '7.200')] -[2023-10-16 05:47:22,421][05218] Updated weights for policy 0, policy_version 76222 (0.0008) -[2023-10-16 05:47:22,653][05219] Updated weights for policy 1, policy_version 75950 (0.0009) -[2023-10-16 05:47:23,021][05219] Updated weights for policy 1, policy_version 75960 (0.0009) -[2023-10-16 05:47:26,162][05218] Updated weights for policy 0, policy_version 76232 (0.0007) -[2023-10-16 05:47:26,549][05218] Updated weights for policy 0, policy_version 76242 (0.0009) -[2023-10-16 05:47:26,686][05219] Updated weights for policy 1, policy_version 75970 (0.0009) -[2023-10-16 05:47:26,921][05218] Updated weights for policy 0, policy_version 76252 (0.0009) -[2023-10-16 05:47:27,054][05219] Updated weights for policy 1, policy_version 75980 (0.0007) -[2023-10-16 05:47:27,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 155877376. Throughput: 0: 1798.9, 1: 1764.1. Samples: 38975752. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:47:27,351][03835] Avg episode reward: [(0, '7.250'), (1, '8.170')] -[2023-10-16 05:47:27,407][05219] Updated weights for policy 1, policy_version 75990 (0.0008) -[2023-10-16 05:47:27,773][05219] Updated weights for policy 1, policy_version 76000 (0.0007) -[2023-10-16 05:47:30,663][05218] Updated weights for policy 0, policy_version 76262 (0.0010) -[2023-10-16 05:47:31,047][05218] Updated weights for policy 0, policy_version 76272 (0.0008) -[2023-10-16 05:47:31,417][05218] Updated weights for policy 0, policy_version 76282 (0.0009) -[2023-10-16 05:47:31,442][05219] Updated weights for policy 1, policy_version 76010 (0.0008) -[2023-10-16 05:47:31,814][05219] Updated weights for policy 1, policy_version 76020 (0.0010) -[2023-10-16 05:47:32,186][05219] Updated weights for policy 1, policy_version 76030 (0.0007) -[2023-10-16 05:47:32,350][03835] Fps is (10 sec: 19661.0, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 155975680. Throughput: 0: 1796.3, 1: 1795.1. Samples: 38996896. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:47:32,351][03835] Avg episode reward: [(0, '7.230'), (1, '6.450')] -[2023-10-16 05:47:35,395][05218] Updated weights for policy 0, policy_version 76292 (0.0008) -[2023-10-16 05:47:35,765][05218] Updated weights for policy 0, policy_version 76302 (0.0007) -[2023-10-16 05:47:35,798][05219] Updated weights for policy 1, policy_version 76040 (0.0008) -[2023-10-16 05:47:36,137][05218] Updated weights for policy 0, policy_version 76312 (0.0008) -[2023-10-16 05:47:36,165][05219] Updated weights for policy 1, policy_version 76050 (0.0007) -[2023-10-16 05:47:36,529][05219] Updated weights for policy 1, policy_version 76060 (0.0008) -[2023-10-16 05:47:37,351][03835] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 156041216. Throughput: 0: 1784.8, 1: 1775.6. Samples: 39017538. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:47:37,352][03835] Avg episode reward: [(0, '6.590'), (1, '7.830')] -[2023-10-16 05:47:37,365][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000076064_77889536.pth... -[2023-10-16 05:47:37,365][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000076320_78151680.pth... -[2023-10-16 05:47:37,399][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000074400_76185600.pth -[2023-10-16 05:47:37,401][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000074656_76447744.pth -[2023-10-16 05:47:39,987][05218] Updated weights for policy 0, policy_version 76322 (0.0008) -[2023-10-16 05:47:40,119][05219] Updated weights for policy 1, policy_version 76070 (0.0009) -[2023-10-16 05:47:40,351][05218] Updated weights for policy 0, policy_version 76332 (0.0008) -[2023-10-16 05:47:40,480][05219] Updated weights for policy 1, policy_version 76080 (0.0009) -[2023-10-16 05:47:40,726][05218] Updated weights for policy 0, policy_version 76342 (0.0008) -[2023-10-16 05:47:40,841][05219] Updated weights for policy 1, policy_version 76090 (0.0007) -[2023-10-16 05:47:41,105][05218] Updated weights for policy 0, policy_version 76352 (0.0008) -[2023-10-16 05:47:42,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 156106752. Throughput: 0: 1800.9, 1: 1798.3. Samples: 39029376. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:47:42,351][03835] Avg episode reward: [(0, '6.980'), (1, '8.520')] -[2023-10-16 05:47:44,674][05219] Updated weights for policy 1, policy_version 76100 (0.0008) -[2023-10-16 05:47:44,751][05218] Updated weights for policy 0, policy_version 76362 (0.0010) -[2023-10-16 05:47:45,043][05219] Updated weights for policy 1, policy_version 76110 (0.0007) -[2023-10-16 05:47:45,131][05218] Updated weights for policy 0, policy_version 76372 (0.0008) -[2023-10-16 05:47:45,398][05219] Updated weights for policy 1, policy_version 76120 (0.0009) -[2023-10-16 05:47:45,509][05218] Updated weights for policy 0, policy_version 76382 (0.0008) -[2023-10-16 05:47:47,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 156172288. Throughput: 0: 1775.0, 1: 1785.7. Samples: 39049594. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:47:47,351][03835] Avg episode reward: [(0, '7.790'), (1, '7.330')] -[2023-10-16 05:47:49,262][05218] Updated weights for policy 0, policy_version 76392 (0.0009) -[2023-10-16 05:47:49,317][05219] Updated weights for policy 1, policy_version 76130 (0.0010) -[2023-10-16 05:47:49,634][05218] Updated weights for policy 0, policy_version 76402 (0.0008) -[2023-10-16 05:47:49,704][05219] Updated weights for policy 1, policy_version 76140 (0.0007) -[2023-10-16 05:47:50,010][05218] Updated weights for policy 0, policy_version 76412 (0.0008) -[2023-10-16 05:47:50,071][05219] Updated weights for policy 1, policy_version 76150 (0.0008) -[2023-10-16 05:47:50,428][05219] Updated weights for policy 1, policy_version 76160 (0.0009) -[2023-10-16 05:47:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 156237824. Throughput: 0: 1778.0, 1: 1785.4. Samples: 39071848. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:47:52,351][03835] Avg episode reward: [(0, '7.230'), (1, '7.580')] -[2023-10-16 05:47:53,738][05218] Updated weights for policy 0, policy_version 76422 (0.0009) -[2023-10-16 05:47:54,112][05218] Updated weights for policy 0, policy_version 76432 (0.0008) -[2023-10-16 05:47:54,279][05219] Updated weights for policy 1, policy_version 76170 (0.0008) -[2023-10-16 05:47:54,482][05218] Updated weights for policy 0, policy_version 76442 (0.0008) -[2023-10-16 05:47:54,632][05219] Updated weights for policy 1, policy_version 76180 (0.0008) -[2023-10-16 05:47:54,996][05219] Updated weights for policy 1, policy_version 76190 (0.0008) -[2023-10-16 05:47:57,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 156303360. Throughput: 0: 1775.6, 1: 1784.8. Samples: 39081486. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:47:57,351][03835] Avg episode reward: [(0, '6.980'), (1, '8.550')] -[2023-10-16 05:47:58,329][05218] Updated weights for policy 0, policy_version 76452 (0.0008) -[2023-10-16 05:47:58,706][05218] Updated weights for policy 0, policy_version 76462 (0.0009) -[2023-10-16 05:47:58,824][05219] Updated weights for policy 1, policy_version 76200 (0.0008) -[2023-10-16 05:47:59,079][05218] Updated weights for policy 0, policy_version 76472 (0.0008) -[2023-10-16 05:47:59,184][05219] Updated weights for policy 1, policy_version 76210 (0.0007) -[2023-10-16 05:47:59,555][05219] Updated weights for policy 1, policy_version 76220 (0.0008) -[2023-10-16 05:48:02,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 156368896. Throughput: 0: 1768.8, 1: 1780.5. Samples: 39103412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:48:02,351][03835] Avg episode reward: [(0, '7.410'), (1, '7.890')] -[2023-10-16 05:48:02,824][05218] Updated weights for policy 0, policy_version 76482 (0.0009) -[2023-10-16 05:48:03,196][05218] Updated weights for policy 0, policy_version 76492 (0.0009) -[2023-10-16 05:48:03,304][05219] Updated weights for policy 1, policy_version 76230 (0.0009) -[2023-10-16 05:48:03,569][05218] Updated weights for policy 0, policy_version 76502 (0.0010) -[2023-10-16 05:48:03,669][05219] Updated weights for policy 1, policy_version 76240 (0.0008) -[2023-10-16 05:48:03,951][05218] Updated weights for policy 0, policy_version 76512 (0.0008) -[2023-10-16 05:48:04,033][05219] Updated weights for policy 1, policy_version 76250 (0.0009) -[2023-10-16 05:48:07,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 156434432. Throughput: 0: 1798.4, 1: 1782.8. Samples: 39125890. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:48:07,351][03835] Avg episode reward: [(0, '7.000'), (1, '7.550')] -[2023-10-16 05:48:07,707][05218] Updated weights for policy 0, policy_version 76522 (0.0007) -[2023-10-16 05:48:07,875][05219] Updated weights for policy 1, policy_version 76260 (0.0008) -[2023-10-16 05:48:08,082][05218] Updated weights for policy 0, policy_version 76532 (0.0007) -[2023-10-16 05:48:08,242][05219] Updated weights for policy 1, policy_version 76270 (0.0009) -[2023-10-16 05:48:08,468][05218] Updated weights for policy 0, policy_version 76542 (0.0007) -[2023-10-16 05:48:08,615][05219] Updated weights for policy 1, policy_version 76280 (0.0007) -[2023-10-16 05:48:12,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 156499968. Throughput: 0: 1768.2, 1: 1784.5. Samples: 39135622. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:48:12,351][03835] Avg episode reward: [(0, '7.640'), (1, '7.390')] -[2023-10-16 05:48:12,433][05219] Updated weights for policy 1, policy_version 76290 (0.0007) -[2023-10-16 05:48:12,443][05218] Updated weights for policy 0, policy_version 76552 (0.0008) -[2023-10-16 05:48:12,799][05219] Updated weights for policy 1, policy_version 76300 (0.0008) -[2023-10-16 05:48:12,822][05218] Updated weights for policy 0, policy_version 76562 (0.0007) -[2023-10-16 05:48:13,164][05219] Updated weights for policy 1, policy_version 76310 (0.0007) -[2023-10-16 05:48:13,199][05218] Updated weights for policy 0, policy_version 76572 (0.0009) -[2023-10-16 05:48:13,538][05219] Updated weights for policy 1, policy_version 76320 (0.0008) -[2023-10-16 05:48:16,759][05218] Updated weights for policy 0, policy_version 76582 (0.0011) -[2023-10-16 05:48:17,130][05218] Updated weights for policy 0, policy_version 76592 (0.0010) -[2023-10-16 05:48:17,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 156565504. Throughput: 0: 1795.6, 1: 1775.2. Samples: 39157582. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:48:17,351][03835] Avg episode reward: [(0, '7.440'), (1, '7.590')] -[2023-10-16 05:48:17,502][05218] Updated weights for policy 0, policy_version 76602 (0.0009) -[2023-10-16 05:48:17,504][05219] Updated weights for policy 1, policy_version 76330 (0.0007) -[2023-10-16 05:48:17,869][05219] Updated weights for policy 1, policy_version 76340 (0.0008) -[2023-10-16 05:48:18,234][05219] Updated weights for policy 1, policy_version 76350 (0.0009) -[2023-10-16 05:48:21,243][05218] Updated weights for policy 0, policy_version 76612 (0.0008) -[2023-10-16 05:48:21,624][05218] Updated weights for policy 0, policy_version 76622 (0.0010) -[2023-10-16 05:48:22,003][05218] Updated weights for policy 0, policy_version 76632 (0.0008) -[2023-10-16 05:48:22,034][05219] Updated weights for policy 1, policy_version 76360 (0.0009) -[2023-10-16 05:48:22,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 156663808. Throughput: 0: 1772.5, 1: 1793.8. Samples: 39178018. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:48:22,351][03835] Avg episode reward: [(0, '7.640'), (1, '7.130')] -[2023-10-16 05:48:22,400][05219] Updated weights for policy 1, policy_version 76370 (0.0009) -[2023-10-16 05:48:22,770][05219] Updated weights for policy 1, policy_version 76380 (0.0008) -[2023-10-16 05:48:25,746][05218] Updated weights for policy 0, policy_version 76642 (0.0008) -[2023-10-16 05:48:26,120][05218] Updated weights for policy 0, policy_version 76652 (0.0011) -[2023-10-16 05:48:26,498][05218] Updated weights for policy 0, policy_version 76662 (0.0009) -[2023-10-16 05:48:26,540][05219] Updated weights for policy 1, policy_version 76390 (0.0008) -[2023-10-16 05:48:26,875][05218] Updated weights for policy 0, policy_version 76672 (0.0007) -[2023-10-16 05:48:26,903][05219] Updated weights for policy 1, policy_version 76400 (0.0008) -[2023-10-16 05:48:27,280][05219] Updated weights for policy 1, policy_version 76410 (0.0008) -[2023-10-16 05:48:27,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 156729344. Throughput: 0: 1792.3, 1: 1773.8. Samples: 39189852. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:48:27,351][03835] Avg episode reward: [(0, '7.360'), (1, '6.960')] -[2023-10-16 05:48:30,450][05218] Updated weights for policy 0, policy_version 76682 (0.0009) -[2023-10-16 05:48:30,834][05218] Updated weights for policy 0, policy_version 76692 (0.0010) -[2023-10-16 05:48:31,090][05219] Updated weights for policy 1, policy_version 76420 (0.0007) -[2023-10-16 05:48:31,205][05218] Updated weights for policy 0, policy_version 76702 (0.0008) -[2023-10-16 05:48:31,451][05219] Updated weights for policy 1, policy_version 76430 (0.0009) -[2023-10-16 05:48:31,816][05219] Updated weights for policy 1, policy_version 76440 (0.0008) -[2023-10-16 05:48:32,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14440.2). Total num frames: 156827648. Throughput: 0: 1781.5, 1: 1798.2. Samples: 39210678. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:48:32,351][03835] Avg episode reward: [(0, '7.030'), (1, '7.020')] -[2023-10-16 05:48:34,949][05218] Updated weights for policy 0, policy_version 76712 (0.0007) -[2023-10-16 05:48:35,332][05218] Updated weights for policy 0, policy_version 76722 (0.0007) -[2023-10-16 05:48:35,596][05219] Updated weights for policy 1, policy_version 76450 (0.0009) -[2023-10-16 05:48:35,710][05218] Updated weights for policy 0, policy_version 76732 (0.0009) -[2023-10-16 05:48:36,003][05219] Updated weights for policy 1, policy_version 76460 (0.0009) -[2023-10-16 05:48:36,372][05219] Updated weights for policy 1, policy_version 76470 (0.0008) -[2023-10-16 05:48:36,734][05219] Updated weights for policy 1, policy_version 76480 (0.0011) -[2023-10-16 05:48:37,351][03835] Fps is (10 sec: 16383.3, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 156893184. Throughput: 0: 1775.9, 1: 1770.5. Samples: 39231438. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:48:37,351][03835] Avg episode reward: [(0, '7.200'), (1, '7.170')] -[2023-10-16 05:48:39,367][05218] Updated weights for policy 0, policy_version 76742 (0.0008) -[2023-10-16 05:48:39,730][05218] Updated weights for policy 0, policy_version 76752 (0.0008) -[2023-10-16 05:48:40,107][05218] Updated weights for policy 0, policy_version 76762 (0.0007) -[2023-10-16 05:48:40,474][05219] Updated weights for policy 1, policy_version 76490 (0.0010) -[2023-10-16 05:48:40,846][05219] Updated weights for policy 1, policy_version 76500 (0.0007) -[2023-10-16 05:48:41,214][05219] Updated weights for policy 1, policy_version 76510 (0.0009) -[2023-10-16 05:48:42,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 156958720. Throughput: 0: 1780.1, 1: 1802.8. Samples: 39242714. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:48:42,352][03835] Avg episode reward: [(0, '7.340'), (1, '7.290')] -[2023-10-16 05:48:43,935][05218] Updated weights for policy 0, policy_version 76772 (0.0007) -[2023-10-16 05:48:44,311][05218] Updated weights for policy 0, policy_version 76782 (0.0007) -[2023-10-16 05:48:44,683][05218] Updated weights for policy 0, policy_version 76792 (0.0009) -[2023-10-16 05:48:44,894][05219] Updated weights for policy 1, policy_version 76520 (0.0007) -[2023-10-16 05:48:45,254][05219] Updated weights for policy 1, policy_version 76530 (0.0009) -[2023-10-16 05:48:45,626][05219] Updated weights for policy 1, policy_version 76540 (0.0008) -[2023-10-16 05:48:47,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 157024256. Throughput: 0: 1784.8, 1: 1780.2. Samples: 39263836. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:48:47,351][03835] Avg episode reward: [(0, '7.150'), (1, '7.560')] -[2023-10-16 05:48:48,679][05218] Updated weights for policy 0, policy_version 76802 (0.0008) -[2023-10-16 05:48:49,050][05218] Updated weights for policy 0, policy_version 76812 (0.0009) -[2023-10-16 05:48:49,399][05219] Updated weights for policy 1, policy_version 76550 (0.0008) -[2023-10-16 05:48:49,421][05218] Updated weights for policy 0, policy_version 76822 (0.0008) -[2023-10-16 05:48:49,766][05219] Updated weights for policy 1, policy_version 76560 (0.0008) -[2023-10-16 05:48:49,802][05218] Updated weights for policy 0, policy_version 76832 (0.0009) -[2023-10-16 05:48:50,133][05219] Updated weights for policy 1, policy_version 76570 (0.0007) -[2023-10-16 05:48:52,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 157089792. Throughput: 0: 1784.1, 1: 1777.9. Samples: 39286182. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:48:52,351][03835] Avg episode reward: [(0, '6.730'), (1, '7.860')] -[2023-10-16 05:48:53,440][05218] Updated weights for policy 0, policy_version 76842 (0.0009) -[2023-10-16 05:48:53,804][05219] Updated weights for policy 1, policy_version 76580 (0.0009) -[2023-10-16 05:48:53,822][05218] Updated weights for policy 0, policy_version 76852 (0.0008) -[2023-10-16 05:48:54,154][05219] Updated weights for policy 1, policy_version 76590 (0.0008) -[2023-10-16 05:48:54,191][05218] Updated weights for policy 0, policy_version 76862 (0.0008) -[2023-10-16 05:48:54,520][05219] Updated weights for policy 1, policy_version 76600 (0.0008) -[2023-10-16 05:48:57,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 157155328. Throughput: 0: 1787.1, 1: 1778.1. Samples: 39296058. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:48:57,351][03835] Avg episode reward: [(0, '6.830'), (1, '7.620')] -[2023-10-16 05:48:57,968][05218] Updated weights for policy 0, policy_version 76872 (0.0009) -[2023-10-16 05:48:58,098][05219] Updated weights for policy 1, policy_version 76610 (0.0008) -[2023-10-16 05:48:58,351][05218] Updated weights for policy 0, policy_version 76882 (0.0007) -[2023-10-16 05:48:58,468][05219] Updated weights for policy 1, policy_version 76620 (0.0009) -[2023-10-16 05:48:58,724][05218] Updated weights for policy 0, policy_version 76892 (0.0007) -[2023-10-16 05:48:58,836][05219] Updated weights for policy 1, policy_version 76630 (0.0008) -[2023-10-16 05:48:59,196][05219] Updated weights for policy 1, policy_version 76640 (0.0007) -[2023-10-16 05:49:02,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 157220864. Throughput: 0: 1780.6, 1: 1791.9. Samples: 39318342. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:49:02,351][03835] Avg episode reward: [(0, '6.230'), (1, '7.640')] -[2023-10-16 05:49:02,500][05218] Updated weights for policy 0, policy_version 76902 (0.0008) -[2023-10-16 05:49:02,879][05218] Updated weights for policy 0, policy_version 76912 (0.0008) -[2023-10-16 05:49:02,915][05219] Updated weights for policy 1, policy_version 76650 (0.0007) -[2023-10-16 05:49:03,259][05218] Updated weights for policy 0, policy_version 76922 (0.0008) -[2023-10-16 05:49:03,277][05219] Updated weights for policy 1, policy_version 76660 (0.0008) -[2023-10-16 05:49:03,645][05219] Updated weights for policy 1, policy_version 76670 (0.0009) -[2023-10-16 05:49:06,931][05218] Updated weights for policy 0, policy_version 76932 (0.0008) -[2023-10-16 05:49:07,302][05218] Updated weights for policy 0, policy_version 76942 (0.0007) -[2023-10-16 05:49:07,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 157286400. Throughput: 0: 1801.6, 1: 1800.4. Samples: 39340112. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:49:07,351][03835] Avg episode reward: [(0, '6.480'), (1, '7.410')] -[2023-10-16 05:49:07,607][05219] Updated weights for policy 1, policy_version 76680 (0.0008) -[2023-10-16 05:49:07,678][05218] Updated weights for policy 0, policy_version 76952 (0.0008) -[2023-10-16 05:49:07,965][05219] Updated weights for policy 1, policy_version 76690 (0.0008) -[2023-10-16 05:49:08,334][05219] Updated weights for policy 1, policy_version 76700 (0.0007) -[2023-10-16 05:49:11,458][05218] Updated weights for policy 0, policy_version 76962 (0.0007) -[2023-10-16 05:49:11,832][05218] Updated weights for policy 0, policy_version 76972 (0.0010) -[2023-10-16 05:49:12,005][05219] Updated weights for policy 1, policy_version 76710 (0.0008) -[2023-10-16 05:49:12,213][05218] Updated weights for policy 0, policy_version 76982 (0.0009) -[2023-10-16 05:49:12,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 157351936. Throughput: 0: 1782.3, 1: 1791.0. Samples: 39350652. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:49:12,351][03835] Avg episode reward: [(0, '7.200'), (1, '8.730')] -[2023-10-16 05:49:12,377][05219] Updated weights for policy 1, policy_version 76720 (0.0009) -[2023-10-16 05:49:12,575][05218] Updated weights for policy 0, policy_version 76992 (0.0009) -[2023-10-16 05:49:12,736][05219] Updated weights for policy 1, policy_version 76730 (0.0009) -[2023-10-16 05:49:16,298][05218] Updated weights for policy 0, policy_version 77002 (0.0010) -[2023-10-16 05:49:16,565][05219] Updated weights for policy 1, policy_version 76740 (0.0008) -[2023-10-16 05:49:16,674][05218] Updated weights for policy 0, policy_version 77012 (0.0007) -[2023-10-16 05:49:16,932][05219] Updated weights for policy 1, policy_version 76750 (0.0010) -[2023-10-16 05:49:17,045][05218] Updated weights for policy 0, policy_version 77022 (0.0007) -[2023-10-16 05:49:17,289][05219] Updated weights for policy 1, policy_version 76760 (0.0009) -[2023-10-16 05:49:17,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 157450240. Throughput: 0: 1799.5, 1: 1793.6. Samples: 39372370. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 05:49:17,351][03835] Avg episode reward: [(0, '6.740'), (1, '7.730')] -[2023-10-16 05:49:20,941][05218] Updated weights for policy 0, policy_version 77032 (0.0009) -[2023-10-16 05:49:21,048][05219] Updated weights for policy 1, policy_version 76770 (0.0008) -[2023-10-16 05:49:21,314][05218] Updated weights for policy 0, policy_version 77042 (0.0007) -[2023-10-16 05:49:21,419][05219] Updated weights for policy 1, policy_version 76780 (0.0007) -[2023-10-16 05:49:21,683][05218] Updated weights for policy 0, policy_version 77052 (0.0007) -[2023-10-16 05:49:21,775][05219] Updated weights for policy 1, policy_version 76790 (0.0007) -[2023-10-16 05:49:22,133][05219] Updated weights for policy 1, policy_version 76800 (0.0011) -[2023-10-16 05:49:22,350][03835] Fps is (10 sec: 19660.6, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 157548544. Throughput: 0: 1778.5, 1: 1796.9. Samples: 39392330. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) -[2023-10-16 05:49:22,351][03835] Avg episode reward: [(0, '6.740'), (1, '7.350')] -[2023-10-16 05:49:25,546][05218] Updated weights for policy 0, policy_version 77062 (0.0009) -[2023-10-16 05:49:25,926][05218] Updated weights for policy 0, policy_version 77072 (0.0011) -[2023-10-16 05:49:25,960][05219] Updated weights for policy 1, policy_version 76810 (0.0008) -[2023-10-16 05:49:26,301][05218] Updated weights for policy 0, policy_version 77082 (0.0009) -[2023-10-16 05:49:26,318][05219] Updated weights for policy 1, policy_version 76820 (0.0007) -[2023-10-16 05:49:26,685][05219] Updated weights for policy 1, policy_version 76830 (0.0009) -[2023-10-16 05:49:27,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 157614080. Throughput: 0: 1807.5, 1: 1797.7. Samples: 39404950. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) -[2023-10-16 05:49:27,351][03835] Avg episode reward: [(0, '7.820'), (1, '8.550')] -[2023-10-16 05:49:30,155][05218] Updated weights for policy 0, policy_version 77092 (0.0008) -[2023-10-16 05:49:30,373][05219] Updated weights for policy 1, policy_version 76840 (0.0008) -[2023-10-16 05:49:30,528][05218] Updated weights for policy 0, policy_version 77102 (0.0007) -[2023-10-16 05:49:30,744][05219] Updated weights for policy 1, policy_version 76850 (0.0008) -[2023-10-16 05:49:30,897][05218] Updated weights for policy 0, policy_version 77112 (0.0010) -[2023-10-16 05:49:31,104][05219] Updated weights for policy 1, policy_version 76860 (0.0010) -[2023-10-16 05:49:32,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 157679616. Throughput: 0: 1771.9, 1: 1799.2. Samples: 39424536. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) -[2023-10-16 05:49:32,351][03835] Avg episode reward: [(0, '7.300'), (1, '7.040')] -[2023-10-16 05:49:34,701][05218] Updated weights for policy 0, policy_version 77122 (0.0008) -[2023-10-16 05:49:34,971][05219] Updated weights for policy 1, policy_version 76870 (0.0007) -[2023-10-16 05:49:35,077][05218] Updated weights for policy 0, policy_version 77132 (0.0008) -[2023-10-16 05:49:35,335][05219] Updated weights for policy 1, policy_version 76880 (0.0008) -[2023-10-16 05:49:35,460][05218] Updated weights for policy 0, policy_version 77142 (0.0007) -[2023-10-16 05:49:35,692][05219] Updated weights for policy 1, policy_version 76890 (0.0010) -[2023-10-16 05:49:35,824][05218] Updated weights for policy 0, policy_version 77152 (0.0008) -[2023-10-16 05:49:37,350][03835] Fps is (10 sec: 13106.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 157745152. Throughput: 0: 1772.7, 1: 1791.3. Samples: 39446562. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) -[2023-10-16 05:49:37,352][03835] Avg episode reward: [(0, '7.490'), (1, '7.360')] -[2023-10-16 05:49:37,362][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000077152_79003648.pth... -[2023-10-16 05:49:37,362][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000076896_78741504.pth... -[2023-10-16 05:49:37,395][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000075488_77299712.pth -[2023-10-16 05:49:37,403][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000075232_77037568.pth -[2023-10-16 05:49:39,386][05218] Updated weights for policy 0, policy_version 77162 (0.0008) -[2023-10-16 05:49:39,521][05219] Updated weights for policy 1, policy_version 76900 (0.0008) -[2023-10-16 05:49:39,772][05218] Updated weights for policy 0, policy_version 77172 (0.0007) -[2023-10-16 05:49:39,887][05219] Updated weights for policy 1, policy_version 76910 (0.0008) -[2023-10-16 05:49:40,142][05218] Updated weights for policy 0, policy_version 77182 (0.0007) -[2023-10-16 05:49:40,253][05219] Updated weights for policy 1, policy_version 76920 (0.0007) -[2023-10-16 05:49:42,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 157810688. Throughput: 0: 1774.0, 1: 1801.5. Samples: 39456954. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) -[2023-10-16 05:49:42,351][03835] Avg episode reward: [(0, '7.430'), (1, '8.540')] -[2023-10-16 05:49:43,903][05218] Updated weights for policy 0, policy_version 77192 (0.0008) -[2023-10-16 05:49:44,094][05219] Updated weights for policy 1, policy_version 76930 (0.0008) -[2023-10-16 05:49:44,278][05218] Updated weights for policy 0, policy_version 77202 (0.0007) -[2023-10-16 05:49:44,453][05219] Updated weights for policy 1, policy_version 76940 (0.0008) -[2023-10-16 05:49:44,654][05218] Updated weights for policy 0, policy_version 77212 (0.0008) -[2023-10-16 05:49:44,832][05219] Updated weights for policy 1, policy_version 76950 (0.0009) -[2023-10-16 05:49:45,200][05219] Updated weights for policy 1, policy_version 76960 (0.0009) -[2023-10-16 05:49:47,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 157876224. Throughput: 0: 1785.9, 1: 1777.9. Samples: 39478712. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) -[2023-10-16 05:49:47,351][03835] Avg episode reward: [(0, '6.260'), (1, '7.840')] -[2023-10-16 05:49:48,473][05218] Updated weights for policy 0, policy_version 77222 (0.0009) -[2023-10-16 05:49:48,850][05218] Updated weights for policy 0, policy_version 77232 (0.0009) -[2023-10-16 05:49:49,144][05219] Updated weights for policy 1, policy_version 76970 (0.0007) -[2023-10-16 05:49:49,229][05218] Updated weights for policy 0, policy_version 77242 (0.0009) -[2023-10-16 05:49:49,510][05219] Updated weights for policy 1, policy_version 76980 (0.0007) -[2023-10-16 05:49:49,882][05219] Updated weights for policy 1, policy_version 76990 (0.0007) -[2023-10-16 05:49:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 157941760. Throughput: 0: 1791.6, 1: 1776.1. Samples: 39500658. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) -[2023-10-16 05:49:52,351][03835] Avg episode reward: [(0, '6.330'), (1, '8.150')] -[2023-10-16 05:49:52,947][05218] Updated weights for policy 0, policy_version 77252 (0.0009) -[2023-10-16 05:49:53,329][05218] Updated weights for policy 0, policy_version 77262 (0.0009) -[2023-10-16 05:49:53,697][05218] Updated weights for policy 0, policy_version 77272 (0.0009) -[2023-10-16 05:49:53,753][05219] Updated weights for policy 1, policy_version 77000 (0.0007) -[2023-10-16 05:49:54,119][05219] Updated weights for policy 1, policy_version 77010 (0.0008) -[2023-10-16 05:49:54,487][05219] Updated weights for policy 1, policy_version 77020 (0.0009) -[2023-10-16 05:49:57,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 158007296. Throughput: 0: 1776.6, 1: 1777.6. Samples: 39510592. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) -[2023-10-16 05:49:57,351][03835] Avg episode reward: [(0, '6.530'), (1, '7.850')] -[2023-10-16 05:49:57,495][05218] Updated weights for policy 0, policy_version 77282 (0.0009) -[2023-10-16 05:49:57,881][05218] Updated weights for policy 0, policy_version 77292 (0.0008) -[2023-10-16 05:49:58,190][05219] Updated weights for policy 1, policy_version 77030 (0.0008) -[2023-10-16 05:49:58,252][05218] Updated weights for policy 0, policy_version 77302 (0.0010) -[2023-10-16 05:49:58,554][05219] Updated weights for policy 1, policy_version 77040 (0.0007) -[2023-10-16 05:49:58,622][05218] Updated weights for policy 0, policy_version 77312 (0.0009) -[2023-10-16 05:49:58,922][05219] Updated weights for policy 1, policy_version 77050 (0.0007) -[2023-10-16 05:50:02,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 158072832. Throughput: 0: 1785.0, 1: 1775.9. Samples: 39532610. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) -[2023-10-16 05:50:02,351][03835] Avg episode reward: [(0, '7.200'), (1, '8.440')] -[2023-10-16 05:50:02,458][05218] Updated weights for policy 0, policy_version 77322 (0.0009) -[2023-10-16 05:50:02,610][05219] Updated weights for policy 1, policy_version 77060 (0.0009) -[2023-10-16 05:50:02,827][05218] Updated weights for policy 0, policy_version 77332 (0.0007) -[2023-10-16 05:50:02,984][05219] Updated weights for policy 1, policy_version 77070 (0.0008) -[2023-10-16 05:50:03,198][05218] Updated weights for policy 0, policy_version 77342 (0.0008) -[2023-10-16 05:50:03,348][05219] Updated weights for policy 1, policy_version 77080 (0.0008) -[2023-10-16 05:50:06,867][05219] Updated weights for policy 1, policy_version 77090 (0.0009) -[2023-10-16 05:50:06,981][05218] Updated weights for policy 0, policy_version 77352 (0.0009) -[2023-10-16 05:50:07,283][05219] Updated weights for policy 1, policy_version 77100 (0.0008) -[2023-10-16 05:50:07,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 158138368. Throughput: 0: 1791.5, 1: 1801.8. Samples: 39554032. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) -[2023-10-16 05:50:07,351][03835] Avg episode reward: [(0, '6.440'), (1, '8.140')] -[2023-10-16 05:50:07,362][05218] Updated weights for policy 0, policy_version 77362 (0.0008) -[2023-10-16 05:50:07,650][05219] Updated weights for policy 1, policy_version 77110 (0.0009) -[2023-10-16 05:50:07,729][05218] Updated weights for policy 0, policy_version 77372 (0.0007) -[2023-10-16 05:50:08,008][05219] Updated weights for policy 1, policy_version 77120 (0.0010) -[2023-10-16 05:50:11,404][05218] Updated weights for policy 0, policy_version 77382 (0.0007) -[2023-10-16 05:50:11,779][05218] Updated weights for policy 0, policy_version 77392 (0.0010) -[2023-10-16 05:50:11,839][05219] Updated weights for policy 1, policy_version 77130 (0.0007) -[2023-10-16 05:50:12,155][05218] Updated weights for policy 0, policy_version 77402 (0.0009) -[2023-10-16 05:50:12,194][05219] Updated weights for policy 1, policy_version 77140 (0.0007) -[2023-10-16 05:50:12,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 158203904. Throughput: 0: 1780.5, 1: 1776.3. Samples: 39565006. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) -[2023-10-16 05:50:12,351][03835] Avg episode reward: [(0, '7.330'), (1, '8.020')] -[2023-10-16 05:50:12,563][05219] Updated weights for policy 1, policy_version 77150 (0.0009) -[2023-10-16 05:50:15,882][05218] Updated weights for policy 0, policy_version 77412 (0.0009) -[2023-10-16 05:50:16,248][05218] Updated weights for policy 0, policy_version 77422 (0.0010) -[2023-10-16 05:50:16,464][05219] Updated weights for policy 1, policy_version 77160 (0.0008) -[2023-10-16 05:50:16,627][05218] Updated weights for policy 0, policy_version 77432 (0.0009) -[2023-10-16 05:50:16,836][05219] Updated weights for policy 1, policy_version 77170 (0.0008) -[2023-10-16 05:50:17,211][05219] Updated weights for policy 1, policy_version 77180 (0.0007) -[2023-10-16 05:50:17,350][03835] Fps is (10 sec: 19661.5, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 158334976. Throughput: 0: 1799.2, 1: 1800.0. Samples: 39586500. Policy #0 lag: (min: 25.0, avg: 36.2, max: 57.0) -[2023-10-16 05:50:17,351][03835] Avg episode reward: [(0, '7.600'), (1, '9.060')] -[2023-10-16 05:50:17,351][04891] Saving new best policy, reward=9.060! -[2023-10-16 05:50:20,376][05218] Updated weights for policy 0, policy_version 77442 (0.0008) -[2023-10-16 05:50:20,756][05218] Updated weights for policy 0, policy_version 77452 (0.0011) -[2023-10-16 05:50:20,943][05219] Updated weights for policy 1, policy_version 77190 (0.0007) -[2023-10-16 05:50:21,119][05218] Updated weights for policy 0, policy_version 77462 (0.0008) -[2023-10-16 05:50:21,312][05219] Updated weights for policy 1, policy_version 77200 (0.0007) -[2023-10-16 05:50:21,492][05218] Updated weights for policy 0, policy_version 77472 (0.0008) -[2023-10-16 05:50:21,684][05219] Updated weights for policy 1, policy_version 77210 (0.0008) -[2023-10-16 05:50:22,350][03835] Fps is (10 sec: 19660.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 158400512. Throughput: 0: 1781.5, 1: 1771.4. Samples: 39606444. Policy #0 lag: (min: 25.0, avg: 36.2, max: 57.0) -[2023-10-16 05:50:22,351][03835] Avg episode reward: [(0, '6.880'), (1, '8.410')] -[2023-10-16 05:50:25,266][05218] Updated weights for policy 0, policy_version 77482 (0.0007) -[2023-10-16 05:50:25,541][05219] Updated weights for policy 1, policy_version 77220 (0.0010) -[2023-10-16 05:50:25,643][05218] Updated weights for policy 0, policy_version 77492 (0.0007) -[2023-10-16 05:50:25,910][05219] Updated weights for policy 1, policy_version 77230 (0.0009) -[2023-10-16 05:50:26,007][05218] Updated weights for policy 0, policy_version 77502 (0.0008) -[2023-10-16 05:50:26,274][05219] Updated weights for policy 1, policy_version 77240 (0.0008) -[2023-10-16 05:50:27,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 158466048. Throughput: 0: 1802.8, 1: 1789.0. Samples: 39618584. Policy #0 lag: (min: 25.0, avg: 36.2, max: 57.0) -[2023-10-16 05:50:27,351][03835] Avg episode reward: [(0, '7.220'), (1, '7.520')] -[2023-10-16 05:50:29,635][05218] Updated weights for policy 0, policy_version 77512 (0.0007) -[2023-10-16 05:50:30,016][05218] Updated weights for policy 0, policy_version 77522 (0.0009) -[2023-10-16 05:50:30,110][05219] Updated weights for policy 1, policy_version 77250 (0.0007) -[2023-10-16 05:50:30,397][05218] Updated weights for policy 0, policy_version 77532 (0.0008) -[2023-10-16 05:50:30,475][05219] Updated weights for policy 1, policy_version 77260 (0.0008) -[2023-10-16 05:50:30,841][05219] Updated weights for policy 1, policy_version 77270 (0.0009) -[2023-10-16 05:50:31,199][05219] Updated weights for policy 1, policy_version 77280 (0.0007) -[2023-10-16 05:50:32,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 158531584. Throughput: 0: 1782.5, 1: 1774.7. Samples: 39638788. Policy #0 lag: (min: 25.0, avg: 36.2, max: 57.0) -[2023-10-16 05:50:32,352][03835] Avg episode reward: [(0, '7.190'), (1, '8.290')] -[2023-10-16 05:50:34,154][05218] Updated weights for policy 0, policy_version 77542 (0.0007) -[2023-10-16 05:50:34,537][05218] Updated weights for policy 0, policy_version 77552 (0.0010) -[2023-10-16 05:50:34,911][05218] Updated weights for policy 0, policy_version 77562 (0.0009) -[2023-10-16 05:50:34,987][05219] Updated weights for policy 1, policy_version 77290 (0.0009) -[2023-10-16 05:50:35,354][05219] Updated weights for policy 1, policy_version 77300 (0.0008) -[2023-10-16 05:50:35,720][05219] Updated weights for policy 1, policy_version 77310 (0.0011) -[2023-10-16 05:50:37,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 158597120. Throughput: 0: 1787.4, 1: 1773.3. Samples: 39660890. Policy #0 lag: (min: 25.0, avg: 36.2, max: 57.0) -[2023-10-16 05:50:37,351][03835] Avg episode reward: [(0, '6.760'), (1, '7.960')] -[2023-10-16 05:50:38,702][05218] Updated weights for policy 0, policy_version 77572 (0.0008) -[2023-10-16 05:50:39,086][05218] Updated weights for policy 0, policy_version 77582 (0.0008) -[2023-10-16 05:50:39,450][05218] Updated weights for policy 0, policy_version 77592 (0.0007) -[2023-10-16 05:50:39,495][05219] Updated weights for policy 1, policy_version 77320 (0.0007) -[2023-10-16 05:50:39,859][05219] Updated weights for policy 1, policy_version 77330 (0.0007) -[2023-10-16 05:50:40,226][05219] Updated weights for policy 1, policy_version 77340 (0.0007) -[2023-10-16 05:50:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 158662656. Throughput: 0: 1786.8, 1: 1785.1. Samples: 39671332. Policy #0 lag: (min: 25.0, avg: 36.2, max: 57.0) -[2023-10-16 05:50:42,351][03835] Avg episode reward: [(0, '6.700'), (1, '7.620')] -[2023-10-16 05:50:43,013][05218] Updated weights for policy 0, policy_version 77602 (0.0007) -[2023-10-16 05:50:43,389][05218] Updated weights for policy 0, policy_version 77612 (0.0008) -[2023-10-16 05:50:43,767][05218] Updated weights for policy 0, policy_version 77622 (0.0009) -[2023-10-16 05:50:44,116][05219] Updated weights for policy 1, policy_version 77350 (0.0008) -[2023-10-16 05:50:44,138][05218] Updated weights for policy 0, policy_version 77632 (0.0009) -[2023-10-16 05:50:44,479][05219] Updated weights for policy 1, policy_version 77360 (0.0010) -[2023-10-16 05:50:44,852][05219] Updated weights for policy 1, policy_version 77370 (0.0010) -[2023-10-16 05:50:47,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 158728192. Throughput: 0: 1793.9, 1: 1774.9. Samples: 39693208. Policy #0 lag: (min: 25.0, avg: 36.2, max: 57.0) -[2023-10-16 05:50:47,351][03835] Avg episode reward: [(0, '6.360'), (1, '8.350')] -[2023-10-16 05:50:47,741][05218] Updated weights for policy 0, policy_version 77642 (0.0008) -[2023-10-16 05:50:48,119][05218] Updated weights for policy 0, policy_version 77652 (0.0009) -[2023-10-16 05:50:48,492][05218] Updated weights for policy 0, policy_version 77662 (0.0010) -[2023-10-16 05:50:48,664][05219] Updated weights for policy 1, policy_version 77380 (0.0009) -[2023-10-16 05:50:49,029][05219] Updated weights for policy 1, policy_version 77390 (0.0007) -[2023-10-16 05:50:49,383][05219] Updated weights for policy 1, policy_version 77400 (0.0008) -[2023-10-16 05:50:52,211][05218] Updated weights for policy 0, policy_version 77672 (0.0008) -[2023-10-16 05:50:52,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 158793728. Throughput: 0: 1801.1, 1: 1774.5. Samples: 39714932. Policy #0 lag: (min: 25.0, avg: 36.2, max: 57.0) -[2023-10-16 05:50:52,351][03835] Avg episode reward: [(0, '6.930'), (1, '7.720')] -[2023-10-16 05:50:52,585][05218] Updated weights for policy 0, policy_version 77682 (0.0008) -[2023-10-16 05:50:52,965][05218] Updated weights for policy 0, policy_version 77692 (0.0008) -[2023-10-16 05:50:53,232][05219] Updated weights for policy 1, policy_version 77410 (0.0009) -[2023-10-16 05:50:53,615][05219] Updated weights for policy 1, policy_version 77420 (0.0010) -[2023-10-16 05:50:53,971][05219] Updated weights for policy 1, policy_version 77430 (0.0009) -[2023-10-16 05:50:54,335][05219] Updated weights for policy 1, policy_version 77440 (0.0008) -[2023-10-16 05:50:56,900][05218] Updated weights for policy 0, policy_version 77702 (0.0008) -[2023-10-16 05:50:57,271][05218] Updated weights for policy 0, policy_version 77712 (0.0007) -[2023-10-16 05:50:57,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 158859264. Throughput: 0: 1791.2, 1: 1767.2. Samples: 39725136. Policy #0 lag: (min: 25.0, avg: 36.2, max: 57.0) -[2023-10-16 05:50:57,351][03835] Avg episode reward: [(0, '6.940'), (1, '8.070')] -[2023-10-16 05:50:57,653][05218] Updated weights for policy 0, policy_version 77722 (0.0007) -[2023-10-16 05:50:58,087][05219] Updated weights for policy 1, policy_version 77450 (0.0007) -[2023-10-16 05:50:58,460][05219] Updated weights for policy 1, policy_version 77460 (0.0008) -[2023-10-16 05:50:58,823][05219] Updated weights for policy 1, policy_version 77470 (0.0009) -[2023-10-16 05:51:01,298][05218] Updated weights for policy 0, policy_version 77732 (0.0009) -[2023-10-16 05:51:01,665][05218] Updated weights for policy 0, policy_version 77742 (0.0008) -[2023-10-16 05:51:02,037][05218] Updated weights for policy 0, policy_version 77752 (0.0008) -[2023-10-16 05:51:02,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 158957568. Throughput: 0: 1806.0, 1: 1771.3. Samples: 39747478. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-16 05:51:02,350][03835] Avg episode reward: [(0, '6.860'), (1, '7.550')] -[2023-10-16 05:51:02,465][05219] Updated weights for policy 1, policy_version 77480 (0.0010) -[2023-10-16 05:51:02,827][05219] Updated weights for policy 1, policy_version 77490 (0.0009) -[2023-10-16 05:51:03,200][05219] Updated weights for policy 1, policy_version 77500 (0.0008) -[2023-10-16 05:51:05,661][05218] Updated weights for policy 0, policy_version 77762 (0.0007) -[2023-10-16 05:51:06,035][05218] Updated weights for policy 0, policy_version 77772 (0.0007) -[2023-10-16 05:51:06,408][05218] Updated weights for policy 0, policy_version 77782 (0.0009) -[2023-10-16 05:51:06,783][05218] Updated weights for policy 0, policy_version 77792 (0.0008) -[2023-10-16 05:51:06,872][05219] Updated weights for policy 1, policy_version 77510 (0.0007) -[2023-10-16 05:51:07,243][05219] Updated weights for policy 1, policy_version 77520 (0.0008) -[2023-10-16 05:51:07,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 159023104. Throughput: 0: 1804.5, 1: 1800.6. Samples: 39768670. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-16 05:51:07,351][03835] Avg episode reward: [(0, '6.760'), (1, '7.350')] -[2023-10-16 05:51:07,602][05219] Updated weights for policy 1, policy_version 77530 (0.0007) -[2023-10-16 05:51:10,372][05218] Updated weights for policy 0, policy_version 77802 (0.0009) -[2023-10-16 05:51:10,754][05218] Updated weights for policy 0, policy_version 77812 (0.0008) -[2023-10-16 05:51:11,131][05218] Updated weights for policy 0, policy_version 77822 (0.0008) -[2023-10-16 05:51:11,287][05219] Updated weights for policy 1, policy_version 77540 (0.0008) -[2023-10-16 05:51:11,648][05219] Updated weights for policy 1, policy_version 77550 (0.0008) -[2023-10-16 05:51:12,015][05219] Updated weights for policy 1, policy_version 77560 (0.0010) -[2023-10-16 05:51:12,350][03835] Fps is (10 sec: 16383.7, 60 sec: 15291.7, 300 sec: 14440.1). Total num frames: 159121408. Throughput: 0: 1812.3, 1: 1784.5. Samples: 39780440. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-16 05:51:12,351][03835] Avg episode reward: [(0, '6.730'), (1, '6.970')] -[2023-10-16 05:51:14,981][05218] Updated weights for policy 0, policy_version 77832 (0.0010) -[2023-10-16 05:51:15,350][05218] Updated weights for policy 0, policy_version 77842 (0.0009) -[2023-10-16 05:51:15,729][05218] Updated weights for policy 0, policy_version 77852 (0.0009) -[2023-10-16 05:51:15,810][05219] Updated weights for policy 1, policy_version 77570 (0.0008) -[2023-10-16 05:51:16,177][05219] Updated weights for policy 1, policy_version 77580 (0.0007) -[2023-10-16 05:51:16,535][05219] Updated weights for policy 1, policy_version 77590 (0.0007) -[2023-10-16 05:51:16,900][05219] Updated weights for policy 1, policy_version 77600 (0.0009) -[2023-10-16 05:51:17,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 159186944. Throughput: 0: 1801.8, 1: 1810.1. Samples: 39801326. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-16 05:51:17,351][03835] Avg episode reward: [(0, '6.210'), (1, '8.350')] -[2023-10-16 05:51:19,540][05218] Updated weights for policy 0, policy_version 77862 (0.0010) -[2023-10-16 05:51:19,927][05218] Updated weights for policy 0, policy_version 77872 (0.0008) -[2023-10-16 05:51:20,309][05218] Updated weights for policy 0, policy_version 77882 (0.0009) -[2023-10-16 05:51:20,669][05219] Updated weights for policy 1, policy_version 77610 (0.0009) -[2023-10-16 05:51:21,032][05219] Updated weights for policy 1, policy_version 77620 (0.0010) -[2023-10-16 05:51:21,400][05219] Updated weights for policy 1, policy_version 77630 (0.0009) -[2023-10-16 05:51:22,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 159252480. Throughput: 0: 1804.9, 1: 1794.6. Samples: 39822866. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-16 05:51:22,351][03835] Avg episode reward: [(0, '6.380'), (1, '7.820')] -[2023-10-16 05:51:24,004][05218] Updated weights for policy 0, policy_version 77892 (0.0009) -[2023-10-16 05:51:24,377][05218] Updated weights for policy 0, policy_version 77902 (0.0008) -[2023-10-16 05:51:24,763][05218] Updated weights for policy 0, policy_version 77912 (0.0007) -[2023-10-16 05:51:25,299][05219] Updated weights for policy 1, policy_version 77640 (0.0009) -[2023-10-16 05:51:25,673][05219] Updated weights for policy 1, policy_version 77650 (0.0010) -[2023-10-16 05:51:26,043][05219] Updated weights for policy 1, policy_version 77660 (0.0009) -[2023-10-16 05:51:27,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 159318016. Throughput: 0: 1800.8, 1: 1802.9. Samples: 39833502. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-16 05:51:27,351][03835] Avg episode reward: [(0, '6.500'), (1, '7.560')] -[2023-10-16 05:51:28,348][05218] Updated weights for policy 0, policy_version 77922 (0.0009) -[2023-10-16 05:51:28,731][05218] Updated weights for policy 0, policy_version 77932 (0.0007) -[2023-10-16 05:51:29,100][05218] Updated weights for policy 0, policy_version 77942 (0.0008) -[2023-10-16 05:51:29,478][05218] Updated weights for policy 0, policy_version 77952 (0.0010) -[2023-10-16 05:51:29,707][05219] Updated weights for policy 1, policy_version 77670 (0.0009) -[2023-10-16 05:51:30,067][05219] Updated weights for policy 1, policy_version 77680 (0.0008) -[2023-10-16 05:51:30,433][05219] Updated weights for policy 1, policy_version 77690 (0.0008) -[2023-10-16 05:51:32,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 159383552. Throughput: 0: 1809.6, 1: 1790.5. Samples: 39855212. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-16 05:51:32,351][03835] Avg episode reward: [(0, '6.480'), (1, '7.810')] -[2023-10-16 05:51:33,025][05218] Updated weights for policy 0, policy_version 77962 (0.0010) -[2023-10-16 05:51:33,406][05218] Updated weights for policy 0, policy_version 77972 (0.0010) -[2023-10-16 05:51:33,770][05218] Updated weights for policy 0, policy_version 77982 (0.0007) -[2023-10-16 05:51:34,221][05219] Updated weights for policy 1, policy_version 77700 (0.0008) -[2023-10-16 05:51:34,588][05219] Updated weights for policy 1, policy_version 77710 (0.0010) -[2023-10-16 05:51:34,960][05219] Updated weights for policy 1, policy_version 77720 (0.0009) -[2023-10-16 05:51:37,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 159449088. Throughput: 0: 1820.9, 1: 1790.3. Samples: 39877438. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-16 05:51:37,351][03835] Avg episode reward: [(0, '7.060'), (1, '8.170')] -[2023-10-16 05:51:37,362][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000077728_79593472.pth... -[2023-10-16 05:51:37,398][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000076064_77889536.pth -[2023-10-16 05:51:37,482][05218] Updated weights for policy 0, policy_version 77992 (0.0009) -[2023-10-16 05:51:37,850][05218] Updated weights for policy 0, policy_version 78002 (0.0009) -[2023-10-16 05:51:38,221][05218] Updated weights for policy 0, policy_version 78012 (0.0008) -[2023-10-16 05:51:38,369][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000078016_79888384.pth... -[2023-10-16 05:51:38,408][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000076320_78151680.pth -[2023-10-16 05:51:38,712][05219] Updated weights for policy 1, policy_version 77730 (0.0010) -[2023-10-16 05:51:39,087][05219] Updated weights for policy 1, policy_version 77740 (0.0009) -[2023-10-16 05:51:39,449][05219] Updated weights for policy 1, policy_version 77750 (0.0010) -[2023-10-16 05:51:39,818][05219] Updated weights for policy 1, policy_version 77760 (0.0011) -[2023-10-16 05:51:41,905][05218] Updated weights for policy 0, policy_version 78022 (0.0011) -[2023-10-16 05:51:42,281][05218] Updated weights for policy 0, policy_version 78032 (0.0010) -[2023-10-16 05:51:42,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 159514624. Throughput: 0: 1816.8, 1: 1791.3. Samples: 39887498. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-16 05:51:42,351][03835] Avg episode reward: [(0, '7.040'), (1, '7.620')] -[2023-10-16 05:51:42,668][05218] Updated weights for policy 0, policy_version 78042 (0.0008) -[2023-10-16 05:51:43,532][05219] Updated weights for policy 1, policy_version 77770 (0.0007) -[2023-10-16 05:51:43,888][05219] Updated weights for policy 1, policy_version 77780 (0.0009) -[2023-10-16 05:51:44,252][05219] Updated weights for policy 1, policy_version 77790 (0.0007) -[2023-10-16 05:51:46,368][05218] Updated weights for policy 0, policy_version 78052 (0.0007) -[2023-10-16 05:51:46,743][05218] Updated weights for policy 0, policy_version 78062 (0.0009) -[2023-10-16 05:51:47,121][05218] Updated weights for policy 0, policy_version 78072 (0.0010) -[2023-10-16 05:51:47,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 159580160. Throughput: 0: 1817.5, 1: 1791.9. Samples: 39909904. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-16 05:51:47,351][03835] Avg episode reward: [(0, '7.420'), (1, '7.970')] -[2023-10-16 05:51:48,006][05219] Updated weights for policy 1, policy_version 77800 (0.0007) -[2023-10-16 05:51:48,371][05219] Updated weights for policy 1, policy_version 77810 (0.0009) -[2023-10-16 05:51:48,748][05219] Updated weights for policy 1, policy_version 77820 (0.0008) -[2023-10-16 05:51:50,812][05218] Updated weights for policy 0, policy_version 78082 (0.0010) -[2023-10-16 05:51:51,195][05218] Updated weights for policy 0, policy_version 78092 (0.0009) -[2023-10-16 05:51:51,571][05218] Updated weights for policy 0, policy_version 78102 (0.0010) -[2023-10-16 05:51:51,939][05218] Updated weights for policy 0, policy_version 78112 (0.0008) -[2023-10-16 05:51:52,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 159678464. Throughput: 0: 1809.6, 1: 1802.3. Samples: 39931206. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-16 05:51:52,351][03835] Avg episode reward: [(0, '6.780'), (1, '8.720')] -[2023-10-16 05:51:52,446][05219] Updated weights for policy 1, policy_version 77830 (0.0007) -[2023-10-16 05:51:52,817][05219] Updated weights for policy 1, policy_version 77840 (0.0007) -[2023-10-16 05:51:53,175][05219] Updated weights for policy 1, policy_version 77850 (0.0008) -[2023-10-16 05:51:55,640][05218] Updated weights for policy 0, policy_version 78122 (0.0007) -[2023-10-16 05:51:56,012][05218] Updated weights for policy 0, policy_version 78132 (0.0010) -[2023-10-16 05:51:56,390][05218] Updated weights for policy 0, policy_version 78142 (0.0009) -[2023-10-16 05:51:56,983][05219] Updated weights for policy 1, policy_version 77860 (0.0009) -[2023-10-16 05:51:57,345][05219] Updated weights for policy 1, policy_version 77870 (0.0011) -[2023-10-16 05:51:57,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 159744000. Throughput: 0: 1809.3, 1: 1786.0. Samples: 39942230. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-16 05:51:57,351][03835] Avg episode reward: [(0, '7.030'), (1, '7.590')] -[2023-10-16 05:51:57,700][05219] Updated weights for policy 1, policy_version 77880 (0.0008) -[2023-10-16 05:52:00,032][05218] Updated weights for policy 0, policy_version 78152 (0.0008) -[2023-10-16 05:52:00,403][05218] Updated weights for policy 0, policy_version 78162 (0.0007) -[2023-10-16 05:52:00,781][05218] Updated weights for policy 0, policy_version 78172 (0.0009) -[2023-10-16 05:52:01,441][05219] Updated weights for policy 1, policy_version 77890 (0.0008) -[2023-10-16 05:52:01,804][05219] Updated weights for policy 1, policy_version 77900 (0.0007) -[2023-10-16 05:52:02,171][05219] Updated weights for policy 1, policy_version 77910 (0.0008) -[2023-10-16 05:52:02,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 159809536. Throughput: 0: 1809.4, 1: 1797.4. Samples: 39963630. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-16 05:52:02,352][03835] Avg episode reward: [(0, '7.150'), (1, '7.570')] -[2023-10-16 05:52:02,531][05219] Updated weights for policy 1, policy_version 77920 (0.0008) -[2023-10-16 05:52:04,576][05218] Updated weights for policy 0, policy_version 78182 (0.0007) -[2023-10-16 05:52:04,965][05218] Updated weights for policy 0, policy_version 78192 (0.0009) -[2023-10-16 05:52:05,341][05218] Updated weights for policy 0, policy_version 78202 (0.0010) -[2023-10-16 05:52:06,346][05219] Updated weights for policy 1, policy_version 77930 (0.0009) -[2023-10-16 05:52:06,713][05219] Updated weights for policy 1, policy_version 77940 (0.0007) -[2023-10-16 05:52:07,081][05219] Updated weights for policy 1, policy_version 77950 (0.0011) -[2023-10-16 05:52:07,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 159907840. Throughput: 0: 1807.6, 1: 1787.4. Samples: 39984642. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-16 05:52:07,352][03835] Avg episode reward: [(0, '6.410'), (1, '8.200')] -[2023-10-16 05:52:09,108][05218] Updated weights for policy 0, policy_version 78212 (0.0011) -[2023-10-16 05:52:09,484][05218] Updated weights for policy 0, policy_version 78222 (0.0009) -[2023-10-16 05:52:09,852][05218] Updated weights for policy 0, policy_version 78232 (0.0008) -[2023-10-16 05:52:10,826][05219] Updated weights for policy 1, policy_version 77960 (0.0008) -[2023-10-16 05:52:11,188][05219] Updated weights for policy 1, policy_version 77970 (0.0008) -[2023-10-16 05:52:11,556][05219] Updated weights for policy 1, policy_version 77980 (0.0007) -[2023-10-16 05:52:12,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 159973376. Throughput: 0: 1810.6, 1: 1796.2. Samples: 39995810. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-16 05:52:12,351][03835] Avg episode reward: [(0, '6.240'), (1, '8.180')] -[2023-10-16 05:52:13,463][05218] Updated weights for policy 0, policy_version 78242 (0.0008) -[2023-10-16 05:52:13,841][05218] Updated weights for policy 0, policy_version 78252 (0.0010) -[2023-10-16 05:52:14,218][05218] Updated weights for policy 0, policy_version 78262 (0.0009) -[2023-10-16 05:52:14,599][05218] Updated weights for policy 0, policy_version 78272 (0.0008) -[2023-10-16 05:52:15,227][05219] Updated weights for policy 1, policy_version 77990 (0.0009) -[2023-10-16 05:52:15,593][05219] Updated weights for policy 1, policy_version 78000 (0.0009) -[2023-10-16 05:52:15,971][05219] Updated weights for policy 1, policy_version 78010 (0.0010) -[2023-10-16 05:52:17,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 160038912. Throughput: 0: 1806.1, 1: 1792.2. Samples: 40017136. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-16 05:52:17,351][03835] Avg episode reward: [(0, '6.320'), (1, '8.440')] -[2023-10-16 05:52:18,388][05218] Updated weights for policy 0, policy_version 78282 (0.0008) -[2023-10-16 05:52:18,767][05218] Updated weights for policy 0, policy_version 78292 (0.0009) -[2023-10-16 05:52:19,147][05218] Updated weights for policy 0, policy_version 78302 (0.0009) -[2023-10-16 05:52:19,883][05219] Updated weights for policy 1, policy_version 78020 (0.0009) -[2023-10-16 05:52:20,256][05219] Updated weights for policy 1, policy_version 78030 (0.0007) -[2023-10-16 05:52:20,616][05219] Updated weights for policy 1, policy_version 78040 (0.0008) -[2023-10-16 05:52:22,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 160104448. Throughput: 0: 1801.9, 1: 1795.2. Samples: 40039308. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-16 05:52:22,351][03835] Avg episode reward: [(0, '6.270'), (1, '9.050')] -[2023-10-16 05:52:23,014][05218] Updated weights for policy 0, policy_version 78312 (0.0009) -[2023-10-16 05:52:23,391][05218] Updated weights for policy 0, policy_version 78322 (0.0009) -[2023-10-16 05:52:23,766][05218] Updated weights for policy 0, policy_version 78332 (0.0009) -[2023-10-16 05:52:24,420][05219] Updated weights for policy 1, policy_version 78050 (0.0009) -[2023-10-16 05:52:24,834][05219] Updated weights for policy 1, policy_version 78060 (0.0010) -[2023-10-16 05:52:25,204][05219] Updated weights for policy 1, policy_version 78070 (0.0008) -[2023-10-16 05:52:25,573][05219] Updated weights for policy 1, policy_version 78080 (0.0009) -[2023-10-16 05:52:27,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 160169984. Throughput: 0: 1795.0, 1: 1804.4. Samples: 40049474. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-16 05:52:27,351][03835] Avg episode reward: [(0, '6.670'), (1, '7.890')] -[2023-10-16 05:52:27,563][05218] Updated weights for policy 0, policy_version 78342 (0.0007) -[2023-10-16 05:52:27,935][05218] Updated weights for policy 0, policy_version 78352 (0.0007) -[2023-10-16 05:52:28,310][05218] Updated weights for policy 0, policy_version 78362 (0.0008) -[2023-10-16 05:52:29,346][05219] Updated weights for policy 1, policy_version 78090 (0.0009) -[2023-10-16 05:52:29,709][05219] Updated weights for policy 1, policy_version 78100 (0.0007) -[2023-10-16 05:52:30,068][05219] Updated weights for policy 1, policy_version 78110 (0.0007) -[2023-10-16 05:52:32,016][05218] Updated weights for policy 0, policy_version 78372 (0.0009) -[2023-10-16 05:52:32,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 160235520. Throughput: 0: 1798.0, 1: 1786.3. Samples: 40071198. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-16 05:52:32,351][03835] Avg episode reward: [(0, '6.670'), (1, '7.900')] -[2023-10-16 05:52:32,398][05218] Updated weights for policy 0, policy_version 78382 (0.0009) -[2023-10-16 05:52:32,780][05218] Updated weights for policy 0, policy_version 78392 (0.0009) -[2023-10-16 05:52:33,900][05219] Updated weights for policy 1, policy_version 78120 (0.0007) -[2023-10-16 05:52:34,258][05219] Updated weights for policy 1, policy_version 78130 (0.0008) -[2023-10-16 05:52:34,624][05219] Updated weights for policy 1, policy_version 78140 (0.0008) -[2023-10-16 05:52:36,562][05218] Updated weights for policy 0, policy_version 78402 (0.0009) -[2023-10-16 05:52:36,944][05218] Updated weights for policy 0, policy_version 78412 (0.0010) -[2023-10-16 05:52:37,313][05218] Updated weights for policy 0, policy_version 78422 (0.0011) -[2023-10-16 05:52:37,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 160301056. Throughput: 0: 1801.5, 1: 1788.4. Samples: 40092754. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-16 05:52:37,351][03835] Avg episode reward: [(0, '6.260'), (1, '8.230')] -[2023-10-16 05:52:37,687][05218] Updated weights for policy 0, policy_version 78432 (0.0007) -[2023-10-16 05:52:38,236][05219] Updated weights for policy 1, policy_version 78150 (0.0007) -[2023-10-16 05:52:38,596][05219] Updated weights for policy 1, policy_version 78160 (0.0007) -[2023-10-16 05:52:38,967][05219] Updated weights for policy 1, policy_version 78170 (0.0010) -[2023-10-16 05:52:41,416][05218] Updated weights for policy 0, policy_version 78442 (0.0008) -[2023-10-16 05:52:41,790][05218] Updated weights for policy 0, policy_version 78452 (0.0009) -[2023-10-16 05:52:42,173][05218] Updated weights for policy 0, policy_version 78462 (0.0010) -[2023-10-16 05:52:42,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 160399360. Throughput: 0: 1794.5, 1: 1790.8. Samples: 40103570. Policy #0 lag: (min: 29.0, avg: 29.2, max: 37.0) -[2023-10-16 05:52:42,351][03835] Avg episode reward: [(0, '6.460'), (1, '9.250')] -[2023-10-16 05:52:42,353][04891] Saving new best policy, reward=9.250! -[2023-10-16 05:52:42,680][05219] Updated weights for policy 1, policy_version 78180 (0.0008) -[2023-10-16 05:52:43,046][05219] Updated weights for policy 1, policy_version 78190 (0.0009) -[2023-10-16 05:52:43,415][05219] Updated weights for policy 1, policy_version 78200 (0.0008) -[2023-10-16 05:52:45,714][05218] Updated weights for policy 0, policy_version 78472 (0.0008) -[2023-10-16 05:52:46,082][05218] Updated weights for policy 0, policy_version 78482 (0.0007) -[2023-10-16 05:52:46,460][05218] Updated weights for policy 0, policy_version 78492 (0.0008) -[2023-10-16 05:52:47,244][05219] Updated weights for policy 1, policy_version 78210 (0.0008) -[2023-10-16 05:52:47,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 160464896. Throughput: 0: 1801.2, 1: 1782.2. Samples: 40124882. Policy #0 lag: (min: 29.0, avg: 29.2, max: 37.0) -[2023-10-16 05:52:47,351][03835] Avg episode reward: [(0, '6.680'), (1, '8.520')] -[2023-10-16 05:52:47,614][05219] Updated weights for policy 1, policy_version 78220 (0.0009) -[2023-10-16 05:52:47,984][05219] Updated weights for policy 1, policy_version 78230 (0.0007) -[2023-10-16 05:52:48,341][05219] Updated weights for policy 1, policy_version 78240 (0.0008) -[2023-10-16 05:52:50,273][05218] Updated weights for policy 0, policy_version 78502 (0.0008) -[2023-10-16 05:52:50,656][05218] Updated weights for policy 0, policy_version 78512 (0.0010) -[2023-10-16 05:52:51,038][05218] Updated weights for policy 0, policy_version 78522 (0.0010) -[2023-10-16 05:52:52,183][05219] Updated weights for policy 1, policy_version 78250 (0.0008) -[2023-10-16 05:52:52,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 160530432. Throughput: 0: 1789.3, 1: 1800.4. Samples: 40146176. Policy #0 lag: (min: 29.0, avg: 29.2, max: 37.0) -[2023-10-16 05:52:52,351][03835] Avg episode reward: [(0, '6.260'), (1, '7.490')] -[2023-10-16 05:52:52,551][05219] Updated weights for policy 1, policy_version 78260 (0.0008) -[2023-10-16 05:52:52,918][05219] Updated weights for policy 1, policy_version 78270 (0.0008) -[2023-10-16 05:52:54,739][05218] Updated weights for policy 0, policy_version 78532 (0.0011) -[2023-10-16 05:52:55,099][05218] Updated weights for policy 0, policy_version 78542 (0.0007) -[2023-10-16 05:52:55,469][05218] Updated weights for policy 0, policy_version 78552 (0.0010) -[2023-10-16 05:52:56,666][05219] Updated weights for policy 1, policy_version 78280 (0.0007) -[2023-10-16 05:52:57,038][05219] Updated weights for policy 1, policy_version 78290 (0.0008) -[2023-10-16 05:52:57,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 160595968. Throughput: 0: 1805.6, 1: 1775.0. Samples: 40156938. Policy #0 lag: (min: 29.0, avg: 29.2, max: 37.0) -[2023-10-16 05:52:57,351][03835] Avg episode reward: [(0, '6.230'), (1, '8.220')] -[2023-10-16 05:52:57,408][05219] Updated weights for policy 1, policy_version 78300 (0.0009) -[2023-10-16 05:52:59,204][05218] Updated weights for policy 0, policy_version 78562 (0.0010) -[2023-10-16 05:52:59,577][05218] Updated weights for policy 0, policy_version 78572 (0.0008) -[2023-10-16 05:52:59,957][05218] Updated weights for policy 0, policy_version 78582 (0.0007) -[2023-10-16 05:53:00,325][05218] Updated weights for policy 0, policy_version 78592 (0.0009) -[2023-10-16 05:53:01,299][05219] Updated weights for policy 1, policy_version 78310 (0.0010) -[2023-10-16 05:53:01,669][05219] Updated weights for policy 1, policy_version 78320 (0.0011) -[2023-10-16 05:53:02,041][05219] Updated weights for policy 1, policy_version 78330 (0.0009) -[2023-10-16 05:53:02,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 160694272. Throughput: 0: 1788.0, 1: 1804.1. Samples: 40178780. Policy #0 lag: (min: 29.0, avg: 29.2, max: 37.0) -[2023-10-16 05:53:02,351][03835] Avg episode reward: [(0, '6.720'), (1, '7.670')] -[2023-10-16 05:53:04,005][05218] Updated weights for policy 0, policy_version 78602 (0.0008) -[2023-10-16 05:53:04,367][05218] Updated weights for policy 0, policy_version 78612 (0.0007) -[2023-10-16 05:53:04,742][05218] Updated weights for policy 0, policy_version 78622 (0.0009) -[2023-10-16 05:53:05,738][05219] Updated weights for policy 1, policy_version 78340 (0.0008) -[2023-10-16 05:53:06,109][05219] Updated weights for policy 1, policy_version 78350 (0.0008) -[2023-10-16 05:53:06,466][05219] Updated weights for policy 1, policy_version 78360 (0.0008) -[2023-10-16 05:53:07,351][03835] Fps is (10 sec: 16383.4, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 160759808. Throughput: 0: 1797.0, 1: 1773.0. Samples: 40199960. Policy #0 lag: (min: 29.0, avg: 29.2, max: 37.0) -[2023-10-16 05:53:07,352][03835] Avg episode reward: [(0, '6.930'), (1, '7.740')] -[2023-10-16 05:53:08,470][05218] Updated weights for policy 0, policy_version 78632 (0.0008) -[2023-10-16 05:53:08,856][05218] Updated weights for policy 0, policy_version 78642 (0.0010) -[2023-10-16 05:53:09,223][05218] Updated weights for policy 0, policy_version 78652 (0.0010) -[2023-10-16 05:53:10,206][05219] Updated weights for policy 1, policy_version 78370 (0.0009) -[2023-10-16 05:53:10,622][05219] Updated weights for policy 1, policy_version 78380 (0.0008) -[2023-10-16 05:53:10,985][05219] Updated weights for policy 1, policy_version 78390 (0.0010) -[2023-10-16 05:53:11,342][05219] Updated weights for policy 1, policy_version 78400 (0.0010) -[2023-10-16 05:53:12,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 160825344. Throughput: 0: 1798.0, 1: 1798.1. Samples: 40211300. Policy #0 lag: (min: 29.0, avg: 29.2, max: 37.0) -[2023-10-16 05:53:12,351][03835] Avg episode reward: [(0, '6.770'), (1, '8.280')] -[2023-10-16 05:53:13,018][05218] Updated weights for policy 0, policy_version 78662 (0.0009) -[2023-10-16 05:53:13,385][05218] Updated weights for policy 0, policy_version 78672 (0.0007) -[2023-10-16 05:53:13,760][05218] Updated weights for policy 0, policy_version 78682 (0.0007) -[2023-10-16 05:53:15,130][05219] Updated weights for policy 1, policy_version 78410 (0.0008) -[2023-10-16 05:53:15,498][05219] Updated weights for policy 1, policy_version 78420 (0.0007) -[2023-10-16 05:53:15,854][05219] Updated weights for policy 1, policy_version 78430 (0.0008) -[2023-10-16 05:53:17,341][05218] Updated weights for policy 0, policy_version 78692 (0.0008) -[2023-10-16 05:53:17,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 160890880. Throughput: 0: 1796.6, 1: 1778.0. Samples: 40232056. Policy #0 lag: (min: 29.0, avg: 29.2, max: 37.0) -[2023-10-16 05:53:17,352][03835] Avg episode reward: [(0, '6.520'), (1, '7.560')] -[2023-10-16 05:53:17,712][05218] Updated weights for policy 0, policy_version 78702 (0.0007) -[2023-10-16 05:53:18,087][05218] Updated weights for policy 0, policy_version 78712 (0.0008) -[2023-10-16 05:53:19,617][05219] Updated weights for policy 1, policy_version 78440 (0.0008) -[2023-10-16 05:53:19,974][05219] Updated weights for policy 1, policy_version 78450 (0.0010) -[2023-10-16 05:53:20,343][05219] Updated weights for policy 1, policy_version 78460 (0.0007) -[2023-10-16 05:53:21,852][05218] Updated weights for policy 0, policy_version 78722 (0.0009) -[2023-10-16 05:53:22,227][05218] Updated weights for policy 0, policy_version 78732 (0.0007) -[2023-10-16 05:53:22,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 160956416. Throughput: 0: 1806.7, 1: 1777.6. Samples: 40254050. Policy #0 lag: (min: 29.0, avg: 29.2, max: 37.0) -[2023-10-16 05:53:22,351][03835] Avg episode reward: [(0, '6.240'), (1, '7.380')] -[2023-10-16 05:53:22,609][05218] Updated weights for policy 0, policy_version 78742 (0.0007) -[2023-10-16 05:53:22,978][05218] Updated weights for policy 0, policy_version 78752 (0.0007) -[2023-10-16 05:53:24,058][05219] Updated weights for policy 1, policy_version 78470 (0.0008) -[2023-10-16 05:53:24,414][05219] Updated weights for policy 1, policy_version 78480 (0.0011) -[2023-10-16 05:53:24,776][05219] Updated weights for policy 1, policy_version 78490 (0.0009) -[2023-10-16 05:53:26,677][05218] Updated weights for policy 0, policy_version 78762 (0.0010) -[2023-10-16 05:53:27,060][05218] Updated weights for policy 0, policy_version 78772 (0.0011) -[2023-10-16 05:53:27,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 161021952. Throughput: 0: 1799.3, 1: 1781.2. Samples: 40264694. Policy #0 lag: (min: 29.0, avg: 29.2, max: 37.0) -[2023-10-16 05:53:27,351][03835] Avg episode reward: [(0, '6.200'), (1, '7.950')] -[2023-10-16 05:53:27,432][05218] Updated weights for policy 0, policy_version 78782 (0.0009) -[2023-10-16 05:53:28,603][05219] Updated weights for policy 1, policy_version 78500 (0.0008) -[2023-10-16 05:53:28,970][05219] Updated weights for policy 1, policy_version 78510 (0.0009) -[2023-10-16 05:53:29,333][05219] Updated weights for policy 1, policy_version 78520 (0.0008) -[2023-10-16 05:53:31,230][05218] Updated weights for policy 0, policy_version 78792 (0.0009) -[2023-10-16 05:53:31,601][05218] Updated weights for policy 0, policy_version 78802 (0.0008) -[2023-10-16 05:53:31,980][05218] Updated weights for policy 0, policy_version 78812 (0.0008) -[2023-10-16 05:53:32,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 161120256. Throughput: 0: 1807.9, 1: 1784.4. Samples: 40286532. Policy #0 lag: (min: 27.0, avg: 27.0, max: 31.0) -[2023-10-16 05:53:32,351][03835] Avg episode reward: [(0, '6.570'), (1, '7.820')] -[2023-10-16 05:53:33,089][05219] Updated weights for policy 1, policy_version 78530 (0.0008) -[2023-10-16 05:53:33,458][05219] Updated weights for policy 1, policy_version 78540 (0.0008) -[2023-10-16 05:53:33,824][05219] Updated weights for policy 1, policy_version 78550 (0.0007) -[2023-10-16 05:53:34,197][05219] Updated weights for policy 1, policy_version 78560 (0.0008) -[2023-10-16 05:53:35,856][05218] Updated weights for policy 0, policy_version 78822 (0.0008) -[2023-10-16 05:53:36,239][05218] Updated weights for policy 0, policy_version 78832 (0.0007) -[2023-10-16 05:53:36,622][05218] Updated weights for policy 0, policy_version 78842 (0.0008) -[2023-10-16 05:53:37,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 161185792. Throughput: 0: 1795.3, 1: 1797.9. Samples: 40307872. Policy #0 lag: (min: 27.0, avg: 27.0, max: 31.0) -[2023-10-16 05:53:37,351][03835] Avg episode reward: [(0, '7.500'), (1, '8.210')] -[2023-10-16 05:53:37,361][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000078848_80740352.pth... -[2023-10-16 05:53:37,361][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000078560_80445440.pth... -[2023-10-16 05:53:37,397][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000076896_78741504.pth -[2023-10-16 05:53:37,399][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000077152_79003648.pth -[2023-10-16 05:53:38,040][05219] Updated weights for policy 1, policy_version 78570 (0.0008) -[2023-10-16 05:53:38,406][05219] Updated weights for policy 1, policy_version 78580 (0.0011) -[2023-10-16 05:53:38,776][05219] Updated weights for policy 1, policy_version 78590 (0.0008) -[2023-10-16 05:53:40,404][05218] Updated weights for policy 0, policy_version 78852 (0.0008) -[2023-10-16 05:53:40,781][05218] Updated weights for policy 0, policy_version 78862 (0.0009) -[2023-10-16 05:53:41,147][05218] Updated weights for policy 0, policy_version 78872 (0.0010) -[2023-10-16 05:53:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 161251328. Throughput: 0: 1810.4, 1: 1794.1. Samples: 40319142. Policy #0 lag: (min: 27.0, avg: 27.0, max: 31.0) -[2023-10-16 05:53:42,351][03835] Avg episode reward: [(0, '7.160'), (1, '8.700')] -[2023-10-16 05:53:42,475][05219] Updated weights for policy 1, policy_version 78600 (0.0007) -[2023-10-16 05:53:42,842][05219] Updated weights for policy 1, policy_version 78610 (0.0007) -[2023-10-16 05:53:43,202][05219] Updated weights for policy 1, policy_version 78620 (0.0007) -[2023-10-16 05:53:44,901][05218] Updated weights for policy 0, policy_version 78882 (0.0010) -[2023-10-16 05:53:45,275][05218] Updated weights for policy 0, policy_version 78892 (0.0011) -[2023-10-16 05:53:45,655][05218] Updated weights for policy 0, policy_version 78902 (0.0009) -[2023-10-16 05:53:46,021][05218] Updated weights for policy 0, policy_version 78912 (0.0007) -[2023-10-16 05:53:46,881][05219] Updated weights for policy 1, policy_version 78630 (0.0008) -[2023-10-16 05:53:47,248][05219] Updated weights for policy 1, policy_version 78640 (0.0008) -[2023-10-16 05:53:47,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 161316864. Throughput: 0: 1795.0, 1: 1793.6. Samples: 40340268. Policy #0 lag: (min: 27.0, avg: 27.0, max: 31.0) -[2023-10-16 05:53:47,351][03835] Avg episode reward: [(0, '7.640'), (1, '7.830')] -[2023-10-16 05:53:47,625][05219] Updated weights for policy 1, policy_version 78650 (0.0007) -[2023-10-16 05:53:49,753][05218] Updated weights for policy 0, policy_version 78922 (0.0009) -[2023-10-16 05:53:50,134][05218] Updated weights for policy 0, policy_version 78932 (0.0008) -[2023-10-16 05:53:50,500][05218] Updated weights for policy 0, policy_version 78942 (0.0009) -[2023-10-16 05:53:51,537][05219] Updated weights for policy 1, policy_version 78660 (0.0008) -[2023-10-16 05:53:51,901][05219] Updated weights for policy 1, policy_version 78670 (0.0008) -[2023-10-16 05:53:52,271][05219] Updated weights for policy 1, policy_version 78680 (0.0008) -[2023-10-16 05:53:52,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 161382400. Throughput: 0: 1793.2, 1: 1801.4. Samples: 40361718. Policy #0 lag: (min: 27.0, avg: 27.0, max: 31.0) -[2023-10-16 05:53:52,351][03835] Avg episode reward: [(0, '6.880'), (1, '8.110')] -[2023-10-16 05:53:54,108][05218] Updated weights for policy 0, policy_version 78952 (0.0008) -[2023-10-16 05:53:54,489][05218] Updated weights for policy 0, policy_version 78962 (0.0009) -[2023-10-16 05:53:54,866][05218] Updated weights for policy 0, policy_version 78972 (0.0009) -[2023-10-16 05:53:56,081][05219] Updated weights for policy 1, policy_version 78690 (0.0011) -[2023-10-16 05:53:56,486][05219] Updated weights for policy 1, policy_version 78700 (0.0010) -[2023-10-16 05:53:56,842][05219] Updated weights for policy 1, policy_version 78710 (0.0009) -[2023-10-16 05:53:57,205][05219] Updated weights for policy 1, policy_version 78720 (0.0011) -[2023-10-16 05:53:57,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 161480704. Throughput: 0: 1791.3, 1: 1787.1. Samples: 40372326. Policy #0 lag: (min: 27.0, avg: 27.0, max: 31.0) -[2023-10-16 05:53:57,351][03835] Avg episode reward: [(0, '6.160'), (1, '8.440')] -[2023-10-16 05:53:58,669][05218] Updated weights for policy 0, policy_version 78982 (0.0010) -[2023-10-16 05:53:59,047][05218] Updated weights for policy 0, policy_version 78992 (0.0008) -[2023-10-16 05:53:59,415][05218] Updated weights for policy 0, policy_version 79002 (0.0009) -[2023-10-16 05:54:00,782][05219] Updated weights for policy 1, policy_version 78730 (0.0011) -[2023-10-16 05:54:01,147][05219] Updated weights for policy 1, policy_version 78740 (0.0009) -[2023-10-16 05:54:01,513][05219] Updated weights for policy 1, policy_version 78750 (0.0008) -[2023-10-16 05:54:02,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 161546240. Throughput: 0: 1791.7, 1: 1805.4. Samples: 40393924. Policy #0 lag: (min: 27.0, avg: 27.0, max: 31.0) -[2023-10-16 05:54:02,351][03835] Avg episode reward: [(0, '6.460'), (1, '7.240')] -[2023-10-16 05:54:03,112][05218] Updated weights for policy 0, policy_version 79012 (0.0008) -[2023-10-16 05:54:03,486][05218] Updated weights for policy 0, policy_version 79022 (0.0009) -[2023-10-16 05:54:03,854][05218] Updated weights for policy 0, policy_version 79032 (0.0009) -[2023-10-16 05:54:05,169][05219] Updated weights for policy 1, policy_version 78760 (0.0010) -[2023-10-16 05:54:05,536][05219] Updated weights for policy 1, policy_version 78770 (0.0009) -[2023-10-16 05:54:05,906][05219] Updated weights for policy 1, policy_version 78780 (0.0007) -[2023-10-16 05:54:07,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 161611776. Throughput: 0: 1806.0, 1: 1789.2. Samples: 40415830. Policy #0 lag: (min: 27.0, avg: 27.0, max: 31.0) -[2023-10-16 05:54:07,351][03835] Avg episode reward: [(0, '6.310'), (1, '8.520')] -[2023-10-16 05:54:07,604][05218] Updated weights for policy 0, policy_version 79042 (0.0009) -[2023-10-16 05:54:07,981][05218] Updated weights for policy 0, policy_version 79052 (0.0007) -[2023-10-16 05:54:08,363][05218] Updated weights for policy 0, policy_version 79062 (0.0009) -[2023-10-16 05:54:08,739][05218] Updated weights for policy 0, policy_version 79072 (0.0007) -[2023-10-16 05:54:09,812][05219] Updated weights for policy 1, policy_version 78790 (0.0008) -[2023-10-16 05:54:10,183][05219] Updated weights for policy 1, policy_version 78800 (0.0007) -[2023-10-16 05:54:10,550][05219] Updated weights for policy 1, policy_version 78810 (0.0008) -[2023-10-16 05:54:12,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 161677312. Throughput: 0: 1791.6, 1: 1802.0. Samples: 40426406. Policy #0 lag: (min: 27.0, avg: 27.0, max: 31.0) -[2023-10-16 05:54:12,351][03835] Avg episode reward: [(0, '6.560'), (1, '8.440')] -[2023-10-16 05:54:12,355][05218] Updated weights for policy 0, policy_version 79082 (0.0008) -[2023-10-16 05:54:12,732][05218] Updated weights for policy 0, policy_version 79092 (0.0008) -[2023-10-16 05:54:13,111][05218] Updated weights for policy 0, policy_version 79102 (0.0009) -[2023-10-16 05:54:14,103][05219] Updated weights for policy 1, policy_version 78820 (0.0008) -[2023-10-16 05:54:14,476][05219] Updated weights for policy 1, policy_version 78830 (0.0010) -[2023-10-16 05:54:14,858][05219] Updated weights for policy 1, policy_version 78840 (0.0010) -[2023-10-16 05:54:16,851][05218] Updated weights for policy 0, policy_version 79112 (0.0009) -[2023-10-16 05:54:17,224][05218] Updated weights for policy 0, policy_version 79122 (0.0007) -[2023-10-16 05:54:17,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 161742848. Throughput: 0: 1804.0, 1: 1785.1. Samples: 40448042. Policy #0 lag: (min: 27.0, avg: 27.0, max: 31.0) -[2023-10-16 05:54:17,351][03835] Avg episode reward: [(0, '7.020'), (1, '7.940')] -[2023-10-16 05:54:17,601][05218] Updated weights for policy 0, policy_version 79132 (0.0010) -[2023-10-16 05:54:18,658][05219] Updated weights for policy 1, policy_version 78850 (0.0010) -[2023-10-16 05:54:19,020][05219] Updated weights for policy 1, policy_version 78860 (0.0008) -[2023-10-16 05:54:19,383][05219] Updated weights for policy 1, policy_version 78870 (0.0009) -[2023-10-16 05:54:19,742][05219] Updated weights for policy 1, policy_version 78880 (0.0007) -[2023-10-16 05:54:21,405][05218] Updated weights for policy 0, policy_version 79142 (0.0009) -[2023-10-16 05:54:21,786][05218] Updated weights for policy 0, policy_version 79152 (0.0007) -[2023-10-16 05:54:22,160][05218] Updated weights for policy 0, policy_version 79162 (0.0007) -[2023-10-16 05:54:22,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 161808384. Throughput: 0: 1796.9, 1: 1786.0. Samples: 40469102. Policy #0 lag: (min: 27.0, avg: 27.0, max: 31.0) -[2023-10-16 05:54:22,351][03835] Avg episode reward: [(0, '6.730'), (1, '8.290')] -[2023-10-16 05:54:23,620][05219] Updated weights for policy 1, policy_version 78890 (0.0007) -[2023-10-16 05:54:23,988][05219] Updated weights for policy 1, policy_version 78900 (0.0008) -[2023-10-16 05:54:24,355][05219] Updated weights for policy 1, policy_version 78910 (0.0010) -[2023-10-16 05:54:25,854][05218] Updated weights for policy 0, policy_version 79172 (0.0009) -[2023-10-16 05:54:26,233][05218] Updated weights for policy 0, policy_version 79182 (0.0010) -[2023-10-16 05:54:26,605][05218] Updated weights for policy 0, policy_version 79192 (0.0010) -[2023-10-16 05:54:27,350][03835] Fps is (10 sec: 16383.5, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 161906688. Throughput: 0: 1795.3, 1: 1781.2. Samples: 40480084. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-16 05:54:27,352][03835] Avg episode reward: [(0, '7.360'), (1, '8.570')] -[2023-10-16 05:54:28,238][05219] Updated weights for policy 1, policy_version 78920 (0.0009) -[2023-10-16 05:54:28,604][05219] Updated weights for policy 1, policy_version 78930 (0.0009) -[2023-10-16 05:54:28,970][05219] Updated weights for policy 1, policy_version 78940 (0.0008) -[2023-10-16 05:54:30,455][05218] Updated weights for policy 0, policy_version 79202 (0.0010) -[2023-10-16 05:54:30,829][05218] Updated weights for policy 0, policy_version 79212 (0.0009) -[2023-10-16 05:54:31,197][05218] Updated weights for policy 0, policy_version 79222 (0.0009) -[2023-10-16 05:54:31,572][05218] Updated weights for policy 0, policy_version 79232 (0.0008) -[2023-10-16 05:54:32,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 161972224. Throughput: 0: 1794.8, 1: 1780.5. Samples: 40501158. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-16 05:54:32,351][03835] Avg episode reward: [(0, '7.370'), (1, '8.310')] -[2023-10-16 05:54:32,699][05219] Updated weights for policy 1, policy_version 78950 (0.0008) -[2023-10-16 05:54:33,074][05219] Updated weights for policy 1, policy_version 78960 (0.0010) -[2023-10-16 05:54:33,440][05219] Updated weights for policy 1, policy_version 78970 (0.0011) -[2023-10-16 05:54:35,418][05218] Updated weights for policy 0, policy_version 79242 (0.0009) -[2023-10-16 05:54:35,796][05218] Updated weights for policy 0, policy_version 79252 (0.0007) -[2023-10-16 05:54:36,173][05218] Updated weights for policy 0, policy_version 79262 (0.0009) -[2023-10-16 05:54:37,307][05219] Updated weights for policy 1, policy_version 78980 (0.0007) -[2023-10-16 05:54:37,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 162037760. Throughput: 0: 1783.7, 1: 1798.7. Samples: 40522928. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-16 05:54:37,352][03835] Avg episode reward: [(0, '7.320'), (1, '8.250')] -[2023-10-16 05:54:37,678][05219] Updated weights for policy 1, policy_version 78990 (0.0008) -[2023-10-16 05:54:38,046][05219] Updated weights for policy 1, policy_version 79000 (0.0008) -[2023-10-16 05:54:39,884][05218] Updated weights for policy 0, policy_version 79272 (0.0008) -[2023-10-16 05:54:40,263][05218] Updated weights for policy 0, policy_version 79282 (0.0007) -[2023-10-16 05:54:40,635][05218] Updated weights for policy 0, policy_version 79292 (0.0009) -[2023-10-16 05:54:41,944][05219] Updated weights for policy 1, policy_version 79010 (0.0009) -[2023-10-16 05:54:42,341][05219] Updated weights for policy 1, policy_version 79020 (0.0009) -[2023-10-16 05:54:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 162103296. Throughput: 0: 1798.6, 1: 1777.7. Samples: 40533256. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-16 05:54:42,351][03835] Avg episode reward: [(0, '6.920'), (1, '8.580')] -[2023-10-16 05:54:42,714][05219] Updated weights for policy 1, policy_version 79030 (0.0009) -[2023-10-16 05:54:43,072][05219] Updated weights for policy 1, policy_version 79040 (0.0009) -[2023-10-16 05:54:44,523][05218] Updated weights for policy 0, policy_version 79302 (0.0011) -[2023-10-16 05:54:44,902][05218] Updated weights for policy 0, policy_version 79312 (0.0008) -[2023-10-16 05:54:45,267][05218] Updated weights for policy 0, policy_version 79322 (0.0009) -[2023-10-16 05:54:46,731][05219] Updated weights for policy 1, policy_version 79050 (0.0010) -[2023-10-16 05:54:47,089][05219] Updated weights for policy 1, policy_version 79060 (0.0008) -[2023-10-16 05:54:47,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 162168832. Throughput: 0: 1785.0, 1: 1796.0. Samples: 40555068. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-16 05:54:47,351][03835] Avg episode reward: [(0, '7.270'), (1, '7.310')] -[2023-10-16 05:54:47,461][05219] Updated weights for policy 1, policy_version 79070 (0.0008) -[2023-10-16 05:54:48,896][05218] Updated weights for policy 0, policy_version 79332 (0.0009) -[2023-10-16 05:54:49,269][05218] Updated weights for policy 0, policy_version 79342 (0.0007) -[2023-10-16 05:54:49,634][05218] Updated weights for policy 0, policy_version 79352 (0.0007) -[2023-10-16 05:54:51,309][05219] Updated weights for policy 1, policy_version 79080 (0.0008) -[2023-10-16 05:54:51,678][05219] Updated weights for policy 1, policy_version 79090 (0.0008) -[2023-10-16 05:54:52,036][05219] Updated weights for policy 1, policy_version 79100 (0.0008) -[2023-10-16 05:54:52,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 162267136. Throughput: 0: 1785.0, 1: 1773.0. Samples: 40575938. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-16 05:54:52,351][03835] Avg episode reward: [(0, '6.740'), (1, '7.880')] -[2023-10-16 05:54:53,313][05218] Updated weights for policy 0, policy_version 79362 (0.0007) -[2023-10-16 05:54:53,692][05218] Updated weights for policy 0, policy_version 79372 (0.0007) -[2023-10-16 05:54:54,059][05218] Updated weights for policy 0, policy_version 79382 (0.0011) -[2023-10-16 05:54:54,434][05218] Updated weights for policy 0, policy_version 79392 (0.0009) -[2023-10-16 05:54:55,701][05219] Updated weights for policy 1, policy_version 79110 (0.0008) -[2023-10-16 05:54:56,060][05219] Updated weights for policy 1, policy_version 79120 (0.0008) -[2023-10-16 05:54:56,433][05219] Updated weights for policy 1, policy_version 79130 (0.0009) -[2023-10-16 05:54:57,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 162332672. Throughput: 0: 1784.6, 1: 1792.9. Samples: 40587396. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-16 05:54:57,351][03835] Avg episode reward: [(0, '6.790'), (1, '8.390')] -[2023-10-16 05:54:58,188][05218] Updated weights for policy 0, policy_version 79402 (0.0007) -[2023-10-16 05:54:58,560][05218] Updated weights for policy 0, policy_version 79412 (0.0007) -[2023-10-16 05:54:58,944][05218] Updated weights for policy 0, policy_version 79422 (0.0009) -[2023-10-16 05:55:00,021][05219] Updated weights for policy 1, policy_version 79140 (0.0009) -[2023-10-16 05:55:00,394][05219] Updated weights for policy 1, policy_version 79150 (0.0007) -[2023-10-16 05:55:00,754][05219] Updated weights for policy 1, policy_version 79160 (0.0008) -[2023-10-16 05:55:02,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 162398208. Throughput: 0: 1788.8, 1: 1783.2. Samples: 40608782. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-16 05:55:02,351][03835] Avg episode reward: [(0, '7.420'), (1, '8.220')] -[2023-10-16 05:55:02,671][05218] Updated weights for policy 0, policy_version 79432 (0.0008) -[2023-10-16 05:55:03,050][05218] Updated weights for policy 0, policy_version 79442 (0.0008) -[2023-10-16 05:55:03,417][05218] Updated weights for policy 0, policy_version 79452 (0.0009) -[2023-10-16 05:55:04,566][05219] Updated weights for policy 1, policy_version 79170 (0.0010) -[2023-10-16 05:55:04,921][05219] Updated weights for policy 1, policy_version 79180 (0.0009) -[2023-10-16 05:55:05,283][05219] Updated weights for policy 1, policy_version 79190 (0.0010) -[2023-10-16 05:55:05,648][05219] Updated weights for policy 1, policy_version 79200 (0.0010) -[2023-10-16 05:55:07,194][05218] Updated weights for policy 0, policy_version 79462 (0.0009) -[2023-10-16 05:55:07,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 162463744. Throughput: 0: 1811.7, 1: 1782.7. Samples: 40630852. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-16 05:55:07,351][03835] Avg episode reward: [(0, '6.640'), (1, '8.930')] -[2023-10-16 05:55:07,575][05218] Updated weights for policy 0, policy_version 79472 (0.0008) -[2023-10-16 05:55:07,955][05218] Updated weights for policy 0, policy_version 79482 (0.0009) -[2023-10-16 05:55:09,458][05219] Updated weights for policy 1, policy_version 79210 (0.0011) -[2023-10-16 05:55:09,831][05219] Updated weights for policy 1, policy_version 79220 (0.0010) -[2023-10-16 05:55:10,198][05219] Updated weights for policy 1, policy_version 79230 (0.0011) -[2023-10-16 05:55:11,509][05218] Updated weights for policy 0, policy_version 79492 (0.0007) -[2023-10-16 05:55:11,876][05218] Updated weights for policy 0, policy_version 79502 (0.0010) -[2023-10-16 05:55:12,251][05218] Updated weights for policy 0, policy_version 79512 (0.0007) -[2023-10-16 05:55:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 162529280. Throughput: 0: 1792.1, 1: 1787.0. Samples: 40641142. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-16 05:55:12,351][03835] Avg episode reward: [(0, '6.120'), (1, '7.360')] -[2023-10-16 05:55:13,931][05219] Updated weights for policy 1, policy_version 79240 (0.0011) -[2023-10-16 05:55:14,302][05219] Updated weights for policy 1, policy_version 79250 (0.0009) -[2023-10-16 05:55:14,675][05219] Updated weights for policy 1, policy_version 79260 (0.0009) -[2023-10-16 05:55:15,889][05218] Updated weights for policy 0, policy_version 79522 (0.0008) -[2023-10-16 05:55:16,267][05218] Updated weights for policy 0, policy_version 79532 (0.0009) -[2023-10-16 05:55:16,642][05218] Updated weights for policy 0, policy_version 79542 (0.0011) -[2023-10-16 05:55:17,018][05218] Updated weights for policy 0, policy_version 79552 (0.0010) -[2023-10-16 05:55:17,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 162627584. Throughput: 0: 1808.3, 1: 1782.9. Samples: 40662762. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-16 05:55:17,351][03835] Avg episode reward: [(0, '7.320'), (1, '8.380')] -[2023-10-16 05:55:18,397][05219] Updated weights for policy 1, policy_version 79270 (0.0009) -[2023-10-16 05:55:18,754][05219] Updated weights for policy 1, policy_version 79280 (0.0009) -[2023-10-16 05:55:19,125][05219] Updated weights for policy 1, policy_version 79290 (0.0010) -[2023-10-16 05:55:20,654][05218] Updated weights for policy 0, policy_version 79562 (0.0009) -[2023-10-16 05:55:21,028][05218] Updated weights for policy 0, policy_version 79572 (0.0010) -[2023-10-16 05:55:21,392][05218] Updated weights for policy 0, policy_version 79582 (0.0009) -[2023-10-16 05:55:22,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 162693120. Throughput: 0: 1801.9, 1: 1790.2. Samples: 40684572. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-16 05:55:22,351][03835] Avg episode reward: [(0, '7.480'), (1, '8.900')] -[2023-10-16 05:55:22,958][05219] Updated weights for policy 1, policy_version 79300 (0.0009) -[2023-10-16 05:55:23,328][05219] Updated weights for policy 1, policy_version 79310 (0.0007) -[2023-10-16 05:55:23,690][05219] Updated weights for policy 1, policy_version 79320 (0.0009) -[2023-10-16 05:55:25,177][05218] Updated weights for policy 0, policy_version 79592 (0.0008) -[2023-10-16 05:55:25,552][05218] Updated weights for policy 0, policy_version 79602 (0.0008) -[2023-10-16 05:55:25,934][05218] Updated weights for policy 0, policy_version 79612 (0.0008) -[2023-10-16 05:55:27,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 162758656. Throughput: 0: 1811.2, 1: 1789.5. Samples: 40695290. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-16 05:55:27,351][03835] Avg episode reward: [(0, '6.210'), (1, '8.120')] -[2023-10-16 05:55:27,522][05219] Updated weights for policy 1, policy_version 79330 (0.0009) -[2023-10-16 05:55:27,920][05219] Updated weights for policy 1, policy_version 79340 (0.0007) -[2023-10-16 05:55:28,290][05219] Updated weights for policy 1, policy_version 79350 (0.0008) -[2023-10-16 05:55:28,659][05219] Updated weights for policy 1, policy_version 79360 (0.0009) -[2023-10-16 05:55:29,548][05218] Updated weights for policy 0, policy_version 79622 (0.0007) -[2023-10-16 05:55:29,919][05218] Updated weights for policy 0, policy_version 79632 (0.0008) -[2023-10-16 05:55:30,293][05218] Updated weights for policy 0, policy_version 79642 (0.0007) -[2023-10-16 05:55:32,259][05219] Updated weights for policy 1, policy_version 79370 (0.0008) -[2023-10-16 05:55:32,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 162824192. Throughput: 0: 1812.2, 1: 1793.4. Samples: 40717320. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-16 05:55:32,351][03835] Avg episode reward: [(0, '6.710'), (1, '8.690')] -[2023-10-16 05:55:32,625][05219] Updated weights for policy 1, policy_version 79380 (0.0008) -[2023-10-16 05:55:32,993][05219] Updated weights for policy 1, policy_version 79390 (0.0010) -[2023-10-16 05:55:33,970][05218] Updated weights for policy 0, policy_version 79652 (0.0009) -[2023-10-16 05:55:34,344][05218] Updated weights for policy 0, policy_version 79662 (0.0010) -[2023-10-16 05:55:34,716][05218] Updated weights for policy 0, policy_version 79672 (0.0009) -[2023-10-16 05:55:36,709][05219] Updated weights for policy 1, policy_version 79400 (0.0007) -[2023-10-16 05:55:37,071][05219] Updated weights for policy 1, policy_version 79410 (0.0010) -[2023-10-16 05:55:37,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 162889728. Throughput: 0: 1807.8, 1: 1809.9. Samples: 40738732. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-16 05:55:37,351][03835] Avg episode reward: [(0, '7.530'), (1, '8.390')] -[2023-10-16 05:55:37,360][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000079680_81592320.pth... -[2023-10-16 05:55:37,388][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000078016_79888384.pth -[2023-10-16 05:55:37,439][05219] Updated weights for policy 1, policy_version 79420 (0.0011) -[2023-10-16 05:55:37,577][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000079424_81330176.pth... -[2023-10-16 05:55:37,613][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000077728_79593472.pth -[2023-10-16 05:55:38,518][05218] Updated weights for policy 0, policy_version 79682 (0.0010) -[2023-10-16 05:55:38,898][05218] Updated weights for policy 0, policy_version 79692 (0.0009) -[2023-10-16 05:55:39,274][05218] Updated weights for policy 0, policy_version 79702 (0.0007) -[2023-10-16 05:55:39,645][05218] Updated weights for policy 0, policy_version 79712 (0.0007) -[2023-10-16 05:55:41,344][05219] Updated weights for policy 1, policy_version 79430 (0.0008) -[2023-10-16 05:55:41,722][05219] Updated weights for policy 1, policy_version 79440 (0.0009) -[2023-10-16 05:55:42,096][05219] Updated weights for policy 1, policy_version 79450 (0.0008) -[2023-10-16 05:55:42,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 162988032. Throughput: 0: 1806.6, 1: 1791.6. Samples: 40749314. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-16 05:55:42,351][03835] Avg episode reward: [(0, '6.900'), (1, '8.710')] -[2023-10-16 05:55:43,313][05218] Updated weights for policy 0, policy_version 79722 (0.0008) -[2023-10-16 05:55:43,684][05218] Updated weights for policy 0, policy_version 79732 (0.0008) -[2023-10-16 05:55:44,055][05218] Updated weights for policy 0, policy_version 79742 (0.0010) -[2023-10-16 05:55:45,841][05219] Updated weights for policy 1, policy_version 79460 (0.0008) -[2023-10-16 05:55:46,210][05219] Updated weights for policy 1, policy_version 79470 (0.0010) -[2023-10-16 05:55:46,575][05219] Updated weights for policy 1, policy_version 79480 (0.0007) -[2023-10-16 05:55:47,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 163053568. Throughput: 0: 1802.4, 1: 1805.1. Samples: 40771120. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-16 05:55:47,351][03835] Avg episode reward: [(0, '6.830'), (1, '7.830')] -[2023-10-16 05:55:47,814][05218] Updated weights for policy 0, policy_version 79752 (0.0007) -[2023-10-16 05:55:48,180][05218] Updated weights for policy 0, policy_version 79762 (0.0007) -[2023-10-16 05:55:48,554][05218] Updated weights for policy 0, policy_version 79772 (0.0009) -[2023-10-16 05:55:50,412][05219] Updated weights for policy 1, policy_version 79490 (0.0008) -[2023-10-16 05:55:50,775][05219] Updated weights for policy 1, policy_version 79500 (0.0010) -[2023-10-16 05:55:51,141][05219] Updated weights for policy 1, policy_version 79510 (0.0007) -[2023-10-16 05:55:51,496][05219] Updated weights for policy 1, policy_version 79520 (0.0008) -[2023-10-16 05:55:52,325][05218] Updated weights for policy 0, policy_version 79782 (0.0007) -[2023-10-16 05:55:52,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 163119104. Throughput: 0: 1804.9, 1: 1780.9. Samples: 40792212. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-16 05:55:52,351][03835] Avg episode reward: [(0, '7.130'), (1, '7.390')] -[2023-10-16 05:55:52,701][05218] Updated weights for policy 0, policy_version 79792 (0.0007) -[2023-10-16 05:55:53,074][05218] Updated weights for policy 0, policy_version 79802 (0.0007) -[2023-10-16 05:55:55,123][05219] Updated weights for policy 1, policy_version 79530 (0.0011) -[2023-10-16 05:55:55,490][05219] Updated weights for policy 1, policy_version 79540 (0.0010) -[2023-10-16 05:55:55,850][05219] Updated weights for policy 1, policy_version 79550 (0.0008) -[2023-10-16 05:55:56,887][05218] Updated weights for policy 0, policy_version 79812 (0.0007) -[2023-10-16 05:55:57,270][05218] Updated weights for policy 0, policy_version 79822 (0.0009) -[2023-10-16 05:55:57,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 163184640. Throughput: 0: 1800.4, 1: 1807.2. Samples: 40803482. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-16 05:55:57,351][03835] Avg episode reward: [(0, '6.710'), (1, '7.370')] -[2023-10-16 05:55:57,648][05218] Updated weights for policy 0, policy_version 79832 (0.0011) -[2023-10-16 05:55:59,633][05219] Updated weights for policy 1, policy_version 79560 (0.0008) -[2023-10-16 05:56:00,007][05219] Updated weights for policy 1, policy_version 79570 (0.0009) -[2023-10-16 05:56:00,363][05219] Updated weights for policy 1, policy_version 79580 (0.0010) -[2023-10-16 05:56:01,409][05218] Updated weights for policy 0, policy_version 79842 (0.0010) -[2023-10-16 05:56:01,787][05218] Updated weights for policy 0, policy_version 79852 (0.0009) -[2023-10-16 05:56:02,159][05218] Updated weights for policy 0, policy_version 79862 (0.0010) -[2023-10-16 05:56:02,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 163250176. Throughput: 0: 1812.5, 1: 1792.9. Samples: 40825008. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-16 05:56:02,351][03835] Avg episode reward: [(0, '6.900'), (1, '8.060')] -[2023-10-16 05:56:02,534][05218] Updated weights for policy 0, policy_version 79872 (0.0007) -[2023-10-16 05:56:04,193][05219] Updated weights for policy 1, policy_version 79590 (0.0010) -[2023-10-16 05:56:04,569][05219] Updated weights for policy 1, policy_version 79600 (0.0008) -[2023-10-16 05:56:04,939][05219] Updated weights for policy 1, policy_version 79610 (0.0010) -[2023-10-16 05:56:06,285][05218] Updated weights for policy 0, policy_version 79882 (0.0010) -[2023-10-16 05:56:06,661][05218] Updated weights for policy 0, policy_version 79892 (0.0010) -[2023-10-16 05:56:07,032][05218] Updated weights for policy 0, policy_version 79902 (0.0010) -[2023-10-16 05:56:07,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 163348480. Throughput: 0: 1791.2, 1: 1795.8. Samples: 40845984. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) -[2023-10-16 05:56:07,352][03835] Avg episode reward: [(0, '7.570'), (1, '7.490')] -[2023-10-16 05:56:08,709][05219] Updated weights for policy 1, policy_version 79620 (0.0007) -[2023-10-16 05:56:09,070][05219] Updated weights for policy 1, policy_version 79630 (0.0008) -[2023-10-16 05:56:09,441][05219] Updated weights for policy 1, policy_version 79640 (0.0010) -[2023-10-16 05:56:10,761][05218] Updated weights for policy 0, policy_version 79912 (0.0009) -[2023-10-16 05:56:11,128][05218] Updated weights for policy 0, policy_version 79922 (0.0007) -[2023-10-16 05:56:11,504][05218] Updated weights for policy 0, policy_version 79932 (0.0007) -[2023-10-16 05:56:12,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 163414016. Throughput: 0: 1805.8, 1: 1801.9. Samples: 40857636. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) -[2023-10-16 05:56:12,351][03835] Avg episode reward: [(0, '6.880'), (1, '7.810')] -[2023-10-16 05:56:13,161][05219] Updated weights for policy 1, policy_version 79650 (0.0009) -[2023-10-16 05:56:13,523][05219] Updated weights for policy 1, policy_version 79660 (0.0009) -[2023-10-16 05:56:13,901][05219] Updated weights for policy 1, policy_version 79670 (0.0009) -[2023-10-16 05:56:14,260][05219] Updated weights for policy 1, policy_version 79680 (0.0010) -[2023-10-16 05:56:15,175][05218] Updated weights for policy 0, policy_version 79942 (0.0009) -[2023-10-16 05:56:15,557][05218] Updated weights for policy 0, policy_version 79952 (0.0008) -[2023-10-16 05:56:15,925][05218] Updated weights for policy 0, policy_version 79962 (0.0009) -[2023-10-16 05:56:17,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 163479552. Throughput: 0: 1789.3, 1: 1801.2. Samples: 40878894. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) -[2023-10-16 05:56:17,351][03835] Avg episode reward: [(0, '6.430'), (1, '8.740')] -[2023-10-16 05:56:18,032][05219] Updated weights for policy 1, policy_version 79690 (0.0008) -[2023-10-16 05:56:18,393][05219] Updated weights for policy 1, policy_version 79700 (0.0009) -[2023-10-16 05:56:18,749][05219] Updated weights for policy 1, policy_version 79710 (0.0009) -[2023-10-16 05:56:19,599][05218] Updated weights for policy 0, policy_version 79972 (0.0008) -[2023-10-16 05:56:19,970][05218] Updated weights for policy 0, policy_version 79982 (0.0009) -[2023-10-16 05:56:20,339][05218] Updated weights for policy 0, policy_version 79992 (0.0007) -[2023-10-16 05:56:22,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 163545088. Throughput: 0: 1796.0, 1: 1813.2. Samples: 40901144. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) -[2023-10-16 05:56:22,351][03835] Avg episode reward: [(0, '7.300'), (1, '7.760')] -[2023-10-16 05:56:22,655][05219] Updated weights for policy 1, policy_version 79720 (0.0011) -[2023-10-16 05:56:23,026][05219] Updated weights for policy 1, policy_version 79730 (0.0010) -[2023-10-16 05:56:23,390][05219] Updated weights for policy 1, policy_version 79740 (0.0010) -[2023-10-16 05:56:24,124][05218] Updated weights for policy 0, policy_version 80002 (0.0008) -[2023-10-16 05:56:24,499][05218] Updated weights for policy 0, policy_version 80012 (0.0008) -[2023-10-16 05:56:24,881][05218] Updated weights for policy 0, policy_version 80022 (0.0008) -[2023-10-16 05:56:25,257][05218] Updated weights for policy 0, policy_version 80032 (0.0010) -[2023-10-16 05:56:27,147][05219] Updated weights for policy 1, policy_version 79750 (0.0007) -[2023-10-16 05:56:27,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 163610624. Throughput: 0: 1795.4, 1: 1794.1. Samples: 40910842. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) -[2023-10-16 05:56:27,351][03835] Avg episode reward: [(0, '6.670'), (1, '7.860')] -[2023-10-16 05:56:27,512][05219] Updated weights for policy 1, policy_version 79760 (0.0007) -[2023-10-16 05:56:27,874][05219] Updated weights for policy 1, policy_version 79770 (0.0008) -[2023-10-16 05:56:29,118][05218] Updated weights for policy 0, policy_version 80042 (0.0008) -[2023-10-16 05:56:29,501][05218] Updated weights for policy 0, policy_version 80052 (0.0007) -[2023-10-16 05:56:29,875][05218] Updated weights for policy 0, policy_version 80062 (0.0008) -[2023-10-16 05:56:31,587][05219] Updated weights for policy 1, policy_version 79780 (0.0007) -[2023-10-16 05:56:31,955][05219] Updated weights for policy 1, policy_version 79790 (0.0008) -[2023-10-16 05:56:32,326][05219] Updated weights for policy 1, policy_version 79800 (0.0007) -[2023-10-16 05:56:32,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 163676160. Throughput: 0: 1790.7, 1: 1808.9. Samples: 40933102. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) -[2023-10-16 05:56:32,351][03835] Avg episode reward: [(0, '6.830'), (1, '8.250')] -[2023-10-16 05:56:33,576][05218] Updated weights for policy 0, policy_version 80072 (0.0009) -[2023-10-16 05:56:33,945][05218] Updated weights for policy 0, policy_version 80082 (0.0011) -[2023-10-16 05:56:34,326][05218] Updated weights for policy 0, policy_version 80092 (0.0010) -[2023-10-16 05:56:36,026][05219] Updated weights for policy 1, policy_version 79810 (0.0008) -[2023-10-16 05:56:36,398][05219] Updated weights for policy 1, policy_version 79820 (0.0009) -[2023-10-16 05:56:36,765][05219] Updated weights for policy 1, policy_version 79830 (0.0007) -[2023-10-16 05:56:37,128][05219] Updated weights for policy 1, policy_version 79840 (0.0007) -[2023-10-16 05:56:37,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 163774464. Throughput: 0: 1799.2, 1: 1803.6. Samples: 40954336. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) -[2023-10-16 05:56:37,351][03835] Avg episode reward: [(0, '7.280'), (1, '9.510')] -[2023-10-16 05:56:37,362][04891] Saving new best policy, reward=9.510! -[2023-10-16 05:56:38,196][05218] Updated weights for policy 0, policy_version 80102 (0.0009) -[2023-10-16 05:56:38,577][05218] Updated weights for policy 0, policy_version 80112 (0.0008) -[2023-10-16 05:56:38,942][05218] Updated weights for policy 0, policy_version 80122 (0.0008) -[2023-10-16 05:56:40,813][05219] Updated weights for policy 1, policy_version 79850 (0.0009) -[2023-10-16 05:56:41,174][05219] Updated weights for policy 1, policy_version 79860 (0.0010) -[2023-10-16 05:56:41,541][05219] Updated weights for policy 1, policy_version 79870 (0.0010) -[2023-10-16 05:56:42,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 163840000. Throughput: 0: 1789.1, 1: 1809.1. Samples: 40965400. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) -[2023-10-16 05:56:42,352][03835] Avg episode reward: [(0, '6.250'), (1, '7.760')] -[2023-10-16 05:56:42,649][05218] Updated weights for policy 0, policy_version 80132 (0.0009) -[2023-10-16 05:56:43,017][05218] Updated weights for policy 0, policy_version 80142 (0.0007) -[2023-10-16 05:56:43,390][05218] Updated weights for policy 0, policy_version 80152 (0.0009) -[2023-10-16 05:56:45,325][05219] Updated weights for policy 1, policy_version 79880 (0.0009) -[2023-10-16 05:56:45,691][05219] Updated weights for policy 1, policy_version 79890 (0.0009) -[2023-10-16 05:56:46,059][05219] Updated weights for policy 1, policy_version 79900 (0.0011) -[2023-10-16 05:56:47,008][05218] Updated weights for policy 0, policy_version 80162 (0.0008) -[2023-10-16 05:56:47,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 163905536. Throughput: 0: 1795.3, 1: 1798.0. Samples: 40986702. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) -[2023-10-16 05:56:47,351][03835] Avg episode reward: [(0, '7.040'), (1, '7.280')] -[2023-10-16 05:56:47,383][05218] Updated weights for policy 0, policy_version 80172 (0.0010) -[2023-10-16 05:56:47,763][05218] Updated weights for policy 0, policy_version 80182 (0.0009) -[2023-10-16 05:56:48,134][05218] Updated weights for policy 0, policy_version 80192 (0.0009) -[2023-10-16 05:56:49,896][05219] Updated weights for policy 1, policy_version 79910 (0.0009) -[2023-10-16 05:56:50,262][05219] Updated weights for policy 1, policy_version 79920 (0.0010) -[2023-10-16 05:56:50,632][05219] Updated weights for policy 1, policy_version 79930 (0.0008) -[2023-10-16 05:56:51,820][05218] Updated weights for policy 0, policy_version 80202 (0.0010) -[2023-10-16 05:56:52,200][05218] Updated weights for policy 0, policy_version 80212 (0.0007) -[2023-10-16 05:56:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 163971072. Throughput: 0: 1811.4, 1: 1787.5. Samples: 41007934. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) -[2023-10-16 05:56:52,351][03835] Avg episode reward: [(0, '6.450'), (1, '9.040')] -[2023-10-16 05:56:52,576][05218] Updated weights for policy 0, policy_version 80222 (0.0008) -[2023-10-16 05:56:54,360][05219] Updated weights for policy 1, policy_version 79940 (0.0008) -[2023-10-16 05:56:54,728][05219] Updated weights for policy 1, policy_version 79950 (0.0007) -[2023-10-16 05:56:55,093][05219] Updated weights for policy 1, policy_version 79960 (0.0008) -[2023-10-16 05:56:56,219][05218] Updated weights for policy 0, policy_version 80232 (0.0007) -[2023-10-16 05:56:56,594][05218] Updated weights for policy 0, policy_version 80242 (0.0007) -[2023-10-16 05:56:56,971][05218] Updated weights for policy 0, policy_version 80252 (0.0009) -[2023-10-16 05:56:57,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 164069376. Throughput: 0: 1800.9, 1: 1792.9. Samples: 41019356. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-16 05:56:57,351][03835] Avg episode reward: [(0, '7.300'), (1, '8.390')] -[2023-10-16 05:56:58,813][05219] Updated weights for policy 1, policy_version 79970 (0.0009) -[2023-10-16 05:56:59,176][05219] Updated weights for policy 1, policy_version 79980 (0.0008) -[2023-10-16 05:56:59,549][05219] Updated weights for policy 1, policy_version 79990 (0.0009) -[2023-10-16 05:56:59,920][05219] Updated weights for policy 1, policy_version 80000 (0.0007) -[2023-10-16 05:57:00,676][05218] Updated weights for policy 0, policy_version 80262 (0.0008) -[2023-10-16 05:57:01,054][05218] Updated weights for policy 0, policy_version 80272 (0.0009) -[2023-10-16 05:57:01,432][05218] Updated weights for policy 0, policy_version 80282 (0.0010) -[2023-10-16 05:57:02,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 164134912. Throughput: 0: 1808.2, 1: 1784.2. Samples: 41040552. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-16 05:57:02,351][03835] Avg episode reward: [(0, '6.740'), (1, '7.800')] -[2023-10-16 05:57:03,760][05219] Updated weights for policy 1, policy_version 80010 (0.0010) -[2023-10-16 05:57:04,124][05219] Updated weights for policy 1, policy_version 80020 (0.0009) -[2023-10-16 05:57:04,501][05219] Updated weights for policy 1, policy_version 80030 (0.0009) -[2023-10-16 05:57:05,255][05218] Updated weights for policy 0, policy_version 80292 (0.0009) -[2023-10-16 05:57:05,627][05218] Updated weights for policy 0, policy_version 80302 (0.0010) -[2023-10-16 05:57:06,014][05218] Updated weights for policy 0, policy_version 80312 (0.0008) -[2023-10-16 05:57:07,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 164200448. Throughput: 0: 1793.9, 1: 1787.0. Samples: 41062286. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-16 05:57:07,351][03835] Avg episode reward: [(0, '7.540'), (1, '8.220')] -[2023-10-16 05:57:08,150][05219] Updated weights for policy 1, policy_version 80040 (0.0007) -[2023-10-16 05:57:08,521][05219] Updated weights for policy 1, policy_version 80050 (0.0008) -[2023-10-16 05:57:08,891][05219] Updated weights for policy 1, policy_version 80060 (0.0009) -[2023-10-16 05:57:09,631][05218] Updated weights for policy 0, policy_version 80322 (0.0009) -[2023-10-16 05:57:10,013][05218] Updated weights for policy 0, policy_version 80332 (0.0007) -[2023-10-16 05:57:10,394][05218] Updated weights for policy 0, policy_version 80342 (0.0007) -[2023-10-16 05:57:10,768][05218] Updated weights for policy 0, policy_version 80352 (0.0009) -[2023-10-16 05:57:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 164265984. Throughput: 0: 1809.6, 1: 1787.4. Samples: 41072706. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-16 05:57:12,351][03835] Avg episode reward: [(0, '7.470'), (1, '8.350')] -[2023-10-16 05:57:12,663][05219] Updated weights for policy 1, policy_version 80070 (0.0011) -[2023-10-16 05:57:13,029][05219] Updated weights for policy 1, policy_version 80080 (0.0007) -[2023-10-16 05:57:13,394][05219] Updated weights for policy 1, policy_version 80090 (0.0007) -[2023-10-16 05:57:14,535][05218] Updated weights for policy 0, policy_version 80362 (0.0008) -[2023-10-16 05:57:14,905][05218] Updated weights for policy 0, policy_version 80372 (0.0008) -[2023-10-16 05:57:15,287][05218] Updated weights for policy 0, policy_version 80382 (0.0009) -[2023-10-16 05:57:17,101][05219] Updated weights for policy 1, policy_version 80100 (0.0008) -[2023-10-16 05:57:17,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 164331520. Throughput: 0: 1801.6, 1: 1785.2. Samples: 41094508. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-16 05:57:17,351][03835] Avg episode reward: [(0, '7.070'), (1, '6.310')] -[2023-10-16 05:57:17,463][05219] Updated weights for policy 1, policy_version 80110 (0.0011) -[2023-10-16 05:57:17,828][05219] Updated weights for policy 1, policy_version 80120 (0.0007) -[2023-10-16 05:57:18,899][05218] Updated weights for policy 0, policy_version 80392 (0.0008) -[2023-10-16 05:57:19,271][05218] Updated weights for policy 0, policy_version 80402 (0.0010) -[2023-10-16 05:57:19,646][05218] Updated weights for policy 0, policy_version 80412 (0.0007) -[2023-10-16 05:57:21,673][05219] Updated weights for policy 1, policy_version 80130 (0.0008) -[2023-10-16 05:57:22,035][05219] Updated weights for policy 1, policy_version 80140 (0.0010) -[2023-10-16 05:57:22,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 164397056. Throughput: 0: 1803.6, 1: 1801.6. Samples: 41116570. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-16 05:57:22,351][03835] Avg episode reward: [(0, '6.710'), (1, '7.330')] -[2023-10-16 05:57:22,392][05219] Updated weights for policy 1, policy_version 80150 (0.0007) -[2023-10-16 05:57:22,765][05219] Updated weights for policy 1, policy_version 80160 (0.0009) -[2023-10-16 05:57:23,364][05218] Updated weights for policy 0, policy_version 80422 (0.0009) -[2023-10-16 05:57:23,747][05218] Updated weights for policy 0, policy_version 80432 (0.0008) -[2023-10-16 05:57:24,127][05218] Updated weights for policy 0, policy_version 80442 (0.0007) -[2023-10-16 05:57:26,443][05219] Updated weights for policy 1, policy_version 80170 (0.0008) -[2023-10-16 05:57:26,805][05219] Updated weights for policy 1, policy_version 80180 (0.0009) -[2023-10-16 05:57:27,178][05219] Updated weights for policy 1, policy_version 80190 (0.0010) -[2023-10-16 05:57:27,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 164495360. Throughput: 0: 1806.2, 1: 1785.9. Samples: 41127046. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-16 05:57:27,351][03835] Avg episode reward: [(0, '7.310'), (1, '8.980')] -[2023-10-16 05:57:27,817][05218] Updated weights for policy 0, policy_version 80452 (0.0008) -[2023-10-16 05:57:28,191][05218] Updated weights for policy 0, policy_version 80462 (0.0007) -[2023-10-16 05:57:28,569][05218] Updated weights for policy 0, policy_version 80472 (0.0008) -[2023-10-16 05:57:30,823][05219] Updated weights for policy 1, policy_version 80200 (0.0009) -[2023-10-16 05:57:31,188][05219] Updated weights for policy 1, policy_version 80210 (0.0011) -[2023-10-16 05:57:31,552][05219] Updated weights for policy 1, policy_version 80220 (0.0010) -[2023-10-16 05:57:32,316][05218] Updated weights for policy 0, policy_version 80482 (0.0008) -[2023-10-16 05:57:32,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 164560896. Throughput: 0: 1804.8, 1: 1803.2. Samples: 41149058. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-16 05:57:32,351][03835] Avg episode reward: [(0, '7.220'), (1, '7.540')] -[2023-10-16 05:57:32,699][05218] Updated weights for policy 0, policy_version 80492 (0.0011) -[2023-10-16 05:57:33,078][05218] Updated weights for policy 0, policy_version 80502 (0.0007) -[2023-10-16 05:57:33,448][05218] Updated weights for policy 0, policy_version 80512 (0.0007) -[2023-10-16 05:57:35,329][05219] Updated weights for policy 1, policy_version 80230 (0.0009) -[2023-10-16 05:57:35,689][05219] Updated weights for policy 1, policy_version 80240 (0.0008) -[2023-10-16 05:57:36,063][05219] Updated weights for policy 1, policy_version 80250 (0.0008) -[2023-10-16 05:57:37,180][05218] Updated weights for policy 0, policy_version 80522 (0.0007) -[2023-10-16 05:57:37,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 164626432. Throughput: 0: 1812.6, 1: 1793.7. Samples: 41170218. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-16 05:57:37,351][03835] Avg episode reward: [(0, '6.880'), (1, '8.330')] -[2023-10-16 05:57:37,359][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000080256_82182144.pth... -[2023-10-16 05:57:37,391][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000078560_80445440.pth -[2023-10-16 05:57:37,552][05218] Updated weights for policy 0, policy_version 80532 (0.0007) -[2023-10-16 05:57:37,934][05218] Updated weights for policy 0, policy_version 80542 (0.0008) -[2023-10-16 05:57:38,002][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000080544_82477056.pth... -[2023-10-16 05:57:38,040][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000078848_80740352.pth -[2023-10-16 05:57:39,780][05219] Updated weights for policy 1, policy_version 80260 (0.0008) -[2023-10-16 05:57:40,137][05219] Updated weights for policy 1, policy_version 80270 (0.0010) -[2023-10-16 05:57:40,504][05219] Updated weights for policy 1, policy_version 80280 (0.0008) -[2023-10-16 05:57:41,630][05218] Updated weights for policy 0, policy_version 80552 (0.0009) -[2023-10-16 05:57:42,016][05218] Updated weights for policy 0, policy_version 80562 (0.0011) -[2023-10-16 05:57:42,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 164691968. Throughput: 0: 1797.6, 1: 1805.1. Samples: 41181478. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-16 05:57:42,351][03835] Avg episode reward: [(0, '7.450'), (1, '7.680')] -[2023-10-16 05:57:42,385][05218] Updated weights for policy 0, policy_version 80572 (0.0008) -[2023-10-16 05:57:44,176][05219] Updated weights for policy 1, policy_version 80290 (0.0008) -[2023-10-16 05:57:44,543][05219] Updated weights for policy 1, policy_version 80300 (0.0010) -[2023-10-16 05:57:44,904][05219] Updated weights for policy 1, policy_version 80310 (0.0010) -[2023-10-16 05:57:45,264][05219] Updated weights for policy 1, policy_version 80320 (0.0009) -[2023-10-16 05:57:46,087][05218] Updated weights for policy 0, policy_version 80582 (0.0009) -[2023-10-16 05:57:46,465][05218] Updated weights for policy 0, policy_version 80592 (0.0010) -[2023-10-16 05:57:46,843][05218] Updated weights for policy 0, policy_version 80602 (0.0009) -[2023-10-16 05:57:47,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 164790272. Throughput: 0: 1810.2, 1: 1791.5. Samples: 41202628. Policy #0 lag: (min: 17.0, avg: 29.0, max: 49.0) -[2023-10-16 05:57:47,351][03835] Avg episode reward: [(0, '7.120'), (1, '7.520')] -[2023-10-16 05:57:49,018][05219] Updated weights for policy 1, policy_version 80330 (0.0009) -[2023-10-16 05:57:49,379][05219] Updated weights for policy 1, policy_version 80340 (0.0009) -[2023-10-16 05:57:49,744][05219] Updated weights for policy 1, policy_version 80350 (0.0007) -[2023-10-16 05:57:50,594][05218] Updated weights for policy 0, policy_version 80612 (0.0008) -[2023-10-16 05:57:50,962][05218] Updated weights for policy 0, policy_version 80622 (0.0011) -[2023-10-16 05:57:51,343][05218] Updated weights for policy 0, policy_version 80632 (0.0009) -[2023-10-16 05:57:52,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 164855808. Throughput: 0: 1803.8, 1: 1796.9. Samples: 41224316. Policy #0 lag: (min: 17.0, avg: 29.0, max: 49.0) -[2023-10-16 05:57:52,352][03835] Avg episode reward: [(0, '6.630'), (1, '7.910')] -[2023-10-16 05:57:53,542][05219] Updated weights for policy 1, policy_version 80360 (0.0009) -[2023-10-16 05:57:53,910][05219] Updated weights for policy 1, policy_version 80370 (0.0007) -[2023-10-16 05:57:54,273][05219] Updated weights for policy 1, policy_version 80380 (0.0008) -[2023-10-16 05:57:55,094][05218] Updated weights for policy 0, policy_version 80642 (0.0008) -[2023-10-16 05:57:55,467][05218] Updated weights for policy 0, policy_version 80652 (0.0008) -[2023-10-16 05:57:55,838][05218] Updated weights for policy 0, policy_version 80662 (0.0009) -[2023-10-16 05:57:56,217][05218] Updated weights for policy 0, policy_version 80672 (0.0007) -[2023-10-16 05:57:57,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 164921344. Throughput: 0: 1812.2, 1: 1798.5. Samples: 41235188. Policy #0 lag: (min: 17.0, avg: 29.0, max: 49.0) -[2023-10-16 05:57:57,351][03835] Avg episode reward: [(0, '7.320'), (1, '7.840')] -[2023-10-16 05:57:57,921][05219] Updated weights for policy 1, policy_version 80390 (0.0010) -[2023-10-16 05:57:58,290][05219] Updated weights for policy 1, policy_version 80400 (0.0007) -[2023-10-16 05:57:58,649][05219] Updated weights for policy 1, policy_version 80410 (0.0007) -[2023-10-16 05:58:00,014][05218] Updated weights for policy 0, policy_version 80682 (0.0007) -[2023-10-16 05:58:00,389][05218] Updated weights for policy 0, policy_version 80692 (0.0010) -[2023-10-16 05:58:00,772][05218] Updated weights for policy 0, policy_version 80702 (0.0010) -[2023-10-16 05:58:02,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 164986880. Throughput: 0: 1798.3, 1: 1803.3. Samples: 41256580. Policy #0 lag: (min: 17.0, avg: 29.0, max: 49.0) -[2023-10-16 05:58:02,351][03835] Avg episode reward: [(0, '7.040'), (1, '8.810')] -[2023-10-16 05:58:02,396][05219] Updated weights for policy 1, policy_version 80420 (0.0010) -[2023-10-16 05:58:02,752][05219] Updated weights for policy 1, policy_version 80430 (0.0010) -[2023-10-16 05:58:03,122][05219] Updated weights for policy 1, policy_version 80440 (0.0008) -[2023-10-16 05:58:04,516][05218] Updated weights for policy 0, policy_version 80712 (0.0007) -[2023-10-16 05:58:04,878][05218] Updated weights for policy 0, policy_version 80722 (0.0008) -[2023-10-16 05:58:05,252][05218] Updated weights for policy 0, policy_version 80732 (0.0010) -[2023-10-16 05:58:07,019][05219] Updated weights for policy 1, policy_version 80450 (0.0009) -[2023-10-16 05:58:07,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 165052416. Throughput: 0: 1793.0, 1: 1807.1. Samples: 41278572. Policy #0 lag: (min: 17.0, avg: 29.0, max: 49.0) -[2023-10-16 05:58:07,351][03835] Avg episode reward: [(0, '6.890'), (1, '8.170')] -[2023-10-16 05:58:07,384][05219] Updated weights for policy 1, policy_version 80460 (0.0008) -[2023-10-16 05:58:07,738][05219] Updated weights for policy 1, policy_version 80470 (0.0007) -[2023-10-16 05:58:08,097][05219] Updated weights for policy 1, policy_version 80480 (0.0007) -[2023-10-16 05:58:09,084][05218] Updated weights for policy 0, policy_version 80742 (0.0009) -[2023-10-16 05:58:09,459][05218] Updated weights for policy 0, policy_version 80752 (0.0009) -[2023-10-16 05:58:09,839][05218] Updated weights for policy 0, policy_version 80762 (0.0007) -[2023-10-16 05:58:11,875][05219] Updated weights for policy 1, policy_version 80490 (0.0008) -[2023-10-16 05:58:12,244][05219] Updated weights for policy 1, policy_version 80500 (0.0011) -[2023-10-16 05:58:12,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 165117952. Throughput: 0: 1794.1, 1: 1796.0. Samples: 41288600. Policy #0 lag: (min: 17.0, avg: 29.0, max: 49.0) -[2023-10-16 05:58:12,351][03835] Avg episode reward: [(0, '7.470'), (1, '7.680')] -[2023-10-16 05:58:12,615][05219] Updated weights for policy 1, policy_version 80510 (0.0009) -[2023-10-16 05:58:13,622][05218] Updated weights for policy 0, policy_version 80772 (0.0007) -[2023-10-16 05:58:13,992][05218] Updated weights for policy 0, policy_version 80782 (0.0007) -[2023-10-16 05:58:14,376][05218] Updated weights for policy 0, policy_version 80792 (0.0009) -[2023-10-16 05:58:16,464][05219] Updated weights for policy 1, policy_version 80520 (0.0008) -[2023-10-16 05:58:16,820][05219] Updated weights for policy 1, policy_version 80530 (0.0008) -[2023-10-16 05:58:17,196][05219] Updated weights for policy 1, policy_version 80540 (0.0007) -[2023-10-16 05:58:17,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 165216256. Throughput: 0: 1792.6, 1: 1805.6. Samples: 41310978. Policy #0 lag: (min: 17.0, avg: 29.0, max: 49.0) -[2023-10-16 05:58:17,351][03835] Avg episode reward: [(0, '6.920'), (1, '8.410')] -[2023-10-16 05:58:17,909][05218] Updated weights for policy 0, policy_version 80802 (0.0008) -[2023-10-16 05:58:18,290][05218] Updated weights for policy 0, policy_version 80812 (0.0009) -[2023-10-16 05:58:18,674][05218] Updated weights for policy 0, policy_version 80822 (0.0009) -[2023-10-16 05:58:19,044][05218] Updated weights for policy 0, policy_version 80832 (0.0009) -[2023-10-16 05:58:20,878][05219] Updated weights for policy 1, policy_version 80550 (0.0009) -[2023-10-16 05:58:21,239][05219] Updated weights for policy 1, policy_version 80560 (0.0007) -[2023-10-16 05:58:21,604][05219] Updated weights for policy 1, policy_version 80570 (0.0008) -[2023-10-16 05:58:22,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 165281792. Throughput: 0: 1803.1, 1: 1793.1. Samples: 41332046. Policy #0 lag: (min: 17.0, avg: 29.0, max: 49.0) -[2023-10-16 05:58:22,351][03835] Avg episode reward: [(0, '6.550'), (1, '9.420')] -[2023-10-16 05:58:22,877][05218] Updated weights for policy 0, policy_version 80842 (0.0009) -[2023-10-16 05:58:23,262][05218] Updated weights for policy 0, policy_version 80852 (0.0008) -[2023-10-16 05:58:23,635][05218] Updated weights for policy 0, policy_version 80862 (0.0008) -[2023-10-16 05:58:25,227][05219] Updated weights for policy 1, policy_version 80580 (0.0008) -[2023-10-16 05:58:25,600][05219] Updated weights for policy 1, policy_version 80590 (0.0008) -[2023-10-16 05:58:25,962][05219] Updated weights for policy 1, policy_version 80600 (0.0007) -[2023-10-16 05:58:27,280][05218] Updated weights for policy 0, policy_version 80872 (0.0009) -[2023-10-16 05:58:27,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 165347328. Throughput: 0: 1790.1, 1: 1805.4. Samples: 41343276. Policy #0 lag: (min: 17.0, avg: 29.0, max: 49.0) -[2023-10-16 05:58:27,351][03835] Avg episode reward: [(0, '7.470'), (1, '8.540')] -[2023-10-16 05:58:27,649][05218] Updated weights for policy 0, policy_version 80882 (0.0010) -[2023-10-16 05:58:28,031][05218] Updated weights for policy 0, policy_version 80892 (0.0009) -[2023-10-16 05:58:29,765][05219] Updated weights for policy 1, policy_version 80610 (0.0007) -[2023-10-16 05:58:30,125][05219] Updated weights for policy 1, policy_version 80620 (0.0011) -[2023-10-16 05:58:30,486][05219] Updated weights for policy 1, policy_version 80630 (0.0010) -[2023-10-16 05:58:30,853][05219] Updated weights for policy 1, policy_version 80640 (0.0007) -[2023-10-16 05:58:31,908][05218] Updated weights for policy 0, policy_version 80902 (0.0010) -[2023-10-16 05:58:32,285][05218] Updated weights for policy 0, policy_version 80912 (0.0010) -[2023-10-16 05:58:32,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 165412864. Throughput: 0: 1795.2, 1: 1793.9. Samples: 41364138. Policy #0 lag: (min: 17.0, avg: 29.0, max: 49.0) -[2023-10-16 05:58:32,351][03835] Avg episode reward: [(0, '7.470'), (1, '8.280')] -[2023-10-16 05:58:32,669][05218] Updated weights for policy 0, policy_version 80922 (0.0010) -[2023-10-16 05:58:34,703][05219] Updated weights for policy 1, policy_version 80650 (0.0007) -[2023-10-16 05:58:35,076][05219] Updated weights for policy 1, policy_version 80660 (0.0008) -[2023-10-16 05:58:35,443][05219] Updated weights for policy 1, policy_version 80670 (0.0009) -[2023-10-16 05:58:36,299][05218] Updated weights for policy 0, policy_version 80932 (0.0009) -[2023-10-16 05:58:36,676][05218] Updated weights for policy 0, policy_version 80942 (0.0007) -[2023-10-16 05:58:37,052][05218] Updated weights for policy 0, policy_version 80952 (0.0009) -[2023-10-16 05:58:37,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 165478400. Throughput: 0: 1784.6, 1: 1789.8. Samples: 41385166. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-16 05:58:37,351][03835] Avg episode reward: [(0, '7.670'), (1, '8.440')] -[2023-10-16 05:58:39,297][05219] Updated weights for policy 1, policy_version 80680 (0.0010) -[2023-10-16 05:58:39,666][05219] Updated weights for policy 1, policy_version 80690 (0.0010) -[2023-10-16 05:58:40,022][05219] Updated weights for policy 1, policy_version 80700 (0.0009) -[2023-10-16 05:58:40,854][05218] Updated weights for policy 0, policy_version 80962 (0.0009) -[2023-10-16 05:58:41,236][05218] Updated weights for policy 0, policy_version 80972 (0.0007) -[2023-10-16 05:58:41,605][05218] Updated weights for policy 0, policy_version 80982 (0.0008) -[2023-10-16 05:58:41,991][05218] Updated weights for policy 0, policy_version 80992 (0.0007) -[2023-10-16 05:58:42,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 165576704. Throughput: 0: 1791.2, 1: 1791.8. Samples: 41396420. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-16 05:58:42,351][03835] Avg episode reward: [(0, '8.310'), (1, '7.550')] -[2023-10-16 05:58:42,352][04766] Saving new best policy, reward=8.310! -[2023-10-16 05:58:44,030][05219] Updated weights for policy 1, policy_version 80710 (0.0010) -[2023-10-16 05:58:44,392][05219] Updated weights for policy 1, policy_version 80720 (0.0011) -[2023-10-16 05:58:44,754][05219] Updated weights for policy 1, policy_version 80730 (0.0008) -[2023-10-16 05:58:45,766][05218] Updated weights for policy 0, policy_version 81002 (0.0007) -[2023-10-16 05:58:46,135][05218] Updated weights for policy 0, policy_version 81012 (0.0008) -[2023-10-16 05:58:46,518][05218] Updated weights for policy 0, policy_version 81022 (0.0009) -[2023-10-16 05:58:47,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 165642240. Throughput: 0: 1788.9, 1: 1782.1. Samples: 41417274. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-16 05:58:47,351][03835] Avg episode reward: [(0, '7.160'), (1, '7.410')] -[2023-10-16 05:58:48,359][05219] Updated weights for policy 1, policy_version 80740 (0.0007) -[2023-10-16 05:58:48,723][05219] Updated weights for policy 1, policy_version 80750 (0.0008) -[2023-10-16 05:58:49,086][05219] Updated weights for policy 1, policy_version 80760 (0.0010) -[2023-10-16 05:58:50,282][05218] Updated weights for policy 0, policy_version 81032 (0.0010) -[2023-10-16 05:58:50,653][05218] Updated weights for policy 0, policy_version 81042 (0.0009) -[2023-10-16 05:58:51,027][05218] Updated weights for policy 0, policy_version 81052 (0.0007) -[2023-10-16 05:58:52,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 165707776. Throughput: 0: 1784.0, 1: 1788.9. Samples: 41439354. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-16 05:58:52,351][03835] Avg episode reward: [(0, '6.540'), (1, '6.730')] -[2023-10-16 05:58:52,884][05219] Updated weights for policy 1, policy_version 80770 (0.0010) -[2023-10-16 05:58:53,242][05219] Updated weights for policy 1, policy_version 80780 (0.0008) -[2023-10-16 05:58:53,605][05219] Updated weights for policy 1, policy_version 80790 (0.0010) -[2023-10-16 05:58:53,974][05219] Updated weights for policy 1, policy_version 80800 (0.0009) -[2023-10-16 05:58:54,818][05218] Updated weights for policy 0, policy_version 81062 (0.0008) -[2023-10-16 05:58:55,205][05218] Updated weights for policy 0, policy_version 81072 (0.0008) -[2023-10-16 05:58:55,574][05218] Updated weights for policy 0, policy_version 81082 (0.0009) -[2023-10-16 05:58:57,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 165773312. Throughput: 0: 1796.4, 1: 1785.7. Samples: 41449798. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-16 05:58:57,351][03835] Avg episode reward: [(0, '7.280'), (1, '6.930')] -[2023-10-16 05:58:57,661][05219] Updated weights for policy 1, policy_version 80810 (0.0008) -[2023-10-16 05:58:58,027][05219] Updated weights for policy 1, policy_version 80820 (0.0008) -[2023-10-16 05:58:58,391][05219] Updated weights for policy 1, policy_version 80830 (0.0008) -[2023-10-16 05:58:59,056][05218] Updated weights for policy 0, policy_version 81092 (0.0008) -[2023-10-16 05:58:59,432][05218] Updated weights for policy 0, policy_version 81102 (0.0010) -[2023-10-16 05:58:59,811][05218] Updated weights for policy 0, policy_version 81112 (0.0009) -[2023-10-16 05:59:01,982][05219] Updated weights for policy 1, policy_version 80840 (0.0009) -[2023-10-16 05:59:02,348][05219] Updated weights for policy 1, policy_version 80850 (0.0008) -[2023-10-16 05:59:02,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 165838848. Throughput: 0: 1786.3, 1: 1793.0. Samples: 41472048. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-16 05:59:02,351][03835] Avg episode reward: [(0, '6.630'), (1, '6.680')] -[2023-10-16 05:59:02,704][05219] Updated weights for policy 1, policy_version 80860 (0.0008) -[2023-10-16 05:59:03,494][05218] Updated weights for policy 0, policy_version 81122 (0.0007) -[2023-10-16 05:59:03,863][05218] Updated weights for policy 0, policy_version 81132 (0.0008) -[2023-10-16 05:59:04,233][05218] Updated weights for policy 0, policy_version 81142 (0.0009) -[2023-10-16 05:59:04,611][05218] Updated weights for policy 0, policy_version 81152 (0.0008) -[2023-10-16 05:59:06,560][05219] Updated weights for policy 1, policy_version 80870 (0.0008) -[2023-10-16 05:59:06,929][05219] Updated weights for policy 1, policy_version 80880 (0.0009) -[2023-10-16 05:59:07,308][05219] Updated weights for policy 1, policy_version 80890 (0.0008) -[2023-10-16 05:59:07,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 165904384. Throughput: 0: 1792.5, 1: 1802.0. Samples: 41493798. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-16 05:59:07,352][03835] Avg episode reward: [(0, '6.580'), (1, '7.710')] -[2023-10-16 05:59:08,348][05218] Updated weights for policy 0, policy_version 81162 (0.0008) -[2023-10-16 05:59:08,727][05218] Updated weights for policy 0, policy_version 81172 (0.0008) -[2023-10-16 05:59:09,110][05218] Updated weights for policy 0, policy_version 81182 (0.0009) -[2023-10-16 05:59:11,045][05219] Updated weights for policy 1, policy_version 80900 (0.0008) -[2023-10-16 05:59:11,414][05219] Updated weights for policy 1, policy_version 80910 (0.0008) -[2023-10-16 05:59:11,779][05219] Updated weights for policy 1, policy_version 80920 (0.0010) -[2023-10-16 05:59:12,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 166002688. Throughput: 0: 1794.5, 1: 1790.2. Samples: 41504590. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-16 05:59:12,351][03835] Avg episode reward: [(0, '7.750'), (1, '8.110')] -[2023-10-16 05:59:12,845][05218] Updated weights for policy 0, policy_version 81192 (0.0007) -[2023-10-16 05:59:13,221][05218] Updated weights for policy 0, policy_version 81202 (0.0008) -[2023-10-16 05:59:13,605][05218] Updated weights for policy 0, policy_version 81212 (0.0009) -[2023-10-16 05:59:15,546][05219] Updated weights for policy 1, policy_version 80930 (0.0010) -[2023-10-16 05:59:15,911][05219] Updated weights for policy 1, policy_version 80940 (0.0009) -[2023-10-16 05:59:16,269][05219] Updated weights for policy 1, policy_version 80950 (0.0009) -[2023-10-16 05:59:16,637][05219] Updated weights for policy 1, policy_version 80960 (0.0008) -[2023-10-16 05:59:17,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 166068224. Throughput: 0: 1804.5, 1: 1803.6. Samples: 41526504. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-16 05:59:17,351][03835] Avg episode reward: [(0, '7.280'), (1, '7.180')] -[2023-10-16 05:59:17,355][05218] Updated weights for policy 0, policy_version 81222 (0.0007) -[2023-10-16 05:59:17,732][05218] Updated weights for policy 0, policy_version 81232 (0.0007) -[2023-10-16 05:59:18,101][05218] Updated weights for policy 0, policy_version 81242 (0.0007) -[2023-10-16 05:59:20,444][05219] Updated weights for policy 1, policy_version 80970 (0.0010) -[2023-10-16 05:59:20,805][05219] Updated weights for policy 1, policy_version 80980 (0.0008) -[2023-10-16 05:59:21,176][05219] Updated weights for policy 1, policy_version 80990 (0.0008) -[2023-10-16 05:59:21,714][05218] Updated weights for policy 0, policy_version 81252 (0.0008) -[2023-10-16 05:59:22,084][05218] Updated weights for policy 0, policy_version 81262 (0.0008) -[2023-10-16 05:59:22,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 166133760. Throughput: 0: 1819.3, 1: 1785.2. Samples: 41547370. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-16 05:59:22,351][03835] Avg episode reward: [(0, '6.900'), (1, '8.280')] -[2023-10-16 05:59:22,470][05218] Updated weights for policy 0, policy_version 81272 (0.0009) -[2023-10-16 05:59:24,903][05219] Updated weights for policy 1, policy_version 81000 (0.0009) -[2023-10-16 05:59:25,276][05219] Updated weights for policy 1, policy_version 81010 (0.0009) -[2023-10-16 05:59:25,634][05219] Updated weights for policy 1, policy_version 81020 (0.0007) -[2023-10-16 05:59:26,243][05218] Updated weights for policy 0, policy_version 81282 (0.0008) -[2023-10-16 05:59:26,620][05218] Updated weights for policy 0, policy_version 81292 (0.0008) -[2023-10-16 05:59:26,997][05218] Updated weights for policy 0, policy_version 81302 (0.0010) -[2023-10-16 05:59:27,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 166199296. Throughput: 0: 1811.0, 1: 1801.4. Samples: 41558980. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-16 05:59:27,351][03835] Avg episode reward: [(0, '6.790'), (1, '8.390')] -[2023-10-16 05:59:27,378][05218] Updated weights for policy 0, policy_version 81312 (0.0010) -[2023-10-16 05:59:29,350][05219] Updated weights for policy 1, policy_version 81030 (0.0008) -[2023-10-16 05:59:29,714][05219] Updated weights for policy 1, policy_version 81040 (0.0008) -[2023-10-16 05:59:30,080][05219] Updated weights for policy 1, policy_version 81050 (0.0007) -[2023-10-16 05:59:30,973][05218] Updated weights for policy 0, policy_version 81322 (0.0010) -[2023-10-16 05:59:31,339][05218] Updated weights for policy 0, policy_version 81332 (0.0009) -[2023-10-16 05:59:31,705][05218] Updated weights for policy 0, policy_version 81342 (0.0009) -[2023-10-16 05:59:32,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14745.7, 300 sec: 14440.2). Total num frames: 166297600. Throughput: 0: 1824.7, 1: 1794.7. Samples: 41580146. Policy #0 lag: (min: 25.0, avg: 34.2, max: 57.0) -[2023-10-16 05:59:32,351][03835] Avg episode reward: [(0, '7.110'), (1, '9.120')] -[2023-10-16 05:59:33,782][05219] Updated weights for policy 1, policy_version 81060 (0.0009) -[2023-10-16 05:59:34,149][05219] Updated weights for policy 1, policy_version 81070 (0.0008) -[2023-10-16 05:59:34,518][05219] Updated weights for policy 1, policy_version 81080 (0.0008) -[2023-10-16 05:59:35,291][05218] Updated weights for policy 0, policy_version 81352 (0.0008) -[2023-10-16 05:59:35,666][05218] Updated weights for policy 0, policy_version 81362 (0.0010) -[2023-10-16 05:59:36,046][05218] Updated weights for policy 0, policy_version 81372 (0.0008) -[2023-10-16 05:59:37,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 166363136. Throughput: 0: 1820.9, 1: 1796.2. Samples: 41602126. Policy #0 lag: (min: 25.0, avg: 34.2, max: 57.0) -[2023-10-16 05:59:37,351][03835] Avg episode reward: [(0, '7.510'), (1, '7.990')] -[2023-10-16 05:59:37,361][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000081088_83034112.pth... -[2023-10-16 05:59:37,362][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000081376_83329024.pth... -[2023-10-16 05:59:37,399][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000079680_81592320.pth -[2023-10-16 05:59:37,402][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000079424_81330176.pth -[2023-10-16 05:59:38,361][05219] Updated weights for policy 1, policy_version 81090 (0.0009) -[2023-10-16 05:59:38,716][05219] Updated weights for policy 1, policy_version 81100 (0.0007) -[2023-10-16 05:59:39,088][05219] Updated weights for policy 1, policy_version 81110 (0.0008) -[2023-10-16 05:59:39,452][05219] Updated weights for policy 1, policy_version 81120 (0.0008) -[2023-10-16 05:59:39,781][05218] Updated weights for policy 0, policy_version 81382 (0.0007) -[2023-10-16 05:59:40,162][05218] Updated weights for policy 0, policy_version 81392 (0.0008) -[2023-10-16 05:59:40,536][05218] Updated weights for policy 0, policy_version 81402 (0.0008) -[2023-10-16 05:59:42,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 166428672. Throughput: 0: 1822.9, 1: 1793.4. Samples: 41612532. Policy #0 lag: (min: 25.0, avg: 34.2, max: 57.0) -[2023-10-16 05:59:42,351][03835] Avg episode reward: [(0, '6.670'), (1, '7.570')] -[2023-10-16 05:59:43,194][05219] Updated weights for policy 1, policy_version 81130 (0.0007) -[2023-10-16 05:59:43,555][05219] Updated weights for policy 1, policy_version 81140 (0.0007) -[2023-10-16 05:59:43,921][05219] Updated weights for policy 1, policy_version 81150 (0.0007) -[2023-10-16 05:59:44,149][05218] Updated weights for policy 0, policy_version 81412 (0.0009) -[2023-10-16 05:59:44,519][05218] Updated weights for policy 0, policy_version 81422 (0.0009) -[2023-10-16 05:59:44,902][05218] Updated weights for policy 0, policy_version 81432 (0.0008) -[2023-10-16 05:59:47,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 166494208. Throughput: 0: 1819.8, 1: 1790.2. Samples: 41634500. Policy #0 lag: (min: 25.0, avg: 34.2, max: 57.0) -[2023-10-16 05:59:47,351][03835] Avg episode reward: [(0, '7.700'), (1, '7.930')] -[2023-10-16 05:59:47,762][05219] Updated weights for policy 1, policy_version 81160 (0.0011) -[2023-10-16 05:59:48,127][05219] Updated weights for policy 1, policy_version 81170 (0.0007) -[2023-10-16 05:59:48,496][05219] Updated weights for policy 1, policy_version 81180 (0.0007) -[2023-10-16 05:59:48,681][05218] Updated weights for policy 0, policy_version 81442 (0.0009) -[2023-10-16 05:59:49,048][05218] Updated weights for policy 0, policy_version 81452 (0.0008) -[2023-10-16 05:59:49,427][05218] Updated weights for policy 0, policy_version 81462 (0.0011) -[2023-10-16 05:59:49,793][05218] Updated weights for policy 0, policy_version 81472 (0.0008) -[2023-10-16 05:59:52,242][05219] Updated weights for policy 1, policy_version 81190 (0.0008) -[2023-10-16 05:59:52,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 166559744. Throughput: 0: 1818.0, 1: 1806.9. Samples: 41656920. Policy #0 lag: (min: 25.0, avg: 34.2, max: 57.0) -[2023-10-16 05:59:52,351][03835] Avg episode reward: [(0, '6.440'), (1, '7.370')] -[2023-10-16 05:59:52,604][05219] Updated weights for policy 1, policy_version 81200 (0.0007) -[2023-10-16 05:59:52,970][05219] Updated weights for policy 1, policy_version 81210 (0.0008) -[2023-10-16 05:59:53,430][05218] Updated weights for policy 0, policy_version 81482 (0.0009) -[2023-10-16 05:59:53,808][05218] Updated weights for policy 0, policy_version 81492 (0.0009) -[2023-10-16 05:59:54,182][05218] Updated weights for policy 0, policy_version 81502 (0.0008) -[2023-10-16 05:59:56,646][05219] Updated weights for policy 1, policy_version 81220 (0.0009) -[2023-10-16 05:59:57,009][05219] Updated weights for policy 1, policy_version 81230 (0.0009) -[2023-10-16 05:59:57,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 166625280. Throughput: 0: 1819.4, 1: 1791.1. Samples: 41667060. Policy #0 lag: (min: 25.0, avg: 34.2, max: 57.0) -[2023-10-16 05:59:57,351][03835] Avg episode reward: [(0, '6.610'), (1, '7.300')] -[2023-10-16 05:59:57,373][05219] Updated weights for policy 1, policy_version 81240 (0.0009) -[2023-10-16 05:59:57,971][05218] Updated weights for policy 0, policy_version 81512 (0.0009) -[2023-10-16 05:59:58,343][05218] Updated weights for policy 0, policy_version 81522 (0.0009) -[2023-10-16 05:59:58,716][05218] Updated weights for policy 0, policy_version 81532 (0.0007) -[2023-10-16 06:00:01,227][05219] Updated weights for policy 1, policy_version 81250 (0.0009) -[2023-10-16 06:00:01,592][05219] Updated weights for policy 1, policy_version 81260 (0.0008) -[2023-10-16 06:00:01,955][05219] Updated weights for policy 1, policy_version 81270 (0.0007) -[2023-10-16 06:00:02,324][05219] Updated weights for policy 1, policy_version 81280 (0.0009) -[2023-10-16 06:00:02,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 166723584. Throughput: 0: 1808.0, 1: 1805.3. Samples: 41689104. Policy #0 lag: (min: 25.0, avg: 34.2, max: 57.0) -[2023-10-16 06:00:02,351][03835] Avg episode reward: [(0, '7.470'), (1, '9.240')] -[2023-10-16 06:00:02,536][05218] Updated weights for policy 0, policy_version 81542 (0.0009) -[2023-10-16 06:00:02,911][05218] Updated weights for policy 0, policy_version 81552 (0.0011) -[2023-10-16 06:00:03,282][05218] Updated weights for policy 0, policy_version 81562 (0.0008) -[2023-10-16 06:00:06,154][05219] Updated weights for policy 1, policy_version 81290 (0.0008) -[2023-10-16 06:00:06,526][05219] Updated weights for policy 1, policy_version 81300 (0.0007) -[2023-10-16 06:00:06,897][05219] Updated weights for policy 1, policy_version 81310 (0.0008) -[2023-10-16 06:00:07,087][05218] Updated weights for policy 0, policy_version 81572 (0.0009) -[2023-10-16 06:00:07,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 166789120. Throughput: 0: 1808.3, 1: 1793.1. Samples: 41709430. Policy #0 lag: (min: 25.0, avg: 34.2, max: 57.0) -[2023-10-16 06:00:07,351][03835] Avg episode reward: [(0, '7.220'), (1, '8.950')] -[2023-10-16 06:00:07,464][05218] Updated weights for policy 0, policy_version 81582 (0.0007) -[2023-10-16 06:00:07,848][05218] Updated weights for policy 0, policy_version 81592 (0.0007) -[2023-10-16 06:00:10,610][05219] Updated weights for policy 1, policy_version 81320 (0.0008) -[2023-10-16 06:00:10,965][05219] Updated weights for policy 1, policy_version 81330 (0.0008) -[2023-10-16 06:00:11,327][05219] Updated weights for policy 1, policy_version 81340 (0.0009) -[2023-10-16 06:00:11,702][05218] Updated weights for policy 0, policy_version 81602 (0.0008) -[2023-10-16 06:00:12,077][05218] Updated weights for policy 0, policy_version 81612 (0.0008) -[2023-10-16 06:00:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 166854656. Throughput: 0: 1791.7, 1: 1804.6. Samples: 41720814. Policy #0 lag: (min: 25.0, avg: 34.2, max: 57.0) -[2023-10-16 06:00:12,351][03835] Avg episode reward: [(0, '7.570'), (1, '7.860')] -[2023-10-16 06:00:12,457][05218] Updated weights for policy 0, policy_version 81622 (0.0009) -[2023-10-16 06:00:12,830][05218] Updated weights for policy 0, policy_version 81632 (0.0007) -[2023-10-16 06:00:15,304][05219] Updated weights for policy 1, policy_version 81350 (0.0009) -[2023-10-16 06:00:15,669][05219] Updated weights for policy 1, policy_version 81360 (0.0007) -[2023-10-16 06:00:16,036][05219] Updated weights for policy 1, policy_version 81370 (0.0010) -[2023-10-16 06:00:16,678][05218] Updated weights for policy 0, policy_version 81642 (0.0009) -[2023-10-16 06:00:17,063][05218] Updated weights for policy 0, policy_version 81652 (0.0007) -[2023-10-16 06:00:17,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 166920192. Throughput: 0: 1802.4, 1: 1790.5. Samples: 41741826. Policy #0 lag: (min: 25.0, avg: 34.2, max: 57.0) -[2023-10-16 06:00:17,351][03835] Avg episode reward: [(0, '6.500'), (1, '8.160')] -[2023-10-16 06:00:17,439][05218] Updated weights for policy 0, policy_version 81662 (0.0010) -[2023-10-16 06:00:19,673][05219] Updated weights for policy 1, policy_version 81380 (0.0010) -[2023-10-16 06:00:20,034][05219] Updated weights for policy 1, policy_version 81390 (0.0009) -[2023-10-16 06:00:20,395][05219] Updated weights for policy 1, policy_version 81400 (0.0007) -[2023-10-16 06:00:21,248][05218] Updated weights for policy 0, policy_version 81672 (0.0009) -[2023-10-16 06:00:21,627][05218] Updated weights for policy 0, policy_version 81682 (0.0007) -[2023-10-16 06:00:22,003][05218] Updated weights for policy 0, policy_version 81692 (0.0009) -[2023-10-16 06:00:22,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 167018496. Throughput: 0: 1778.0, 1: 1787.3. Samples: 41762568. Policy #0 lag: (min: 1.0, avg: 20.2, max: 33.0) -[2023-10-16 06:00:22,351][03835] Avg episode reward: [(0, '7.510'), (1, '8.040')] -[2023-10-16 06:00:24,218][05219] Updated weights for policy 1, policy_version 81410 (0.0009) -[2023-10-16 06:00:24,584][05219] Updated weights for policy 1, policy_version 81420 (0.0011) -[2023-10-16 06:00:24,956][05219] Updated weights for policy 1, policy_version 81430 (0.0010) -[2023-10-16 06:00:25,320][05219] Updated weights for policy 1, policy_version 81440 (0.0008) -[2023-10-16 06:00:25,827][05218] Updated weights for policy 0, policy_version 81702 (0.0008) -[2023-10-16 06:00:26,215][05218] Updated weights for policy 0, policy_version 81712 (0.0009) -[2023-10-16 06:00:26,592][05218] Updated weights for policy 0, policy_version 81722 (0.0007) -[2023-10-16 06:00:27,350][03835] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 167084032. Throughput: 0: 1801.9, 1: 1788.8. Samples: 41774114. Policy #0 lag: (min: 1.0, avg: 20.2, max: 33.0) -[2023-10-16 06:00:27,351][03835] Avg episode reward: [(0, '7.300'), (1, '7.040')] -[2023-10-16 06:00:29,014][05219] Updated weights for policy 1, policy_version 81450 (0.0008) -[2023-10-16 06:00:29,371][05219] Updated weights for policy 1, policy_version 81460 (0.0007) -[2023-10-16 06:00:29,737][05219] Updated weights for policy 1, policy_version 81470 (0.0008) -[2023-10-16 06:00:30,236][05218] Updated weights for policy 0, policy_version 81732 (0.0009) -[2023-10-16 06:00:30,616][05218] Updated weights for policy 0, policy_version 81742 (0.0010) -[2023-10-16 06:00:30,992][05218] Updated weights for policy 0, policy_version 81752 (0.0011) -[2023-10-16 06:00:32,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 167149568. Throughput: 0: 1776.1, 1: 1783.9. Samples: 41794698. Policy #0 lag: (min: 1.0, avg: 20.2, max: 33.0) -[2023-10-16 06:00:32,351][03835] Avg episode reward: [(0, '7.070'), (1, '8.240')] -[2023-10-16 06:00:33,507][05219] Updated weights for policy 1, policy_version 81480 (0.0010) -[2023-10-16 06:00:33,874][05219] Updated weights for policy 1, policy_version 81490 (0.0009) -[2023-10-16 06:00:34,245][05219] Updated weights for policy 1, policy_version 81500 (0.0008) -[2023-10-16 06:00:34,833][05218] Updated weights for policy 0, policy_version 81762 (0.0008) -[2023-10-16 06:00:35,211][05218] Updated weights for policy 0, policy_version 81772 (0.0010) -[2023-10-16 06:00:35,573][05218] Updated weights for policy 0, policy_version 81782 (0.0010) -[2023-10-16 06:00:35,944][05218] Updated weights for policy 0, policy_version 81792 (0.0011) -[2023-10-16 06:00:37,351][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 167215104. Throughput: 0: 1768.9, 1: 1790.3. Samples: 41817084. Policy #0 lag: (min: 1.0, avg: 20.2, max: 33.0) -[2023-10-16 06:00:37,352][03835] Avg episode reward: [(0, '7.240'), (1, '8.980')] -[2023-10-16 06:00:37,853][05219] Updated weights for policy 1, policy_version 81510 (0.0007) -[2023-10-16 06:00:38,222][05219] Updated weights for policy 1, policy_version 81520 (0.0010) -[2023-10-16 06:00:38,589][05219] Updated weights for policy 1, policy_version 81530 (0.0010) -[2023-10-16 06:00:39,800][05218] Updated weights for policy 0, policy_version 81802 (0.0010) -[2023-10-16 06:00:40,173][05218] Updated weights for policy 0, policy_version 81812 (0.0011) -[2023-10-16 06:00:40,550][05218] Updated weights for policy 0, policy_version 81822 (0.0010) -[2023-10-16 06:00:42,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 167280640. Throughput: 0: 1773.6, 1: 1785.6. Samples: 41827226. Policy #0 lag: (min: 1.0, avg: 20.2, max: 33.0) -[2023-10-16 06:00:42,351][03835] Avg episode reward: [(0, '6.610'), (1, '8.860')] -[2023-10-16 06:00:42,648][05219] Updated weights for policy 1, policy_version 81540 (0.0009) -[2023-10-16 06:00:43,016][05219] Updated weights for policy 1, policy_version 81550 (0.0007) -[2023-10-16 06:00:43,378][05219] Updated weights for policy 1, policy_version 81560 (0.0008) -[2023-10-16 06:00:44,320][05218] Updated weights for policy 0, policy_version 81832 (0.0008) -[2023-10-16 06:00:44,689][05218] Updated weights for policy 0, policy_version 81842 (0.0007) -[2023-10-16 06:00:45,076][05218] Updated weights for policy 0, policy_version 81852 (0.0007) -[2023-10-16 06:00:47,144][05219] Updated weights for policy 1, policy_version 81570 (0.0008) -[2023-10-16 06:00:47,350][03835] Fps is (10 sec: 13107.8, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 167346176. Throughput: 0: 1769.4, 1: 1783.3. Samples: 41848976. Policy #0 lag: (min: 1.0, avg: 20.2, max: 33.0) -[2023-10-16 06:00:47,351][03835] Avg episode reward: [(0, '7.050'), (1, '7.950')] -[2023-10-16 06:00:47,517][05219] Updated weights for policy 1, policy_version 81580 (0.0011) -[2023-10-16 06:00:47,873][05219] Updated weights for policy 1, policy_version 81590 (0.0007) -[2023-10-16 06:00:48,241][05219] Updated weights for policy 1, policy_version 81600 (0.0009) -[2023-10-16 06:00:48,574][05218] Updated weights for policy 0, policy_version 81862 (0.0008) -[2023-10-16 06:00:48,946][05218] Updated weights for policy 0, policy_version 81872 (0.0009) -[2023-10-16 06:00:49,330][05218] Updated weights for policy 0, policy_version 81882 (0.0008) -[2023-10-16 06:00:51,975][05219] Updated weights for policy 1, policy_version 81610 (0.0008) -[2023-10-16 06:00:52,350][05219] Updated weights for policy 1, policy_version 81620 (0.0009) -[2023-10-16 06:00:52,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 167411712. Throughput: 0: 1783.5, 1: 1803.0. Samples: 41870822. Policy #0 lag: (min: 1.0, avg: 20.2, max: 33.0) -[2023-10-16 06:00:52,351][03835] Avg episode reward: [(0, '6.630'), (1, '8.520')] -[2023-10-16 06:00:52,718][05219] Updated weights for policy 1, policy_version 81630 (0.0007) -[2023-10-16 06:00:53,237][05218] Updated weights for policy 0, policy_version 81892 (0.0009) -[2023-10-16 06:00:53,608][05218] Updated weights for policy 0, policy_version 81902 (0.0011) -[2023-10-16 06:00:53,980][05218] Updated weights for policy 0, policy_version 81912 (0.0009) -[2023-10-16 06:00:56,466][05219] Updated weights for policy 1, policy_version 81640 (0.0007) -[2023-10-16 06:00:56,823][05219] Updated weights for policy 1, policy_version 81650 (0.0008) -[2023-10-16 06:00:57,181][05219] Updated weights for policy 1, policy_version 81660 (0.0008) -[2023-10-16 06:00:57,351][03835] Fps is (10 sec: 16383.4, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 167510016. Throughput: 0: 1771.2, 1: 1788.7. Samples: 41881010. Policy #0 lag: (min: 1.0, avg: 20.2, max: 33.0) -[2023-10-16 06:00:57,352][03835] Avg episode reward: [(0, '6.940'), (1, '8.780')] -[2023-10-16 06:00:57,798][05218] Updated weights for policy 0, policy_version 81922 (0.0010) -[2023-10-16 06:00:58,171][05218] Updated weights for policy 0, policy_version 81932 (0.0010) -[2023-10-16 06:00:58,544][05218] Updated weights for policy 0, policy_version 81942 (0.0010) -[2023-10-16 06:00:58,923][05218] Updated weights for policy 0, policy_version 81952 (0.0008) -[2023-10-16 06:01:00,874][05219] Updated weights for policy 1, policy_version 81670 (0.0009) -[2023-10-16 06:01:01,230][05219] Updated weights for policy 1, policy_version 81680 (0.0009) -[2023-10-16 06:01:01,601][05219] Updated weights for policy 1, policy_version 81690 (0.0010) -[2023-10-16 06:01:02,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 167575552. Throughput: 0: 1775.2, 1: 1804.7. Samples: 41902918. Policy #0 lag: (min: 1.0, avg: 20.2, max: 33.0) -[2023-10-16 06:01:02,351][03835] Avg episode reward: [(0, '7.080'), (1, '7.570')] -[2023-10-16 06:01:02,666][05218] Updated weights for policy 0, policy_version 81962 (0.0009) -[2023-10-16 06:01:03,029][05218] Updated weights for policy 0, policy_version 81972 (0.0009) -[2023-10-16 06:01:03,411][05218] Updated weights for policy 0, policy_version 81982 (0.0008) -[2023-10-16 06:01:05,220][05219] Updated weights for policy 1, policy_version 81700 (0.0009) -[2023-10-16 06:01:05,591][05219] Updated weights for policy 1, policy_version 81710 (0.0008) -[2023-10-16 06:01:05,956][05219] Updated weights for policy 1, policy_version 81720 (0.0007) -[2023-10-16 06:01:07,098][05218] Updated weights for policy 0, policy_version 81992 (0.0008) -[2023-10-16 06:01:07,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 167641088. Throughput: 0: 1797.6, 1: 1789.4. Samples: 41923980. Policy #0 lag: (min: 1.0, avg: 20.2, max: 33.0) -[2023-10-16 06:01:07,351][03835] Avg episode reward: [(0, '6.550'), (1, '7.620')] -[2023-10-16 06:01:07,461][05218] Updated weights for policy 0, policy_version 82002 (0.0009) -[2023-10-16 06:01:07,832][05218] Updated weights for policy 0, policy_version 82012 (0.0008) -[2023-10-16 06:01:09,594][05219] Updated weights for policy 1, policy_version 81730 (0.0009) -[2023-10-16 06:01:09,958][05219] Updated weights for policy 1, policy_version 81740 (0.0007) -[2023-10-16 06:01:10,327][05219] Updated weights for policy 1, policy_version 81750 (0.0008) -[2023-10-16 06:01:10,693][05219] Updated weights for policy 1, policy_version 81760 (0.0007) -[2023-10-16 06:01:11,523][05218] Updated weights for policy 0, policy_version 82022 (0.0009) -[2023-10-16 06:01:11,900][05218] Updated weights for policy 0, policy_version 82032 (0.0008) -[2023-10-16 06:01:12,270][05218] Updated weights for policy 0, policy_version 82042 (0.0007) -[2023-10-16 06:01:12,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 167706624. Throughput: 0: 1776.9, 1: 1803.8. Samples: 41935246. Policy #0 lag: (min: 1.0, avg: 20.2, max: 33.0) -[2023-10-16 06:01:12,351][03835] Avg episode reward: [(0, '7.210'), (1, '9.450')] -[2023-10-16 06:01:14,253][05219] Updated weights for policy 1, policy_version 81770 (0.0007) -[2023-10-16 06:01:14,631][05219] Updated weights for policy 1, policy_version 81780 (0.0008) -[2023-10-16 06:01:14,996][05219] Updated weights for policy 1, policy_version 81790 (0.0007) -[2023-10-16 06:01:15,964][05218] Updated weights for policy 0, policy_version 82052 (0.0009) -[2023-10-16 06:01:16,333][05218] Updated weights for policy 0, policy_version 82062 (0.0009) -[2023-10-16 06:01:16,713][05218] Updated weights for policy 0, policy_version 82072 (0.0009) -[2023-10-16 06:01:17,350][03835] Fps is (10 sec: 16383.4, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 167804928. Throughput: 0: 1800.2, 1: 1795.1. Samples: 41956486. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:01:17,352][03835] Avg episode reward: [(0, '7.040'), (1, '8.340')] -[2023-10-16 06:01:18,755][05219] Updated weights for policy 1, policy_version 81800 (0.0008) -[2023-10-16 06:01:19,118][05219] Updated weights for policy 1, policy_version 81810 (0.0007) -[2023-10-16 06:01:19,481][05219] Updated weights for policy 1, policy_version 81820 (0.0008) -[2023-10-16 06:01:20,473][05218] Updated weights for policy 0, policy_version 82082 (0.0009) -[2023-10-16 06:01:20,840][05218] Updated weights for policy 0, policy_version 82092 (0.0010) -[2023-10-16 06:01:21,216][05218] Updated weights for policy 0, policy_version 82102 (0.0007) -[2023-10-16 06:01:21,591][05218] Updated weights for policy 0, policy_version 82112 (0.0010) -[2023-10-16 06:01:22,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 167870464. Throughput: 0: 1784.1, 1: 1793.7. Samples: 41978086. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:01:22,351][03835] Avg episode reward: [(0, '6.440'), (1, '8.660')] -[2023-10-16 06:01:23,392][05219] Updated weights for policy 1, policy_version 81830 (0.0009) -[2023-10-16 06:01:23,764][05219] Updated weights for policy 1, policy_version 81840 (0.0007) -[2023-10-16 06:01:24,130][05219] Updated weights for policy 1, policy_version 81850 (0.0009) -[2023-10-16 06:01:25,405][05218] Updated weights for policy 0, policy_version 82122 (0.0010) -[2023-10-16 06:01:25,778][05218] Updated weights for policy 0, policy_version 82132 (0.0009) -[2023-10-16 06:01:26,152][05218] Updated weights for policy 0, policy_version 82142 (0.0010) -[2023-10-16 06:01:27,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 167936000. Throughput: 0: 1798.5, 1: 1792.6. Samples: 41988828. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:01:27,351][03835] Avg episode reward: [(0, '7.120'), (1, '8.860')] -[2023-10-16 06:01:27,722][05219] Updated weights for policy 1, policy_version 81860 (0.0008) -[2023-10-16 06:01:28,093][05219] Updated weights for policy 1, policy_version 81870 (0.0008) -[2023-10-16 06:01:28,464][05219] Updated weights for policy 1, policy_version 81880 (0.0008) -[2023-10-16 06:01:29,895][05218] Updated weights for policy 0, policy_version 82152 (0.0007) -[2023-10-16 06:01:30,266][05218] Updated weights for policy 0, policy_version 82162 (0.0009) -[2023-10-16 06:01:30,638][05218] Updated weights for policy 0, policy_version 82172 (0.0010) -[2023-10-16 06:01:32,283][05219] Updated weights for policy 1, policy_version 81890 (0.0008) -[2023-10-16 06:01:32,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 168001536. Throughput: 0: 1782.8, 1: 1801.9. Samples: 42010284. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:01:32,351][03835] Avg episode reward: [(0, '6.850'), (1, '9.180')] -[2023-10-16 06:01:32,648][05219] Updated weights for policy 1, policy_version 81900 (0.0007) -[2023-10-16 06:01:33,014][05219] Updated weights for policy 1, policy_version 81910 (0.0008) -[2023-10-16 06:01:33,387][05219] Updated weights for policy 1, policy_version 81920 (0.0011) -[2023-10-16 06:01:34,239][05218] Updated weights for policy 0, policy_version 82182 (0.0010) -[2023-10-16 06:01:34,620][05218] Updated weights for policy 0, policy_version 82192 (0.0008) -[2023-10-16 06:01:34,980][05218] Updated weights for policy 0, policy_version 82202 (0.0009) -[2023-10-16 06:01:37,199][05219] Updated weights for policy 1, policy_version 81930 (0.0008) -[2023-10-16 06:01:37,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 168067072. Throughput: 0: 1790.6, 1: 1806.1. Samples: 42032670. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:01:37,351][03835] Avg episode reward: [(0, '7.040'), (1, '8.650')] -[2023-10-16 06:01:37,360][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000082208_84180992.pth... -[2023-10-16 06:01:37,397][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000080544_82477056.pth -[2023-10-16 06:01:37,574][05219] Updated weights for policy 1, policy_version 81940 (0.0010) -[2023-10-16 06:01:37,940][05219] Updated weights for policy 1, policy_version 81950 (0.0008) -[2023-10-16 06:01:38,009][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000081952_83918848.pth... -[2023-10-16 06:01:38,046][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000080256_82182144.pth -[2023-10-16 06:01:38,878][05218] Updated weights for policy 0, policy_version 82212 (0.0008) -[2023-10-16 06:01:39,244][05218] Updated weights for policy 0, policy_version 82222 (0.0007) -[2023-10-16 06:01:39,617][05218] Updated weights for policy 0, policy_version 82232 (0.0009) -[2023-10-16 06:01:41,647][05219] Updated weights for policy 1, policy_version 81960 (0.0009) -[2023-10-16 06:01:42,008][05219] Updated weights for policy 1, policy_version 81970 (0.0009) -[2023-10-16 06:01:42,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 168132608. Throughput: 0: 1792.4, 1: 1803.9. Samples: 42042844. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:01:42,351][03835] Avg episode reward: [(0, '7.290'), (1, '8.120')] -[2023-10-16 06:01:42,373][05219] Updated weights for policy 1, policy_version 81980 (0.0009) -[2023-10-16 06:01:43,439][05218] Updated weights for policy 0, policy_version 82242 (0.0008) -[2023-10-16 06:01:43,822][05218] Updated weights for policy 0, policy_version 82252 (0.0009) -[2023-10-16 06:01:44,190][05218] Updated weights for policy 0, policy_version 82262 (0.0010) -[2023-10-16 06:01:44,573][05218] Updated weights for policy 0, policy_version 82272 (0.0010) -[2023-10-16 06:01:46,365][05219] Updated weights for policy 1, policy_version 81990 (0.0008) -[2023-10-16 06:01:46,736][05219] Updated weights for policy 1, policy_version 82000 (0.0007) -[2023-10-16 06:01:47,090][05219] Updated weights for policy 1, policy_version 82010 (0.0007) -[2023-10-16 06:01:47,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 168230912. Throughput: 0: 1788.6, 1: 1813.8. Samples: 42065026. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:01:47,351][03835] Avg episode reward: [(0, '6.710'), (1, '8.890')] -[2023-10-16 06:01:48,415][05218] Updated weights for policy 0, policy_version 82282 (0.0008) -[2023-10-16 06:01:48,796][05218] Updated weights for policy 0, policy_version 82292 (0.0009) -[2023-10-16 06:01:49,167][05218] Updated weights for policy 0, policy_version 82302 (0.0009) -[2023-10-16 06:01:50,753][05219] Updated weights for policy 1, policy_version 82020 (0.0008) -[2023-10-16 06:01:51,114][05219] Updated weights for policy 1, policy_version 82030 (0.0011) -[2023-10-16 06:01:51,473][05219] Updated weights for policy 1, policy_version 82040 (0.0009) -[2023-10-16 06:01:52,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 168296448. Throughput: 0: 1802.5, 1: 1801.2. Samples: 42086144. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:01:52,351][03835] Avg episode reward: [(0, '7.310'), (1, '7.480')] -[2023-10-16 06:01:52,829][05218] Updated weights for policy 0, policy_version 82312 (0.0009) -[2023-10-16 06:01:53,203][05218] Updated weights for policy 0, policy_version 82322 (0.0009) -[2023-10-16 06:01:53,585][05218] Updated weights for policy 0, policy_version 82332 (0.0008) -[2023-10-16 06:01:55,170][05219] Updated weights for policy 1, policy_version 82050 (0.0011) -[2023-10-16 06:01:55,541][05219] Updated weights for policy 1, policy_version 82060 (0.0008) -[2023-10-16 06:01:55,904][05219] Updated weights for policy 1, policy_version 82070 (0.0008) -[2023-10-16 06:01:56,274][05219] Updated weights for policy 1, policy_version 82080 (0.0009) -[2023-10-16 06:01:57,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 168361984. Throughput: 0: 1782.3, 1: 1819.3. Samples: 42097318. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:01:57,351][03835] Avg episode reward: [(0, '7.330'), (1, '7.500')] -[2023-10-16 06:01:57,490][05218] Updated weights for policy 0, policy_version 82342 (0.0007) -[2023-10-16 06:01:57,872][05218] Updated weights for policy 0, policy_version 82352 (0.0009) -[2023-10-16 06:01:58,252][05218] Updated weights for policy 0, policy_version 82362 (0.0008) -[2023-10-16 06:01:59,871][05219] Updated weights for policy 1, policy_version 82090 (0.0009) -[2023-10-16 06:02:00,232][05219] Updated weights for policy 1, policy_version 82100 (0.0009) -[2023-10-16 06:02:00,600][05219] Updated weights for policy 1, policy_version 82110 (0.0008) -[2023-10-16 06:02:01,929][05218] Updated weights for policy 0, policy_version 82372 (0.0007) -[2023-10-16 06:02:02,309][05218] Updated weights for policy 0, policy_version 82382 (0.0008) -[2023-10-16 06:02:02,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 168427520. Throughput: 0: 1793.9, 1: 1805.4. Samples: 42118454. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:02:02,351][03835] Avg episode reward: [(0, '6.850'), (1, '8.180')] -[2023-10-16 06:02:02,682][05218] Updated weights for policy 0, policy_version 82392 (0.0008) -[2023-10-16 06:02:04,278][05219] Updated weights for policy 1, policy_version 82120 (0.0010) -[2023-10-16 06:02:04,647][05219] Updated weights for policy 1, policy_version 82130 (0.0011) -[2023-10-16 06:02:05,016][05219] Updated weights for policy 1, policy_version 82140 (0.0008) -[2023-10-16 06:02:06,357][05218] Updated weights for policy 0, policy_version 82402 (0.0011) -[2023-10-16 06:02:06,740][05218] Updated weights for policy 0, policy_version 82412 (0.0008) -[2023-10-16 06:02:07,114][05218] Updated weights for policy 0, policy_version 82422 (0.0009) -[2023-10-16 06:02:07,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 168493056. Throughput: 0: 1787.0, 1: 1804.9. Samples: 42139722. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:02:07,351][03835] Avg episode reward: [(0, '7.120'), (1, '8.220')] -[2023-10-16 06:02:07,503][05218] Updated weights for policy 0, policy_version 82432 (0.0010) -[2023-10-16 06:02:08,703][05219] Updated weights for policy 1, policy_version 82150 (0.0009) -[2023-10-16 06:02:09,071][05219] Updated weights for policy 1, policy_version 82160 (0.0008) -[2023-10-16 06:02:09,432][05219] Updated weights for policy 1, policy_version 82170 (0.0008) -[2023-10-16 06:02:11,022][05218] Updated weights for policy 0, policy_version 82442 (0.0007) -[2023-10-16 06:02:11,402][05218] Updated weights for policy 0, policy_version 82452 (0.0008) -[2023-10-16 06:02:11,778][05218] Updated weights for policy 0, policy_version 82462 (0.0009) -[2023-10-16 06:02:12,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 168591360. Throughput: 0: 1795.2, 1: 1806.5. Samples: 42150904. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-16 06:02:12,351][03835] Avg episode reward: [(0, '7.360'), (1, '8.420')] -[2023-10-16 06:02:13,144][05219] Updated weights for policy 1, policy_version 82180 (0.0007) -[2023-10-16 06:02:13,503][05219] Updated weights for policy 1, policy_version 82190 (0.0008) -[2023-10-16 06:02:13,874][05219] Updated weights for policy 1, policy_version 82200 (0.0007) -[2023-10-16 06:02:15,433][05218] Updated weights for policy 0, policy_version 82472 (0.0009) -[2023-10-16 06:02:15,808][05218] Updated weights for policy 0, policy_version 82482 (0.0009) -[2023-10-16 06:02:16,193][05218] Updated weights for policy 0, policy_version 82492 (0.0011) -[2023-10-16 06:02:17,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 168656896. Throughput: 0: 1789.0, 1: 1806.3. Samples: 42172070. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-16 06:02:17,351][03835] Avg episode reward: [(0, '6.500'), (1, '9.300')] -[2023-10-16 06:02:17,619][05219] Updated weights for policy 1, policy_version 82210 (0.0008) -[2023-10-16 06:02:17,984][05219] Updated weights for policy 1, policy_version 82220 (0.0010) -[2023-10-16 06:02:18,354][05219] Updated weights for policy 1, policy_version 82230 (0.0008) -[2023-10-16 06:02:18,718][05219] Updated weights for policy 1, policy_version 82240 (0.0008) -[2023-10-16 06:02:19,939][05218] Updated weights for policy 0, policy_version 82502 (0.0009) -[2023-10-16 06:02:20,316][05218] Updated weights for policy 0, policy_version 82512 (0.0009) -[2023-10-16 06:02:20,698][05218] Updated weights for policy 0, policy_version 82522 (0.0010) -[2023-10-16 06:02:22,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 168722432. Throughput: 0: 1783.2, 1: 1817.4. Samples: 42194694. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-16 06:02:22,351][03835] Avg episode reward: [(0, '6.490'), (1, '8.320')] -[2023-10-16 06:02:22,733][05219] Updated weights for policy 1, policy_version 82250 (0.0008) -[2023-10-16 06:02:23,105][05219] Updated weights for policy 1, policy_version 82260 (0.0009) -[2023-10-16 06:02:23,461][05219] Updated weights for policy 1, policy_version 82270 (0.0010) -[2023-10-16 06:02:24,486][05218] Updated weights for policy 0, policy_version 82532 (0.0008) -[2023-10-16 06:02:24,860][05218] Updated weights for policy 0, policy_version 82542 (0.0007) -[2023-10-16 06:02:25,243][05218] Updated weights for policy 0, policy_version 82552 (0.0009) -[2023-10-16 06:02:27,241][05219] Updated weights for policy 1, policy_version 82280 (0.0010) -[2023-10-16 06:02:27,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 168787968. Throughput: 0: 1795.1, 1: 1797.7. Samples: 42204520. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-16 06:02:27,351][03835] Avg episode reward: [(0, '6.370'), (1, '8.360')] -[2023-10-16 06:02:27,612][05219] Updated weights for policy 1, policy_version 82290 (0.0007) -[2023-10-16 06:02:27,969][05219] Updated weights for policy 1, policy_version 82300 (0.0007) -[2023-10-16 06:02:28,935][05218] Updated weights for policy 0, policy_version 82562 (0.0010) -[2023-10-16 06:02:29,308][05218] Updated weights for policy 0, policy_version 82572 (0.0010) -[2023-10-16 06:02:29,683][05218] Updated weights for policy 0, policy_version 82582 (0.0010) -[2023-10-16 06:02:30,065][05218] Updated weights for policy 0, policy_version 82592 (0.0007) -[2023-10-16 06:02:31,834][05219] Updated weights for policy 1, policy_version 82310 (0.0008) -[2023-10-16 06:02:32,208][05219] Updated weights for policy 1, policy_version 82320 (0.0007) -[2023-10-16 06:02:32,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 168853504. Throughput: 0: 1794.9, 1: 1798.6. Samples: 42226734. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-16 06:02:32,351][03835] Avg episode reward: [(0, '6.000'), (1, '8.760')] -[2023-10-16 06:02:32,579][05219] Updated weights for policy 1, policy_version 82330 (0.0007) -[2023-10-16 06:02:33,793][05218] Updated weights for policy 0, policy_version 82602 (0.0007) -[2023-10-16 06:02:34,166][05218] Updated weights for policy 0, policy_version 82612 (0.0008) -[2023-10-16 06:02:34,544][05218] Updated weights for policy 0, policy_version 82622 (0.0010) -[2023-10-16 06:02:36,302][05219] Updated weights for policy 1, policy_version 82340 (0.0008) -[2023-10-16 06:02:36,665][05219] Updated weights for policy 1, policy_version 82350 (0.0008) -[2023-10-16 06:02:37,024][05219] Updated weights for policy 1, policy_version 82360 (0.0009) -[2023-10-16 06:02:37,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 168951808. Throughput: 0: 1802.0, 1: 1802.3. Samples: 42248338. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-16 06:02:37,351][03835] Avg episode reward: [(0, '6.710'), (1, '9.160')] -[2023-10-16 06:02:38,083][05218] Updated weights for policy 0, policy_version 82632 (0.0007) -[2023-10-16 06:02:38,461][05218] Updated weights for policy 0, policy_version 82642 (0.0008) -[2023-10-16 06:02:38,840][05218] Updated weights for policy 0, policy_version 82652 (0.0007) -[2023-10-16 06:02:40,826][05219] Updated weights for policy 1, policy_version 82370 (0.0010) -[2023-10-16 06:02:41,196][05219] Updated weights for policy 1, policy_version 82380 (0.0009) -[2023-10-16 06:02:41,558][05219] Updated weights for policy 1, policy_version 82390 (0.0009) -[2023-10-16 06:02:41,931][05219] Updated weights for policy 1, policy_version 82400 (0.0007) -[2023-10-16 06:02:42,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 169017344. Throughput: 0: 1803.2, 1: 1793.1. Samples: 42259152. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-16 06:02:42,351][03835] Avg episode reward: [(0, '7.150'), (1, '8.440')] -[2023-10-16 06:02:42,716][05218] Updated weights for policy 0, policy_version 82662 (0.0007) -[2023-10-16 06:02:43,088][05218] Updated weights for policy 0, policy_version 82672 (0.0007) -[2023-10-16 06:02:43,468][05218] Updated weights for policy 0, policy_version 82682 (0.0008) -[2023-10-16 06:02:45,670][05219] Updated weights for policy 1, policy_version 82410 (0.0008) -[2023-10-16 06:02:46,028][05219] Updated weights for policy 1, policy_version 82420 (0.0008) -[2023-10-16 06:02:46,397][05219] Updated weights for policy 1, policy_version 82430 (0.0009) -[2023-10-16 06:02:47,181][05218] Updated weights for policy 0, policy_version 82692 (0.0007) -[2023-10-16 06:02:47,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 169082880. Throughput: 0: 1802.0, 1: 1799.6. Samples: 42280524. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-16 06:02:47,351][03835] Avg episode reward: [(0, '6.950'), (1, '8.850')] -[2023-10-16 06:02:47,559][05218] Updated weights for policy 0, policy_version 82702 (0.0007) -[2023-10-16 06:02:47,937][05218] Updated weights for policy 0, policy_version 82712 (0.0007) -[2023-10-16 06:02:50,196][05219] Updated weights for policy 1, policy_version 82440 (0.0009) -[2023-10-16 06:02:50,560][05219] Updated weights for policy 1, policy_version 82450 (0.0007) -[2023-10-16 06:02:50,931][05219] Updated weights for policy 1, policy_version 82460 (0.0008) -[2023-10-16 06:02:51,563][05218] Updated weights for policy 0, policy_version 82722 (0.0008) -[2023-10-16 06:02:51,932][05218] Updated weights for policy 0, policy_version 82732 (0.0009) -[2023-10-16 06:02:52,314][05218] Updated weights for policy 0, policy_version 82742 (0.0009) -[2023-10-16 06:02:52,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 169148416. Throughput: 0: 1811.0, 1: 1787.2. Samples: 42301642. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-16 06:02:52,351][03835] Avg episode reward: [(0, '7.320'), (1, '8.260')] -[2023-10-16 06:02:52,694][05218] Updated weights for policy 0, policy_version 82752 (0.0009) -[2023-10-16 06:02:54,487][05219] Updated weights for policy 1, policy_version 82470 (0.0008) -[2023-10-16 06:02:54,855][05219] Updated weights for policy 1, policy_version 82480 (0.0007) -[2023-10-16 06:02:55,216][05219] Updated weights for policy 1, policy_version 82490 (0.0008) -[2023-10-16 06:02:56,353][05218] Updated weights for policy 0, policy_version 82762 (0.0009) -[2023-10-16 06:02:56,726][05218] Updated weights for policy 0, policy_version 82772 (0.0008) -[2023-10-16 06:02:57,104][05218] Updated weights for policy 0, policy_version 82782 (0.0009) -[2023-10-16 06:02:57,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 169246720. Throughput: 0: 1808.0, 1: 1796.5. Samples: 42313108. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-16 06:02:57,351][03835] Avg episode reward: [(0, '7.200'), (1, '7.120')] -[2023-10-16 06:02:58,881][05219] Updated weights for policy 1, policy_version 82500 (0.0008) -[2023-10-16 06:02:59,252][05219] Updated weights for policy 1, policy_version 82510 (0.0008) -[2023-10-16 06:02:59,624][05219] Updated weights for policy 1, policy_version 82520 (0.0007) -[2023-10-16 06:03:00,781][05218] Updated weights for policy 0, policy_version 82792 (0.0008) -[2023-10-16 06:03:01,154][05218] Updated weights for policy 0, policy_version 82802 (0.0007) -[2023-10-16 06:03:01,536][05218] Updated weights for policy 0, policy_version 82812 (0.0009) -[2023-10-16 06:03:02,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 169312256. Throughput: 0: 1817.7, 1: 1785.2. Samples: 42334200. Policy #0 lag: (min: 25.0, avg: 34.9, max: 57.0) -[2023-10-16 06:03:02,351][03835] Avg episode reward: [(0, '6.350'), (1, '7.740')] -[2023-10-16 06:03:03,303][05219] Updated weights for policy 1, policy_version 82530 (0.0008) -[2023-10-16 06:03:03,665][05219] Updated weights for policy 1, policy_version 82540 (0.0010) -[2023-10-16 06:03:04,029][05219] Updated weights for policy 1, policy_version 82550 (0.0011) -[2023-10-16 06:03:04,396][05219] Updated weights for policy 1, policy_version 82560 (0.0009) -[2023-10-16 06:03:05,317][05218] Updated weights for policy 0, policy_version 82822 (0.0009) -[2023-10-16 06:03:05,695][05218] Updated weights for policy 0, policy_version 82832 (0.0010) -[2023-10-16 06:03:06,065][05218] Updated weights for policy 0, policy_version 82842 (0.0007) -[2023-10-16 06:03:07,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 169377792. Throughput: 0: 1804.9, 1: 1784.6. Samples: 42356220. Policy #0 lag: (min: 25.0, avg: 34.9, max: 57.0) -[2023-10-16 06:03:07,351][03835] Avg episode reward: [(0, '7.170'), (1, '7.700')] -[2023-10-16 06:03:08,285][05219] Updated weights for policy 1, policy_version 82570 (0.0009) -[2023-10-16 06:03:08,655][05219] Updated weights for policy 1, policy_version 82580 (0.0010) -[2023-10-16 06:03:09,017][05219] Updated weights for policy 1, policy_version 82590 (0.0008) -[2023-10-16 06:03:09,866][05218] Updated weights for policy 0, policy_version 82852 (0.0009) -[2023-10-16 06:03:10,240][05218] Updated weights for policy 0, policy_version 82862 (0.0009) -[2023-10-16 06:03:10,617][05218] Updated weights for policy 0, policy_version 82872 (0.0008) -[2023-10-16 06:03:12,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 169443328. Throughput: 0: 1812.7, 1: 1784.1. Samples: 42366374. Policy #0 lag: (min: 25.0, avg: 34.9, max: 57.0) -[2023-10-16 06:03:12,351][03835] Avg episode reward: [(0, '7.560'), (1, '8.040')] -[2023-10-16 06:03:12,872][05219] Updated weights for policy 1, policy_version 82600 (0.0010) -[2023-10-16 06:03:13,246][05219] Updated weights for policy 1, policy_version 82610 (0.0010) -[2023-10-16 06:03:13,599][05219] Updated weights for policy 1, policy_version 82620 (0.0010) -[2023-10-16 06:03:14,203][05218] Updated weights for policy 0, policy_version 82882 (0.0009) -[2023-10-16 06:03:14,577][05218] Updated weights for policy 0, policy_version 82892 (0.0009) -[2023-10-16 06:03:14,952][05218] Updated weights for policy 0, policy_version 82902 (0.0008) -[2023-10-16 06:03:15,325][05218] Updated weights for policy 0, policy_version 82912 (0.0007) -[2023-10-16 06:03:17,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 169508864. Throughput: 0: 1802.6, 1: 1785.0. Samples: 42388174. Policy #0 lag: (min: 25.0, avg: 34.9, max: 57.0) -[2023-10-16 06:03:17,351][03835] Avg episode reward: [(0, '6.870'), (1, '8.150')] -[2023-10-16 06:03:17,521][05219] Updated weights for policy 1, policy_version 82630 (0.0008) -[2023-10-16 06:03:17,892][05219] Updated weights for policy 1, policy_version 82640 (0.0009) -[2023-10-16 06:03:18,255][05219] Updated weights for policy 1, policy_version 82650 (0.0008) -[2023-10-16 06:03:19,114][05218] Updated weights for policy 0, policy_version 82922 (0.0008) -[2023-10-16 06:03:19,486][05218] Updated weights for policy 0, policy_version 82932 (0.0007) -[2023-10-16 06:03:19,861][05218] Updated weights for policy 0, policy_version 82942 (0.0010) -[2023-10-16 06:03:22,015][05219] Updated weights for policy 1, policy_version 82660 (0.0009) -[2023-10-16 06:03:22,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 169574400. Throughput: 0: 1794.0, 1: 1807.7. Samples: 42410412. Policy #0 lag: (min: 25.0, avg: 34.9, max: 57.0) -[2023-10-16 06:03:22,351][03835] Avg episode reward: [(0, '7.580'), (1, '8.140')] -[2023-10-16 06:03:22,374][05219] Updated weights for policy 1, policy_version 82670 (0.0008) -[2023-10-16 06:03:22,742][05219] Updated weights for policy 1, policy_version 82680 (0.0007) -[2023-10-16 06:03:23,538][05218] Updated weights for policy 0, policy_version 82952 (0.0008) -[2023-10-16 06:03:23,912][05218] Updated weights for policy 0, policy_version 82962 (0.0009) -[2023-10-16 06:03:24,290][05218] Updated weights for policy 0, policy_version 82972 (0.0010) -[2023-10-16 06:03:26,272][05219] Updated weights for policy 1, policy_version 82690 (0.0009) -[2023-10-16 06:03:26,638][05219] Updated weights for policy 1, policy_version 82700 (0.0007) -[2023-10-16 06:03:26,999][05219] Updated weights for policy 1, policy_version 82710 (0.0007) -[2023-10-16 06:03:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 169639936. Throughput: 0: 1794.8, 1: 1790.8. Samples: 42420506. Policy #0 lag: (min: 25.0, avg: 34.9, max: 57.0) -[2023-10-16 06:03:27,351][03835] Avg episode reward: [(0, '6.770'), (1, '8.920')] -[2023-10-16 06:03:27,359][05219] Updated weights for policy 1, policy_version 82720 (0.0007) -[2023-10-16 06:03:28,328][05218] Updated weights for policy 0, policy_version 82982 (0.0010) -[2023-10-16 06:03:28,700][05218] Updated weights for policy 0, policy_version 82992 (0.0011) -[2023-10-16 06:03:29,080][05218] Updated weights for policy 0, policy_version 83002 (0.0009) -[2023-10-16 06:03:31,192][05219] Updated weights for policy 1, policy_version 82730 (0.0009) -[2023-10-16 06:03:31,558][05219] Updated weights for policy 1, policy_version 82740 (0.0007) -[2023-10-16 06:03:31,924][05219] Updated weights for policy 1, policy_version 82750 (0.0008) -[2023-10-16 06:03:32,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 169738240. Throughput: 0: 1796.0, 1: 1805.2. Samples: 42442578. Policy #0 lag: (min: 25.0, avg: 34.9, max: 57.0) -[2023-10-16 06:03:32,351][03835] Avg episode reward: [(0, '6.370'), (1, '8.160')] -[2023-10-16 06:03:32,730][05218] Updated weights for policy 0, policy_version 83012 (0.0011) -[2023-10-16 06:03:33,109][05218] Updated weights for policy 0, policy_version 83022 (0.0007) -[2023-10-16 06:03:33,488][05218] Updated weights for policy 0, policy_version 83032 (0.0010) -[2023-10-16 06:03:35,796][05219] Updated weights for policy 1, policy_version 82760 (0.0008) -[2023-10-16 06:03:36,171][05219] Updated weights for policy 1, policy_version 82770 (0.0011) -[2023-10-16 06:03:36,539][05219] Updated weights for policy 1, policy_version 82780 (0.0010) -[2023-10-16 06:03:37,005][05218] Updated weights for policy 0, policy_version 83042 (0.0010) -[2023-10-16 06:03:37,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 169803776. Throughput: 0: 1807.3, 1: 1794.9. Samples: 42463742. Policy #0 lag: (min: 25.0, avg: 34.9, max: 57.0) -[2023-10-16 06:03:37,351][03835] Avg episode reward: [(0, '6.720'), (1, '7.950')] -[2023-10-16 06:03:37,359][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000082784_84770816.pth... -[2023-10-16 06:03:37,387][05218] Updated weights for policy 0, policy_version 83052 (0.0008) -[2023-10-16 06:03:37,395][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000081088_83034112.pth -[2023-10-16 06:03:37,763][05218] Updated weights for policy 0, policy_version 83062 (0.0007) -[2023-10-16 06:03:38,129][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000083072_85065728.pth... -[2023-10-16 06:03:38,130][05218] Updated weights for policy 0, policy_version 83072 (0.0007) -[2023-10-16 06:03:38,158][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000081376_83329024.pth -[2023-10-16 06:03:40,339][05219] Updated weights for policy 1, policy_version 82790 (0.0010) -[2023-10-16 06:03:40,703][05219] Updated weights for policy 1, policy_version 82800 (0.0009) -[2023-10-16 06:03:41,056][05219] Updated weights for policy 1, policy_version 82810 (0.0007) -[2023-10-16 06:03:41,908][05218] Updated weights for policy 0, policy_version 83082 (0.0008) -[2023-10-16 06:03:42,281][05218] Updated weights for policy 0, policy_version 83092 (0.0007) -[2023-10-16 06:03:42,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 169869312. Throughput: 0: 1792.6, 1: 1814.0. Samples: 42475406. Policy #0 lag: (min: 25.0, avg: 34.9, max: 57.0) -[2023-10-16 06:03:42,351][03835] Avg episode reward: [(0, '7.030'), (1, '7.840')] -[2023-10-16 06:03:42,661][05218] Updated weights for policy 0, policy_version 83102 (0.0007) -[2023-10-16 06:03:44,707][05219] Updated weights for policy 1, policy_version 82820 (0.0010) -[2023-10-16 06:03:45,076][05219] Updated weights for policy 1, policy_version 82830 (0.0011) -[2023-10-16 06:03:45,431][05219] Updated weights for policy 1, policy_version 82840 (0.0011) -[2023-10-16 06:03:46,493][05218] Updated weights for policy 0, policy_version 83112 (0.0008) -[2023-10-16 06:03:46,863][05218] Updated weights for policy 0, policy_version 83122 (0.0007) -[2023-10-16 06:03:47,245][05218] Updated weights for policy 0, policy_version 83132 (0.0007) -[2023-10-16 06:03:47,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 169934848. Throughput: 0: 1805.3, 1: 1785.5. Samples: 42495788. Policy #0 lag: (min: 25.0, avg: 34.9, max: 57.0) -[2023-10-16 06:03:47,351][03835] Avg episode reward: [(0, '6.820'), (1, '7.870')] -[2023-10-16 06:03:49,231][05219] Updated weights for policy 1, policy_version 82850 (0.0009) -[2023-10-16 06:03:49,586][05219] Updated weights for policy 1, policy_version 82860 (0.0007) -[2023-10-16 06:03:49,958][05219] Updated weights for policy 1, policy_version 82870 (0.0009) -[2023-10-16 06:03:50,327][05219] Updated weights for policy 1, policy_version 82880 (0.0008) -[2023-10-16 06:03:51,030][05218] Updated weights for policy 0, policy_version 83142 (0.0008) -[2023-10-16 06:03:51,406][05218] Updated weights for policy 0, policy_version 83152 (0.0007) -[2023-10-16 06:03:51,770][05218] Updated weights for policy 0, policy_version 83162 (0.0010) -[2023-10-16 06:03:52,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 170033152. Throughput: 0: 1790.2, 1: 1784.2. Samples: 42517066. Policy #0 lag: (min: 25.0, avg: 34.9, max: 57.0) -[2023-10-16 06:03:52,351][03835] Avg episode reward: [(0, '6.840'), (1, '8.290')] -[2023-10-16 06:03:54,324][05219] Updated weights for policy 1, policy_version 82890 (0.0010) -[2023-10-16 06:03:54,687][05219] Updated weights for policy 1, policy_version 82900 (0.0008) -[2023-10-16 06:03:55,061][05219] Updated weights for policy 1, policy_version 82910 (0.0009) -[2023-10-16 06:03:55,517][05218] Updated weights for policy 0, policy_version 83172 (0.0008) -[2023-10-16 06:03:55,909][05218] Updated weights for policy 0, policy_version 83182 (0.0008) -[2023-10-16 06:03:56,274][05218] Updated weights for policy 0, policy_version 83192 (0.0008) -[2023-10-16 06:03:57,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 170098688. Throughput: 0: 1808.8, 1: 1787.9. Samples: 42528226. Policy #0 lag: (min: 11.0, avg: 18.3, max: 43.0) -[2023-10-16 06:03:57,351][03835] Avg episode reward: [(0, '7.080'), (1, '8.630')] -[2023-10-16 06:03:58,693][05219] Updated weights for policy 1, policy_version 82920 (0.0009) -[2023-10-16 06:03:59,059][05219] Updated weights for policy 1, policy_version 82930 (0.0009) -[2023-10-16 06:03:59,434][05219] Updated weights for policy 1, policy_version 82940 (0.0010) -[2023-10-16 06:03:59,884][05218] Updated weights for policy 0, policy_version 83202 (0.0008) -[2023-10-16 06:04:00,261][05218] Updated weights for policy 0, policy_version 83212 (0.0011) -[2023-10-16 06:04:00,635][05218] Updated weights for policy 0, policy_version 83222 (0.0011) -[2023-10-16 06:04:01,006][05218] Updated weights for policy 0, policy_version 83232 (0.0010) -[2023-10-16 06:04:02,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 170164224. Throughput: 0: 1788.9, 1: 1785.0. Samples: 42549000. Policy #0 lag: (min: 11.0, avg: 18.3, max: 43.0) -[2023-10-16 06:04:02,352][03835] Avg episode reward: [(0, '7.310'), (1, '8.200')] -[2023-10-16 06:04:03,159][05219] Updated weights for policy 1, policy_version 82950 (0.0009) -[2023-10-16 06:04:03,522][05219] Updated weights for policy 1, policy_version 82960 (0.0007) -[2023-10-16 06:04:03,893][05219] Updated weights for policy 1, policy_version 82970 (0.0007) -[2023-10-16 06:04:04,825][05218] Updated weights for policy 0, policy_version 83242 (0.0010) -[2023-10-16 06:04:05,198][05218] Updated weights for policy 0, policy_version 83252 (0.0009) -[2023-10-16 06:04:05,581][05218] Updated weights for policy 0, policy_version 83262 (0.0009) -[2023-10-16 06:04:07,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 170229760. Throughput: 0: 1784.7, 1: 1790.0. Samples: 42571272. Policy #0 lag: (min: 11.0, avg: 18.3, max: 43.0) -[2023-10-16 06:04:07,351][03835] Avg episode reward: [(0, '7.750'), (1, '8.330')] -[2023-10-16 06:04:07,590][05219] Updated weights for policy 1, policy_version 82980 (0.0008) -[2023-10-16 06:04:07,955][05219] Updated weights for policy 1, policy_version 82990 (0.0010) -[2023-10-16 06:04:08,321][05219] Updated weights for policy 1, policy_version 83000 (0.0009) -[2023-10-16 06:04:09,241][05218] Updated weights for policy 0, policy_version 83272 (0.0008) -[2023-10-16 06:04:09,624][05218] Updated weights for policy 0, policy_version 83282 (0.0007) -[2023-10-16 06:04:09,992][05218] Updated weights for policy 0, policy_version 83292 (0.0009) -[2023-10-16 06:04:12,175][05219] Updated weights for policy 1, policy_version 83010 (0.0007) -[2023-10-16 06:04:12,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 170295296. Throughput: 0: 1787.5, 1: 1783.4. Samples: 42581196. Policy #0 lag: (min: 11.0, avg: 18.3, max: 43.0) -[2023-10-16 06:04:12,351][03835] Avg episode reward: [(0, '7.270'), (1, '8.530')] -[2023-10-16 06:04:12,530][05219] Updated weights for policy 1, policy_version 83020 (0.0009) -[2023-10-16 06:04:12,904][05219] Updated weights for policy 1, policy_version 83030 (0.0012) -[2023-10-16 06:04:13,265][05219] Updated weights for policy 1, policy_version 83040 (0.0009) -[2023-10-16 06:04:13,814][05218] Updated weights for policy 0, policy_version 83302 (0.0010) -[2023-10-16 06:04:14,196][05218] Updated weights for policy 0, policy_version 83312 (0.0009) -[2023-10-16 06:04:14,563][05218] Updated weights for policy 0, policy_version 83322 (0.0007) -[2023-10-16 06:04:17,088][05219] Updated weights for policy 1, policy_version 83050 (0.0008) -[2023-10-16 06:04:17,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 170360832. Throughput: 0: 1786.9, 1: 1785.4. Samples: 42603332. Policy #0 lag: (min: 11.0, avg: 18.3, max: 43.0) -[2023-10-16 06:04:17,351][03835] Avg episode reward: [(0, '7.220'), (1, '8.700')] -[2023-10-16 06:04:17,455][05219] Updated weights for policy 1, policy_version 83060 (0.0009) -[2023-10-16 06:04:17,824][05219] Updated weights for policy 1, policy_version 83070 (0.0008) -[2023-10-16 06:04:18,201][05218] Updated weights for policy 0, policy_version 83332 (0.0009) -[2023-10-16 06:04:18,581][05218] Updated weights for policy 0, policy_version 83342 (0.0009) -[2023-10-16 06:04:18,964][05218] Updated weights for policy 0, policy_version 83352 (0.0009) -[2023-10-16 06:04:21,579][05219] Updated weights for policy 1, policy_version 83080 (0.0008) -[2023-10-16 06:04:21,947][05219] Updated weights for policy 1, policy_version 83090 (0.0011) -[2023-10-16 06:04:22,318][05219] Updated weights for policy 1, policy_version 83100 (0.0011) -[2023-10-16 06:04:22,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 170426368. Throughput: 0: 1798.8, 1: 1782.2. Samples: 42624888. Policy #0 lag: (min: 11.0, avg: 18.3, max: 43.0) -[2023-10-16 06:04:22,351][03835] Avg episode reward: [(0, '7.040'), (1, '8.070')] -[2023-10-16 06:04:22,700][05218] Updated weights for policy 0, policy_version 83362 (0.0010) -[2023-10-16 06:04:23,073][05218] Updated weights for policy 0, policy_version 83372 (0.0008) -[2023-10-16 06:04:23,445][05218] Updated weights for policy 0, policy_version 83382 (0.0009) -[2023-10-16 06:04:23,818][05218] Updated weights for policy 0, policy_version 83392 (0.0009) -[2023-10-16 06:04:26,172][05219] Updated weights for policy 1, policy_version 83110 (0.0009) -[2023-10-16 06:04:26,531][05219] Updated weights for policy 1, policy_version 83120 (0.0009) -[2023-10-16 06:04:26,908][05219] Updated weights for policy 1, policy_version 83130 (0.0010) -[2023-10-16 06:04:27,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 170524672. Throughput: 0: 1787.7, 1: 1773.1. Samples: 42635642. Policy #0 lag: (min: 11.0, avg: 18.3, max: 43.0) -[2023-10-16 06:04:27,351][03835] Avg episode reward: [(0, '6.460'), (1, '8.010')] -[2023-10-16 06:04:27,557][05218] Updated weights for policy 0, policy_version 83402 (0.0008) -[2023-10-16 06:04:27,925][05218] Updated weights for policy 0, policy_version 83412 (0.0008) -[2023-10-16 06:04:28,307][05218] Updated weights for policy 0, policy_version 83422 (0.0009) -[2023-10-16 06:04:30,552][05219] Updated weights for policy 1, policy_version 83140 (0.0009) -[2023-10-16 06:04:30,911][05219] Updated weights for policy 1, policy_version 83150 (0.0007) -[2023-10-16 06:04:31,276][05219] Updated weights for policy 1, policy_version 83160 (0.0010) -[2023-10-16 06:04:31,887][05218] Updated weights for policy 0, policy_version 83432 (0.0007) -[2023-10-16 06:04:32,252][05218] Updated weights for policy 0, policy_version 83442 (0.0007) -[2023-10-16 06:04:32,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 170590208. Throughput: 0: 1803.1, 1: 1792.7. Samples: 42657600. Policy #0 lag: (min: 11.0, avg: 18.3, max: 43.0) -[2023-10-16 06:04:32,351][03835] Avg episode reward: [(0, '7.310'), (1, '7.670')] -[2023-10-16 06:04:32,635][05218] Updated weights for policy 0, policy_version 83452 (0.0007) -[2023-10-16 06:04:35,011][05219] Updated weights for policy 1, policy_version 83170 (0.0009) -[2023-10-16 06:04:35,380][05219] Updated weights for policy 1, policy_version 83180 (0.0007) -[2023-10-16 06:04:35,739][05219] Updated weights for policy 1, policy_version 83190 (0.0007) -[2023-10-16 06:04:36,104][05219] Updated weights for policy 1, policy_version 83200 (0.0007) -[2023-10-16 06:04:36,523][05218] Updated weights for policy 0, policy_version 83462 (0.0008) -[2023-10-16 06:04:36,909][05218] Updated weights for policy 0, policy_version 83472 (0.0010) -[2023-10-16 06:04:37,278][05218] Updated weights for policy 0, policy_version 83482 (0.0007) -[2023-10-16 06:04:37,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 170655744. Throughput: 0: 1802.0, 1: 1784.3. Samples: 42678452. Policy #0 lag: (min: 11.0, avg: 18.3, max: 43.0) -[2023-10-16 06:04:37,351][03835] Avg episode reward: [(0, '7.570'), (1, '8.290')] -[2023-10-16 06:04:39,871][05219] Updated weights for policy 1, policy_version 83210 (0.0007) -[2023-10-16 06:04:40,237][05219] Updated weights for policy 1, policy_version 83220 (0.0008) -[2023-10-16 06:04:40,598][05219] Updated weights for policy 1, policy_version 83230 (0.0008) -[2023-10-16 06:04:41,191][05218] Updated weights for policy 0, policy_version 83492 (0.0008) -[2023-10-16 06:04:41,565][05218] Updated weights for policy 0, policy_version 83502 (0.0009) -[2023-10-16 06:04:41,946][05218] Updated weights for policy 0, policy_version 83512 (0.0008) -[2023-10-16 06:04:42,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 170754048. Throughput: 0: 1795.4, 1: 1798.5. Samples: 42689948. Policy #0 lag: (min: 11.0, avg: 18.3, max: 43.0) -[2023-10-16 06:04:42,351][03835] Avg episode reward: [(0, '7.060'), (1, '8.810')] -[2023-10-16 06:04:44,306][05219] Updated weights for policy 1, policy_version 83240 (0.0010) -[2023-10-16 06:04:44,670][05219] Updated weights for policy 1, policy_version 83250 (0.0009) -[2023-10-16 06:04:45,040][05219] Updated weights for policy 1, policy_version 83260 (0.0009) -[2023-10-16 06:04:45,706][05218] Updated weights for policy 0, policy_version 83522 (0.0008) -[2023-10-16 06:04:46,083][05218] Updated weights for policy 0, policy_version 83532 (0.0007) -[2023-10-16 06:04:46,469][05218] Updated weights for policy 0, policy_version 83542 (0.0007) -[2023-10-16 06:04:46,843][05218] Updated weights for policy 0, policy_version 83552 (0.0008) -[2023-10-16 06:04:47,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.7, 300 sec: 14440.2). Total num frames: 170819584. Throughput: 0: 1808.0, 1: 1783.7. Samples: 42710624. Policy #0 lag: (min: 11.0, avg: 18.3, max: 43.0) -[2023-10-16 06:04:47,351][03835] Avg episode reward: [(0, '7.870'), (1, '8.340')] -[2023-10-16 06:04:48,858][05219] Updated weights for policy 1, policy_version 83270 (0.0007) -[2023-10-16 06:04:49,231][05219] Updated weights for policy 1, policy_version 83280 (0.0008) -[2023-10-16 06:04:49,603][05219] Updated weights for policy 1, policy_version 83290 (0.0007) -[2023-10-16 06:04:50,622][05218] Updated weights for policy 0, policy_version 83562 (0.0008) -[2023-10-16 06:04:51,004][05218] Updated weights for policy 0, policy_version 83572 (0.0010) -[2023-10-16 06:04:51,380][05218] Updated weights for policy 0, policy_version 83582 (0.0010) -[2023-10-16 06:04:52,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 170885120. Throughput: 0: 1800.8, 1: 1785.1. Samples: 42732638. Policy #0 lag: (min: 27.0, avg: 35.8, max: 59.0) -[2023-10-16 06:04:52,351][03835] Avg episode reward: [(0, '6.840'), (1, '9.400')] -[2023-10-16 06:04:53,423][05219] Updated weights for policy 1, policy_version 83300 (0.0007) -[2023-10-16 06:04:53,791][05219] Updated weights for policy 1, policy_version 83310 (0.0007) -[2023-10-16 06:04:54,143][05219] Updated weights for policy 1, policy_version 83320 (0.0007) -[2023-10-16 06:04:54,977][05218] Updated weights for policy 0, policy_version 83592 (0.0010) -[2023-10-16 06:04:55,357][05218] Updated weights for policy 0, policy_version 83602 (0.0010) -[2023-10-16 06:04:55,739][05218] Updated weights for policy 0, policy_version 83612 (0.0008) -[2023-10-16 06:04:57,351][03835] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 170950656. Throughput: 0: 1815.1, 1: 1784.5. Samples: 42743180. Policy #0 lag: (min: 27.0, avg: 35.8, max: 59.0) -[2023-10-16 06:04:57,352][03835] Avg episode reward: [(0, '6.890'), (1, '8.730')] -[2023-10-16 06:04:57,851][05219] Updated weights for policy 1, policy_version 83330 (0.0007) -[2023-10-16 06:04:58,222][05219] Updated weights for policy 1, policy_version 83340 (0.0008) -[2023-10-16 06:04:58,587][05219] Updated weights for policy 1, policy_version 83350 (0.0008) -[2023-10-16 06:04:58,940][05219] Updated weights for policy 1, policy_version 83360 (0.0009) -[2023-10-16 06:04:59,308][05218] Updated weights for policy 0, policy_version 83622 (0.0008) -[2023-10-16 06:04:59,688][05218] Updated weights for policy 0, policy_version 83632 (0.0007) -[2023-10-16 06:05:00,072][05218] Updated weights for policy 0, policy_version 83642 (0.0009) -[2023-10-16 06:05:02,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 171016192. Throughput: 0: 1799.8, 1: 1796.0. Samples: 42765140. Policy #0 lag: (min: 27.0, avg: 35.8, max: 59.0) -[2023-10-16 06:05:02,351][03835] Avg episode reward: [(0, '7.100'), (1, '7.760')] -[2023-10-16 06:05:02,587][05219] Updated weights for policy 1, policy_version 83370 (0.0009) -[2023-10-16 06:05:02,960][05219] Updated weights for policy 1, policy_version 83380 (0.0007) -[2023-10-16 06:05:03,330][05219] Updated weights for policy 1, policy_version 83390 (0.0009) -[2023-10-16 06:05:03,680][05218] Updated weights for policy 0, policy_version 83652 (0.0009) -[2023-10-16 06:05:04,043][05218] Updated weights for policy 0, policy_version 83662 (0.0008) -[2023-10-16 06:05:04,423][05218] Updated weights for policy 0, policy_version 83672 (0.0009) -[2023-10-16 06:05:07,137][05219] Updated weights for policy 1, policy_version 83400 (0.0008) -[2023-10-16 06:05:07,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 171081728. Throughput: 0: 1799.9, 1: 1810.6. Samples: 42787360. Policy #0 lag: (min: 27.0, avg: 35.8, max: 59.0) -[2023-10-16 06:05:07,352][03835] Avg episode reward: [(0, '6.860'), (1, '8.840')] -[2023-10-16 06:05:07,501][05219] Updated weights for policy 1, policy_version 83410 (0.0008) -[2023-10-16 06:05:07,873][05219] Updated weights for policy 1, policy_version 83420 (0.0010) -[2023-10-16 06:05:08,098][05218] Updated weights for policy 0, policy_version 83682 (0.0009) -[2023-10-16 06:05:08,474][05218] Updated weights for policy 0, policy_version 83692 (0.0008) -[2023-10-16 06:05:08,844][05218] Updated weights for policy 0, policy_version 83702 (0.0010) -[2023-10-16 06:05:09,218][05218] Updated weights for policy 0, policy_version 83712 (0.0009) -[2023-10-16 06:05:11,432][05219] Updated weights for policy 1, policy_version 83430 (0.0007) -[2023-10-16 06:05:11,791][05219] Updated weights for policy 1, policy_version 83440 (0.0008) -[2023-10-16 06:05:12,151][05219] Updated weights for policy 1, policy_version 83450 (0.0010) -[2023-10-16 06:05:12,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 171147264. Throughput: 0: 1799.9, 1: 1800.3. Samples: 42797650. Policy #0 lag: (min: 27.0, avg: 35.8, max: 59.0) -[2023-10-16 06:05:12,351][03835] Avg episode reward: [(0, '7.140'), (1, '8.460')] -[2023-10-16 06:05:13,007][05218] Updated weights for policy 0, policy_version 83722 (0.0007) -[2023-10-16 06:05:13,385][05218] Updated weights for policy 0, policy_version 83732 (0.0009) -[2023-10-16 06:05:13,767][05218] Updated weights for policy 0, policy_version 83742 (0.0010) -[2023-10-16 06:05:15,984][05219] Updated weights for policy 1, policy_version 83460 (0.0010) -[2023-10-16 06:05:16,346][05219] Updated weights for policy 1, policy_version 83470 (0.0010) -[2023-10-16 06:05:16,703][05219] Updated weights for policy 1, policy_version 83480 (0.0010) -[2023-10-16 06:05:17,350][03835] Fps is (10 sec: 16384.6, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 171245568. Throughput: 0: 1791.3, 1: 1812.3. Samples: 42819764. Policy #0 lag: (min: 27.0, avg: 35.8, max: 59.0) -[2023-10-16 06:05:17,351][03835] Avg episode reward: [(0, '6.680'), (1, '8.510')] -[2023-10-16 06:05:17,527][05218] Updated weights for policy 0, policy_version 83752 (0.0007) -[2023-10-16 06:05:17,901][05218] Updated weights for policy 0, policy_version 83762 (0.0009) -[2023-10-16 06:05:18,277][05218] Updated weights for policy 0, policy_version 83772 (0.0011) -[2023-10-16 06:05:20,438][05219] Updated weights for policy 1, policy_version 83490 (0.0010) -[2023-10-16 06:05:20,799][05219] Updated weights for policy 1, policy_version 83500 (0.0009) -[2023-10-16 06:05:21,171][05219] Updated weights for policy 1, policy_version 83510 (0.0009) -[2023-10-16 06:05:21,533][05219] Updated weights for policy 1, policy_version 83520 (0.0008) -[2023-10-16 06:05:22,116][05218] Updated weights for policy 0, policy_version 83782 (0.0009) -[2023-10-16 06:05:22,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 171311104. Throughput: 0: 1804.4, 1: 1798.5. Samples: 42840582. Policy #0 lag: (min: 27.0, avg: 35.8, max: 59.0) -[2023-10-16 06:05:22,351][03835] Avg episode reward: [(0, '6.830'), (1, '7.940')] -[2023-10-16 06:05:22,481][05218] Updated weights for policy 0, policy_version 83792 (0.0007) -[2023-10-16 06:05:22,862][05218] Updated weights for policy 0, policy_version 83802 (0.0008) -[2023-10-16 06:05:25,372][05219] Updated weights for policy 1, policy_version 83530 (0.0010) -[2023-10-16 06:05:25,745][05219] Updated weights for policy 1, policy_version 83540 (0.0009) -[2023-10-16 06:05:26,111][05219] Updated weights for policy 1, policy_version 83550 (0.0009) -[2023-10-16 06:05:26,678][05218] Updated weights for policy 0, policy_version 83812 (0.0008) -[2023-10-16 06:05:27,054][05218] Updated weights for policy 0, policy_version 83822 (0.0008) -[2023-10-16 06:05:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 171376640. Throughput: 0: 1790.3, 1: 1814.8. Samples: 42852174. Policy #0 lag: (min: 27.0, avg: 35.8, max: 59.0) -[2023-10-16 06:05:27,351][03835] Avg episode reward: [(0, '7.130'), (1, '8.990')] -[2023-10-16 06:05:27,420][05218] Updated weights for policy 0, policy_version 83832 (0.0007) -[2023-10-16 06:05:29,741][05219] Updated weights for policy 1, policy_version 83560 (0.0007) -[2023-10-16 06:05:30,111][05219] Updated weights for policy 1, policy_version 83570 (0.0009) -[2023-10-16 06:05:30,476][05219] Updated weights for policy 1, policy_version 83580 (0.0008) -[2023-10-16 06:05:31,165][05218] Updated weights for policy 0, policy_version 83842 (0.0008) -[2023-10-16 06:05:31,546][05218] Updated weights for policy 0, policy_version 83852 (0.0009) -[2023-10-16 06:05:31,922][05218] Updated weights for policy 0, policy_version 83862 (0.0010) -[2023-10-16 06:05:32,306][05218] Updated weights for policy 0, policy_version 83872 (0.0009) -[2023-10-16 06:05:32,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.2). Total num frames: 171474944. Throughput: 0: 1804.2, 1: 1804.4. Samples: 42873014. Policy #0 lag: (min: 27.0, avg: 35.8, max: 59.0) -[2023-10-16 06:05:32,351][03835] Avg episode reward: [(0, '7.230'), (1, '8.250')] -[2023-10-16 06:05:34,164][05219] Updated weights for policy 1, policy_version 83590 (0.0011) -[2023-10-16 06:05:34,534][05219] Updated weights for policy 1, policy_version 83600 (0.0008) -[2023-10-16 06:05:34,897][05219] Updated weights for policy 1, policy_version 83610 (0.0007) -[2023-10-16 06:05:36,227][05218] Updated weights for policy 0, policy_version 83882 (0.0010) -[2023-10-16 06:05:36,598][05218] Updated weights for policy 0, policy_version 83892 (0.0008) -[2023-10-16 06:05:36,977][05218] Updated weights for policy 0, policy_version 83902 (0.0008) -[2023-10-16 06:05:37,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 171540480. Throughput: 0: 1782.5, 1: 1806.1. Samples: 42894126. Policy #0 lag: (min: 27.0, avg: 35.8, max: 59.0) -[2023-10-16 06:05:37,351][03835] Avg episode reward: [(0, '7.120'), (1, '8.190')] -[2023-10-16 06:05:37,361][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000083616_85622784.pth... -[2023-10-16 06:05:37,362][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000083904_85917696.pth... -[2023-10-16 06:05:37,400][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000081952_83918848.pth -[2023-10-16 06:05:37,403][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000082208_84180992.pth -[2023-10-16 06:05:37,406][04891] Saving a milestone ./train_atari/atari_timepilot_APPO/checkpoint_p1/milestones/checkpoint_000083616_85622784.pth -[2023-10-16 06:05:37,408][04766] Saving a milestone ./train_atari/atari_timepilot_APPO/checkpoint_p0/milestones/checkpoint_000083904_85917696.pth -[2023-10-16 06:05:38,735][05219] Updated weights for policy 1, policy_version 83620 (0.0007) -[2023-10-16 06:05:39,105][05219] Updated weights for policy 1, policy_version 83630 (0.0009) -[2023-10-16 06:05:39,465][05219] Updated weights for policy 1, policy_version 83640 (0.0008) -[2023-10-16 06:05:40,644][05218] Updated weights for policy 0, policy_version 83912 (0.0008) -[2023-10-16 06:05:41,016][05218] Updated weights for policy 0, policy_version 83922 (0.0009) -[2023-10-16 06:05:41,389][05218] Updated weights for policy 0, policy_version 83932 (0.0008) -[2023-10-16 06:05:42,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 171606016. Throughput: 0: 1802.1, 1: 1806.6. Samples: 42905570. Policy #0 lag: (min: 27.0, avg: 35.8, max: 59.0) -[2023-10-16 06:05:42,351][03835] Avg episode reward: [(0, '7.810'), (1, '8.870')] -[2023-10-16 06:05:43,220][05219] Updated weights for policy 1, policy_version 83650 (0.0008) -[2023-10-16 06:05:43,588][05219] Updated weights for policy 1, policy_version 83660 (0.0007) -[2023-10-16 06:05:43,955][05219] Updated weights for policy 1, policy_version 83670 (0.0009) -[2023-10-16 06:05:44,318][05219] Updated weights for policy 1, policy_version 83680 (0.0007) -[2023-10-16 06:05:45,320][05218] Updated weights for policy 0, policy_version 83942 (0.0007) -[2023-10-16 06:05:45,701][05218] Updated weights for policy 0, policy_version 83952 (0.0009) -[2023-10-16 06:05:46,071][05218] Updated weights for policy 0, policy_version 83962 (0.0010) -[2023-10-16 06:05:47,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 171671552. Throughput: 0: 1784.2, 1: 1802.7. Samples: 42926550. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:05:47,352][03835] Avg episode reward: [(0, '6.740'), (1, '7.960')] -[2023-10-16 06:05:47,995][05219] Updated weights for policy 1, policy_version 83690 (0.0008) -[2023-10-16 06:05:48,375][05219] Updated weights for policy 1, policy_version 83700 (0.0008) -[2023-10-16 06:05:48,734][05219] Updated weights for policy 1, policy_version 83710 (0.0009) -[2023-10-16 06:05:49,830][05218] Updated weights for policy 0, policy_version 83972 (0.0007) -[2023-10-16 06:05:50,206][05218] Updated weights for policy 0, policy_version 83982 (0.0008) -[2023-10-16 06:05:50,582][05218] Updated weights for policy 0, policy_version 83992 (0.0008) -[2023-10-16 06:05:52,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 171737088. Throughput: 0: 1775.5, 1: 1813.8. Samples: 42948878. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:05:52,351][03835] Avg episode reward: [(0, '7.230'), (1, '7.220')] -[2023-10-16 06:05:52,487][05219] Updated weights for policy 1, policy_version 83720 (0.0008) -[2023-10-16 06:05:52,851][05219] Updated weights for policy 1, policy_version 83730 (0.0007) -[2023-10-16 06:05:53,211][05219] Updated weights for policy 1, policy_version 83740 (0.0007) -[2023-10-16 06:05:54,125][05218] Updated weights for policy 0, policy_version 84002 (0.0009) -[2023-10-16 06:05:54,500][05218] Updated weights for policy 0, policy_version 84012 (0.0007) -[2023-10-16 06:05:54,881][05218] Updated weights for policy 0, policy_version 84022 (0.0007) -[2023-10-16 06:05:55,259][05218] Updated weights for policy 0, policy_version 84032 (0.0008) -[2023-10-16 06:05:57,102][05219] Updated weights for policy 1, policy_version 83750 (0.0007) -[2023-10-16 06:05:57,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 171802624. Throughput: 0: 1776.9, 1: 1804.5. Samples: 42958810. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:05:57,351][03835] Avg episode reward: [(0, '7.950'), (1, '7.850')] -[2023-10-16 06:05:57,479][05219] Updated weights for policy 1, policy_version 83760 (0.0007) -[2023-10-16 06:05:57,846][05219] Updated weights for policy 1, policy_version 83770 (0.0010) -[2023-10-16 06:05:58,902][05218] Updated weights for policy 0, policy_version 84042 (0.0008) -[2023-10-16 06:05:59,273][05218] Updated weights for policy 0, policy_version 84052 (0.0011) -[2023-10-16 06:05:59,641][05218] Updated weights for policy 0, policy_version 84062 (0.0011) -[2023-10-16 06:06:01,599][05219] Updated weights for policy 1, policy_version 83780 (0.0009) -[2023-10-16 06:06:01,962][05219] Updated weights for policy 1, policy_version 83790 (0.0008) -[2023-10-16 06:06:02,329][05219] Updated weights for policy 1, policy_version 83800 (0.0008) -[2023-10-16 06:06:02,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 171868160. Throughput: 0: 1780.8, 1: 1804.0. Samples: 42981078. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:06:02,351][03835] Avg episode reward: [(0, '7.550'), (1, '8.510')] -[2023-10-16 06:06:03,354][05218] Updated weights for policy 0, policy_version 84072 (0.0010) -[2023-10-16 06:06:03,723][05218] Updated weights for policy 0, policy_version 84082 (0.0009) -[2023-10-16 06:06:04,095][05218] Updated weights for policy 0, policy_version 84092 (0.0009) -[2023-10-16 06:06:05,957][05219] Updated weights for policy 1, policy_version 83810 (0.0009) -[2023-10-16 06:06:06,313][05219] Updated weights for policy 1, policy_version 83820 (0.0009) -[2023-10-16 06:06:06,688][05219] Updated weights for policy 1, policy_version 83830 (0.0007) -[2023-10-16 06:06:07,047][05219] Updated weights for policy 1, policy_version 83840 (0.0007) -[2023-10-16 06:06:07,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 171966464. Throughput: 0: 1799.1, 1: 1797.7. Samples: 43002438. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:06:07,351][03835] Avg episode reward: [(0, '7.430'), (1, '8.060')] -[2023-10-16 06:06:07,868][05218] Updated weights for policy 0, policy_version 84102 (0.0009) -[2023-10-16 06:06:08,248][05218] Updated weights for policy 0, policy_version 84112 (0.0008) -[2023-10-16 06:06:08,621][05218] Updated weights for policy 0, policy_version 84122 (0.0009) -[2023-10-16 06:06:10,826][05219] Updated weights for policy 1, policy_version 83850 (0.0008) -[2023-10-16 06:06:11,194][05219] Updated weights for policy 1, policy_version 83860 (0.0009) -[2023-10-16 06:06:11,559][05219] Updated weights for policy 1, policy_version 83870 (0.0010) -[2023-10-16 06:06:12,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 172032000. Throughput: 0: 1783.8, 1: 1807.3. Samples: 43013776. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:06:12,351][03835] Avg episode reward: [(0, '7.720'), (1, '8.480')] -[2023-10-16 06:06:12,568][05218] Updated weights for policy 0, policy_version 84132 (0.0008) -[2023-10-16 06:06:12,952][05218] Updated weights for policy 0, policy_version 84142 (0.0007) -[2023-10-16 06:06:13,326][05218] Updated weights for policy 0, policy_version 84152 (0.0009) -[2023-10-16 06:06:15,220][05219] Updated weights for policy 1, policy_version 83880 (0.0008) -[2023-10-16 06:06:15,581][05219] Updated weights for policy 1, policy_version 83890 (0.0008) -[2023-10-16 06:06:15,950][05219] Updated weights for policy 1, policy_version 83900 (0.0008) -[2023-10-16 06:06:17,115][05218] Updated weights for policy 0, policy_version 84162 (0.0008) -[2023-10-16 06:06:17,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 172097536. Throughput: 0: 1788.1, 1: 1799.7. Samples: 43034468. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:06:17,351][03835] Avg episode reward: [(0, '7.220'), (1, '8.380')] -[2023-10-16 06:06:17,488][05218] Updated weights for policy 0, policy_version 84172 (0.0007) -[2023-10-16 06:06:17,872][05218] Updated weights for policy 0, policy_version 84182 (0.0010) -[2023-10-16 06:06:18,249][05218] Updated weights for policy 0, policy_version 84192 (0.0010) -[2023-10-16 06:06:19,696][05219] Updated weights for policy 1, policy_version 83910 (0.0008) -[2023-10-16 06:06:20,055][05219] Updated weights for policy 1, policy_version 83920 (0.0007) -[2023-10-16 06:06:20,420][05219] Updated weights for policy 1, policy_version 83930 (0.0007) -[2023-10-16 06:06:21,900][05218] Updated weights for policy 0, policy_version 84202 (0.0009) -[2023-10-16 06:06:22,279][05218] Updated weights for policy 0, policy_version 84212 (0.0009) -[2023-10-16 06:06:22,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 172163072. Throughput: 0: 1798.8, 1: 1801.2. Samples: 43056126. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:06:22,351][03835] Avg episode reward: [(0, '7.010'), (1, '8.140')] -[2023-10-16 06:06:22,655][05218] Updated weights for policy 0, policy_version 84222 (0.0008) -[2023-10-16 06:06:24,063][05219] Updated weights for policy 1, policy_version 83940 (0.0010) -[2023-10-16 06:06:24,422][05219] Updated weights for policy 1, policy_version 83950 (0.0012) -[2023-10-16 06:06:24,790][05219] Updated weights for policy 1, policy_version 83960 (0.0009) -[2023-10-16 06:06:26,465][05218] Updated weights for policy 0, policy_version 84232 (0.0008) -[2023-10-16 06:06:26,853][05218] Updated weights for policy 0, policy_version 84242 (0.0009) -[2023-10-16 06:06:27,224][05218] Updated weights for policy 0, policy_version 84252 (0.0010) -[2023-10-16 06:06:27,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 172228608. Throughput: 0: 1782.0, 1: 1799.0. Samples: 43066716. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:06:27,351][03835] Avg episode reward: [(0, '7.440'), (1, '8.360')] -[2023-10-16 06:06:28,514][05219] Updated weights for policy 1, policy_version 83970 (0.0009) -[2023-10-16 06:06:28,887][05219] Updated weights for policy 1, policy_version 83980 (0.0011) -[2023-10-16 06:06:29,250][05219] Updated weights for policy 1, policy_version 83990 (0.0008) -[2023-10-16 06:06:29,606][05219] Updated weights for policy 1, policy_version 84000 (0.0010) -[2023-10-16 06:06:31,060][05218] Updated weights for policy 0, policy_version 84262 (0.0007) -[2023-10-16 06:06:31,442][05218] Updated weights for policy 0, policy_version 84272 (0.0009) -[2023-10-16 06:06:31,817][05218] Updated weights for policy 0, policy_version 84282 (0.0009) -[2023-10-16 06:06:32,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 172326912. Throughput: 0: 1801.8, 1: 1795.4. Samples: 43088424. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:06:32,351][03835] Avg episode reward: [(0, '7.000'), (1, '8.460')] -[2023-10-16 06:06:33,275][05219] Updated weights for policy 1, policy_version 84010 (0.0008) -[2023-10-16 06:06:33,640][05219] Updated weights for policy 1, policy_version 84020 (0.0009) -[2023-10-16 06:06:33,996][05219] Updated weights for policy 1, policy_version 84030 (0.0007) -[2023-10-16 06:06:35,487][05218] Updated weights for policy 0, policy_version 84292 (0.0009) -[2023-10-16 06:06:35,867][05218] Updated weights for policy 0, policy_version 84302 (0.0009) -[2023-10-16 06:06:36,241][05218] Updated weights for policy 0, policy_version 84312 (0.0009) -[2023-10-16 06:06:37,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 172392448. Throughput: 0: 1786.3, 1: 1801.6. Samples: 43110330. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:06:37,351][03835] Avg episode reward: [(0, '7.760'), (1, '7.980')] -[2023-10-16 06:06:37,716][05219] Updated weights for policy 1, policy_version 84040 (0.0009) -[2023-10-16 06:06:38,077][05219] Updated weights for policy 1, policy_version 84050 (0.0008) -[2023-10-16 06:06:38,446][05219] Updated weights for policy 1, policy_version 84060 (0.0009) -[2023-10-16 06:06:39,891][05218] Updated weights for policy 0, policy_version 84322 (0.0010) -[2023-10-16 06:06:40,263][05218] Updated weights for policy 0, policy_version 84332 (0.0008) -[2023-10-16 06:06:40,642][05218] Updated weights for policy 0, policy_version 84342 (0.0008) -[2023-10-16 06:06:41,022][05218] Updated weights for policy 0, policy_version 84352 (0.0009) -[2023-10-16 06:06:42,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 172457984. Throughput: 0: 1806.0, 1: 1799.6. Samples: 43121066. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:06:42,351][03835] Avg episode reward: [(0, '7.620'), (1, '7.120')] -[2023-10-16 06:06:42,488][05219] Updated weights for policy 1, policy_version 84070 (0.0007) -[2023-10-16 06:06:42,849][05219] Updated weights for policy 1, policy_version 84080 (0.0008) -[2023-10-16 06:06:43,216][05219] Updated weights for policy 1, policy_version 84090 (0.0007) -[2023-10-16 06:06:44,811][05218] Updated weights for policy 0, policy_version 84362 (0.0010) -[2023-10-16 06:06:45,179][05218] Updated weights for policy 0, policy_version 84372 (0.0008) -[2023-10-16 06:06:45,556][05218] Updated weights for policy 0, policy_version 84382 (0.0009) -[2023-10-16 06:06:46,922][05219] Updated weights for policy 1, policy_version 84100 (0.0008) -[2023-10-16 06:06:47,290][05219] Updated weights for policy 1, policy_version 84110 (0.0010) -[2023-10-16 06:06:47,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 172523520. Throughput: 0: 1786.8, 1: 1802.1. Samples: 43142580. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:06:47,351][03835] Avg episode reward: [(0, '6.740'), (1, '7.210')] -[2023-10-16 06:06:47,654][05219] Updated weights for policy 1, policy_version 84120 (0.0008) -[2023-10-16 06:06:49,344][05218] Updated weights for policy 0, policy_version 84392 (0.0010) -[2023-10-16 06:06:49,717][05218] Updated weights for policy 0, policy_version 84402 (0.0008) -[2023-10-16 06:06:50,088][05218] Updated weights for policy 0, policy_version 84412 (0.0007) -[2023-10-16 06:06:51,339][05219] Updated weights for policy 1, policy_version 84130 (0.0010) -[2023-10-16 06:06:51,708][05219] Updated weights for policy 1, policy_version 84140 (0.0008) -[2023-10-16 06:06:52,073][05219] Updated weights for policy 1, policy_version 84150 (0.0011) -[2023-10-16 06:06:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 172589056. Throughput: 0: 1779.5, 1: 1806.2. Samples: 43163792. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:06:52,351][03835] Avg episode reward: [(0, '7.700'), (1, '7.660')] -[2023-10-16 06:06:52,447][05219] Updated weights for policy 1, policy_version 84160 (0.0008) -[2023-10-16 06:06:53,960][05218] Updated weights for policy 0, policy_version 84422 (0.0009) -[2023-10-16 06:06:54,341][05218] Updated weights for policy 0, policy_version 84432 (0.0009) -[2023-10-16 06:06:54,715][05218] Updated weights for policy 0, policy_version 84442 (0.0009) -[2023-10-16 06:06:56,187][05219] Updated weights for policy 1, policy_version 84170 (0.0008) -[2023-10-16 06:06:56,554][05219] Updated weights for policy 1, policy_version 84180 (0.0008) -[2023-10-16 06:06:56,918][05219] Updated weights for policy 1, policy_version 84190 (0.0008) -[2023-10-16 06:06:57,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 172687360. Throughput: 0: 1781.0, 1: 1793.5. Samples: 43174630. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:06:57,351][03835] Avg episode reward: [(0, '6.620'), (1, '8.440')] -[2023-10-16 06:06:58,369][05218] Updated weights for policy 0, policy_version 84452 (0.0010) -[2023-10-16 06:06:58,749][05218] Updated weights for policy 0, policy_version 84462 (0.0011) -[2023-10-16 06:06:59,115][05218] Updated weights for policy 0, policy_version 84472 (0.0009) -[2023-10-16 06:07:00,615][05219] Updated weights for policy 1, policy_version 84200 (0.0008) -[2023-10-16 06:07:00,984][05219] Updated weights for policy 1, policy_version 84210 (0.0010) -[2023-10-16 06:07:01,341][05219] Updated weights for policy 1, policy_version 84220 (0.0010) -[2023-10-16 06:07:02,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 172752896. Throughput: 0: 1784.0, 1: 1808.0. Samples: 43196104. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:07:02,351][03835] Avg episode reward: [(0, '6.960'), (1, '8.100')] -[2023-10-16 06:07:02,863][05218] Updated weights for policy 0, policy_version 84482 (0.0009) -[2023-10-16 06:07:03,238][05218] Updated weights for policy 0, policy_version 84492 (0.0011) -[2023-10-16 06:07:03,606][05218] Updated weights for policy 0, policy_version 84502 (0.0007) -[2023-10-16 06:07:03,987][05218] Updated weights for policy 0, policy_version 84512 (0.0010) -[2023-10-16 06:07:05,071][05219] Updated weights for policy 1, policy_version 84230 (0.0009) -[2023-10-16 06:07:05,448][05219] Updated weights for policy 1, policy_version 84240 (0.0008) -[2023-10-16 06:07:05,813][05219] Updated weights for policy 1, policy_version 84250 (0.0008) -[2023-10-16 06:07:07,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 172818432. Throughput: 0: 1804.3, 1: 1794.5. Samples: 43218068. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:07:07,351][03835] Avg episode reward: [(0, '8.040'), (1, '8.300')] -[2023-10-16 06:07:07,733][05218] Updated weights for policy 0, policy_version 84522 (0.0007) -[2023-10-16 06:07:08,109][05218] Updated weights for policy 0, policy_version 84532 (0.0007) -[2023-10-16 06:07:08,482][05218] Updated weights for policy 0, policy_version 84542 (0.0007) -[2023-10-16 06:07:09,661][05219] Updated weights for policy 1, policy_version 84260 (0.0009) -[2023-10-16 06:07:10,027][05219] Updated weights for policy 1, policy_version 84270 (0.0010) -[2023-10-16 06:07:10,395][05219] Updated weights for policy 1, policy_version 84280 (0.0010) -[2023-10-16 06:07:12,142][05218] Updated weights for policy 0, policy_version 84552 (0.0007) -[2023-10-16 06:07:12,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 172883968. Throughput: 0: 1789.3, 1: 1809.1. Samples: 43228642. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:07:12,351][03835] Avg episode reward: [(0, '7.070'), (1, '8.790')] -[2023-10-16 06:07:12,515][05218] Updated weights for policy 0, policy_version 84562 (0.0007) -[2023-10-16 06:07:12,894][05218] Updated weights for policy 0, policy_version 84572 (0.0009) -[2023-10-16 06:07:14,159][05219] Updated weights for policy 1, policy_version 84290 (0.0010) -[2023-10-16 06:07:14,527][05219] Updated weights for policy 1, policy_version 84300 (0.0008) -[2023-10-16 06:07:14,893][05219] Updated weights for policy 1, policy_version 84310 (0.0007) -[2023-10-16 06:07:15,257][05219] Updated weights for policy 1, policy_version 84320 (0.0008) -[2023-10-16 06:07:16,757][05218] Updated weights for policy 0, policy_version 84582 (0.0009) -[2023-10-16 06:07:17,126][05218] Updated weights for policy 0, policy_version 84592 (0.0009) -[2023-10-16 06:07:17,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 172949504. Throughput: 0: 1799.6, 1: 1797.2. Samples: 43250280. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:07:17,351][03835] Avg episode reward: [(0, '7.630'), (1, '8.310')] -[2023-10-16 06:07:17,505][05218] Updated weights for policy 0, policy_version 84602 (0.0007) -[2023-10-16 06:07:19,044][05219] Updated weights for policy 1, policy_version 84330 (0.0010) -[2023-10-16 06:07:19,410][05219] Updated weights for policy 1, policy_version 84340 (0.0009) -[2023-10-16 06:07:19,775][05219] Updated weights for policy 1, policy_version 84350 (0.0012) -[2023-10-16 06:07:21,156][05218] Updated weights for policy 0, policy_version 84612 (0.0008) -[2023-10-16 06:07:21,528][05218] Updated weights for policy 0, policy_version 84622 (0.0009) -[2023-10-16 06:07:21,899][05218] Updated weights for policy 0, policy_version 84632 (0.0008) -[2023-10-16 06:07:22,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 173047808. Throughput: 0: 1786.7, 1: 1788.5. Samples: 43271214. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:07:22,352][03835] Avg episode reward: [(0, '6.970'), (1, '8.160')] -[2023-10-16 06:07:23,449][05219] Updated weights for policy 1, policy_version 84360 (0.0008) -[2023-10-16 06:07:23,813][05219] Updated weights for policy 1, policy_version 84370 (0.0008) -[2023-10-16 06:07:24,184][05219] Updated weights for policy 1, policy_version 84380 (0.0009) -[2023-10-16 06:07:25,527][05218] Updated weights for policy 0, policy_version 84642 (0.0008) -[2023-10-16 06:07:25,903][05218] Updated weights for policy 0, policy_version 84652 (0.0011) -[2023-10-16 06:07:26,286][05218] Updated weights for policy 0, policy_version 84662 (0.0011) -[2023-10-16 06:07:26,663][05218] Updated weights for policy 0, policy_version 84672 (0.0010) -[2023-10-16 06:07:27,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 173113344. Throughput: 0: 1801.9, 1: 1787.3. Samples: 43282580. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:07:27,351][03835] Avg episode reward: [(0, '7.120'), (1, '8.190')] -[2023-10-16 06:07:27,927][05219] Updated weights for policy 1, policy_version 84390 (0.0009) -[2023-10-16 06:07:28,289][05219] Updated weights for policy 1, policy_version 84400 (0.0010) -[2023-10-16 06:07:28,663][05219] Updated weights for policy 1, policy_version 84410 (0.0007) -[2023-10-16 06:07:30,426][05218] Updated weights for policy 0, policy_version 84682 (0.0008) -[2023-10-16 06:07:30,800][05218] Updated weights for policy 0, policy_version 84692 (0.0008) -[2023-10-16 06:07:31,184][05218] Updated weights for policy 0, policy_version 84702 (0.0010) -[2023-10-16 06:07:32,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 173178880. Throughput: 0: 1786.4, 1: 1791.1. Samples: 43303566. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:07:32,351][03835] Avg episode reward: [(0, '7.220'), (1, '7.490')] -[2023-10-16 06:07:32,397][05219] Updated weights for policy 1, policy_version 84420 (0.0008) -[2023-10-16 06:07:32,761][05219] Updated weights for policy 1, policy_version 84430 (0.0009) -[2023-10-16 06:07:33,125][05219] Updated weights for policy 1, policy_version 84440 (0.0010) -[2023-10-16 06:07:34,959][05218] Updated weights for policy 0, policy_version 84712 (0.0008) -[2023-10-16 06:07:35,335][05218] Updated weights for policy 0, policy_version 84722 (0.0009) -[2023-10-16 06:07:35,719][05218] Updated weights for policy 0, policy_version 84732 (0.0009) -[2023-10-16 06:07:37,058][05219] Updated weights for policy 1, policy_version 84450 (0.0008) -[2023-10-16 06:07:37,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 173244416. Throughput: 0: 1788.6, 1: 1812.8. Samples: 43325858. Policy #0 lag: (min: 31.0, avg: 31.6, max: 46.0) -[2023-10-16 06:07:37,351][03835] Avg episode reward: [(0, '7.000'), (1, '7.150')] -[2023-10-16 06:07:37,359][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000084736_86769664.pth... -[2023-10-16 06:07:37,395][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000083072_85065728.pth -[2023-10-16 06:07:37,419][05219] Updated weights for policy 1, policy_version 84460 (0.0007) -[2023-10-16 06:07:37,789][05219] Updated weights for policy 1, policy_version 84470 (0.0008) -[2023-10-16 06:07:38,149][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000084480_86507520.pth... -[2023-10-16 06:07:38,154][05219] Updated weights for policy 1, policy_version 84480 (0.0007) -[2023-10-16 06:07:38,187][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000082784_84770816.pth -[2023-10-16 06:07:39,643][05218] Updated weights for policy 0, policy_version 84742 (0.0010) -[2023-10-16 06:07:40,014][05218] Updated weights for policy 0, policy_version 84752 (0.0010) -[2023-10-16 06:07:40,395][05218] Updated weights for policy 0, policy_version 84762 (0.0009) -[2023-10-16 06:07:41,983][05219] Updated weights for policy 1, policy_version 84490 (0.0007) -[2023-10-16 06:07:42,349][05219] Updated weights for policy 1, policy_version 84500 (0.0008) -[2023-10-16 06:07:42,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 173309952. Throughput: 0: 1797.0, 1: 1795.0. Samples: 43336268. Policy #0 lag: (min: 31.0, avg: 31.6, max: 46.0) -[2023-10-16 06:07:42,351][03835] Avg episode reward: [(0, '7.540'), (1, '7.200')] -[2023-10-16 06:07:42,723][05219] Updated weights for policy 1, policy_version 84510 (0.0009) -[2023-10-16 06:07:44,350][05218] Updated weights for policy 0, policy_version 84772 (0.0008) -[2023-10-16 06:07:44,713][05218] Updated weights for policy 0, policy_version 84782 (0.0011) -[2023-10-16 06:07:45,089][05218] Updated weights for policy 0, policy_version 84792 (0.0008) -[2023-10-16 06:07:46,453][05219] Updated weights for policy 1, policy_version 84520 (0.0008) -[2023-10-16 06:07:46,810][05219] Updated weights for policy 1, policy_version 84530 (0.0007) -[2023-10-16 06:07:47,184][05219] Updated weights for policy 1, policy_version 84540 (0.0008) -[2023-10-16 06:07:47,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 173408256. Throughput: 0: 1778.4, 1: 1816.0. Samples: 43357852. Policy #0 lag: (min: 31.0, avg: 31.6, max: 46.0) -[2023-10-16 06:07:47,351][03835] Avg episode reward: [(0, '6.760'), (1, '8.010')] -[2023-10-16 06:07:48,944][05218] Updated weights for policy 0, policy_version 84802 (0.0009) -[2023-10-16 06:07:49,310][05218] Updated weights for policy 0, policy_version 84812 (0.0008) -[2023-10-16 06:07:49,680][05218] Updated weights for policy 0, policy_version 84822 (0.0010) -[2023-10-16 06:07:50,058][05218] Updated weights for policy 0, policy_version 84832 (0.0008) -[2023-10-16 06:07:50,930][05219] Updated weights for policy 1, policy_version 84550 (0.0008) -[2023-10-16 06:07:51,292][05219] Updated weights for policy 1, policy_version 84560 (0.0008) -[2023-10-16 06:07:51,655][05219] Updated weights for policy 1, policy_version 84570 (0.0008) -[2023-10-16 06:07:52,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 173473792. Throughput: 0: 1777.7, 1: 1791.4. Samples: 43378678. Policy #0 lag: (min: 31.0, avg: 31.6, max: 46.0) -[2023-10-16 06:07:52,351][03835] Avg episode reward: [(0, '6.860'), (1, '7.540')] -[2023-10-16 06:07:53,681][05218] Updated weights for policy 0, policy_version 84842 (0.0009) -[2023-10-16 06:07:54,063][05218] Updated weights for policy 0, policy_version 84852 (0.0011) -[2023-10-16 06:07:54,426][05218] Updated weights for policy 0, policy_version 84862 (0.0011) -[2023-10-16 06:07:55,390][05219] Updated weights for policy 1, policy_version 84580 (0.0008) -[2023-10-16 06:07:55,760][05219] Updated weights for policy 1, policy_version 84590 (0.0009) -[2023-10-16 06:07:56,132][05219] Updated weights for policy 1, policy_version 84600 (0.0008) -[2023-10-16 06:07:57,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 173539328. Throughput: 0: 1771.7, 1: 1811.5. Samples: 43389886. Policy #0 lag: (min: 31.0, avg: 31.6, max: 46.0) -[2023-10-16 06:07:57,351][03835] Avg episode reward: [(0, '6.890'), (1, '7.480')] -[2023-10-16 06:07:58,431][05218] Updated weights for policy 0, policy_version 84872 (0.0011) -[2023-10-16 06:07:58,800][05218] Updated weights for policy 0, policy_version 84882 (0.0008) -[2023-10-16 06:07:59,179][05218] Updated weights for policy 0, policy_version 84892 (0.0007) -[2023-10-16 06:07:59,827][05219] Updated weights for policy 1, policy_version 84610 (0.0008) -[2023-10-16 06:08:00,194][05219] Updated weights for policy 1, policy_version 84620 (0.0008) -[2023-10-16 06:08:00,554][05219] Updated weights for policy 1, policy_version 84630 (0.0007) -[2023-10-16 06:08:00,917][05219] Updated weights for policy 1, policy_version 84640 (0.0007) -[2023-10-16 06:08:02,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 173604864. Throughput: 0: 1777.6, 1: 1792.8. Samples: 43410948. Policy #0 lag: (min: 31.0, avg: 31.6, max: 46.0) -[2023-10-16 06:08:02,352][03835] Avg episode reward: [(0, '6.950'), (1, '9.040')] -[2023-10-16 06:08:02,925][05218] Updated weights for policy 0, policy_version 84902 (0.0007) -[2023-10-16 06:08:03,304][05218] Updated weights for policy 0, policy_version 84912 (0.0009) -[2023-10-16 06:08:03,690][05218] Updated weights for policy 0, policy_version 84922 (0.0008) -[2023-10-16 06:08:04,606][05219] Updated weights for policy 1, policy_version 84650 (0.0009) -[2023-10-16 06:08:04,969][05219] Updated weights for policy 1, policy_version 84660 (0.0010) -[2023-10-16 06:08:05,326][05219] Updated weights for policy 1, policy_version 84670 (0.0010) -[2023-10-16 06:08:07,250][05218] Updated weights for policy 0, policy_version 84932 (0.0009) -[2023-10-16 06:08:07,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 173670400. Throughput: 0: 1805.6, 1: 1797.2. Samples: 43433340. Policy #0 lag: (min: 31.0, avg: 31.6, max: 46.0) -[2023-10-16 06:08:07,351][03835] Avg episode reward: [(0, '7.910'), (1, '7.590')] -[2023-10-16 06:08:07,624][05218] Updated weights for policy 0, policy_version 84942 (0.0008) -[2023-10-16 06:08:07,998][05218] Updated weights for policy 0, policy_version 84952 (0.0008) -[2023-10-16 06:08:09,068][05219] Updated weights for policy 1, policy_version 84680 (0.0010) -[2023-10-16 06:08:09,431][05219] Updated weights for policy 1, policy_version 84690 (0.0010) -[2023-10-16 06:08:09,804][05219] Updated weights for policy 1, policy_version 84700 (0.0007) -[2023-10-16 06:08:11,852][05218] Updated weights for policy 0, policy_version 84962 (0.0007) -[2023-10-16 06:08:12,226][05218] Updated weights for policy 0, policy_version 84972 (0.0008) -[2023-10-16 06:08:12,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 173735936. Throughput: 0: 1772.4, 1: 1798.9. Samples: 43443286. Policy #0 lag: (min: 31.0, avg: 31.6, max: 46.0) -[2023-10-16 06:08:12,351][03835] Avg episode reward: [(0, '7.600'), (1, '8.050')] -[2023-10-16 06:08:12,596][05218] Updated weights for policy 0, policy_version 84982 (0.0009) -[2023-10-16 06:08:12,975][05218] Updated weights for policy 0, policy_version 84992 (0.0010) -[2023-10-16 06:08:13,493][05219] Updated weights for policy 1, policy_version 84710 (0.0008) -[2023-10-16 06:08:13,843][05219] Updated weights for policy 1, policy_version 84720 (0.0010) -[2023-10-16 06:08:14,210][05219] Updated weights for policy 1, policy_version 84730 (0.0008) -[2023-10-16 06:08:16,606][05218] Updated weights for policy 0, policy_version 85002 (0.0009) -[2023-10-16 06:08:16,989][05218] Updated weights for policy 0, policy_version 85012 (0.0009) -[2023-10-16 06:08:17,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 173801472. Throughput: 0: 1800.7, 1: 1801.4. Samples: 43465660. Policy #0 lag: (min: 31.0, avg: 31.6, max: 46.0) -[2023-10-16 06:08:17,351][03835] Avg episode reward: [(0, '7.140'), (1, '8.150')] -[2023-10-16 06:08:17,359][05218] Updated weights for policy 0, policy_version 85022 (0.0010) -[2023-10-16 06:08:17,958][05219] Updated weights for policy 1, policy_version 84740 (0.0008) -[2023-10-16 06:08:18,323][05219] Updated weights for policy 1, policy_version 84750 (0.0007) -[2023-10-16 06:08:18,679][05219] Updated weights for policy 1, policy_version 84760 (0.0008) -[2023-10-16 06:08:21,102][05218] Updated weights for policy 0, policy_version 85032 (0.0010) -[2023-10-16 06:08:21,485][05218] Updated weights for policy 0, policy_version 85042 (0.0009) -[2023-10-16 06:08:21,860][05218] Updated weights for policy 0, policy_version 85052 (0.0009) -[2023-10-16 06:08:22,351][03835] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 173899776. Throughput: 0: 1765.7, 1: 1805.6. Samples: 43486568. Policy #0 lag: (min: 31.0, avg: 31.6, max: 46.0) -[2023-10-16 06:08:22,352][03835] Avg episode reward: [(0, '7.460'), (1, '7.130')] -[2023-10-16 06:08:22,390][05219] Updated weights for policy 1, policy_version 84770 (0.0008) -[2023-10-16 06:08:22,753][05219] Updated weights for policy 1, policy_version 84780 (0.0009) -[2023-10-16 06:08:23,124][05219] Updated weights for policy 1, policy_version 84790 (0.0009) -[2023-10-16 06:08:23,482][05219] Updated weights for policy 1, policy_version 84800 (0.0008) -[2023-10-16 06:08:25,402][05218] Updated weights for policy 0, policy_version 85062 (0.0008) -[2023-10-16 06:08:25,777][05218] Updated weights for policy 0, policy_version 85072 (0.0010) -[2023-10-16 06:08:26,151][05218] Updated weights for policy 0, policy_version 85082 (0.0009) -[2023-10-16 06:08:27,283][05219] Updated weights for policy 1, policy_version 84810 (0.0008) -[2023-10-16 06:08:27,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 173965312. Throughput: 0: 1790.4, 1: 1796.6. Samples: 43497684. Policy #0 lag: (min: 31.0, avg: 31.6, max: 46.0) -[2023-10-16 06:08:27,351][03835] Avg episode reward: [(0, '7.050'), (1, '6.990')] -[2023-10-16 06:08:27,646][05219] Updated weights for policy 1, policy_version 84820 (0.0010) -[2023-10-16 06:08:28,008][05219] Updated weights for policy 1, policy_version 84830 (0.0008) -[2023-10-16 06:08:29,998][05218] Updated weights for policy 0, policy_version 85092 (0.0009) -[2023-10-16 06:08:30,381][05218] Updated weights for policy 0, policy_version 85102 (0.0008) -[2023-10-16 06:08:30,757][05218] Updated weights for policy 0, policy_version 85112 (0.0011) -[2023-10-16 06:08:31,683][05219] Updated weights for policy 1, policy_version 84840 (0.0010) -[2023-10-16 06:08:32,051][05219] Updated weights for policy 1, policy_version 84850 (0.0008) -[2023-10-16 06:08:32,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 174030848. Throughput: 0: 1775.1, 1: 1796.8. Samples: 43518590. Policy #0 lag: (min: 8.0, avg: 32.1, max: 40.0) -[2023-10-16 06:08:32,351][03835] Avg episode reward: [(0, '7.680'), (1, '8.360')] -[2023-10-16 06:08:32,410][05219] Updated weights for policy 1, policy_version 84860 (0.0007) -[2023-10-16 06:08:34,456][05218] Updated weights for policy 0, policy_version 85122 (0.0010) -[2023-10-16 06:08:34,831][05218] Updated weights for policy 0, policy_version 85132 (0.0008) -[2023-10-16 06:08:35,211][05218] Updated weights for policy 0, policy_version 85142 (0.0007) -[2023-10-16 06:08:35,585][05218] Updated weights for policy 0, policy_version 85152 (0.0009) -[2023-10-16 06:08:36,126][05219] Updated weights for policy 1, policy_version 84870 (0.0008) -[2023-10-16 06:08:36,490][05219] Updated weights for policy 1, policy_version 84880 (0.0009) -[2023-10-16 06:08:36,857][05219] Updated weights for policy 1, policy_version 84890 (0.0008) -[2023-10-16 06:08:37,350][03835] Fps is (10 sec: 16383.4, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 174129152. Throughput: 0: 1779.4, 1: 1802.1. Samples: 43539844. Policy #0 lag: (min: 8.0, avg: 32.1, max: 40.0) -[2023-10-16 06:08:37,352][03835] Avg episode reward: [(0, '7.960'), (1, '7.520')] -[2023-10-16 06:08:39,350][05218] Updated weights for policy 0, policy_version 85162 (0.0009) -[2023-10-16 06:08:39,711][05218] Updated weights for policy 0, policy_version 85172 (0.0008) -[2023-10-16 06:08:40,089][05218] Updated weights for policy 0, policy_version 85182 (0.0008) -[2023-10-16 06:08:40,654][05219] Updated weights for policy 1, policy_version 84900 (0.0009) -[2023-10-16 06:08:41,014][05219] Updated weights for policy 1, policy_version 84910 (0.0010) -[2023-10-16 06:08:41,380][05219] Updated weights for policy 1, policy_version 84920 (0.0009) -[2023-10-16 06:08:42,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 174194688. Throughput: 0: 1779.6, 1: 1798.8. Samples: 43550916. Policy #0 lag: (min: 8.0, avg: 32.1, max: 40.0) -[2023-10-16 06:08:42,351][03835] Avg episode reward: [(0, '8.610'), (1, '8.320')] -[2023-10-16 06:08:42,352][04766] Saving new best policy, reward=8.610! -[2023-10-16 06:08:43,954][05218] Updated weights for policy 0, policy_version 85192 (0.0009) -[2023-10-16 06:08:44,333][05218] Updated weights for policy 0, policy_version 85202 (0.0010) -[2023-10-16 06:08:44,716][05218] Updated weights for policy 0, policy_version 85212 (0.0011) -[2023-10-16 06:08:45,213][05219] Updated weights for policy 1, policy_version 84930 (0.0009) -[2023-10-16 06:08:45,573][05219] Updated weights for policy 1, policy_version 84940 (0.0008) -[2023-10-16 06:08:45,946][05219] Updated weights for policy 1, policy_version 84950 (0.0009) -[2023-10-16 06:08:46,315][05219] Updated weights for policy 1, policy_version 84960 (0.0009) -[2023-10-16 06:08:47,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 174260224. Throughput: 0: 1772.8, 1: 1800.7. Samples: 43571756. Policy #0 lag: (min: 8.0, avg: 32.1, max: 40.0) -[2023-10-16 06:08:47,351][03835] Avg episode reward: [(0, '7.480'), (1, '7.930')] -[2023-10-16 06:08:48,697][05218] Updated weights for policy 0, policy_version 85222 (0.0010) -[2023-10-16 06:08:49,078][05218] Updated weights for policy 0, policy_version 85232 (0.0011) -[2023-10-16 06:08:49,453][05218] Updated weights for policy 0, policy_version 85242 (0.0008) -[2023-10-16 06:08:50,004][05219] Updated weights for policy 1, policy_version 84970 (0.0008) -[2023-10-16 06:08:50,375][05219] Updated weights for policy 1, policy_version 84980 (0.0008) -[2023-10-16 06:08:50,740][05219] Updated weights for policy 1, policy_version 84990 (0.0010) -[2023-10-16 06:08:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 174325760. Throughput: 0: 1773.6, 1: 1792.8. Samples: 43593830. Policy #0 lag: (min: 8.0, avg: 32.1, max: 40.0) -[2023-10-16 06:08:52,352][03835] Avg episode reward: [(0, '7.250'), (1, '7.560')] -[2023-10-16 06:08:53,186][05218] Updated weights for policy 0, policy_version 85252 (0.0009) -[2023-10-16 06:08:53,555][05218] Updated weights for policy 0, policy_version 85262 (0.0008) -[2023-10-16 06:08:53,936][05218] Updated weights for policy 0, policy_version 85272 (0.0008) -[2023-10-16 06:08:54,664][05219] Updated weights for policy 1, policy_version 85000 (0.0010) -[2023-10-16 06:08:55,030][05219] Updated weights for policy 1, policy_version 85010 (0.0007) -[2023-10-16 06:08:55,398][05219] Updated weights for policy 1, policy_version 85020 (0.0007) -[2023-10-16 06:08:57,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 174391296. Throughput: 0: 1769.6, 1: 1804.9. Samples: 43604140. Policy #0 lag: (min: 8.0, avg: 32.1, max: 40.0) -[2023-10-16 06:08:57,351][03835] Avg episode reward: [(0, '8.110'), (1, '8.080')] -[2023-10-16 06:08:57,646][05218] Updated weights for policy 0, policy_version 85282 (0.0009) -[2023-10-16 06:08:58,020][05218] Updated weights for policy 0, policy_version 85292 (0.0009) -[2023-10-16 06:08:58,395][05218] Updated weights for policy 0, policy_version 85302 (0.0009) -[2023-10-16 06:08:58,763][05218] Updated weights for policy 0, policy_version 85312 (0.0010) -[2023-10-16 06:08:59,128][05219] Updated weights for policy 1, policy_version 85030 (0.0007) -[2023-10-16 06:08:59,494][05219] Updated weights for policy 1, policy_version 85040 (0.0008) -[2023-10-16 06:08:59,872][05219] Updated weights for policy 1, policy_version 85050 (0.0008) -[2023-10-16 06:09:02,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 174456832. Throughput: 0: 1773.9, 1: 1786.1. Samples: 43625862. Policy #0 lag: (min: 8.0, avg: 32.1, max: 40.0) -[2023-10-16 06:09:02,351][03835] Avg episode reward: [(0, '7.790'), (1, '7.150')] -[2023-10-16 06:09:02,614][05218] Updated weights for policy 0, policy_version 85322 (0.0009) -[2023-10-16 06:09:03,002][05218] Updated weights for policy 0, policy_version 85332 (0.0009) -[2023-10-16 06:09:03,378][05218] Updated weights for policy 0, policy_version 85342 (0.0008) -[2023-10-16 06:09:03,627][05219] Updated weights for policy 1, policy_version 85060 (0.0009) -[2023-10-16 06:09:04,000][05219] Updated weights for policy 1, policy_version 85070 (0.0008) -[2023-10-16 06:09:04,355][05219] Updated weights for policy 1, policy_version 85080 (0.0008) -[2023-10-16 06:09:07,093][05218] Updated weights for policy 0, policy_version 85352 (0.0008) -[2023-10-16 06:09:07,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 174522368. Throughput: 0: 1795.3, 1: 1792.2. Samples: 43648008. Policy #0 lag: (min: 8.0, avg: 32.1, max: 40.0) -[2023-10-16 06:09:07,351][03835] Avg episode reward: [(0, '6.940'), (1, '8.140')] -[2023-10-16 06:09:07,473][05218] Updated weights for policy 0, policy_version 85362 (0.0010) -[2023-10-16 06:09:07,853][05218] Updated weights for policy 0, policy_version 85372 (0.0008) -[2023-10-16 06:09:08,041][05219] Updated weights for policy 1, policy_version 85090 (0.0008) -[2023-10-16 06:09:08,399][05219] Updated weights for policy 1, policy_version 85100 (0.0007) -[2023-10-16 06:09:08,770][05219] Updated weights for policy 1, policy_version 85110 (0.0008) -[2023-10-16 06:09:09,131][05219] Updated weights for policy 1, policy_version 85120 (0.0008) -[2023-10-16 06:09:11,553][05218] Updated weights for policy 0, policy_version 85382 (0.0009) -[2023-10-16 06:09:11,930][05218] Updated weights for policy 0, policy_version 85392 (0.0010) -[2023-10-16 06:09:12,319][05218] Updated weights for policy 0, policy_version 85402 (0.0009) -[2023-10-16 06:09:12,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 174587904. Throughput: 0: 1779.2, 1: 1798.4. Samples: 43658676. Policy #0 lag: (min: 8.0, avg: 32.1, max: 40.0) -[2023-10-16 06:09:12,351][03835] Avg episode reward: [(0, '7.160'), (1, '8.560')] -[2023-10-16 06:09:12,913][05219] Updated weights for policy 1, policy_version 85130 (0.0010) -[2023-10-16 06:09:13,283][05219] Updated weights for policy 1, policy_version 85140 (0.0008) -[2023-10-16 06:09:13,644][05219] Updated weights for policy 1, policy_version 85150 (0.0010) -[2023-10-16 06:09:16,004][05218] Updated weights for policy 0, policy_version 85412 (0.0008) -[2023-10-16 06:09:16,380][05218] Updated weights for policy 0, policy_version 85422 (0.0007) -[2023-10-16 06:09:16,758][05218] Updated weights for policy 0, policy_version 85432 (0.0007) -[2023-10-16 06:09:17,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14440.2). Total num frames: 174686208. Throughput: 0: 1799.1, 1: 1793.4. Samples: 43680250. Policy #0 lag: (min: 8.0, avg: 32.1, max: 40.0) -[2023-10-16 06:09:17,351][03835] Avg episode reward: [(0, '7.240'), (1, '7.890')] -[2023-10-16 06:09:17,451][05219] Updated weights for policy 1, policy_version 85160 (0.0010) -[2023-10-16 06:09:17,817][05219] Updated weights for policy 1, policy_version 85170 (0.0008) -[2023-10-16 06:09:18,179][05219] Updated weights for policy 1, policy_version 85180 (0.0010) -[2023-10-16 06:09:20,557][05218] Updated weights for policy 0, policy_version 85442 (0.0009) -[2023-10-16 06:09:20,930][05218] Updated weights for policy 0, policy_version 85452 (0.0009) -[2023-10-16 06:09:21,307][05218] Updated weights for policy 0, policy_version 85462 (0.0010) -[2023-10-16 06:09:21,683][05218] Updated weights for policy 0, policy_version 85472 (0.0008) -[2023-10-16 06:09:21,895][05219] Updated weights for policy 1, policy_version 85190 (0.0009) -[2023-10-16 06:09:22,262][05219] Updated weights for policy 1, policy_version 85200 (0.0007) -[2023-10-16 06:09:22,350][03835] Fps is (10 sec: 16383.5, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 174751744. Throughput: 0: 1777.6, 1: 1809.3. Samples: 43701254. Policy #0 lag: (min: 8.0, avg: 32.1, max: 40.0) -[2023-10-16 06:09:22,351][03835] Avg episode reward: [(0, '6.470'), (1, '8.220')] -[2023-10-16 06:09:22,612][05219] Updated weights for policy 1, policy_version 85210 (0.0010) -[2023-10-16 06:09:25,303][05218] Updated weights for policy 0, policy_version 85482 (0.0010) -[2023-10-16 06:09:25,666][05218] Updated weights for policy 0, policy_version 85492 (0.0009) -[2023-10-16 06:09:26,045][05218] Updated weights for policy 0, policy_version 85502 (0.0009) -[2023-10-16 06:09:26,329][05219] Updated weights for policy 1, policy_version 85220 (0.0010) -[2023-10-16 06:09:26,689][05219] Updated weights for policy 1, policy_version 85230 (0.0010) -[2023-10-16 06:09:27,064][05219] Updated weights for policy 1, policy_version 85240 (0.0009) -[2023-10-16 06:09:27,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 174850048. Throughput: 0: 1804.2, 1: 1786.0. Samples: 43712474. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:09:27,351][03835] Avg episode reward: [(0, '7.530'), (1, '7.840')] -[2023-10-16 06:09:29,726][05218] Updated weights for policy 0, policy_version 85512 (0.0008) -[2023-10-16 06:09:30,103][05218] Updated weights for policy 0, policy_version 85522 (0.0009) -[2023-10-16 06:09:30,480][05218] Updated weights for policy 0, policy_version 85532 (0.0009) -[2023-10-16 06:09:30,891][05219] Updated weights for policy 1, policy_version 85250 (0.0009) -[2023-10-16 06:09:31,254][05219] Updated weights for policy 1, policy_version 85260 (0.0008) -[2023-10-16 06:09:31,616][05219] Updated weights for policy 1, policy_version 85270 (0.0009) -[2023-10-16 06:09:31,985][05219] Updated weights for policy 1, policy_version 85280 (0.0007) -[2023-10-16 06:09:32,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 174915584. Throughput: 0: 1790.7, 1: 1806.7. Samples: 43733644. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:09:32,351][03835] Avg episode reward: [(0, '7.470'), (1, '7.860')] -[2023-10-16 06:09:34,336][05218] Updated weights for policy 0, policy_version 85542 (0.0010) -[2023-10-16 06:09:34,723][05218] Updated weights for policy 0, policy_version 85552 (0.0010) -[2023-10-16 06:09:35,097][05218] Updated weights for policy 0, policy_version 85562 (0.0008) -[2023-10-16 06:09:35,571][05219] Updated weights for policy 1, policy_version 85290 (0.0008) -[2023-10-16 06:09:35,940][05219] Updated weights for policy 1, policy_version 85300 (0.0007) -[2023-10-16 06:09:36,310][05219] Updated weights for policy 1, policy_version 85310 (0.0007) -[2023-10-16 06:09:37,351][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 174981120. Throughput: 0: 1791.1, 1: 1792.5. Samples: 43755092. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:09:37,352][03835] Avg episode reward: [(0, '7.000'), (1, '7.960')] -[2023-10-16 06:09:37,362][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000085568_87621632.pth... -[2023-10-16 06:09:37,363][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000085312_87359488.pth... -[2023-10-16 06:09:37,395][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000083904_85917696.pth -[2023-10-16 06:09:37,396][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000083616_85622784.pth -[2023-10-16 06:09:38,775][05218] Updated weights for policy 0, policy_version 85572 (0.0008) -[2023-10-16 06:09:39,150][05218] Updated weights for policy 0, policy_version 85582 (0.0007) -[2023-10-16 06:09:39,535][05218] Updated weights for policy 0, policy_version 85592 (0.0008) -[2023-10-16 06:09:40,174][05219] Updated weights for policy 1, policy_version 85320 (0.0007) -[2023-10-16 06:09:40,540][05219] Updated weights for policy 1, policy_version 85330 (0.0011) -[2023-10-16 06:09:40,913][05219] Updated weights for policy 1, policy_version 85340 (0.0009) -[2023-10-16 06:09:42,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 175046656. Throughput: 0: 1791.7, 1: 1806.0. Samples: 43766036. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:09:42,351][03835] Avg episode reward: [(0, '6.810'), (1, '8.300')] -[2023-10-16 06:09:43,333][05218] Updated weights for policy 0, policy_version 85602 (0.0008) -[2023-10-16 06:09:43,698][05218] Updated weights for policy 0, policy_version 85612 (0.0011) -[2023-10-16 06:09:44,074][05218] Updated weights for policy 0, policy_version 85622 (0.0010) -[2023-10-16 06:09:44,446][05218] Updated weights for policy 0, policy_version 85632 (0.0008) -[2023-10-16 06:09:44,617][05219] Updated weights for policy 1, policy_version 85350 (0.0009) -[2023-10-16 06:09:44,988][05219] Updated weights for policy 1, policy_version 85360 (0.0008) -[2023-10-16 06:09:45,352][05219] Updated weights for policy 1, policy_version 85370 (0.0010) -[2023-10-16 06:09:47,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 175112192. Throughput: 0: 1791.7, 1: 1798.6. Samples: 43787426. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:09:47,351][03835] Avg episode reward: [(0, '7.480'), (1, '7.880')] -[2023-10-16 06:09:48,115][05218] Updated weights for policy 0, policy_version 85642 (0.0009) -[2023-10-16 06:09:48,485][05218] Updated weights for policy 0, policy_version 85652 (0.0008) -[2023-10-16 06:09:48,860][05218] Updated weights for policy 0, policy_version 85662 (0.0010) -[2023-10-16 06:09:49,094][05219] Updated weights for policy 1, policy_version 85380 (0.0008) -[2023-10-16 06:09:49,465][05219] Updated weights for policy 1, policy_version 85390 (0.0008) -[2023-10-16 06:09:49,828][05219] Updated weights for policy 1, policy_version 85400 (0.0009) -[2023-10-16 06:09:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 175177728. Throughput: 0: 1805.8, 1: 1790.0. Samples: 43809816. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:09:52,351][03835] Avg episode reward: [(0, '7.390'), (1, '8.420')] -[2023-10-16 06:09:52,647][05218] Updated weights for policy 0, policy_version 85672 (0.0008) -[2023-10-16 06:09:53,011][05218] Updated weights for policy 0, policy_version 85682 (0.0008) -[2023-10-16 06:09:53,388][05218] Updated weights for policy 0, policy_version 85692 (0.0009) -[2023-10-16 06:09:53,731][05219] Updated weights for policy 1, policy_version 85410 (0.0011) -[2023-10-16 06:09:54,093][05219] Updated weights for policy 1, policy_version 85420 (0.0008) -[2023-10-16 06:09:54,463][05219] Updated weights for policy 1, policy_version 85430 (0.0008) -[2023-10-16 06:09:54,830][05219] Updated weights for policy 1, policy_version 85440 (0.0007) -[2023-10-16 06:09:57,117][05218] Updated weights for policy 0, policy_version 85702 (0.0007) -[2023-10-16 06:09:57,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 175243264. Throughput: 0: 1788.9, 1: 1784.0. Samples: 43819454. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:09:57,351][03835] Avg episode reward: [(0, '6.920'), (1, '7.660')] -[2023-10-16 06:09:57,489][05218] Updated weights for policy 0, policy_version 85712 (0.0008) -[2023-10-16 06:09:57,853][05218] Updated weights for policy 0, policy_version 85722 (0.0009) -[2023-10-16 06:09:58,716][05219] Updated weights for policy 1, policy_version 85450 (0.0008) -[2023-10-16 06:09:59,078][05219] Updated weights for policy 1, policy_version 85460 (0.0010) -[2023-10-16 06:09:59,449][05219] Updated weights for policy 1, policy_version 85470 (0.0009) -[2023-10-16 06:10:01,493][05218] Updated weights for policy 0, policy_version 85732 (0.0010) -[2023-10-16 06:10:01,873][05218] Updated weights for policy 0, policy_version 85742 (0.0007) -[2023-10-16 06:10:02,246][05218] Updated weights for policy 0, policy_version 85752 (0.0007) -[2023-10-16 06:10:02,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 175308800. Throughput: 0: 1808.0, 1: 1786.9. Samples: 43842022. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:10:02,352][03835] Avg episode reward: [(0, '7.110'), (1, '7.600')] -[2023-10-16 06:10:03,143][05219] Updated weights for policy 1, policy_version 85480 (0.0007) -[2023-10-16 06:10:03,502][05219] Updated weights for policy 1, policy_version 85490 (0.0008) -[2023-10-16 06:10:03,881][05219] Updated weights for policy 1, policy_version 85500 (0.0008) -[2023-10-16 06:10:05,895][05218] Updated weights for policy 0, policy_version 85762 (0.0007) -[2023-10-16 06:10:06,269][05218] Updated weights for policy 0, policy_version 85772 (0.0009) -[2023-10-16 06:10:06,644][05218] Updated weights for policy 0, policy_version 85782 (0.0009) -[2023-10-16 06:10:07,012][05218] Updated weights for policy 0, policy_version 85792 (0.0007) -[2023-10-16 06:10:07,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 175407104. Throughput: 0: 1799.9, 1: 1800.8. Samples: 43863284. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:10:07,351][03835] Avg episode reward: [(0, '6.240'), (1, '8.670')] -[2023-10-16 06:10:07,602][05219] Updated weights for policy 1, policy_version 85510 (0.0008) -[2023-10-16 06:10:07,966][05219] Updated weights for policy 1, policy_version 85520 (0.0009) -[2023-10-16 06:10:08,334][05219] Updated weights for policy 1, policy_version 85530 (0.0008) -[2023-10-16 06:10:10,569][05218] Updated weights for policy 0, policy_version 85802 (0.0011) -[2023-10-16 06:10:10,951][05218] Updated weights for policy 0, policy_version 85812 (0.0010) -[2023-10-16 06:10:11,321][05218] Updated weights for policy 0, policy_version 85822 (0.0008) -[2023-10-16 06:10:11,878][05219] Updated weights for policy 1, policy_version 85540 (0.0009) -[2023-10-16 06:10:12,240][05219] Updated weights for policy 1, policy_version 85550 (0.0009) -[2023-10-16 06:10:12,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 175472640. Throughput: 0: 1809.8, 1: 1794.8. Samples: 43874680. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:10:12,351][03835] Avg episode reward: [(0, '6.730'), (1, '8.290')] -[2023-10-16 06:10:12,608][05219] Updated weights for policy 1, policy_version 85560 (0.0009) -[2023-10-16 06:10:15,110][05218] Updated weights for policy 0, policy_version 85832 (0.0010) -[2023-10-16 06:10:15,484][05218] Updated weights for policy 0, policy_version 85842 (0.0008) -[2023-10-16 06:10:15,859][05218] Updated weights for policy 0, policy_version 85852 (0.0007) -[2023-10-16 06:10:16,459][05219] Updated weights for policy 1, policy_version 85570 (0.0008) -[2023-10-16 06:10:16,836][05219] Updated weights for policy 1, policy_version 85580 (0.0009) -[2023-10-16 06:10:17,196][05219] Updated weights for policy 1, policy_version 85590 (0.0009) -[2023-10-16 06:10:17,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 175538176. Throughput: 0: 1798.6, 1: 1804.3. Samples: 43895774. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:10:17,351][03835] Avg episode reward: [(0, '7.410'), (1, '7.620')] -[2023-10-16 06:10:17,563][05219] Updated weights for policy 1, policy_version 85600 (0.0009) -[2023-10-16 06:10:19,747][05218] Updated weights for policy 0, policy_version 85862 (0.0008) -[2023-10-16 06:10:20,129][05218] Updated weights for policy 0, policy_version 85872 (0.0008) -[2023-10-16 06:10:20,501][05218] Updated weights for policy 0, policy_version 85882 (0.0007) -[2023-10-16 06:10:21,424][05219] Updated weights for policy 1, policy_version 85610 (0.0008) -[2023-10-16 06:10:21,785][05219] Updated weights for policy 1, policy_version 85620 (0.0008) -[2023-10-16 06:10:22,163][05219] Updated weights for policy 1, policy_version 85630 (0.0009) -[2023-10-16 06:10:22,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 175636480. Throughput: 0: 1799.9, 1: 1795.0. Samples: 43916862. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:10:22,351][03835] Avg episode reward: [(0, '6.880'), (1, '9.060')] -[2023-10-16 06:10:24,094][05218] Updated weights for policy 0, policy_version 85892 (0.0010) -[2023-10-16 06:10:24,471][05218] Updated weights for policy 0, policy_version 85902 (0.0010) -[2023-10-16 06:10:24,843][05218] Updated weights for policy 0, policy_version 85912 (0.0010) -[2023-10-16 06:10:25,734][05219] Updated weights for policy 1, policy_version 85640 (0.0008) -[2023-10-16 06:10:26,110][05219] Updated weights for policy 1, policy_version 85650 (0.0007) -[2023-10-16 06:10:26,479][05219] Updated weights for policy 1, policy_version 85660 (0.0008) -[2023-10-16 06:10:27,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 175702016. Throughput: 0: 1797.5, 1: 1796.1. Samples: 43927750. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:10:27,351][03835] Avg episode reward: [(0, '7.560'), (1, '8.380')] -[2023-10-16 06:10:28,710][05218] Updated weights for policy 0, policy_version 85922 (0.0011) -[2023-10-16 06:10:29,095][05218] Updated weights for policy 0, policy_version 85932 (0.0010) -[2023-10-16 06:10:29,472][05218] Updated weights for policy 0, policy_version 85942 (0.0008) -[2023-10-16 06:10:29,839][05218] Updated weights for policy 0, policy_version 85952 (0.0008) -[2023-10-16 06:10:30,189][05219] Updated weights for policy 1, policy_version 85670 (0.0009) -[2023-10-16 06:10:30,558][05219] Updated weights for policy 1, policy_version 85680 (0.0007) -[2023-10-16 06:10:30,922][05219] Updated weights for policy 1, policy_version 85690 (0.0009) -[2023-10-16 06:10:32,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 175767552. Throughput: 0: 1796.1, 1: 1791.2. Samples: 43948856. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:10:32,351][03835] Avg episode reward: [(0, '7.230'), (1, '8.320')] -[2023-10-16 06:10:33,568][05218] Updated weights for policy 0, policy_version 85962 (0.0009) -[2023-10-16 06:10:33,938][05218] Updated weights for policy 0, policy_version 85972 (0.0008) -[2023-10-16 06:10:34,314][05218] Updated weights for policy 0, policy_version 85982 (0.0008) -[2023-10-16 06:10:34,769][05219] Updated weights for policy 1, policy_version 85700 (0.0008) -[2023-10-16 06:10:35,137][05219] Updated weights for policy 1, policy_version 85710 (0.0009) -[2023-10-16 06:10:35,492][05219] Updated weights for policy 1, policy_version 85720 (0.0009) -[2023-10-16 06:10:37,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 175833088. Throughput: 0: 1801.4, 1: 1785.5. Samples: 43971228. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:10:37,351][03835] Avg episode reward: [(0, '6.450'), (1, '8.950')] -[2023-10-16 06:10:38,041][05218] Updated weights for policy 0, policy_version 85992 (0.0007) -[2023-10-16 06:10:38,424][05218] Updated weights for policy 0, policy_version 86002 (0.0008) -[2023-10-16 06:10:38,800][05218] Updated weights for policy 0, policy_version 86012 (0.0011) -[2023-10-16 06:10:39,244][05219] Updated weights for policy 1, policy_version 85730 (0.0009) -[2023-10-16 06:10:39,613][05219] Updated weights for policy 1, policy_version 85740 (0.0007) -[2023-10-16 06:10:39,990][05219] Updated weights for policy 1, policy_version 85750 (0.0007) -[2023-10-16 06:10:40,364][05219] Updated weights for policy 1, policy_version 85760 (0.0009) -[2023-10-16 06:10:42,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 175898624. Throughput: 0: 1801.5, 1: 1795.0. Samples: 43981296. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:10:42,351][03835] Avg episode reward: [(0, '7.540'), (1, '8.820')] -[2023-10-16 06:10:42,591][05218] Updated weights for policy 0, policy_version 86022 (0.0010) -[2023-10-16 06:10:42,971][05218] Updated weights for policy 0, policy_version 86032 (0.0007) -[2023-10-16 06:10:43,337][05218] Updated weights for policy 0, policy_version 86042 (0.0008) -[2023-10-16 06:10:44,088][05219] Updated weights for policy 1, policy_version 85770 (0.0008) -[2023-10-16 06:10:44,456][05219] Updated weights for policy 1, policy_version 85780 (0.0008) -[2023-10-16 06:10:44,819][05219] Updated weights for policy 1, policy_version 85790 (0.0009) -[2023-10-16 06:10:47,053][05218] Updated weights for policy 0, policy_version 86052 (0.0009) -[2023-10-16 06:10:47,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 175964160. Throughput: 0: 1798.1, 1: 1788.0. Samples: 44003398. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:10:47,351][03835] Avg episode reward: [(0, '6.030'), (1, '8.160')] -[2023-10-16 06:10:47,425][05218] Updated weights for policy 0, policy_version 86062 (0.0009) -[2023-10-16 06:10:47,797][05218] Updated weights for policy 0, policy_version 86072 (0.0009) -[2023-10-16 06:10:48,902][05219] Updated weights for policy 1, policy_version 85800 (0.0008) -[2023-10-16 06:10:49,285][05219] Updated weights for policy 1, policy_version 85810 (0.0008) -[2023-10-16 06:10:49,641][05219] Updated weights for policy 1, policy_version 85820 (0.0009) -[2023-10-16 06:10:51,617][05218] Updated weights for policy 0, policy_version 86082 (0.0008) -[2023-10-16 06:10:52,000][05218] Updated weights for policy 0, policy_version 86092 (0.0009) -[2023-10-16 06:10:52,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 176029696. Throughput: 0: 1800.9, 1: 1779.7. Samples: 44024414. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:10:52,351][03835] Avg episode reward: [(0, '6.540'), (1, '8.380')] -[2023-10-16 06:10:52,371][05218] Updated weights for policy 0, policy_version 86102 (0.0009) -[2023-10-16 06:10:52,746][05218] Updated weights for policy 0, policy_version 86112 (0.0011) -[2023-10-16 06:10:53,494][05219] Updated weights for policy 1, policy_version 85830 (0.0007) -[2023-10-16 06:10:53,850][05219] Updated weights for policy 1, policy_version 85840 (0.0009) -[2023-10-16 06:10:54,208][05219] Updated weights for policy 1, policy_version 85850 (0.0010) -[2023-10-16 06:10:56,491][05218] Updated weights for policy 0, policy_version 86122 (0.0008) -[2023-10-16 06:10:56,873][05218] Updated weights for policy 0, policy_version 86132 (0.0010) -[2023-10-16 06:10:57,246][05218] Updated weights for policy 0, policy_version 86142 (0.0008) -[2023-10-16 06:10:57,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 176128000. Throughput: 0: 1786.5, 1: 1775.7. Samples: 44034978. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:10:57,351][03835] Avg episode reward: [(0, '7.490'), (1, '8.280')] -[2023-10-16 06:10:57,988][05219] Updated weights for policy 1, policy_version 85860 (0.0010) -[2023-10-16 06:10:58,352][05219] Updated weights for policy 1, policy_version 85870 (0.0007) -[2023-10-16 06:10:58,724][05219] Updated weights for policy 1, policy_version 85880 (0.0008) -[2023-10-16 06:11:01,163][05218] Updated weights for policy 0, policy_version 86152 (0.0009) -[2023-10-16 06:11:01,538][05218] Updated weights for policy 0, policy_version 86162 (0.0008) -[2023-10-16 06:11:01,916][05218] Updated weights for policy 0, policy_version 86172 (0.0007) -[2023-10-16 06:11:02,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 176193536. Throughput: 0: 1798.7, 1: 1774.7. Samples: 44056574. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:11:02,351][03835] Avg episode reward: [(0, '7.300'), (1, '7.800')] -[2023-10-16 06:11:02,556][05219] Updated weights for policy 1, policy_version 85890 (0.0008) -[2023-10-16 06:11:02,914][05219] Updated weights for policy 1, policy_version 85900 (0.0008) -[2023-10-16 06:11:03,279][05219] Updated weights for policy 1, policy_version 85910 (0.0007) -[2023-10-16 06:11:03,640][05219] Updated weights for policy 1, policy_version 85920 (0.0008) -[2023-10-16 06:11:05,585][05218] Updated weights for policy 0, policy_version 86182 (0.0007) -[2023-10-16 06:11:05,958][05218] Updated weights for policy 0, policy_version 86192 (0.0008) -[2023-10-16 06:11:06,331][05218] Updated weights for policy 0, policy_version 86202 (0.0011) -[2023-10-16 06:11:07,186][05219] Updated weights for policy 1, policy_version 85930 (0.0008) -[2023-10-16 06:11:07,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 176259072. Throughput: 0: 1779.9, 1: 1800.8. Samples: 44077994. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:11:07,351][03835] Avg episode reward: [(0, '6.760'), (1, '8.500')] -[2023-10-16 06:11:07,554][05219] Updated weights for policy 1, policy_version 85940 (0.0008) -[2023-10-16 06:11:07,916][05219] Updated weights for policy 1, policy_version 85950 (0.0009) -[2023-10-16 06:11:09,828][05218] Updated weights for policy 0, policy_version 86212 (0.0010) -[2023-10-16 06:11:10,209][05218] Updated weights for policy 0, policy_version 86222 (0.0007) -[2023-10-16 06:11:10,580][05218] Updated weights for policy 0, policy_version 86232 (0.0009) -[2023-10-16 06:11:11,807][05219] Updated weights for policy 1, policy_version 85960 (0.0007) -[2023-10-16 06:11:12,183][05219] Updated weights for policy 1, policy_version 85970 (0.0009) -[2023-10-16 06:11:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 176324608. Throughput: 0: 1802.3, 1: 1779.2. Samples: 44088914. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:11:12,351][03835] Avg episode reward: [(0, '7.370'), (1, '7.320')] -[2023-10-16 06:11:12,542][05219] Updated weights for policy 1, policy_version 85980 (0.0007) -[2023-10-16 06:11:14,372][05218] Updated weights for policy 0, policy_version 86242 (0.0010) -[2023-10-16 06:11:14,742][05218] Updated weights for policy 0, policy_version 86252 (0.0010) -[2023-10-16 06:11:15,117][05218] Updated weights for policy 0, policy_version 86262 (0.0011) -[2023-10-16 06:11:15,494][05218] Updated weights for policy 0, policy_version 86272 (0.0010) -[2023-10-16 06:11:16,373][05219] Updated weights for policy 1, policy_version 85990 (0.0008) -[2023-10-16 06:11:16,749][05219] Updated weights for policy 1, policy_version 86000 (0.0009) -[2023-10-16 06:11:17,108][05219] Updated weights for policy 1, policy_version 86010 (0.0010) -[2023-10-16 06:11:17,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 176422912. Throughput: 0: 1788.4, 1: 1807.5. Samples: 44110672. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-16 06:11:17,351][03835] Avg episode reward: [(0, '7.170'), (1, '8.100')] -[2023-10-16 06:11:19,313][05218] Updated weights for policy 0, policy_version 86282 (0.0009) -[2023-10-16 06:11:19,698][05218] Updated weights for policy 0, policy_version 86292 (0.0007) -[2023-10-16 06:11:20,066][05218] Updated weights for policy 0, policy_version 86302 (0.0007) -[2023-10-16 06:11:20,535][05219] Updated weights for policy 1, policy_version 86020 (0.0009) -[2023-10-16 06:11:20,911][05219] Updated weights for policy 1, policy_version 86030 (0.0011) -[2023-10-16 06:11:21,268][05219] Updated weights for policy 1, policy_version 86040 (0.0009) -[2023-10-16 06:11:22,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 176488448. Throughput: 0: 1783.6, 1: 1789.8. Samples: 44132028. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-16 06:11:22,351][03835] Avg episode reward: [(0, '7.750'), (1, '8.520')] -[2023-10-16 06:11:23,781][05218] Updated weights for policy 0, policy_version 86312 (0.0007) -[2023-10-16 06:11:24,164][05218] Updated weights for policy 0, policy_version 86322 (0.0009) -[2023-10-16 06:11:24,535][05218] Updated weights for policy 0, policy_version 86332 (0.0008) -[2023-10-16 06:11:24,965][05219] Updated weights for policy 1, policy_version 86050 (0.0008) -[2023-10-16 06:11:25,324][05219] Updated weights for policy 1, policy_version 86060 (0.0007) -[2023-10-16 06:11:25,687][05219] Updated weights for policy 1, policy_version 86070 (0.0009) -[2023-10-16 06:11:26,051][05219] Updated weights for policy 1, policy_version 86080 (0.0009) -[2023-10-16 06:11:27,351][03835] Fps is (10 sec: 13106.6, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 176553984. Throughput: 0: 1787.5, 1: 1811.4. Samples: 44143248. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-16 06:11:27,352][03835] Avg episode reward: [(0, '8.240'), (1, '8.450')] -[2023-10-16 06:11:28,192][05218] Updated weights for policy 0, policy_version 86342 (0.0010) -[2023-10-16 06:11:28,553][05218] Updated weights for policy 0, policy_version 86352 (0.0008) -[2023-10-16 06:11:28,929][05218] Updated weights for policy 0, policy_version 86362 (0.0009) -[2023-10-16 06:11:29,773][05219] Updated weights for policy 1, policy_version 86090 (0.0008) -[2023-10-16 06:11:30,142][05219] Updated weights for policy 1, policy_version 86100 (0.0008) -[2023-10-16 06:11:30,510][05219] Updated weights for policy 1, policy_version 86110 (0.0009) -[2023-10-16 06:11:32,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 176619520. Throughput: 0: 1787.3, 1: 1795.5. Samples: 44164626. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-16 06:11:32,351][03835] Avg episode reward: [(0, '7.810'), (1, '8.400')] -[2023-10-16 06:11:32,732][05218] Updated weights for policy 0, policy_version 86372 (0.0010) -[2023-10-16 06:11:33,109][05218] Updated weights for policy 0, policy_version 86382 (0.0010) -[2023-10-16 06:11:33,489][05218] Updated weights for policy 0, policy_version 86392 (0.0008) -[2023-10-16 06:11:34,298][05219] Updated weights for policy 1, policy_version 86120 (0.0010) -[2023-10-16 06:11:34,681][05219] Updated weights for policy 1, policy_version 86130 (0.0008) -[2023-10-16 06:11:35,041][05219] Updated weights for policy 1, policy_version 86140 (0.0007) -[2023-10-16 06:11:37,060][05218] Updated weights for policy 0, policy_version 86402 (0.0008) -[2023-10-16 06:11:37,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 176685056. Throughput: 0: 1806.7, 1: 1799.6. Samples: 44186694. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-16 06:11:37,351][03835] Avg episode reward: [(0, '7.680'), (1, '8.410')] -[2023-10-16 06:11:37,361][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000086144_88211456.pth... -[2023-10-16 06:11:37,395][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000084480_86507520.pth -[2023-10-16 06:11:37,425][05218] Updated weights for policy 0, policy_version 86412 (0.0007) -[2023-10-16 06:11:37,805][05218] Updated weights for policy 0, policy_version 86422 (0.0009) -[2023-10-16 06:11:38,187][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000086432_88506368.pth... -[2023-10-16 06:11:38,188][05218] Updated weights for policy 0, policy_version 86432 (0.0008) -[2023-10-16 06:11:38,216][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000084736_86769664.pth -[2023-10-16 06:11:38,799][05219] Updated weights for policy 1, policy_version 86150 (0.0009) -[2023-10-16 06:11:39,163][05219] Updated weights for policy 1, policy_version 86160 (0.0008) -[2023-10-16 06:11:39,523][05219] Updated weights for policy 1, policy_version 86170 (0.0008) -[2023-10-16 06:11:41,882][05218] Updated weights for policy 0, policy_version 86442 (0.0008) -[2023-10-16 06:11:42,267][05218] Updated weights for policy 0, policy_version 86452 (0.0009) -[2023-10-16 06:11:42,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 176750592. Throughput: 0: 1798.9, 1: 1800.2. Samples: 44196940. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-16 06:11:42,352][03835] Avg episode reward: [(0, '7.880'), (1, '8.170')] -[2023-10-16 06:11:42,645][05218] Updated weights for policy 0, policy_version 86462 (0.0009) -[2023-10-16 06:11:43,446][05219] Updated weights for policy 1, policy_version 86180 (0.0008) -[2023-10-16 06:11:43,814][05219] Updated weights for policy 1, policy_version 86190 (0.0008) -[2023-10-16 06:11:44,178][05219] Updated weights for policy 1, policy_version 86200 (0.0009) -[2023-10-16 06:11:46,500][05218] Updated weights for policy 0, policy_version 86472 (0.0008) -[2023-10-16 06:11:46,880][05218] Updated weights for policy 0, policy_version 86482 (0.0008) -[2023-10-16 06:11:47,250][05218] Updated weights for policy 0, policy_version 86492 (0.0007) -[2023-10-16 06:11:47,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 176816128. Throughput: 0: 1812.2, 1: 1794.6. Samples: 44218880. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-16 06:11:47,351][03835] Avg episode reward: [(0, '6.940'), (1, '8.080')] -[2023-10-16 06:11:47,927][05219] Updated weights for policy 1, policy_version 86210 (0.0011) -[2023-10-16 06:11:48,300][05219] Updated weights for policy 1, policy_version 86220 (0.0008) -[2023-10-16 06:11:48,660][05219] Updated weights for policy 1, policy_version 86230 (0.0008) -[2023-10-16 06:11:49,017][05219] Updated weights for policy 1, policy_version 86240 (0.0008) -[2023-10-16 06:11:51,116][05218] Updated weights for policy 0, policy_version 86502 (0.0010) -[2023-10-16 06:11:51,498][05218] Updated weights for policy 0, policy_version 86512 (0.0008) -[2023-10-16 06:11:51,875][05218] Updated weights for policy 0, policy_version 86522 (0.0011) -[2023-10-16 06:11:52,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 176914432. Throughput: 0: 1798.4, 1: 1795.6. Samples: 44239724. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-16 06:11:52,351][03835] Avg episode reward: [(0, '7.370'), (1, '8.490')] -[2023-10-16 06:11:52,814][05219] Updated weights for policy 1, policy_version 86250 (0.0007) -[2023-10-16 06:11:53,171][05219] Updated weights for policy 1, policy_version 86260 (0.0008) -[2023-10-16 06:11:53,535][05219] Updated weights for policy 1, policy_version 86270 (0.0007) -[2023-10-16 06:11:55,543][05218] Updated weights for policy 0, policy_version 86532 (0.0009) -[2023-10-16 06:11:55,911][05218] Updated weights for policy 0, policy_version 86542 (0.0010) -[2023-10-16 06:11:56,282][05218] Updated weights for policy 0, policy_version 86552 (0.0011) -[2023-10-16 06:11:57,250][05219] Updated weights for policy 1, policy_version 86280 (0.0009) -[2023-10-16 06:11:57,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 176979968. Throughput: 0: 1814.5, 1: 1790.4. Samples: 44251136. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-16 06:11:57,351][03835] Avg episode reward: [(0, '7.600'), (1, '8.000')] -[2023-10-16 06:11:57,611][05219] Updated weights for policy 1, policy_version 86290 (0.0009) -[2023-10-16 06:11:57,971][05219] Updated weights for policy 1, policy_version 86300 (0.0007) -[2023-10-16 06:12:00,028][05218] Updated weights for policy 0, policy_version 86562 (0.0012) -[2023-10-16 06:12:00,405][05218] Updated weights for policy 0, policy_version 86572 (0.0010) -[2023-10-16 06:12:00,770][05218] Updated weights for policy 0, policy_version 86582 (0.0011) -[2023-10-16 06:12:01,153][05218] Updated weights for policy 0, policy_version 86592 (0.0010) -[2023-10-16 06:12:01,801][05219] Updated weights for policy 1, policy_version 86310 (0.0008) -[2023-10-16 06:12:02,168][05219] Updated weights for policy 1, policy_version 86320 (0.0009) -[2023-10-16 06:12:02,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 177045504. Throughput: 0: 1799.0, 1: 1793.7. Samples: 44272344. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-16 06:12:02,351][03835] Avg episode reward: [(0, '7.950'), (1, '8.430')] -[2023-10-16 06:12:02,531][05219] Updated weights for policy 1, policy_version 86330 (0.0008) -[2023-10-16 06:12:04,812][05218] Updated weights for policy 0, policy_version 86602 (0.0009) -[2023-10-16 06:12:05,180][05218] Updated weights for policy 0, policy_version 86612 (0.0009) -[2023-10-16 06:12:05,559][05218] Updated weights for policy 0, policy_version 86622 (0.0011) -[2023-10-16 06:12:06,264][05219] Updated weights for policy 1, policy_version 86340 (0.0009) -[2023-10-16 06:12:06,626][05219] Updated weights for policy 1, policy_version 86350 (0.0010) -[2023-10-16 06:12:06,987][05219] Updated weights for policy 1, policy_version 86360 (0.0011) -[2023-10-16 06:12:07,351][03835] Fps is (10 sec: 16383.4, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 177143808. Throughput: 0: 1803.9, 1: 1787.3. Samples: 44293632. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-16 06:12:07,352][03835] Avg episode reward: [(0, '7.210'), (1, '8.420')] -[2023-10-16 06:12:09,276][05218] Updated weights for policy 0, policy_version 86632 (0.0008) -[2023-10-16 06:12:09,644][05218] Updated weights for policy 0, policy_version 86642 (0.0009) -[2023-10-16 06:12:10,023][05218] Updated weights for policy 0, policy_version 86652 (0.0008) -[2023-10-16 06:12:10,860][05219] Updated weights for policy 1, policy_version 86370 (0.0009) -[2023-10-16 06:12:11,231][05219] Updated weights for policy 1, policy_version 86380 (0.0009) -[2023-10-16 06:12:11,598][05219] Updated weights for policy 1, policy_version 86390 (0.0008) -[2023-10-16 06:12:11,965][05219] Updated weights for policy 1, policy_version 86400 (0.0009) -[2023-10-16 06:12:12,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 177209344. Throughput: 0: 1801.7, 1: 1782.5. Samples: 44304540. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-16 06:12:12,351][03835] Avg episode reward: [(0, '6.830'), (1, '7.580')] -[2023-10-16 06:12:13,686][05218] Updated weights for policy 0, policy_version 86662 (0.0007) -[2023-10-16 06:12:14,061][05218] Updated weights for policy 0, policy_version 86672 (0.0007) -[2023-10-16 06:12:14,438][05218] Updated weights for policy 0, policy_version 86682 (0.0007) -[2023-10-16 06:12:15,689][05219] Updated weights for policy 1, policy_version 86410 (0.0007) -[2023-10-16 06:12:16,053][05219] Updated weights for policy 1, policy_version 86420 (0.0007) -[2023-10-16 06:12:16,409][05219] Updated weights for policy 1, policy_version 86430 (0.0007) -[2023-10-16 06:12:17,350][03835] Fps is (10 sec: 13107.8, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 177274880. Throughput: 0: 1804.0, 1: 1790.0. Samples: 44326354. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-16 06:12:17,351][03835] Avg episode reward: [(0, '7.230'), (1, '8.460')] -[2023-10-16 06:12:18,007][05218] Updated weights for policy 0, policy_version 86692 (0.0007) -[2023-10-16 06:12:18,376][05218] Updated weights for policy 0, policy_version 86702 (0.0009) -[2023-10-16 06:12:18,755][05218] Updated weights for policy 0, policy_version 86712 (0.0008) -[2023-10-16 06:12:20,099][05219] Updated weights for policy 1, policy_version 86440 (0.0008) -[2023-10-16 06:12:20,457][05219] Updated weights for policy 1, policy_version 86450 (0.0007) -[2023-10-16 06:12:20,829][05219] Updated weights for policy 1, policy_version 86460 (0.0009) -[2023-10-16 06:12:22,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 177340416. Throughput: 0: 1813.7, 1: 1783.5. Samples: 44348570. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-16 06:12:22,351][03835] Avg episode reward: [(0, '6.160'), (1, '8.480')] -[2023-10-16 06:12:22,598][05218] Updated weights for policy 0, policy_version 86722 (0.0008) -[2023-10-16 06:12:22,975][05218] Updated weights for policy 0, policy_version 86732 (0.0008) -[2023-10-16 06:12:23,350][05218] Updated weights for policy 0, policy_version 86742 (0.0011) -[2023-10-16 06:12:23,734][05218] Updated weights for policy 0, policy_version 86752 (0.0009) -[2023-10-16 06:12:24,598][05219] Updated weights for policy 1, policy_version 86470 (0.0008) -[2023-10-16 06:12:24,964][05219] Updated weights for policy 1, policy_version 86480 (0.0011) -[2023-10-16 06:12:25,327][05219] Updated weights for policy 1, policy_version 86490 (0.0010) -[2023-10-16 06:12:27,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 177405952. Throughput: 0: 1802.7, 1: 1795.6. Samples: 44358862. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-16 06:12:27,351][03835] Avg episode reward: [(0, '6.810'), (1, '8.000')] -[2023-10-16 06:12:27,370][05218] Updated weights for policy 0, policy_version 86762 (0.0010) -[2023-10-16 06:12:27,753][05218] Updated weights for policy 0, policy_version 86772 (0.0007) -[2023-10-16 06:12:28,121][05218] Updated weights for policy 0, policy_version 86782 (0.0008) -[2023-10-16 06:12:29,000][05219] Updated weights for policy 1, policy_version 86500 (0.0009) -[2023-10-16 06:12:29,371][05219] Updated weights for policy 1, policy_version 86510 (0.0007) -[2023-10-16 06:12:29,732][05219] Updated weights for policy 1, policy_version 86520 (0.0011) -[2023-10-16 06:12:31,881][05218] Updated weights for policy 0, policy_version 86792 (0.0009) -[2023-10-16 06:12:32,260][05218] Updated weights for policy 0, policy_version 86802 (0.0008) -[2023-10-16 06:12:32,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 177471488. Throughput: 0: 1811.7, 1: 1788.4. Samples: 44380886. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-16 06:12:32,351][03835] Avg episode reward: [(0, '7.190'), (1, '8.170')] -[2023-10-16 06:12:32,639][05218] Updated weights for policy 0, policy_version 86812 (0.0008) -[2023-10-16 06:12:33,496][05219] Updated weights for policy 1, policy_version 86530 (0.0008) -[2023-10-16 06:12:33,869][05219] Updated weights for policy 1, policy_version 86540 (0.0008) -[2023-10-16 06:12:34,234][05219] Updated weights for policy 1, policy_version 86550 (0.0007) -[2023-10-16 06:12:34,595][05219] Updated weights for policy 1, policy_version 86560 (0.0010) -[2023-10-16 06:12:36,436][05218] Updated weights for policy 0, policy_version 86822 (0.0009) -[2023-10-16 06:12:36,824][05218] Updated weights for policy 0, policy_version 86832 (0.0010) -[2023-10-16 06:12:37,200][05218] Updated weights for policy 0, policy_version 86842 (0.0009) -[2023-10-16 06:12:37,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 177537024. Throughput: 0: 1812.7, 1: 1793.9. Samples: 44402018. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-16 06:12:37,351][03835] Avg episode reward: [(0, '6.730'), (1, '8.310')] -[2023-10-16 06:12:38,477][05219] Updated weights for policy 1, policy_version 86570 (0.0011) -[2023-10-16 06:12:38,842][05219] Updated weights for policy 1, policy_version 86580 (0.0010) -[2023-10-16 06:12:39,199][05219] Updated weights for policy 1, policy_version 86590 (0.0010) -[2023-10-16 06:12:40,711][05218] Updated weights for policy 0, policy_version 86852 (0.0009) -[2023-10-16 06:12:41,091][05218] Updated weights for policy 0, policy_version 86862 (0.0008) -[2023-10-16 06:12:41,458][05218] Updated weights for policy 0, policy_version 86872 (0.0009) -[2023-10-16 06:12:42,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 177635328. Throughput: 0: 1811.6, 1: 1791.2. Samples: 44413262. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-16 06:12:42,351][03835] Avg episode reward: [(0, '8.310'), (1, '7.960')] -[2023-10-16 06:12:42,994][05219] Updated weights for policy 1, policy_version 86600 (0.0009) -[2023-10-16 06:12:43,362][05219] Updated weights for policy 1, policy_version 86610 (0.0008) -[2023-10-16 06:12:43,739][05219] Updated weights for policy 1, policy_version 86620 (0.0009) -[2023-10-16 06:12:45,148][05218] Updated weights for policy 0, policy_version 86882 (0.0007) -[2023-10-16 06:12:45,516][05218] Updated weights for policy 0, policy_version 86892 (0.0011) -[2023-10-16 06:12:45,903][05218] Updated weights for policy 0, policy_version 86902 (0.0010) -[2023-10-16 06:12:46,276][05218] Updated weights for policy 0, policy_version 86912 (0.0011) -[2023-10-16 06:12:47,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 177700864. Throughput: 0: 1808.8, 1: 1785.4. Samples: 44434082. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-16 06:12:47,351][03835] Avg episode reward: [(0, '7.510'), (1, '7.660')] -[2023-10-16 06:12:47,552][05219] Updated weights for policy 1, policy_version 86630 (0.0009) -[2023-10-16 06:12:47,928][05219] Updated weights for policy 1, policy_version 86640 (0.0007) -[2023-10-16 06:12:48,296][05219] Updated weights for policy 1, policy_version 86650 (0.0009) -[2023-10-16 06:12:50,092][05218] Updated weights for policy 0, policy_version 86922 (0.0007) -[2023-10-16 06:12:50,468][05218] Updated weights for policy 0, policy_version 86932 (0.0007) -[2023-10-16 06:12:50,841][05218] Updated weights for policy 0, policy_version 86942 (0.0011) -[2023-10-16 06:12:52,152][05219] Updated weights for policy 1, policy_version 86660 (0.0010) -[2023-10-16 06:12:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 177766400. Throughput: 0: 1806.5, 1: 1809.7. Samples: 44456356. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-16 06:12:52,351][03835] Avg episode reward: [(0, '7.870'), (1, '8.720')] -[2023-10-16 06:12:52,516][05219] Updated weights for policy 1, policy_version 86670 (0.0008) -[2023-10-16 06:12:52,883][05219] Updated weights for policy 1, policy_version 86680 (0.0009) -[2023-10-16 06:12:54,449][05218] Updated weights for policy 0, policy_version 86952 (0.0011) -[2023-10-16 06:12:54,828][05218] Updated weights for policy 0, policy_version 86962 (0.0007) -[2023-10-16 06:12:55,202][05218] Updated weights for policy 0, policy_version 86972 (0.0009) -[2023-10-16 06:12:56,751][05219] Updated weights for policy 1, policy_version 86690 (0.0011) -[2023-10-16 06:12:57,111][05219] Updated weights for policy 1, policy_version 86700 (0.0008) -[2023-10-16 06:12:57,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 177831936. Throughput: 0: 1806.1, 1: 1786.7. Samples: 44466216. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-16 06:12:57,351][03835] Avg episode reward: [(0, '7.860'), (1, '7.750')] -[2023-10-16 06:12:57,473][05219] Updated weights for policy 1, policy_version 86710 (0.0009) -[2023-10-16 06:12:57,844][05219] Updated weights for policy 1, policy_version 86720 (0.0011) -[2023-10-16 06:12:59,002][05218] Updated weights for policy 0, policy_version 86982 (0.0009) -[2023-10-16 06:12:59,380][05218] Updated weights for policy 0, policy_version 86992 (0.0010) -[2023-10-16 06:12:59,764][05218] Updated weights for policy 0, policy_version 87002 (0.0007) -[2023-10-16 06:13:01,565][05219] Updated weights for policy 1, policy_version 86730 (0.0009) -[2023-10-16 06:13:01,936][05219] Updated weights for policy 1, policy_version 86740 (0.0009) -[2023-10-16 06:13:02,306][05219] Updated weights for policy 1, policy_version 86750 (0.0008) -[2023-10-16 06:13:02,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 177897472. Throughput: 0: 1795.2, 1: 1802.8. Samples: 44488262. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-16 06:13:02,351][03835] Avg episode reward: [(0, '6.960'), (1, '8.350')] -[2023-10-16 06:13:03,589][05218] Updated weights for policy 0, policy_version 87012 (0.0008) -[2023-10-16 06:13:03,975][05218] Updated weights for policy 0, policy_version 87022 (0.0007) -[2023-10-16 06:13:04,346][05218] Updated weights for policy 0, policy_version 87032 (0.0008) -[2023-10-16 06:13:06,219][05219] Updated weights for policy 1, policy_version 86760 (0.0008) -[2023-10-16 06:13:06,603][05219] Updated weights for policy 1, policy_version 86770 (0.0008) -[2023-10-16 06:13:06,963][05219] Updated weights for policy 1, policy_version 86780 (0.0009) -[2023-10-16 06:13:07,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.6, 300 sec: 14440.1). Total num frames: 177995776. Throughput: 0: 1790.6, 1: 1777.9. Samples: 44509152. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) -[2023-10-16 06:13:07,351][03835] Avg episode reward: [(0, '7.520'), (1, '8.260')] -[2023-10-16 06:13:08,115][05218] Updated weights for policy 0, policy_version 87042 (0.0008) -[2023-10-16 06:13:08,491][05218] Updated weights for policy 0, policy_version 87052 (0.0011) -[2023-10-16 06:13:08,876][05218] Updated weights for policy 0, policy_version 87062 (0.0007) -[2023-10-16 06:13:09,253][05218] Updated weights for policy 0, policy_version 87072 (0.0007) -[2023-10-16 06:13:10,597][05219] Updated weights for policy 1, policy_version 86790 (0.0008) -[2023-10-16 06:13:10,967][05219] Updated weights for policy 1, policy_version 86800 (0.0010) -[2023-10-16 06:13:11,329][05219] Updated weights for policy 1, policy_version 86810 (0.0010) -[2023-10-16 06:13:12,351][03835] Fps is (10 sec: 16383.4, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 178061312. Throughput: 0: 1787.9, 1: 1801.1. Samples: 44520366. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) -[2023-10-16 06:13:12,352][03835] Avg episode reward: [(0, '8.160'), (1, '7.610')] -[2023-10-16 06:13:13,056][05218] Updated weights for policy 0, policy_version 87082 (0.0009) -[2023-10-16 06:13:13,438][05218] Updated weights for policy 0, policy_version 87092 (0.0009) -[2023-10-16 06:13:13,810][05218] Updated weights for policy 0, policy_version 87102 (0.0008) -[2023-10-16 06:13:15,162][05219] Updated weights for policy 1, policy_version 86820 (0.0010) -[2023-10-16 06:13:15,524][05219] Updated weights for policy 1, policy_version 86830 (0.0008) -[2023-10-16 06:13:15,896][05219] Updated weights for policy 1, policy_version 86840 (0.0009) -[2023-10-16 06:13:17,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 178126848. Throughput: 0: 1783.9, 1: 1785.0. Samples: 44541486. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) -[2023-10-16 06:13:17,351][03835] Avg episode reward: [(0, '8.100'), (1, '8.470')] -[2023-10-16 06:13:17,509][05218] Updated weights for policy 0, policy_version 87112 (0.0007) -[2023-10-16 06:13:17,885][05218] Updated weights for policy 0, policy_version 87122 (0.0007) -[2023-10-16 06:13:18,266][05218] Updated weights for policy 0, policy_version 87132 (0.0007) -[2023-10-16 06:13:19,652][05219] Updated weights for policy 1, policy_version 86850 (0.0008) -[2023-10-16 06:13:20,013][05219] Updated weights for policy 1, policy_version 86860 (0.0007) -[2023-10-16 06:13:20,392][05219] Updated weights for policy 1, policy_version 86870 (0.0007) -[2023-10-16 06:13:20,751][05219] Updated weights for policy 1, policy_version 86880 (0.0009) -[2023-10-16 06:13:22,079][05218] Updated weights for policy 0, policy_version 87142 (0.0008) -[2023-10-16 06:13:22,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 178192384. Throughput: 0: 1799.8, 1: 1778.0. Samples: 44563018. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) -[2023-10-16 06:13:22,351][03835] Avg episode reward: [(0, '7.210'), (1, '7.950')] -[2023-10-16 06:13:22,453][05218] Updated weights for policy 0, policy_version 87152 (0.0010) -[2023-10-16 06:13:22,829][05218] Updated weights for policy 0, policy_version 87162 (0.0008) -[2023-10-16 06:13:24,555][05219] Updated weights for policy 1, policy_version 86890 (0.0007) -[2023-10-16 06:13:24,927][05219] Updated weights for policy 1, policy_version 86900 (0.0010) -[2023-10-16 06:13:25,288][05219] Updated weights for policy 1, policy_version 86910 (0.0011) -[2023-10-16 06:13:26,517][05218] Updated weights for policy 0, policy_version 87172 (0.0009) -[2023-10-16 06:13:26,902][05218] Updated weights for policy 0, policy_version 87182 (0.0008) -[2023-10-16 06:13:27,269][05218] Updated weights for policy 0, policy_version 87192 (0.0010) -[2023-10-16 06:13:27,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 178257920. Throughput: 0: 1776.5, 1: 1786.0. Samples: 44573574. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) -[2023-10-16 06:13:27,351][03835] Avg episode reward: [(0, '6.890'), (1, '8.570')] -[2023-10-16 06:13:28,914][05219] Updated weights for policy 1, policy_version 86920 (0.0007) -[2023-10-16 06:13:29,274][05219] Updated weights for policy 1, policy_version 86930 (0.0008) -[2023-10-16 06:13:29,642][05219] Updated weights for policy 1, policy_version 86940 (0.0009) -[2023-10-16 06:13:31,073][05218] Updated weights for policy 0, policy_version 87202 (0.0007) -[2023-10-16 06:13:31,451][05218] Updated weights for policy 0, policy_version 87212 (0.0008) -[2023-10-16 06:13:31,815][05218] Updated weights for policy 0, policy_version 87222 (0.0009) -[2023-10-16 06:13:32,187][05218] Updated weights for policy 0, policy_version 87232 (0.0009) -[2023-10-16 06:13:32,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 178356224. Throughput: 0: 1800.3, 1: 1775.5. Samples: 44594996. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) -[2023-10-16 06:13:32,351][03835] Avg episode reward: [(0, '7.520'), (1, '7.910')] -[2023-10-16 06:13:33,318][05219] Updated weights for policy 1, policy_version 86950 (0.0010) -[2023-10-16 06:13:33,682][05219] Updated weights for policy 1, policy_version 86960 (0.0008) -[2023-10-16 06:13:34,053][05219] Updated weights for policy 1, policy_version 86970 (0.0011) -[2023-10-16 06:13:36,009][05218] Updated weights for policy 0, policy_version 87242 (0.0009) -[2023-10-16 06:13:36,381][05218] Updated weights for policy 0, policy_version 87252 (0.0011) -[2023-10-16 06:13:36,751][05218] Updated weights for policy 0, policy_version 87262 (0.0010) -[2023-10-16 06:13:37,351][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 178421760. Throughput: 0: 1775.3, 1: 1785.2. Samples: 44616580. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) -[2023-10-16 06:13:37,352][03835] Avg episode reward: [(0, '6.690'), (1, '7.640')] -[2023-10-16 06:13:37,361][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000087264_89358336.pth... -[2023-10-16 06:13:37,361][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000086976_89063424.pth... -[2023-10-16 06:13:37,392][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000085568_87621632.pth -[2023-10-16 06:13:37,400][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000085312_87359488.pth -[2023-10-16 06:13:37,823][05219] Updated weights for policy 1, policy_version 86980 (0.0010) -[2023-10-16 06:13:38,186][05219] Updated weights for policy 1, policy_version 86990 (0.0009) -[2023-10-16 06:13:38,554][05219] Updated weights for policy 1, policy_version 87000 (0.0007) -[2023-10-16 06:13:40,561][05218] Updated weights for policy 0, policy_version 87272 (0.0010) -[2023-10-16 06:13:40,942][05218] Updated weights for policy 0, policy_version 87282 (0.0010) -[2023-10-16 06:13:41,319][05218] Updated weights for policy 0, policy_version 87292 (0.0010) -[2023-10-16 06:13:42,234][05219] Updated weights for policy 1, policy_version 87010 (0.0008) -[2023-10-16 06:13:42,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 178487296. Throughput: 0: 1803.2, 1: 1785.2. Samples: 44627692. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) -[2023-10-16 06:13:42,351][03835] Avg episode reward: [(0, '7.170'), (1, '8.320')] -[2023-10-16 06:13:42,613][05219] Updated weights for policy 1, policy_version 87020 (0.0009) -[2023-10-16 06:13:42,982][05219] Updated weights for policy 1, policy_version 87030 (0.0008) -[2023-10-16 06:13:43,356][05219] Updated weights for policy 1, policy_version 87040 (0.0007) -[2023-10-16 06:13:44,994][05218] Updated weights for policy 0, policy_version 87302 (0.0009) -[2023-10-16 06:13:45,384][05218] Updated weights for policy 0, policy_version 87312 (0.0009) -[2023-10-16 06:13:45,750][05218] Updated weights for policy 0, policy_version 87322 (0.0009) -[2023-10-16 06:13:47,216][05219] Updated weights for policy 1, policy_version 87050 (0.0009) -[2023-10-16 06:13:47,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 178552832. Throughput: 0: 1782.2, 1: 1785.7. Samples: 44648818. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) -[2023-10-16 06:13:47,351][03835] Avg episode reward: [(0, '7.280'), (1, '7.970')] -[2023-10-16 06:13:47,572][05219] Updated weights for policy 1, policy_version 87060 (0.0009) -[2023-10-16 06:13:47,941][05219] Updated weights for policy 1, policy_version 87070 (0.0008) -[2023-10-16 06:13:49,248][05218] Updated weights for policy 0, policy_version 87332 (0.0010) -[2023-10-16 06:13:49,628][05218] Updated weights for policy 0, policy_version 87342 (0.0011) -[2023-10-16 06:13:49,996][05218] Updated weights for policy 0, policy_version 87352 (0.0008) -[2023-10-16 06:13:51,698][05219] Updated weights for policy 1, policy_version 87080 (0.0009) -[2023-10-16 06:13:52,074][05219] Updated weights for policy 1, policy_version 87090 (0.0009) -[2023-10-16 06:13:52,351][03835] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 178618368. Throughput: 0: 1789.5, 1: 1795.4. Samples: 44670470. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) -[2023-10-16 06:13:52,352][03835] Avg episode reward: [(0, '7.310'), (1, '8.440')] -[2023-10-16 06:13:52,446][05219] Updated weights for policy 1, policy_version 87100 (0.0007) -[2023-10-16 06:13:53,761][05218] Updated weights for policy 0, policy_version 87362 (0.0007) -[2023-10-16 06:13:54,141][05218] Updated weights for policy 0, policy_version 87372 (0.0009) -[2023-10-16 06:13:54,512][05218] Updated weights for policy 0, policy_version 87382 (0.0008) -[2023-10-16 06:13:54,880][05218] Updated weights for policy 0, policy_version 87392 (0.0008) -[2023-10-16 06:13:56,301][05219] Updated weights for policy 1, policy_version 87110 (0.0007) -[2023-10-16 06:13:56,666][05219] Updated weights for policy 1, policy_version 87120 (0.0009) -[2023-10-16 06:13:57,032][05219] Updated weights for policy 1, policy_version 87130 (0.0010) -[2023-10-16 06:13:57,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 178716672. Throughput: 0: 1790.1, 1: 1780.8. Samples: 44681058. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) -[2023-10-16 06:13:57,351][03835] Avg episode reward: [(0, '7.860'), (1, '7.630')] -[2023-10-16 06:13:58,659][05218] Updated weights for policy 0, policy_version 87402 (0.0008) -[2023-10-16 06:13:59,049][05218] Updated weights for policy 0, policy_version 87412 (0.0007) -[2023-10-16 06:13:59,419][05218] Updated weights for policy 0, policy_version 87422 (0.0007) -[2023-10-16 06:14:00,857][05219] Updated weights for policy 1, policy_version 87140 (0.0008) -[2023-10-16 06:14:01,222][05219] Updated weights for policy 1, policy_version 87150 (0.0008) -[2023-10-16 06:14:01,591][05219] Updated weights for policy 1, policy_version 87160 (0.0008) -[2023-10-16 06:14:02,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 178782208. Throughput: 0: 1791.4, 1: 1794.9. Samples: 44702870. Policy #0 lag: (min: 17.0, avg: 28.0, max: 49.0) -[2023-10-16 06:14:02,351][03835] Avg episode reward: [(0, '7.170'), (1, '8.220')] -[2023-10-16 06:14:03,035][05218] Updated weights for policy 0, policy_version 87432 (0.0007) -[2023-10-16 06:14:03,406][05218] Updated weights for policy 0, policy_version 87442 (0.0007) -[2023-10-16 06:14:03,782][05218] Updated weights for policy 0, policy_version 87452 (0.0008) -[2023-10-16 06:14:05,370][05219] Updated weights for policy 1, policy_version 87170 (0.0007) -[2023-10-16 06:14:05,732][05219] Updated weights for policy 1, policy_version 87180 (0.0009) -[2023-10-16 06:14:06,102][05219] Updated weights for policy 1, policy_version 87190 (0.0009) -[2023-10-16 06:14:06,468][05219] Updated weights for policy 1, policy_version 87200 (0.0007) -[2023-10-16 06:14:07,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 178847744. Throughput: 0: 1809.4, 1: 1772.8. Samples: 44724218. Policy #0 lag: (min: 17.0, avg: 28.0, max: 49.0) -[2023-10-16 06:14:07,351][03835] Avg episode reward: [(0, '7.610'), (1, '7.950')] -[2023-10-16 06:14:07,544][05218] Updated weights for policy 0, policy_version 87462 (0.0008) -[2023-10-16 06:14:07,933][05218] Updated weights for policy 0, policy_version 87472 (0.0008) -[2023-10-16 06:14:08,308][05218] Updated weights for policy 0, policy_version 87482 (0.0007) -[2023-10-16 06:14:10,248][05219] Updated weights for policy 1, policy_version 87210 (0.0008) -[2023-10-16 06:14:10,612][05219] Updated weights for policy 1, policy_version 87220 (0.0009) -[2023-10-16 06:14:10,985][05219] Updated weights for policy 1, policy_version 87230 (0.0011) -[2023-10-16 06:14:11,887][05218] Updated weights for policy 0, policy_version 87492 (0.0008) -[2023-10-16 06:14:12,258][05218] Updated weights for policy 0, policy_version 87502 (0.0009) -[2023-10-16 06:14:12,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 178913280. Throughput: 0: 1798.9, 1: 1796.5. Samples: 44735370. Policy #0 lag: (min: 17.0, avg: 28.0, max: 49.0) -[2023-10-16 06:14:12,351][03835] Avg episode reward: [(0, '7.650'), (1, '9.030')] -[2023-10-16 06:14:12,635][05218] Updated weights for policy 0, policy_version 87512 (0.0008) -[2023-10-16 06:14:14,926][05219] Updated weights for policy 1, policy_version 87240 (0.0008) -[2023-10-16 06:14:15,284][05219] Updated weights for policy 1, policy_version 87250 (0.0009) -[2023-10-16 06:14:15,652][05219] Updated weights for policy 1, policy_version 87260 (0.0009) -[2023-10-16 06:14:16,347][05218] Updated weights for policy 0, policy_version 87522 (0.0009) -[2023-10-16 06:14:16,722][05218] Updated weights for policy 0, policy_version 87532 (0.0008) -[2023-10-16 06:14:17,088][05218] Updated weights for policy 0, policy_version 87542 (0.0007) -[2023-10-16 06:14:17,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 178978816. Throughput: 0: 1811.5, 1: 1777.8. Samples: 44756512. Policy #0 lag: (min: 17.0, avg: 28.0, max: 49.0) -[2023-10-16 06:14:17,351][03835] Avg episode reward: [(0, '7.700'), (1, '9.810')] -[2023-10-16 06:14:17,352][04891] Saving new best policy, reward=9.810! -[2023-10-16 06:14:17,472][05218] Updated weights for policy 0, policy_version 87552 (0.0007) -[2023-10-16 06:14:19,419][05219] Updated weights for policy 1, policy_version 87270 (0.0010) -[2023-10-16 06:14:19,770][05219] Updated weights for policy 1, policy_version 87280 (0.0008) -[2023-10-16 06:14:20,141][05219] Updated weights for policy 1, policy_version 87290 (0.0008) -[2023-10-16 06:14:21,166][05218] Updated weights for policy 0, policy_version 87562 (0.0010) -[2023-10-16 06:14:21,539][05218] Updated weights for policy 0, policy_version 87572 (0.0007) -[2023-10-16 06:14:21,914][05218] Updated weights for policy 0, policy_version 87582 (0.0008) -[2023-10-16 06:14:22,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 179077120. Throughput: 0: 1808.2, 1: 1774.1. Samples: 44777786. Policy #0 lag: (min: 17.0, avg: 28.0, max: 49.0) -[2023-10-16 06:14:22,351][03835] Avg episode reward: [(0, '8.070'), (1, '7.460')] -[2023-10-16 06:14:23,982][05219] Updated weights for policy 1, policy_version 87300 (0.0009) -[2023-10-16 06:14:24,354][05219] Updated weights for policy 1, policy_version 87310 (0.0008) -[2023-10-16 06:14:24,718][05219] Updated weights for policy 1, policy_version 87320 (0.0008) -[2023-10-16 06:14:25,614][05218] Updated weights for policy 0, policy_version 87592 (0.0008) -[2023-10-16 06:14:25,987][05218] Updated weights for policy 0, policy_version 87602 (0.0008) -[2023-10-16 06:14:26,362][05218] Updated weights for policy 0, policy_version 87612 (0.0007) -[2023-10-16 06:14:27,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 179142656. Throughput: 0: 1817.9, 1: 1770.5. Samples: 44789172. Policy #0 lag: (min: 17.0, avg: 28.0, max: 49.0) -[2023-10-16 06:14:27,351][03835] Avg episode reward: [(0, '7.780'), (1, '8.220')] -[2023-10-16 06:14:28,370][05219] Updated weights for policy 1, policy_version 87330 (0.0008) -[2023-10-16 06:14:28,739][05219] Updated weights for policy 1, policy_version 87340 (0.0007) -[2023-10-16 06:14:29,096][05219] Updated weights for policy 1, policy_version 87350 (0.0008) -[2023-10-16 06:14:29,459][05219] Updated weights for policy 1, policy_version 87360 (0.0008) -[2023-10-16 06:14:30,099][05218] Updated weights for policy 0, policy_version 87622 (0.0007) -[2023-10-16 06:14:30,466][05218] Updated weights for policy 0, policy_version 87632 (0.0007) -[2023-10-16 06:14:30,847][05218] Updated weights for policy 0, policy_version 87642 (0.0007) -[2023-10-16 06:14:32,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 179208192. Throughput: 0: 1815.6, 1: 1778.8. Samples: 44810562. Policy #0 lag: (min: 17.0, avg: 28.0, max: 49.0) -[2023-10-16 06:14:32,351][03835] Avg episode reward: [(0, '7.550'), (1, '8.600')] -[2023-10-16 06:14:33,263][05219] Updated weights for policy 1, policy_version 87370 (0.0009) -[2023-10-16 06:14:33,626][05219] Updated weights for policy 1, policy_version 87380 (0.0008) -[2023-10-16 06:14:33,996][05219] Updated weights for policy 1, policy_version 87390 (0.0007) -[2023-10-16 06:14:34,553][05218] Updated weights for policy 0, policy_version 87652 (0.0007) -[2023-10-16 06:14:34,928][05218] Updated weights for policy 0, policy_version 87662 (0.0007) -[2023-10-16 06:14:35,308][05218] Updated weights for policy 0, policy_version 87672 (0.0007) -[2023-10-16 06:14:37,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 179273728. Throughput: 0: 1810.9, 1: 1803.7. Samples: 44833130. Policy #0 lag: (min: 17.0, avg: 28.0, max: 49.0) -[2023-10-16 06:14:37,351][03835] Avg episode reward: [(0, '7.190'), (1, '7.230')] -[2023-10-16 06:14:37,822][05219] Updated weights for policy 1, policy_version 87400 (0.0008) -[2023-10-16 06:14:38,201][05219] Updated weights for policy 1, policy_version 87410 (0.0008) -[2023-10-16 06:14:38,571][05219] Updated weights for policy 1, policy_version 87420 (0.0009) -[2023-10-16 06:14:38,877][05218] Updated weights for policy 0, policy_version 87682 (0.0008) -[2023-10-16 06:14:39,243][05218] Updated weights for policy 0, policy_version 87692 (0.0011) -[2023-10-16 06:14:39,619][05218] Updated weights for policy 0, policy_version 87702 (0.0010) -[2023-10-16 06:14:40,000][05218] Updated weights for policy 0, policy_version 87712 (0.0010) -[2023-10-16 06:14:42,273][05219] Updated weights for policy 1, policy_version 87430 (0.0008) -[2023-10-16 06:14:42,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 179339264. Throughput: 0: 1813.2, 1: 1780.9. Samples: 44842794. Policy #0 lag: (min: 17.0, avg: 28.0, max: 49.0) -[2023-10-16 06:14:42,351][03835] Avg episode reward: [(0, '7.320'), (1, '8.000')] -[2023-10-16 06:14:42,647][05219] Updated weights for policy 1, policy_version 87440 (0.0008) -[2023-10-16 06:14:43,018][05219] Updated weights for policy 1, policy_version 87450 (0.0009) -[2023-10-16 06:14:43,725][05218] Updated weights for policy 0, policy_version 87722 (0.0007) -[2023-10-16 06:14:44,103][05218] Updated weights for policy 0, policy_version 87732 (0.0007) -[2023-10-16 06:14:44,480][05218] Updated weights for policy 0, policy_version 87742 (0.0009) -[2023-10-16 06:14:46,646][05219] Updated weights for policy 1, policy_version 87460 (0.0008) -[2023-10-16 06:14:47,013][05219] Updated weights for policy 1, policy_version 87470 (0.0008) -[2023-10-16 06:14:47,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 179404800. Throughput: 0: 1812.8, 1: 1795.0. Samples: 44865220. Policy #0 lag: (min: 17.0, avg: 28.0, max: 49.0) -[2023-10-16 06:14:47,351][03835] Avg episode reward: [(0, '7.840'), (1, '8.770')] -[2023-10-16 06:14:47,374][05219] Updated weights for policy 1, policy_version 87480 (0.0008) -[2023-10-16 06:14:48,108][05218] Updated weights for policy 0, policy_version 87752 (0.0010) -[2023-10-16 06:14:48,479][05218] Updated weights for policy 0, policy_version 87762 (0.0008) -[2023-10-16 06:14:48,859][05218] Updated weights for policy 0, policy_version 87772 (0.0009) -[2023-10-16 06:14:51,030][05219] Updated weights for policy 1, policy_version 87490 (0.0007) -[2023-10-16 06:14:51,405][05219] Updated weights for policy 1, policy_version 87500 (0.0008) -[2023-10-16 06:14:51,766][05219] Updated weights for policy 1, policy_version 87510 (0.0009) -[2023-10-16 06:14:52,137][05219] Updated weights for policy 1, policy_version 87520 (0.0009) -[2023-10-16 06:14:52,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 179503104. Throughput: 0: 1818.0, 1: 1790.9. Samples: 44886622. Policy #0 lag: (min: 17.0, avg: 28.0, max: 49.0) -[2023-10-16 06:14:52,351][03835] Avg episode reward: [(0, '8.070'), (1, '8.510')] -[2023-10-16 06:14:52,777][05218] Updated weights for policy 0, policy_version 87782 (0.0010) -[2023-10-16 06:14:53,158][05218] Updated weights for policy 0, policy_version 87792 (0.0008) -[2023-10-16 06:14:53,532][05218] Updated weights for policy 0, policy_version 87802 (0.0007) -[2023-10-16 06:14:56,070][05219] Updated weights for policy 1, policy_version 87530 (0.0008) -[2023-10-16 06:14:56,436][05219] Updated weights for policy 1, policy_version 87540 (0.0008) -[2023-10-16 06:14:56,816][05219] Updated weights for policy 1, policy_version 87550 (0.0010) -[2023-10-16 06:14:57,095][05218] Updated weights for policy 0, policy_version 87812 (0.0008) -[2023-10-16 06:14:57,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 179568640. Throughput: 0: 1815.9, 1: 1791.5. Samples: 44897702. Policy #0 lag: (min: 31.0, avg: 32.3, max: 56.0) -[2023-10-16 06:14:57,351][03835] Avg episode reward: [(0, '7.370'), (1, '9.040')] -[2023-10-16 06:14:57,482][05218] Updated weights for policy 0, policy_version 87822 (0.0008) -[2023-10-16 06:14:57,850][05218] Updated weights for policy 0, policy_version 87832 (0.0009) -[2023-10-16 06:15:00,681][05219] Updated weights for policy 1, policy_version 87560 (0.0009) -[2023-10-16 06:15:01,050][05219] Updated weights for policy 1, policy_version 87570 (0.0008) -[2023-10-16 06:15:01,424][05219] Updated weights for policy 1, policy_version 87580 (0.0008) -[2023-10-16 06:15:01,571][05218] Updated weights for policy 0, policy_version 87842 (0.0008) -[2023-10-16 06:15:01,938][05218] Updated weights for policy 0, policy_version 87852 (0.0009) -[2023-10-16 06:15:02,320][05218] Updated weights for policy 0, policy_version 87862 (0.0009) -[2023-10-16 06:15:02,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 179634176. Throughput: 0: 1817.9, 1: 1801.1. Samples: 44919364. Policy #0 lag: (min: 31.0, avg: 32.3, max: 56.0) -[2023-10-16 06:15:02,351][03835] Avg episode reward: [(0, '7.920'), (1, '8.600')] -[2023-10-16 06:15:02,692][05218] Updated weights for policy 0, policy_version 87872 (0.0010) -[2023-10-16 06:15:05,130][05219] Updated weights for policy 1, policy_version 87590 (0.0008) -[2023-10-16 06:15:05,499][05219] Updated weights for policy 1, policy_version 87600 (0.0009) -[2023-10-16 06:15:05,851][05219] Updated weights for policy 1, policy_version 87610 (0.0009) -[2023-10-16 06:15:06,510][05218] Updated weights for policy 0, policy_version 87882 (0.0007) -[2023-10-16 06:15:06,892][05218] Updated weights for policy 0, policy_version 87892 (0.0009) -[2023-10-16 06:15:07,267][05218] Updated weights for policy 0, policy_version 87902 (0.0010) -[2023-10-16 06:15:07,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 179732480. Throughput: 0: 1809.8, 1: 1793.6. Samples: 44939940. Policy #0 lag: (min: 31.0, avg: 32.3, max: 56.0) -[2023-10-16 06:15:07,351][03835] Avg episode reward: [(0, '8.110'), (1, '8.640')] -[2023-10-16 06:15:09,315][05219] Updated weights for policy 1, policy_version 87620 (0.0010) -[2023-10-16 06:15:09,689][05219] Updated weights for policy 1, policy_version 87630 (0.0010) -[2023-10-16 06:15:10,042][05219] Updated weights for policy 1, policy_version 87640 (0.0008) -[2023-10-16 06:15:10,942][05218] Updated weights for policy 0, policy_version 87912 (0.0008) -[2023-10-16 06:15:11,323][05218] Updated weights for policy 0, policy_version 87922 (0.0009) -[2023-10-16 06:15:11,692][05218] Updated weights for policy 0, policy_version 87932 (0.0009) -[2023-10-16 06:15:12,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 179798016. Throughput: 0: 1806.8, 1: 1806.9. Samples: 44951786. Policy #0 lag: (min: 31.0, avg: 32.3, max: 56.0) -[2023-10-16 06:15:12,351][03835] Avg episode reward: [(0, '7.930'), (1, '8.130')] -[2023-10-16 06:15:13,868][05219] Updated weights for policy 1, policy_version 87650 (0.0010) -[2023-10-16 06:15:14,239][05219] Updated weights for policy 1, policy_version 87660 (0.0010) -[2023-10-16 06:15:14,616][05219] Updated weights for policy 1, policy_version 87670 (0.0011) -[2023-10-16 06:15:14,980][05219] Updated weights for policy 1, policy_version 87680 (0.0010) -[2023-10-16 06:15:15,356][05218] Updated weights for policy 0, policy_version 87942 (0.0009) -[2023-10-16 06:15:15,726][05218] Updated weights for policy 0, policy_version 87952 (0.0008) -[2023-10-16 06:15:16,113][05218] Updated weights for policy 0, policy_version 87962 (0.0009) -[2023-10-16 06:15:17,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 179863552. Throughput: 0: 1806.5, 1: 1792.0. Samples: 44972498. Policy #0 lag: (min: 31.0, avg: 32.3, max: 56.0) -[2023-10-16 06:15:17,351][03835] Avg episode reward: [(0, '7.970'), (1, '7.830')] -[2023-10-16 06:15:18,701][05219] Updated weights for policy 1, policy_version 87690 (0.0007) -[2023-10-16 06:15:19,067][05219] Updated weights for policy 1, policy_version 87700 (0.0008) -[2023-10-16 06:15:19,430][05219] Updated weights for policy 1, policy_version 87710 (0.0007) -[2023-10-16 06:15:19,889][05218] Updated weights for policy 0, policy_version 87972 (0.0008) -[2023-10-16 06:15:20,263][05218] Updated weights for policy 0, policy_version 87982 (0.0010) -[2023-10-16 06:15:20,640][05218] Updated weights for policy 0, policy_version 87992 (0.0010) -[2023-10-16 06:15:22,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 179929088. Throughput: 0: 1799.7, 1: 1792.9. Samples: 44994796. Policy #0 lag: (min: 31.0, avg: 32.3, max: 56.0) -[2023-10-16 06:15:22,351][03835] Avg episode reward: [(0, '7.100'), (1, '8.450')] -[2023-10-16 06:15:23,240][05219] Updated weights for policy 1, policy_version 87720 (0.0010) -[2023-10-16 06:15:23,605][05219] Updated weights for policy 1, policy_version 87730 (0.0011) -[2023-10-16 06:15:23,972][05219] Updated weights for policy 1, policy_version 87740 (0.0011) -[2023-10-16 06:15:24,460][05218] Updated weights for policy 0, policy_version 88002 (0.0010) -[2023-10-16 06:15:24,837][05218] Updated weights for policy 0, policy_version 88012 (0.0009) -[2023-10-16 06:15:25,223][05218] Updated weights for policy 0, policy_version 88022 (0.0010) -[2023-10-16 06:15:25,595][05218] Updated weights for policy 0, policy_version 88032 (0.0009) -[2023-10-16 06:15:27,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 179994624. Throughput: 0: 1806.6, 1: 1792.1. Samples: 45004736. Policy #0 lag: (min: 31.0, avg: 32.3, max: 56.0) -[2023-10-16 06:15:27,351][03835] Avg episode reward: [(0, '7.220'), (1, '8.280')] -[2023-10-16 06:15:27,854][05219] Updated weights for policy 1, policy_version 87750 (0.0008) -[2023-10-16 06:15:28,229][05219] Updated weights for policy 1, policy_version 87760 (0.0008) -[2023-10-16 06:15:28,589][05219] Updated weights for policy 1, policy_version 87770 (0.0008) -[2023-10-16 06:15:29,294][05218] Updated weights for policy 0, policy_version 88042 (0.0010) -[2023-10-16 06:15:29,657][05218] Updated weights for policy 0, policy_version 88052 (0.0009) -[2023-10-16 06:15:30,035][05218] Updated weights for policy 0, policy_version 88062 (0.0007) -[2023-10-16 06:15:32,312][05219] Updated weights for policy 1, policy_version 87780 (0.0009) -[2023-10-16 06:15:32,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 180060160. Throughput: 0: 1797.1, 1: 1790.9. Samples: 45026684. Policy #0 lag: (min: 31.0, avg: 32.3, max: 56.0) -[2023-10-16 06:15:32,351][03835] Avg episode reward: [(0, '7.180'), (1, '8.730')] -[2023-10-16 06:15:32,675][05219] Updated weights for policy 1, policy_version 87790 (0.0010) -[2023-10-16 06:15:33,036][05219] Updated weights for policy 1, policy_version 87800 (0.0007) -[2023-10-16 06:15:33,728][05218] Updated weights for policy 0, policy_version 88072 (0.0008) -[2023-10-16 06:15:34,110][05218] Updated weights for policy 0, policy_version 88082 (0.0008) -[2023-10-16 06:15:34,482][05218] Updated weights for policy 0, policy_version 88092 (0.0008) -[2023-10-16 06:15:36,772][05219] Updated weights for policy 1, policy_version 87810 (0.0010) -[2023-10-16 06:15:37,140][05219] Updated weights for policy 1, policy_version 87820 (0.0010) -[2023-10-16 06:15:37,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 180125696. Throughput: 0: 1792.4, 1: 1809.4. Samples: 45048700. Policy #0 lag: (min: 31.0, avg: 32.3, max: 56.0) -[2023-10-16 06:15:37,351][03835] Avg episode reward: [(0, '6.980'), (1, '8.540')] -[2023-10-16 06:15:37,359][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000088096_90210304.pth... -[2023-10-16 06:15:37,393][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000086432_88506368.pth -[2023-10-16 06:15:37,512][05219] Updated weights for policy 1, policy_version 87830 (0.0007) -[2023-10-16 06:15:37,868][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000087840_89948160.pth... -[2023-10-16 06:15:37,869][05219] Updated weights for policy 1, policy_version 87840 (0.0008) -[2023-10-16 06:15:37,898][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000086144_88211456.pth -[2023-10-16 06:15:38,317][05218] Updated weights for policy 0, policy_version 88102 (0.0009) -[2023-10-16 06:15:38,693][05218] Updated weights for policy 0, policy_version 88112 (0.0007) -[2023-10-16 06:15:39,061][05218] Updated weights for policy 0, policy_version 88122 (0.0007) -[2023-10-16 06:15:41,609][05219] Updated weights for policy 1, policy_version 87850 (0.0008) -[2023-10-16 06:15:41,975][05219] Updated weights for policy 1, policy_version 87860 (0.0007) -[2023-10-16 06:15:42,335][05219] Updated weights for policy 1, policy_version 87870 (0.0007) -[2023-10-16 06:15:42,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 180191232. Throughput: 0: 1788.3, 1: 1791.2. Samples: 45058778. Policy #0 lag: (min: 31.0, avg: 32.3, max: 56.0) -[2023-10-16 06:15:42,351][03835] Avg episode reward: [(0, '7.680'), (1, '8.290')] -[2023-10-16 06:15:42,820][05218] Updated weights for policy 0, policy_version 88132 (0.0010) -[2023-10-16 06:15:43,198][05218] Updated weights for policy 0, policy_version 88142 (0.0010) -[2023-10-16 06:15:43,585][05218] Updated weights for policy 0, policy_version 88152 (0.0011) -[2023-10-16 06:15:46,205][05219] Updated weights for policy 1, policy_version 87880 (0.0008) -[2023-10-16 06:15:46,568][05219] Updated weights for policy 1, policy_version 87890 (0.0008) -[2023-10-16 06:15:46,941][05219] Updated weights for policy 1, policy_version 87900 (0.0009) -[2023-10-16 06:15:47,275][05218] Updated weights for policy 0, policy_version 88162 (0.0009) -[2023-10-16 06:15:47,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 180289536. Throughput: 0: 1785.9, 1: 1805.8. Samples: 45080992. Policy #0 lag: (min: 31.0, avg: 32.3, max: 56.0) -[2023-10-16 06:15:47,351][03835] Avg episode reward: [(0, '7.650'), (1, '8.370')] -[2023-10-16 06:15:47,660][05218] Updated weights for policy 0, policy_version 88172 (0.0008) -[2023-10-16 06:15:48,040][05218] Updated weights for policy 0, policy_version 88182 (0.0007) -[2023-10-16 06:15:48,422][05218] Updated weights for policy 0, policy_version 88192 (0.0008) -[2023-10-16 06:15:50,704][05219] Updated weights for policy 1, policy_version 87910 (0.0010) -[2023-10-16 06:15:51,068][05219] Updated weights for policy 1, policy_version 87920 (0.0008) -[2023-10-16 06:15:51,438][05219] Updated weights for policy 1, policy_version 87930 (0.0007) -[2023-10-16 06:15:52,132][05218] Updated weights for policy 0, policy_version 88202 (0.0008) -[2023-10-16 06:15:52,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 180355072. Throughput: 0: 1805.2, 1: 1788.4. Samples: 45101648. Policy #0 lag: (min: 31.0, avg: 32.4, max: 56.0) -[2023-10-16 06:15:52,351][03835] Avg episode reward: [(0, '7.120'), (1, '9.060')] -[2023-10-16 06:15:52,508][05218] Updated weights for policy 0, policy_version 88212 (0.0009) -[2023-10-16 06:15:52,883][05218] Updated weights for policy 0, policy_version 88222 (0.0008) -[2023-10-16 06:15:55,271][05219] Updated weights for policy 1, policy_version 87940 (0.0009) -[2023-10-16 06:15:55,647][05219] Updated weights for policy 1, policy_version 87950 (0.0011) -[2023-10-16 06:15:56,003][05219] Updated weights for policy 1, policy_version 87960 (0.0008) -[2023-10-16 06:15:56,465][05218] Updated weights for policy 0, policy_version 88232 (0.0007) -[2023-10-16 06:15:56,841][05218] Updated weights for policy 0, policy_version 88242 (0.0009) -[2023-10-16 06:15:57,208][05218] Updated weights for policy 0, policy_version 88252 (0.0008) -[2023-10-16 06:15:57,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 180420608. Throughput: 0: 1789.3, 1: 1808.5. Samples: 45113688. Policy #0 lag: (min: 31.0, avg: 32.4, max: 56.0) -[2023-10-16 06:15:57,351][03835] Avg episode reward: [(0, '7.030'), (1, '8.370')] -[2023-10-16 06:15:59,734][05219] Updated weights for policy 1, policy_version 87970 (0.0009) -[2023-10-16 06:16:00,098][05219] Updated weights for policy 1, policy_version 87980 (0.0010) -[2023-10-16 06:16:00,477][05219] Updated weights for policy 1, policy_version 87990 (0.0010) -[2023-10-16 06:16:00,831][05219] Updated weights for policy 1, policy_version 88000 (0.0009) -[2023-10-16 06:16:00,891][05218] Updated weights for policy 0, policy_version 88262 (0.0009) -[2023-10-16 06:16:01,271][05218] Updated weights for policy 0, policy_version 88272 (0.0009) -[2023-10-16 06:16:01,649][05218] Updated weights for policy 0, policy_version 88282 (0.0008) -[2023-10-16 06:16:02,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 180518912. Throughput: 0: 1805.3, 1: 1783.7. Samples: 45134004. Policy #0 lag: (min: 31.0, avg: 32.4, max: 56.0) -[2023-10-16 06:16:02,351][03835] Avg episode reward: [(0, '7.330'), (1, '7.790')] -[2023-10-16 06:16:04,568][05219] Updated weights for policy 1, policy_version 88010 (0.0007) -[2023-10-16 06:16:04,935][05219] Updated weights for policy 1, policy_version 88020 (0.0009) -[2023-10-16 06:16:05,291][05219] Updated weights for policy 1, policy_version 88030 (0.0008) -[2023-10-16 06:16:05,444][05218] Updated weights for policy 0, policy_version 88292 (0.0007) -[2023-10-16 06:16:05,819][05218] Updated weights for policy 0, policy_version 88302 (0.0009) -[2023-10-16 06:16:06,201][05218] Updated weights for policy 0, policy_version 88312 (0.0008) -[2023-10-16 06:16:07,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 180584448. Throughput: 0: 1798.6, 1: 1782.1. Samples: 45155928. Policy #0 lag: (min: 31.0, avg: 32.4, max: 56.0) -[2023-10-16 06:16:07,351][03835] Avg episode reward: [(0, '8.120'), (1, '9.430')] -[2023-10-16 06:16:09,104][05219] Updated weights for policy 1, policy_version 88040 (0.0008) -[2023-10-16 06:16:09,466][05219] Updated weights for policy 1, policy_version 88050 (0.0009) -[2023-10-16 06:16:09,830][05219] Updated weights for policy 1, policy_version 88060 (0.0010) -[2023-10-16 06:16:09,970][05218] Updated weights for policy 0, policy_version 88322 (0.0009) -[2023-10-16 06:16:10,340][05218] Updated weights for policy 0, policy_version 88332 (0.0009) -[2023-10-16 06:16:10,724][05218] Updated weights for policy 0, policy_version 88342 (0.0009) -[2023-10-16 06:16:11,096][05218] Updated weights for policy 0, policy_version 88352 (0.0008) -[2023-10-16 06:16:12,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 180649984. Throughput: 0: 1812.0, 1: 1784.6. Samples: 45166584. Policy #0 lag: (min: 31.0, avg: 32.4, max: 56.0) -[2023-10-16 06:16:12,351][03835] Avg episode reward: [(0, '8.260'), (1, '8.170')] -[2023-10-16 06:16:13,729][05219] Updated weights for policy 1, policy_version 88070 (0.0007) -[2023-10-16 06:16:14,090][05219] Updated weights for policy 1, policy_version 88080 (0.0008) -[2023-10-16 06:16:14,451][05219] Updated weights for policy 1, policy_version 88090 (0.0007) -[2023-10-16 06:16:14,883][05218] Updated weights for policy 0, policy_version 88362 (0.0010) -[2023-10-16 06:16:15,254][05218] Updated weights for policy 0, policy_version 88372 (0.0008) -[2023-10-16 06:16:15,636][05218] Updated weights for policy 0, policy_version 88382 (0.0010) -[2023-10-16 06:16:17,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 180715520. Throughput: 0: 1799.7, 1: 1785.3. Samples: 45188010. Policy #0 lag: (min: 31.0, avg: 32.4, max: 56.0) -[2023-10-16 06:16:17,351][03835] Avg episode reward: [(0, '7.260'), (1, '7.610')] -[2023-10-16 06:16:18,156][05219] Updated weights for policy 1, policy_version 88100 (0.0007) -[2023-10-16 06:16:18,528][05219] Updated weights for policy 1, policy_version 88110 (0.0008) -[2023-10-16 06:16:18,885][05219] Updated weights for policy 1, policy_version 88120 (0.0008) -[2023-10-16 06:16:19,255][05218] Updated weights for policy 0, policy_version 88392 (0.0008) -[2023-10-16 06:16:19,626][05218] Updated weights for policy 0, policy_version 88402 (0.0009) -[2023-10-16 06:16:20,006][05218] Updated weights for policy 0, policy_version 88412 (0.0008) -[2023-10-16 06:16:22,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 180781056. Throughput: 0: 1799.8, 1: 1796.0. Samples: 45210512. Policy #0 lag: (min: 31.0, avg: 32.4, max: 56.0) -[2023-10-16 06:16:22,351][03835] Avg episode reward: [(0, '6.850'), (1, '8.050')] -[2023-10-16 06:16:22,673][05219] Updated weights for policy 1, policy_version 88130 (0.0009) -[2023-10-16 06:16:23,044][05219] Updated weights for policy 1, policy_version 88140 (0.0008) -[2023-10-16 06:16:23,399][05219] Updated weights for policy 1, policy_version 88150 (0.0008) -[2023-10-16 06:16:23,732][05218] Updated weights for policy 0, policy_version 88422 (0.0009) -[2023-10-16 06:16:23,763][05219] Updated weights for policy 1, policy_version 88160 (0.0008) -[2023-10-16 06:16:24,114][05218] Updated weights for policy 0, policy_version 88432 (0.0010) -[2023-10-16 06:16:24,484][05218] Updated weights for policy 0, policy_version 88442 (0.0008) -[2023-10-16 06:16:27,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 180846592. Throughput: 0: 1801.4, 1: 1785.7. Samples: 45220198. Policy #0 lag: (min: 31.0, avg: 32.4, max: 56.0) -[2023-10-16 06:16:27,351][03835] Avg episode reward: [(0, '6.930'), (1, '7.320')] -[2023-10-16 06:16:27,621][05219] Updated weights for policy 1, policy_version 88170 (0.0007) -[2023-10-16 06:16:27,990][05219] Updated weights for policy 1, policy_version 88180 (0.0008) -[2023-10-16 06:16:28,227][05218] Updated weights for policy 0, policy_version 88452 (0.0007) -[2023-10-16 06:16:28,346][05219] Updated weights for policy 1, policy_version 88190 (0.0009) -[2023-10-16 06:16:28,600][05218] Updated weights for policy 0, policy_version 88462 (0.0008) -[2023-10-16 06:16:28,984][05218] Updated weights for policy 0, policy_version 88472 (0.0009) -[2023-10-16 06:16:32,019][05219] Updated weights for policy 1, policy_version 88200 (0.0010) -[2023-10-16 06:16:32,351][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 180912128. Throughput: 0: 1799.3, 1: 1785.8. Samples: 45242324. Policy #0 lag: (min: 31.0, avg: 32.4, max: 56.0) -[2023-10-16 06:16:32,352][03835] Avg episode reward: [(0, '7.150'), (1, '6.790')] -[2023-10-16 06:16:32,379][05219] Updated weights for policy 1, policy_version 88210 (0.0007) -[2023-10-16 06:16:32,719][05218] Updated weights for policy 0, policy_version 88482 (0.0008) -[2023-10-16 06:16:32,751][05219] Updated weights for policy 1, policy_version 88220 (0.0007) -[2023-10-16 06:16:33,096][05218] Updated weights for policy 0, policy_version 88492 (0.0007) -[2023-10-16 06:16:33,477][05218] Updated weights for policy 0, policy_version 88502 (0.0008) -[2023-10-16 06:16:33,849][05218] Updated weights for policy 0, policy_version 88512 (0.0008) -[2023-10-16 06:16:36,579][05219] Updated weights for policy 1, policy_version 88230 (0.0008) -[2023-10-16 06:16:36,945][05219] Updated weights for policy 1, policy_version 88240 (0.0007) -[2023-10-16 06:16:37,314][05219] Updated weights for policy 1, policy_version 88250 (0.0009) -[2023-10-16 06:16:37,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 180977664. Throughput: 0: 1808.9, 1: 1791.6. Samples: 45263670. Policy #0 lag: (min: 31.0, avg: 32.4, max: 56.0) -[2023-10-16 06:16:37,351][03835] Avg episode reward: [(0, '7.480'), (1, '6.780')] -[2023-10-16 06:16:37,615][05218] Updated weights for policy 0, policy_version 88522 (0.0008) -[2023-10-16 06:16:37,987][05218] Updated weights for policy 0, policy_version 88532 (0.0009) -[2023-10-16 06:16:38,367][05218] Updated weights for policy 0, policy_version 88542 (0.0008) -[2023-10-16 06:16:41,110][05219] Updated weights for policy 1, policy_version 88260 (0.0008) -[2023-10-16 06:16:41,482][05219] Updated weights for policy 1, policy_version 88270 (0.0008) -[2023-10-16 06:16:41,846][05219] Updated weights for policy 1, policy_version 88280 (0.0009) -[2023-10-16 06:16:42,102][05218] Updated weights for policy 0, policy_version 88552 (0.0008) -[2023-10-16 06:16:42,350][03835] Fps is (10 sec: 16384.6, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 181075968. Throughput: 0: 1791.7, 1: 1779.1. Samples: 45274374. Policy #0 lag: (min: 31.0, avg: 32.4, max: 56.0) -[2023-10-16 06:16:42,351][03835] Avg episode reward: [(0, '7.580'), (1, '7.660')] -[2023-10-16 06:16:42,481][05218] Updated weights for policy 0, policy_version 88562 (0.0009) -[2023-10-16 06:16:42,868][05218] Updated weights for policy 0, policy_version 88572 (0.0009) -[2023-10-16 06:16:45,717][05219] Updated weights for policy 1, policy_version 88290 (0.0009) -[2023-10-16 06:16:46,080][05219] Updated weights for policy 1, policy_version 88300 (0.0011) -[2023-10-16 06:16:46,437][05219] Updated weights for policy 1, policy_version 88310 (0.0009) -[2023-10-16 06:16:46,678][05218] Updated weights for policy 0, policy_version 88582 (0.0008) -[2023-10-16 06:16:46,799][05219] Updated weights for policy 1, policy_version 88320 (0.0008) -[2023-10-16 06:16:47,049][05218] Updated weights for policy 0, policy_version 88592 (0.0007) -[2023-10-16 06:16:47,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 181141504. Throughput: 0: 1807.7, 1: 1793.6. Samples: 45296064. Policy #0 lag: (min: 0.0, avg: 20.2, max: 32.0) -[2023-10-16 06:16:47,351][03835] Avg episode reward: [(0, '7.520'), (1, '8.810')] -[2023-10-16 06:16:47,422][05218] Updated weights for policy 0, policy_version 88602 (0.0009) -[2023-10-16 06:16:50,680][05219] Updated weights for policy 1, policy_version 88330 (0.0009) -[2023-10-16 06:16:51,038][05219] Updated weights for policy 1, policy_version 88340 (0.0008) -[2023-10-16 06:16:51,166][05218] Updated weights for policy 0, policy_version 88612 (0.0009) -[2023-10-16 06:16:51,405][05219] Updated weights for policy 1, policy_version 88350 (0.0009) -[2023-10-16 06:16:51,545][05218] Updated weights for policy 0, policy_version 88622 (0.0008) -[2023-10-16 06:16:51,926][05218] Updated weights for policy 0, policy_version 88632 (0.0009) -[2023-10-16 06:16:52,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 181239808. Throughput: 0: 1780.2, 1: 1773.6. Samples: 45315852. Policy #0 lag: (min: 0.0, avg: 20.2, max: 32.0) -[2023-10-16 06:16:52,352][03835] Avg episode reward: [(0, '6.590'), (1, '7.500')] -[2023-10-16 06:16:55,237][05219] Updated weights for policy 1, policy_version 88360 (0.0009) -[2023-10-16 06:16:55,612][05219] Updated weights for policy 1, policy_version 88370 (0.0010) -[2023-10-16 06:16:55,647][05218] Updated weights for policy 0, policy_version 88642 (0.0009) -[2023-10-16 06:16:55,975][05219] Updated weights for policy 1, policy_version 88380 (0.0007) -[2023-10-16 06:16:56,025][05218] Updated weights for policy 0, policy_version 88652 (0.0009) -[2023-10-16 06:16:56,386][05218] Updated weights for policy 0, policy_version 88662 (0.0009) -[2023-10-16 06:16:56,769][05218] Updated weights for policy 0, policy_version 88672 (0.0010) -[2023-10-16 06:16:57,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 181305344. Throughput: 0: 1795.3, 1: 1801.6. Samples: 45328444. Policy #0 lag: (min: 0.0, avg: 20.2, max: 32.0) -[2023-10-16 06:16:57,351][03835] Avg episode reward: [(0, '7.150'), (1, '8.610')] -[2023-10-16 06:16:59,538][05219] Updated weights for policy 1, policy_version 88390 (0.0008) -[2023-10-16 06:16:59,903][05219] Updated weights for policy 1, policy_version 88400 (0.0009) -[2023-10-16 06:17:00,273][05219] Updated weights for policy 1, policy_version 88410 (0.0009) -[2023-10-16 06:17:00,396][05218] Updated weights for policy 0, policy_version 88682 (0.0009) -[2023-10-16 06:17:00,778][05218] Updated weights for policy 0, policy_version 88692 (0.0009) -[2023-10-16 06:17:01,155][05218] Updated weights for policy 0, policy_version 88702 (0.0008) -[2023-10-16 06:17:02,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 181370880. Throughput: 0: 1783.7, 1: 1773.8. Samples: 45348100. Policy #0 lag: (min: 0.0, avg: 20.2, max: 32.0) -[2023-10-16 06:17:02,351][03835] Avg episode reward: [(0, '8.540'), (1, '9.220')] -[2023-10-16 06:17:04,031][05219] Updated weights for policy 1, policy_version 88420 (0.0008) -[2023-10-16 06:17:04,394][05219] Updated weights for policy 1, policy_version 88430 (0.0010) -[2023-10-16 06:17:04,771][05219] Updated weights for policy 1, policy_version 88440 (0.0007) -[2023-10-16 06:17:05,033][05218] Updated weights for policy 0, policy_version 88712 (0.0009) -[2023-10-16 06:17:05,410][05218] Updated weights for policy 0, policy_version 88722 (0.0008) -[2023-10-16 06:17:05,794][05218] Updated weights for policy 0, policy_version 88732 (0.0010) -[2023-10-16 06:17:07,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 181436416. Throughput: 0: 1780.4, 1: 1773.7. Samples: 45370448. Policy #0 lag: (min: 0.0, avg: 20.2, max: 32.0) -[2023-10-16 06:17:07,352][03835] Avg episode reward: [(0, '7.660'), (1, '8.070')] -[2023-10-16 06:17:08,587][05219] Updated weights for policy 1, policy_version 88450 (0.0008) -[2023-10-16 06:17:08,950][05219] Updated weights for policy 1, policy_version 88460 (0.0009) -[2023-10-16 06:17:09,318][05219] Updated weights for policy 1, policy_version 88470 (0.0008) -[2023-10-16 06:17:09,473][05218] Updated weights for policy 0, policy_version 88742 (0.0008) -[2023-10-16 06:17:09,687][05219] Updated weights for policy 1, policy_version 88480 (0.0007) -[2023-10-16 06:17:09,855][05218] Updated weights for policy 0, policy_version 88752 (0.0007) -[2023-10-16 06:17:10,241][05218] Updated weights for policy 0, policy_version 88762 (0.0007) -[2023-10-16 06:17:12,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 181501952. Throughput: 0: 1789.8, 1: 1769.9. Samples: 45380388. Policy #0 lag: (min: 0.0, avg: 20.2, max: 32.0) -[2023-10-16 06:17:12,351][03835] Avg episode reward: [(0, '7.800'), (1, '8.340')] -[2023-10-16 06:17:13,560][05219] Updated weights for policy 1, policy_version 88490 (0.0009) -[2023-10-16 06:17:13,927][05219] Updated weights for policy 1, policy_version 88500 (0.0011) -[2023-10-16 06:17:14,120][05218] Updated weights for policy 0, policy_version 88772 (0.0008) -[2023-10-16 06:17:14,283][05219] Updated weights for policy 1, policy_version 88510 (0.0007) -[2023-10-16 06:17:14,498][05218] Updated weights for policy 0, policy_version 88782 (0.0009) -[2023-10-16 06:17:14,879][05218] Updated weights for policy 0, policy_version 88792 (0.0009) -[2023-10-16 06:17:17,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 181567488. Throughput: 0: 1780.5, 1: 1774.5. Samples: 45402300. Policy #0 lag: (min: 0.0, avg: 20.2, max: 32.0) -[2023-10-16 06:17:17,352][03835] Avg episode reward: [(0, '8.880'), (1, '9.310')] -[2023-10-16 06:17:17,353][04766] Saving new best policy, reward=8.880! -[2023-10-16 06:17:18,114][05219] Updated weights for policy 1, policy_version 88520 (0.0009) -[2023-10-16 06:17:18,486][05219] Updated weights for policy 1, policy_version 88530 (0.0009) -[2023-10-16 06:17:18,750][05218] Updated weights for policy 0, policy_version 88802 (0.0008) -[2023-10-16 06:17:18,850][05219] Updated weights for policy 1, policy_version 88540 (0.0007) -[2023-10-16 06:17:19,126][05218] Updated weights for policy 0, policy_version 88812 (0.0009) -[2023-10-16 06:17:19,505][05218] Updated weights for policy 0, policy_version 88822 (0.0011) -[2023-10-16 06:17:19,870][05218] Updated weights for policy 0, policy_version 88832 (0.0010) -[2023-10-16 06:17:22,351][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 181633024. Throughput: 0: 1779.4, 1: 1788.8. Samples: 45424240. Policy #0 lag: (min: 0.0, avg: 20.2, max: 32.0) -[2023-10-16 06:17:22,352][03835] Avg episode reward: [(0, '7.330'), (1, '8.510')] -[2023-10-16 06:17:22,771][05219] Updated weights for policy 1, policy_version 88550 (0.0009) -[2023-10-16 06:17:23,141][05219] Updated weights for policy 1, policy_version 88560 (0.0008) -[2023-10-16 06:17:23,502][05219] Updated weights for policy 1, policy_version 88570 (0.0008) -[2023-10-16 06:17:23,688][05218] Updated weights for policy 0, policy_version 88842 (0.0008) -[2023-10-16 06:17:24,072][05218] Updated weights for policy 0, policy_version 88852 (0.0008) -[2023-10-16 06:17:24,445][05218] Updated weights for policy 0, policy_version 88862 (0.0010) -[2023-10-16 06:17:27,351][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 181698560. Throughput: 0: 1778.8, 1: 1769.7. Samples: 45434058. Policy #0 lag: (min: 0.0, avg: 20.2, max: 32.0) -[2023-10-16 06:17:27,352][03835] Avg episode reward: [(0, '7.390'), (1, '8.210')] -[2023-10-16 06:17:27,441][05219] Updated weights for policy 1, policy_version 88580 (0.0008) -[2023-10-16 06:17:27,817][05219] Updated weights for policy 1, policy_version 88590 (0.0010) -[2023-10-16 06:17:28,181][05219] Updated weights for policy 1, policy_version 88600 (0.0009) -[2023-10-16 06:17:28,181][05218] Updated weights for policy 0, policy_version 88872 (0.0008) -[2023-10-16 06:17:28,549][05218] Updated weights for policy 0, policy_version 88882 (0.0011) -[2023-10-16 06:17:28,923][05218] Updated weights for policy 0, policy_version 88892 (0.0009) -[2023-10-16 06:17:31,952][05219] Updated weights for policy 1, policy_version 88610 (0.0008) -[2023-10-16 06:17:32,319][05219] Updated weights for policy 1, policy_version 88620 (0.0010) -[2023-10-16 06:17:32,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.6, 300 sec: 14329.1). Total num frames: 181764096. Throughput: 0: 1777.3, 1: 1788.4. Samples: 45456522. Policy #0 lag: (min: 0.0, avg: 20.2, max: 32.0) -[2023-10-16 06:17:32,351][03835] Avg episode reward: [(0, '7.320'), (1, '8.640')] -[2023-10-16 06:17:32,566][05218] Updated weights for policy 0, policy_version 88902 (0.0011) -[2023-10-16 06:17:32,688][05219] Updated weights for policy 1, policy_version 88630 (0.0009) -[2023-10-16 06:17:32,937][05218] Updated weights for policy 0, policy_version 88912 (0.0007) -[2023-10-16 06:17:33,044][05219] Updated weights for policy 1, policy_version 88640 (0.0008) -[2023-10-16 06:17:33,313][05218] Updated weights for policy 0, policy_version 88922 (0.0008) -[2023-10-16 06:17:36,763][05219] Updated weights for policy 1, policy_version 88650 (0.0009) -[2023-10-16 06:17:37,034][05218] Updated weights for policy 0, policy_version 88932 (0.0009) -[2023-10-16 06:17:37,125][05219] Updated weights for policy 1, policy_version 88660 (0.0007) -[2023-10-16 06:17:37,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 181829632. Throughput: 0: 1801.6, 1: 1789.7. Samples: 45477460. Policy #0 lag: (min: 0.0, avg: 20.2, max: 32.0) -[2023-10-16 06:17:37,351][03835] Avg episode reward: [(0, '7.420'), (1, '8.530')] -[2023-10-16 06:17:37,398][05218] Updated weights for policy 0, policy_version 88942 (0.0009) -[2023-10-16 06:17:37,489][05219] Updated weights for policy 1, policy_version 88670 (0.0007) -[2023-10-16 06:17:37,561][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000088672_90800128.pth... -[2023-10-16 06:17:37,596][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000086976_89063424.pth -[2023-10-16 06:17:37,781][05218] Updated weights for policy 0, policy_version 88952 (0.0008) -[2023-10-16 06:17:38,084][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000088960_91095040.pth... -[2023-10-16 06:17:38,113][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000087264_89358336.pth -[2023-10-16 06:17:41,153][05219] Updated weights for policy 1, policy_version 88680 (0.0008) -[2023-10-16 06:17:41,516][05218] Updated weights for policy 0, policy_version 88962 (0.0010) -[2023-10-16 06:17:41,524][05219] Updated weights for policy 1, policy_version 88690 (0.0007) -[2023-10-16 06:17:41,884][05219] Updated weights for policy 1, policy_version 88700 (0.0008) -[2023-10-16 06:17:41,897][05218] Updated weights for policy 0, policy_version 88972 (0.0007) -[2023-10-16 06:17:42,268][05218] Updated weights for policy 0, policy_version 88982 (0.0009) -[2023-10-16 06:17:42,350][03835] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 181927936. Throughput: 0: 1774.0, 1: 1780.7. Samples: 45488404. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-16 06:17:42,351][03835] Avg episode reward: [(0, '7.760'), (1, '7.960')] -[2023-10-16 06:17:42,647][05218] Updated weights for policy 0, policy_version 88992 (0.0011) -[2023-10-16 06:17:45,672][05219] Updated weights for policy 1, policy_version 88710 (0.0008) -[2023-10-16 06:17:46,027][05219] Updated weights for policy 1, policy_version 88720 (0.0010) -[2023-10-16 06:17:46,393][05219] Updated weights for policy 1, policy_version 88730 (0.0008) -[2023-10-16 06:17:46,425][05218] Updated weights for policy 0, policy_version 89002 (0.0009) -[2023-10-16 06:17:46,811][05218] Updated weights for policy 0, policy_version 89012 (0.0008) -[2023-10-16 06:17:47,185][05218] Updated weights for policy 0, policy_version 89022 (0.0008) -[2023-10-16 06:17:47,350][03835] Fps is (10 sec: 19660.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 182026240. Throughput: 0: 1797.2, 1: 1785.5. Samples: 45509322. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-16 06:17:47,351][03835] Avg episode reward: [(0, '7.030'), (1, '7.640')] -[2023-10-16 06:17:50,186][05219] Updated weights for policy 1, policy_version 88740 (0.0008) -[2023-10-16 06:17:50,546][05219] Updated weights for policy 1, policy_version 88750 (0.0008) -[2023-10-16 06:17:50,905][05219] Updated weights for policy 1, policy_version 88760 (0.0007) -[2023-10-16 06:17:50,992][05218] Updated weights for policy 0, policy_version 89032 (0.0007) -[2023-10-16 06:17:51,369][05218] Updated weights for policy 0, policy_version 89042 (0.0008) -[2023-10-16 06:17:51,740][05218] Updated weights for policy 0, policy_version 89052 (0.0009) -[2023-10-16 06:17:52,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 182091776. Throughput: 0: 1771.4, 1: 1771.9. Samples: 45529896. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-16 06:17:52,351][03835] Avg episode reward: [(0, '6.410'), (1, '9.160')] -[2023-10-16 06:17:54,752][05219] Updated weights for policy 1, policy_version 88770 (0.0007) -[2023-10-16 06:17:55,121][05219] Updated weights for policy 1, policy_version 88780 (0.0008) -[2023-10-16 06:17:55,412][05218] Updated weights for policy 0, policy_version 89062 (0.0008) -[2023-10-16 06:17:55,479][05219] Updated weights for policy 1, policy_version 88790 (0.0007) -[2023-10-16 06:17:55,791][05218] Updated weights for policy 0, policy_version 89072 (0.0009) -[2023-10-16 06:17:55,841][05219] Updated weights for policy 1, policy_version 88800 (0.0007) -[2023-10-16 06:17:56,172][05218] Updated weights for policy 0, policy_version 89082 (0.0008) -[2023-10-16 06:17:57,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 182157312. Throughput: 0: 1796.4, 1: 1789.1. Samples: 45541736. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-16 06:17:57,351][03835] Avg episode reward: [(0, '7.360'), (1, '8.410')] -[2023-10-16 06:17:59,508][05219] Updated weights for policy 1, policy_version 88810 (0.0008) -[2023-10-16 06:17:59,843][05218] Updated weights for policy 0, policy_version 89092 (0.0010) -[2023-10-16 06:17:59,875][05219] Updated weights for policy 1, policy_version 88820 (0.0008) -[2023-10-16 06:18:00,219][05218] Updated weights for policy 0, policy_version 89102 (0.0010) -[2023-10-16 06:18:00,236][05219] Updated weights for policy 1, policy_version 88830 (0.0009) -[2023-10-16 06:18:00,591][05218] Updated weights for policy 0, policy_version 89112 (0.0009) -[2023-10-16 06:18:02,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 182222848. Throughput: 0: 1781.9, 1: 1772.5. Samples: 45562246. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-16 06:18:02,351][03835] Avg episode reward: [(0, '6.910'), (1, '8.550')] -[2023-10-16 06:18:03,966][05219] Updated weights for policy 1, policy_version 88840 (0.0008) -[2023-10-16 06:18:04,332][05219] Updated weights for policy 1, policy_version 88850 (0.0007) -[2023-10-16 06:18:04,376][05218] Updated weights for policy 0, policy_version 89122 (0.0008) -[2023-10-16 06:18:04,701][05219] Updated weights for policy 1, policy_version 88860 (0.0009) -[2023-10-16 06:18:04,746][05218] Updated weights for policy 0, policy_version 89132 (0.0008) -[2023-10-16 06:18:05,128][05218] Updated weights for policy 0, policy_version 89142 (0.0010) -[2023-10-16 06:18:05,506][05218] Updated weights for policy 0, policy_version 89152 (0.0009) -[2023-10-16 06:18:07,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 182288384. Throughput: 0: 1784.8, 1: 1780.4. Samples: 45584674. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-16 06:18:07,351][03835] Avg episode reward: [(0, '7.430'), (1, '9.090')] -[2023-10-16 06:18:08,363][05219] Updated weights for policy 1, policy_version 88870 (0.0007) -[2023-10-16 06:18:08,716][05219] Updated weights for policy 1, policy_version 88880 (0.0008) -[2023-10-16 06:18:09,089][05219] Updated weights for policy 1, policy_version 88890 (0.0008) -[2023-10-16 06:18:09,297][05218] Updated weights for policy 0, policy_version 89162 (0.0008) -[2023-10-16 06:18:09,686][05218] Updated weights for policy 0, policy_version 89172 (0.0009) -[2023-10-16 06:18:10,058][05218] Updated weights for policy 0, policy_version 89182 (0.0008) -[2023-10-16 06:18:12,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 182353920. Throughput: 0: 1779.7, 1: 1785.4. Samples: 45594486. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-16 06:18:12,351][03835] Avg episode reward: [(0, '8.400'), (1, '8.480')] -[2023-10-16 06:18:12,813][05219] Updated weights for policy 1, policy_version 88900 (0.0008) -[2023-10-16 06:18:13,172][05219] Updated weights for policy 1, policy_version 88910 (0.0007) -[2023-10-16 06:18:13,533][05219] Updated weights for policy 1, policy_version 88920 (0.0010) -[2023-10-16 06:18:13,801][05218] Updated weights for policy 0, policy_version 89192 (0.0008) -[2023-10-16 06:18:14,173][05218] Updated weights for policy 0, policy_version 89202 (0.0009) -[2023-10-16 06:18:14,546][05218] Updated weights for policy 0, policy_version 89212 (0.0008) -[2023-10-16 06:18:17,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 182419456. Throughput: 0: 1782.8, 1: 1783.2. Samples: 45616992. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-16 06:18:17,351][03835] Avg episode reward: [(0, '7.840'), (1, '8.710')] -[2023-10-16 06:18:17,414][05219] Updated weights for policy 1, policy_version 88930 (0.0009) -[2023-10-16 06:18:17,777][05219] Updated weights for policy 1, policy_version 88940 (0.0007) -[2023-10-16 06:18:18,140][05219] Updated weights for policy 1, policy_version 88950 (0.0007) -[2023-10-16 06:18:18,255][05218] Updated weights for policy 0, policy_version 89222 (0.0009) -[2023-10-16 06:18:18,505][05219] Updated weights for policy 1, policy_version 88960 (0.0007) -[2023-10-16 06:18:18,633][05218] Updated weights for policy 0, policy_version 89232 (0.0008) -[2023-10-16 06:18:19,010][05218] Updated weights for policy 0, policy_version 89242 (0.0008) -[2023-10-16 06:18:22,292][05219] Updated weights for policy 1, policy_version 88970 (0.0009) -[2023-10-16 06:18:22,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 182484992. Throughput: 0: 1800.9, 1: 1795.1. Samples: 45639284. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-16 06:18:22,351][03835] Avg episode reward: [(0, '7.560'), (1, '8.820')] -[2023-10-16 06:18:22,661][05219] Updated weights for policy 1, policy_version 88980 (0.0007) -[2023-10-16 06:18:22,729][05218] Updated weights for policy 0, policy_version 89252 (0.0009) -[2023-10-16 06:18:23,033][05219] Updated weights for policy 1, policy_version 88990 (0.0009) -[2023-10-16 06:18:23,105][05218] Updated weights for policy 0, policy_version 89262 (0.0008) -[2023-10-16 06:18:23,487][05218] Updated weights for policy 0, policy_version 89272 (0.0010) -[2023-10-16 06:18:26,881][05219] Updated weights for policy 1, policy_version 89000 (0.0008) -[2023-10-16 06:18:27,151][05218] Updated weights for policy 0, policy_version 89282 (0.0010) -[2023-10-16 06:18:27,256][05219] Updated weights for policy 1, policy_version 89010 (0.0009) -[2023-10-16 06:18:27,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.6, 300 sec: 14218.0). Total num frames: 182550528. Throughput: 0: 1794.5, 1: 1782.2. Samples: 45649354. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-16 06:18:27,351][03835] Avg episode reward: [(0, '7.530'), (1, '8.390')] -[2023-10-16 06:18:27,534][05218] Updated weights for policy 0, policy_version 89292 (0.0009) -[2023-10-16 06:18:27,626][05219] Updated weights for policy 1, policy_version 89020 (0.0008) -[2023-10-16 06:18:27,910][05218] Updated weights for policy 0, policy_version 89302 (0.0009) -[2023-10-16 06:18:28,285][05218] Updated weights for policy 0, policy_version 89312 (0.0009) -[2023-10-16 06:18:31,381][05219] Updated weights for policy 1, policy_version 89030 (0.0008) -[2023-10-16 06:18:31,754][05219] Updated weights for policy 1, policy_version 89040 (0.0008) -[2023-10-16 06:18:32,081][05218] Updated weights for policy 0, policy_version 89322 (0.0009) -[2023-10-16 06:18:32,112][05219] Updated weights for policy 1, policy_version 89050 (0.0008) -[2023-10-16 06:18:32,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 182648832. Throughput: 0: 1803.0, 1: 1806.0. Samples: 45671724. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-16 06:18:32,351][03835] Avg episode reward: [(0, '7.950'), (1, '7.150')] -[2023-10-16 06:18:32,461][05218] Updated weights for policy 0, policy_version 89332 (0.0008) -[2023-10-16 06:18:32,823][05218] Updated weights for policy 0, policy_version 89342 (0.0009) -[2023-10-16 06:18:35,898][05219] Updated weights for policy 1, policy_version 89060 (0.0008) -[2023-10-16 06:18:36,252][05219] Updated weights for policy 1, policy_version 89070 (0.0009) -[2023-10-16 06:18:36,542][05218] Updated weights for policy 0, policy_version 89352 (0.0008) -[2023-10-16 06:18:36,619][05219] Updated weights for policy 1, policy_version 89080 (0.0008) -[2023-10-16 06:18:36,922][05218] Updated weights for policy 0, policy_version 89362 (0.0008) -[2023-10-16 06:18:37,296][05218] Updated weights for policy 0, policy_version 89372 (0.0008) -[2023-10-16 06:18:37,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 182714368. Throughput: 0: 1801.5, 1: 1788.3. Samples: 45691436. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-16 06:18:37,351][03835] Avg episode reward: [(0, '7.360'), (1, '7.060')] -[2023-10-16 06:18:40,382][05219] Updated weights for policy 1, policy_version 89090 (0.0008) -[2023-10-16 06:18:40,738][05219] Updated weights for policy 1, policy_version 89100 (0.0010) -[2023-10-16 06:18:40,969][05218] Updated weights for policy 0, policy_version 89382 (0.0010) -[2023-10-16 06:18:41,103][05219] Updated weights for policy 1, policy_version 89110 (0.0007) -[2023-10-16 06:18:41,352][05218] Updated weights for policy 0, policy_version 89392 (0.0009) -[2023-10-16 06:18:41,465][05219] Updated weights for policy 1, policy_version 89120 (0.0008) -[2023-10-16 06:18:41,724][05218] Updated weights for policy 0, policy_version 89402 (0.0010) -[2023-10-16 06:18:42,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 182812672. Throughput: 0: 1805.3, 1: 1801.8. Samples: 45704058. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-16 06:18:42,351][03835] Avg episode reward: [(0, '7.000'), (1, '8.770')] -[2023-10-16 06:18:45,030][05219] Updated weights for policy 1, policy_version 89130 (0.0008) -[2023-10-16 06:18:45,388][05218] Updated weights for policy 0, policy_version 89412 (0.0008) -[2023-10-16 06:18:45,392][05219] Updated weights for policy 1, policy_version 89140 (0.0007) -[2023-10-16 06:18:45,757][05219] Updated weights for policy 1, policy_version 89150 (0.0007) -[2023-10-16 06:18:45,762][05218] Updated weights for policy 0, policy_version 89422 (0.0009) -[2023-10-16 06:18:46,134][05218] Updated weights for policy 0, policy_version 89432 (0.0009) -[2023-10-16 06:18:47,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 182878208. Throughput: 0: 1801.9, 1: 1789.6. Samples: 45723866. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-16 06:18:47,351][03835] Avg episode reward: [(0, '8.150'), (1, '8.210')] -[2023-10-16 06:18:49,616][05219] Updated weights for policy 1, policy_version 89160 (0.0009) -[2023-10-16 06:18:49,880][05218] Updated weights for policy 0, policy_version 89442 (0.0009) -[2023-10-16 06:18:49,980][05219] Updated weights for policy 1, policy_version 89170 (0.0007) -[2023-10-16 06:18:50,259][05218] Updated weights for policy 0, policy_version 89452 (0.0008) -[2023-10-16 06:18:50,343][05219] Updated weights for policy 1, policy_version 89180 (0.0009) -[2023-10-16 06:18:50,625][05218] Updated weights for policy 0, policy_version 89462 (0.0008) -[2023-10-16 06:18:50,999][05218] Updated weights for policy 0, policy_version 89472 (0.0010) -[2023-10-16 06:18:52,351][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 182943744. Throughput: 0: 1797.6, 1: 1784.8. Samples: 45745884. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-16 06:18:52,352][03835] Avg episode reward: [(0, '8.400'), (1, '8.190')] -[2023-10-16 06:18:54,067][05219] Updated weights for policy 1, policy_version 89190 (0.0010) -[2023-10-16 06:18:54,432][05219] Updated weights for policy 1, policy_version 89200 (0.0008) -[2023-10-16 06:18:54,803][05219] Updated weights for policy 1, policy_version 89210 (0.0007) -[2023-10-16 06:18:54,876][05218] Updated weights for policy 0, policy_version 89482 (0.0009) -[2023-10-16 06:18:55,256][05218] Updated weights for policy 0, policy_version 89492 (0.0008) -[2023-10-16 06:18:55,639][05218] Updated weights for policy 0, policy_version 89502 (0.0007) -[2023-10-16 06:18:57,351][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 183009280. Throughput: 0: 1811.5, 1: 1780.7. Samples: 45756138. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-16 06:18:57,352][03835] Avg episode reward: [(0, '8.570'), (1, '9.280')] -[2023-10-16 06:18:58,567][05219] Updated weights for policy 1, policy_version 89220 (0.0009) -[2023-10-16 06:18:58,929][05219] Updated weights for policy 1, policy_version 89230 (0.0009) -[2023-10-16 06:18:59,294][05219] Updated weights for policy 1, policy_version 89240 (0.0007) -[2023-10-16 06:18:59,436][05218] Updated weights for policy 0, policy_version 89512 (0.0008) -[2023-10-16 06:18:59,809][05218] Updated weights for policy 0, policy_version 89522 (0.0009) -[2023-10-16 06:19:00,188][05218] Updated weights for policy 0, policy_version 89532 (0.0009) -[2023-10-16 06:19:02,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 183074816. Throughput: 0: 1791.7, 1: 1787.3. Samples: 45778046. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-16 06:19:02,351][03835] Avg episode reward: [(0, '7.680'), (1, '8.400')] -[2023-10-16 06:19:03,121][05219] Updated weights for policy 1, policy_version 89250 (0.0007) -[2023-10-16 06:19:03,481][05219] Updated weights for policy 1, policy_version 89260 (0.0010) -[2023-10-16 06:19:03,843][05219] Updated weights for policy 1, policy_version 89270 (0.0009) -[2023-10-16 06:19:04,072][05218] Updated weights for policy 0, policy_version 89542 (0.0008) -[2023-10-16 06:19:04,210][05219] Updated weights for policy 1, policy_version 89280 (0.0009) -[2023-10-16 06:19:04,457][05218] Updated weights for policy 0, policy_version 89552 (0.0008) -[2023-10-16 06:19:04,839][05218] Updated weights for policy 0, policy_version 89562 (0.0008) -[2023-10-16 06:19:07,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 183140352. Throughput: 0: 1782.5, 1: 1792.2. Samples: 45800148. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-16 06:19:07,351][03835] Avg episode reward: [(0, '7.830'), (1, '8.400')] -[2023-10-16 06:19:07,985][05219] Updated weights for policy 1, policy_version 89290 (0.0008) -[2023-10-16 06:19:08,338][05219] Updated weights for policy 1, policy_version 89300 (0.0010) -[2023-10-16 06:19:08,573][05218] Updated weights for policy 0, policy_version 89572 (0.0009) -[2023-10-16 06:19:08,709][05219] Updated weights for policy 1, policy_version 89310 (0.0008) -[2023-10-16 06:19:08,963][05218] Updated weights for policy 0, policy_version 89582 (0.0009) -[2023-10-16 06:19:09,335][05218] Updated weights for policy 0, policy_version 89592 (0.0009) -[2023-10-16 06:19:12,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 183205888. Throughput: 0: 1779.3, 1: 1789.5. Samples: 45809952. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-16 06:19:12,351][03835] Avg episode reward: [(0, '7.870'), (1, '8.500')] -[2023-10-16 06:19:12,536][05219] Updated weights for policy 1, policy_version 89320 (0.0009) -[2023-10-16 06:19:12,902][05219] Updated weights for policy 1, policy_version 89330 (0.0008) -[2023-10-16 06:19:13,157][05218] Updated weights for policy 0, policy_version 89602 (0.0008) -[2023-10-16 06:19:13,261][05219] Updated weights for policy 1, policy_version 89340 (0.0007) -[2023-10-16 06:19:13,529][05218] Updated weights for policy 0, policy_version 89612 (0.0009) -[2023-10-16 06:19:13,902][05218] Updated weights for policy 0, policy_version 89622 (0.0009) -[2023-10-16 06:19:14,284][05218] Updated weights for policy 0, policy_version 89632 (0.0009) -[2023-10-16 06:19:17,105][05219] Updated weights for policy 1, policy_version 89350 (0.0008) -[2023-10-16 06:19:17,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 183271424. Throughput: 0: 1775.1, 1: 1783.7. Samples: 45831870. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-16 06:19:17,351][03835] Avg episode reward: [(0, '8.140'), (1, '8.810')] -[2023-10-16 06:19:17,469][05219] Updated weights for policy 1, policy_version 89360 (0.0010) -[2023-10-16 06:19:17,840][05219] Updated weights for policy 1, policy_version 89370 (0.0009) -[2023-10-16 06:19:18,073][05218] Updated weights for policy 0, policy_version 89642 (0.0008) -[2023-10-16 06:19:18,441][05218] Updated weights for policy 0, policy_version 89652 (0.0009) -[2023-10-16 06:19:18,826][05218] Updated weights for policy 0, policy_version 89662 (0.0007) -[2023-10-16 06:19:21,530][05219] Updated weights for policy 1, policy_version 89380 (0.0008) -[2023-10-16 06:19:21,901][05219] Updated weights for policy 1, policy_version 89390 (0.0007) -[2023-10-16 06:19:22,263][05219] Updated weights for policy 1, policy_version 89400 (0.0008) -[2023-10-16 06:19:22,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 183336960. Throughput: 0: 1800.0, 1: 1795.9. Samples: 45853250. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-16 06:19:22,351][03835] Avg episode reward: [(0, '7.460'), (1, '9.300')] -[2023-10-16 06:19:22,594][05218] Updated weights for policy 0, policy_version 89672 (0.0008) -[2023-10-16 06:19:22,966][05218] Updated weights for policy 0, policy_version 89682 (0.0008) -[2023-10-16 06:19:23,339][05218] Updated weights for policy 0, policy_version 89692 (0.0009) -[2023-10-16 06:19:26,063][05219] Updated weights for policy 1, policy_version 89410 (0.0008) -[2023-10-16 06:19:26,428][05219] Updated weights for policy 1, policy_version 89420 (0.0008) -[2023-10-16 06:19:26,789][05219] Updated weights for policy 1, policy_version 89430 (0.0007) -[2023-10-16 06:19:27,152][05218] Updated weights for policy 0, policy_version 89702 (0.0009) -[2023-10-16 06:19:27,157][05219] Updated weights for policy 1, policy_version 89440 (0.0008) -[2023-10-16 06:19:27,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 183435264. Throughput: 0: 1763.6, 1: 1789.0. Samples: 45863926. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-16 06:19:27,351][03835] Avg episode reward: [(0, '7.510'), (1, '9.080')] -[2023-10-16 06:19:27,544][05218] Updated weights for policy 0, policy_version 89712 (0.0007) -[2023-10-16 06:19:27,928][05218] Updated weights for policy 0, policy_version 89722 (0.0008) -[2023-10-16 06:19:30,885][05219] Updated weights for policy 1, policy_version 89450 (0.0009) -[2023-10-16 06:19:31,257][05219] Updated weights for policy 1, policy_version 89460 (0.0007) -[2023-10-16 06:19:31,562][05218] Updated weights for policy 0, policy_version 89732 (0.0008) -[2023-10-16 06:19:31,614][05219] Updated weights for policy 1, policy_version 89470 (0.0007) -[2023-10-16 06:19:31,927][05218] Updated weights for policy 0, policy_version 89742 (0.0007) -[2023-10-16 06:19:32,300][05218] Updated weights for policy 0, policy_version 89752 (0.0008) -[2023-10-16 06:19:32,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 183500800. Throughput: 0: 1793.3, 1: 1801.2. Samples: 45885614. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-16 06:19:32,351][03835] Avg episode reward: [(0, '8.250'), (1, '9.190')] -[2023-10-16 06:19:35,563][05219] Updated weights for policy 1, policy_version 89480 (0.0008) -[2023-10-16 06:19:35,861][05218] Updated weights for policy 0, policy_version 89762 (0.0009) -[2023-10-16 06:19:35,931][05219] Updated weights for policy 1, policy_version 89490 (0.0008) -[2023-10-16 06:19:36,232][05218] Updated weights for policy 0, policy_version 89772 (0.0009) -[2023-10-16 06:19:36,302][05219] Updated weights for policy 1, policy_version 89500 (0.0009) -[2023-10-16 06:19:36,609][05218] Updated weights for policy 0, policy_version 89782 (0.0008) -[2023-10-16 06:19:36,982][05218] Updated weights for policy 0, policy_version 89792 (0.0009) -[2023-10-16 06:19:37,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 183599104. Throughput: 0: 1768.5, 1: 1782.9. Samples: 45905696. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-16 06:19:37,351][03835] Avg episode reward: [(0, '8.140'), (1, '8.200')] -[2023-10-16 06:19:37,362][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000089504_91652096.pth... -[2023-10-16 06:19:37,362][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000089792_91947008.pth... -[2023-10-16 06:19:37,394][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000087840_89948160.pth -[2023-10-16 06:19:37,398][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000088096_90210304.pth -[2023-10-16 06:19:40,033][05219] Updated weights for policy 1, policy_version 89510 (0.0008) -[2023-10-16 06:19:40,404][05219] Updated weights for policy 1, policy_version 89520 (0.0007) -[2023-10-16 06:19:40,746][05218] Updated weights for policy 0, policy_version 89802 (0.0008) -[2023-10-16 06:19:40,771][05219] Updated weights for policy 1, policy_version 89530 (0.0010) -[2023-10-16 06:19:41,124][05218] Updated weights for policy 0, policy_version 89812 (0.0008) -[2023-10-16 06:19:41,494][05218] Updated weights for policy 0, policy_version 89822 (0.0007) -[2023-10-16 06:19:42,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 183664640. Throughput: 0: 1797.7, 1: 1807.0. Samples: 45918348. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-16 06:19:42,351][03835] Avg episode reward: [(0, '7.460'), (1, '8.960')] -[2023-10-16 06:19:44,503][05219] Updated weights for policy 1, policy_version 89540 (0.0009) -[2023-10-16 06:19:44,877][05219] Updated weights for policy 1, policy_version 89550 (0.0009) -[2023-10-16 06:19:45,233][05218] Updated weights for policy 0, policy_version 89832 (0.0008) -[2023-10-16 06:19:45,236][05219] Updated weights for policy 1, policy_version 89560 (0.0007) -[2023-10-16 06:19:45,602][05218] Updated weights for policy 0, policy_version 89842 (0.0010) -[2023-10-16 06:19:45,982][05218] Updated weights for policy 0, policy_version 89852 (0.0011) -[2023-10-16 06:19:47,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 183730176. Throughput: 0: 1780.5, 1: 1779.4. Samples: 45938242. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-16 06:19:47,351][03835] Avg episode reward: [(0, '7.700'), (1, '8.410')] -[2023-10-16 06:19:49,088][05219] Updated weights for policy 1, policy_version 89570 (0.0008) -[2023-10-16 06:19:49,450][05219] Updated weights for policy 1, policy_version 89580 (0.0007) -[2023-10-16 06:19:49,794][05218] Updated weights for policy 0, policy_version 89862 (0.0009) -[2023-10-16 06:19:49,821][05219] Updated weights for policy 1, policy_version 89590 (0.0008) -[2023-10-16 06:19:50,170][05218] Updated weights for policy 0, policy_version 89872 (0.0009) -[2023-10-16 06:19:50,178][05219] Updated weights for policy 1, policy_version 89600 (0.0007) -[2023-10-16 06:19:50,540][05218] Updated weights for policy 0, policy_version 89882 (0.0009) -[2023-10-16 06:19:52,351][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 183795712. Throughput: 0: 1785.2, 1: 1782.5. Samples: 45960696. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-16 06:19:52,352][03835] Avg episode reward: [(0, '7.690'), (1, '8.320')] -[2023-10-16 06:19:53,766][05219] Updated weights for policy 1, policy_version 89610 (0.0007) -[2023-10-16 06:19:54,129][05219] Updated weights for policy 1, policy_version 89620 (0.0007) -[2023-10-16 06:19:54,153][05218] Updated weights for policy 0, policy_version 89892 (0.0010) -[2023-10-16 06:19:54,495][05219] Updated weights for policy 1, policy_version 89630 (0.0008) -[2023-10-16 06:19:54,512][05218] Updated weights for policy 0, policy_version 89902 (0.0008) -[2023-10-16 06:19:54,888][05218] Updated weights for policy 0, policy_version 89912 (0.0008) -[2023-10-16 06:19:57,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.6, 300 sec: 14329.1). Total num frames: 183861248. Throughput: 0: 1787.3, 1: 1781.5. Samples: 45970546. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-16 06:19:57,351][03835] Avg episode reward: [(0, '6.800'), (1, '9.510')] -[2023-10-16 06:19:58,367][05219] Updated weights for policy 1, policy_version 89640 (0.0009) -[2023-10-16 06:19:58,658][05218] Updated weights for policy 0, policy_version 89922 (0.0009) -[2023-10-16 06:19:58,738][05219] Updated weights for policy 1, policy_version 89650 (0.0008) -[2023-10-16 06:19:59,031][05218] Updated weights for policy 0, policy_version 89932 (0.0009) -[2023-10-16 06:19:59,107][05219] Updated weights for policy 1, policy_version 89660 (0.0008) -[2023-10-16 06:19:59,412][05218] Updated weights for policy 0, policy_version 89942 (0.0008) -[2023-10-16 06:19:59,781][05218] Updated weights for policy 0, policy_version 89952 (0.0009) -[2023-10-16 06:20:02,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 183926784. Throughput: 0: 1792.6, 1: 1785.1. Samples: 45992864. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-16 06:20:02,351][03835] Avg episode reward: [(0, '7.100'), (1, '7.590')] -[2023-10-16 06:20:02,837][05219] Updated weights for policy 1, policy_version 89670 (0.0009) -[2023-10-16 06:20:03,190][05219] Updated weights for policy 1, policy_version 89680 (0.0009) -[2023-10-16 06:20:03,558][05219] Updated weights for policy 1, policy_version 89690 (0.0008) -[2023-10-16 06:20:03,685][05218] Updated weights for policy 0, policy_version 89962 (0.0008) -[2023-10-16 06:20:04,052][05218] Updated weights for policy 0, policy_version 89972 (0.0010) -[2023-10-16 06:20:04,427][05218] Updated weights for policy 0, policy_version 89982 (0.0010) -[2023-10-16 06:20:07,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 183992320. Throughput: 0: 1792.4, 1: 1803.2. Samples: 46015056. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-16 06:20:07,351][03835] Avg episode reward: [(0, '7.860'), (1, '9.150')] -[2023-10-16 06:20:07,405][05219] Updated weights for policy 1, policy_version 89700 (0.0009) -[2023-10-16 06:20:07,759][05219] Updated weights for policy 1, policy_version 89710 (0.0008) -[2023-10-16 06:20:08,127][05219] Updated weights for policy 1, policy_version 89720 (0.0008) -[2023-10-16 06:20:08,256][05218] Updated weights for policy 0, policy_version 89992 (0.0010) -[2023-10-16 06:20:08,636][05218] Updated weights for policy 0, policy_version 90002 (0.0007) -[2023-10-16 06:20:09,008][05218] Updated weights for policy 0, policy_version 90012 (0.0007) -[2023-10-16 06:20:11,875][05219] Updated weights for policy 1, policy_version 89730 (0.0009) -[2023-10-16 06:20:12,243][05219] Updated weights for policy 1, policy_version 89740 (0.0008) -[2023-10-16 06:20:12,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 184057856. Throughput: 0: 1796.0, 1: 1783.2. Samples: 46024992. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-16 06:20:12,351][03835] Avg episode reward: [(0, '7.390'), (1, '8.990')] -[2023-10-16 06:20:12,610][05219] Updated weights for policy 1, policy_version 89750 (0.0008) -[2023-10-16 06:20:12,722][05218] Updated weights for policy 0, policy_version 90022 (0.0008) -[2023-10-16 06:20:12,981][05219] Updated weights for policy 1, policy_version 89760 (0.0008) -[2023-10-16 06:20:13,095][05218] Updated weights for policy 0, policy_version 90032 (0.0008) -[2023-10-16 06:20:13,468][05218] Updated weights for policy 0, policy_version 90042 (0.0008) -[2023-10-16 06:20:16,721][05219] Updated weights for policy 1, policy_version 89770 (0.0008) -[2023-10-16 06:20:17,083][05219] Updated weights for policy 1, policy_version 89780 (0.0009) -[2023-10-16 06:20:17,256][05218] Updated weights for policy 0, policy_version 90052 (0.0009) -[2023-10-16 06:20:17,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 184123392. Throughput: 0: 1792.8, 1: 1799.5. Samples: 46047268. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-16 06:20:17,351][03835] Avg episode reward: [(0, '7.560'), (1, '7.590')] -[2023-10-16 06:20:17,435][05219] Updated weights for policy 1, policy_version 89790 (0.0010) -[2023-10-16 06:20:17,637][05218] Updated weights for policy 0, policy_version 90062 (0.0008) -[2023-10-16 06:20:18,003][05218] Updated weights for policy 0, policy_version 90072 (0.0011) -[2023-10-16 06:20:21,277][05219] Updated weights for policy 1, policy_version 89800 (0.0008) -[2023-10-16 06:20:21,645][05219] Updated weights for policy 1, policy_version 89810 (0.0008) -[2023-10-16 06:20:21,665][05218] Updated weights for policy 0, policy_version 90082 (0.0009) -[2023-10-16 06:20:21,995][05219] Updated weights for policy 1, policy_version 89820 (0.0008) -[2023-10-16 06:20:22,036][05218] Updated weights for policy 0, policy_version 90092 (0.0007) -[2023-10-16 06:20:22,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 184221696. Throughput: 0: 1806.6, 1: 1789.3. Samples: 46067514. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-16 06:20:22,351][03835] Avg episode reward: [(0, '7.300'), (1, '7.630')] -[2023-10-16 06:20:22,419][05218] Updated weights for policy 0, policy_version 90102 (0.0007) -[2023-10-16 06:20:22,793][05218] Updated weights for policy 0, policy_version 90112 (0.0009) -[2023-10-16 06:20:25,816][05219] Updated weights for policy 1, policy_version 89830 (0.0008) -[2023-10-16 06:20:26,176][05219] Updated weights for policy 1, policy_version 89840 (0.0008) -[2023-10-16 06:20:26,518][05218] Updated weights for policy 0, policy_version 90122 (0.0008) -[2023-10-16 06:20:26,537][05219] Updated weights for policy 1, policy_version 89850 (0.0008) -[2023-10-16 06:20:26,884][05218] Updated weights for policy 0, policy_version 90132 (0.0007) -[2023-10-16 06:20:27,268][05218] Updated weights for policy 0, policy_version 90142 (0.0008) -[2023-10-16 06:20:27,350][03835] Fps is (10 sec: 19660.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 184320000. Throughput: 0: 1784.4, 1: 1795.3. Samples: 46079430. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-16 06:20:27,351][03835] Avg episode reward: [(0, '8.360'), (1, '7.500')] -[2023-10-16 06:20:30,327][05219] Updated weights for policy 1, policy_version 89860 (0.0008) -[2023-10-16 06:20:30,690][05219] Updated weights for policy 1, policy_version 89870 (0.0010) -[2023-10-16 06:20:31,025][05218] Updated weights for policy 0, policy_version 90152 (0.0008) -[2023-10-16 06:20:31,045][05219] Updated weights for policy 1, policy_version 89880 (0.0008) -[2023-10-16 06:20:31,403][05218] Updated weights for policy 0, policy_version 90162 (0.0009) -[2023-10-16 06:20:31,771][05218] Updated weights for policy 0, policy_version 90172 (0.0009) -[2023-10-16 06:20:32,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 184385536. Throughput: 0: 1801.2, 1: 1794.5. Samples: 46100046. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-16 06:20:32,351][03835] Avg episode reward: [(0, '7.500'), (1, '7.470')] -[2023-10-16 06:20:34,791][05219] Updated weights for policy 1, policy_version 89890 (0.0007) -[2023-10-16 06:20:35,161][05219] Updated weights for policy 1, policy_version 89900 (0.0008) -[2023-10-16 06:20:35,518][05219] Updated weights for policy 1, policy_version 89910 (0.0008) -[2023-10-16 06:20:35,608][05218] Updated weights for policy 0, policy_version 90182 (0.0009) -[2023-10-16 06:20:35,879][05219] Updated weights for policy 1, policy_version 89920 (0.0008) -[2023-10-16 06:20:35,977][05218] Updated weights for policy 0, policy_version 90192 (0.0007) -[2023-10-16 06:20:36,354][05218] Updated weights for policy 0, policy_version 90202 (0.0008) -[2023-10-16 06:20:37,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 184451072. Throughput: 0: 1783.7, 1: 1786.7. Samples: 46121366. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-16 06:20:37,351][03835] Avg episode reward: [(0, '7.730'), (1, '7.740')] -[2023-10-16 06:20:39,583][05219] Updated weights for policy 1, policy_version 89930 (0.0008) -[2023-10-16 06:20:39,943][05219] Updated weights for policy 1, policy_version 89940 (0.0008) -[2023-10-16 06:20:39,980][05218] Updated weights for policy 0, policy_version 90212 (0.0007) -[2023-10-16 06:20:40,308][05219] Updated weights for policy 1, policy_version 89950 (0.0008) -[2023-10-16 06:20:40,363][05218] Updated weights for policy 0, policy_version 90222 (0.0007) -[2023-10-16 06:20:40,744][05218] Updated weights for policy 0, policy_version 90232 (0.0010) -[2023-10-16 06:20:42,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 184516608. Throughput: 0: 1804.5, 1: 1796.0. Samples: 46132568. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-16 06:20:42,351][03835] Avg episode reward: [(0, '8.290'), (1, '8.540')] -[2023-10-16 06:20:44,183][05219] Updated weights for policy 1, policy_version 89960 (0.0007) -[2023-10-16 06:20:44,540][05219] Updated weights for policy 1, policy_version 89970 (0.0007) -[2023-10-16 06:20:44,620][05218] Updated weights for policy 0, policy_version 90242 (0.0010) -[2023-10-16 06:20:44,897][05219] Updated weights for policy 1, policy_version 89980 (0.0007) -[2023-10-16 06:20:44,999][05218] Updated weights for policy 0, policy_version 90252 (0.0008) -[2023-10-16 06:20:45,379][05218] Updated weights for policy 0, policy_version 90262 (0.0008) -[2023-10-16 06:20:45,754][05218] Updated weights for policy 0, policy_version 90272 (0.0007) -[2023-10-16 06:20:47,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 184582144. Throughput: 0: 1783.1, 1: 1789.5. Samples: 46153630. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-16 06:20:47,351][03835] Avg episode reward: [(0, '7.410'), (1, '7.960')] -[2023-10-16 06:20:48,491][05219] Updated weights for policy 1, policy_version 89990 (0.0008) -[2023-10-16 06:20:48,851][05219] Updated weights for policy 1, policy_version 90000 (0.0007) -[2023-10-16 06:20:49,215][05219] Updated weights for policy 1, policy_version 90010 (0.0008) -[2023-10-16 06:20:49,491][05218] Updated weights for policy 0, policy_version 90282 (0.0007) -[2023-10-16 06:20:49,858][05218] Updated weights for policy 0, policy_version 90292 (0.0009) -[2023-10-16 06:20:50,234][05218] Updated weights for policy 0, policy_version 90302 (0.0009) -[2023-10-16 06:20:52,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.6, 300 sec: 14329.1). Total num frames: 184647680. Throughput: 0: 1787.0, 1: 1791.6. Samples: 46176090. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-16 06:20:52,351][03835] Avg episode reward: [(0, '7.390'), (1, '7.660')] -[2023-10-16 06:20:52,952][05219] Updated weights for policy 1, policy_version 90020 (0.0008) -[2023-10-16 06:20:53,318][05219] Updated weights for policy 1, policy_version 90030 (0.0007) -[2023-10-16 06:20:53,683][05219] Updated weights for policy 1, policy_version 90040 (0.0008) -[2023-10-16 06:20:53,970][05218] Updated weights for policy 0, policy_version 90312 (0.0009) -[2023-10-16 06:20:54,347][05218] Updated weights for policy 0, policy_version 90322 (0.0010) -[2023-10-16 06:20:54,710][05218] Updated weights for policy 0, policy_version 90332 (0.0011) -[2023-10-16 06:20:57,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 184713216. Throughput: 0: 1784.1, 1: 1790.0. Samples: 46185826. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-16 06:20:57,351][03835] Avg episode reward: [(0, '7.520'), (1, '7.620')] -[2023-10-16 06:20:57,483][05219] Updated weights for policy 1, policy_version 90050 (0.0008) -[2023-10-16 06:20:57,850][05219] Updated weights for policy 1, policy_version 90060 (0.0007) -[2023-10-16 06:20:58,215][05219] Updated weights for policy 1, policy_version 90070 (0.0007) -[2023-10-16 06:20:58,460][05218] Updated weights for policy 0, policy_version 90342 (0.0007) -[2023-10-16 06:20:58,575][05219] Updated weights for policy 1, policy_version 90080 (0.0007) -[2023-10-16 06:20:58,840][05218] Updated weights for policy 0, policy_version 90352 (0.0007) -[2023-10-16 06:20:59,209][05218] Updated weights for policy 0, policy_version 90362 (0.0007) -[2023-10-16 06:21:02,334][05219] Updated weights for policy 1, policy_version 90090 (0.0008) -[2023-10-16 06:21:02,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 184778752. Throughput: 0: 1786.3, 1: 1791.6. Samples: 46208274. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-16 06:21:02,351][03835] Avg episode reward: [(0, '8.400'), (1, '7.250')] -[2023-10-16 06:21:02,699][05219] Updated weights for policy 1, policy_version 90100 (0.0009) -[2023-10-16 06:21:02,843][05218] Updated weights for policy 0, policy_version 90372 (0.0008) -[2023-10-16 06:21:03,071][05219] Updated weights for policy 1, policy_version 90110 (0.0008) -[2023-10-16 06:21:03,207][05218] Updated weights for policy 0, policy_version 90382 (0.0010) -[2023-10-16 06:21:03,587][05218] Updated weights for policy 0, policy_version 90392 (0.0007) -[2023-10-16 06:21:06,915][05219] Updated weights for policy 1, policy_version 90120 (0.0007) -[2023-10-16 06:21:07,274][05219] Updated weights for policy 1, policy_version 90130 (0.0007) -[2023-10-16 06:21:07,333][05218] Updated weights for policy 0, policy_version 90402 (0.0008) -[2023-10-16 06:21:07,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 184844288. Throughput: 0: 1799.7, 1: 1805.8. Samples: 46229764. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-16 06:21:07,351][03835] Avg episode reward: [(0, '7.810'), (1, '7.680')] -[2023-10-16 06:21:07,635][05219] Updated weights for policy 1, policy_version 90140 (0.0008) -[2023-10-16 06:21:07,707][05218] Updated weights for policy 0, policy_version 90412 (0.0009) -[2023-10-16 06:21:08,078][05218] Updated weights for policy 0, policy_version 90422 (0.0010) -[2023-10-16 06:21:08,451][05218] Updated weights for policy 0, policy_version 90432 (0.0009) -[2023-10-16 06:21:11,390][05219] Updated weights for policy 1, policy_version 90150 (0.0009) -[2023-10-16 06:21:11,757][05219] Updated weights for policy 1, policy_version 90160 (0.0008) -[2023-10-16 06:21:12,121][05219] Updated weights for policy 1, policy_version 90170 (0.0007) -[2023-10-16 06:21:12,272][05218] Updated weights for policy 0, policy_version 90442 (0.0009) -[2023-10-16 06:21:12,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 184942592. Throughput: 0: 1785.7, 1: 1791.1. Samples: 46240384. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-16 06:21:12,351][03835] Avg episode reward: [(0, '6.960'), (1, '8.640')] -[2023-10-16 06:21:12,644][05218] Updated weights for policy 0, policy_version 90452 (0.0008) -[2023-10-16 06:21:13,026][05218] Updated weights for policy 0, policy_version 90462 (0.0008) -[2023-10-16 06:21:16,091][05219] Updated weights for policy 1, policy_version 90180 (0.0008) -[2023-10-16 06:21:16,460][05219] Updated weights for policy 1, policy_version 90190 (0.0008) -[2023-10-16 06:21:16,818][05219] Updated weights for policy 1, policy_version 90200 (0.0009) -[2023-10-16 06:21:16,860][05218] Updated weights for policy 0, policy_version 90472 (0.0007) -[2023-10-16 06:21:17,234][05218] Updated weights for policy 0, policy_version 90482 (0.0008) -[2023-10-16 06:21:17,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 185008128. Throughput: 0: 1802.5, 1: 1807.8. Samples: 46262512. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-16 06:21:17,351][03835] Avg episode reward: [(0, '7.750'), (1, '8.490')] -[2023-10-16 06:21:17,604][05218] Updated weights for policy 0, policy_version 90492 (0.0009) -[2023-10-16 06:21:20,501][05219] Updated weights for policy 1, policy_version 90210 (0.0009) -[2023-10-16 06:21:20,869][05219] Updated weights for policy 1, policy_version 90220 (0.0010) -[2023-10-16 06:21:21,230][05219] Updated weights for policy 1, policy_version 90230 (0.0009) -[2023-10-16 06:21:21,336][05218] Updated weights for policy 0, policy_version 90502 (0.0008) -[2023-10-16 06:21:21,594][05219] Updated weights for policy 1, policy_version 90240 (0.0007) -[2023-10-16 06:21:21,715][05218] Updated weights for policy 0, policy_version 90512 (0.0009) -[2023-10-16 06:21:22,083][05218] Updated weights for policy 0, policy_version 90522 (0.0008) -[2023-10-16 06:21:22,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 185106432. Throughput: 0: 1785.8, 1: 1785.4. Samples: 46282070. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-16 06:21:22,351][03835] Avg episode reward: [(0, '7.770'), (1, '8.030')] -[2023-10-16 06:21:25,466][05219] Updated weights for policy 1, policy_version 90250 (0.0011) -[2023-10-16 06:21:25,835][05219] Updated weights for policy 1, policy_version 90260 (0.0008) -[2023-10-16 06:21:25,857][05218] Updated weights for policy 0, policy_version 90532 (0.0009) -[2023-10-16 06:21:26,196][05219] Updated weights for policy 1, policy_version 90270 (0.0007) -[2023-10-16 06:21:26,227][05218] Updated weights for policy 0, policy_version 90542 (0.0008) -[2023-10-16 06:21:26,606][05218] Updated weights for policy 0, policy_version 90552 (0.0009) -[2023-10-16 06:21:27,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 185171968. Throughput: 0: 1796.9, 1: 1802.8. Samples: 46294556. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-16 06:21:27,352][03835] Avg episode reward: [(0, '7.560'), (1, '8.010')] -[2023-10-16 06:21:29,872][05219] Updated weights for policy 1, policy_version 90280 (0.0008) -[2023-10-16 06:21:30,172][05218] Updated weights for policy 0, policy_version 90562 (0.0007) -[2023-10-16 06:21:30,243][05219] Updated weights for policy 1, policy_version 90290 (0.0007) -[2023-10-16 06:21:30,556][05218] Updated weights for policy 0, policy_version 90572 (0.0007) -[2023-10-16 06:21:30,607][05219] Updated weights for policy 1, policy_version 90300 (0.0007) -[2023-10-16 06:21:30,926][05218] Updated weights for policy 0, policy_version 90582 (0.0007) -[2023-10-16 06:21:31,298][05218] Updated weights for policy 0, policy_version 90592 (0.0007) -[2023-10-16 06:21:32,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 185237504. Throughput: 0: 1793.2, 1: 1778.6. Samples: 46314360. Policy #0 lag: (min: 31.0, avg: 33.0, max: 61.0) -[2023-10-16 06:21:32,352][03835] Avg episode reward: [(0, '7.150'), (1, '6.600')] -[2023-10-16 06:21:34,480][05219] Updated weights for policy 1, policy_version 90310 (0.0009) -[2023-10-16 06:21:34,841][05219] Updated weights for policy 1, policy_version 90320 (0.0008) -[2023-10-16 06:21:34,905][05218] Updated weights for policy 0, policy_version 90602 (0.0008) -[2023-10-16 06:21:35,205][05219] Updated weights for policy 1, policy_version 90330 (0.0007) -[2023-10-16 06:21:35,274][05218] Updated weights for policy 0, policy_version 90612 (0.0008) -[2023-10-16 06:21:35,647][05218] Updated weights for policy 0, policy_version 90622 (0.0010) -[2023-10-16 06:21:37,351][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 185303040. Throughput: 0: 1795.1, 1: 1772.4. Samples: 46336626. Policy #0 lag: (min: 31.0, avg: 33.0, max: 61.0) -[2023-10-16 06:21:37,352][03835] Avg episode reward: [(0, '8.580'), (1, '6.720')] -[2023-10-16 06:21:37,365][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000090624_92798976.pth... -[2023-10-16 06:21:37,366][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000090336_92504064.pth... -[2023-10-16 06:21:37,401][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000088672_90800128.pth -[2023-10-16 06:21:37,407][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000088960_91095040.pth -[2023-10-16 06:21:39,114][05219] Updated weights for policy 1, policy_version 90340 (0.0009) -[2023-10-16 06:21:39,472][05219] Updated weights for policy 1, policy_version 90350 (0.0007) -[2023-10-16 06:21:39,528][05218] Updated weights for policy 0, policy_version 90632 (0.0007) -[2023-10-16 06:21:39,836][05219] Updated weights for policy 1, policy_version 90360 (0.0008) -[2023-10-16 06:21:39,896][05218] Updated weights for policy 0, policy_version 90642 (0.0007) -[2023-10-16 06:21:40,280][05218] Updated weights for policy 0, policy_version 90652 (0.0010) -[2023-10-16 06:21:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 185368576. Throughput: 0: 1798.1, 1: 1775.6. Samples: 46346642. Policy #0 lag: (min: 31.0, avg: 33.0, max: 61.0) -[2023-10-16 06:21:42,351][03835] Avg episode reward: [(0, '8.240'), (1, '6.410')] -[2023-10-16 06:21:43,544][05219] Updated weights for policy 1, policy_version 90370 (0.0007) -[2023-10-16 06:21:43,917][05219] Updated weights for policy 1, policy_version 90380 (0.0007) -[2023-10-16 06:21:44,107][05218] Updated weights for policy 0, policy_version 90662 (0.0008) -[2023-10-16 06:21:44,285][05219] Updated weights for policy 1, policy_version 90390 (0.0008) -[2023-10-16 06:21:44,480][05218] Updated weights for policy 0, policy_version 90672 (0.0007) -[2023-10-16 06:21:44,642][05219] Updated weights for policy 1, policy_version 90400 (0.0008) -[2023-10-16 06:21:44,856][05218] Updated weights for policy 0, policy_version 90682 (0.0009) -[2023-10-16 06:21:47,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 185434112. Throughput: 0: 1789.4, 1: 1772.2. Samples: 46368548. Policy #0 lag: (min: 31.0, avg: 33.0, max: 61.0) -[2023-10-16 06:21:47,351][03835] Avg episode reward: [(0, '7.200'), (1, '7.440')] -[2023-10-16 06:21:48,368][05219] Updated weights for policy 1, policy_version 90410 (0.0009) -[2023-10-16 06:21:48,712][05218] Updated weights for policy 0, policy_version 90692 (0.0011) -[2023-10-16 06:21:48,736][05219] Updated weights for policy 1, policy_version 90420 (0.0009) -[2023-10-16 06:21:49,095][05219] Updated weights for policy 1, policy_version 90430 (0.0008) -[2023-10-16 06:21:49,104][05218] Updated weights for policy 0, policy_version 90702 (0.0010) -[2023-10-16 06:21:49,485][05218] Updated weights for policy 0, policy_version 90712 (0.0008) -[2023-10-16 06:21:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 185499648. Throughput: 0: 1788.9, 1: 1787.2. Samples: 46390686. Policy #0 lag: (min: 31.0, avg: 33.0, max: 61.0) -[2023-10-16 06:21:52,351][03835] Avg episode reward: [(0, '8.380'), (1, '7.890')] -[2023-10-16 06:21:52,944][05219] Updated weights for policy 1, policy_version 90440 (0.0009) -[2023-10-16 06:21:53,206][05218] Updated weights for policy 0, policy_version 90722 (0.0008) -[2023-10-16 06:21:53,313][05219] Updated weights for policy 1, policy_version 90450 (0.0010) -[2023-10-16 06:21:53,589][05218] Updated weights for policy 0, policy_version 90732 (0.0009) -[2023-10-16 06:21:53,680][05219] Updated weights for policy 1, policy_version 90460 (0.0008) -[2023-10-16 06:21:53,960][05218] Updated weights for policy 0, policy_version 90742 (0.0007) -[2023-10-16 06:21:54,333][05218] Updated weights for policy 0, policy_version 90752 (0.0008) -[2023-10-16 06:21:57,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 185565184. Throughput: 0: 1788.7, 1: 1772.5. Samples: 46400636. Policy #0 lag: (min: 31.0, avg: 33.0, max: 61.0) -[2023-10-16 06:21:57,351][03835] Avg episode reward: [(0, '9.360'), (1, '7.150')] -[2023-10-16 06:21:57,352][04766] Saving new best policy, reward=9.360! -[2023-10-16 06:21:57,491][05219] Updated weights for policy 1, policy_version 90470 (0.0009) -[2023-10-16 06:21:57,860][05219] Updated weights for policy 1, policy_version 90480 (0.0008) -[2023-10-16 06:21:57,999][05218] Updated weights for policy 0, policy_version 90762 (0.0009) -[2023-10-16 06:21:58,227][05219] Updated weights for policy 1, policy_version 90490 (0.0008) -[2023-10-16 06:21:58,382][05218] Updated weights for policy 0, policy_version 90772 (0.0007) -[2023-10-16 06:21:58,755][05218] Updated weights for policy 0, policy_version 90782 (0.0007) -[2023-10-16 06:22:01,992][05219] Updated weights for policy 1, policy_version 90500 (0.0009) -[2023-10-16 06:22:02,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 185630720. Throughput: 0: 1787.1, 1: 1770.4. Samples: 46422600. Policy #0 lag: (min: 31.0, avg: 33.0, max: 61.0) -[2023-10-16 06:22:02,352][03835] Avg episode reward: [(0, '7.410'), (1, '8.560')] -[2023-10-16 06:22:02,353][05219] Updated weights for policy 1, policy_version 90510 (0.0007) -[2023-10-16 06:22:02,434][05218] Updated weights for policy 0, policy_version 90792 (0.0009) -[2023-10-16 06:22:02,722][05219] Updated weights for policy 1, policy_version 90520 (0.0009) -[2023-10-16 06:22:02,805][05218] Updated weights for policy 0, policy_version 90802 (0.0008) -[2023-10-16 06:22:03,181][05218] Updated weights for policy 0, policy_version 90812 (0.0007) -[2023-10-16 06:22:06,565][05219] Updated weights for policy 1, policy_version 90530 (0.0007) -[2023-10-16 06:22:06,931][05219] Updated weights for policy 1, policy_version 90540 (0.0007) -[2023-10-16 06:22:07,085][05218] Updated weights for policy 0, policy_version 90822 (0.0007) -[2023-10-16 06:22:07,302][05219] Updated weights for policy 1, policy_version 90550 (0.0009) -[2023-10-16 06:22:07,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 185696256. Throughput: 0: 1804.2, 1: 1779.0. Samples: 46443314. Policy #0 lag: (min: 31.0, avg: 33.0, max: 61.0) -[2023-10-16 06:22:07,351][03835] Avg episode reward: [(0, '7.650'), (1, '8.940')] -[2023-10-16 06:22:07,457][05218] Updated weights for policy 0, policy_version 90832 (0.0009) -[2023-10-16 06:22:07,671][05219] Updated weights for policy 1, policy_version 90560 (0.0008) -[2023-10-16 06:22:07,829][05218] Updated weights for policy 0, policy_version 90842 (0.0010) -[2023-10-16 06:22:11,440][05219] Updated weights for policy 1, policy_version 90570 (0.0008) -[2023-10-16 06:22:11,724][05218] Updated weights for policy 0, policy_version 90852 (0.0009) -[2023-10-16 06:22:11,800][05219] Updated weights for policy 1, policy_version 90580 (0.0008) -[2023-10-16 06:22:12,097][05218] Updated weights for policy 0, policy_version 90862 (0.0009) -[2023-10-16 06:22:12,164][05219] Updated weights for policy 1, policy_version 90590 (0.0009) -[2023-10-16 06:22:12,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 185794560. Throughput: 0: 1782.2, 1: 1763.6. Samples: 46454114. Policy #0 lag: (min: 31.0, avg: 33.0, max: 61.0) -[2023-10-16 06:22:12,351][03835] Avg episode reward: [(0, '8.780'), (1, '7.910')] -[2023-10-16 06:22:12,468][05218] Updated weights for policy 0, policy_version 90872 (0.0009) -[2023-10-16 06:22:16,039][05219] Updated weights for policy 1, policy_version 90600 (0.0009) -[2023-10-16 06:22:16,155][05218] Updated weights for policy 0, policy_version 90882 (0.0009) -[2023-10-16 06:22:16,413][05219] Updated weights for policy 1, policy_version 90610 (0.0007) -[2023-10-16 06:22:16,525][05218] Updated weights for policy 0, policy_version 90892 (0.0007) -[2023-10-16 06:22:16,774][05219] Updated weights for policy 1, policy_version 90620 (0.0008) -[2023-10-16 06:22:16,897][05218] Updated weights for policy 0, policy_version 90902 (0.0007) -[2023-10-16 06:22:17,271][05218] Updated weights for policy 0, policy_version 90912 (0.0007) -[2023-10-16 06:22:17,350][03835] Fps is (10 sec: 19661.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 185892864. Throughput: 0: 1800.0, 1: 1786.2. Samples: 46475736. Policy #0 lag: (min: 31.0, avg: 33.0, max: 61.0) -[2023-10-16 06:22:17,351][03835] Avg episode reward: [(0, '7.370'), (1, '9.470')] -[2023-10-16 06:22:20,683][05219] Updated weights for policy 1, policy_version 90630 (0.0008) -[2023-10-16 06:22:20,976][05218] Updated weights for policy 0, policy_version 90922 (0.0008) -[2023-10-16 06:22:21,050][05219] Updated weights for policy 1, policy_version 90640 (0.0008) -[2023-10-16 06:22:21,347][05218] Updated weights for policy 0, policy_version 90932 (0.0008) -[2023-10-16 06:22:21,420][05219] Updated weights for policy 1, policy_version 90650 (0.0007) -[2023-10-16 06:22:21,723][05218] Updated weights for policy 0, policy_version 90942 (0.0009) -[2023-10-16 06:22:22,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 185958400. Throughput: 0: 1767.8, 1: 1766.1. Samples: 46495650. Policy #0 lag: (min: 31.0, avg: 33.0, max: 61.0) -[2023-10-16 06:22:22,351][03835] Avg episode reward: [(0, '7.040'), (1, '8.350')] -[2023-10-16 06:22:25,241][05219] Updated weights for policy 1, policy_version 90660 (0.0008) -[2023-10-16 06:22:25,591][05218] Updated weights for policy 0, policy_version 90952 (0.0009) -[2023-10-16 06:22:25,609][05219] Updated weights for policy 1, policy_version 90670 (0.0007) -[2023-10-16 06:22:25,965][05218] Updated weights for policy 0, policy_version 90962 (0.0009) -[2023-10-16 06:22:25,977][05219] Updated weights for policy 1, policy_version 90680 (0.0007) -[2023-10-16 06:22:26,348][05218] Updated weights for policy 0, policy_version 90972 (0.0010) -[2023-10-16 06:22:27,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 186023936. Throughput: 0: 1797.3, 1: 1793.2. Samples: 46508214. Policy #0 lag: (min: 31.0, avg: 33.0, max: 61.0) -[2023-10-16 06:22:27,351][03835] Avg episode reward: [(0, '7.130'), (1, '8.010')] -[2023-10-16 06:22:29,836][05219] Updated weights for policy 1, policy_version 90690 (0.0007) -[2023-10-16 06:22:30,051][05218] Updated weights for policy 0, policy_version 90982 (0.0008) -[2023-10-16 06:22:30,202][05219] Updated weights for policy 1, policy_version 90700 (0.0008) -[2023-10-16 06:22:30,423][05218] Updated weights for policy 0, policy_version 90992 (0.0009) -[2023-10-16 06:22:30,566][05219] Updated weights for policy 1, policy_version 90710 (0.0007) -[2023-10-16 06:22:30,800][05218] Updated weights for policy 0, policy_version 91002 (0.0009) -[2023-10-16 06:22:30,932][05219] Updated weights for policy 1, policy_version 90720 (0.0007) -[2023-10-16 06:22:32,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 186089472. Throughput: 0: 1774.2, 1: 1766.0. Samples: 46527854. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:22:32,351][03835] Avg episode reward: [(0, '8.180'), (1, '8.120')] -[2023-10-16 06:22:34,520][05219] Updated weights for policy 1, policy_version 90730 (0.0008) -[2023-10-16 06:22:34,749][05218] Updated weights for policy 0, policy_version 91012 (0.0009) -[2023-10-16 06:22:34,892][05219] Updated weights for policy 1, policy_version 90740 (0.0007) -[2023-10-16 06:22:35,136][05218] Updated weights for policy 0, policy_version 91022 (0.0007) -[2023-10-16 06:22:35,255][05219] Updated weights for policy 1, policy_version 90750 (0.0009) -[2023-10-16 06:22:35,504][05218] Updated weights for policy 0, policy_version 91032 (0.0007) -[2023-10-16 06:22:37,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 186155008. Throughput: 0: 1768.8, 1: 1766.3. Samples: 46549762. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:22:37,351][03835] Avg episode reward: [(0, '7.180'), (1, '9.120')] -[2023-10-16 06:22:39,051][05219] Updated weights for policy 1, policy_version 90760 (0.0009) -[2023-10-16 06:22:39,207][05218] Updated weights for policy 0, policy_version 91042 (0.0008) -[2023-10-16 06:22:39,415][05219] Updated weights for policy 1, policy_version 90770 (0.0008) -[2023-10-16 06:22:39,571][05218] Updated weights for policy 0, policy_version 91052 (0.0009) -[2023-10-16 06:22:39,785][05219] Updated weights for policy 1, policy_version 90780 (0.0008) -[2023-10-16 06:22:39,951][05218] Updated weights for policy 0, policy_version 91062 (0.0009) -[2023-10-16 06:22:40,329][05218] Updated weights for policy 0, policy_version 91072 (0.0008) -[2023-10-16 06:22:42,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 186220544. Throughput: 0: 1770.1, 1: 1766.7. Samples: 46559792. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:22:42,351][03835] Avg episode reward: [(0, '7.200'), (1, '8.400')] -[2023-10-16 06:22:43,729][05219] Updated weights for policy 1, policy_version 90790 (0.0007) -[2023-10-16 06:22:44,098][05219] Updated weights for policy 1, policy_version 90800 (0.0008) -[2023-10-16 06:22:44,100][05218] Updated weights for policy 0, policy_version 91082 (0.0008) -[2023-10-16 06:22:44,458][05219] Updated weights for policy 1, policy_version 90810 (0.0008) -[2023-10-16 06:22:44,474][05218] Updated weights for policy 0, policy_version 91092 (0.0008) -[2023-10-16 06:22:44,844][05218] Updated weights for policy 0, policy_version 91102 (0.0007) -[2023-10-16 06:22:47,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 186286080. Throughput: 0: 1765.6, 1: 1769.6. Samples: 46581684. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:22:47,351][03835] Avg episode reward: [(0, '8.460'), (1, '8.570')] -[2023-10-16 06:22:48,211][05219] Updated weights for policy 1, policy_version 90820 (0.0007) -[2023-10-16 06:22:48,574][05219] Updated weights for policy 1, policy_version 90830 (0.0009) -[2023-10-16 06:22:48,781][05218] Updated weights for policy 0, policy_version 91112 (0.0009) -[2023-10-16 06:22:48,942][05219] Updated weights for policy 1, policy_version 90840 (0.0008) -[2023-10-16 06:22:49,157][05218] Updated weights for policy 0, policy_version 91122 (0.0008) -[2023-10-16 06:22:49,537][05218] Updated weights for policy 0, policy_version 91132 (0.0008) -[2023-10-16 06:22:52,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 186351616. Throughput: 0: 1779.6, 1: 1789.7. Samples: 46603932. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:22:52,351][03835] Avg episode reward: [(0, '7.290'), (1, '9.210')] -[2023-10-16 06:22:52,707][05219] Updated weights for policy 1, policy_version 90850 (0.0007) -[2023-10-16 06:22:53,063][05219] Updated weights for policy 1, policy_version 90860 (0.0007) -[2023-10-16 06:22:53,269][05218] Updated weights for policy 0, policy_version 91142 (0.0008) -[2023-10-16 06:22:53,428][05219] Updated weights for policy 1, policy_version 90870 (0.0008) -[2023-10-16 06:22:53,645][05218] Updated weights for policy 0, policy_version 91152 (0.0008) -[2023-10-16 06:22:53,787][05219] Updated weights for policy 1, policy_version 90880 (0.0007) -[2023-10-16 06:22:54,019][05218] Updated weights for policy 0, policy_version 91162 (0.0008) -[2023-10-16 06:22:57,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 186417152. Throughput: 0: 1768.3, 1: 1780.1. Samples: 46613794. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:22:57,352][03835] Avg episode reward: [(0, '7.690'), (1, '7.830')] -[2023-10-16 06:22:57,488][05219] Updated weights for policy 1, policy_version 90890 (0.0008) -[2023-10-16 06:22:57,641][05218] Updated weights for policy 0, policy_version 91172 (0.0008) -[2023-10-16 06:22:57,854][05219] Updated weights for policy 1, policy_version 90900 (0.0007) -[2023-10-16 06:22:58,017][05218] Updated weights for policy 0, policy_version 91182 (0.0009) -[2023-10-16 06:22:58,216][05219] Updated weights for policy 1, policy_version 90910 (0.0009) -[2023-10-16 06:22:58,392][05218] Updated weights for policy 0, policy_version 91192 (0.0008) -[2023-10-16 06:23:02,031][05219] Updated weights for policy 1, policy_version 90920 (0.0008) -[2023-10-16 06:23:02,127][05218] Updated weights for policy 0, policy_version 91202 (0.0009) -[2023-10-16 06:23:02,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 186482688. Throughput: 0: 1782.4, 1: 1792.2. Samples: 46636592. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:23:02,351][03835] Avg episode reward: [(0, '7.760'), (1, '8.020')] -[2023-10-16 06:23:02,405][05219] Updated weights for policy 1, policy_version 90930 (0.0007) -[2023-10-16 06:23:02,494][05218] Updated weights for policy 0, policy_version 91212 (0.0008) -[2023-10-16 06:23:02,779][05219] Updated weights for policy 1, policy_version 90940 (0.0007) -[2023-10-16 06:23:02,871][05218] Updated weights for policy 0, policy_version 91222 (0.0009) -[2023-10-16 06:23:03,231][05218] Updated weights for policy 0, policy_version 91232 (0.0010) -[2023-10-16 06:23:06,386][05219] Updated weights for policy 1, policy_version 90950 (0.0009) -[2023-10-16 06:23:06,759][05219] Updated weights for policy 1, policy_version 90960 (0.0009) -[2023-10-16 06:23:07,003][05218] Updated weights for policy 0, policy_version 91242 (0.0007) -[2023-10-16 06:23:07,120][05219] Updated weights for policy 1, policy_version 90970 (0.0008) -[2023-10-16 06:23:07,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 186580992. Throughput: 0: 1791.1, 1: 1792.6. Samples: 46656914. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:23:07,352][03835] Avg episode reward: [(0, '6.130'), (1, '7.720')] -[2023-10-16 06:23:07,375][05218] Updated weights for policy 0, policy_version 91252 (0.0007) -[2023-10-16 06:23:07,759][05218] Updated weights for policy 0, policy_version 91262 (0.0007) -[2023-10-16 06:23:10,817][05219] Updated weights for policy 1, policy_version 90980 (0.0009) -[2023-10-16 06:23:11,180][05219] Updated weights for policy 1, policy_version 90990 (0.0008) -[2023-10-16 06:23:11,353][05218] Updated weights for policy 0, policy_version 91272 (0.0008) -[2023-10-16 06:23:11,553][05219] Updated weights for policy 1, policy_version 91000 (0.0010) -[2023-10-16 06:23:11,728][05218] Updated weights for policy 0, policy_version 91282 (0.0008) -[2023-10-16 06:23:12,102][05218] Updated weights for policy 0, policy_version 91292 (0.0010) -[2023-10-16 06:23:12,350][03835] Fps is (10 sec: 19660.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 186679296. Throughput: 0: 1780.1, 1: 1786.8. Samples: 46668722. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:23:12,351][03835] Avg episode reward: [(0, '7.200'), (1, '8.160')] -[2023-10-16 06:23:15,258][05219] Updated weights for policy 1, policy_version 91010 (0.0007) -[2023-10-16 06:23:15,621][05219] Updated weights for policy 1, policy_version 91020 (0.0009) -[2023-10-16 06:23:15,924][05218] Updated weights for policy 0, policy_version 91302 (0.0008) -[2023-10-16 06:23:15,983][05219] Updated weights for policy 1, policy_version 91030 (0.0008) -[2023-10-16 06:23:16,298][05218] Updated weights for policy 0, policy_version 91312 (0.0007) -[2023-10-16 06:23:16,344][05219] Updated weights for policy 1, policy_version 91040 (0.0008) -[2023-10-16 06:23:16,678][05218] Updated weights for policy 0, policy_version 91322 (0.0009) -[2023-10-16 06:23:17,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 186744832. Throughput: 0: 1794.6, 1: 1792.5. Samples: 46689276. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:23:17,351][03835] Avg episode reward: [(0, '7.710'), (1, '7.630')] -[2023-10-16 06:23:20,130][05219] Updated weights for policy 1, policy_version 91050 (0.0007) -[2023-10-16 06:23:20,443][05218] Updated weights for policy 0, policy_version 91332 (0.0009) -[2023-10-16 06:23:20,504][05219] Updated weights for policy 1, policy_version 91060 (0.0007) -[2023-10-16 06:23:20,841][05218] Updated weights for policy 0, policy_version 91342 (0.0009) -[2023-10-16 06:23:20,870][05219] Updated weights for policy 1, policy_version 91070 (0.0008) -[2023-10-16 06:23:21,214][05218] Updated weights for policy 0, policy_version 91352 (0.0009) -[2023-10-16 06:23:22,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 186810368. Throughput: 0: 1787.0, 1: 1786.7. Samples: 46710578. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:23:22,352][03835] Avg episode reward: [(0, '7.850'), (1, '7.660')] -[2023-10-16 06:23:24,742][05219] Updated weights for policy 1, policy_version 91080 (0.0009) -[2023-10-16 06:23:24,799][05218] Updated weights for policy 0, policy_version 91362 (0.0009) -[2023-10-16 06:23:25,119][05219] Updated weights for policy 1, policy_version 91090 (0.0008) -[2023-10-16 06:23:25,169][05218] Updated weights for policy 0, policy_version 91372 (0.0008) -[2023-10-16 06:23:25,481][05219] Updated weights for policy 1, policy_version 91100 (0.0007) -[2023-10-16 06:23:25,552][05218] Updated weights for policy 0, policy_version 91382 (0.0010) -[2023-10-16 06:23:25,915][05218] Updated weights for policy 0, policy_version 91392 (0.0010) -[2023-10-16 06:23:27,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 186875904. Throughput: 0: 1799.1, 1: 1798.0. Samples: 46721666. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:23:27,351][03835] Avg episode reward: [(0, '7.800'), (1, '7.330')] -[2023-10-16 06:23:29,229][05219] Updated weights for policy 1, policy_version 91110 (0.0008) -[2023-10-16 06:23:29,590][05219] Updated weights for policy 1, policy_version 91120 (0.0007) -[2023-10-16 06:23:29,637][05218] Updated weights for policy 0, policy_version 91402 (0.0007) -[2023-10-16 06:23:29,956][05219] Updated weights for policy 1, policy_version 91130 (0.0007) -[2023-10-16 06:23:30,010][05218] Updated weights for policy 0, policy_version 91412 (0.0008) -[2023-10-16 06:23:30,390][05218] Updated weights for policy 0, policy_version 91422 (0.0009) -[2023-10-16 06:23:32,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 186941440. Throughput: 0: 1789.7, 1: 1791.6. Samples: 46742844. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-16 06:23:32,351][03835] Avg episode reward: [(0, '8.070'), (1, '7.240')] -[2023-10-16 06:23:33,757][05219] Updated weights for policy 1, policy_version 91140 (0.0008) -[2023-10-16 06:23:34,053][05218] Updated weights for policy 0, policy_version 91432 (0.0009) -[2023-10-16 06:23:34,120][05219] Updated weights for policy 1, policy_version 91150 (0.0008) -[2023-10-16 06:23:34,429][05218] Updated weights for policy 0, policy_version 91442 (0.0007) -[2023-10-16 06:23:34,483][05219] Updated weights for policy 1, policy_version 91160 (0.0008) -[2023-10-16 06:23:34,809][05218] Updated weights for policy 0, policy_version 91452 (0.0009) -[2023-10-16 06:23:37,351][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 187006976. Throughput: 0: 1796.1, 1: 1791.0. Samples: 46765352. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-16 06:23:37,352][03835] Avg episode reward: [(0, '7.990'), (1, '7.560')] -[2023-10-16 06:23:37,362][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000091456_93650944.pth... -[2023-10-16 06:23:37,362][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000091168_93356032.pth... -[2023-10-16 06:23:37,397][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000089792_91947008.pth -[2023-10-16 06:23:37,398][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000089504_91652096.pth -[2023-10-16 06:23:38,318][05219] Updated weights for policy 1, policy_version 91170 (0.0007) -[2023-10-16 06:23:38,487][05218] Updated weights for policy 0, policy_version 91462 (0.0007) -[2023-10-16 06:23:38,678][05219] Updated weights for policy 1, policy_version 91180 (0.0007) -[2023-10-16 06:23:38,863][05218] Updated weights for policy 0, policy_version 91472 (0.0007) -[2023-10-16 06:23:39,034][05219] Updated weights for policy 1, policy_version 91190 (0.0009) -[2023-10-16 06:23:39,241][05218] Updated weights for policy 0, policy_version 91482 (0.0007) -[2023-10-16 06:23:39,396][05219] Updated weights for policy 1, policy_version 91200 (0.0008) -[2023-10-16 06:23:42,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 187072512. Throughput: 0: 1797.0, 1: 1788.0. Samples: 46775116. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-16 06:23:42,351][03835] Avg episode reward: [(0, '7.960'), (1, '8.100')] -[2023-10-16 06:23:43,054][05218] Updated weights for policy 0, policy_version 91492 (0.0007) -[2023-10-16 06:23:43,252][05219] Updated weights for policy 1, policy_version 91210 (0.0008) -[2023-10-16 06:23:43,431][05218] Updated weights for policy 0, policy_version 91502 (0.0007) -[2023-10-16 06:23:43,628][05219] Updated weights for policy 1, policy_version 91220 (0.0008) -[2023-10-16 06:23:43,810][05218] Updated weights for policy 0, policy_version 91512 (0.0007) -[2023-10-16 06:23:43,987][05219] Updated weights for policy 1, policy_version 91230 (0.0008) -[2023-10-16 06:23:47,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 187138048. Throughput: 0: 1789.8, 1: 1781.4. Samples: 46797294. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-16 06:23:47,351][03835] Avg episode reward: [(0, '8.170'), (1, '8.040')] -[2023-10-16 06:23:47,611][05218] Updated weights for policy 0, policy_version 91522 (0.0009) -[2023-10-16 06:23:47,792][05219] Updated weights for policy 1, policy_version 91240 (0.0008) -[2023-10-16 06:23:47,982][05218] Updated weights for policy 0, policy_version 91532 (0.0007) -[2023-10-16 06:23:48,161][05219] Updated weights for policy 1, policy_version 91250 (0.0010) -[2023-10-16 06:23:48,348][05218] Updated weights for policy 0, policy_version 91542 (0.0008) -[2023-10-16 06:23:48,524][05219] Updated weights for policy 1, policy_version 91260 (0.0008) -[2023-10-16 06:23:48,721][05218] Updated weights for policy 0, policy_version 91552 (0.0009) -[2023-10-16 06:23:52,320][05219] Updated weights for policy 1, policy_version 91270 (0.0010) -[2023-10-16 06:23:52,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 187203584. Throughput: 0: 1808.5, 1: 1804.6. Samples: 46819506. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-16 06:23:52,351][03835] Avg episode reward: [(0, '7.600'), (1, '7.830')] -[2023-10-16 06:23:52,509][05218] Updated weights for policy 0, policy_version 91562 (0.0007) -[2023-10-16 06:23:52,682][05219] Updated weights for policy 1, policy_version 91280 (0.0009) -[2023-10-16 06:23:52,886][05218] Updated weights for policy 0, policy_version 91572 (0.0008) -[2023-10-16 06:23:53,054][05219] Updated weights for policy 1, policy_version 91290 (0.0007) -[2023-10-16 06:23:53,265][05218] Updated weights for policy 0, policy_version 91582 (0.0007) -[2023-10-16 06:23:56,859][05219] Updated weights for policy 1, policy_version 91300 (0.0008) -[2023-10-16 06:23:56,934][05218] Updated weights for policy 0, policy_version 91592 (0.0008) -[2023-10-16 06:23:57,223][05219] Updated weights for policy 1, policy_version 91310 (0.0007) -[2023-10-16 06:23:57,312][05218] Updated weights for policy 0, policy_version 91602 (0.0007) -[2023-10-16 06:23:57,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 187269120. Throughput: 0: 1790.3, 1: 1778.3. Samples: 46829310. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-16 06:23:57,351][03835] Avg episode reward: [(0, '8.040'), (1, '6.620')] -[2023-10-16 06:23:57,598][05219] Updated weights for policy 1, policy_version 91320 (0.0008) -[2023-10-16 06:23:57,680][05218] Updated weights for policy 0, policy_version 91612 (0.0008) -[2023-10-16 06:24:01,318][05219] Updated weights for policy 1, policy_version 91330 (0.0008) -[2023-10-16 06:24:01,405][05218] Updated weights for policy 0, policy_version 91622 (0.0008) -[2023-10-16 06:24:01,679][05219] Updated weights for policy 1, policy_version 91340 (0.0008) -[2023-10-16 06:24:01,780][05218] Updated weights for policy 0, policy_version 91632 (0.0009) -[2023-10-16 06:24:02,043][05219] Updated weights for policy 1, policy_version 91350 (0.0008) -[2023-10-16 06:24:02,144][05218] Updated weights for policy 0, policy_version 91642 (0.0007) -[2023-10-16 06:24:02,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 187334656. Throughput: 0: 1805.9, 1: 1801.2. Samples: 46851596. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-16 06:24:02,351][03835] Avg episode reward: [(0, '7.860'), (1, '6.680')] -[2023-10-16 06:24:02,411][05219] Updated weights for policy 1, policy_version 91360 (0.0008) -[2023-10-16 06:24:06,064][05218] Updated weights for policy 0, policy_version 91652 (0.0007) -[2023-10-16 06:24:06,122][05219] Updated weights for policy 1, policy_version 91370 (0.0007) -[2023-10-16 06:24:06,455][05218] Updated weights for policy 0, policy_version 91662 (0.0007) -[2023-10-16 06:24:06,491][05219] Updated weights for policy 1, policy_version 91380 (0.0008) -[2023-10-16 06:24:06,832][05218] Updated weights for policy 0, policy_version 91672 (0.0007) -[2023-10-16 06:24:06,865][05219] Updated weights for policy 1, policy_version 91390 (0.0008) -[2023-10-16 06:24:07,350][03835] Fps is (10 sec: 19660.8, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 187465728. Throughput: 0: 1790.0, 1: 1775.7. Samples: 46871036. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-16 06:24:07,351][03835] Avg episode reward: [(0, '7.810'), (1, '6.820')] -[2023-10-16 06:24:10,558][05218] Updated weights for policy 0, policy_version 91682 (0.0011) -[2023-10-16 06:24:10,682][05219] Updated weights for policy 1, policy_version 91400 (0.0009) -[2023-10-16 06:24:10,940][05218] Updated weights for policy 0, policy_version 91692 (0.0008) -[2023-10-16 06:24:11,050][05219] Updated weights for policy 1, policy_version 91410 (0.0007) -[2023-10-16 06:24:11,304][05218] Updated weights for policy 0, policy_version 91702 (0.0009) -[2023-10-16 06:24:11,411][05219] Updated weights for policy 1, policy_version 91420 (0.0008) -[2023-10-16 06:24:11,681][05218] Updated weights for policy 0, policy_version 91712 (0.0009) -[2023-10-16 06:24:12,350][03835] Fps is (10 sec: 19660.6, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 187531264. Throughput: 0: 1809.3, 1: 1795.0. Samples: 46883862. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-16 06:24:12,351][03835] Avg episode reward: [(0, '7.250'), (1, '7.090')] -[2023-10-16 06:24:15,243][05219] Updated weights for policy 1, policy_version 91430 (0.0008) -[2023-10-16 06:24:15,570][05218] Updated weights for policy 0, policy_version 91722 (0.0008) -[2023-10-16 06:24:15,608][05219] Updated weights for policy 1, policy_version 91440 (0.0007) -[2023-10-16 06:24:15,951][05218] Updated weights for policy 0, policy_version 91732 (0.0007) -[2023-10-16 06:24:15,968][05219] Updated weights for policy 1, policy_version 91450 (0.0009) -[2023-10-16 06:24:16,323][05218] Updated weights for policy 0, policy_version 91742 (0.0008) -[2023-10-16 06:24:17,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 187596800. Throughput: 0: 1792.5, 1: 1774.3. Samples: 46903348. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-16 06:24:17,351][03835] Avg episode reward: [(0, '8.070'), (1, '7.060')] -[2023-10-16 06:24:19,732][05219] Updated weights for policy 1, policy_version 91460 (0.0009) -[2023-10-16 06:24:20,090][05218] Updated weights for policy 0, policy_version 91752 (0.0008) -[2023-10-16 06:24:20,097][05219] Updated weights for policy 1, policy_version 91470 (0.0009) -[2023-10-16 06:24:20,461][05219] Updated weights for policy 1, policy_version 91480 (0.0009) -[2023-10-16 06:24:20,471][05218] Updated weights for policy 0, policy_version 91762 (0.0008) -[2023-10-16 06:24:20,844][05218] Updated weights for policy 0, policy_version 91772 (0.0007) -[2023-10-16 06:24:22,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 187662336. Throughput: 0: 1783.2, 1: 1771.7. Samples: 46925322. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-16 06:24:22,351][03835] Avg episode reward: [(0, '7.260'), (1, '6.980')] -[2023-10-16 06:24:24,390][05219] Updated weights for policy 1, policy_version 91490 (0.0009) -[2023-10-16 06:24:24,575][05218] Updated weights for policy 0, policy_version 91782 (0.0008) -[2023-10-16 06:24:24,756][05219] Updated weights for policy 1, policy_version 91500 (0.0009) -[2023-10-16 06:24:24,957][05218] Updated weights for policy 0, policy_version 91792 (0.0007) -[2023-10-16 06:24:25,122][05219] Updated weights for policy 1, policy_version 91510 (0.0008) -[2023-10-16 06:24:25,322][05218] Updated weights for policy 0, policy_version 91802 (0.0009) -[2023-10-16 06:24:25,482][05219] Updated weights for policy 1, policy_version 91520 (0.0008) -[2023-10-16 06:24:27,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 187727872. Throughput: 0: 1788.0, 1: 1780.8. Samples: 46935708. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-16 06:24:27,351][03835] Avg episode reward: [(0, '7.560'), (1, '5.570')] -[2023-10-16 06:24:28,970][05218] Updated weights for policy 0, policy_version 91812 (0.0010) -[2023-10-16 06:24:29,342][05218] Updated weights for policy 0, policy_version 91822 (0.0010) -[2023-10-16 06:24:29,348][05219] Updated weights for policy 1, policy_version 91530 (0.0009) -[2023-10-16 06:24:29,713][05219] Updated weights for policy 1, policy_version 91540 (0.0009) -[2023-10-16 06:24:29,718][05218] Updated weights for policy 0, policy_version 91832 (0.0008) -[2023-10-16 06:24:30,082][05219] Updated weights for policy 1, policy_version 91550 (0.0008) -[2023-10-16 06:24:32,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 187793408. Throughput: 0: 1785.6, 1: 1771.2. Samples: 46957346. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-16 06:24:32,351][03835] Avg episode reward: [(0, '8.320'), (1, '5.620')] -[2023-10-16 06:24:33,380][05218] Updated weights for policy 0, policy_version 91842 (0.0008) -[2023-10-16 06:24:33,762][05218] Updated weights for policy 0, policy_version 91852 (0.0008) -[2023-10-16 06:24:33,871][05219] Updated weights for policy 1, policy_version 91560 (0.0008) -[2023-10-16 06:24:34,128][05218] Updated weights for policy 0, policy_version 91862 (0.0008) -[2023-10-16 06:24:34,226][05219] Updated weights for policy 1, policy_version 91570 (0.0007) -[2023-10-16 06:24:34,500][05218] Updated weights for policy 0, policy_version 91872 (0.0008) -[2023-10-16 06:24:34,593][05219] Updated weights for policy 1, policy_version 91580 (0.0007) -[2023-10-16 06:24:37,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 187858944. Throughput: 0: 1787.9, 1: 1770.9. Samples: 46979650. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-16 06:24:37,352][03835] Avg episode reward: [(0, '7.210'), (1, '7.190')] -[2023-10-16 06:24:38,323][05218] Updated weights for policy 0, policy_version 91882 (0.0009) -[2023-10-16 06:24:38,440][05219] Updated weights for policy 1, policy_version 91590 (0.0008) -[2023-10-16 06:24:38,703][05218] Updated weights for policy 0, policy_version 91892 (0.0008) -[2023-10-16 06:24:38,801][05219] Updated weights for policy 1, policy_version 91600 (0.0008) -[2023-10-16 06:24:39,072][05218] Updated weights for policy 0, policy_version 91902 (0.0010) -[2023-10-16 06:24:39,167][05219] Updated weights for policy 1, policy_version 91610 (0.0008) -[2023-10-16 06:24:42,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 187924480. Throughput: 0: 1783.8, 1: 1772.6. Samples: 46989348. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-16 06:24:42,351][03835] Avg episode reward: [(0, '8.210'), (1, '6.880')] -[2023-10-16 06:24:42,868][05218] Updated weights for policy 0, policy_version 91912 (0.0010) -[2023-10-16 06:24:42,921][05219] Updated weights for policy 1, policy_version 91620 (0.0007) -[2023-10-16 06:24:43,233][05218] Updated weights for policy 0, policy_version 91922 (0.0008) -[2023-10-16 06:24:43,272][05219] Updated weights for policy 1, policy_version 91630 (0.0009) -[2023-10-16 06:24:43,608][05218] Updated weights for policy 0, policy_version 91932 (0.0007) -[2023-10-16 06:24:43,635][05219] Updated weights for policy 1, policy_version 91640 (0.0007) -[2023-10-16 06:24:47,291][05218] Updated weights for policy 0, policy_version 91942 (0.0008) -[2023-10-16 06:24:47,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 187990016. Throughput: 0: 1783.8, 1: 1771.7. Samples: 47011594. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-16 06:24:47,351][03835] Avg episode reward: [(0, '8.140'), (1, '7.360')] -[2023-10-16 06:24:47,463][05219] Updated weights for policy 1, policy_version 91650 (0.0007) -[2023-10-16 06:24:47,657][05218] Updated weights for policy 0, policy_version 91952 (0.0009) -[2023-10-16 06:24:47,834][05219] Updated weights for policy 1, policy_version 91660 (0.0007) -[2023-10-16 06:24:48,037][05218] Updated weights for policy 0, policy_version 91962 (0.0008) -[2023-10-16 06:24:48,201][05219] Updated weights for policy 1, policy_version 91670 (0.0007) -[2023-10-16 06:24:48,556][05219] Updated weights for policy 1, policy_version 91680 (0.0008) -[2023-10-16 06:24:52,040][05218] Updated weights for policy 0, policy_version 91972 (0.0009) -[2023-10-16 06:24:52,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 188055552. Throughput: 0: 1798.6, 1: 1800.1. Samples: 47032978. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-16 06:24:52,351][03835] Avg episode reward: [(0, '7.860'), (1, '8.700')] -[2023-10-16 06:24:52,427][05218] Updated weights for policy 0, policy_version 91982 (0.0009) -[2023-10-16 06:24:52,568][05219] Updated weights for policy 1, policy_version 91690 (0.0009) -[2023-10-16 06:24:52,796][05218] Updated weights for policy 0, policy_version 91992 (0.0007) -[2023-10-16 06:24:52,928][05219] Updated weights for policy 1, policy_version 91700 (0.0008) -[2023-10-16 06:24:53,298][05219] Updated weights for policy 1, policy_version 91710 (0.0010) -[2023-10-16 06:24:56,400][05218] Updated weights for policy 0, policy_version 92002 (0.0008) -[2023-10-16 06:24:56,779][05218] Updated weights for policy 0, policy_version 92012 (0.0008) -[2023-10-16 06:24:57,122][05219] Updated weights for policy 1, policy_version 91720 (0.0009) -[2023-10-16 06:24:57,145][05218] Updated weights for policy 0, policy_version 92022 (0.0009) -[2023-10-16 06:24:57,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 188121088. Throughput: 0: 1778.2, 1: 1765.4. Samples: 47043326. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-16 06:24:57,351][03835] Avg episode reward: [(0, '7.450'), (1, '7.710')] -[2023-10-16 06:24:57,497][05219] Updated weights for policy 1, policy_version 91730 (0.0008) -[2023-10-16 06:24:57,515][05218] Updated weights for policy 0, policy_version 92032 (0.0008) -[2023-10-16 06:24:57,865][05219] Updated weights for policy 1, policy_version 91740 (0.0007) -[2023-10-16 06:25:01,312][05218] Updated weights for policy 0, policy_version 92042 (0.0008) -[2023-10-16 06:25:01,690][05218] Updated weights for policy 0, policy_version 92052 (0.0007) -[2023-10-16 06:25:01,695][05219] Updated weights for policy 1, policy_version 91750 (0.0010) -[2023-10-16 06:25:02,060][05218] Updated weights for policy 0, policy_version 92062 (0.0009) -[2023-10-16 06:25:02,066][05219] Updated weights for policy 1, policy_version 91760 (0.0007) -[2023-10-16 06:25:02,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 188219392. Throughput: 0: 1797.5, 1: 1794.1. Samples: 47064972. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-16 06:25:02,351][03835] Avg episode reward: [(0, '8.510'), (1, '7.320')] -[2023-10-16 06:25:02,423][05219] Updated weights for policy 1, policy_version 91770 (0.0007) -[2023-10-16 06:25:05,966][05218] Updated weights for policy 0, policy_version 92072 (0.0009) -[2023-10-16 06:25:06,108][05219] Updated weights for policy 1, policy_version 91780 (0.0008) -[2023-10-16 06:25:06,343][05218] Updated weights for policy 0, policy_version 92082 (0.0008) -[2023-10-16 06:25:06,487][05219] Updated weights for policy 1, policy_version 91790 (0.0009) -[2023-10-16 06:25:06,719][05218] Updated weights for policy 0, policy_version 92092 (0.0008) -[2023-10-16 06:25:06,837][05219] Updated weights for policy 1, policy_version 91800 (0.0009) -[2023-10-16 06:25:07,350][03835] Fps is (10 sec: 19660.6, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 188317696. Throughput: 0: 1777.7, 1: 1764.5. Samples: 47084724. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-16 06:25:07,352][03835] Avg episode reward: [(0, '8.170'), (1, '8.530')] -[2023-10-16 06:25:10,238][05218] Updated weights for policy 0, policy_version 92102 (0.0009) -[2023-10-16 06:25:10,553][05219] Updated weights for policy 1, policy_version 91810 (0.0010) -[2023-10-16 06:25:10,606][05218] Updated weights for policy 0, policy_version 92112 (0.0009) -[2023-10-16 06:25:10,914][05219] Updated weights for policy 1, policy_version 91820 (0.0008) -[2023-10-16 06:25:10,987][05218] Updated weights for policy 0, policy_version 92122 (0.0009) -[2023-10-16 06:25:11,282][05219] Updated weights for policy 1, policy_version 91830 (0.0007) -[2023-10-16 06:25:11,640][05219] Updated weights for policy 1, policy_version 91840 (0.0008) -[2023-10-16 06:25:12,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 188383232. Throughput: 0: 1802.2, 1: 1788.1. Samples: 47097274. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-16 06:25:12,351][03835] Avg episode reward: [(0, '7.830'), (1, '7.600')] -[2023-10-16 06:25:14,888][05218] Updated weights for policy 0, policy_version 92132 (0.0008) -[2023-10-16 06:25:15,261][05218] Updated weights for policy 0, policy_version 92142 (0.0007) -[2023-10-16 06:25:15,557][05219] Updated weights for policy 1, policy_version 91850 (0.0008) -[2023-10-16 06:25:15,633][05218] Updated weights for policy 0, policy_version 92152 (0.0007) -[2023-10-16 06:25:15,918][05219] Updated weights for policy 1, policy_version 91860 (0.0008) -[2023-10-16 06:25:16,276][05219] Updated weights for policy 1, policy_version 91870 (0.0008) -[2023-10-16 06:25:17,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 188448768. Throughput: 0: 1779.5, 1: 1771.5. Samples: 47117140. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-16 06:25:17,351][03835] Avg episode reward: [(0, '7.710'), (1, '7.760')] -[2023-10-16 06:25:19,380][05218] Updated weights for policy 0, policy_version 92162 (0.0008) -[2023-10-16 06:25:19,753][05218] Updated weights for policy 0, policy_version 92172 (0.0007) -[2023-10-16 06:25:20,125][05218] Updated weights for policy 0, policy_version 92182 (0.0008) -[2023-10-16 06:25:20,257][05219] Updated weights for policy 1, policy_version 91880 (0.0009) -[2023-10-16 06:25:20,500][05218] Updated weights for policy 0, policy_version 92192 (0.0009) -[2023-10-16 06:25:20,625][05219] Updated weights for policy 1, policy_version 91890 (0.0009) -[2023-10-16 06:25:20,990][05219] Updated weights for policy 1, policy_version 91900 (0.0008) -[2023-10-16 06:25:22,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 188514304. Throughput: 0: 1782.9, 1: 1763.3. Samples: 47139224. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-16 06:25:22,351][03835] Avg episode reward: [(0, '8.180'), (1, '7.790')] -[2023-10-16 06:25:24,353][05218] Updated weights for policy 0, policy_version 92202 (0.0007) -[2023-10-16 06:25:24,633][05219] Updated weights for policy 1, policy_version 91910 (0.0008) -[2023-10-16 06:25:24,728][05218] Updated weights for policy 0, policy_version 92212 (0.0009) -[2023-10-16 06:25:25,005][05219] Updated weights for policy 1, policy_version 91920 (0.0008) -[2023-10-16 06:25:25,103][05218] Updated weights for policy 0, policy_version 92222 (0.0009) -[2023-10-16 06:25:25,372][05219] Updated weights for policy 1, policy_version 91930 (0.0007) -[2023-10-16 06:25:27,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 188579840. Throughput: 0: 1782.3, 1: 1779.5. Samples: 47149628. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-16 06:25:27,351][03835] Avg episode reward: [(0, '7.710'), (1, '8.060')] -[2023-10-16 06:25:28,890][05218] Updated weights for policy 0, policy_version 92232 (0.0010) -[2023-10-16 06:25:29,124][05219] Updated weights for policy 1, policy_version 91940 (0.0008) -[2023-10-16 06:25:29,260][05218] Updated weights for policy 0, policy_version 92242 (0.0008) -[2023-10-16 06:25:29,482][05219] Updated weights for policy 1, policy_version 91950 (0.0009) -[2023-10-16 06:25:29,640][05218] Updated weights for policy 0, policy_version 92252 (0.0008) -[2023-10-16 06:25:29,839][05219] Updated weights for policy 1, policy_version 91960 (0.0007) -[2023-10-16 06:25:32,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 188645376. Throughput: 0: 1781.0, 1: 1761.6. Samples: 47171008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-16 06:25:32,351][03835] Avg episode reward: [(0, '7.650'), (1, '7.250')] -[2023-10-16 06:25:33,344][05218] Updated weights for policy 0, policy_version 92262 (0.0008) -[2023-10-16 06:25:33,630][05219] Updated weights for policy 1, policy_version 91970 (0.0010) -[2023-10-16 06:25:33,717][05218] Updated weights for policy 0, policy_version 92272 (0.0009) -[2023-10-16 06:25:33,989][05219] Updated weights for policy 1, policy_version 91980 (0.0007) -[2023-10-16 06:25:34,105][05218] Updated weights for policy 0, policy_version 92282 (0.0007) -[2023-10-16 06:25:34,367][05219] Updated weights for policy 1, policy_version 91990 (0.0008) -[2023-10-16 06:25:34,734][05219] Updated weights for policy 1, policy_version 92000 (0.0007) -[2023-10-16 06:25:37,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 188710912. Throughput: 0: 1803.9, 1: 1767.7. Samples: 47193700. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-16 06:25:37,351][03835] Avg episode reward: [(0, '8.820'), (1, '7.690')] -[2023-10-16 06:25:37,361][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000092288_94502912.pth... -[2023-10-16 06:25:37,362][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000092000_94208000.pth... -[2023-10-16 06:25:37,391][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000090624_92798976.pth -[2023-10-16 06:25:37,395][04766] Saving a milestone ./train_atari/atari_timepilot_APPO/checkpoint_p0/milestones/checkpoint_000092288_94502912.pth -[2023-10-16 06:25:37,397][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000090336_92504064.pth -[2023-10-16 06:25:37,401][04891] Saving a milestone ./train_atari/atari_timepilot_APPO/checkpoint_p1/milestones/checkpoint_000092000_94208000.pth -[2023-10-16 06:25:37,892][05218] Updated weights for policy 0, policy_version 92292 (0.0009) -[2023-10-16 06:25:38,279][05218] Updated weights for policy 0, policy_version 92302 (0.0009) -[2023-10-16 06:25:38,539][05219] Updated weights for policy 1, policy_version 92010 (0.0007) -[2023-10-16 06:25:38,656][05218] Updated weights for policy 0, policy_version 92312 (0.0007) -[2023-10-16 06:25:38,906][05219] Updated weights for policy 1, policy_version 92020 (0.0008) -[2023-10-16 06:25:39,270][05219] Updated weights for policy 1, policy_version 92030 (0.0009) -[2023-10-16 06:25:42,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 188776448. Throughput: 0: 1786.5, 1: 1768.5. Samples: 47203304. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-16 06:25:42,351][03835] Avg episode reward: [(0, '7.450'), (1, '8.180')] -[2023-10-16 06:25:42,474][05218] Updated weights for policy 0, policy_version 92322 (0.0010) -[2023-10-16 06:25:42,849][05218] Updated weights for policy 0, policy_version 92332 (0.0009) -[2023-10-16 06:25:43,105][05219] Updated weights for policy 1, policy_version 92040 (0.0008) -[2023-10-16 06:25:43,226][05218] Updated weights for policy 0, policy_version 92342 (0.0010) -[2023-10-16 06:25:43,478][05219] Updated weights for policy 1, policy_version 92050 (0.0009) -[2023-10-16 06:25:43,599][05218] Updated weights for policy 0, policy_version 92352 (0.0011) -[2023-10-16 06:25:43,845][05219] Updated weights for policy 1, policy_version 92060 (0.0008) -[2023-10-16 06:25:47,173][05218] Updated weights for policy 0, policy_version 92362 (0.0010) -[2023-10-16 06:25:47,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 188841984. Throughput: 0: 1793.6, 1: 1765.5. Samples: 47225130. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-16 06:25:47,351][03835] Avg episode reward: [(0, '7.170'), (1, '7.020')] -[2023-10-16 06:25:47,550][05218] Updated weights for policy 0, policy_version 92372 (0.0008) -[2023-10-16 06:25:47,816][05219] Updated weights for policy 1, policy_version 92070 (0.0007) -[2023-10-16 06:25:47,923][05218] Updated weights for policy 0, policy_version 92382 (0.0008) -[2023-10-16 06:25:48,176][05219] Updated weights for policy 1, policy_version 92080 (0.0007) -[2023-10-16 06:25:48,543][05219] Updated weights for policy 1, policy_version 92090 (0.0007) -[2023-10-16 06:25:51,675][05218] Updated weights for policy 0, policy_version 92392 (0.0008) -[2023-10-16 06:25:52,046][05218] Updated weights for policy 0, policy_version 92402 (0.0008) -[2023-10-16 06:25:52,191][05219] Updated weights for policy 1, policy_version 92100 (0.0009) -[2023-10-16 06:25:52,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 188907520. Throughput: 0: 1793.9, 1: 1795.7. Samples: 47246252. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-16 06:25:52,351][03835] Avg episode reward: [(0, '7.580'), (1, '9.020')] -[2023-10-16 06:25:52,421][05218] Updated weights for policy 0, policy_version 92412 (0.0009) -[2023-10-16 06:25:52,554][05219] Updated weights for policy 1, policy_version 92110 (0.0007) -[2023-10-16 06:25:52,912][05219] Updated weights for policy 1, policy_version 92120 (0.0007) -[2023-10-16 06:25:56,096][05218] Updated weights for policy 0, policy_version 92422 (0.0008) -[2023-10-16 06:25:56,477][05218] Updated weights for policy 0, policy_version 92432 (0.0007) -[2023-10-16 06:25:56,700][05219] Updated weights for policy 1, policy_version 92130 (0.0009) -[2023-10-16 06:25:56,848][05218] Updated weights for policy 0, policy_version 92442 (0.0008) -[2023-10-16 06:25:57,061][05219] Updated weights for policy 1, policy_version 92140 (0.0008) -[2023-10-16 06:25:57,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 189005824. Throughput: 0: 1790.1, 1: 1769.3. Samples: 47257450. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-16 06:25:57,351][03835] Avg episode reward: [(0, '6.620'), (1, '7.890')] -[2023-10-16 06:25:57,432][05219] Updated weights for policy 1, policy_version 92150 (0.0007) -[2023-10-16 06:25:57,788][05219] Updated weights for policy 1, policy_version 92160 (0.0007) -[2023-10-16 06:26:00,597][05218] Updated weights for policy 0, policy_version 92452 (0.0008) -[2023-10-16 06:26:00,968][05218] Updated weights for policy 0, policy_version 92462 (0.0008) -[2023-10-16 06:26:01,346][05218] Updated weights for policy 0, policy_version 92472 (0.0010) -[2023-10-16 06:26:01,418][05219] Updated weights for policy 1, policy_version 92170 (0.0008) -[2023-10-16 06:26:01,785][05219] Updated weights for policy 1, policy_version 92180 (0.0009) -[2023-10-16 06:26:02,157][05219] Updated weights for policy 1, policy_version 92190 (0.0009) -[2023-10-16 06:26:02,350][03835] Fps is (10 sec: 19660.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 189104128. Throughput: 0: 1788.0, 1: 1803.3. Samples: 47278746. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-16 06:26:02,351][03835] Avg episode reward: [(0, '7.250'), (1, '8.000')] -[2023-10-16 06:26:05,152][05218] Updated weights for policy 0, policy_version 92482 (0.0009) -[2023-10-16 06:26:05,533][05218] Updated weights for policy 0, policy_version 92492 (0.0008) -[2023-10-16 06:26:05,903][05218] Updated weights for policy 0, policy_version 92502 (0.0008) -[2023-10-16 06:26:06,071][05219] Updated weights for policy 1, policy_version 92200 (0.0008) -[2023-10-16 06:26:06,275][05218] Updated weights for policy 0, policy_version 92512 (0.0010) -[2023-10-16 06:26:06,448][05219] Updated weights for policy 1, policy_version 92210 (0.0010) -[2023-10-16 06:26:06,808][05219] Updated weights for policy 1, policy_version 92220 (0.0008) -[2023-10-16 06:26:07,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 189169664. Throughput: 0: 1775.6, 1: 1780.2. Samples: 47299232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-16 06:26:07,351][03835] Avg episode reward: [(0, '7.670'), (1, '8.200')] -[2023-10-16 06:26:10,237][05218] Updated weights for policy 0, policy_version 92522 (0.0009) -[2023-10-16 06:26:10,440][05219] Updated weights for policy 1, policy_version 92230 (0.0008) -[2023-10-16 06:26:10,603][05218] Updated weights for policy 0, policy_version 92532 (0.0009) -[2023-10-16 06:26:10,807][05219] Updated weights for policy 1, policy_version 92240 (0.0008) -[2023-10-16 06:26:10,976][05218] Updated weights for policy 0, policy_version 92542 (0.0009) -[2023-10-16 06:26:11,160][05219] Updated weights for policy 1, policy_version 92250 (0.0008) -[2023-10-16 06:26:12,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 189235200. Throughput: 0: 1790.5, 1: 1800.1. Samples: 47311206. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-16 06:26:12,351][03835] Avg episode reward: [(0, '8.040'), (1, '7.090')] -[2023-10-16 06:26:14,689][05218] Updated weights for policy 0, policy_version 92552 (0.0009) -[2023-10-16 06:26:14,912][05219] Updated weights for policy 1, policy_version 92260 (0.0009) -[2023-10-16 06:26:15,068][05218] Updated weights for policy 0, policy_version 92562 (0.0009) -[2023-10-16 06:26:15,278][05219] Updated weights for policy 1, policy_version 92270 (0.0007) -[2023-10-16 06:26:15,435][05218] Updated weights for policy 0, policy_version 92572 (0.0008) -[2023-10-16 06:26:15,643][05219] Updated weights for policy 1, policy_version 92280 (0.0009) -[2023-10-16 06:26:17,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 189300736. Throughput: 0: 1769.2, 1: 1787.2. Samples: 47331046. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-16 06:26:17,351][03835] Avg episode reward: [(0, '8.500'), (1, '7.660')] -[2023-10-16 06:26:19,266][05218] Updated weights for policy 0, policy_version 92582 (0.0010) -[2023-10-16 06:26:19,378][05219] Updated weights for policy 1, policy_version 92290 (0.0010) -[2023-10-16 06:26:19,637][05218] Updated weights for policy 0, policy_version 92592 (0.0009) -[2023-10-16 06:26:19,746][05219] Updated weights for policy 1, policy_version 92300 (0.0007) -[2023-10-16 06:26:20,006][05218] Updated weights for policy 0, policy_version 92602 (0.0007) -[2023-10-16 06:26:20,100][05219] Updated weights for policy 1, policy_version 92310 (0.0007) -[2023-10-16 06:26:20,471][05219] Updated weights for policy 1, policy_version 92320 (0.0007) -[2023-10-16 06:26:22,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 189366272. Throughput: 0: 1766.1, 1: 1784.2. Samples: 47353462. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-16 06:26:22,352][03835] Avg episode reward: [(0, '7.830'), (1, '8.220')] -[2023-10-16 06:26:23,675][05218] Updated weights for policy 0, policy_version 92612 (0.0007) -[2023-10-16 06:26:24,064][05218] Updated weights for policy 0, policy_version 92622 (0.0007) -[2023-10-16 06:26:24,250][05219] Updated weights for policy 1, policy_version 92330 (0.0008) -[2023-10-16 06:26:24,435][05218] Updated weights for policy 0, policy_version 92632 (0.0007) -[2023-10-16 06:26:24,620][05219] Updated weights for policy 1, policy_version 92340 (0.0008) -[2023-10-16 06:26:24,983][05219] Updated weights for policy 1, policy_version 92350 (0.0009) -[2023-10-16 06:26:27,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 189431808. Throughput: 0: 1764.4, 1: 1786.1. Samples: 47363076. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-16 06:26:27,351][03835] Avg episode reward: [(0, '7.750'), (1, '8.340')] -[2023-10-16 06:26:28,331][05218] Updated weights for policy 0, policy_version 92642 (0.0008) -[2023-10-16 06:26:28,715][05218] Updated weights for policy 0, policy_version 92652 (0.0007) -[2023-10-16 06:26:28,863][05219] Updated weights for policy 1, policy_version 92360 (0.0007) -[2023-10-16 06:26:29,087][05218] Updated weights for policy 0, policy_version 92662 (0.0008) -[2023-10-16 06:26:29,226][05219] Updated weights for policy 1, policy_version 92370 (0.0008) -[2023-10-16 06:26:29,466][05218] Updated weights for policy 0, policy_version 92672 (0.0008) -[2023-10-16 06:26:29,590][05219] Updated weights for policy 1, policy_version 92380 (0.0009) -[2023-10-16 06:26:32,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 189497344. Throughput: 0: 1768.9, 1: 1790.9. Samples: 47385322. Policy #0 lag: (min: 14.0, avg: 18.2, max: 46.0) -[2023-10-16 06:26:32,352][03835] Avg episode reward: [(0, '8.330'), (1, '8.750')] -[2023-10-16 06:26:33,251][05218] Updated weights for policy 0, policy_version 92682 (0.0009) -[2023-10-16 06:26:33,329][05219] Updated weights for policy 1, policy_version 92390 (0.0009) -[2023-10-16 06:26:33,632][05218] Updated weights for policy 0, policy_version 92692 (0.0008) -[2023-10-16 06:26:33,688][05219] Updated weights for policy 1, policy_version 92400 (0.0008) -[2023-10-16 06:26:33,997][05218] Updated weights for policy 0, policy_version 92702 (0.0008) -[2023-10-16 06:26:34,051][05219] Updated weights for policy 1, policy_version 92410 (0.0007) -[2023-10-16 06:26:37,351][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 189562880. Throughput: 0: 1789.5, 1: 1789.3. Samples: 47407300. Policy #0 lag: (min: 14.0, avg: 18.2, max: 46.0) -[2023-10-16 06:26:37,352][03835] Avg episode reward: [(0, '7.640'), (1, '8.590')] -[2023-10-16 06:26:37,860][05218] Updated weights for policy 0, policy_version 92712 (0.0007) -[2023-10-16 06:26:37,885][05219] Updated weights for policy 1, policy_version 92420 (0.0008) -[2023-10-16 06:26:38,230][05218] Updated weights for policy 0, policy_version 92722 (0.0007) -[2023-10-16 06:26:38,257][05219] Updated weights for policy 1, policy_version 92430 (0.0007) -[2023-10-16 06:26:38,613][05218] Updated weights for policy 0, policy_version 92732 (0.0008) -[2023-10-16 06:26:38,614][05219] Updated weights for policy 1, policy_version 92440 (0.0007) -[2023-10-16 06:26:42,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 189628416. Throughput: 0: 1762.0, 1: 1783.6. Samples: 47417002. Policy #0 lag: (min: 14.0, avg: 18.2, max: 46.0) -[2023-10-16 06:26:42,351][03835] Avg episode reward: [(0, '8.180'), (1, '7.950')] -[2023-10-16 06:26:42,354][05218] Updated weights for policy 0, policy_version 92742 (0.0007) -[2023-10-16 06:26:42,379][05219] Updated weights for policy 1, policy_version 92450 (0.0007) -[2023-10-16 06:26:42,733][05218] Updated weights for policy 0, policy_version 92752 (0.0008) -[2023-10-16 06:26:42,741][05219] Updated weights for policy 1, policy_version 92460 (0.0007) -[2023-10-16 06:26:43,103][05218] Updated weights for policy 0, policy_version 92762 (0.0008) -[2023-10-16 06:26:43,106][05219] Updated weights for policy 1, policy_version 92470 (0.0008) -[2023-10-16 06:26:43,476][05219] Updated weights for policy 1, policy_version 92480 (0.0008) -[2023-10-16 06:26:46,909][05218] Updated weights for policy 0, policy_version 92772 (0.0008) -[2023-10-16 06:26:47,272][05218] Updated weights for policy 0, policy_version 92782 (0.0007) -[2023-10-16 06:26:47,293][05219] Updated weights for policy 1, policy_version 92490 (0.0010) -[2023-10-16 06:26:47,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 189693952. Throughput: 0: 1791.0, 1: 1776.6. Samples: 47439286. Policy #0 lag: (min: 14.0, avg: 18.2, max: 46.0) -[2023-10-16 06:26:47,351][03835] Avg episode reward: [(0, '8.180'), (1, '8.690')] -[2023-10-16 06:26:47,648][05219] Updated weights for policy 1, policy_version 92500 (0.0008) -[2023-10-16 06:26:47,651][05218] Updated weights for policy 0, policy_version 92792 (0.0008) -[2023-10-16 06:26:48,016][05219] Updated weights for policy 1, policy_version 92510 (0.0008) -[2023-10-16 06:26:51,459][05218] Updated weights for policy 0, policy_version 92802 (0.0008) -[2023-10-16 06:26:51,835][05218] Updated weights for policy 0, policy_version 92812 (0.0007) -[2023-10-16 06:26:51,968][05219] Updated weights for policy 1, policy_version 92520 (0.0007) -[2023-10-16 06:26:52,206][05218] Updated weights for policy 0, policy_version 92822 (0.0007) -[2023-10-16 06:26:52,329][05219] Updated weights for policy 1, policy_version 92530 (0.0008) -[2023-10-16 06:26:52,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 189759488. Throughput: 0: 1775.4, 1: 1792.0. Samples: 47459766. Policy #0 lag: (min: 14.0, avg: 18.2, max: 46.0) -[2023-10-16 06:26:52,351][03835] Avg episode reward: [(0, '8.520'), (1, '8.270')] -[2023-10-16 06:26:52,579][05218] Updated weights for policy 0, policy_version 92832 (0.0009) -[2023-10-16 06:26:52,688][05219] Updated weights for policy 1, policy_version 92540 (0.0008) -[2023-10-16 06:26:56,274][05218] Updated weights for policy 0, policy_version 92842 (0.0008) -[2023-10-16 06:26:56,420][05219] Updated weights for policy 1, policy_version 92550 (0.0009) -[2023-10-16 06:26:56,655][05218] Updated weights for policy 0, policy_version 92852 (0.0008) -[2023-10-16 06:26:56,790][05219] Updated weights for policy 1, policy_version 92560 (0.0008) -[2023-10-16 06:26:57,036][05218] Updated weights for policy 0, policy_version 92862 (0.0007) -[2023-10-16 06:26:57,156][05219] Updated weights for policy 1, policy_version 92570 (0.0010) -[2023-10-16 06:26:57,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 189857792. Throughput: 0: 1788.1, 1: 1769.1. Samples: 47471278. Policy #0 lag: (min: 14.0, avg: 18.2, max: 46.0) -[2023-10-16 06:26:57,351][03835] Avg episode reward: [(0, '7.410'), (1, '8.210')] -[2023-10-16 06:27:00,777][05218] Updated weights for policy 0, policy_version 92872 (0.0009) -[2023-10-16 06:27:01,085][05219] Updated weights for policy 1, policy_version 92580 (0.0009) -[2023-10-16 06:27:01,160][05218] Updated weights for policy 0, policy_version 92882 (0.0008) -[2023-10-16 06:27:01,446][05219] Updated weights for policy 1, policy_version 92590 (0.0008) -[2023-10-16 06:27:01,534][05218] Updated weights for policy 0, policy_version 92892 (0.0008) -[2023-10-16 06:27:01,816][05219] Updated weights for policy 1, policy_version 92600 (0.0008) -[2023-10-16 06:27:02,350][03835] Fps is (10 sec: 19660.9, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 189956096. Throughput: 0: 1786.6, 1: 1795.1. Samples: 47492220. Policy #0 lag: (min: 14.0, avg: 18.2, max: 46.0) -[2023-10-16 06:27:02,351][03835] Avg episode reward: [(0, '8.670'), (1, '7.830')] -[2023-10-16 06:27:05,411][05218] Updated weights for policy 0, policy_version 92902 (0.0007) -[2023-10-16 06:27:05,635][05219] Updated weights for policy 1, policy_version 92610 (0.0007) -[2023-10-16 06:27:05,780][05218] Updated weights for policy 0, policy_version 92912 (0.0007) -[2023-10-16 06:27:06,004][05219] Updated weights for policy 1, policy_version 92620 (0.0009) -[2023-10-16 06:27:06,159][05218] Updated weights for policy 0, policy_version 92922 (0.0010) -[2023-10-16 06:27:06,367][05219] Updated weights for policy 1, policy_version 92630 (0.0008) -[2023-10-16 06:27:06,726][05219] Updated weights for policy 1, policy_version 92640 (0.0007) -[2023-10-16 06:27:07,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 190021632. Throughput: 0: 1775.5, 1: 1765.9. Samples: 47512826. Policy #0 lag: (min: 14.0, avg: 18.2, max: 46.0) -[2023-10-16 06:27:07,351][03835] Avg episode reward: [(0, '8.790'), (1, '8.460')] -[2023-10-16 06:27:09,836][05218] Updated weights for policy 0, policy_version 92932 (0.0009) -[2023-10-16 06:27:10,222][05218] Updated weights for policy 0, policy_version 92942 (0.0009) -[2023-10-16 06:27:10,541][05219] Updated weights for policy 1, policy_version 92650 (0.0007) -[2023-10-16 06:27:10,594][05218] Updated weights for policy 0, policy_version 92952 (0.0008) -[2023-10-16 06:27:10,901][05219] Updated weights for policy 1, policy_version 92660 (0.0009) -[2023-10-16 06:27:11,263][05219] Updated weights for policy 1, policy_version 92670 (0.0009) -[2023-10-16 06:27:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 190087168. Throughput: 0: 1793.3, 1: 1798.8. Samples: 47524722. Policy #0 lag: (min: 14.0, avg: 18.2, max: 46.0) -[2023-10-16 06:27:12,351][03835] Avg episode reward: [(0, '7.500'), (1, '7.270')] -[2023-10-16 06:27:14,422][05218] Updated weights for policy 0, policy_version 92962 (0.0008) -[2023-10-16 06:27:14,793][05218] Updated weights for policy 0, policy_version 92972 (0.0007) -[2023-10-16 06:27:14,974][05219] Updated weights for policy 1, policy_version 92680 (0.0007) -[2023-10-16 06:27:15,168][05218] Updated weights for policy 0, policy_version 92982 (0.0007) -[2023-10-16 06:27:15,341][05219] Updated weights for policy 1, policy_version 92690 (0.0007) -[2023-10-16 06:27:15,539][05218] Updated weights for policy 0, policy_version 92992 (0.0007) -[2023-10-16 06:27:15,710][05219] Updated weights for policy 1, policy_version 92700 (0.0009) -[2023-10-16 06:27:17,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 190152704. Throughput: 0: 1778.4, 1: 1769.6. Samples: 47544982. Policy #0 lag: (min: 14.0, avg: 18.2, max: 46.0) -[2023-10-16 06:27:17,351][03835] Avg episode reward: [(0, '7.990'), (1, '7.130')] -[2023-10-16 06:27:19,199][05218] Updated weights for policy 0, policy_version 93002 (0.0010) -[2023-10-16 06:27:19,579][05218] Updated weights for policy 0, policy_version 93012 (0.0008) -[2023-10-16 06:27:19,628][05219] Updated weights for policy 1, policy_version 92710 (0.0009) -[2023-10-16 06:27:19,958][05218] Updated weights for policy 0, policy_version 93022 (0.0008) -[2023-10-16 06:27:19,983][05219] Updated weights for policy 1, policy_version 92720 (0.0007) -[2023-10-16 06:27:20,362][05219] Updated weights for policy 1, policy_version 92730 (0.0009) -[2023-10-16 06:27:22,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 190218240. Throughput: 0: 1786.0, 1: 1765.4. Samples: 47567110. Policy #0 lag: (min: 14.0, avg: 18.2, max: 46.0) -[2023-10-16 06:27:22,351][03835] Avg episode reward: [(0, '7.660'), (1, '8.590')] -[2023-10-16 06:27:23,653][05218] Updated weights for policy 0, policy_version 93032 (0.0007) -[2023-10-16 06:27:24,028][05218] Updated weights for policy 0, policy_version 93042 (0.0008) -[2023-10-16 06:27:24,133][05219] Updated weights for policy 1, policy_version 92740 (0.0009) -[2023-10-16 06:27:24,402][05218] Updated weights for policy 0, policy_version 93052 (0.0007) -[2023-10-16 06:27:24,491][05219] Updated weights for policy 1, policy_version 92750 (0.0009) -[2023-10-16 06:27:24,859][05219] Updated weights for policy 1, policy_version 92760 (0.0008) -[2023-10-16 06:27:27,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 190283776. Throughput: 0: 1787.3, 1: 1769.0. Samples: 47577036. Policy #0 lag: (min: 14.0, avg: 18.2, max: 46.0) -[2023-10-16 06:27:27,351][03835] Avg episode reward: [(0, '6.760'), (1, '7.540')] -[2023-10-16 06:27:28,076][05218] Updated weights for policy 0, policy_version 93062 (0.0008) -[2023-10-16 06:27:28,456][05218] Updated weights for policy 0, policy_version 93072 (0.0008) -[2023-10-16 06:27:28,625][05219] Updated weights for policy 1, policy_version 92770 (0.0009) -[2023-10-16 06:27:28,818][05218] Updated weights for policy 0, policy_version 93082 (0.0008) -[2023-10-16 06:27:28,986][05219] Updated weights for policy 1, policy_version 92780 (0.0008) -[2023-10-16 06:27:29,358][05219] Updated weights for policy 1, policy_version 92790 (0.0008) -[2023-10-16 06:27:29,720][05219] Updated weights for policy 1, policy_version 92800 (0.0008) -[2023-10-16 06:27:32,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 190349312. Throughput: 0: 1785.7, 1: 1773.2. Samples: 47599438. Policy #0 lag: (min: 12.0, avg: 14.0, max: 41.0) -[2023-10-16 06:27:32,351][03835] Avg episode reward: [(0, '7.980'), (1, '8.030')] -[2023-10-16 06:27:32,576][05218] Updated weights for policy 0, policy_version 93092 (0.0008) -[2023-10-16 06:27:32,950][05218] Updated weights for policy 0, policy_version 93102 (0.0007) -[2023-10-16 06:27:33,321][05218] Updated weights for policy 0, policy_version 93112 (0.0007) -[2023-10-16 06:27:33,471][05219] Updated weights for policy 1, policy_version 92810 (0.0008) -[2023-10-16 06:27:33,829][05219] Updated weights for policy 1, policy_version 92820 (0.0008) -[2023-10-16 06:27:34,200][05219] Updated weights for policy 1, policy_version 92830 (0.0007) -[2023-10-16 06:27:37,106][05218] Updated weights for policy 0, policy_version 93122 (0.0009) -[2023-10-16 06:27:37,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 190414848. Throughput: 0: 1803.6, 1: 1790.4. Samples: 47621496. Policy #0 lag: (min: 12.0, avg: 14.0, max: 41.0) -[2023-10-16 06:27:37,351][03835] Avg episode reward: [(0, '8.320'), (1, '8.590')] -[2023-10-16 06:27:37,357][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000092832_95059968.pth... -[2023-10-16 06:27:37,394][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000091168_93356032.pth -[2023-10-16 06:27:37,483][05218] Updated weights for policy 0, policy_version 93132 (0.0007) -[2023-10-16 06:27:37,849][05218] Updated weights for policy 0, policy_version 93142 (0.0008) -[2023-10-16 06:27:38,004][05219] Updated weights for policy 1, policy_version 92840 (0.0007) -[2023-10-16 06:27:38,220][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000093152_95387648.pth... -[2023-10-16 06:27:38,220][05218] Updated weights for policy 0, policy_version 93152 (0.0009) -[2023-10-16 06:27:38,253][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000091456_93650944.pth -[2023-10-16 06:27:38,370][05219] Updated weights for policy 1, policy_version 92850 (0.0008) -[2023-10-16 06:27:38,736][05219] Updated weights for policy 1, policy_version 92860 (0.0009) -[2023-10-16 06:27:42,078][05218] Updated weights for policy 0, policy_version 93162 (0.0009) -[2023-10-16 06:27:42,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 190480384. Throughput: 0: 1783.8, 1: 1776.4. Samples: 47631488. Policy #0 lag: (min: 12.0, avg: 14.0, max: 41.0) -[2023-10-16 06:27:42,351][03835] Avg episode reward: [(0, '8.120'), (1, '8.130')] -[2023-10-16 06:27:42,451][05218] Updated weights for policy 0, policy_version 93172 (0.0009) -[2023-10-16 06:27:42,533][05219] Updated weights for policy 1, policy_version 92870 (0.0007) -[2023-10-16 06:27:42,838][05218] Updated weights for policy 0, policy_version 93182 (0.0009) -[2023-10-16 06:27:42,898][05219] Updated weights for policy 1, policy_version 92880 (0.0008) -[2023-10-16 06:27:43,273][05219] Updated weights for policy 1, policy_version 92890 (0.0009) -[2023-10-16 06:27:46,602][05218] Updated weights for policy 0, policy_version 93192 (0.0009) -[2023-10-16 06:27:46,972][05218] Updated weights for policy 0, policy_version 93202 (0.0009) -[2023-10-16 06:27:47,004][05219] Updated weights for policy 1, policy_version 92900 (0.0009) -[2023-10-16 06:27:47,337][05218] Updated weights for policy 0, policy_version 93212 (0.0007) -[2023-10-16 06:27:47,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 190545920. Throughput: 0: 1805.2, 1: 1778.7. Samples: 47653492. Policy #0 lag: (min: 12.0, avg: 14.0, max: 41.0) -[2023-10-16 06:27:47,351][03835] Avg episode reward: [(0, '8.070'), (1, '8.490')] -[2023-10-16 06:27:47,374][05219] Updated weights for policy 1, policy_version 92910 (0.0008) -[2023-10-16 06:27:47,741][05219] Updated weights for policy 1, policy_version 92920 (0.0009) -[2023-10-16 06:27:51,086][05218] Updated weights for policy 0, policy_version 93222 (0.0009) -[2023-10-16 06:27:51,463][05218] Updated weights for policy 0, policy_version 93232 (0.0008) -[2023-10-16 06:27:51,597][05219] Updated weights for policy 1, policy_version 92930 (0.0009) -[2023-10-16 06:27:51,838][05218] Updated weights for policy 0, policy_version 93242 (0.0007) -[2023-10-16 06:27:51,960][05219] Updated weights for policy 1, policy_version 92940 (0.0007) -[2023-10-16 06:27:52,322][05219] Updated weights for policy 1, policy_version 92950 (0.0010) -[2023-10-16 06:27:52,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 190644224. Throughput: 0: 1781.6, 1: 1790.4. Samples: 47673564. Policy #0 lag: (min: 12.0, avg: 14.0, max: 41.0) -[2023-10-16 06:27:52,351][03835] Avg episode reward: [(0, '9.090'), (1, '7.830')] -[2023-10-16 06:27:52,676][05219] Updated weights for policy 1, policy_version 92960 (0.0010) -[2023-10-16 06:27:55,585][05218] Updated weights for policy 0, policy_version 93252 (0.0009) -[2023-10-16 06:27:55,966][05218] Updated weights for policy 0, policy_version 93262 (0.0007) -[2023-10-16 06:27:56,338][05218] Updated weights for policy 0, policy_version 93272 (0.0007) -[2023-10-16 06:27:56,538][05219] Updated weights for policy 1, policy_version 92970 (0.0008) -[2023-10-16 06:27:56,909][05219] Updated weights for policy 1, policy_version 92980 (0.0009) -[2023-10-16 06:27:57,278][05219] Updated weights for policy 1, policy_version 92990 (0.0009) -[2023-10-16 06:27:57,350][03835] Fps is (10 sec: 19661.0, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 190742528. Throughput: 0: 1800.4, 1: 1769.3. Samples: 47685362. Policy #0 lag: (min: 12.0, avg: 14.0, max: 41.0) -[2023-10-16 06:27:57,351][03835] Avg episode reward: [(0, '7.480'), (1, '8.940')] -[2023-10-16 06:28:00,143][05218] Updated weights for policy 0, policy_version 93282 (0.0008) -[2023-10-16 06:28:00,521][05218] Updated weights for policy 0, policy_version 93292 (0.0008) -[2023-10-16 06:28:00,889][05218] Updated weights for policy 0, policy_version 93302 (0.0009) -[2023-10-16 06:28:01,161][05219] Updated weights for policy 1, policy_version 93000 (0.0008) -[2023-10-16 06:28:01,268][05218] Updated weights for policy 0, policy_version 93312 (0.0008) -[2023-10-16 06:28:01,522][05219] Updated weights for policy 1, policy_version 93010 (0.0008) -[2023-10-16 06:28:01,884][05219] Updated weights for policy 1, policy_version 93020 (0.0008) -[2023-10-16 06:28:02,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 190808064. Throughput: 0: 1779.5, 1: 1789.2. Samples: 47705572. Policy #0 lag: (min: 12.0, avg: 14.0, max: 41.0) -[2023-10-16 06:28:02,351][03835] Avg episode reward: [(0, '7.900'), (1, '8.360')] -[2023-10-16 06:28:04,940][05218] Updated weights for policy 0, policy_version 93322 (0.0009) -[2023-10-16 06:28:05,301][05218] Updated weights for policy 0, policy_version 93332 (0.0008) -[2023-10-16 06:28:05,615][05219] Updated weights for policy 1, policy_version 93030 (0.0008) -[2023-10-16 06:28:05,675][05218] Updated weights for policy 0, policy_version 93342 (0.0007) -[2023-10-16 06:28:05,980][05219] Updated weights for policy 1, policy_version 93040 (0.0007) -[2023-10-16 06:28:06,341][05219] Updated weights for policy 1, policy_version 93050 (0.0009) -[2023-10-16 06:28:07,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 190873600. Throughput: 0: 1785.5, 1: 1770.6. Samples: 47727136. Policy #0 lag: (min: 12.0, avg: 14.0, max: 41.0) -[2023-10-16 06:28:07,351][03835] Avg episode reward: [(0, '8.530'), (1, '8.720')] -[2023-10-16 06:28:09,370][05218] Updated weights for policy 0, policy_version 93352 (0.0010) -[2023-10-16 06:28:09,745][05218] Updated weights for policy 0, policy_version 93362 (0.0010) -[2023-10-16 06:28:09,977][05219] Updated weights for policy 1, policy_version 93060 (0.0008) -[2023-10-16 06:28:10,120][05218] Updated weights for policy 0, policy_version 93372 (0.0009) -[2023-10-16 06:28:10,341][05219] Updated weights for policy 1, policy_version 93070 (0.0007) -[2023-10-16 06:28:10,712][05219] Updated weights for policy 1, policy_version 93080 (0.0009) -[2023-10-16 06:28:12,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 190939136. Throughput: 0: 1783.4, 1: 1795.8. Samples: 47738098. Policy #0 lag: (min: 12.0, avg: 14.0, max: 41.0) -[2023-10-16 06:28:12,351][03835] Avg episode reward: [(0, '8.660'), (1, '8.710')] -[2023-10-16 06:28:13,781][05218] Updated weights for policy 0, policy_version 93382 (0.0009) -[2023-10-16 06:28:14,157][05218] Updated weights for policy 0, policy_version 93392 (0.0009) -[2023-10-16 06:28:14,472][05219] Updated weights for policy 1, policy_version 93090 (0.0010) -[2023-10-16 06:28:14,529][05218] Updated weights for policy 0, policy_version 93402 (0.0008) -[2023-10-16 06:28:14,837][05219] Updated weights for policy 1, policy_version 93100 (0.0008) -[2023-10-16 06:28:15,207][05219] Updated weights for policy 1, policy_version 93110 (0.0008) -[2023-10-16 06:28:15,572][05219] Updated weights for policy 1, policy_version 93120 (0.0008) -[2023-10-16 06:28:17,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 191004672. Throughput: 0: 1784.3, 1: 1775.2. Samples: 47759616. Policy #0 lag: (min: 12.0, avg: 14.0, max: 41.0) -[2023-10-16 06:28:17,351][03835] Avg episode reward: [(0, '8.620'), (1, '8.500')] -[2023-10-16 06:28:18,311][05218] Updated weights for policy 0, policy_version 93412 (0.0009) -[2023-10-16 06:28:18,693][05218] Updated weights for policy 0, policy_version 93422 (0.0008) -[2023-10-16 06:28:19,064][05218] Updated weights for policy 0, policy_version 93432 (0.0008) -[2023-10-16 06:28:19,459][05219] Updated weights for policy 1, policy_version 93130 (0.0009) -[2023-10-16 06:28:19,824][05219] Updated weights for policy 1, policy_version 93140 (0.0009) -[2023-10-16 06:28:20,193][05219] Updated weights for policy 1, policy_version 93150 (0.0008) -[2023-10-16 06:28:22,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 191070208. Throughput: 0: 1794.8, 1: 1774.9. Samples: 47782134. Policy #0 lag: (min: 12.0, avg: 14.0, max: 41.0) -[2023-10-16 06:28:22,351][03835] Avg episode reward: [(0, '7.990'), (1, '9.300')] -[2023-10-16 06:28:22,860][05218] Updated weights for policy 0, policy_version 93442 (0.0008) -[2023-10-16 06:28:23,229][05218] Updated weights for policy 0, policy_version 93452 (0.0007) -[2023-10-16 06:28:23,607][05218] Updated weights for policy 0, policy_version 93462 (0.0011) -[2023-10-16 06:28:23,922][05219] Updated weights for policy 1, policy_version 93160 (0.0009) -[2023-10-16 06:28:23,983][05218] Updated weights for policy 0, policy_version 93472 (0.0007) -[2023-10-16 06:28:24,287][05219] Updated weights for policy 1, policy_version 93170 (0.0009) -[2023-10-16 06:28:24,655][05219] Updated weights for policy 1, policy_version 93180 (0.0008) -[2023-10-16 06:28:27,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 191135744. Throughput: 0: 1787.9, 1: 1772.0. Samples: 47791684. Policy #0 lag: (min: 12.0, avg: 14.0, max: 41.0) -[2023-10-16 06:28:27,351][03835] Avg episode reward: [(0, '9.180'), (1, '8.540')] -[2023-10-16 06:28:27,719][05218] Updated weights for policy 0, policy_version 93482 (0.0009) -[2023-10-16 06:28:28,104][05218] Updated weights for policy 0, policy_version 93492 (0.0007) -[2023-10-16 06:28:28,431][05219] Updated weights for policy 1, policy_version 93190 (0.0009) -[2023-10-16 06:28:28,484][05218] Updated weights for policy 0, policy_version 93502 (0.0007) -[2023-10-16 06:28:28,796][05219] Updated weights for policy 1, policy_version 93200 (0.0010) -[2023-10-16 06:28:29,165][05219] Updated weights for policy 1, policy_version 93210 (0.0010) -[2023-10-16 06:28:32,249][05218] Updated weights for policy 0, policy_version 93512 (0.0007) -[2023-10-16 06:28:32,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 191201280. Throughput: 0: 1789.2, 1: 1775.7. Samples: 47813912. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:28:32,351][03835] Avg episode reward: [(0, '7.730'), (1, '8.960')] -[2023-10-16 06:28:32,612][05218] Updated weights for policy 0, policy_version 93522 (0.0007) -[2023-10-16 06:28:32,988][05218] Updated weights for policy 0, policy_version 93532 (0.0007) -[2023-10-16 06:28:33,042][05219] Updated weights for policy 1, policy_version 93220 (0.0008) -[2023-10-16 06:28:33,408][05219] Updated weights for policy 1, policy_version 93230 (0.0008) -[2023-10-16 06:28:33,768][05219] Updated weights for policy 1, policy_version 93240 (0.0010) -[2023-10-16 06:28:36,769][05218] Updated weights for policy 0, policy_version 93542 (0.0008) -[2023-10-16 06:28:37,144][05218] Updated weights for policy 0, policy_version 93552 (0.0007) -[2023-10-16 06:28:37,351][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 191266816. Throughput: 0: 1802.3, 1: 1793.2. Samples: 47835366. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:28:37,352][03835] Avg episode reward: [(0, '7.780'), (1, '8.440')] -[2023-10-16 06:28:37,524][05218] Updated weights for policy 0, policy_version 93562 (0.0007) -[2023-10-16 06:28:37,603][05219] Updated weights for policy 1, policy_version 93250 (0.0009) -[2023-10-16 06:28:37,966][05219] Updated weights for policy 1, policy_version 93260 (0.0008) -[2023-10-16 06:28:38,337][05219] Updated weights for policy 1, policy_version 93270 (0.0008) -[2023-10-16 06:28:38,694][05219] Updated weights for policy 1, policy_version 93280 (0.0009) -[2023-10-16 06:28:41,302][05218] Updated weights for policy 0, policy_version 93572 (0.0008) -[2023-10-16 06:28:41,675][05218] Updated weights for policy 0, policy_version 93582 (0.0007) -[2023-10-16 06:28:42,057][05218] Updated weights for policy 0, policy_version 93592 (0.0008) -[2023-10-16 06:28:42,222][05219] Updated weights for policy 1, policy_version 93290 (0.0007) -[2023-10-16 06:28:42,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 191332352. Throughput: 0: 1791.2, 1: 1783.9. Samples: 47846242. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:28:42,351][03835] Avg episode reward: [(0, '7.510'), (1, '8.540')] -[2023-10-16 06:28:42,590][05219] Updated weights for policy 1, policy_version 93300 (0.0009) -[2023-10-16 06:28:42,957][05219] Updated weights for policy 1, policy_version 93310 (0.0009) -[2023-10-16 06:28:45,830][05218] Updated weights for policy 0, policy_version 93602 (0.0010) -[2023-10-16 06:28:46,211][05218] Updated weights for policy 0, policy_version 93612 (0.0010) -[2023-10-16 06:28:46,582][05218] Updated weights for policy 0, policy_version 93622 (0.0008) -[2023-10-16 06:28:46,787][05219] Updated weights for policy 1, policy_version 93320 (0.0008) -[2023-10-16 06:28:46,951][05218] Updated weights for policy 0, policy_version 93632 (0.0009) -[2023-10-16 06:28:47,141][05219] Updated weights for policy 1, policy_version 93330 (0.0008) -[2023-10-16 06:28:47,350][03835] Fps is (10 sec: 16384.6, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 191430656. Throughput: 0: 1812.9, 1: 1794.3. Samples: 47867896. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:28:47,351][03835] Avg episode reward: [(0, '7.520'), (1, '8.510')] -[2023-10-16 06:28:47,508][05219] Updated weights for policy 1, policy_version 93340 (0.0007) -[2023-10-16 06:28:50,849][05218] Updated weights for policy 0, policy_version 93642 (0.0011) -[2023-10-16 06:28:51,214][05219] Updated weights for policy 1, policy_version 93350 (0.0007) -[2023-10-16 06:28:51,222][05218] Updated weights for policy 0, policy_version 93652 (0.0008) -[2023-10-16 06:28:51,572][05219] Updated weights for policy 1, policy_version 93360 (0.0007) -[2023-10-16 06:28:51,601][05218] Updated weights for policy 0, policy_version 93662 (0.0009) -[2023-10-16 06:28:51,934][05219] Updated weights for policy 1, policy_version 93370 (0.0009) -[2023-10-16 06:28:52,350][03835] Fps is (10 sec: 19660.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 191528960. Throughput: 0: 1781.8, 1: 1790.5. Samples: 47887890. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:28:52,351][03835] Avg episode reward: [(0, '7.520'), (1, '8.220')] -[2023-10-16 06:28:55,307][05218] Updated weights for policy 0, policy_version 93672 (0.0007) -[2023-10-16 06:28:55,678][05218] Updated weights for policy 0, policy_version 93682 (0.0008) -[2023-10-16 06:28:55,693][05219] Updated weights for policy 1, policy_version 93380 (0.0007) -[2023-10-16 06:28:56,053][05219] Updated weights for policy 1, policy_version 93390 (0.0008) -[2023-10-16 06:28:56,058][05218] Updated weights for policy 0, policy_version 93692 (0.0008) -[2023-10-16 06:28:56,420][05219] Updated weights for policy 1, policy_version 93400 (0.0008) -[2023-10-16 06:28:57,350][03835] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 191594496. Throughput: 0: 1807.6, 1: 1793.3. Samples: 47900140. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:28:57,351][03835] Avg episode reward: [(0, '7.020'), (1, '8.060')] -[2023-10-16 06:28:59,924][05218] Updated weights for policy 0, policy_version 93702 (0.0009) -[2023-10-16 06:29:00,189][05219] Updated weights for policy 1, policy_version 93410 (0.0008) -[2023-10-16 06:29:00,301][05218] Updated weights for policy 0, policy_version 93712 (0.0007) -[2023-10-16 06:29:00,551][05219] Updated weights for policy 1, policy_version 93420 (0.0008) -[2023-10-16 06:29:00,679][05218] Updated weights for policy 0, policy_version 93722 (0.0007) -[2023-10-16 06:29:00,914][05219] Updated weights for policy 1, policy_version 93430 (0.0008) -[2023-10-16 06:29:01,277][05219] Updated weights for policy 1, policy_version 93440 (0.0008) -[2023-10-16 06:29:02,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 191660032. Throughput: 0: 1779.1, 1: 1795.7. Samples: 47920484. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:29:02,351][03835] Avg episode reward: [(0, '7.440'), (1, '9.790')] -[2023-10-16 06:29:04,451][05218] Updated weights for policy 0, policy_version 93732 (0.0009) -[2023-10-16 06:29:04,826][05218] Updated weights for policy 0, policy_version 93742 (0.0009) -[2023-10-16 06:29:05,082][05219] Updated weights for policy 1, policy_version 93450 (0.0008) -[2023-10-16 06:29:05,207][05218] Updated weights for policy 0, policy_version 93752 (0.0007) -[2023-10-16 06:29:05,455][05219] Updated weights for policy 1, policy_version 93460 (0.0008) -[2023-10-16 06:29:05,816][05219] Updated weights for policy 1, policy_version 93470 (0.0007) -[2023-10-16 06:29:07,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 191725568. Throughput: 0: 1775.4, 1: 1788.2. Samples: 47942496. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:29:07,351][03835] Avg episode reward: [(0, '7.940'), (1, '8.810')] -[2023-10-16 06:29:08,917][05218] Updated weights for policy 0, policy_version 93762 (0.0009) -[2023-10-16 06:29:09,289][05218] Updated weights for policy 0, policy_version 93772 (0.0009) -[2023-10-16 06:29:09,668][05218] Updated weights for policy 0, policy_version 93782 (0.0008) -[2023-10-16 06:29:09,795][05219] Updated weights for policy 1, policy_version 93480 (0.0007) -[2023-10-16 06:29:10,045][05218] Updated weights for policy 0, policy_version 93792 (0.0007) -[2023-10-16 06:29:10,157][05219] Updated weights for policy 1, policy_version 93490 (0.0007) -[2023-10-16 06:29:10,511][05219] Updated weights for policy 1, policy_version 93500 (0.0007) -[2023-10-16 06:29:12,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 191791104. Throughput: 0: 1774.8, 1: 1804.3. Samples: 47952744. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:29:12,351][03835] Avg episode reward: [(0, '7.820'), (1, '8.780')] -[2023-10-16 06:29:13,766][05218] Updated weights for policy 0, policy_version 93802 (0.0007) -[2023-10-16 06:29:14,144][05218] Updated weights for policy 0, policy_version 93812 (0.0007) -[2023-10-16 06:29:14,178][05219] Updated weights for policy 1, policy_version 93510 (0.0007) -[2023-10-16 06:29:14,522][05218] Updated weights for policy 0, policy_version 93822 (0.0008) -[2023-10-16 06:29:14,549][05219] Updated weights for policy 1, policy_version 93520 (0.0010) -[2023-10-16 06:29:14,923][05219] Updated weights for policy 1, policy_version 93530 (0.0011) -[2023-10-16 06:29:17,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 191856640. Throughput: 0: 1777.1, 1: 1786.5. Samples: 47974272. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:29:17,351][03835] Avg episode reward: [(0, '7.860'), (1, '8.990')] -[2023-10-16 06:29:18,159][05218] Updated weights for policy 0, policy_version 93832 (0.0009) -[2023-10-16 06:29:18,546][05218] Updated weights for policy 0, policy_version 93842 (0.0010) -[2023-10-16 06:29:18,863][05219] Updated weights for policy 1, policy_version 93540 (0.0008) -[2023-10-16 06:29:18,906][05218] Updated weights for policy 0, policy_version 93852 (0.0009) -[2023-10-16 06:29:19,223][05219] Updated weights for policy 1, policy_version 93550 (0.0009) -[2023-10-16 06:29:19,582][05219] Updated weights for policy 1, policy_version 93560 (0.0010) -[2023-10-16 06:29:22,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 191922176. Throughput: 0: 1796.1, 1: 1779.8. Samples: 47996282. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:29:22,351][03835] Avg episode reward: [(0, '7.610'), (1, '8.410')] -[2023-10-16 06:29:22,729][05218] Updated weights for policy 0, policy_version 93862 (0.0007) -[2023-10-16 06:29:23,096][05218] Updated weights for policy 0, policy_version 93872 (0.0009) -[2023-10-16 06:29:23,367][05219] Updated weights for policy 1, policy_version 93570 (0.0010) -[2023-10-16 06:29:23,489][05218] Updated weights for policy 0, policy_version 93882 (0.0008) -[2023-10-16 06:29:23,732][05219] Updated weights for policy 1, policy_version 93580 (0.0008) -[2023-10-16 06:29:24,100][05219] Updated weights for policy 1, policy_version 93590 (0.0007) -[2023-10-16 06:29:24,474][05219] Updated weights for policy 1, policy_version 93600 (0.0008) -[2023-10-16 06:29:27,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 191987712. Throughput: 0: 1774.1, 1: 1775.9. Samples: 48005990. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:29:27,351][03835] Avg episode reward: [(0, '7.520'), (1, '8.720')] -[2023-10-16 06:29:27,405][05218] Updated weights for policy 0, policy_version 93892 (0.0010) -[2023-10-16 06:29:27,803][05218] Updated weights for policy 0, policy_version 93902 (0.0008) -[2023-10-16 06:29:28,144][05219] Updated weights for policy 1, policy_version 93610 (0.0007) -[2023-10-16 06:29:28,182][05218] Updated weights for policy 0, policy_version 93912 (0.0008) -[2023-10-16 06:29:28,513][05219] Updated weights for policy 1, policy_version 93620 (0.0008) -[2023-10-16 06:29:28,870][05219] Updated weights for policy 1, policy_version 93630 (0.0011) -[2023-10-16 06:29:31,820][05218] Updated weights for policy 0, policy_version 93922 (0.0007) -[2023-10-16 06:29:32,185][05218] Updated weights for policy 0, policy_version 93932 (0.0007) -[2023-10-16 06:29:32,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 192053248. Throughput: 0: 1788.5, 1: 1779.3. Samples: 48028446. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-16 06:29:32,351][03835] Avg episode reward: [(0, '7.250'), (1, '7.960')] -[2023-10-16 06:29:32,566][05218] Updated weights for policy 0, policy_version 93942 (0.0007) -[2023-10-16 06:29:32,624][05219] Updated weights for policy 1, policy_version 93640 (0.0008) -[2023-10-16 06:29:32,934][05218] Updated weights for policy 0, policy_version 93952 (0.0007) -[2023-10-16 06:29:32,983][05219] Updated weights for policy 1, policy_version 93650 (0.0008) -[2023-10-16 06:29:33,353][05219] Updated weights for policy 1, policy_version 93660 (0.0009) -[2023-10-16 06:29:36,855][05218] Updated weights for policy 0, policy_version 93962 (0.0008) -[2023-10-16 06:29:37,033][05219] Updated weights for policy 1, policy_version 93670 (0.0009) -[2023-10-16 06:29:37,238][05218] Updated weights for policy 0, policy_version 93972 (0.0009) -[2023-10-16 06:29:37,351][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 192118784. Throughput: 0: 1783.4, 1: 1804.3. Samples: 48049336. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-16 06:29:37,352][03835] Avg episode reward: [(0, '7.640'), (1, '8.030')] -[2023-10-16 06:29:37,410][05219] Updated weights for policy 1, policy_version 93680 (0.0007) -[2023-10-16 06:29:37,611][05218] Updated weights for policy 0, policy_version 93982 (0.0009) -[2023-10-16 06:29:37,685][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000093984_96239616.pth... -[2023-10-16 06:29:37,714][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000092288_94502912.pth -[2023-10-16 06:29:37,771][05219] Updated weights for policy 1, policy_version 93690 (0.0008) -[2023-10-16 06:29:37,983][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000093696_95944704.pth... -[2023-10-16 06:29:38,026][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000092000_94208000.pth -[2023-10-16 06:29:41,365][05218] Updated weights for policy 0, policy_version 93992 (0.0010) -[2023-10-16 06:29:41,499][05219] Updated weights for policy 1, policy_version 93700 (0.0009) -[2023-10-16 06:29:41,735][05218] Updated weights for policy 0, policy_version 94002 (0.0009) -[2023-10-16 06:29:41,870][05219] Updated weights for policy 1, policy_version 93710 (0.0008) -[2023-10-16 06:29:42,109][05218] Updated weights for policy 0, policy_version 94012 (0.0007) -[2023-10-16 06:29:42,224][05219] Updated weights for policy 1, policy_version 93720 (0.0009) -[2023-10-16 06:29:42,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 192217088. Throughput: 0: 1782.8, 1: 1782.4. Samples: 48060572. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-16 06:29:42,351][03835] Avg episode reward: [(0, '7.490'), (1, '8.220')] -[2023-10-16 06:29:45,809][05218] Updated weights for policy 0, policy_version 94022 (0.0008) -[2023-10-16 06:29:46,149][05219] Updated weights for policy 1, policy_version 93730 (0.0008) -[2023-10-16 06:29:46,190][05218] Updated weights for policy 0, policy_version 94032 (0.0008) -[2023-10-16 06:29:46,508][05219] Updated weights for policy 1, policy_version 93740 (0.0009) -[2023-10-16 06:29:46,568][05218] Updated weights for policy 0, policy_version 94042 (0.0007) -[2023-10-16 06:29:46,872][05219] Updated weights for policy 1, policy_version 93750 (0.0008) -[2023-10-16 06:29:47,240][05219] Updated weights for policy 1, policy_version 93760 (0.0007) -[2023-10-16 06:29:47,350][03835] Fps is (10 sec: 19661.6, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 192315392. Throughput: 0: 1790.1, 1: 1795.1. Samples: 48081818. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-16 06:29:47,351][03835] Avg episode reward: [(0, '7.550'), (1, '8.420')] -[2023-10-16 06:29:50,341][05218] Updated weights for policy 0, policy_version 94052 (0.0007) -[2023-10-16 06:29:50,728][05218] Updated weights for policy 0, policy_version 94062 (0.0008) -[2023-10-16 06:29:51,064][05219] Updated weights for policy 1, policy_version 93770 (0.0008) -[2023-10-16 06:29:51,097][05218] Updated weights for policy 0, policy_version 94072 (0.0010) -[2023-10-16 06:29:51,436][05219] Updated weights for policy 1, policy_version 93780 (0.0009) -[2023-10-16 06:29:51,802][05219] Updated weights for policy 1, policy_version 93790 (0.0009) -[2023-10-16 06:29:52,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 192380928. Throughput: 0: 1775.4, 1: 1771.0. Samples: 48102084. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-16 06:29:52,352][03835] Avg episode reward: [(0, '7.350'), (1, '7.890')] -[2023-10-16 06:29:54,868][05218] Updated weights for policy 0, policy_version 94082 (0.0009) -[2023-10-16 06:29:55,237][05218] Updated weights for policy 0, policy_version 94092 (0.0008) -[2023-10-16 06:29:55,614][05218] Updated weights for policy 0, policy_version 94102 (0.0010) -[2023-10-16 06:29:55,808][05219] Updated weights for policy 1, policy_version 93800 (0.0009) -[2023-10-16 06:29:55,978][05218] Updated weights for policy 0, policy_version 94112 (0.0007) -[2023-10-16 06:29:56,176][05219] Updated weights for policy 1, policy_version 93810 (0.0008) -[2023-10-16 06:29:56,544][05219] Updated weights for policy 1, policy_version 93820 (0.0007) -[2023-10-16 06:29:57,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.6, 300 sec: 14329.1). Total num frames: 192446464. Throughput: 0: 1795.2, 1: 1788.7. Samples: 48114018. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-16 06:29:57,351][03835] Avg episode reward: [(0, '6.320'), (1, '9.720')] -[2023-10-16 06:29:59,572][05218] Updated weights for policy 0, policy_version 94122 (0.0009) -[2023-10-16 06:29:59,952][05218] Updated weights for policy 0, policy_version 94132 (0.0008) -[2023-10-16 06:30:00,210][05219] Updated weights for policy 1, policy_version 93830 (0.0009) -[2023-10-16 06:30:00,329][05218] Updated weights for policy 0, policy_version 94142 (0.0009) -[2023-10-16 06:30:00,575][05219] Updated weights for policy 1, policy_version 93840 (0.0007) -[2023-10-16 06:30:00,935][05219] Updated weights for policy 1, policy_version 93850 (0.0008) -[2023-10-16 06:30:02,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 192512000. Throughput: 0: 1779.2, 1: 1779.7. Samples: 48134424. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-16 06:30:02,351][03835] Avg episode reward: [(0, '6.400'), (1, '9.000')] -[2023-10-16 06:30:04,105][05218] Updated weights for policy 0, policy_version 94152 (0.0009) -[2023-10-16 06:30:04,480][05218] Updated weights for policy 0, policy_version 94162 (0.0007) -[2023-10-16 06:30:04,731][05219] Updated weights for policy 1, policy_version 93860 (0.0009) -[2023-10-16 06:30:04,850][05218] Updated weights for policy 0, policy_version 94172 (0.0009) -[2023-10-16 06:30:05,085][05219] Updated weights for policy 1, policy_version 93870 (0.0008) -[2023-10-16 06:30:05,447][05219] Updated weights for policy 1, policy_version 93880 (0.0011) -[2023-10-16 06:30:07,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 192577536. Throughput: 0: 1776.4, 1: 1787.8. Samples: 48156672. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-16 06:30:07,351][03835] Avg episode reward: [(0, '7.580'), (1, '8.310')] -[2023-10-16 06:30:08,738][05218] Updated weights for policy 0, policy_version 94182 (0.0008) -[2023-10-16 06:30:09,088][05219] Updated weights for policy 1, policy_version 93890 (0.0010) -[2023-10-16 06:30:09,103][05218] Updated weights for policy 0, policy_version 94192 (0.0007) -[2023-10-16 06:30:09,461][05219] Updated weights for policy 1, policy_version 93900 (0.0007) -[2023-10-16 06:30:09,489][05218] Updated weights for policy 0, policy_version 94202 (0.0008) -[2023-10-16 06:30:09,830][05219] Updated weights for policy 1, policy_version 93910 (0.0009) -[2023-10-16 06:30:10,195][05219] Updated weights for policy 1, policy_version 93920 (0.0010) -[2023-10-16 06:30:12,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 192643072. Throughput: 0: 1776.7, 1: 1796.1. Samples: 48166768. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-16 06:30:12,351][03835] Avg episode reward: [(0, '6.630'), (1, '8.270')] -[2023-10-16 06:30:13,332][05218] Updated weights for policy 0, policy_version 94212 (0.0008) -[2023-10-16 06:30:13,708][05218] Updated weights for policy 0, policy_version 94222 (0.0009) -[2023-10-16 06:30:14,007][05219] Updated weights for policy 1, policy_version 93930 (0.0008) -[2023-10-16 06:30:14,085][05218] Updated weights for policy 0, policy_version 94232 (0.0008) -[2023-10-16 06:30:14,368][05219] Updated weights for policy 1, policy_version 93940 (0.0007) -[2023-10-16 06:30:14,738][05219] Updated weights for policy 1, policy_version 93950 (0.0009) -[2023-10-16 06:30:17,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 192708608. Throughput: 0: 1776.0, 1: 1785.9. Samples: 48188730. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-16 06:30:17,351][03835] Avg episode reward: [(0, '6.840'), (1, '8.380')] -[2023-10-16 06:30:17,895][05218] Updated weights for policy 0, policy_version 94242 (0.0008) -[2023-10-16 06:30:18,294][05218] Updated weights for policy 0, policy_version 94252 (0.0007) -[2023-10-16 06:30:18,477][05219] Updated weights for policy 1, policy_version 93960 (0.0010) -[2023-10-16 06:30:18,671][05218] Updated weights for policy 0, policy_version 94262 (0.0008) -[2023-10-16 06:30:18,849][05219] Updated weights for policy 1, policy_version 93970 (0.0007) -[2023-10-16 06:30:19,046][05218] Updated weights for policy 0, policy_version 94272 (0.0008) -[2023-10-16 06:30:19,204][05219] Updated weights for policy 1, policy_version 93980 (0.0009) -[2023-10-16 06:30:22,351][03835] Fps is (10 sec: 13106.6, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 192774144. Throughput: 0: 1798.4, 1: 1787.9. Samples: 48210718. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-16 06:30:22,352][03835] Avg episode reward: [(0, '8.200'), (1, '8.510')] -[2023-10-16 06:30:22,722][05218] Updated weights for policy 0, policy_version 94282 (0.0007) -[2023-10-16 06:30:23,057][05219] Updated weights for policy 1, policy_version 93990 (0.0008) -[2023-10-16 06:30:23,105][05218] Updated weights for policy 0, policy_version 94292 (0.0007) -[2023-10-16 06:30:23,416][05219] Updated weights for policy 1, policy_version 94000 (0.0009) -[2023-10-16 06:30:23,475][05218] Updated weights for policy 0, policy_version 94302 (0.0007) -[2023-10-16 06:30:23,772][05219] Updated weights for policy 1, policy_version 94010 (0.0008) -[2023-10-16 06:30:27,126][05218] Updated weights for policy 0, policy_version 94312 (0.0007) -[2023-10-16 06:30:27,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 192839680. Throughput: 0: 1780.2, 1: 1780.3. Samples: 48220794. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-16 06:30:27,351][03835] Avg episode reward: [(0, '6.930'), (1, '7.720')] -[2023-10-16 06:30:27,502][05218] Updated weights for policy 0, policy_version 94322 (0.0007) -[2023-10-16 06:30:27,546][05219] Updated weights for policy 1, policy_version 94020 (0.0009) -[2023-10-16 06:30:27,871][05218] Updated weights for policy 0, policy_version 94332 (0.0007) -[2023-10-16 06:30:27,908][05219] Updated weights for policy 1, policy_version 94030 (0.0009) -[2023-10-16 06:30:28,276][05219] Updated weights for policy 1, policy_version 94040 (0.0010) -[2023-10-16 06:30:31,479][05218] Updated weights for policy 0, policy_version 94342 (0.0008) -[2023-10-16 06:30:31,856][05218] Updated weights for policy 0, policy_version 94352 (0.0009) -[2023-10-16 06:30:32,021][05219] Updated weights for policy 1, policy_version 94050 (0.0008) -[2023-10-16 06:30:32,230][05218] Updated weights for policy 0, policy_version 94362 (0.0010) -[2023-10-16 06:30:32,350][03835] Fps is (10 sec: 13107.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 192905216. Throughput: 0: 1799.0, 1: 1781.5. Samples: 48242942. Policy #0 lag: (min: 17.0, avg: 31.1, max: 49.0) -[2023-10-16 06:30:32,351][03835] Avg episode reward: [(0, '6.980'), (1, '8.370')] -[2023-10-16 06:30:32,389][05219] Updated weights for policy 1, policy_version 94060 (0.0007) -[2023-10-16 06:30:32,752][05219] Updated weights for policy 1, policy_version 94070 (0.0007) -[2023-10-16 06:30:33,114][05219] Updated weights for policy 1, policy_version 94080 (0.0008) -[2023-10-16 06:30:35,953][05218] Updated weights for policy 0, policy_version 94372 (0.0010) -[2023-10-16 06:30:36,332][05218] Updated weights for policy 0, policy_version 94382 (0.0011) -[2023-10-16 06:30:36,697][05218] Updated weights for policy 0, policy_version 94392 (0.0009) -[2023-10-16 06:30:36,969][05219] Updated weights for policy 1, policy_version 94090 (0.0009) -[2023-10-16 06:30:37,343][05219] Updated weights for policy 1, policy_version 94100 (0.0011) -[2023-10-16 06:30:37,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 193003520. Throughput: 0: 1782.2, 1: 1797.2. Samples: 48263156. Policy #0 lag: (min: 17.0, avg: 31.1, max: 49.0) -[2023-10-16 06:30:37,351][03835] Avg episode reward: [(0, '7.450'), (1, '8.580')] -[2023-10-16 06:30:37,721][05219] Updated weights for policy 1, policy_version 94110 (0.0009) -[2023-10-16 06:30:40,527][05218] Updated weights for policy 0, policy_version 94402 (0.0009) -[2023-10-16 06:30:40,893][05218] Updated weights for policy 0, policy_version 94412 (0.0007) -[2023-10-16 06:30:41,268][05218] Updated weights for policy 0, policy_version 94422 (0.0007) -[2023-10-16 06:30:41,554][05219] Updated weights for policy 1, policy_version 94120 (0.0008) -[2023-10-16 06:30:41,643][05218] Updated weights for policy 0, policy_version 94432 (0.0008) -[2023-10-16 06:30:41,915][05219] Updated weights for policy 1, policy_version 94130 (0.0010) -[2023-10-16 06:30:42,278][05219] Updated weights for policy 1, policy_version 94140 (0.0009) -[2023-10-16 06:30:42,351][03835] Fps is (10 sec: 16383.4, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 193069056. Throughput: 0: 1796.8, 1: 1776.5. Samples: 48274820. Policy #0 lag: (min: 17.0, avg: 31.1, max: 49.0) -[2023-10-16 06:30:42,352][03835] Avg episode reward: [(0, '7.170'), (1, '8.010')] -[2023-10-16 06:30:45,584][05218] Updated weights for policy 0, policy_version 94442 (0.0007) -[2023-10-16 06:30:45,953][05218] Updated weights for policy 0, policy_version 94452 (0.0009) -[2023-10-16 06:30:46,190][05219] Updated weights for policy 1, policy_version 94150 (0.0010) -[2023-10-16 06:30:46,328][05218] Updated weights for policy 0, policy_version 94462 (0.0009) -[2023-10-16 06:30:46,556][05219] Updated weights for policy 1, policy_version 94160 (0.0009) -[2023-10-16 06:30:46,920][05219] Updated weights for policy 1, policy_version 94170 (0.0009) -[2023-10-16 06:30:47,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 193167360. Throughput: 0: 1777.4, 1: 1790.1. Samples: 48294962. Policy #0 lag: (min: 17.0, avg: 31.1, max: 49.0) -[2023-10-16 06:30:47,352][03835] Avg episode reward: [(0, '7.210'), (1, '8.320')] -[2023-10-16 06:30:50,156][05218] Updated weights for policy 0, policy_version 94472 (0.0008) -[2023-10-16 06:30:50,537][05218] Updated weights for policy 0, policy_version 94482 (0.0008) -[2023-10-16 06:30:50,684][05219] Updated weights for policy 1, policy_version 94180 (0.0009) -[2023-10-16 06:30:50,900][05218] Updated weights for policy 0, policy_version 94492 (0.0010) -[2023-10-16 06:30:51,047][05219] Updated weights for policy 1, policy_version 94190 (0.0009) -[2023-10-16 06:30:51,413][05219] Updated weights for policy 1, policy_version 94200 (0.0009) -[2023-10-16 06:30:52,350][03835] Fps is (10 sec: 16384.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 193232896. Throughput: 0: 1778.6, 1: 1757.8. Samples: 48315810. Policy #0 lag: (min: 17.0, avg: 31.1, max: 49.0) -[2023-10-16 06:30:52,351][03835] Avg episode reward: [(0, '6.920'), (1, '8.460')] -[2023-10-16 06:30:54,644][05218] Updated weights for policy 0, policy_version 94502 (0.0008) -[2023-10-16 06:30:55,029][05218] Updated weights for policy 0, policy_version 94512 (0.0010) -[2023-10-16 06:30:55,234][05219] Updated weights for policy 1, policy_version 94210 (0.0008) -[2023-10-16 06:30:55,409][05218] Updated weights for policy 0, policy_version 94522 (0.0007) -[2023-10-16 06:30:55,602][05219] Updated weights for policy 1, policy_version 94220 (0.0008) -[2023-10-16 06:30:55,965][05219] Updated weights for policy 1, policy_version 94230 (0.0010) -[2023-10-16 06:30:56,320][05219] Updated weights for policy 1, policy_version 94240 (0.0010) -[2023-10-16 06:30:57,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 193298432. Throughput: 0: 1785.3, 1: 1783.0. Samples: 48327340. Policy #0 lag: (min: 17.0, avg: 31.1, max: 49.0) -[2023-10-16 06:30:57,351][03835] Avg episode reward: [(0, '7.460'), (1, '8.200')] -[2023-10-16 06:30:59,088][05218] Updated weights for policy 0, policy_version 94532 (0.0007) -[2023-10-16 06:30:59,465][05218] Updated weights for policy 0, policy_version 94542 (0.0007) -[2023-10-16 06:30:59,851][05218] Updated weights for policy 0, policy_version 94552 (0.0008) -[2023-10-16 06:31:00,145][05219] Updated weights for policy 1, policy_version 94250 (0.0008) -[2023-10-16 06:31:00,510][05219] Updated weights for policy 1, policy_version 94260 (0.0008) -[2023-10-16 06:31:00,881][05219] Updated weights for policy 1, policy_version 94270 (0.0010) -[2023-10-16 06:31:02,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 193363968. Throughput: 0: 1780.8, 1: 1762.4. Samples: 48348176. Policy #0 lag: (min: 17.0, avg: 31.1, max: 49.0) -[2023-10-16 06:31:02,351][03835] Avg episode reward: [(0, '7.590'), (1, '7.700')] -[2023-10-16 06:31:03,618][05218] Updated weights for policy 0, policy_version 94562 (0.0008) -[2023-10-16 06:31:04,019][05218] Updated weights for policy 0, policy_version 94572 (0.0009) -[2023-10-16 06:31:04,395][05218] Updated weights for policy 0, policy_version 94582 (0.0011) -[2023-10-16 06:31:04,617][05219] Updated weights for policy 1, policy_version 94280 (0.0007) -[2023-10-16 06:31:04,768][05218] Updated weights for policy 0, policy_version 94592 (0.0008) -[2023-10-16 06:31:04,985][05219] Updated weights for policy 1, policy_version 94290 (0.0007) -[2023-10-16 06:31:05,342][05219] Updated weights for policy 1, policy_version 94300 (0.0009) -[2023-10-16 06:31:07,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 193429504. Throughput: 0: 1789.4, 1: 1765.9. Samples: 48370706. Policy #0 lag: (min: 17.0, avg: 31.1, max: 49.0) -[2023-10-16 06:31:07,351][03835] Avg episode reward: [(0, '7.500'), (1, '8.020')] -[2023-10-16 06:31:08,415][05218] Updated weights for policy 0, policy_version 94602 (0.0008) -[2023-10-16 06:31:08,790][05218] Updated weights for policy 0, policy_version 94612 (0.0007) -[2023-10-16 06:31:09,087][05219] Updated weights for policy 1, policy_version 94310 (0.0008) -[2023-10-16 06:31:09,175][05218] Updated weights for policy 0, policy_version 94622 (0.0009) -[2023-10-16 06:31:09,459][05219] Updated weights for policy 1, policy_version 94320 (0.0009) -[2023-10-16 06:31:09,826][05219] Updated weights for policy 1, policy_version 94330 (0.0007) -[2023-10-16 06:31:12,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 193495040. Throughput: 0: 1785.9, 1: 1763.0. Samples: 48380496. Policy #0 lag: (min: 17.0, avg: 31.1, max: 49.0) -[2023-10-16 06:31:12,351][03835] Avg episode reward: [(0, '7.370'), (1, '8.090')] -[2023-10-16 06:31:12,840][05218] Updated weights for policy 0, policy_version 94632 (0.0009) -[2023-10-16 06:31:13,218][05218] Updated weights for policy 0, policy_version 94642 (0.0010) -[2023-10-16 06:31:13,595][05218] Updated weights for policy 0, policy_version 94652 (0.0008) -[2023-10-16 06:31:13,680][05219] Updated weights for policy 1, policy_version 94340 (0.0007) -[2023-10-16 06:31:14,044][05219] Updated weights for policy 1, policy_version 94350 (0.0008) -[2023-10-16 06:31:14,405][05219] Updated weights for policy 1, policy_version 94360 (0.0008) -[2023-10-16 06:31:17,254][05218] Updated weights for policy 0, policy_version 94662 (0.0008) -[2023-10-16 06:31:17,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 193560576. Throughput: 0: 1786.3, 1: 1766.3. Samples: 48402810. Policy #0 lag: (min: 17.0, avg: 31.1, max: 49.0) -[2023-10-16 06:31:17,351][03835] Avg episode reward: [(0, '8.670'), (1, '8.740')] -[2023-10-16 06:31:17,637][05218] Updated weights for policy 0, policy_version 94672 (0.0008) -[2023-10-16 06:31:18,020][05218] Updated weights for policy 0, policy_version 94682 (0.0007) -[2023-10-16 06:31:18,325][05219] Updated weights for policy 1, policy_version 94370 (0.0007) -[2023-10-16 06:31:18,694][05219] Updated weights for policy 1, policy_version 94380 (0.0007) -[2023-10-16 06:31:19,057][05219] Updated weights for policy 1, policy_version 94390 (0.0008) -[2023-10-16 06:31:19,424][05219] Updated weights for policy 1, policy_version 94400 (0.0008) -[2023-10-16 06:31:21,690][05218] Updated weights for policy 0, policy_version 94692 (0.0009) -[2023-10-16 06:31:22,067][05218] Updated weights for policy 0, policy_version 94702 (0.0010) -[2023-10-16 06:31:22,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 193626112. Throughput: 0: 1802.0, 1: 1779.5. Samples: 48424324. Policy #0 lag: (min: 17.0, avg: 31.1, max: 49.0) -[2023-10-16 06:31:22,351][03835] Avg episode reward: [(0, '7.990'), (1, '8.580')] -[2023-10-16 06:31:22,444][05218] Updated weights for policy 0, policy_version 94712 (0.0007) -[2023-10-16 06:31:23,094][05219] Updated weights for policy 1, policy_version 94410 (0.0007) -[2023-10-16 06:31:23,459][05219] Updated weights for policy 1, policy_version 94420 (0.0009) -[2023-10-16 06:31:23,828][05219] Updated weights for policy 1, policy_version 94430 (0.0009) -[2023-10-16 06:31:26,281][05218] Updated weights for policy 0, policy_version 94722 (0.0007) -[2023-10-16 06:31:26,652][05218] Updated weights for policy 0, policy_version 94732 (0.0009) -[2023-10-16 06:31:27,031][05218] Updated weights for policy 0, policy_version 94742 (0.0009) -[2023-10-16 06:31:27,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 193691648. Throughput: 0: 1786.0, 1: 1770.5. Samples: 48434862. Policy #0 lag: (min: 17.0, avg: 31.1, max: 49.0) -[2023-10-16 06:31:27,351][03835] Avg episode reward: [(0, '7.020'), (1, '8.470')] -[2023-10-16 06:31:27,414][05218] Updated weights for policy 0, policy_version 94752 (0.0008) -[2023-10-16 06:31:27,708][05219] Updated weights for policy 1, policy_version 94440 (0.0009) -[2023-10-16 06:31:28,065][05219] Updated weights for policy 1, policy_version 94450 (0.0008) -[2023-10-16 06:31:28,424][05219] Updated weights for policy 1, policy_version 94460 (0.0007) -[2023-10-16 06:31:31,113][05218] Updated weights for policy 0, policy_version 94762 (0.0010) -[2023-10-16 06:31:31,487][05218] Updated weights for policy 0, policy_version 94772 (0.0009) -[2023-10-16 06:31:31,866][05218] Updated weights for policy 0, policy_version 94782 (0.0007) -[2023-10-16 06:31:32,232][05219] Updated weights for policy 1, policy_version 94470 (0.0008) -[2023-10-16 06:31:32,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 193789952. Throughput: 0: 1806.3, 1: 1784.8. Samples: 48456560. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:31:32,351][03835] Avg episode reward: [(0, '7.930'), (1, '8.910')] -[2023-10-16 06:31:32,599][05219] Updated weights for policy 1, policy_version 94480 (0.0008) -[2023-10-16 06:31:32,959][05219] Updated weights for policy 1, policy_version 94490 (0.0007) -[2023-10-16 06:31:35,571][05218] Updated weights for policy 0, policy_version 94792 (0.0009) -[2023-10-16 06:31:35,944][05218] Updated weights for policy 0, policy_version 94802 (0.0008) -[2023-10-16 06:31:36,307][05218] Updated weights for policy 0, policy_version 94812 (0.0008) -[2023-10-16 06:31:36,720][05219] Updated weights for policy 1, policy_version 94500 (0.0009) -[2023-10-16 06:31:37,089][05219] Updated weights for policy 1, policy_version 94510 (0.0009) -[2023-10-16 06:31:37,351][03835] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 193855488. Throughput: 0: 1792.3, 1: 1804.2. Samples: 48477650. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:31:37,352][03835] Avg episode reward: [(0, '8.500'), (1, '8.900')] -[2023-10-16 06:31:37,362][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000094816_97091584.pth... -[2023-10-16 06:31:37,390][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000093152_95387648.pth -[2023-10-16 06:31:37,462][05219] Updated weights for policy 1, policy_version 94520 (0.0009) -[2023-10-16 06:31:37,744][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000094528_96796672.pth... -[2023-10-16 06:31:37,781][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000092832_95059968.pth -[2023-10-16 06:31:40,013][05218] Updated weights for policy 0, policy_version 94822 (0.0008) -[2023-10-16 06:31:40,385][05218] Updated weights for policy 0, policy_version 94832 (0.0008) -[2023-10-16 06:31:40,770][05218] Updated weights for policy 0, policy_version 94842 (0.0009) -[2023-10-16 06:31:41,293][05219] Updated weights for policy 1, policy_version 94530 (0.0009) -[2023-10-16 06:31:41,658][05219] Updated weights for policy 1, policy_version 94540 (0.0007) -[2023-10-16 06:31:42,016][05219] Updated weights for policy 1, policy_version 94550 (0.0007) -[2023-10-16 06:31:42,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 193921024. Throughput: 0: 1806.3, 1: 1783.5. Samples: 48488882. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:31:42,352][03835] Avg episode reward: [(0, '7.830'), (1, '9.680')] -[2023-10-16 06:31:42,389][05219] Updated weights for policy 1, policy_version 94560 (0.0008) -[2023-10-16 06:31:44,544][05218] Updated weights for policy 0, policy_version 94852 (0.0010) -[2023-10-16 06:31:44,913][05218] Updated weights for policy 0, policy_version 94862 (0.0009) -[2023-10-16 06:31:45,282][05218] Updated weights for policy 0, policy_version 94872 (0.0007) -[2023-10-16 06:31:46,126][05219] Updated weights for policy 1, policy_version 94570 (0.0010) -[2023-10-16 06:31:46,494][05219] Updated weights for policy 1, policy_version 94580 (0.0009) -[2023-10-16 06:31:46,857][05219] Updated weights for policy 1, policy_version 94590 (0.0010) -[2023-10-16 06:31:47,350][03835] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 194019328. Throughput: 0: 1793.4, 1: 1800.2. Samples: 48509888. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:31:47,351][03835] Avg episode reward: [(0, '7.490'), (1, '9.000')] -[2023-10-16 06:31:48,993][05218] Updated weights for policy 0, policy_version 94882 (0.0008) -[2023-10-16 06:31:49,395][05218] Updated weights for policy 0, policy_version 94892 (0.0007) -[2023-10-16 06:31:49,774][05218] Updated weights for policy 0, policy_version 94902 (0.0007) -[2023-10-16 06:31:50,151][05218] Updated weights for policy 0, policy_version 94912 (0.0007) -[2023-10-16 06:31:50,575][05219] Updated weights for policy 1, policy_version 94600 (0.0009) -[2023-10-16 06:31:50,935][05219] Updated weights for policy 1, policy_version 94610 (0.0010) -[2023-10-16 06:31:51,300][05219] Updated weights for policy 1, policy_version 94620 (0.0011) -[2023-10-16 06:31:52,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 194084864. Throughput: 0: 1795.2, 1: 1776.5. Samples: 48531430. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:31:52,351][03835] Avg episode reward: [(0, '8.870'), (1, '8.230')] -[2023-10-16 06:31:53,909][05218] Updated weights for policy 0, policy_version 94922 (0.0011) -[2023-10-16 06:31:54,287][05218] Updated weights for policy 0, policy_version 94932 (0.0010) -[2023-10-16 06:31:54,673][05218] Updated weights for policy 0, policy_version 94942 (0.0011) -[2023-10-16 06:31:55,028][05219] Updated weights for policy 1, policy_version 94630 (0.0009) -[2023-10-16 06:31:55,394][05219] Updated weights for policy 1, policy_version 94640 (0.0008) -[2023-10-16 06:31:55,765][05219] Updated weights for policy 1, policy_version 94650 (0.0008) -[2023-10-16 06:31:57,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 194150400. Throughput: 0: 1790.2, 1: 1801.5. Samples: 48542122. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:31:57,351][03835] Avg episode reward: [(0, '8.250'), (1, '8.640')] -[2023-10-16 06:31:58,524][05218] Updated weights for policy 0, policy_version 94952 (0.0009) -[2023-10-16 06:31:58,897][05218] Updated weights for policy 0, policy_version 94962 (0.0009) -[2023-10-16 06:31:59,284][05218] Updated weights for policy 0, policy_version 94972 (0.0008) -[2023-10-16 06:31:59,495][05219] Updated weights for policy 1, policy_version 94660 (0.0009) -[2023-10-16 06:31:59,866][05219] Updated weights for policy 1, policy_version 94670 (0.0009) -[2023-10-16 06:32:00,238][05219] Updated weights for policy 1, policy_version 94680 (0.0008) -[2023-10-16 06:32:02,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 194215936. Throughput: 0: 1791.4, 1: 1782.4. Samples: 48563630. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:32:02,351][03835] Avg episode reward: [(0, '7.470'), (1, '8.240')] -[2023-10-16 06:32:03,016][05218] Updated weights for policy 0, policy_version 94982 (0.0008) -[2023-10-16 06:32:03,402][05218] Updated weights for policy 0, policy_version 94992 (0.0009) -[2023-10-16 06:32:03,782][05218] Updated weights for policy 0, policy_version 95002 (0.0009) -[2023-10-16 06:32:04,117][05219] Updated weights for policy 1, policy_version 94690 (0.0008) -[2023-10-16 06:32:04,484][05219] Updated weights for policy 1, policy_version 94700 (0.0007) -[2023-10-16 06:32:04,842][05219] Updated weights for policy 1, policy_version 94710 (0.0007) -[2023-10-16 06:32:05,210][05219] Updated weights for policy 1, policy_version 94720 (0.0007) -[2023-10-16 06:32:07,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 194281472. Throughput: 0: 1812.3, 1: 1782.8. Samples: 48586102. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:32:07,351][03835] Avg episode reward: [(0, '7.410'), (1, '8.750')] -[2023-10-16 06:32:07,489][05218] Updated weights for policy 0, policy_version 95012 (0.0010) -[2023-10-16 06:32:07,868][05218] Updated weights for policy 0, policy_version 95022 (0.0009) -[2023-10-16 06:32:08,244][05218] Updated weights for policy 0, policy_version 95032 (0.0007) -[2023-10-16 06:32:09,024][05219] Updated weights for policy 1, policy_version 94730 (0.0008) -[2023-10-16 06:32:09,390][05219] Updated weights for policy 1, policy_version 94740 (0.0010) -[2023-10-16 06:32:09,763][05219] Updated weights for policy 1, policy_version 94750 (0.0009) -[2023-10-16 06:32:11,939][05218] Updated weights for policy 0, policy_version 95042 (0.0009) -[2023-10-16 06:32:12,314][05218] Updated weights for policy 0, policy_version 95052 (0.0009) -[2023-10-16 06:32:12,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 194347008. Throughput: 0: 1795.7, 1: 1783.2. Samples: 48595916. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:32:12,352][03835] Avg episode reward: [(0, '8.810'), (1, '9.060')] -[2023-10-16 06:32:12,698][05218] Updated weights for policy 0, policy_version 95062 (0.0010) -[2023-10-16 06:32:13,065][05218] Updated weights for policy 0, policy_version 95072 (0.0008) -[2023-10-16 06:32:13,313][05219] Updated weights for policy 1, policy_version 94760 (0.0008) -[2023-10-16 06:32:13,675][05219] Updated weights for policy 1, policy_version 94770 (0.0009) -[2023-10-16 06:32:14,041][05219] Updated weights for policy 1, policy_version 94780 (0.0010) -[2023-10-16 06:32:16,875][05218] Updated weights for policy 0, policy_version 95082 (0.0007) -[2023-10-16 06:32:17,252][05218] Updated weights for policy 0, policy_version 95092 (0.0007) -[2023-10-16 06:32:17,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 194412544. Throughput: 0: 1804.3, 1: 1784.9. Samples: 48618076. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:32:17,351][03835] Avg episode reward: [(0, '7.430'), (1, '8.490')] -[2023-10-16 06:32:17,626][05218] Updated weights for policy 0, policy_version 95102 (0.0010) -[2023-10-16 06:32:18,091][05219] Updated weights for policy 1, policy_version 94790 (0.0010) -[2023-10-16 06:32:18,459][05219] Updated weights for policy 1, policy_version 94800 (0.0009) -[2023-10-16 06:32:18,830][05219] Updated weights for policy 1, policy_version 94810 (0.0009) -[2023-10-16 06:32:21,200][05218] Updated weights for policy 0, policy_version 95112 (0.0008) -[2023-10-16 06:32:21,579][05218] Updated weights for policy 0, policy_version 95122 (0.0010) -[2023-10-16 06:32:21,951][05218] Updated weights for policy 0, policy_version 95132 (0.0011) -[2023-10-16 06:32:22,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 194510848. Throughput: 0: 1795.9, 1: 1795.7. Samples: 48639272. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:32:22,351][03835] Avg episode reward: [(0, '7.260'), (1, '8.330')] -[2023-10-16 06:32:22,566][05219] Updated weights for policy 1, policy_version 94820 (0.0008) -[2023-10-16 06:32:22,925][05219] Updated weights for policy 1, policy_version 94830 (0.0008) -[2023-10-16 06:32:23,283][05219] Updated weights for policy 1, policy_version 94840 (0.0008) -[2023-10-16 06:32:25,616][05218] Updated weights for policy 0, policy_version 95142 (0.0009) -[2023-10-16 06:32:25,990][05218] Updated weights for policy 0, policy_version 95152 (0.0010) -[2023-10-16 06:32:26,372][05218] Updated weights for policy 0, policy_version 95162 (0.0011) -[2023-10-16 06:32:27,137][05219] Updated weights for policy 1, policy_version 94850 (0.0007) -[2023-10-16 06:32:27,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 194576384. Throughput: 0: 1812.8, 1: 1782.9. Samples: 48650690. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:32:27,351][03835] Avg episode reward: [(0, '8.500'), (1, '9.310')] -[2023-10-16 06:32:27,502][05219] Updated weights for policy 1, policy_version 94860 (0.0008) -[2023-10-16 06:32:27,873][05219] Updated weights for policy 1, policy_version 94870 (0.0008) -[2023-10-16 06:32:28,240][05219] Updated weights for policy 1, policy_version 94880 (0.0008) -[2023-10-16 06:32:30,036][05218] Updated weights for policy 0, policy_version 95172 (0.0008) -[2023-10-16 06:32:30,419][05218] Updated weights for policy 0, policy_version 95182 (0.0007) -[2023-10-16 06:32:30,797][05218] Updated weights for policy 0, policy_version 95192 (0.0009) -[2023-10-16 06:32:31,933][05219] Updated weights for policy 1, policy_version 94890 (0.0009) -[2023-10-16 06:32:32,296][05219] Updated weights for policy 1, policy_version 94900 (0.0011) -[2023-10-16 06:32:32,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 194641920. Throughput: 0: 1804.4, 1: 1795.2. Samples: 48671868. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:32:32,351][03835] Avg episode reward: [(0, '7.390'), (1, '7.990')] -[2023-10-16 06:32:32,650][05219] Updated weights for policy 1, policy_version 94910 (0.0011) -[2023-10-16 06:32:34,423][05218] Updated weights for policy 0, policy_version 95202 (0.0010) -[2023-10-16 06:32:34,817][05218] Updated weights for policy 0, policy_version 95212 (0.0008) -[2023-10-16 06:32:35,198][05218] Updated weights for policy 0, policy_version 95222 (0.0007) -[2023-10-16 06:32:35,579][05218] Updated weights for policy 0, policy_version 95232 (0.0011) -[2023-10-16 06:32:36,468][05219] Updated weights for policy 1, policy_version 94920 (0.0010) -[2023-10-16 06:32:36,833][05219] Updated weights for policy 1, policy_version 94930 (0.0008) -[2023-10-16 06:32:37,200][05219] Updated weights for policy 1, policy_version 94940 (0.0007) -[2023-10-16 06:32:37,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 194740224. Throughput: 0: 1803.4, 1: 1792.7. Samples: 48693256. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:32:37,351][03835] Avg episode reward: [(0, '7.110'), (1, '7.740')] -[2023-10-16 06:32:39,262][05218] Updated weights for policy 0, policy_version 95242 (0.0011) -[2023-10-16 06:32:39,642][05218] Updated weights for policy 0, policy_version 95252 (0.0009) -[2023-10-16 06:32:40,014][05218] Updated weights for policy 0, policy_version 95262 (0.0010) -[2023-10-16 06:32:40,829][05219] Updated weights for policy 1, policy_version 94950 (0.0008) -[2023-10-16 06:32:41,191][05219] Updated weights for policy 1, policy_version 94960 (0.0009) -[2023-10-16 06:32:41,557][05219] Updated weights for policy 1, policy_version 94970 (0.0010) -[2023-10-16 06:32:42,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 194805760. Throughput: 0: 1805.7, 1: 1794.5. Samples: 48704130. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:32:42,351][03835] Avg episode reward: [(0, '8.090'), (1, '8.540')] -[2023-10-16 06:32:43,709][05218] Updated weights for policy 0, policy_version 95272 (0.0009) -[2023-10-16 06:32:44,084][05218] Updated weights for policy 0, policy_version 95282 (0.0010) -[2023-10-16 06:32:44,456][05218] Updated weights for policy 0, policy_version 95292 (0.0009) -[2023-10-16 06:32:45,298][05219] Updated weights for policy 1, policy_version 94980 (0.0009) -[2023-10-16 06:32:45,668][05219] Updated weights for policy 1, policy_version 94990 (0.0010) -[2023-10-16 06:32:46,038][05219] Updated weights for policy 1, policy_version 95000 (0.0008) -[2023-10-16 06:32:47,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 194871296. Throughput: 0: 1809.7, 1: 1787.6. Samples: 48725512. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:32:47,351][03835] Avg episode reward: [(0, '7.210'), (1, '8.750')] -[2023-10-16 06:32:48,071][05218] Updated weights for policy 0, policy_version 95302 (0.0007) -[2023-10-16 06:32:48,457][05218] Updated weights for policy 0, policy_version 95312 (0.0007) -[2023-10-16 06:32:48,835][05218] Updated weights for policy 0, policy_version 95322 (0.0007) -[2023-10-16 06:32:49,875][05219] Updated weights for policy 1, policy_version 95010 (0.0009) -[2023-10-16 06:32:50,235][05219] Updated weights for policy 1, policy_version 95020 (0.0007) -[2023-10-16 06:32:50,604][05219] Updated weights for policy 1, policy_version 95030 (0.0008) -[2023-10-16 06:32:50,965][05219] Updated weights for policy 1, policy_version 95040 (0.0009) -[2023-10-16 06:32:52,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 194936832. Throughput: 0: 1807.5, 1: 1785.9. Samples: 48747804. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:32:52,351][03835] Avg episode reward: [(0, '7.280'), (1, '8.220')] -[2023-10-16 06:32:52,630][05218] Updated weights for policy 0, policy_version 95332 (0.0008) -[2023-10-16 06:32:53,009][05218] Updated weights for policy 0, policy_version 95342 (0.0008) -[2023-10-16 06:32:53,387][05218] Updated weights for policy 0, policy_version 95352 (0.0009) -[2023-10-16 06:32:54,694][05219] Updated weights for policy 1, policy_version 95050 (0.0009) -[2023-10-16 06:32:55,059][05219] Updated weights for policy 1, policy_version 95060 (0.0008) -[2023-10-16 06:32:55,417][05219] Updated weights for policy 1, policy_version 95070 (0.0011) -[2023-10-16 06:32:57,040][05218] Updated weights for policy 0, policy_version 95362 (0.0009) -[2023-10-16 06:32:57,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 195002368. Throughput: 0: 1809.0, 1: 1798.3. Samples: 48758246. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:32:57,351][03835] Avg episode reward: [(0, '7.230'), (1, '8.390')] -[2023-10-16 06:32:57,410][05218] Updated weights for policy 0, policy_version 95372 (0.0010) -[2023-10-16 06:32:57,784][05218] Updated weights for policy 0, policy_version 95382 (0.0011) -[2023-10-16 06:32:58,165][05218] Updated weights for policy 0, policy_version 95392 (0.0011) -[2023-10-16 06:32:59,260][05219] Updated weights for policy 1, policy_version 95080 (0.0008) -[2023-10-16 06:32:59,630][05219] Updated weights for policy 1, policy_version 95090 (0.0008) -[2023-10-16 06:33:00,001][05219] Updated weights for policy 1, policy_version 95100 (0.0008) -[2023-10-16 06:33:01,846][05218] Updated weights for policy 0, policy_version 95402 (0.0008) -[2023-10-16 06:33:02,207][05218] Updated weights for policy 0, policy_version 95412 (0.0010) -[2023-10-16 06:33:02,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 195067904. Throughput: 0: 1816.6, 1: 1779.1. Samples: 48779882. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:33:02,351][03835] Avg episode reward: [(0, '8.650'), (1, '8.330')] -[2023-10-16 06:33:02,588][05218] Updated weights for policy 0, policy_version 95422 (0.0007) -[2023-10-16 06:33:03,798][05219] Updated weights for policy 1, policy_version 95110 (0.0009) -[2023-10-16 06:33:04,161][05219] Updated weights for policy 1, policy_version 95120 (0.0010) -[2023-10-16 06:33:04,541][05219] Updated weights for policy 1, policy_version 95130 (0.0007) -[2023-10-16 06:33:06,317][05218] Updated weights for policy 0, policy_version 95432 (0.0008) -[2023-10-16 06:33:06,688][05218] Updated weights for policy 0, policy_version 95442 (0.0009) -[2023-10-16 06:33:07,072][05218] Updated weights for policy 0, policy_version 95452 (0.0009) -[2023-10-16 06:33:07,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 195166208. Throughput: 0: 1810.9, 1: 1778.8. Samples: 48800806. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:33:07,351][03835] Avg episode reward: [(0, '7.540'), (1, '8.070')] -[2023-10-16 06:33:08,379][05219] Updated weights for policy 1, policy_version 95140 (0.0007) -[2023-10-16 06:33:08,750][05219] Updated weights for policy 1, policy_version 95150 (0.0009) -[2023-10-16 06:33:09,120][05219] Updated weights for policy 1, policy_version 95160 (0.0011) -[2023-10-16 06:33:10,707][05218] Updated weights for policy 0, policy_version 95462 (0.0009) -[2023-10-16 06:33:11,073][05218] Updated weights for policy 0, policy_version 95472 (0.0011) -[2023-10-16 06:33:11,456][05218] Updated weights for policy 0, policy_version 95482 (0.0008) -[2023-10-16 06:33:12,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 195231744. Throughput: 0: 1809.7, 1: 1779.8. Samples: 48812218. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:33:12,351][03835] Avg episode reward: [(0, '7.670'), (1, '8.660')] -[2023-10-16 06:33:12,893][05219] Updated weights for policy 1, policy_version 95170 (0.0009) -[2023-10-16 06:33:13,258][05219] Updated weights for policy 1, policy_version 95180 (0.0010) -[2023-10-16 06:33:13,626][05219] Updated weights for policy 1, policy_version 95190 (0.0008) -[2023-10-16 06:33:13,989][05219] Updated weights for policy 1, policy_version 95200 (0.0007) -[2023-10-16 06:33:15,199][05218] Updated weights for policy 0, policy_version 95492 (0.0009) -[2023-10-16 06:33:15,578][05218] Updated weights for policy 0, policy_version 95502 (0.0010) -[2023-10-16 06:33:15,952][05218] Updated weights for policy 0, policy_version 95512 (0.0010) -[2023-10-16 06:33:17,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 195297280. Throughput: 0: 1803.9, 1: 1780.4. Samples: 48833162. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:33:17,351][03835] Avg episode reward: [(0, '8.560'), (1, '8.360')] -[2023-10-16 06:33:17,716][05219] Updated weights for policy 1, policy_version 95210 (0.0008) -[2023-10-16 06:33:18,084][05219] Updated weights for policy 1, policy_version 95220 (0.0007) -[2023-10-16 06:33:18,444][05219] Updated weights for policy 1, policy_version 95230 (0.0007) -[2023-10-16 06:33:19,647][05218] Updated weights for policy 0, policy_version 95522 (0.0008) -[2023-10-16 06:33:20,031][05218] Updated weights for policy 0, policy_version 95532 (0.0009) -[2023-10-16 06:33:20,405][05218] Updated weights for policy 0, policy_version 95542 (0.0010) -[2023-10-16 06:33:20,768][05218] Updated weights for policy 0, policy_version 95552 (0.0011) -[2023-10-16 06:33:22,207][05219] Updated weights for policy 1, policy_version 95240 (0.0008) -[2023-10-16 06:33:22,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 195362816. Throughput: 0: 1801.9, 1: 1799.2. Samples: 48855308. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:33:22,351][03835] Avg episode reward: [(0, '7.350'), (1, '9.190')] -[2023-10-16 06:33:22,568][05219] Updated weights for policy 1, policy_version 95250 (0.0008) -[2023-10-16 06:33:22,932][05219] Updated weights for policy 1, policy_version 95260 (0.0009) -[2023-10-16 06:33:24,568][05218] Updated weights for policy 0, policy_version 95562 (0.0007) -[2023-10-16 06:33:24,950][05218] Updated weights for policy 0, policy_version 95572 (0.0007) -[2023-10-16 06:33:25,333][05218] Updated weights for policy 0, policy_version 95582 (0.0007) -[2023-10-16 06:33:26,868][05219] Updated weights for policy 1, policy_version 95270 (0.0008) -[2023-10-16 06:33:27,239][05219] Updated weights for policy 1, policy_version 95280 (0.0009) -[2023-10-16 06:33:27,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 195428352. Throughput: 0: 1804.2, 1: 1776.7. Samples: 48865270. Policy #0 lag: (min: 2.0, avg: 9.6, max: 34.0) -[2023-10-16 06:33:27,351][03835] Avg episode reward: [(0, '7.320'), (1, '8.430')] -[2023-10-16 06:33:27,597][05219] Updated weights for policy 1, policy_version 95290 (0.0008) -[2023-10-16 06:33:29,056][05218] Updated weights for policy 0, policy_version 95592 (0.0010) -[2023-10-16 06:33:29,421][05218] Updated weights for policy 0, policy_version 95602 (0.0008) -[2023-10-16 06:33:29,804][05218] Updated weights for policy 0, policy_version 95612 (0.0009) -[2023-10-16 06:33:31,263][05219] Updated weights for policy 1, policy_version 95300 (0.0008) -[2023-10-16 06:33:31,631][05219] Updated weights for policy 1, policy_version 95310 (0.0009) -[2023-10-16 06:33:31,982][05219] Updated weights for policy 1, policy_version 95320 (0.0009) -[2023-10-16 06:33:32,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 195526656. Throughput: 0: 1796.5, 1: 1803.9. Samples: 48887530. Policy #0 lag: (min: 2.0, avg: 9.6, max: 34.0) -[2023-10-16 06:33:32,352][03835] Avg episode reward: [(0, '7.900'), (1, '7.860')] -[2023-10-16 06:33:33,612][05218] Updated weights for policy 0, policy_version 95622 (0.0009) -[2023-10-16 06:33:33,988][05218] Updated weights for policy 0, policy_version 95632 (0.0007) -[2023-10-16 06:33:34,368][05218] Updated weights for policy 0, policy_version 95642 (0.0007) -[2023-10-16 06:33:35,788][05219] Updated weights for policy 1, policy_version 95330 (0.0010) -[2023-10-16 06:33:36,155][05219] Updated weights for policy 1, policy_version 95340 (0.0008) -[2023-10-16 06:33:36,523][05219] Updated weights for policy 1, policy_version 95350 (0.0008) -[2023-10-16 06:33:36,890][05219] Updated weights for policy 1, policy_version 95360 (0.0007) -[2023-10-16 06:33:37,351][03835] Fps is (10 sec: 16383.5, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 195592192. Throughput: 0: 1803.2, 1: 1779.5. Samples: 48909026. Policy #0 lag: (min: 2.0, avg: 9.6, max: 34.0) -[2023-10-16 06:33:37,352][03835] Avg episode reward: [(0, '6.860'), (1, '9.290')] -[2023-10-16 06:33:37,363][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000095648_97943552.pth... -[2023-10-16 06:33:37,363][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000095360_97648640.pth... -[2023-10-16 06:33:37,392][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000093984_96239616.pth -[2023-10-16 06:33:37,403][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000093696_95944704.pth -[2023-10-16 06:33:37,960][05218] Updated weights for policy 0, policy_version 95652 (0.0008) -[2023-10-16 06:33:38,332][05218] Updated weights for policy 0, policy_version 95662 (0.0007) -[2023-10-16 06:33:38,714][05218] Updated weights for policy 0, policy_version 95672 (0.0009) -[2023-10-16 06:33:40,494][05219] Updated weights for policy 1, policy_version 95370 (0.0008) -[2023-10-16 06:33:40,843][05219] Updated weights for policy 1, policy_version 95380 (0.0009) -[2023-10-16 06:33:41,219][05219] Updated weights for policy 1, policy_version 95390 (0.0008) -[2023-10-16 06:33:42,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 195657728. Throughput: 0: 1799.7, 1: 1797.7. Samples: 48920130. Policy #0 lag: (min: 2.0, avg: 9.6, max: 34.0) -[2023-10-16 06:33:42,351][03835] Avg episode reward: [(0, '6.780'), (1, '8.310')] -[2023-10-16 06:33:42,588][05218] Updated weights for policy 0, policy_version 95682 (0.0009) -[2023-10-16 06:33:42,962][05218] Updated weights for policy 0, policy_version 95692 (0.0007) -[2023-10-16 06:33:43,341][05218] Updated weights for policy 0, policy_version 95702 (0.0008) -[2023-10-16 06:33:43,714][05218] Updated weights for policy 0, policy_version 95712 (0.0011) -[2023-10-16 06:33:45,038][05219] Updated weights for policy 1, policy_version 95400 (0.0009) -[2023-10-16 06:33:45,411][05219] Updated weights for policy 1, policy_version 95410 (0.0010) -[2023-10-16 06:33:45,772][05219] Updated weights for policy 1, policy_version 95420 (0.0009) -[2023-10-16 06:33:47,238][05218] Updated weights for policy 0, policy_version 95722 (0.0008) -[2023-10-16 06:33:47,350][03835] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 195723264. Throughput: 0: 1807.2, 1: 1781.4. Samples: 48941366. Policy #0 lag: (min: 2.0, avg: 9.6, max: 34.0) -[2023-10-16 06:33:47,351][03835] Avg episode reward: [(0, '7.740'), (1, '8.280')] -[2023-10-16 06:33:47,609][05218] Updated weights for policy 0, policy_version 95732 (0.0007) -[2023-10-16 06:33:47,981][05218] Updated weights for policy 0, policy_version 95742 (0.0008) -[2023-10-16 06:33:49,668][05219] Updated weights for policy 1, policy_version 95430 (0.0009) -[2023-10-16 06:33:50,035][05219] Updated weights for policy 1, policy_version 95440 (0.0008) -[2023-10-16 06:33:50,397][05219] Updated weights for policy 1, policy_version 95450 (0.0007) -[2023-10-16 06:33:51,558][05218] Updated weights for policy 0, policy_version 95752 (0.0010) -[2023-10-16 06:33:51,931][05218] Updated weights for policy 0, policy_version 95762 (0.0011) -[2023-10-16 06:33:52,311][05218] Updated weights for policy 0, policy_version 95772 (0.0009) -[2023-10-16 06:33:52,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 195788800. Throughput: 0: 1816.8, 1: 1779.6. Samples: 48962646. Policy #0 lag: (min: 2.0, avg: 9.6, max: 34.0) -[2023-10-16 06:33:52,351][03835] Avg episode reward: [(0, '7.640'), (1, '8.510')] -[2023-10-16 06:33:54,121][05219] Updated weights for policy 1, policy_version 95460 (0.0009) -[2023-10-16 06:33:54,483][05219] Updated weights for policy 1, policy_version 95470 (0.0007) -[2023-10-16 06:33:54,859][05219] Updated weights for policy 1, policy_version 95480 (0.0007) -[2023-10-16 06:33:55,957][05218] Updated weights for policy 0, policy_version 95782 (0.0011) -[2023-10-16 06:33:56,338][05218] Updated weights for policy 0, policy_version 95792 (0.0007) -[2023-10-16 06:33:56,709][05218] Updated weights for policy 0, policy_version 95802 (0.0007) -[2023-10-16 06:33:57,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 195887104. Throughput: 0: 1811.7, 1: 1781.6. Samples: 48973920. Policy #0 lag: (min: 2.0, avg: 9.6, max: 34.0) -[2023-10-16 06:33:57,351][03835] Avg episode reward: [(0, '8.110'), (1, '9.000')] -[2023-10-16 06:33:58,581][05219] Updated weights for policy 1, policy_version 95490 (0.0007) -[2023-10-16 06:33:58,957][05219] Updated weights for policy 1, policy_version 95500 (0.0009) -[2023-10-16 06:33:59,316][05219] Updated weights for policy 1, policy_version 95510 (0.0008) -[2023-10-16 06:33:59,683][05219] Updated weights for policy 1, policy_version 95520 (0.0008) -[2023-10-16 06:34:00,348][05218] Updated weights for policy 0, policy_version 95812 (0.0009) -[2023-10-16 06:34:00,720][05218] Updated weights for policy 0, policy_version 95822 (0.0010) -[2023-10-16 06:34:01,095][05218] Updated weights for policy 0, policy_version 95832 (0.0010) -[2023-10-16 06:34:02,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 195952640. Throughput: 0: 1815.9, 1: 1780.1. Samples: 48994982. Policy #0 lag: (min: 2.0, avg: 9.6, max: 34.0) -[2023-10-16 06:34:02,351][03835] Avg episode reward: [(0, '7.380'), (1, '7.600')] -[2023-10-16 06:34:03,535][05219] Updated weights for policy 1, policy_version 95530 (0.0007) -[2023-10-16 06:34:03,900][05219] Updated weights for policy 1, policy_version 95540 (0.0009) -[2023-10-16 06:34:04,265][05219] Updated weights for policy 1, policy_version 95550 (0.0009) -[2023-10-16 06:34:04,793][05218] Updated weights for policy 0, policy_version 95842 (0.0009) -[2023-10-16 06:34:05,196][05218] Updated weights for policy 0, policy_version 95852 (0.0010) -[2023-10-16 06:34:05,569][05218] Updated weights for policy 0, policy_version 95862 (0.0009) -[2023-10-16 06:34:05,956][05218] Updated weights for policy 0, policy_version 95872 (0.0009) -[2023-10-16 06:34:07,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 196018176. Throughput: 0: 1814.5, 1: 1790.8. Samples: 49017546. Policy #0 lag: (min: 2.0, avg: 9.6, max: 34.0) -[2023-10-16 06:34:07,351][03835] Avg episode reward: [(0, '8.060'), (1, '7.630')] -[2023-10-16 06:34:08,060][05219] Updated weights for policy 1, policy_version 95560 (0.0008) -[2023-10-16 06:34:08,431][05219] Updated weights for policy 1, policy_version 95570 (0.0008) -[2023-10-16 06:34:08,792][05219] Updated weights for policy 1, policy_version 95580 (0.0008) -[2023-10-16 06:34:09,586][05218] Updated weights for policy 0, policy_version 95882 (0.0008) -[2023-10-16 06:34:09,949][05218] Updated weights for policy 0, policy_version 95892 (0.0009) -[2023-10-16 06:34:10,326][05218] Updated weights for policy 0, policy_version 95902 (0.0008) -[2023-10-16 06:34:12,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 196083712. Throughput: 0: 1820.4, 1: 1786.6. Samples: 49027586. Policy #0 lag: (min: 2.0, avg: 9.6, max: 34.0) -[2023-10-16 06:34:12,351][03835] Avg episode reward: [(0, '8.340'), (1, '8.540')] -[2023-10-16 06:34:12,563][05219] Updated weights for policy 1, policy_version 95590 (0.0010) -[2023-10-16 06:34:12,919][05219] Updated weights for policy 1, policy_version 95600 (0.0009) -[2023-10-16 06:34:13,284][05219] Updated weights for policy 1, policy_version 95610 (0.0008) -[2023-10-16 06:34:14,104][05218] Updated weights for policy 0, policy_version 95912 (0.0007) -[2023-10-16 06:34:14,479][05218] Updated weights for policy 0, policy_version 95922 (0.0007) -[2023-10-16 06:34:14,856][05218] Updated weights for policy 0, policy_version 95932 (0.0007) -[2023-10-16 06:34:17,000][05219] Updated weights for policy 1, policy_version 95620 (0.0009) -[2023-10-16 06:34:17,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 196149248. Throughput: 0: 1818.1, 1: 1788.2. Samples: 49049814. Policy #0 lag: (min: 2.0, avg: 9.6, max: 34.0) -[2023-10-16 06:34:17,351][03835] Avg episode reward: [(0, '7.190'), (1, '7.450')] -[2023-10-16 06:34:17,363][05219] Updated weights for policy 1, policy_version 95630 (0.0009) -[2023-10-16 06:34:17,744][05219] Updated weights for policy 1, policy_version 95640 (0.0009) -[2023-10-16 06:34:18,626][05218] Updated weights for policy 0, policy_version 95942 (0.0007) -[2023-10-16 06:34:19,008][05218] Updated weights for policy 0, policy_version 95952 (0.0009) -[2023-10-16 06:34:19,376][05218] Updated weights for policy 0, policy_version 95962 (0.0007) -[2023-10-16 06:34:21,459][05219] Updated weights for policy 1, policy_version 95650 (0.0008) -[2023-10-16 06:34:21,819][05219] Updated weights for policy 1, policy_version 95660 (0.0007) -[2023-10-16 06:34:22,194][05219] Updated weights for policy 1, policy_version 95670 (0.0008) -[2023-10-16 06:34:22,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 196214784. Throughput: 0: 1816.1, 1: 1801.0. Samples: 49071794. Policy #0 lag: (min: 2.0, avg: 9.6, max: 34.0) -[2023-10-16 06:34:22,351][03835] Avg episode reward: [(0, '8.140'), (1, '8.010')] -[2023-10-16 06:34:22,556][05219] Updated weights for policy 1, policy_version 95680 (0.0009) -[2023-10-16 06:34:23,054][05218] Updated weights for policy 0, policy_version 95972 (0.0007) -[2023-10-16 06:34:23,436][05218] Updated weights for policy 0, policy_version 95982 (0.0010) -[2023-10-16 06:34:23,804][05218] Updated weights for policy 0, policy_version 95992 (0.0008) -[2023-10-16 06:34:26,366][05219] Updated weights for policy 1, policy_version 95690 (0.0010) -[2023-10-16 06:34:26,725][05219] Updated weights for policy 1, policy_version 95700 (0.0011) -[2023-10-16 06:34:27,095][05219] Updated weights for policy 1, policy_version 95710 (0.0008) -[2023-10-16 06:34:27,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 196313088. Throughput: 0: 1814.1, 1: 1785.4. Samples: 49082110. Policy #0 lag: (min: 25.0, avg: 36.4, max: 57.0) -[2023-10-16 06:34:27,351][03835] Avg episode reward: [(0, '7.570'), (1, '8.820')] -[2023-10-16 06:34:27,531][05218] Updated weights for policy 0, policy_version 96002 (0.0009) -[2023-10-16 06:34:27,910][05218] Updated weights for policy 0, policy_version 96012 (0.0009) -[2023-10-16 06:34:28,287][05218] Updated weights for policy 0, policy_version 96022 (0.0007) -[2023-10-16 06:34:28,659][05218] Updated weights for policy 0, policy_version 96032 (0.0007) -[2023-10-16 06:34:30,873][05219] Updated weights for policy 1, policy_version 95720 (0.0009) -[2023-10-16 06:34:31,240][05219] Updated weights for policy 1, policy_version 95730 (0.0008) -[2023-10-16 06:34:31,599][05219] Updated weights for policy 1, policy_version 95740 (0.0007) -[2023-10-16 06:34:32,350][03835] Fps is (10 sec: 16384.6, 60 sec: 14199.6, 300 sec: 14440.2). Total num frames: 196378624. Throughput: 0: 1805.8, 1: 1806.2. Samples: 49103906. Policy #0 lag: (min: 25.0, avg: 36.4, max: 57.0) -[2023-10-16 06:34:32,351][03835] Avg episode reward: [(0, '6.780'), (1, '8.150')] -[2023-10-16 06:34:32,476][05218] Updated weights for policy 0, policy_version 96042 (0.0007) -[2023-10-16 06:34:32,847][05218] Updated weights for policy 0, policy_version 96052 (0.0008) -[2023-10-16 06:34:33,221][05218] Updated weights for policy 0, policy_version 96062 (0.0007) -[2023-10-16 06:34:35,380][05219] Updated weights for policy 1, policy_version 95750 (0.0009) -[2023-10-16 06:34:35,751][05219] Updated weights for policy 1, policy_version 95760 (0.0010) -[2023-10-16 06:34:36,113][05219] Updated weights for policy 1, policy_version 95770 (0.0009) -[2023-10-16 06:34:36,799][05218] Updated weights for policy 0, policy_version 96072 (0.0008) -[2023-10-16 06:34:37,174][05218] Updated weights for policy 0, policy_version 96082 (0.0009) -[2023-10-16 06:34:37,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 196444160. Throughput: 0: 1810.4, 1: 1788.0. Samples: 49124570. Policy #0 lag: (min: 25.0, avg: 36.4, max: 57.0) -[2023-10-16 06:34:37,351][03835] Avg episode reward: [(0, '7.510'), (1, '7.980')] -[2023-10-16 06:34:37,551][05218] Updated weights for policy 0, policy_version 96092 (0.0007) -[2023-10-16 06:34:39,746][05219] Updated weights for policy 1, policy_version 95780 (0.0009) -[2023-10-16 06:34:40,108][05219] Updated weights for policy 1, policy_version 95790 (0.0008) -[2023-10-16 06:34:40,468][05219] Updated weights for policy 1, policy_version 95800 (0.0007) -[2023-10-16 06:34:41,347][05218] Updated weights for policy 0, policy_version 96102 (0.0009) -[2023-10-16 06:34:41,721][05218] Updated weights for policy 0, policy_version 96112 (0.0010) -[2023-10-16 06:34:42,095][05218] Updated weights for policy 0, policy_version 96122 (0.0010) -[2023-10-16 06:34:42,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 196542464. Throughput: 0: 1800.0, 1: 1807.2. Samples: 49136242. Policy #0 lag: (min: 25.0, avg: 36.4, max: 57.0) -[2023-10-16 06:34:42,351][03835] Avg episode reward: [(0, '8.050'), (1, '7.510')] -[2023-10-16 06:34:44,250][05219] Updated weights for policy 1, policy_version 95810 (0.0010) -[2023-10-16 06:34:44,619][05219] Updated weights for policy 1, policy_version 95820 (0.0010) -[2023-10-16 06:34:44,984][05219] Updated weights for policy 1, policy_version 95830 (0.0007) -[2023-10-16 06:34:45,354][05219] Updated weights for policy 1, policy_version 95840 (0.0009) -[2023-10-16 06:34:45,845][05218] Updated weights for policy 0, policy_version 96132 (0.0008) -[2023-10-16 06:34:46,220][05218] Updated weights for policy 0, policy_version 96142 (0.0007) -[2023-10-16 06:34:46,591][05218] Updated weights for policy 0, policy_version 96152 (0.0008) -[2023-10-16 06:34:47,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 196608000. Throughput: 0: 1808.2, 1: 1786.5. Samples: 49156744. Policy #0 lag: (min: 25.0, avg: 36.4, max: 57.0) -[2023-10-16 06:34:47,351][03835] Avg episode reward: [(0, '7.250'), (1, '8.140')] -[2023-10-16 06:34:49,219][05219] Updated weights for policy 1, policy_version 95850 (0.0011) -[2023-10-16 06:34:49,579][05219] Updated weights for policy 1, policy_version 95860 (0.0011) -[2023-10-16 06:34:49,945][05219] Updated weights for policy 1, policy_version 95870 (0.0010) -[2023-10-16 06:34:50,403][05218] Updated weights for policy 0, policy_version 96162 (0.0008) -[2023-10-16 06:34:50,792][05218] Updated weights for policy 0, policy_version 96172 (0.0008) -[2023-10-16 06:34:51,167][05218] Updated weights for policy 0, policy_version 96182 (0.0008) -[2023-10-16 06:34:51,532][05218] Updated weights for policy 0, policy_version 96192 (0.0008) -[2023-10-16 06:34:52,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 196673536. Throughput: 0: 1791.8, 1: 1783.5. Samples: 49178432. Policy #0 lag: (min: 25.0, avg: 36.4, max: 57.0) -[2023-10-16 06:34:52,351][03835] Avg episode reward: [(0, '8.310'), (1, '8.430')] -[2023-10-16 06:34:53,832][05219] Updated weights for policy 1, policy_version 95880 (0.0009) -[2023-10-16 06:34:54,196][05219] Updated weights for policy 1, policy_version 95890 (0.0010) -[2023-10-16 06:34:54,560][05219] Updated weights for policy 1, policy_version 95900 (0.0008) -[2023-10-16 06:34:55,243][05218] Updated weights for policy 0, policy_version 96202 (0.0007) -[2023-10-16 06:34:55,615][05218] Updated weights for policy 0, policy_version 96212 (0.0010) -[2023-10-16 06:34:55,988][05218] Updated weights for policy 0, policy_version 96222 (0.0009) -[2023-10-16 06:34:57,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 196739072. Throughput: 0: 1809.6, 1: 1780.0. Samples: 49189116. Policy #0 lag: (min: 25.0, avg: 36.4, max: 57.0) -[2023-10-16 06:34:57,351][03835] Avg episode reward: [(0, '7.660'), (1, '9.370')] -[2023-10-16 06:34:58,320][05219] Updated weights for policy 1, policy_version 95910 (0.0008) -[2023-10-16 06:34:58,697][05219] Updated weights for policy 1, policy_version 95920 (0.0008) -[2023-10-16 06:34:59,061][05219] Updated weights for policy 1, policy_version 95930 (0.0009) -[2023-10-16 06:34:59,714][05218] Updated weights for policy 0, policy_version 96232 (0.0010) -[2023-10-16 06:35:00,085][05218] Updated weights for policy 0, policy_version 96242 (0.0008) -[2023-10-16 06:35:00,448][05218] Updated weights for policy 0, policy_version 96252 (0.0011) -[2023-10-16 06:35:02,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 196804608. Throughput: 0: 1794.2, 1: 1781.4. Samples: 49210716. Policy #0 lag: (min: 25.0, avg: 36.4, max: 57.0) -[2023-10-16 06:35:02,351][03835] Avg episode reward: [(0, '7.530'), (1, '8.370')] -[2023-10-16 06:35:02,691][05219] Updated weights for policy 1, policy_version 95940 (0.0009) -[2023-10-16 06:35:03,056][05219] Updated weights for policy 1, policy_version 95950 (0.0009) -[2023-10-16 06:35:03,425][05219] Updated weights for policy 1, policy_version 95960 (0.0008) -[2023-10-16 06:35:04,252][05218] Updated weights for policy 0, policy_version 96262 (0.0009) -[2023-10-16 06:35:04,620][05218] Updated weights for policy 0, policy_version 96272 (0.0009) -[2023-10-16 06:35:04,998][05218] Updated weights for policy 0, policy_version 96282 (0.0010) -[2023-10-16 06:35:07,206][05219] Updated weights for policy 1, policy_version 95970 (0.0009) -[2023-10-16 06:35:07,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 196870144. Throughput: 0: 1785.1, 1: 1800.6. Samples: 49233150. Policy #0 lag: (min: 25.0, avg: 36.4, max: 57.0) -[2023-10-16 06:35:07,351][03835] Avg episode reward: [(0, '8.550'), (1, '9.690')] -[2023-10-16 06:35:07,568][05219] Updated weights for policy 1, policy_version 95980 (0.0008) -[2023-10-16 06:35:07,937][05219] Updated weights for policy 1, policy_version 95990 (0.0008) -[2023-10-16 06:35:08,291][05219] Updated weights for policy 1, policy_version 96000 (0.0007) -[2023-10-16 06:35:08,675][05218] Updated weights for policy 0, policy_version 96292 (0.0008) -[2023-10-16 06:35:09,044][05218] Updated weights for policy 0, policy_version 96302 (0.0007) -[2023-10-16 06:35:09,422][05218] Updated weights for policy 0, policy_version 96312 (0.0009) -[2023-10-16 06:35:12,138][05219] Updated weights for policy 1, policy_version 96010 (0.0007) -[2023-10-16 06:35:12,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 196935680. Throughput: 0: 1791.7, 1: 1787.4. Samples: 49243170. Policy #0 lag: (min: 25.0, avg: 36.4, max: 57.0) -[2023-10-16 06:35:12,351][03835] Avg episode reward: [(0, '7.890'), (1, '8.820')] -[2023-10-16 06:35:12,507][05219] Updated weights for policy 1, policy_version 96020 (0.0007) -[2023-10-16 06:35:12,867][05219] Updated weights for policy 1, policy_version 96030 (0.0007) -[2023-10-16 06:35:13,206][05218] Updated weights for policy 0, policy_version 96322 (0.0010) -[2023-10-16 06:35:13,579][05218] Updated weights for policy 0, policy_version 96332 (0.0008) -[2023-10-16 06:35:13,965][05218] Updated weights for policy 0, policy_version 96342 (0.0010) -[2023-10-16 06:35:14,333][05218] Updated weights for policy 0, policy_version 96352 (0.0009) -[2023-10-16 06:35:16,721][05219] Updated weights for policy 1, policy_version 96040 (0.0007) -[2023-10-16 06:35:17,082][05219] Updated weights for policy 1, policy_version 96050 (0.0009) -[2023-10-16 06:35:17,351][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 197001216. Throughput: 0: 1791.9, 1: 1795.0. Samples: 49265320. Policy #0 lag: (min: 25.0, avg: 36.4, max: 57.0) -[2023-10-16 06:35:17,352][03835] Avg episode reward: [(0, '7.980'), (1, '8.000')] -[2023-10-16 06:35:17,450][05219] Updated weights for policy 1, policy_version 96060 (0.0007) -[2023-10-16 06:35:18,134][05218] Updated weights for policy 0, policy_version 96362 (0.0009) -[2023-10-16 06:35:18,518][05218] Updated weights for policy 0, policy_version 96372 (0.0009) -[2023-10-16 06:35:18,891][05218] Updated weights for policy 0, policy_version 96382 (0.0007) -[2023-10-16 06:35:21,227][05219] Updated weights for policy 1, policy_version 96070 (0.0009) -[2023-10-16 06:35:21,603][05219] Updated weights for policy 1, policy_version 96080 (0.0007) -[2023-10-16 06:35:21,971][05219] Updated weights for policy 1, policy_version 96090 (0.0009) -[2023-10-16 06:35:22,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 197099520. Throughput: 0: 1811.4, 1: 1787.6. Samples: 49286528. Policy #0 lag: (min: 25.0, avg: 36.4, max: 57.0) -[2023-10-16 06:35:22,351][03835] Avg episode reward: [(0, '7.810'), (1, '9.270')] -[2023-10-16 06:35:22,609][05218] Updated weights for policy 0, policy_version 96392 (0.0009) -[2023-10-16 06:35:22,986][05218] Updated weights for policy 0, policy_version 96402 (0.0008) -[2023-10-16 06:35:23,369][05218] Updated weights for policy 0, policy_version 96412 (0.0010) -[2023-10-16 06:35:25,700][05219] Updated weights for policy 1, policy_version 96100 (0.0009) -[2023-10-16 06:35:26,064][05219] Updated weights for policy 1, policy_version 96110 (0.0008) -[2023-10-16 06:35:26,434][05219] Updated weights for policy 1, policy_version 96120 (0.0008) -[2023-10-16 06:35:27,169][05218] Updated weights for policy 0, policy_version 96422 (0.0008) -[2023-10-16 06:35:27,350][03835] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 197165056. Throughput: 0: 1790.7, 1: 1792.2. Samples: 49297474. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-16 06:35:27,351][03835] Avg episode reward: [(0, '8.020'), (1, '9.820')] -[2023-10-16 06:35:27,353][04891] Saving new best policy, reward=9.820! -[2023-10-16 06:35:27,541][05218] Updated weights for policy 0, policy_version 96432 (0.0009) -[2023-10-16 06:35:27,919][05218] Updated weights for policy 0, policy_version 96442 (0.0007) -[2023-10-16 06:35:30,069][05219] Updated weights for policy 1, policy_version 96130 (0.0009) -[2023-10-16 06:35:30,437][05219] Updated weights for policy 1, policy_version 96140 (0.0008) -[2023-10-16 06:35:30,792][05219] Updated weights for policy 1, policy_version 96150 (0.0011) -[2023-10-16 06:35:31,155][05219] Updated weights for policy 1, policy_version 96160 (0.0011) -[2023-10-16 06:35:31,544][05218] Updated weights for policy 0, policy_version 96452 (0.0007) -[2023-10-16 06:35:31,918][05218] Updated weights for policy 0, policy_version 96462 (0.0007) -[2023-10-16 06:35:32,308][05218] Updated weights for policy 0, policy_version 96472 (0.0007) -[2023-10-16 06:35:32,351][03835] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 197230592. Throughput: 0: 1812.3, 1: 1786.2. Samples: 49318680. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-16 06:35:32,352][03835] Avg episode reward: [(0, '7.490'), (1, '8.700')] -[2023-10-16 06:35:34,820][05219] Updated weights for policy 1, policy_version 96170 (0.0008) -[2023-10-16 06:35:35,190][05219] Updated weights for policy 1, policy_version 96180 (0.0008) -[2023-10-16 06:35:35,542][05219] Updated weights for policy 1, policy_version 96190 (0.0010) -[2023-10-16 06:35:36,157][05218] Updated weights for policy 0, policy_version 96482 (0.0008) -[2023-10-16 06:35:36,571][05218] Updated weights for policy 0, policy_version 96492 (0.0009) -[2023-10-16 06:35:36,946][05218] Updated weights for policy 0, policy_version 96502 (0.0008) -[2023-10-16 06:35:37,317][05218] Updated weights for policy 0, policy_version 96512 (0.0007) -[2023-10-16 06:35:37,351][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14440.1). Total num frames: 197328896. Throughput: 0: 1796.2, 1: 1787.6. Samples: 49339702. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-16 06:35:37,352][03835] Avg episode reward: [(0, '8.050'), (1, '7.990')] -[2023-10-16 06:35:37,363][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000096512_98828288.pth... -[2023-10-16 06:35:37,363][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000096192_98500608.pth... -[2023-10-16 06:35:37,400][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000094528_96796672.pth -[2023-10-16 06:35:37,400][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000094816_97091584.pth -[2023-10-16 06:35:39,309][05219] Updated weights for policy 1, policy_version 96200 (0.0007) -[2023-10-16 06:35:39,680][05219] Updated weights for policy 1, policy_version 96210 (0.0007) -[2023-10-16 06:35:40,053][05219] Updated weights for policy 1, policy_version 96220 (0.0007) -[2023-10-16 06:35:40,789][05218] Updated weights for policy 0, policy_version 96522 (0.0008) -[2023-10-16 06:35:41,160][05218] Updated weights for policy 0, policy_version 96532 (0.0007) -[2023-10-16 06:35:41,535][05218] Updated weights for policy 0, policy_version 96542 (0.0007) -[2023-10-16 06:35:42,350][03835] Fps is (10 sec: 16384.6, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 197394432. Throughput: 0: 1809.0, 1: 1795.9. Samples: 49351338. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-16 06:35:42,351][03835] Avg episode reward: [(0, '8.450'), (1, '10.260')] -[2023-10-16 06:35:42,352][04891] Saving new best policy, reward=10.260! -[2023-10-16 06:35:43,833][05219] Updated weights for policy 1, policy_version 96230 (0.0008) -[2023-10-16 06:35:44,196][05219] Updated weights for policy 1, policy_version 96240 (0.0007) -[2023-10-16 06:35:44,569][05219] Updated weights for policy 1, policy_version 96250 (0.0008) -[2023-10-16 06:35:45,212][05218] Updated weights for policy 0, policy_version 96552 (0.0008) -[2023-10-16 06:35:45,587][05218] Updated weights for policy 0, policy_version 96562 (0.0009) -[2023-10-16 06:35:45,962][05218] Updated weights for policy 0, policy_version 96572 (0.0010) -[2023-10-16 06:35:47,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 197459968. Throughput: 0: 1796.8, 1: 1794.1. Samples: 49372308. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-16 06:35:47,351][03835] Avg episode reward: [(0, '8.410'), (1, '8.870')] -[2023-10-16 06:35:48,258][05219] Updated weights for policy 1, policy_version 96260 (0.0009) -[2023-10-16 06:35:48,612][05219] Updated weights for policy 1, policy_version 96270 (0.0009) -[2023-10-16 06:35:48,969][05219] Updated weights for policy 1, policy_version 96280 (0.0007) -[2023-10-16 06:35:49,636][05218] Updated weights for policy 0, policy_version 96582 (0.0008) -[2023-10-16 06:35:50,009][05218] Updated weights for policy 0, policy_version 96592 (0.0010) -[2023-10-16 06:35:50,381][05218] Updated weights for policy 0, policy_version 96602 (0.0008) -[2023-10-16 06:35:52,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 197525504. Throughput: 0: 1810.7, 1: 1790.7. Samples: 49395214. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-16 06:35:52,351][03835] Avg episode reward: [(0, '7.890'), (1, '9.370')] -[2023-10-16 06:35:52,830][05219] Updated weights for policy 1, policy_version 96290 (0.0008) -[2023-10-16 06:35:53,201][05219] Updated weights for policy 1, policy_version 96300 (0.0007) -[2023-10-16 06:35:53,555][05219] Updated weights for policy 1, policy_version 96310 (0.0008) -[2023-10-16 06:35:53,842][05218] Updated weights for policy 0, policy_version 96612 (0.0007) -[2023-10-16 06:35:53,918][05219] Updated weights for policy 1, policy_version 96320 (0.0008) -[2023-10-16 06:35:54,215][05218] Updated weights for policy 0, policy_version 96622 (0.0009) -[2023-10-16 06:35:54,588][05218] Updated weights for policy 0, policy_version 96632 (0.0007) -[2023-10-16 06:35:57,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 197591040. Throughput: 0: 1812.0, 1: 1786.7. Samples: 49405108. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-16 06:35:57,351][03835] Avg episode reward: [(0, '8.460'), (1, '9.580')] -[2023-10-16 06:35:57,782][05219] Updated weights for policy 1, policy_version 96330 (0.0010) -[2023-10-16 06:35:58,139][05219] Updated weights for policy 1, policy_version 96340 (0.0009) -[2023-10-16 06:35:58,283][05218] Updated weights for policy 0, policy_version 96642 (0.0009) -[2023-10-16 06:35:58,497][05219] Updated weights for policy 1, policy_version 96350 (0.0007) -[2023-10-16 06:35:58,666][05218] Updated weights for policy 0, policy_version 96652 (0.0010) -[2023-10-16 06:35:59,054][05218] Updated weights for policy 0, policy_version 96662 (0.0010) -[2023-10-16 06:35:59,424][05218] Updated weights for policy 0, policy_version 96672 (0.0009) -[2023-10-16 06:36:02,218][05219] Updated weights for policy 1, policy_version 96360 (0.0009) -[2023-10-16 06:36:02,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 197656576. Throughput: 0: 1814.2, 1: 1791.4. Samples: 49427572. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-16 06:36:02,351][03835] Avg episode reward: [(0, '8.380'), (1, '10.360')] -[2023-10-16 06:36:02,586][05219] Updated weights for policy 1, policy_version 96370 (0.0007) -[2023-10-16 06:36:02,940][05219] Updated weights for policy 1, policy_version 96380 (0.0008) -[2023-10-16 06:36:03,081][04891] Saving new best policy, reward=10.360! -[2023-10-16 06:36:03,125][05218] Updated weights for policy 0, policy_version 96682 (0.0008) -[2023-10-16 06:36:03,501][05218] Updated weights for policy 0, policy_version 96692 (0.0009) -[2023-10-16 06:36:03,867][05218] Updated weights for policy 0, policy_version 96702 (0.0009) -[2023-10-16 06:36:06,901][05219] Updated weights for policy 1, policy_version 96390 (0.0007) -[2023-10-16 06:36:07,276][05219] Updated weights for policy 1, policy_version 96400 (0.0007) -[2023-10-16 06:36:07,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 197722112. Throughput: 0: 1812.6, 1: 1806.1. Samples: 49449372. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-16 06:36:07,351][03835] Avg episode reward: [(0, '8.110'), (1, '8.940')] -[2023-10-16 06:36:07,640][05219] Updated weights for policy 1, policy_version 96410 (0.0007) -[2023-10-16 06:36:07,693][05218] Updated weights for policy 0, policy_version 96712 (0.0007) -[2023-10-16 06:36:08,072][05218] Updated weights for policy 0, policy_version 96722 (0.0008) -[2023-10-16 06:36:08,447][05218] Updated weights for policy 0, policy_version 96732 (0.0007) -[2023-10-16 06:36:11,319][05219] Updated weights for policy 1, policy_version 96420 (0.0007) -[2023-10-16 06:36:11,689][05219] Updated weights for policy 1, policy_version 96430 (0.0008) -[2023-10-16 06:36:12,061][05219] Updated weights for policy 1, policy_version 96440 (0.0007) -[2023-10-16 06:36:12,293][05218] Updated weights for policy 0, policy_version 96742 (0.0008) -[2023-10-16 06:36:12,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14440.2). Total num frames: 197820416. Throughput: 0: 1811.1, 1: 1797.3. Samples: 49459850. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-16 06:36:12,351][03835] Avg episode reward: [(0, '8.150'), (1, '8.240')] -[2023-10-16 06:36:12,666][05218] Updated weights for policy 0, policy_version 96752 (0.0009) -[2023-10-16 06:36:13,043][05218] Updated weights for policy 0, policy_version 96762 (0.0009) -[2023-10-16 06:36:15,848][05219] Updated weights for policy 1, policy_version 96450 (0.0007) -[2023-10-16 06:36:16,207][05219] Updated weights for policy 1, policy_version 96460 (0.0010) -[2023-10-16 06:36:16,567][05219] Updated weights for policy 1, policy_version 96470 (0.0008) -[2023-10-16 06:36:16,785][05218] Updated weights for policy 0, policy_version 96772 (0.0008) -[2023-10-16 06:36:16,928][05219] Updated weights for policy 1, policy_version 96480 (0.0007) -[2023-10-16 06:36:17,147][05218] Updated weights for policy 0, policy_version 96782 (0.0010) -[2023-10-16 06:36:17,350][03835] Fps is (10 sec: 16384.1, 60 sec: 14745.7, 300 sec: 14440.1). Total num frames: 197885952. Throughput: 0: 1808.2, 1: 1813.6. Samples: 49481662. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-16 06:36:17,351][03835] Avg episode reward: [(0, '9.220'), (1, '8.360')] -[2023-10-16 06:36:17,521][05218] Updated weights for policy 0, policy_version 96792 (0.0009) -[2023-10-16 06:36:20,789][05219] Updated weights for policy 1, policy_version 96490 (0.0010) -[2023-10-16 06:36:21,150][05219] Updated weights for policy 1, policy_version 96500 (0.0009) -[2023-10-16 06:36:21,424][05218] Updated weights for policy 0, policy_version 96802 (0.0007) -[2023-10-16 06:36:21,527][05219] Updated weights for policy 1, policy_version 96510 (0.0011) -[2023-10-16 06:36:21,799][05218] Updated weights for policy 0, policy_version 96812 (0.0008) -[2023-10-16 06:36:22,184][05218] Updated weights for policy 0, policy_version 96822 (0.0008) -[2023-10-16 06:36:22,350][03835] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 197951488. Throughput: 0: 1811.9, 1: 1791.5. Samples: 49501856. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-16 06:36:22,351][03835] Avg episode reward: [(0, '9.020'), (1, '7.510')] -[2023-10-16 06:36:22,556][05218] Updated weights for policy 0, policy_version 96832 (0.0008) -[2023-10-16 06:36:25,322][05219] Updated weights for policy 1, policy_version 96520 (0.0009) -[2023-10-16 06:36:25,693][05219] Updated weights for policy 1, policy_version 96530 (0.0009) -[2023-10-16 06:36:26,061][05219] Updated weights for policy 1, policy_version 96540 (0.0008) -[2023-10-16 06:36:26,317][05218] Updated weights for policy 0, policy_version 96842 (0.0009) -[2023-10-16 06:36:26,692][05218] Updated weights for policy 0, policy_version 96852 (0.0009) -[2023-10-16 06:36:27,067][05218] Updated weights for policy 0, policy_version 96862 (0.0009) -[2023-10-16 06:36:27,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 198049792. Throughput: 0: 1800.7, 1: 1811.8. Samples: 49513898. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-16 06:36:27,351][03835] Avg episode reward: [(0, '8.240'), (1, '7.380')] -[2023-10-16 06:36:29,644][05219] Updated weights for policy 1, policy_version 96550 (0.0009) -[2023-10-16 06:36:30,019][05219] Updated weights for policy 1, policy_version 96560 (0.0008) -[2023-10-16 06:36:30,378][05219] Updated weights for policy 1, policy_version 96570 (0.0008) -[2023-10-16 06:36:30,764][05218] Updated weights for policy 0, policy_version 96872 (0.0010) -[2023-10-16 06:36:31,147][05218] Updated weights for policy 0, policy_version 96882 (0.0009) -[2023-10-16 06:36:31,521][05218] Updated weights for policy 0, policy_version 96892 (0.0008) -[2023-10-16 06:36:32,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 198115328. Throughput: 0: 1813.5, 1: 1782.0. Samples: 49534110. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-16 06:36:32,352][03835] Avg episode reward: [(0, '8.760'), (1, '8.230')] -[2023-10-16 06:36:34,274][05219] Updated weights for policy 1, policy_version 96580 (0.0009) -[2023-10-16 06:36:34,637][05219] Updated weights for policy 1, policy_version 96590 (0.0008) -[2023-10-16 06:36:35,001][05219] Updated weights for policy 1, policy_version 96600 (0.0008) -[2023-10-16 06:36:35,175][05218] Updated weights for policy 0, policy_version 96902 (0.0008) -[2023-10-16 06:36:35,547][05218] Updated weights for policy 0, policy_version 96912 (0.0009) -[2023-10-16 06:36:35,928][05218] Updated weights for policy 0, policy_version 96922 (0.0012) -[2023-10-16 06:36:37,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14440.1). Total num frames: 198180864. Throughput: 0: 1793.0, 1: 1779.2. Samples: 49555962. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-16 06:36:37,351][03835] Avg episode reward: [(0, '9.000'), (1, '8.840')] -[2023-10-16 06:36:38,704][05219] Updated weights for policy 1, policy_version 96610 (0.0008) -[2023-10-16 06:36:39,070][05219] Updated weights for policy 1, policy_version 96620 (0.0008) -[2023-10-16 06:36:39,438][05219] Updated weights for policy 1, policy_version 96630 (0.0010) -[2023-10-16 06:36:39,721][05218] Updated weights for policy 0, policy_version 96932 (0.0010) -[2023-10-16 06:36:39,792][05219] Updated weights for policy 1, policy_version 96640 (0.0010) -[2023-10-16 06:36:40,098][05218] Updated weights for policy 0, policy_version 96942 (0.0007) -[2023-10-16 06:36:40,471][05218] Updated weights for policy 0, policy_version 96952 (0.0009) -[2023-10-16 06:36:42,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 198246400. Throughput: 0: 1800.5, 1: 1778.8. Samples: 49566176. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-16 06:36:42,351][03835] Avg episode reward: [(0, '7.830'), (1, '7.800')] -[2023-10-16 06:36:43,557][05219] Updated weights for policy 1, policy_version 96650 (0.0007) -[2023-10-16 06:36:43,924][05219] Updated weights for policy 1, policy_version 96660 (0.0008) -[2023-10-16 06:36:44,249][05218] Updated weights for policy 0, policy_version 96962 (0.0010) -[2023-10-16 06:36:44,285][05219] Updated weights for policy 1, policy_version 96670 (0.0007) -[2023-10-16 06:36:44,623][05218] Updated weights for policy 0, policy_version 96972 (0.0010) -[2023-10-16 06:36:45,001][05218] Updated weights for policy 0, policy_version 96982 (0.0010) -[2023-10-16 06:36:45,366][05218] Updated weights for policy 0, policy_version 96992 (0.0007) -[2023-10-16 06:36:47,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 198311936. Throughput: 0: 1782.5, 1: 1778.5. Samples: 49587818. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-16 06:36:47,352][03835] Avg episode reward: [(0, '7.710'), (1, '8.220')] -[2023-10-16 06:36:47,977][05219] Updated weights for policy 1, policy_version 96680 (0.0008) -[2023-10-16 06:36:48,348][05219] Updated weights for policy 1, policy_version 96690 (0.0008) -[2023-10-16 06:36:48,702][05219] Updated weights for policy 1, policy_version 96700 (0.0009) -[2023-10-16 06:36:49,122][05218] Updated weights for policy 0, policy_version 97002 (0.0009) -[2023-10-16 06:36:49,496][05218] Updated weights for policy 0, policy_version 97012 (0.0009) -[2023-10-16 06:36:49,872][05218] Updated weights for policy 0, policy_version 97022 (0.0008) -[2023-10-16 06:36:52,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 198377472. Throughput: 0: 1781.6, 1: 1795.0. Samples: 49610322. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-16 06:36:52,351][03835] Avg episode reward: [(0, '9.010'), (1, '9.920')] -[2023-10-16 06:36:52,633][05219] Updated weights for policy 1, policy_version 96710 (0.0008) -[2023-10-16 06:36:53,016][05219] Updated weights for policy 1, policy_version 96720 (0.0008) -[2023-10-16 06:36:53,383][05219] Updated weights for policy 1, policy_version 96730 (0.0009) -[2023-10-16 06:36:53,615][05218] Updated weights for policy 0, policy_version 97032 (0.0010) -[2023-10-16 06:36:53,987][05218] Updated weights for policy 0, policy_version 97042 (0.0008) -[2023-10-16 06:36:54,364][05218] Updated weights for policy 0, policy_version 97052 (0.0009) -[2023-10-16 06:36:57,151][05219] Updated weights for policy 1, policy_version 96740 (0.0008) -[2023-10-16 06:36:57,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 198443008. Throughput: 0: 1783.3, 1: 1776.0. Samples: 49620018. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-16 06:36:57,351][03835] Avg episode reward: [(0, '8.290'), (1, '8.690')] -[2023-10-16 06:36:57,519][05219] Updated weights for policy 1, policy_version 96750 (0.0008) -[2023-10-16 06:36:57,887][05219] Updated weights for policy 1, policy_version 96760 (0.0008) -[2023-10-16 06:36:58,001][05218] Updated weights for policy 0, policy_version 97062 (0.0008) -[2023-10-16 06:36:58,380][05218] Updated weights for policy 0, policy_version 97072 (0.0009) -[2023-10-16 06:36:58,757][05218] Updated weights for policy 0, policy_version 97082 (0.0009) -[2023-10-16 06:37:01,587][05219] Updated weights for policy 1, policy_version 96770 (0.0008) -[2023-10-16 06:37:01,955][05219] Updated weights for policy 1, policy_version 96780 (0.0010) -[2023-10-16 06:37:02,321][05219] Updated weights for policy 1, policy_version 96790 (0.0007) -[2023-10-16 06:37:02,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 198508544. Throughput: 0: 1783.2, 1: 1786.9. Samples: 49642318. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-16 06:37:02,351][03835] Avg episode reward: [(0, '7.220'), (1, '8.630')] -[2023-10-16 06:37:02,568][05218] Updated weights for policy 0, policy_version 97092 (0.0008) -[2023-10-16 06:37:02,683][05219] Updated weights for policy 1, policy_version 96800 (0.0007) -[2023-10-16 06:37:02,941][05218] Updated weights for policy 0, policy_version 97102 (0.0008) -[2023-10-16 06:37:03,322][05218] Updated weights for policy 0, policy_version 97112 (0.0009) -[2023-10-16 06:37:06,468][05219] Updated weights for policy 1, policy_version 96810 (0.0009) -[2023-10-16 06:37:06,824][05219] Updated weights for policy 1, policy_version 96820 (0.0007) -[2023-10-16 06:37:07,103][05218] Updated weights for policy 0, policy_version 97122 (0.0010) -[2023-10-16 06:37:07,185][05219] Updated weights for policy 1, policy_version 96830 (0.0007) -[2023-10-16 06:37:07,350][03835] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 198606848. Throughput: 0: 1802.4, 1: 1783.8. Samples: 49663232. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-16 06:37:07,351][03835] Avg episode reward: [(0, '7.670'), (1, '9.110')] -[2023-10-16 06:37:07,506][05218] Updated weights for policy 0, policy_version 97132 (0.0008) -[2023-10-16 06:37:07,881][05218] Updated weights for policy 0, policy_version 97142 (0.0007) -[2023-10-16 06:37:08,252][05218] Updated weights for policy 0, policy_version 97152 (0.0009) -[2023-10-16 06:37:10,929][05219] Updated weights for policy 1, policy_version 96840 (0.0008) -[2023-10-16 06:37:11,296][05219] Updated weights for policy 1, policy_version 96850 (0.0008) -[2023-10-16 06:37:11,661][05219] Updated weights for policy 1, policy_version 96860 (0.0008) -[2023-10-16 06:37:11,941][05218] Updated weights for policy 0, policy_version 97162 (0.0007) -[2023-10-16 06:37:12,307][05218] Updated weights for policy 0, policy_version 97172 (0.0008) -[2023-10-16 06:37:12,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 198672384. Throughput: 0: 1784.9, 1: 1788.8. Samples: 49674716. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-16 06:37:12,351][03835] Avg episode reward: [(0, '7.950'), (1, '8.940')] -[2023-10-16 06:37:12,682][05218] Updated weights for policy 0, policy_version 97182 (0.0007) -[2023-10-16 06:37:15,476][05219] Updated weights for policy 1, policy_version 96870 (0.0007) -[2023-10-16 06:37:15,835][05219] Updated weights for policy 1, policy_version 96880 (0.0010) -[2023-10-16 06:37:16,198][05219] Updated weights for policy 1, policy_version 96890 (0.0009) -[2023-10-16 06:37:16,451][05218] Updated weights for policy 0, policy_version 97192 (0.0008) -[2023-10-16 06:37:16,829][05218] Updated weights for policy 0, policy_version 97202 (0.0008) -[2023-10-16 06:37:17,196][05218] Updated weights for policy 0, policy_version 97212 (0.0009) -[2023-10-16 06:37:17,350][03835] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 198770688. Throughput: 0: 1799.3, 1: 1796.6. Samples: 49695928. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-16 06:37:17,351][03835] Avg episode reward: [(0, '7.030'), (1, '8.940')] -[2023-10-16 06:37:19,921][05219] Updated weights for policy 1, policy_version 96900 (0.0008) -[2023-10-16 06:37:20,284][05219] Updated weights for policy 1, policy_version 96910 (0.0009) -[2023-10-16 06:37:20,640][05219] Updated weights for policy 1, policy_version 96920 (0.0008) -[2023-10-16 06:37:20,783][05218] Updated weights for policy 0, policy_version 97222 (0.0009) -[2023-10-16 06:37:21,161][05218] Updated weights for policy 0, policy_version 97232 (0.0008) -[2023-10-16 06:37:21,528][05218] Updated weights for policy 0, policy_version 97242 (0.0009) -[2023-10-16 06:37:22,350][03835] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 198836224. Throughput: 0: 1780.4, 1: 1792.8. Samples: 49716758. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-16 06:37:22,351][03835] Avg episode reward: [(0, '7.490'), (1, '8.410')] -[2023-10-16 06:37:24,353][05219] Updated weights for policy 1, policy_version 96930 (0.0008) -[2023-10-16 06:37:24,722][05219] Updated weights for policy 1, policy_version 96940 (0.0010) -[2023-10-16 06:37:25,088][05219] Updated weights for policy 1, policy_version 96950 (0.0008) -[2023-10-16 06:37:25,103][05218] Updated weights for policy 0, policy_version 97252 (0.0010) -[2023-10-16 06:37:25,451][05219] Updated weights for policy 1, policy_version 96960 (0.0008) -[2023-10-16 06:37:25,486][05218] Updated weights for policy 0, policy_version 97262 (0.0009) -[2023-10-16 06:37:25,861][05218] Updated weights for policy 0, policy_version 97272 (0.0009) -[2023-10-16 06:37:27,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 198901760. Throughput: 0: 1797.1, 1: 1803.5. Samples: 49728202. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-16 06:37:27,351][03835] Avg episode reward: [(0, '8.120'), (1, '7.250')] -[2023-10-16 06:37:29,229][05219] Updated weights for policy 1, policy_version 96970 (0.0010) -[2023-10-16 06:37:29,597][05219] Updated weights for policy 1, policy_version 96980 (0.0009) -[2023-10-16 06:37:29,773][05218] Updated weights for policy 0, policy_version 97282 (0.0010) -[2023-10-16 06:37:29,967][05219] Updated weights for policy 1, policy_version 96990 (0.0007) -[2023-10-16 06:37:30,152][05218] Updated weights for policy 0, policy_version 97292 (0.0010) -[2023-10-16 06:37:30,528][05218] Updated weights for policy 0, policy_version 97302 (0.0008) -[2023-10-16 06:37:30,902][05218] Updated weights for policy 0, policy_version 97312 (0.0009) -[2023-10-16 06:37:32,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 198967296. Throughput: 0: 1788.4, 1: 1797.0. Samples: 49749158. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:37:32,352][03835] Avg episode reward: [(0, '9.040'), (1, '6.110')] -[2023-10-16 06:37:33,721][05219] Updated weights for policy 1, policy_version 97000 (0.0009) -[2023-10-16 06:37:34,091][05219] Updated weights for policy 1, policy_version 97010 (0.0009) -[2023-10-16 06:37:34,464][05219] Updated weights for policy 1, policy_version 97020 (0.0009) -[2023-10-16 06:37:34,643][05218] Updated weights for policy 0, policy_version 97322 (0.0008) -[2023-10-16 06:37:35,024][05218] Updated weights for policy 0, policy_version 97332 (0.0007) -[2023-10-16 06:37:35,404][05218] Updated weights for policy 0, policy_version 97342 (0.0007) -[2023-10-16 06:37:37,351][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 199032832. Throughput: 0: 1793.0, 1: 1792.6. Samples: 49771674. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:37:37,352][03835] Avg episode reward: [(0, '7.540'), (1, '5.780')] -[2023-10-16 06:37:37,362][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000097344_99680256.pth... -[2023-10-16 06:37:37,362][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000097024_99352576.pth... -[2023-10-16 06:37:37,392][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000095648_97943552.pth -[2023-10-16 06:37:37,400][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000095360_97648640.pth -[2023-10-16 06:37:38,210][05219] Updated weights for policy 1, policy_version 97030 (0.0008) -[2023-10-16 06:37:38,579][05219] Updated weights for policy 1, policy_version 97040 (0.0009) -[2023-10-16 06:37:38,946][05219] Updated weights for policy 1, policy_version 97050 (0.0008) -[2023-10-16 06:37:38,998][05218] Updated weights for policy 0, policy_version 97352 (0.0007) -[2023-10-16 06:37:39,374][05218] Updated weights for policy 0, policy_version 97362 (0.0010) -[2023-10-16 06:37:39,746][05218] Updated weights for policy 0, policy_version 97372 (0.0009) -[2023-10-16 06:37:42,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 199098368. Throughput: 0: 1794.5, 1: 1797.4. Samples: 49781656. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:37:42,351][03835] Avg episode reward: [(0, '7.990'), (1, '6.910')] -[2023-10-16 06:37:42,699][05219] Updated weights for policy 1, policy_version 97060 (0.0008) -[2023-10-16 06:37:43,070][05219] Updated weights for policy 1, policy_version 97070 (0.0008) -[2023-10-16 06:37:43,413][05218] Updated weights for policy 0, policy_version 97382 (0.0008) -[2023-10-16 06:37:43,424][05219] Updated weights for policy 1, policy_version 97080 (0.0008) -[2023-10-16 06:37:43,794][05218] Updated weights for policy 0, policy_version 97392 (0.0009) -[2023-10-16 06:37:44,170][05218] Updated weights for policy 0, policy_version 97402 (0.0008) -[2023-10-16 06:37:47,195][05219] Updated weights for policy 1, policy_version 97090 (0.0008) -[2023-10-16 06:37:47,350][03835] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 199163904. Throughput: 0: 1802.0, 1: 1796.7. Samples: 49804258. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:37:47,351][03835] Avg episode reward: [(0, '8.300'), (1, '7.730')] -[2023-10-16 06:37:47,553][05219] Updated weights for policy 1, policy_version 97100 (0.0008) -[2023-10-16 06:37:47,898][05218] Updated weights for policy 0, policy_version 97412 (0.0009) -[2023-10-16 06:37:47,917][05219] Updated weights for policy 1, policy_version 97110 (0.0008) -[2023-10-16 06:37:48,271][05218] Updated weights for policy 0, policy_version 97422 (0.0008) -[2023-10-16 06:37:48,293][05219] Updated weights for policy 1, policy_version 97120 (0.0008) -[2023-10-16 06:37:48,643][05218] Updated weights for policy 0, policy_version 97432 (0.0009) -[2023-10-16 06:37:51,958][05219] Updated weights for policy 1, policy_version 97130 (0.0008) -[2023-10-16 06:37:52,327][05219] Updated weights for policy 1, policy_version 97140 (0.0009) -[2023-10-16 06:37:52,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 199229440. Throughput: 0: 1812.7, 1: 1806.9. Samples: 49826110. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:37:52,351][03835] Avg episode reward: [(0, '8.230'), (1, '8.760')] -[2023-10-16 06:37:52,540][05218] Updated weights for policy 0, policy_version 97442 (0.0010) -[2023-10-16 06:37:52,682][05219] Updated weights for policy 1, policy_version 97150 (0.0008) -[2023-10-16 06:37:52,931][05218] Updated weights for policy 0, policy_version 97452 (0.0009) -[2023-10-16 06:37:53,308][05218] Updated weights for policy 0, policy_version 97462 (0.0008) -[2023-10-16 06:37:53,678][05218] Updated weights for policy 0, policy_version 97472 (0.0009) -[2023-10-16 06:37:56,565][05219] Updated weights for policy 1, policy_version 97160 (0.0008) -[2023-10-16 06:37:56,927][05219] Updated weights for policy 1, policy_version 97170 (0.0009) -[2023-10-16 06:37:57,290][05219] Updated weights for policy 1, policy_version 97180 (0.0008) -[2023-10-16 06:37:57,350][03835] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 199294976. Throughput: 0: 1801.0, 1: 1791.5. Samples: 49836378. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:37:57,351][03835] Avg episode reward: [(0, '8.150'), (1, '8.970')] -[2023-10-16 06:37:57,360][05218] Updated weights for policy 0, policy_version 97482 (0.0008) -[2023-10-16 06:37:57,730][05218] Updated weights for policy 0, policy_version 97492 (0.0009) -[2023-10-16 06:37:58,110][05218] Updated weights for policy 0, policy_version 97502 (0.0008) -[2023-10-16 06:38:01,182][05219] Updated weights for policy 1, policy_version 97190 (0.0008) -[2023-10-16 06:38:01,551][05219] Updated weights for policy 1, policy_version 97200 (0.0008) -[2023-10-16 06:38:01,821][05218] Updated weights for policy 0, policy_version 97512 (0.0007) -[2023-10-16 06:38:01,913][05219] Updated weights for policy 1, policy_version 97210 (0.0008) -[2023-10-16 06:38:02,205][05218] Updated weights for policy 0, policy_version 97522 (0.0007) -[2023-10-16 06:38:02,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 199393280. Throughput: 0: 1811.3, 1: 1803.2. Samples: 49858580. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:38:02,351][03835] Avg episode reward: [(0, '8.380'), (1, '8.970')] -[2023-10-16 06:38:02,584][05218] Updated weights for policy 0, policy_version 97532 (0.0007) -[2023-10-16 06:38:05,795][05219] Updated weights for policy 1, policy_version 97220 (0.0008) -[2023-10-16 06:38:06,163][05219] Updated weights for policy 1, policy_version 97230 (0.0008) -[2023-10-16 06:38:06,386][05218] Updated weights for policy 0, policy_version 97542 (0.0008) -[2023-10-16 06:38:06,532][05219] Updated weights for policy 1, policy_version 97240 (0.0008) -[2023-10-16 06:38:06,769][05218] Updated weights for policy 0, policy_version 97552 (0.0007) -[2023-10-16 06:38:07,141][05218] Updated weights for policy 0, policy_version 97562 (0.0009) -[2023-10-16 06:38:07,350][03835] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 199458816. Throughput: 0: 1806.3, 1: 1780.1. Samples: 49878146. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:38:07,351][03835] Avg episode reward: [(0, '8.480'), (1, '9.710')] -[2023-10-16 06:38:10,300][05219] Updated weights for policy 1, policy_version 97250 (0.0007) -[2023-10-16 06:38:10,669][05219] Updated weights for policy 1, policy_version 97260 (0.0007) -[2023-10-16 06:38:10,848][05218] Updated weights for policy 0, policy_version 97572 (0.0008) -[2023-10-16 06:38:11,030][05219] Updated weights for policy 1, policy_version 97270 (0.0007) -[2023-10-16 06:38:11,215][05218] Updated weights for policy 0, policy_version 97582 (0.0010) -[2023-10-16 06:38:11,397][05219] Updated weights for policy 1, policy_version 97280 (0.0007) -[2023-10-16 06:38:11,581][05218] Updated weights for policy 0, policy_version 97592 (0.0007) -[2023-10-16 06:38:12,350][03835] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 199557120. Throughput: 0: 1811.6, 1: 1802.0. Samples: 49890814. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:38:12,352][03835] Avg episode reward: [(0, '8.160'), (1, '9.350')] -[2023-10-16 06:38:15,174][05219] Updated weights for policy 1, policy_version 97290 (0.0007) -[2023-10-16 06:38:15,330][05218] Updated weights for policy 0, policy_version 97602 (0.0010) -[2023-10-16 06:38:15,546][05219] Updated weights for policy 1, policy_version 97300 (0.0008) -[2023-10-16 06:38:15,700][05218] Updated weights for policy 0, policy_version 97612 (0.0009) -[2023-10-16 06:38:15,909][05219] Updated weights for policy 1, policy_version 97310 (0.0007) -[2023-10-16 06:38:16,074][05218] Updated weights for policy 0, policy_version 97622 (0.0008) -[2023-10-16 06:38:16,449][05218] Updated weights for policy 0, policy_version 97632 (0.0009) -[2023-10-16 06:38:17,350][03835] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 199622656. Throughput: 0: 1807.1, 1: 1774.1. Samples: 49910312. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:38:17,351][03835] Avg episode reward: [(0, '7.370'), (1, '9.010')] -[2023-10-16 06:38:19,652][05219] Updated weights for policy 1, policy_version 97320 (0.0010) -[2023-10-16 06:38:20,020][05219] Updated weights for policy 1, policy_version 97330 (0.0009) -[2023-10-16 06:38:20,189][05218] Updated weights for policy 0, policy_version 97642 (0.0007) -[2023-10-16 06:38:20,388][05219] Updated weights for policy 1, policy_version 97340 (0.0008) -[2023-10-16 06:38:20,565][05218] Updated weights for policy 0, policy_version 97652 (0.0008) -[2023-10-16 06:38:20,936][05218] Updated weights for policy 0, policy_version 97662 (0.0009) -[2023-10-16 06:38:22,350][03835] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14440.1). Total num frames: 199688192. Throughput: 0: 1798.4, 1: 1778.6. Samples: 49932640. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:38:22,351][03835] Avg episode reward: [(0, '8.800'), (1, '9.030')] -[2023-10-16 06:38:24,225][05219] Updated weights for policy 1, policy_version 97350 (0.0010) -[2023-10-16 06:38:24,608][05219] Updated weights for policy 1, policy_version 97360 (0.0008) -[2023-10-16 06:38:24,682][05218] Updated weights for policy 0, policy_version 97672 (0.0007) -[2023-10-16 06:38:24,966][05219] Updated weights for policy 1, policy_version 97370 (0.0007) -[2023-10-16 06:38:25,052][05218] Updated weights for policy 0, policy_version 97682 (0.0008) -[2023-10-16 06:38:25,435][05218] Updated weights for policy 0, policy_version 97692 (0.0011) -[2023-10-16 06:38:27,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 199753728. Throughput: 0: 1806.1, 1: 1779.1. Samples: 49942988. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:38:27,351][03835] Avg episode reward: [(0, '9.300'), (1, '8.570')] -[2023-10-16 06:38:28,597][05219] Updated weights for policy 1, policy_version 97380 (0.0007) -[2023-10-16 06:38:28,957][05219] Updated weights for policy 1, policy_version 97390 (0.0008) -[2023-10-16 06:38:29,093][05218] Updated weights for policy 0, policy_version 97702 (0.0009) -[2023-10-16 06:38:29,323][05219] Updated weights for policy 1, policy_version 97400 (0.0008) -[2023-10-16 06:38:29,457][05218] Updated weights for policy 0, policy_version 97712 (0.0008) -[2023-10-16 06:38:29,835][05218] Updated weights for policy 0, policy_version 97722 (0.0009) -[2023-10-16 06:38:32,350][03835] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 199819264. Throughput: 0: 1791.7, 1: 1780.0. Samples: 49964986. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-16 06:38:32,351][03835] Avg episode reward: [(0, '8.300'), (1, '8.430')] -[2023-10-16 06:38:32,916][05219] Updated weights for policy 1, policy_version 97410 (0.0009) -[2023-10-16 06:38:33,282][05219] Updated weights for policy 1, policy_version 97420 (0.0010) -[2023-10-16 06:38:33,639][05219] Updated weights for policy 1, policy_version 97430 (0.0008) -[2023-10-16 06:38:33,642][05218] Updated weights for policy 0, policy_version 97732 (0.0008) -[2023-10-16 06:38:34,000][05219] Updated weights for policy 1, policy_version 97440 (0.0009) -[2023-10-16 06:38:34,004][05218] Updated weights for policy 0, policy_version 97742 (0.0008) -[2023-10-16 06:38:34,377][05218] Updated weights for policy 0, policy_version 97752 (0.0009) -[2023-10-16 06:38:37,350][03835] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 199884800. Throughput: 0: 1793.7, 1: 1794.3. Samples: 49987574. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-16 06:38:37,352][03835] Avg episode reward: [(0, '7.320'), (1, '9.230')] -[2023-10-16 06:38:37,847][05219] Updated weights for policy 1, policy_version 97450 (0.0008) -[2023-10-16 06:38:38,070][05218] Updated weights for policy 0, policy_version 97762 (0.0009) -[2023-10-16 06:38:38,209][05219] Updated weights for policy 1, policy_version 97460 (0.0008) -[2023-10-16 06:38:38,468][05218] Updated weights for policy 0, policy_version 97772 (0.0008) -[2023-10-16 06:38:38,577][05219] Updated weights for policy 1, policy_version 97470 (0.0008) -[2023-10-16 06:38:38,848][05218] Updated weights for policy 0, policy_version 97782 (0.0009) -[2023-10-16 06:38:39,217][05218] Updated weights for policy 0, policy_version 97792 (0.0009) -[2023-10-16 06:38:42,350][03835] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 199950336. Throughput: 0: 1797.6, 1: 1778.7. Samples: 49997310. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-16 06:38:42,351][03835] Avg episode reward: [(0, '8.790'), (1, '8.230')] -[2023-10-16 06:38:42,468][05219] Updated weights for policy 1, policy_version 97480 (0.0008) -[2023-10-16 06:38:42,829][05219] Updated weights for policy 1, policy_version 97490 (0.0008) -[2023-10-16 06:38:42,853][05218] Updated weights for policy 0, policy_version 97802 (0.0009) -[2023-10-16 06:38:43,193][05219] Updated weights for policy 1, policy_version 97500 (0.0009) -[2023-10-16 06:38:43,220][05218] Updated weights for policy 0, policy_version 97812 (0.0008) -[2023-10-16 06:38:43,596][05218] Updated weights for policy 0, policy_version 97822 (0.0010) -[2023-10-16 06:38:47,070][05219] Updated weights for policy 1, policy_version 97510 (0.0008) -[2023-10-16 06:38:47,215][05218] Updated weights for policy 0, policy_version 97832 (0.0007) -[2023-10-16 06:38:47,350][03835] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 200015872. Throughput: 0: 1795.9, 1: 1789.6. Samples: 50019926. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-16 06:38:47,351][03835] Avg episode reward: [(0, '8.500'), (1, '8.250')] -[2023-10-16 06:38:47,438][05219] Updated weights for policy 1, policy_version 97520 (0.0008) -[2023-10-16 06:38:47,587][05218] Updated weights for policy 0, policy_version 97842 (0.0008) -[2023-10-16 06:38:47,792][05219] Updated weights for policy 1, policy_version 97530 (0.0007) -[2023-10-16 06:38:47,962][05218] Updated weights for policy 0, policy_version 97852 (0.0008) -[2023-10-16 06:38:51,534][05219] Updated weights for policy 1, policy_version 97540 (0.0009) -[2023-10-16 06:38:51,888][05218] Updated weights for policy 0, policy_version 97862 (0.0010) -[2023-10-16 06:38:51,891][05219] Updated weights for policy 1, policy_version 97550 (0.0008) -[2023-10-16 06:38:52,256][05218] Updated weights for policy 0, policy_version 97872 (0.0011) -[2023-10-16 06:38:52,258][05219] Updated weights for policy 1, policy_version 97560 (0.0008) -[2023-10-16 06:38:52,350][03835] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 200081408. Throughput: 0: 1802.0, 1: 1798.6. Samples: 50040174. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-16 06:38:52,351][03835] Avg episode reward: [(0, '8.130'), (1, '8.910')] -[2023-10-16 06:38:52,637][05218] Updated weights for policy 0, policy_version 97882 (0.0007) -[2023-10-16 06:38:55,995][05219] Updated weights for policy 1, policy_version 97570 (0.0008) -[2023-10-16 06:38:56,350][05219] Updated weights for policy 1, policy_version 97580 (0.0007) -[2023-10-16 06:38:56,472][05218] Updated weights for policy 0, policy_version 97892 (0.0009) -[2023-10-16 06:38:56,719][05219] Updated weights for policy 1, policy_version 97590 (0.0008) -[2023-10-16 06:38:56,845][05218] Updated weights for policy 0, policy_version 97902 (0.0008) -[2023-10-16 06:38:57,079][05219] Updated weights for policy 1, policy_version 97600 (0.0007) -[2023-10-16 06:38:57,224][05218] Updated weights for policy 0, policy_version 97912 (0.0007) -[2023-10-16 06:38:57,350][03835] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 200179712. Throughput: 0: 1783.1, 1: 1788.4. Samples: 50051534. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-16 06:38:57,351][03835] Avg episode reward: [(0, '8.630'), (1, '8.640')] -[2023-10-16 06:39:00,819][05219] Updated weights for policy 1, policy_version 97610 (0.0009) -[2023-10-16 06:39:01,098][05218] Updated weights for policy 0, policy_version 97922 (0.0008) -[2023-10-16 06:39:01,183][05219] Updated weights for policy 1, policy_version 97620 (0.0007) -[2023-10-16 06:39:01,463][05218] Updated weights for policy 0, policy_version 97932 (0.0008) -[2023-10-16 06:39:01,553][05219] Updated weights for policy 1, policy_version 97630 (0.0009) -[2023-10-16 06:39:01,835][05218] Updated weights for policy 0, policy_version 97942 (0.0010) -[2023-10-16 06:39:02,210][05218] Updated weights for policy 0, policy_version 97952 (0.0010) -[2023-10-16 06:39:02,350][03835] Fps is (10 sec: 19660.9, 60 sec: 14745.6, 300 sec: 14440.1). Total num frames: 200278016. Throughput: 0: 1804.3, 1: 1808.0. Samples: 50072866. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-16 06:39:02,351][03835] Avg episode reward: [(0, '8.800'), (1, '8.610')] -[2023-10-16 06:39:05,181][05219] Updated weights for policy 1, policy_version 97640 (0.0008) -[2023-10-16 06:39:05,544][05219] Updated weights for policy 1, policy_version 97650 (0.0008) -[2023-10-16 06:39:05,880][05218] Updated weights for policy 0, policy_version 97962 (0.0008) -[2023-10-16 06:39:05,911][05219] Updated weights for policy 1, policy_version 97660 (0.0009) -[2023-10-16 06:39:06,246][05218] Updated weights for policy 0, policy_version 97972 (0.0007) -[2023-10-16 06:39:06,628][05218] Updated weights for policy 0, policy_version 97982 (0.0010) -[2023-10-16 06:39:06,702][05223] Stopping RolloutWorker_w3... -[2023-10-16 06:39:06,702][05231] Stopping RolloutWorker_w11... -[2023-10-16 06:39:06,702][05224] Stopping RolloutWorker_w4... -[2023-10-16 06:39:06,702][05225] Stopping RolloutWorker_w5... -[2023-10-16 06:39:06,702][05223] Loop rollout_proc3_evt_loop terminating... -[2023-10-16 06:39:06,702][05232] Stopping RolloutWorker_w12... -[2023-10-16 06:39:06,702][05231] Loop rollout_proc11_evt_loop terminating... -[2023-10-16 06:39:06,702][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000097984_100335616.pth... -[2023-10-16 06:39:06,702][05224] Loop rollout_proc4_evt_loop terminating... -[2023-10-16 06:39:06,702][05227] Stopping RolloutWorker_w7... -[2023-10-16 06:39:06,703][05225] Loop rollout_proc5_evt_loop terminating... -[2023-10-16 06:39:06,703][05232] Loop rollout_proc12_evt_loop terminating... -[2023-10-16 06:39:06,703][05227] Loop rollout_proc7_evt_loop terminating... -[2023-10-16 06:39:06,702][03835] Component RolloutWorker_w3 stopped! -[2023-10-16 06:39:06,703][05233] Stopping RolloutWorker_w13... -[2023-10-16 06:39:06,703][04891] Stopping Batcher_1... -[2023-10-16 06:39:06,703][03835] Component RolloutWorker_w4 stopped! -[2023-10-16 06:39:06,703][05233] Loop rollout_proc13_evt_loop terminating... -[2023-10-16 06:39:06,704][03835] Component RolloutWorker_w11 stopped! -[2023-10-16 06:39:06,704][05970] Stopping RolloutWorker_w15... -[2023-10-16 06:39:06,703][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000097664_100007936.pth... -[2023-10-16 06:39:06,704][03835] Component RolloutWorker_w5 stopped! -[2023-10-16 06:39:06,704][05970] Loop rollout_proc15_evt_loop terminating... -[2023-10-16 06:39:06,704][03835] Component RolloutWorker_w12 stopped! -[2023-10-16 06:39:06,705][03835] Component Batcher_0 stopped! -[2023-10-16 06:39:06,705][05969] Stopping RolloutWorker_w14... -[2023-10-16 06:39:06,705][05220] Stopping RolloutWorker_w0... -[2023-10-16 06:39:06,705][03835] Component RolloutWorker_w7 stopped! -[2023-10-16 06:39:06,706][05969] Loop rollout_proc14_evt_loop terminating... -[2023-10-16 06:39:06,706][05220] Loop rollout_proc0_evt_loop terminating... -[2023-10-16 06:39:06,706][03835] Component RolloutWorker_w13 stopped! -[2023-10-16 06:39:06,706][05226] Stopping RolloutWorker_w6... -[2023-10-16 06:39:06,706][03835] Component Batcher_1 stopped! -[2023-10-16 06:39:06,706][05229] Stopping RolloutWorker_w9... -[2023-10-16 06:39:06,706][05221] Stopping RolloutWorker_w1... -[2023-10-16 06:39:06,706][05226] Loop rollout_proc6_evt_loop terminating... -[2023-10-16 06:39:06,706][05229] Loop rollout_proc9_evt_loop terminating... -[2023-10-16 06:39:06,706][05221] Loop rollout_proc1_evt_loop terminating... -[2023-10-16 06:39:06,706][03835] Component RolloutWorker_w15 stopped! -[2023-10-16 06:39:06,706][05228] Stopping RolloutWorker_w8... -[2023-10-16 06:39:06,707][05228] Loop rollout_proc8_evt_loop terminating... -[2023-10-16 06:39:06,707][03835] Component RolloutWorker_w14 stopped! -[2023-10-16 06:39:06,707][03835] Component RolloutWorker_w0 stopped! -[2023-10-16 06:39:06,708][03835] Component RolloutWorker_w6 stopped! -[2023-10-16 06:39:06,708][03835] Component RolloutWorker_w9 stopped! -[2023-10-16 06:39:06,708][05222] Stopping RolloutWorker_w2... -[2023-10-16 06:39:06,708][05230] Stopping RolloutWorker_w10... -[2023-10-16 06:39:06,708][03835] Component RolloutWorker_w1 stopped! -[2023-10-16 06:39:06,709][05222] Loop rollout_proc2_evt_loop terminating... -[2023-10-16 06:39:06,709][05230] Loop rollout_proc10_evt_loop terminating... -[2023-10-16 06:39:06,709][03835] Component RolloutWorker_w8 stopped! -[2023-10-16 06:39:06,709][03835] Component RolloutWorker_w2 stopped! -[2023-10-16 06:39:06,704][04891] Loop batcher_evt_loop terminating... -[2023-10-16 06:39:06,709][03835] Component RolloutWorker_w10 stopped! -[2023-10-16 06:39:06,702][04766] Stopping Batcher_0... -[2023-10-16 06:39:06,729][05219] Weights refcount: 2 0 -[2023-10-16 06:39:06,731][05219] Stopping InferenceWorker_p1-w0... -[2023-10-16 06:39:06,732][05219] Loop inference_proc1-0_evt_loop terminating... -[2023-10-16 06:39:06,732][05218] Weights refcount: 2 0 -[2023-10-16 06:39:06,732][03835] Component InferenceWorker_p1-w0 stopped! -[2023-10-16 06:39:06,734][05218] Stopping InferenceWorker_p0-w0... -[2023-10-16 06:39:06,734][05218] Loop inference_proc0-0_evt_loop terminating... -[2023-10-16 06:39:06,734][03835] Component InferenceWorker_p0-w0 stopped! -[2023-10-16 06:39:06,744][04891] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000096192_98500608.pth -[2023-10-16 06:39:06,731][04766] Loop batcher_evt_loop terminating... -[2023-10-16 06:39:06,749][04891] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p1/checkpoint_000097664_100007936.pth... -[2023-10-16 06:39:06,749][04766] Removing ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000096512_98828288.pth -[2023-10-16 06:39:06,756][04766] Saving ./train_atari/atari_timepilot_APPO/checkpoint_p0/checkpoint_000097984_100335616.pth... -[2023-10-16 06:39:06,794][04891] Stopping LearnerWorker_p1... -[2023-10-16 06:39:06,794][04891] Loop learner_proc1_evt_loop terminating... -[2023-10-16 06:39:06,794][03835] Component LearnerWorker_p1 stopped! -[2023-10-16 06:39:06,810][04766] Stopping LearnerWorker_p0... -[2023-10-16 06:39:06,811][04766] Loop learner_proc0_evt_loop terminating... -[2023-10-16 06:39:06,810][03835] Component LearnerWorker_p0 stopped! -[2023-10-16 06:39:06,811][03835] Waiting for process learner_proc0 to stop... -[2023-10-16 06:39:07,725][03835] Waiting for process learner_proc1 to stop... -[2023-10-16 06:39:07,726][03835] Waiting for process inference_proc0-0 to join... -[2023-10-16 06:39:07,727][03835] Waiting for process inference_proc1-0 to join... -[2023-10-16 06:39:07,728][03835] Waiting for process rollout_proc0 to join... -[2023-10-16 06:39:07,728][03835] Waiting for process rollout_proc1 to join... -[2023-10-16 06:39:07,729][03835] Waiting for process rollout_proc2 to join... -[2023-10-16 06:39:07,730][03835] Waiting for process rollout_proc3 to join... -[2023-10-16 06:39:07,730][03835] Waiting for process rollout_proc4 to join... -[2023-10-16 06:39:07,731][03835] Waiting for process rollout_proc5 to join... -[2023-10-16 06:39:07,731][03835] Waiting for process rollout_proc6 to join... -[2023-10-16 06:39:07,732][03835] Waiting for process rollout_proc7 to join... -[2023-10-16 06:39:07,732][03835] Waiting for process rollout_proc8 to join... -[2023-10-16 06:39:07,733][03835] Waiting for process rollout_proc9 to join... -[2023-10-16 06:39:07,733][03835] Waiting for process rollout_proc10 to join... -[2023-10-16 06:39:07,734][03835] Waiting for process rollout_proc11 to join... -[2023-10-16 06:39:07,734][03835] Waiting for process rollout_proc12 to join... -[2023-10-16 06:39:07,735][03835] Waiting for process rollout_proc13 to join... -[2023-10-16 06:39:07,735][03835] Waiting for process rollout_proc14 to join... -[2023-10-16 06:39:07,736][03835] Waiting for process rollout_proc15 to join... -[2023-10-16 06:39:07,736][03835] Batcher 0 profile tree view: -batching: 173.1060, releasing_batches: 0.0901 -[2023-10-16 06:39:07,737][03835] Batcher 1 profile tree view: -batching: 171.8587, releasing_batches: 0.0900 -[2023-10-16 06:39:07,737][03835] InferenceWorker_p0-w0 profile tree view: -wait_policy: 0.0014 - wait_policy_total: 1824.4878 -update_model: 202.9296 - weight_update: 0.0010 -one_step: 0.0028 - handle_policy_step: 11288.9652 - deserialize: 62.6105, stack: 189.8188, obs_to_device_normalize: 2538.8063, forward: 5097.6547, prepare_outputs: 2449.3362, send_messages: 464.6067 -[2023-10-16 06:39:07,738][03835] InferenceWorker_p1-w0 profile tree view: -wait_policy: 0.0001 - wait_policy_total: 2025.5595 -update_model: 199.2572 - weight_update: 0.0008 -one_step: 0.0026 - handle_policy_step: 11097.4147 - deserialize: 63.8084, stack: 189.9044, obs_to_device_normalize: 2476.8164, forward: 5011.3249, prepare_outputs: 2412.1320, send_messages: 461.0152 -[2023-10-16 06:39:07,738][03835] Learner 0 profile tree view: -misc: 0.0195, prepare_batch: 261.5460 -train: 3689.6055 - epoch_init: 0.1915, minibatch_init: 13.0298, losses_postprocess: 907.0285, kl_divergence: 29.0739, update: 405.8248, after_optimizer: 2150.6527 - calculate_losses: 166.9026 - losses_init: 0.3857, forward_head: 56.4878, bptt_initial: 1.4355, bptt: 1.9781, tail: 38.4095, advantages_returns: 11.0922, losses: 43.6083 -[2023-10-16 06:39:07,739][03835] Learner 1 profile tree view: -misc: 0.0194, prepare_batch: 259.6702 -train: 3584.1886 - epoch_init: 0.1866, minibatch_init: 12.9592, losses_postprocess: 881.7893, kl_divergence: 30.9104, update: 387.6294, after_optimizer: 2087.8586 - calculate_losses: 165.6882 - losses_init: 0.3932, forward_head: 55.8008, bptt_initial: 1.4227, bptt: 1.7946, tail: 38.1534, advantages_returns: 11.0586, losses: 43.3396 -[2023-10-16 06:39:07,739][03835] RolloutWorker_w0 profile tree view: -wait_for_trajectories: 1.2254, enqueue_policy_requests: 408.4343, process_policy_outputs: 195.5297, env_step: 6580.3847, finalize_trajectories: 3.4025, complete_rollouts: 2.9838 -post_env_step: 375.2697 - process_env_step: 83.8288 -[2023-10-16 06:39:07,740][03835] RolloutWorker_w15 profile tree view: -wait_for_trajectories: 1.2174, enqueue_policy_requests: 403.7673, process_policy_outputs: 187.4128, env_step: 6740.9546, finalize_trajectories: 3.7625, complete_rollouts: 3.0311 -post_env_step: 377.9258 - process_env_step: 84.1607 -[2023-10-16 06:39:07,740][03835] Loop Runner_EvtLoop terminating... -[2023-10-16 06:39:07,740][03835] Runner profile tree view: -main_loop: 14005.7754 -[2023-10-16 06:39:07,741][03835] Collected {0: 100335616, 1: 100007936}, FPS: 14304.4 +version https://git-lfs.github.com/spec/v1 +oid sha256:cdf56b86e01aea201585f6c301f63db410d6cf14362086492eb8fadfe4fdb495 +size 48234755