{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6788311004638672, "min": 1.6788311004638672, "max": 1.6829555034637451, "count": 2 }, "SoccerTwos.Policy.Entropy.sum": { "value": 31911.220703125, "min": 31127.9453125, "max": 31911.220703125, "count": 2 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 63.72727272727273, "min": 63.72727272727273, "max": 64.82539682539682, "count": 2 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19628.0, "min": 16336.0, "max": 19628.0, "count": 2 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1632.8647177530843, "min": 1632.8647177530843, "max": 1638.4677131037708, "count": 2 }, "SoccerTwos.Self-play.ELO.sum": { "value": 251461.166533975, "min": 206446.93185107512, "max": 251461.166533975, "count": 2 }, "SoccerTwos.Step.mean": { "value": 11529990.0, "min": 11519997.0, "max": 11529990.0, "count": 2 }, "SoccerTwos.Step.sum": { "value": 11529990.0, "min": 11519997.0, "max": 11529990.0, "count": 2 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.06437841802835464, "min": -0.07045652717351913, "max": -0.06437841802835464, "count": 2 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -9.914276123046875, "min": -9.914276123046875, "max": -8.807065963745117, "count": 2 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.06181387975811958, "min": -0.06980134546756744, "max": -0.06181387975811958, "count": 2 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -9.51933765411377, "min": -9.51933765411377, "max": -8.725168228149414, "count": 2 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.1314272717996077, "min": -0.2555904026031494, "max": -0.1314272717996077, "count": 2 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -20.239799857139587, "min": -31.948800325393677, "max": -20.239799857139587, "count": 2 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.1314272717996077, "min": -0.2555904026031494, "max": -0.1314272717996077, "count": 2 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -20.239799857139587, "min": -31.948800325393677, "max": -20.239799857139587, "count": 2 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1696491521", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/home/ana/Projektit/hugging/soccertwos/venv/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1696491582" }, "total": 61.57282909400237, "count": 1, "self": 0.7364250690152403, "children": { "run_training.setup": { "total": 0.030083947000093758, "count": 1, "self": 0.030083947000093758 }, "TrainerController.start_learning": { "total": 60.80632007798704, "count": 1, "self": 0.03989709609595593, "children": { "TrainerController._reset_env": { "total": 6.799640182987787, "count": 2, "self": 6.799640182987787 }, "TrainerController.advance": { "total": 53.42278458290093, "count": 1478, "self": 0.03544026076269802, "children": { "env_step": { "total": 28.330933276040014, "count": 1478, "self": 21.80962856815313, "children": { "SubprocessEnvManager._take_step": { "total": 6.500497538159834, "count": 1478, "self": 0.20263866777531803, "children": { "TorchPolicy.evaluate": { "total": 6.297858870384516, "count": 2686, "self": 6.297858870384516 } } }, "workers": { "total": 0.020807169727049768, "count": 1478, "self": 0.0, "children": { "worker_root": { "total": 44.16046370769618, "count": 1478, "is_parallel": true, "self": 26.821750550632714, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003850438995868899, "count": 2, "is_parallel": true, "self": 0.0009601740166544914, "children": { "_process_rank_one_or_two_observation": { "total": 0.0028902649792144075, "count": 8, "is_parallel": true, "self": 0.0028902649792144075 } } }, "UnityEnvironment.step": { "total": 0.026216419995762408, "count": 1, "is_parallel": true, "self": 0.0006972309784032404, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0007348080107476562, "count": 1, "is_parallel": true, "self": 0.0007348080107476562 }, "communicator.exchange": { "total": 0.022396772998035885, "count": 1, "is_parallel": true, "self": 0.022396772998035885 }, "steps_from_proto": { "total": 0.0023876080085756257, "count": 2, "is_parallel": true, "self": 0.0004839759785681963, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019036320300074294, "count": 8, "is_parallel": true, "self": 0.0019036320300074294 } } } } } } }, "steps_from_proto": { "total": 0.0023256010026670992, "count": 2, "is_parallel": true, "self": 0.0005124810122651979, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018131199904019013, "count": 8, "is_parallel": true, "self": 0.0018131199904019013 } } }, "UnityEnvironment.step": { "total": 17.3363875560608, "count": 1477, "is_parallel": true, "self": 0.9461618925270159, "children": { "UnityEnvironment._generate_step_input": { "total": 0.9797643240308389, "count": 1477, "is_parallel": true, "self": 0.9797643240308389 }, "communicator.exchange": { "total": 12.38035620978917, "count": 1477, "is_parallel": true, "self": 12.38035620978917 }, "steps_from_proto": { "total": 3.0301051297137747, "count": 2954, "is_parallel": true, "self": 0.6764998308208305, "children": { "_process_rank_one_or_two_observation": { "total": 2.353605298892944, "count": 11816, "is_parallel": true, "self": 2.353605298892944 } } } } } } } } } } }, "trainer_advance": { "total": 25.05641104609822, "count": 1478, "self": 0.21700152996345423, "children": { "process_trajectory": { "total": 8.821250546126976, "count": 1478, "self": 8.821250546126976 }, "_update_policy": { "total": 16.01815897000779, "count": 1, "self": 2.6248928839922883, "children": { "TorchPOCAOptimizer.update": { "total": 13.393266086015501, "count": 10, "self": 13.393266086015501 } } } } } } }, "trainer_threads": { "total": 1.1499942047521472e-06, "count": 1, "self": 1.1499942047521472e-06 }, "TrainerController._save_models": { "total": 0.5439970660081599, "count": 1, "self": 0.0021870180062251166, "children": { "RLTrainer._checkpoint": { "total": 0.5418100480019348, "count": 1, "self": 0.5418100480019348 } } } } } } }