{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.888009786605835, "min": 1.8311636447906494, "max": 1.959346890449524, "count": 801 }, "SoccerTwos.Policy.Entropy.sum": { "value": 39331.01953125, "min": 1819.8912353515625, "max": 48154.59375, "count": 801 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 96.09615384615384, "min": 25.5, "max": 145.73529411764707, "count": 801 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19988.0, "min": 204.0, "max": 21540.0, "count": 801 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1255.5466302384193, "min": 1172.8204168941593, "max": 1292.0871171030165, "count": 801 }, "SoccerTwos.Self-play.ELO.sum": { "value": 130576.84954479561, "min": 4777.322614426512, "max": 202045.14151784935, "count": 801 }, "SoccerTwos.Step.mean": { "value": 99999958.0, "min": 91999974.0, "max": 99999958.0, "count": 801 }, "SoccerTwos.Step.sum": { "value": 99999958.0, "min": 91999974.0, "max": 99999958.0, "count": 801 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.011170216836035252, "min": -0.10366028547286987, "max": 0.27148541808128357, "count": 801 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 1.1617025136947632, "min": -9.909892082214355, "max": 11.412410736083984, "count": 801 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.010454973205924034, "min": -0.10391616076231003, "max": 0.25962936878204346, "count": 801 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.0873172283172607, "min": -10.197688102722168, "max": 11.668359756469727, "count": 801 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 801 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 801 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.0009730767745238084, "min": -0.48741333617104426, "max": 0.973800003528595, "count": 801 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -0.10119998455047607, "min": -51.632599890232086, "max": 43.781599938869476, "count": 801 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.0009730767745238084, "min": -0.48741333617104426, "max": 0.973800003528595, "count": 801 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -0.10119998455047607, "min": -51.632599890232086, "max": 43.781599938869476, "count": 801 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 801 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 801 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.03705909576549727, "min": 0.0348788173470114, "max": 0.04165394398982503, "count": 387 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.03705909576549727, "min": 0.0348788173470114, "max": 0.04165394398982503, "count": 387 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0351282373336809, "min": 0.029210525937378405, "max": 0.04823799559048244, "count": 387 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0351282373336809, "min": 0.029210525937378405, "max": 0.04823799559048244, "count": 387 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.035853533233915054, "min": 0.0302964643442205, "max": 0.04926804788410664, "count": 387 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.035853533233915054, "min": 0.0302964643442205, "max": 0.04926804788410664, "count": 387 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.00030000000000000014, "min": 0.00030000000000000014, "max": 0.00030000000000000014, "count": 387 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.00030000000000000014, "min": 0.00030000000000000014, "max": 0.00030000000000000014, "count": 387 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.15000000000000002, "min": 0.15000000000000002, "max": 0.15000000000000002, "count": 387 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.15000000000000002, "min": 0.15000000000000002, "max": 0.15000000000000002, "count": 387 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.007499999999999997, "min": 0.007499999999999997, "max": 0.007499999999999997, "count": 387 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.007499999999999997, "min": 0.007499999999999997, "max": 0.007499999999999997, "count": 387 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1682099556", "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "E:\\ProgramData\\Anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.0+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1682173797" }, "total": 74241.41468059999, "count": 1, "self": 0.8190269999904558, "children": { "run_training.setup": { "total": 0.1846551999999999, "count": 1, "self": 0.1846551999999999 }, "TrainerController.start_learning": { "total": 74240.4109984, "count": 1, "self": 14.906384497313411, "children": { "TrainerController._reset_env": { "total": 8.796456700028592, "count": 41, "self": 8.796456700028592 }, "TrainerController.advance": { "total": 74216.50738250265, "count": 537138, "self": 13.548255704488838, "children": { "env_step": { "total": 10851.157855802614, "count": 537138, "self": 8053.994533206816, "children": { "SubprocessEnvManager._take_step": { "total": 2787.380743899268, "count": 537138, "self": 88.36784830023953, "children": { "TorchPolicy.evaluate": { "total": 2699.0128955990285, "count": 1006016, "self": 2699.0128955990285 } } }, "workers": { "total": 9.782578696529532, "count": 537138, "self": 0.0, "children": { "worker_root": { "total": 74213.09890529854, "count": 537138, "is_parallel": true, "self": 67847.0200776994, "children": { "steps_from_proto": { "total": 0.09415409996984625, "count": 82, "is_parallel": true, "self": 0.01869509999147656, "children": { "_process_rank_one_or_two_observation": { "total": 0.07545899997836969, "count": 328, "is_parallel": true, "self": 0.07545899997836969 } } }, "UnityEnvironment.step": { "total": 6365.984673499165, "count": 537138, "is_parallel": true, "self": 351.8846960898827, "children": { "UnityEnvironment._generate_step_input": { "total": 303.0113294023722, "count": 537138, "is_parallel": true, "self": 303.0113294023722 }, "communicator.exchange": { "total": 4600.752456200797, "count": 537138, "is_parallel": true, "self": 4600.752456200797 }, "steps_from_proto": { "total": 1110.336191806114, "count": 1074276, "is_parallel": true, "self": 217.09260710833303, "children": { "_process_rank_one_or_two_observation": { "total": 893.2435846977809, "count": 4297104, "is_parallel": true, "self": 893.2435846977809 } } } } } } } } } } }, "trainer_advance": { "total": 63351.80127099555, "count": 537138, "self": 120.4491249943967, "children": { "process_trajectory": { "total": 4088.742428101126, "count": 537138, "self": 4085.4002123011164, "children": { "RLTrainer._checkpoint": { "total": 3.3422158000095674, "count": 17, "self": 3.3422158000095674 } } }, "_update_policy": { "total": 59142.60971790003, "count": 387, "self": 3747.502850699464, "children": { "TorchPOCAOptimizer.update": { "total": 55395.106867200564, "count": 27090, "self": 55395.106867200564 } } } } } } }, "trainer_threads": { "total": 1.3999961083754897e-06, "count": 1, "self": 1.3999961083754897e-06 }, "TrainerController._save_models": { "total": 0.2007733000064036, "count": 1, "self": 0.011347999999998137, "children": { "RLTrainer._checkpoint": { "total": 0.18942530000640545, "count": 1, "self": 0.18942530000640545 } } } } } } }