| { | |
| "name": "root", | |
| "gauges": { | |
| "SoccerTwos.Policy.Entropy.mean": { | |
| "value": 0.9073097109794617, | |
| "min": 0.8696509003639221, | |
| "max": 3.295811414718628, | |
| "count": 2200 | |
| }, | |
| "SoccerTwos.Policy.Entropy.sum": { | |
| "value": 35856.87890625, | |
| "min": 21059.609375, | |
| "max": 1019961.375, | |
| "count": 2200 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.mean": { | |
| "value": 24.602040816326532, | |
| "min": 17.152416356877325, | |
| "max": 392.75, | |
| "count": 2200 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.sum": { | |
| "value": 19288.0, | |
| "min": 17756.0, | |
| "max": 21412.0, | |
| "count": 2200 | |
| }, | |
| "SoccerTwos.Self-play.ELO.mean": { | |
| "value": 1533.4588753226842, | |
| "min": 1200.328406833094, | |
| "max": 1579.4606048764724, | |
| "count": 2200 | |
| }, | |
| "SoccerTwos.Self-play.ELO.sum": { | |
| "value": 601115.8791264922, | |
| "min": 2409.9434577136913, | |
| "max": 781900.3774073822, | |
| "count": 2200 | |
| }, | |
| "SoccerTwos.Step.mean": { | |
| "value": 21999994.0, | |
| "min": 9958.0, | |
| "max": 21999994.0, | |
| "count": 2200 | |
| }, | |
| "SoccerTwos.Step.sum": { | |
| "value": 21999994.0, | |
| "min": 9958.0, | |
| "max": 21999994.0, | |
| "count": 2200 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { | |
| "value": 0.0006931066163815558, | |
| "min": -0.11423704773187637, | |
| "max": 0.23437894880771637, | |
| "count": 2200 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { | |
| "value": 0.27100467681884766, | |
| "min": -49.42055130004883, | |
| "max": 68.4496078491211, | |
| "count": 2200 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.0009028149652294815, | |
| "min": -0.11388174444437027, | |
| "max": 0.21143116056919098, | |
| "count": 2200 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 0.3530006408691406, | |
| "min": -50.347877502441406, | |
| "max": 67.15494537353516, | |
| "count": 2200 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.mean": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 2200 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.sum": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 2200 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.mean": { | |
| "value": 0.052163681105884444, | |
| "min": -0.3903066684802373, | |
| "max": 0.5489372896440958, | |
| "count": 2200 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.sum": { | |
| "value": 20.395999312400818, | |
| "min": -103.09040009975433, | |
| "max": 141.59099984169006, | |
| "count": 2200 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.mean": { | |
| "value": 0.052163681105884444, | |
| "min": -0.3903066684802373, | |
| "max": 0.5489372896440958, | |
| "count": 2200 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.sum": { | |
| "value": 20.395999312400818, | |
| "min": -103.09040009975433, | |
| "max": 141.59099984169006, | |
| "count": 2200 | |
| }, | |
| "SoccerTwos.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 2200 | |
| }, | |
| "SoccerTwos.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 2200 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.mean": { | |
| "value": 0.016792847060908875, | |
| "min": 0.01056482947509115, | |
| "max": 0.024503496209702765, | |
| "count": 1065 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.sum": { | |
| "value": 0.016792847060908875, | |
| "min": 0.01056482947509115, | |
| "max": 0.024503496209702765, | |
| "count": 1065 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.mean": { | |
| "value": 0.11256088341275851, | |
| "min": 0.005557317488516371, | |
| "max": 0.12470681170622508, | |
| "count": 1065 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.sum": { | |
| "value": 0.11256088341275851, | |
| "min": 0.005557317488516371, | |
| "max": 0.12470681170622508, | |
| "count": 1065 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.mean": { | |
| "value": 0.11302393625179927, | |
| "min": 0.005690486178112527, | |
| "max": 0.12509485532840092, | |
| "count": 1065 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.sum": { | |
| "value": 0.11302393625179927, | |
| "min": 0.005690486178112527, | |
| "max": 0.12509485532840092, | |
| "count": 1065 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.mean": { | |
| "value": 1.933272083181791e-07, | |
| "min": 1.933272083181791e-07, | |
| "max": 0.0002997203455477637, | |
| "count": 1065 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.sum": { | |
| "value": 1.933272083181791e-07, | |
| "min": 1.933272083181791e-07, | |
| "max": 0.0002997203455477637, | |
| "count": 1065 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.mean": { | |
| "value": 0.25, | |
| "min": 0.25, | |
| "max": 0.25, | |
| "count": 1065 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.sum": { | |
| "value": 0.25, | |
| "min": 0.25, | |
| "max": 0.25, | |
| "count": 1065 | |
| }, | |
| "SoccerTwos.Policy.Beta.mean": { | |
| "value": 1.6434468181818088e-05, | |
| "min": 1.6434468181818088e-05, | |
| "max": 0.009990687503636362, | |
| "count": 1065 | |
| }, | |
| "SoccerTwos.Policy.Beta.sum": { | |
| "value": 1.6434468181818088e-05, | |
| "min": 1.6434468181818088e-05, | |
| "max": 0.009990687503636362, | |
| "count": 1065 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1693348019", | |
| "python_version": "3.9.17 (main, Jul 5 2023, 20:41:20) \n[GCC 11.2.0]", | |
| "command_line_arguments": "/home/mgmeskill/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=Downstrike-20M --no-graphics --num-envs=32", | |
| "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": "1693373657" | |
| }, | |
| "total": 25638.07527213078, | |
| "count": 1, | |
| "self": 0.836282589007169, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.17577498173341155, | |
| "count": 1, | |
| "self": 0.17577498173341155 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 25637.06321456004, | |
| "count": 1, | |
| "self": 8.342477745376527, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 271.783062253613, | |
| "count": 1088, | |
| "self": 271.783062253613 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 25356.61511585163, | |
| "count": 108628, | |
| "self": 3.1089843809604645, | |
| "children": { | |
| "env_step": { | |
| "total": 15745.96533632977, | |
| "count": 108628, | |
| "self": 5440.94653446367, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 10292.108620898332, | |
| "count": 3116235, | |
| "self": 255.61927175475284, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 10036.48934914358, | |
| "count": 5628498, | |
| "self": 10036.48934914358 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 12.910180967766792, | |
| "count": 108628, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 818588.5154348165, | |
| "count": 3112826, | |
| "is_parallel": true, | |
| "self": 780482.6229405664, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.07693493086844683, | |
| "count": 64, | |
| "is_parallel": true, | |
| "self": 0.015927689615637064, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.06100724125280976, | |
| "count": 256, | |
| "is_parallel": true, | |
| "self": 0.06100724125280976 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.719481447711587, | |
| "count": 32, | |
| "is_parallel": true, | |
| "self": 0.020501975435763597, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.013642964884638786, | |
| "count": 32, | |
| "is_parallel": true, | |
| "self": 0.013642964884638786 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.627972015645355, | |
| "count": 32, | |
| "is_parallel": true, | |
| "self": 0.627972015645355 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.05736449174582958, | |
| "count": 64, | |
| "is_parallel": true, | |
| "self": 0.01029907027259469, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.04706542147323489, | |
| "count": 256, | |
| "is_parallel": true, | |
| "self": 0.04706542147323489 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 38019.55847894726, | |
| "count": 3112794, | |
| "is_parallel": true, | |
| "self": 2457.6824236582033, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 1512.2425317005254, | |
| "count": 3112794, | |
| "is_parallel": true, | |
| "self": 1512.2425317005254 | |
| }, | |
| "communicator.exchange": { | |
| "total": 27368.108181226067, | |
| "count": 3112794, | |
| "is_parallel": true, | |
| "self": 27368.108181226067 | |
| }, | |
| "steps_from_proto": { | |
| "total": 6681.525342362467, | |
| "count": 6225588, | |
| "is_parallel": true, | |
| "self": 1143.5824937582947, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 5537.9428486041725, | |
| "count": 24902352, | |
| "is_parallel": true, | |
| "self": 5537.9428486041725 | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "steps_from_proto": { | |
| "total": 86.33401530282572, | |
| "count": 69568, | |
| "is_parallel": true, | |
| "self": 14.690878832247108, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 71.64313647057861, | |
| "count": 278272, | |
| "is_parallel": true, | |
| "self": 71.64313647057861 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 9607.5407951409, | |
| "count": 108628, | |
| "self": 132.7211998142302, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 4697.321105179377, | |
| "count": 108628, | |
| "self": 4693.751423222944, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 3.5696819564327598, | |
| "count": 11, | |
| "self": 3.5696819564327598 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 4777.498490147293, | |
| "count": 1065, | |
| "self": 2678.744994345121, | |
| "children": { | |
| "TorchPOCAOptimizer.update": { | |
| "total": 2098.7534958021715, | |
| "count": 31950, | |
| "self": 2098.7534958021715 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 6.621703505516052e-07, | |
| "count": 1, | |
| "self": 6.621703505516052e-07 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.3225580472499132, | |
| "count": 1, | |
| "self": 0.0020071682520210743, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.32055087899789214, | |
| "count": 1, | |
| "self": 0.32055087899789214 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |