{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 0.5792381167411804, "min": 0.5564664006233215, "max": 0.5887471437454224, "count": 100 }, "SoccerTwos.Policy.Entropy.sum": { "value": 12900.7919921875, "min": 10070.765625, "max": 13885.1533203125, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 58.395348837209305, "min": 49.816326530612244, "max": 96.98113207547169, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20088.0, "min": 18760.0, "max": 20616.0, "count": 100 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1959.6460793924448, "min": 1959.6460793924448, "max": 2028.746127635349, "count": 100 }, "SoccerTwos.Self-play.ELO.sum": { "value": 337059.1256555005, "min": 212126.76521623315, "max": 396619.2366332673, "count": 100 }, "SoccerTwos.Step.mean": { "value": 100999978.0, "min": 100009993.0, "max": 100999978.0, "count": 100 }, "SoccerTwos.Step.sum": { "value": 100999978.0, "min": 100009993.0, "max": 100999978.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.07485218346118927, "min": -0.08581339567899704, "max": 0.02643662318587303, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -12.799723625183105, "min": -13.815957069396973, "max": 3.463197708129883, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.07520425319671631, "min": -0.08607710152864456, "max": 0.026166336610913277, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -12.8599271774292, "min": -13.858413696289062, "max": 3.4277901649475098, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.11691461947926304, "min": -0.28821942806243894, "max": 0.25472156479467756, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -19.99239993095398, "min": -50.43839991092682, "max": 38.97239941358566, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.11691461947926304, "min": -0.28821942806243894, "max": 0.25472156479467756, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -19.99239993095398, "min": -50.43839991092682, "max": 38.97239941358566, "count": 100 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01662449202267453, "min": 0.012663374465773813, "max": 0.024226253782399, "count": 48 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01662449202267453, "min": 0.012663374465773813, "max": 0.024226253782399, "count": 48 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09193826963504155, "min": 0.08983121737837792, "max": 0.11326624130209287, "count": 48 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09193826963504155, "min": 0.08983121737837792, "max": 0.11326624130209287, "count": 48 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0920833706855774, "min": 0.08964181194702785, "max": 0.11334493284424146, "count": 48 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0920833706855774, "min": 0.08964181194702785, "max": 0.11334493284424146, "count": 48 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 3.3539592813848834e-08, "min": 3.3539592813848834e-08, "max": 2.9093564559900864e-06, "count": 48 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 3.3539592813848834e-08, "min": 3.3539592813848834e-08, "max": 2.9093564559900864e-06, "count": 48 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.1000111465346535, "min": 0.1000111465346535, "max": 0.10096975247524753, "count": 48 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.1000111465346535, "min": 0.1000111465346535, "max": 0.10096975247524753, "count": 48 }, "SoccerTwos.Policy.Beta.mean": { "value": 1.0556212079207713e-05, "min": 1.0556212079207713e-05, "max": 5.83906485148513e-05, "count": 48 }, "SoccerTwos.Policy.Beta.sum": { "value": 1.0556212079207713e-05, "min": 1.0556212079207713e-05, "max": 5.83906485148513e-05, "count": 48 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1694665389", "python_version": "3.9.16 (main, Jan 11 2023, 16:16:36) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\ProgramData\\Anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./results/SoccerTwos/configuration.yaml --env=./training-envs-executables/SoccerTwos/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": "1.13.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1694689283" }, "total": 23894.6875082, "count": 1, "self": 1.8670897999982117, "children": { "run_training.setup": { "total": 0.07142919999999986, "count": 1, "self": 0.07142919999999986 }, "TrainerController.start_learning": { "total": 23892.7489892, "count": 1, "self": 11.533405399924959, "children": { "TrainerController._reset_env": { "total": 6.530474599999533, "count": 6, "self": 6.530474599999533 }, "TrainerController.advance": { "total": 23874.241076400078, "count": 68739, "self": 12.1592365994984, "children": { "env_step": { "total": 5442.032858000261, "count": 68739, "self": 4181.5577431, "children": { "SubprocessEnvManager._take_step": { "total": 1256.5973129000124, "count": 68739, "self": 53.87535380028339, "children": { "TorchPolicy.evaluate": { "total": 1202.721959099729, "count": 125540, "self": 1202.721959099729 } } }, "workers": { "total": 3.877802000248556, "count": 68739, "self": 0.0, "children": { "worker_root": { "total": 23872.61769279986, "count": 68739, "is_parallel": true, "self": 20440.53269169994, "children": { "steps_from_proto": { "total": 0.046844100000484445, "count": 12, "is_parallel": true, "self": 0.007820300003988478, "children": { "_process_rank_one_or_two_observation": { "total": 0.03902379999649597, "count": 48, "is_parallel": true, "self": 0.03902379999649597 } } }, "UnityEnvironment.step": { "total": 3432.0381569999186, "count": 68739, "is_parallel": true, "self": 172.01244159941643, "children": { "UnityEnvironment._generate_step_input": { "total": 45.29206190030795, "count": 68739, "is_parallel": true, "self": 45.29206190030795 }, "communicator.exchange": { "total": 2687.663070400131, "count": 68739, "is_parallel": true, "self": 2687.663070400131 }, "steps_from_proto": { "total": 527.070583100063, "count": 137478, "is_parallel": true, "self": 106.85737990000939, "children": { "_process_rank_one_or_two_observation": { "total": 420.2132032000536, "count": 549912, "is_parallel": true, "self": 420.2132032000536 } } } } } } } } } } }, "trainer_advance": { "total": 18420.04898180032, "count": 68739, "self": 62.809541700189584, "children": { "process_trajectory": { "total": 1631.3916463001242, "count": 68739, "self": 1626.5552326001284, "children": { "RLTrainer._checkpoint": { "total": 4.83641369999566, "count": 10, "self": 4.83641369999566 } } }, "_update_policy": { "total": 16725.847793800003, "count": 48, "self": 520.884617199974, "children": { "TorchPOCAOptimizer.update": { "total": 16204.96317660003, "count": 1440, "self": 16204.96317660003 } } } } } } }, "trainer_threads": { "total": 1.1999982234556228e-06, "count": 1, "self": 1.1999982234556228e-06 }, "TrainerController._save_models": { "total": 0.4440316000000166, "count": 1, "self": 0.011391500000172528, "children": { "RLTrainer._checkpoint": { "total": 0.4326400999998441, "count": 1, "self": 0.4326400999998441 } } } } } } }