| { | |
| "name": "root", | |
| "gauges": { | |
| "SoccerTwos.Policy.Entropy.mean": { | |
| "value": 2.327099084854126, | |
| "min": 2.2909886837005615, | |
| "max": 3.2956619262695312, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.Entropy.sum": { | |
| "value": 46095.1796875, | |
| "min": 17667.0234375, | |
| "max": 109077.3125, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.mean": { | |
| "value": 69.82857142857142, | |
| "min": 49.642857142857146, | |
| "max": 999.0, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.sum": { | |
| "value": 19552.0, | |
| "min": 10568.0, | |
| "max": 28660.0, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Self-play.ELO.mean": { | |
| "value": 1464.6314575105607, | |
| "min": 1165.3195416719932, | |
| "max": 1480.6366933530337, | |
| "count": 444 | |
| }, | |
| "SoccerTwos.Self-play.ELO.sum": { | |
| "value": 205048.4040514785, | |
| "min": 2332.78422683418, | |
| "max": 278289.2758788568, | |
| "count": 444 | |
| }, | |
| "SoccerTwos.Step.mean": { | |
| "value": 4999822.0, | |
| "min": 9302.0, | |
| "max": 4999822.0, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Step.sum": { | |
| "value": 4999822.0, | |
| "min": 9302.0, | |
| "max": 4999822.0, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { | |
| "value": 0.04910920187830925, | |
| "min": -0.05691852048039436, | |
| "max": 0.13701178133487701, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { | |
| "value": 6.875288009643555, | |
| "min": -6.488711357116699, | |
| "max": 22.028100967407227, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.04565862938761711, | |
| "min": -0.05375753715634346, | |
| "max": 0.14484956860542297, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 6.392208099365234, | |
| "min": -7.363629341125488, | |
| "max": 21.85969352722168, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.mean": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.sum": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.mean": { | |
| "value": -0.04758142786366599, | |
| "min": -0.5306250005960464, | |
| "max": 0.46597646965700035, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.sum": { | |
| "value": -6.6613999009132385, | |
| "min": -40.82599997520447, | |
| "max": 45.76739966869354, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.mean": { | |
| "value": -0.04758142786366599, | |
| "min": -0.5306250005960464, | |
| "max": 0.46597646965700035, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.sum": { | |
| "value": -6.6613999009132385, | |
| "min": -40.82599997520447, | |
| "max": 45.76739966869354, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.mean": { | |
| "value": 0.015372107938552896, | |
| "min": 0.010311565268784762, | |
| "max": 0.02428540332863728, | |
| "count": 236 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.sum": { | |
| "value": 0.015372107938552896, | |
| "min": 0.010311565268784762, | |
| "max": 0.02428540332863728, | |
| "count": 236 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.mean": { | |
| "value": 0.09709168200691541, | |
| "min": 1.198309100421587e-06, | |
| "max": 0.10211053341627122, | |
| "count": 236 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.sum": { | |
| "value": 0.09709168200691541, | |
| "min": 1.198309100421587e-06, | |
| "max": 0.10211053341627122, | |
| "count": 236 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.mean": { | |
| "value": 0.0986694390575091, | |
| "min": 1.1829045746480916e-06, | |
| "max": 0.10395682180921237, | |
| "count": 236 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.sum": { | |
| "value": 0.0986694390575091, | |
| "min": 1.1829045746480916e-06, | |
| "max": 0.10395682180921237, | |
| "count": 236 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.mean": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 236 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.sum": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 236 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.mean": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000004, | |
| "max": 0.20000000000000007, | |
| "count": 236 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.sum": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000004, | |
| "max": 0.20000000000000007, | |
| "count": 236 | |
| }, | |
| "SoccerTwos.Policy.Beta.mean": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 236 | |
| }, | |
| "SoccerTwos.Policy.Beta.sum": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 236 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1710621155", | |
| "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", | |
| "command_line_arguments": "\\\\?\\C:\\Users\\johnn\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", | |
| "mlagents_version": "1.1.0.dev0", | |
| "mlagents_envs_version": "1.1.0.dev0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "2.2.1+cpu", | |
| "numpy_version": "1.23.5", | |
| "end_time_seconds": "1710630600" | |
| }, | |
| "total": 9445.6425626, | |
| "count": 1, | |
| "self": 0.18430280000029597, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.07261109999990367, | |
| "count": 1, | |
| "self": 0.07261109999990367 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 9445.3856487, | |
| "count": 1, | |
| "self": 4.6957126002726, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 4.453341700002056, | |
| "count": 25, | |
| "self": 4.453341700002056 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 9436.145233299723, | |
| "count": 329893, | |
| "self": 4.334159799849658, | |
| "children": { | |
| "env_step": { | |
| "total": 3434.7734725000673, | |
| "count": 329893, | |
| "self": 2572.567239900205, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 859.3580607997762, | |
| "count": 329893, | |
| "self": 28.85285559975523, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 830.505205200021, | |
| "count": 639256, | |
| "self": 830.505205200021 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 2.84817180008622, | |
| "count": 329893, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 9436.903225499878, | |
| "count": 329893, | |
| "is_parallel": true, | |
| "self": 7454.163669999512, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.03125449999834018, | |
| "count": 50, | |
| "is_parallel": true, | |
| "self": 0.006143499998643165, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.025110999999697015, | |
| "count": 200, | |
| "is_parallel": true, | |
| "self": 0.025110999999697015 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 1982.7083010003676, | |
| "count": 329893, | |
| "is_parallel": true, | |
| "self": 120.46139400073389, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 116.27273929956073, | |
| "count": 329893, | |
| "is_parallel": true, | |
| "self": 116.27273929956073 | |
| }, | |
| "communicator.exchange": { | |
| "total": 1376.3918962994578, | |
| "count": 329893, | |
| "is_parallel": true, | |
| "self": 1376.3918962994578 | |
| }, | |
| "steps_from_proto": { | |
| "total": 369.5822714006151, | |
| "count": 659786, | |
| "is_parallel": true, | |
| "self": 71.86431850061376, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 297.71795290000136, | |
| "count": 2639144, | |
| "is_parallel": true, | |
| "self": 297.71795290000136 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 5997.037600999805, | |
| "count": 329893, | |
| "self": 41.6415364998702, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 844.9703577999342, | |
| "count": 329893, | |
| "self": 844.0955600999307, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.8747977000034552, | |
| "count": 10, | |
| "self": 0.8747977000034552 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 5110.425706700001, | |
| "count": 236, | |
| "self": 580.4289696999604, | |
| "children": { | |
| "TorchPOCAOptimizer.update": { | |
| "total": 4529.99673700004, | |
| "count": 7089, | |
| "self": 4529.99673700004 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 6.999998731771484e-07, | |
| "count": 1, | |
| "self": 6.999998731771484e-07 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.09136040000157664, | |
| "count": 1, | |
| "self": 0.006359800001519034, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.0850006000000576, | |
| "count": 1, | |
| "self": 0.0850006000000576 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |