| { | |
| "name": "root", | |
| "gauges": { | |
| "SoccerTwos.Policy.Entropy.mean": { | |
| "value": 1.7564705610275269, | |
| "min": 1.6862115859985352, | |
| "max": 3.2894952297210693, | |
| "count": 328 | |
| }, | |
| "SoccerTwos.Policy.Entropy.sum": { | |
| "value": 176209.125, | |
| "min": 169322.625, | |
| "max": 393855.34375, | |
| "count": 328 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.mean": { | |
| "value": 59.826405867970664, | |
| "min": 46.07924528301887, | |
| "max": 953.9230769230769, | |
| "count": 328 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.sum": { | |
| "value": 97876.0, | |
| "min": 96536.0, | |
| "max": 102964.0, | |
| "count": 328 | |
| }, | |
| "SoccerTwos.Self-play.ELO.mean": { | |
| "value": 1602.708888592256, | |
| "min": 1196.5659790628026, | |
| "max": 1629.8939584252985, | |
| "count": 328 | |
| }, | |
| "SoccerTwos.Self-play.ELO.sum": { | |
| "value": 1311015.8708684654, | |
| "min": 9595.098442082712, | |
| "max": 1707915.410533633, | |
| "count": 328 | |
| }, | |
| "SoccerTwos.Step.mean": { | |
| "value": 16399992.0, | |
| "min": 49088.0, | |
| "max": 16399992.0, | |
| "count": 328 | |
| }, | |
| "SoccerTwos.Step.sum": { | |
| "value": 16399992.0, | |
| "min": 49088.0, | |
| "max": 16399992.0, | |
| "count": 328 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { | |
| "value": -0.0033658314496278763, | |
| "min": -0.08460671454668045, | |
| "max": 0.1390356868505478, | |
| "count": 328 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { | |
| "value": -2.7498843669891357, | |
| "min": -79.2764892578125, | |
| "max": 99.82762145996094, | |
| "count": 328 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": -0.0048483810387551785, | |
| "min": -0.08766990154981613, | |
| "max": 0.143933966755867, | |
| "count": 328 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": -3.961127281188965, | |
| "min": -82.14669799804688, | |
| "max": 103.34458923339844, | |
| "count": 328 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.mean": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 328 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.sum": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 328 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.mean": { | |
| "value": -0.02692043992851472, | |
| "min": -0.2808304330253083, | |
| "max": 0.18349247955014114, | |
| "count": 328 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.sum": { | |
| "value": -21.993999421596527, | |
| "min": -151.29859918355942, | |
| "max": 131.74760031700134, | |
| "count": 328 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.mean": { | |
| "value": -0.02692043992851472, | |
| "min": -0.2808304330253083, | |
| "max": 0.18349247955014114, | |
| "count": 328 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.sum": { | |
| "value": -21.993999421596527, | |
| "min": -151.29859918355942, | |
| "max": 131.74760031700134, | |
| "count": 328 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.mean": { | |
| "value": 0.013252768508876519, | |
| "min": 0.01297366823127959, | |
| "max": 0.02173578997705287, | |
| "count": 328 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.sum": { | |
| "value": 0.026505537017753038, | |
| "min": 0.02594733646255918, | |
| "max": 0.0611676517718782, | |
| "count": 328 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.mean": { | |
| "value": 0.10513233728706836, | |
| "min": 0.0004024625793438948, | |
| "max": 0.12297326177358628, | |
| "count": 328 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.sum": { | |
| "value": 0.21026467457413672, | |
| "min": 0.0008049251586877896, | |
| "max": 0.36854586377739906, | |
| "count": 328 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.mean": { | |
| "value": 0.10670649247864883, | |
| "min": 0.0004262993086740607, | |
| "max": 0.12469334908657603, | |
| "count": 328 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.sum": { | |
| "value": 0.21341298495729766, | |
| "min": 0.0008525986173481214, | |
| "max": 0.3740800472597281, | |
| "count": 328 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.mean": { | |
| "value": 0.00019999999999999996, | |
| "min": 0.00019999999999999996, | |
| "max": 0.00019999999999999996, | |
| "count": 328 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.sum": { | |
| "value": 0.0003999999999999999, | |
| "min": 0.0003999999999999999, | |
| "max": 0.0005999999999999998, | |
| "count": 328 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.mean": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000007, | |
| "max": 0.20000000000000007, | |
| "count": 328 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.sum": { | |
| "value": 0.40000000000000013, | |
| "min": 0.40000000000000013, | |
| "max": 0.6000000000000002, | |
| "count": 328 | |
| }, | |
| "SoccerTwos.Policy.Beta.mean": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 328 | |
| }, | |
| "SoccerTwos.Policy.Beta.sum": { | |
| "value": 0.010000000000000002, | |
| "min": 0.010000000000000002, | |
| "max": 0.015000000000000003, | |
| "count": 328 | |
| }, | |
| "SoccerTwos.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 328 | |
| }, | |
| "SoccerTwos.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 328 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1758538876", | |
| "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\\travi\\.conda\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force", | |
| "mlagents_version": "1.2.0.dev0", | |
| "mlagents_envs_version": "1.2.0.dev0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "2.8.0+cpu", | |
| "numpy_version": "1.23.5", | |
| "end_time_seconds": "1758649252" | |
| }, | |
| "total": 110376.94695080002, | |
| "count": 1, | |
| "self": 1.0160212999908254, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.05945110000902787, | |
| "count": 1, | |
| "self": 0.05945110000902787 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 110375.87147840002, | |
| "count": 1, | |
| "self": 56.45513357798336, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 11.60015240003122, | |
| "count": 83, | |
| "self": 11.60015240003122 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 110307.50539932202, | |
| "count": 1129479, | |
| "self": 58.16995546070393, | |
| "children": { | |
| "env_step": { | |
| "total": 44376.25314289302, | |
| "count": 1129479, | |
| "self": 31179.975847236754, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 13164.036727181985, | |
| "count": 1129479, | |
| "self": 366.3107746823225, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 12797.725952499663, | |
| "count": 2071366, | |
| "self": 12797.725952499663 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 32.24056847428437, | |
| "count": 1129478, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 110338.88217584434, | |
| "count": 1129478, | |
| "is_parallel": true, | |
| "self": 85757.98004859698, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.1040870999568142, | |
| "count": 166, | |
| "is_parallel": true, | |
| "self": 0.02159029961330816, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.08249680034350604, | |
| "count": 664, | |
| "is_parallel": true, | |
| "self": 0.08249680034350604 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 24580.798040147405, | |
| "count": 1129478, | |
| "is_parallel": true, | |
| "self": 411.8885549954721, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 407.1164513088879, | |
| "count": 1129478, | |
| "is_parallel": true, | |
| "self": 407.1164513088879 | |
| }, | |
| "communicator.exchange": { | |
| "total": 22508.529119877785, | |
| "count": 1129478, | |
| "is_parallel": true, | |
| "self": 22508.529119877785 | |
| }, | |
| "steps_from_proto": { | |
| "total": 1253.2639139652601, | |
| "count": 2258956, | |
| "is_parallel": true, | |
| "self": 268.47785401536385, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 984.7860599498963, | |
| "count": 9035824, | |
| "is_parallel": true, | |
| "self": 984.7860599498963 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 65873.0823009683, | |
| "count": 1129478, | |
| "self": 335.68821560638025, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 14445.269417263276, | |
| "count": 1129478, | |
| "self": 14435.513299863436, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 9.75611739984015, | |
| "count": 32, | |
| "self": 9.75611739984015 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 51092.12466809864, | |
| "count": 793, | |
| "self": 6188.487225891673, | |
| "children": { | |
| "TorchPOCAOptimizer.update": { | |
| "total": 44903.637442206964, | |
| "count": 23790, | |
| "self": 44903.637442206964 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 2.300017513334751e-06, | |
| "count": 1, | |
| "self": 2.300017513334751e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.3107907999656163, | |
| "count": 1, | |
| "self": 0.006381499930284917, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.3044093000353314, | |
| "count": 1, | |
| "self": 0.3044093000353314 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |