{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.775322437286377, "min": 1.6298277378082275, "max": 3.2957680225372314, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 30734.3828125, "min": 16904.1484375, "max": 130905.96875, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 104.45652173913044, "min": 41.27731092436975, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19220.0, "min": 13136.0, "max": 28160.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1638.9537084054139, "min": 1183.5839788722587, "max": 1696.0502651368638, "count": 4938 }, "SoccerTwos.Self-play.ELO.sum": { "value": 150783.74117329807, "min": 2367.668007025154, "max": 392986.48737818724, "count": 4938 }, "SoccerTwos.Step.mean": { "value": 49999781.0, "min": 9098.0, "max": 49999781.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999781.0, "min": 9098.0, "max": 49999781.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.059134457260370255, "min": -0.13769377768039703, "max": 0.1500210464000702, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -5.499504566192627, "min": -24.25472068786621, "max": 28.71771240234375, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.05913936346769333, "min": -0.13808733224868774, "max": 0.15207020938396454, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -5.499960899353027, "min": -24.533588409423828, "max": 29.36444091796875, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.12514623647095055, "min": -0.7368421052631579, "max": 0.5526818158951673, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -11.6385999917984, "min": -74.47360020875931, "max": 66.92720007896423, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.12514623647095055, "min": -0.7368421052631579, "max": 0.5526818158951673, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -11.6385999917984, "min": -74.47360020875931, "max": 66.92720007896423, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.011726681794971227, "min": 0.004552160150342388, "max": 0.019573200820013882, "count": 2416 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.011726681794971227, "min": 0.004552160150342388, "max": 0.019573200820013882, "count": 2416 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08268043200174967, "min": 3.718550609240386e-06, "max": 0.13321264286835988, "count": 2416 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08268043200174967, "min": 3.718550609240386e-06, "max": 0.13321264286835988, "count": 2416 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08324140906333924, "min": 3.874821550198248e-06, "max": 0.13406763573487598, "count": 2416 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08324140906333924, "min": 3.874821550198248e-06, "max": 0.13406763573487598, "count": 2416 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2416 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2416 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2416 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2416 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005, "min": 0.005, "max": 0.005, "count": 2416 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005, "min": 0.005, "max": 0.005, "count": 2416 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1692845011", "python_version": "3.9.17 (main, Jul 5 2023, 20:41:20) \n[GCC 11.2.0]", "command_line_arguments": "/home/ml1/miniconda3/envs/ai2ai/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=ScooerTwos --no-graphics --force", "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": "1692912965" }, "total": 67953.762195813, "count": 1, "self": 0.21896838200336788, "children": { "run_training.setup": { "total": 0.007480952001060359, "count": 1, "self": 0.007480952001060359 }, "TrainerController.start_learning": { "total": 67953.535746479, "count": 1, "self": 62.02943620404403, "children": { "TrainerController._reset_env": { "total": 8.13554351608036, "count": 250, "self": 8.13554351608036 }, "TrainerController.advance": { "total": 67883.01235183283, "count": 3425519, "self": 63.30651859434147, "children": { "env_step": { "total": 52156.55961768422, "count": 3425519, "self": 41131.937237726015, "children": { "SubprocessEnvManager._take_step": { "total": 10985.3791652996, "count": 3425519, "self": 306.65292474688613, "children": { "TorchPolicy.evaluate": { "total": 10678.726240552714, "count": 6295136, "self": 10678.726240552714 } } }, "workers": { "total": 39.24321465860703, "count": 3425519, "self": 0.0, "children": { "worker_root": { "total": 67856.21336730095, "count": 3425519, "is_parallel": true, "self": 33412.63628678667, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019195719942217693, "count": 2, "is_parallel": true, "self": 0.0004653650103136897, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014542069839080796, "count": 8, "is_parallel": true, "self": 0.0014542069839080796 } } }, "UnityEnvironment.step": { "total": 0.02074020500003826, "count": 1, "is_parallel": true, "self": 0.00042888300959020853, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00033699000778142363, "count": 1, "is_parallel": true, "self": 0.00033699000778142363 }, "communicator.exchange": { "total": 0.01859493499796372, "count": 1, "is_parallel": true, "self": 0.01859493499796372 }, "steps_from_proto": { "total": 0.0013793969847029075, "count": 2, "is_parallel": true, "self": 0.0002855439961422235, "children": { "_process_rank_one_or_two_observation": { "total": 0.001093852988560684, "count": 8, "is_parallel": true, "self": 0.001093852988560684 } } } } } } }, "UnityEnvironment.step": { "total": 34443.215409836106, "count": 3425518, "is_parallel": true, "self": 1718.695632901945, "children": { "UnityEnvironment._generate_step_input": { "total": 1007.526351927736, "count": 3425518, "is_parallel": true, "self": 1007.526351927736 }, "communicator.exchange": { "total": 26877.749937991102, "count": 3425518, "is_parallel": true, "self": 26877.749937991102 }, "steps_from_proto": { "total": 4839.243487015323, "count": 6851036, "is_parallel": true, "self": 929.3002669682319, "children": { "_process_rank_one_or_two_observation": { "total": 3909.943220047091, "count": 27404144, "is_parallel": true, "self": 3909.943220047091 } } } } }, "steps_from_proto": { "total": 0.3616706781758694, "count": 498, "is_parallel": true, "self": 0.06784306035842746, "children": { "_process_rank_one_or_two_observation": { "total": 0.29382761781744193, "count": 1992, "is_parallel": true, "self": 0.29382761781744193 } } } } } } } } }, "trainer_advance": { "total": 15663.146215554269, "count": 3425519, "self": 427.91628870645945, "children": { "process_trajectory": { "total": 6264.885807112951, "count": 3425519, "self": 6228.250475969937, "children": { "RLTrainer._checkpoint": { "total": 36.6353311430139, "count": 100, "self": 36.6353311430139 } } }, "_update_policy": { "total": 8970.344119734858, "count": 2416, "self": 5623.456814095378, "children": { "TorchPOCAOptimizer.update": { "total": 3346.8873056394805, "count": 36240, "self": 3346.8873056394805 } } } } } } }, "trainer_threads": { "total": 6.540212780237198e-07, "count": 1, "self": 6.540212780237198e-07 }, "TrainerController._save_models": { "total": 0.3584142720210366, "count": 1, "self": 0.0016411060350947082, "children": { "RLTrainer._checkpoint": { "total": 0.3567731659859419, "count": 1, "self": 0.3567731659859419 } } } } } } }