{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.3212369680404663, "min": 1.3013328313827515, "max": 3.2957303524017334, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 25705.986328125, "min": 14508.73046875, "max": 148683.609375, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 61.6375, "min": 35.666666666666664, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19724.0, "min": 12144.0, "max": 25604.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1741.8944695471516, "min": 1167.3469151065638, "max": 1803.514926967946, "count": 4684 }, "SoccerTwos.Self-play.ELO.sum": { "value": 278703.11512754427, "min": 2334.6938302131275, "max": 413872.8474389917, "count": 4684 }, "SoccerTwos.Step.mean": { "value": 49999969.0, "min": 9822.0, "max": 49999969.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999969.0, "min": 9822.0, "max": 49999969.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.07048972696065903, "min": -0.12329477071762085, "max": 0.18717484176158905, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -11.348845481872559, "min": -24.820899963378906, "max": 23.49005889892578, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.07061980664730072, "min": -0.12268247455358505, "max": 0.1868142932653427, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -11.369789123535156, "min": -25.01974868774414, "max": 25.432092666625977, "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": -0.1187428565499205, "min": -0.6666666666666666, "max": 0.4564640045166016, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -19.1175999045372, "min": -65.70319998264313, "max": 62.20959973335266, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.1187428565499205, "min": -0.6666666666666666, "max": 0.4564640045166016, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -19.1175999045372, "min": -65.70319998264313, "max": 62.20959973335266, "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": 0.017049789781837413, "min": 0.00897990516483939, "max": 0.02741359656987091, "count": 2407 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017049789781837413, "min": 0.00897990516483939, "max": 0.02741359656987091, "count": 2407 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10246860732634862, "min": 6.08721804814157e-09, "max": 0.1270749698082606, "count": 2407 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10246860732634862, "min": 6.08721804814157e-09, "max": 0.1270749698082606, "count": 2407 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.103428815305233, "min": 4.943643183707991e-09, "max": 0.12960378751158713, "count": 2407 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.103428815305233, "min": 4.943643183707991e-09, "max": 0.12960378751158713, "count": 2407 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2407 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2407 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 2407 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 2407 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2407 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2407 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675315222", "python_version": "3.8.16 (default, Jan 17 2023, 16:42:09) \n[Clang 14.0.6 ]", "command_line_arguments": "/Users/jpopham/opt/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1", "numpy_version": "1.21.2", "end_time_seconds": "1675640728" }, "total": 325502.29409919603, "count": 1, "self": 0.49318160803522915, "children": { "run_training.setup": { "total": 0.04113677700000018, "count": 1, "self": 0.04113677700000018 }, "TrainerController.start_learning": { "total": 325501.759780811, "count": 1, "self": 89.94194521935424, "children": { "TrainerController._reset_env": { "total": 8.360289732902144, "count": 250, "self": 8.360289732902144 }, "TrainerController.advance": { "total": 325403.2966888357, "count": 3417035, "self": 96.53357025445439, "children": { "env_step": { "total": 62548.50434311989, "count": 3417035, "self": 51338.242917803254, "children": { "SubprocessEnvManager._take_step": { "total": 11149.20717855026, "count": 3417035, "self": 509.4784541680783, "children": { "TorchPolicy.evaluate": { "total": 10639.728724382181, "count": 6307602, "self": 10639.728724382181 } } }, "workers": { "total": 61.0542467663733, "count": 3417035, "self": 0.0, "children": { "worker_root": { "total": 325332.843797146, "count": 3417035, "is_parallel": true, "self": 283791.91603274876, "children": { "steps_from_proto": { "total": 0.44556669192865517, "count": 500, "is_parallel": true, "self": 0.0896909281218159, "children": { "_process_rank_one_or_two_observation": { "total": 0.3558757638068393, "count": 2000, "is_parallel": true, "self": 0.3558757638068393 } } }, "UnityEnvironment.step": { "total": 41540.48219770532, "count": 3417035, "is_parallel": true, "self": 2074.4453152688657, "children": { "UnityEnvironment._generate_step_input": { "total": 1304.6043743230957, "count": 3417035, "is_parallel": true, "self": 1304.6043743230957 }, "communicator.exchange": { "total": 31639.826660167557, "count": 3417035, "is_parallel": true, "self": 31639.826660167557 }, "steps_from_proto": { "total": 6521.6058479458, "count": 6834070, "is_parallel": true, "self": 1319.7220031650868, "children": { "_process_rank_one_or_two_observation": { "total": 5201.883844780713, "count": 27336280, "is_parallel": true, "self": 5201.883844780713 } } } } } } } } } } }, "trainer_advance": { "total": 262758.2587754614, "count": 3417035, "self": 535.2400868876721, "children": { "process_trajectory": { "total": 19883.80749704296, "count": 3417035, "self": 19863.026011773094, "children": { "RLTrainer._checkpoint": { "total": 20.78148526986297, "count": 100, "self": 20.78148526986297 } } }, "_update_policy": { "total": 242339.21119153075, "count": 2407, "self": 8650.119142643322, "children": { "TorchPOCAOptimizer.update": { "total": 233689.09204888743, "count": 72216, "self": 233689.09204888743 } } } } } } }, "trainer_threads": { "total": 9.249779395759106e-07, "count": 1, "self": 9.249779395759106e-07 }, "TrainerController._save_models": { "total": 0.1608560979948379, "count": 1, "self": 0.0025962459621950984, "children": { "RLTrainer._checkpoint": { "total": 0.1582598520326428, "count": 1, "self": 0.1582598520326428 } } } } } } }