{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6837366819381714, "min": 1.6100215911865234, "max": 3.2957382202148438, "count": 1000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 35291.12109375, "min": 25396.923828125, "max": 142843.59375, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 48.75247524752475, "min": 39.65853658536585, "max": 999.0, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19696.0, "min": 16256.0, "max": 24948.0, "count": 1000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1653.4436225655966, "min": 1203.703637312568, "max": 1709.3558585159587, "count": 993 }, "SoccerTwos.Self-play.ELO.sum": { "value": 333995.6117582505, "min": 2416.958745232774, "max": 398327.08254496066, "count": 993 }, "SoccerTwos.Step.mean": { "value": 9999904.0, "min": 9494.0, "max": 9999904.0, "count": 1000 }, "SoccerTwos.Step.sum": { "value": 9999904.0, "min": 9494.0, "max": 9999904.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.009315802715718746, "min": -0.10659247636795044, "max": 0.28814801573753357, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.8817920684814453, "min": -23.023975372314453, "max": 43.057220458984375, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.010952056385576725, "min": -0.10793488472700119, "max": 0.29318004846572876, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.212315320968628, "min": -23.313934326171875, "max": 41.14143371582031, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.029237625032368274, "min": -0.6390588230946485, "max": 0.7295999974012375, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 5.906000256538391, "min": -78.34259968996048, "max": 94.40279972553253, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.029237625032368274, "min": -0.6390588230946485, "max": 0.7295999974012375, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 5.906000256538391, "min": -78.34259968996048, "max": 94.40279972553253, "count": 1000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015737251300985616, "min": 0.00984176245146955, "max": 0.024220061220694332, "count": 483 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015737251300985616, "min": 0.00984176245146955, "max": 0.024220061220694332, "count": 483 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11703772768378258, "min": 0.001030222350770297, "max": 0.1301369110743205, "count": 483 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11703772768378258, "min": 0.001030222350770297, "max": 0.1301369110743205, "count": 483 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11866468712687492, "min": 0.001040662774660935, "max": 0.13178172906239827, "count": 483 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11866468712687492, "min": 0.001040662774660935, "max": 0.13178172906239827, "count": 483 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 483 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 483 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 483 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 483 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 483 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 483 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1689147513", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/home/polaris/miniconda3/envs/pytorch_env/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --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": "1.11.0+cu113", "numpy_version": "1.21.2", "end_time_seconds": "1689169708" }, "total": 22195.855055613996, "count": 1, "self": 0.3712426720012445, "children": { "run_training.setup": { "total": 0.0166235559991037, "count": 1, "self": 0.0166235559991037 }, "TrainerController.start_learning": { "total": 22195.467189385996, "count": 1, "self": 9.075370749702415, "children": { "TrainerController._reset_env": { "total": 6.365705802978482, "count": 42, "self": 6.365705802978482 }, "TrainerController.advance": { "total": 22179.847765996317, "count": 692544, "self": 9.87363565295891, "children": { "env_step": { "total": 18867.386559155995, "count": 692544, "self": 16610.09937452691, "children": { "SubprocessEnvManager._take_step": { "total": 2251.9333483813716, "count": 692544, "self": 69.83050468589136, "children": { "TorchPolicy.evaluate": { "total": 2182.1028436954803, "count": 1256474, "self": 2182.1028436954803 } } }, "workers": { "total": 5.3538362477120245, "count": 692544, "self": 0.0, "children": { "worker_root": { "total": 22154.65998181563, "count": 692544, "is_parallel": true, "self": 7120.18227396713, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002154409998183837, "count": 2, "is_parallel": true, "self": 0.0004941080005664844, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016603019976173528, "count": 8, "is_parallel": true, "self": 0.0016603019976173528 } } }, "UnityEnvironment.step": { "total": 0.03840278200004832, "count": 1, "is_parallel": true, "self": 0.0006222910014912486, "children": { "UnityEnvironment._generate_step_input": { "total": 0.001035420998960035, "count": 1, "is_parallel": true, "self": 0.001035420998960035 }, "communicator.exchange": { "total": 0.034855812999012414, "count": 1, "is_parallel": true, "self": 0.034855812999012414 }, "steps_from_proto": { "total": 0.001889257000584621, "count": 2, "is_parallel": true, "self": 0.000456012010545237, "children": { "_process_rank_one_or_two_observation": { "total": 0.001433244990039384, "count": 8, "is_parallel": true, "self": 0.001433244990039384 } } } } } } }, "UnityEnvironment.step": { "total": 15034.311949221468, "count": 692543, "is_parallel": true, "self": 868.0310067201681, "children": { "UnityEnvironment._generate_step_input": { "total": 569.2707809006024, "count": 692543, "is_parallel": true, "self": 569.2707809006024 }, "communicator.exchange": { "total": 11005.331696281817, "count": 692543, "is_parallel": true, "self": 11005.331696281817 }, "steps_from_proto": { "total": 2591.6784653188806, "count": 1385086, "is_parallel": true, "self": 477.315260345993, "children": { "_process_rank_one_or_two_observation": { "total": 2114.3632049728876, "count": 5540344, "is_parallel": true, "self": 2114.3632049728876 } } } } }, "steps_from_proto": { "total": 0.16575862703029998, "count": 82, "is_parallel": true, "self": 0.030041002046345966, "children": { "_process_rank_one_or_two_observation": { "total": 0.135717624983954, "count": 328, "is_parallel": true, "self": 0.135717624983954 } } } } } } } } }, "trainer_advance": { "total": 3302.587571187363, "count": 692544, "self": 65.780504120572, "children": { "process_trajectory": { "total": 1382.9761093278103, "count": 692544, "self": 1378.7118953278077, "children": { "RLTrainer._checkpoint": { "total": 4.264214000002539, "count": 20, "self": 4.264214000002539 } } }, "_update_policy": { "total": 1853.830957738981, "count": 483, "self": 1171.9652939338266, "children": { "TorchPOCAOptimizer.update": { "total": 681.8656638051543, "count": 14490, "self": 681.8656638051543 } } } } } } }, "trainer_threads": { "total": 8.200004231184721e-07, "count": 1, "self": 8.200004231184721e-07 }, "TrainerController._save_models": { "total": 0.17834601699723862, "count": 1, "self": 0.0013135970002622344, "children": { "RLTrainer._checkpoint": { "total": 0.1770324199969764, "count": 1, "self": 0.1770324199969764 } } } } } } }