{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.626590609550476, "min": 1.570356845855713, "max": 3.295746326446533, "count": 880 }, "SoccerTwos.Policy.Entropy.sum": { "value": 29877.216796875, "min": 29877.216796875, "max": 126865.7109375, "count": 880 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 59.82716049382716, "min": 35.52238805970149, "max": 999.0, "count": 880 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19384.0, "min": 11764.0, "max": 29016.0, "count": 880 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1600.1734929871834, "min": 1183.7241625259917, "max": 1618.019371793397, "count": 874 }, "SoccerTwos.Self-play.ELO.sum": { "value": 259228.1058639237, "min": 2373.4453551609795, "max": 420834.5504338483, "count": 874 }, "SoccerTwos.Step.mean": { "value": 8819987.0, "min": 29758.0, "max": 8819987.0, "count": 880 }, "SoccerTwos.Step.sum": { "value": 8819987.0, "min": 29758.0, "max": 8819987.0, "count": 880 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.01727524772286415, "min": -0.13113708794116974, "max": 0.1816548854112625, "count": 880 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.8158655166625977, "min": -28.18567657470703, "max": 31.650232315063477, "count": 880 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.02033625729382038, "min": -0.12809991836547852, "max": 0.17683276534080505, "count": 880 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.314809799194336, "min": -28.279970169067383, "max": 31.39327621459961, "count": 880 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 880 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 880 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.03291533695408172, "min": -0.5228307705659133, "max": 0.6182486479346817, "count": 880 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 5.36519992351532, "min": -62.39780002832413, "max": 71.58879971504211, "count": 880 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.03291533695408172, "min": -0.5228307705659133, "max": 0.6182486479346817, "count": 880 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 5.36519992351532, "min": -62.39780002832413, "max": 71.58879971504211, "count": 880 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 880 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 880 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.019107498485391262, "min": 0.011222539778100327, "max": 0.025776354467961938, "count": 426 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019107498485391262, "min": 0.011222539778100327, "max": 0.025776354467961938, "count": 426 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11075551907221476, "min": 0.0007812240711549142, "max": 0.1363170529405276, "count": 426 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11075551907221476, "min": 0.0007812240711549142, "max": 0.1363170529405276, "count": 426 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11256632059812546, "min": 0.0007885153046421086, "max": 0.13938360263903934, "count": 426 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11256632059812546, "min": 0.0007885153046421086, "max": 0.13938360263903934, "count": 426 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 426 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 426 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 426 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 426 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 426 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 426 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675365125", "python_version": "3.8.16 | packaged by conda-forge | (default, Feb 1 2023, 16:01:55) \n[GCC 11.3.0]", "command_line_arguments": "/home/mari/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1675411523" }, "total": 46397.57168548368, "count": 1, "self": 0.054505739361047745, "children": { "run_training.setup": { "total": 0.01516575925052166, "count": 1, "self": 0.01516575925052166 }, "TrainerController.start_learning": { "total": 46397.50201398507, "count": 1, "self": 18.840512711554766, "children": { "TrainerController._reset_env": { "total": 2.2461910862475634, "count": 36, "self": 2.2461910862475634 }, "TrainerController.advance": { "total": 46376.044676734135, "count": 615216, "self": 17.116184206679463, "children": { "env_step": { "total": 16517.073874624446, "count": 615216, "self": 12563.193481325172, "children": { "SubprocessEnvManager._take_step": { "total": 3942.6622877884656, "count": 615216, "self": 100.87639274541289, "children": { "TorchPolicy.evaluate": { "total": 3841.7858950430527, "count": 1106532, "self": 3841.7858950430527 } } }, "workers": { "total": 11.218105510808527, "count": 615215, "self": 0.0, "children": { "worker_root": { "total": 46371.050302866846, "count": 615215, "is_parallel": true, "self": 36244.40890670288, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00449126772582531, "count": 2, "is_parallel": true, "self": 0.0009222114458680153, "children": { "_process_rank_one_or_two_observation": { "total": 0.0035690562799572945, "count": 8, "is_parallel": true, "self": 0.0035690562799572945 } } }, "UnityEnvironment.step": { "total": 0.03746625315397978, "count": 1, "is_parallel": true, "self": 0.0010318318381905556, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0010815411806106567, "count": 1, "is_parallel": true, "self": 0.0010815411806106567 }, "communicator.exchange": { "total": 0.032170078717172146, "count": 1, "is_parallel": true, "self": 0.032170078717172146 }, "steps_from_proto": { "total": 0.00318280141800642, "count": 2, "is_parallel": true, "self": 0.0007063746452331543, "children": { "_process_rank_one_or_two_observation": { "total": 0.002476426772773266, "count": 8, "is_parallel": true, "self": 0.002476426772773266 } } } } } } }, "UnityEnvironment.step": { "total": 10126.482435171492, "count": 615214, "is_parallel": true, "self": 568.7853545155376, "children": { "UnityEnvironment._generate_step_input": { "total": 565.3862631097436, "count": 615214, "is_parallel": true, "self": 565.3862631097436 }, "communicator.exchange": { "total": 7133.5254578739405, "count": 615214, "is_parallel": true, "self": 7133.5254578739405 }, "steps_from_proto": { "total": 1858.7853596722707, "count": 1230428, "is_parallel": true, "self": 370.55482043512166, "children": { "_process_rank_one_or_two_observation": { "total": 1488.230539237149, "count": 4921712, "is_parallel": true, "self": 1488.230539237149 } } } } }, "steps_from_proto": { "total": 0.15896099247038364, "count": 70, "is_parallel": true, "self": 0.030034859664738178, "children": { "_process_rank_one_or_two_observation": { "total": 0.12892613280564547, "count": 280, "is_parallel": true, "self": 0.12892613280564547 } } } } } } } } }, "trainer_advance": { "total": 29841.85461790301, "count": 615215, "self": 118.7299439534545, "children": { "process_trajectory": { "total": 5547.163462118246, "count": 615215, "self": 5540.763096098788, "children": { "RLTrainer._checkpoint": { "total": 6.400366019457579, "count": 17, "self": 6.400366019457579 } } }, "_update_policy": { "total": 24175.96121183131, "count": 426, "self": 2461.974079676904, "children": { "TorchPOCAOptimizer.update": { "total": 21713.987132154405, "count": 12780, "self": 21713.987132154405 } } } } } } }, "trainer_threads": { "total": 1.8849968910217285e-06, "count": 1, "self": 1.8849968910217285e-06 }, "TrainerController._save_models": { "total": 0.370631568133831, "count": 1, "self": 0.002726670354604721, "children": { "RLTrainer._checkpoint": { "total": 0.3679048977792263, "count": 1, "self": 0.3679048977792263 } } } } } } }