{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9705954790115356, "min": 1.9429445266723633, "max": 3.29573655128479, "count": 905 }, "SoccerTwos.Policy.Entropy.sum": { "value": 38276.84765625, "min": 15261.478515625, "max": 150050.390625, "count": 905 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 72.07246376811594, "min": 40.96638655462185, "max": 999.0, "count": 905 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19892.0, "min": 10964.0, "max": 27156.0, "count": 905 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1472.3354228406217, "min": 1179.6452773600556, "max": 1480.3466910984039, "count": 637 }, "SoccerTwos.Self-play.ELO.sum": { "value": 203182.2883520058, "min": 2359.2905547201112, "max": 316631.07014630514, "count": 637 }, "SoccerTwos.Step.mean": { "value": 9049933.0, "min": 9294.0, "max": 9049933.0, "count": 905 }, "SoccerTwos.Step.sum": { "value": 9049933.0, "min": 9294.0, "max": 9049933.0, "count": 905 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.011109698563814163, "min": -0.1073542907834053, "max": 0.17955440282821655, "count": 905 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.533138394355774, "min": -14.61380386352539, "max": 22.739479064941406, "count": 905 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.01597021333873272, "min": -0.11050280928611755, "max": 0.17454886436462402, "count": 905 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.2038893699645996, "min": -15.085655212402344, "max": 22.857147216796875, "count": 905 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 905 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 905 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.07222608682038127, "min": -0.6428571428571429, "max": 0.4416571429797581, "count": 905 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -9.967199981212616, "min": -60.1353999376297, "max": 72.32640016078949, "count": 905 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.07222608682038127, "min": -0.6428571428571429, "max": 0.4416571429797581, "count": 905 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -9.967199981212616, "min": -60.1353999376297, "max": 72.32640016078949, "count": 905 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 905 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 905 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.012020615170088907, "min": 0.009754687480259842, "max": 0.024939382448792458, "count": 427 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.012020615170088907, "min": 0.009754687480259842, "max": 0.024939382448792458, "count": 427 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09323971420526504, "min": 5.635003266964607e-08, "max": 0.10726530998945236, "count": 427 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09323971420526504, "min": 5.635003266964607e-08, "max": 0.10726530998945236, "count": 427 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09491016988952955, "min": 5.255707774172909e-08, "max": 0.10973455235362053, "count": 427 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09491016988952955, "min": 5.255707774172909e-08, "max": 0.10973455235362053, "count": 427 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 427 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 427 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 427 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 427 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 427 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 427 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1682315691", "python_version": "3.9.16 (main, Dec 7 2022, 01:12:08) \n[GCC 11.3.0]", "command_line_arguments": "/home/nikita/.venvs/py39/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos7 --no-graphics", "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": "1682349098" }, "total": 33406.74239535, "count": 1, "self": 0.005059529983554967, "children": { "run_training.setup": { "total": 0.023993826005607843, "count": 1, "self": 0.023993826005607843 }, "TrainerController.start_learning": { "total": 33406.71334199401, "count": 1, "self": 13.38581212569261, "children": { "TrainerController._reset_env": { "total": 3.4810442159650847, "count": 46, "self": 3.4810442159650847 }, "TrainerController.advance": { "total": 33389.59595913235, "count": 603521, "self": 14.279038802575087, "children": { "env_step": { "total": 11976.792494187801, "count": 603521, "self": 9999.759178769964, "children": { "SubprocessEnvManager._take_step": { "total": 1968.1808704329014, "count": 603521, "self": 93.03351615325664, "children": { "TorchPolicy.evaluate": { "total": 1875.1473542796448, "count": 1156852, "self": 1875.1473542796448 } } }, "workers": { "total": 8.852444984935573, "count": 603521, "self": 0.0, "children": { "worker_root": { "total": 33340.9093865693, "count": 603521, "is_parallel": true, "self": 24935.615906424966, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025034940044861287, "count": 2, "is_parallel": true, "self": 0.0007033770234556869, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018001169810304418, "count": 8, "is_parallel": true, "self": 0.0018001169810304418 } } }, "UnityEnvironment.step": { "total": 0.02882568200584501, "count": 1, "is_parallel": true, "self": 0.000567786002648063, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004294280079193413, "count": 1, "is_parallel": true, "self": 0.0004294280079193413 }, "communicator.exchange": { "total": 0.026051287990412675, "count": 1, "is_parallel": true, "self": 0.026051287990412675 }, "steps_from_proto": { "total": 0.001777180004864931, "count": 2, "is_parallel": true, "self": 0.0003852460067719221, "children": { "_process_rank_one_or_two_observation": { "total": 0.001391933998093009, "count": 8, "is_parallel": true, "self": 0.001391933998093009 } } } } } } }, "UnityEnvironment.step": { "total": 8405.213898981267, "count": 603520, "is_parallel": true, "self": 540.058660706869, "children": { "UnityEnvironment._generate_step_input": { "total": 391.03464867196453, "count": 603520, "is_parallel": true, "self": 391.03464867196453 }, "communicator.exchange": { "total": 5916.412721045286, "count": 603520, "is_parallel": true, "self": 5916.412721045286 }, "steps_from_proto": { "total": 1557.7078685571469, "count": 1207040, "is_parallel": true, "self": 289.1741179211822, "children": { "_process_rank_one_or_two_observation": { "total": 1268.5337506359647, "count": 4828160, "is_parallel": true, "self": 1268.5337506359647 } } } } }, "steps_from_proto": { "total": 0.07958116306690499, "count": 90, "is_parallel": true, "self": 0.01610665486077778, "children": { "_process_rank_one_or_two_observation": { "total": 0.06347450820612721, "count": 360, "is_parallel": true, "self": 0.06347450820612721 } } } } } } } } }, "trainer_advance": { "total": 21398.524426141972, "count": 603521, "self": 96.16470503159508, "children": { "process_trajectory": { "total": 2169.391593826178, "count": 603521, "self": 2164.8242866242217, "children": { "RLTrainer._checkpoint": { "total": 4.567307201956282, "count": 18, "self": 4.567307201956282 } } }, "_update_policy": { "total": 19132.9681272842, "count": 428, "self": 1336.0912950159836, "children": { "TorchPOCAOptimizer.update": { "total": 17796.876832268215, "count": 12842, "self": 17796.876832268215 } } } } } } }, "trainer_threads": { "total": 1.4789984561502934e-06, "count": 1, "self": 1.4789984561502934e-06 }, "TrainerController._save_models": { "total": 0.25052504100312945, "count": 1, "self": 0.0017778490000637248, "children": { "RLTrainer._checkpoint": { "total": 0.24874719200306572, "count": 1, "self": 0.24874719200306572 } } } } } } }