{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7681738138198853, "min": 1.7681738138198853, "max": 3.295642614364624, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 34514.75390625, "min": 24271.265625, "max": 120132.578125, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 43.6875, "min": 38.338582677165356, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19572.0, "min": 16328.0, "max": 23836.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1589.0166094459983, "min": 1199.9138816860068, "max": 1589.0166094459983, "count": 484 }, "SoccerTwos.Self-play.ELO.sum": { "value": 355939.7205159036, "min": 2401.8191495173396, "max": 397295.1680901315, "count": 484 }, "SoccerTwos.Step.mean": { "value": 4999996.0, "min": 9394.0, "max": 4999996.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999996.0, "min": 9394.0, "max": 4999996.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.01623365469276905, "min": -0.10175494849681854, "max": 0.23288288712501526, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 3.6201047897338867, "min": -24.01416778564453, "max": 36.43886947631836, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.014008472673594952, "min": -0.10036388039588928, "max": 0.23254656791687012, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 3.123889446258545, "min": -23.685874938964844, "max": 36.923553466796875, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.009366814598374303, "min": -0.6435999989509582, "max": 0.5506250005215406, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.0887996554374695, "min": -54.90400004386902, "max": 61.47480022907257, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.009366814598374303, "min": -0.6435999989509582, "max": 0.5506250005215406, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.0887996554374695, "min": -54.90400004386902, "max": 61.47480022907257, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.011787139686445396, "min": 0.011787139686445396, "max": 0.023223802206727366, "count": 240 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.011787139686445396, "min": 0.011787139686445396, "max": 0.023223802206727366, "count": 240 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11468195418516795, "min": 0.0005849755194503814, "max": 0.12465251013636588, "count": 240 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11468195418516795, "min": 0.0005849755194503814, "max": 0.12465251013636588, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11618416383862495, "min": 0.0005940931145839083, "max": 0.1268347553908825, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11618416383862495, "min": 0.0005940931145839083, "max": 0.1268347553908825, "count": 240 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 240 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 240 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1687269109", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./SoccerTwos.x86_64 --run-id=SoccerTwos --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+cu113", "numpy_version": "1.21.2", "end_time_seconds": "1687277145" }, "total": 8035.639042728, "count": 1, "self": 3.015388246000839, "children": { "run_training.setup": { "total": 0.023708859000066695, "count": 1, "self": 0.023708859000066695 }, "TrainerController.start_learning": { "total": 8032.599945622999, "count": 1, "self": 6.141547434827771, "children": { "TrainerController._reset_env": { "total": 52.750931389001835, "count": 25, "self": 52.750931389001835 }, "TrainerController.advance": { "total": 7973.344187329171, "count": 342811, "self": 5.679056609867075, "children": { "env_step": { "total": 5922.987007657171, "count": 342811, "self": 3799.3641949011208, "children": { "SubprocessEnvManager._take_step": { "total": 2119.6661500220825, "count": 342811, "self": 31.738625064273037, "children": { "TorchPolicy.evaluate": { "total": 2087.9275249578095, "count": 631092, "self": 2087.9275249578095 } } }, "workers": { "total": 3.9566627339673914, "count": 342811, "self": 0.0, "children": { "worker_root": { "total": 8020.359469669038, "count": 342811, "is_parallel": true, "self": 4831.638454978029, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018271140000933883, "count": 2, "is_parallel": true, "self": 0.0005396119998977156, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012875020001956727, "count": 8, "is_parallel": true, "self": 0.0012875020001956727 } } }, "UnityEnvironment.step": { "total": 0.020950649000042176, "count": 1, "is_parallel": true, "self": 0.00032619800003885757, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005561049999869283, "count": 1, "is_parallel": true, "self": 0.0005561049999869283 }, "communicator.exchange": { "total": 0.019138429999998152, "count": 1, "is_parallel": true, "self": 0.019138429999998152 }, "steps_from_proto": { "total": 0.0009299160000182383, "count": 2, "is_parallel": true, "self": 0.00021523800012346328, "children": { "_process_rank_one_or_two_observation": { "total": 0.000714677999894775, "count": 8, "is_parallel": true, "self": 0.000714677999894775 } } } } } } }, "UnityEnvironment.step": { "total": 3188.6982417270074, "count": 342810, "is_parallel": true, "self": 96.01140620154001, "children": { "UnityEnvironment._generate_step_input": { "total": 61.96973046557616, "count": 342810, "is_parallel": true, "self": 61.96973046557616 }, "communicator.exchange": { "total": 2750.33833704199, "count": 342810, "is_parallel": true, "self": 2750.33833704199 }, "steps_from_proto": { "total": 280.3787680179014, "count": 685620, "is_parallel": true, "self": 59.436001587206874, "children": { "_process_rank_one_or_two_observation": { "total": 220.94276643069452, "count": 2742480, "is_parallel": true, "self": 220.94276643069452 } } } } }, "steps_from_proto": { "total": 0.022772964001433138, "count": 48, "is_parallel": true, "self": 0.004926209004224802, "children": { "_process_rank_one_or_two_observation": { "total": 0.017846754997208336, "count": 192, "is_parallel": true, "self": 0.017846754997208336 } } } } } } } } }, "trainer_advance": { "total": 2044.6781230621332, "count": 342811, "self": 58.14423320692754, "children": { "process_trajectory": { "total": 1024.4031813551987, "count": 342811, "self": 1021.1212438951984, "children": { "RLTrainer._checkpoint": { "total": 3.2819374600003357, "count": 10, "self": 3.2819374600003357 } } }, "_update_policy": { "total": 962.1307085000069, "count": 240, "self": 505.9994802299823, "children": { "TorchPOCAOptimizer.update": { "total": 456.1312282700246, "count": 7200, "self": 456.1312282700246 } } } } } } }, "trainer_threads": { "total": 5.259989848127589e-07, "count": 1, "self": 5.259989848127589e-07 }, "TrainerController._save_models": { "total": 0.3632789439998305, "count": 1, "self": 0.05790008499934629, "children": { "RLTrainer._checkpoint": { "total": 0.3053788590004842, "count": 1, "self": 0.3053788590004842 } } } } } } }