{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2957217693328857, "min": 3.2957217693328857, "max": 3.2957217693328857, "count": 1 }, "SoccerTwos.Policy.Entropy.sum": { "value": 105463.09375, "min": 105463.09375, "max": 105463.09375, "count": 1 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 756.625, "min": 756.625, "max": 756.625, "count": 1 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 24212.0, "min": 24212.0, "max": 24212.0, "count": 1 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1202.234955112457, "min": 1202.234955112457, "max": 1202.234955112457, "count": 1 }, "SoccerTwos.Self-play.ELO.sum": { "value": 9617.879640899657, "min": 9617.879640899657, "max": 9617.879640899657, "count": 1 }, "SoccerTwos.Step.mean": { "value": 9122.0, "min": 9122.0, "max": 9122.0, "count": 1 }, "SoccerTwos.Step.sum": { "value": 9122.0, "min": 9122.0, "max": 9122.0, "count": 1 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.10343889892101288, "min": -0.10343889892101288, "max": -0.10343889892101288, "count": 1 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.3447057008743286, "min": -1.3447057008743286, "max": -1.3447057008743286, "count": 1 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.10348843038082123, "min": -0.10348843038082123, "max": -0.10348843038082123, "count": 1 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -1.3453495502471924, "min": -1.3453495502471924, "max": -1.3453495502471924, "count": 1 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.29861539143782395, "min": 0.29861539143782395, "max": 0.29861539143782395, "count": 1 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 3.8820000886917114, "min": 3.8820000886917114, "max": 3.8820000886917114, "count": 1 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.29861539143782395, "min": 0.29861539143782395, "max": 0.29861539143782395, "count": 1 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 3.8820000886917114, "min": 3.8820000886917114, "max": 3.8820000886917114, "count": 1 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1694074756", "python_version": "3.9.18 (main, Aug 24 2023, 21:20:15) \n[Clang 14.0.0 (clang-1400.0.29.202)]", "command_line_arguments": "/Users/cikriibr/projects/learning/deepRL/env/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos2 --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", "numpy_version": "1.21.2", "end_time_seconds": "1694074809" }, "total": 53.066556375000005, "count": 1, "self": 0.28110941700000325, "children": { "run_training.setup": { "total": 0.030046958000000012, "count": 1, "self": 0.030046958000000012 }, "TrainerController.start_learning": { "total": 52.7554, "count": 1, "self": 0.012068182999939836, "children": { "TrainerController._reset_env": { "total": 1.694077167, "count": 1, "self": 1.694077167 }, "TrainerController.advance": { "total": 50.90541894100006, "count": 1004, "self": 0.01212669900018426, "children": { "env_step": { "total": 49.66604145199994, "count": 1004, "self": 48.0027904279998, "children": { "SubprocessEnvManager._take_step": { "total": 1.6545578100000276, "count": 1004, "self": 0.045994196000025855, "children": { "TorchPolicy.evaluate": { "total": 1.6085636140000017, "count": 2000, "self": 1.6085636140000017 } } }, "workers": { "total": 0.008693214000111027, "count": 1004, "self": 0.0, "children": { "worker_root": { "total": 50.13892670999993, "count": 1004, "is_parallel": true, "self": 3.555963091999992, "children": { "steps_from_proto": { "total": 0.0014188749999999306, "count": 2, "is_parallel": true, "self": 0.0002449999999993846, "children": { "_process_rank_one_or_two_observation": { "total": 0.001173875000000546, "count": 8, "is_parallel": true, "self": 0.001173875000000546 } } }, "UnityEnvironment.step": { "total": 46.58154474299994, "count": 1004, "is_parallel": true, "self": 0.12588737199990874, "children": { "UnityEnvironment._generate_step_input": { "total": 0.7080112539999688, "count": 1004, "is_parallel": true, "self": 0.7080112539999688 }, "communicator.exchange": { "total": 44.389486800000086, "count": 1004, "is_parallel": true, "self": 44.389486800000086 }, "steps_from_proto": { "total": 1.3581593169999737, "count": 2008, "is_parallel": true, "self": 0.19286627000009937, "children": { "_process_rank_one_or_two_observation": { "total": 1.1652930469998743, "count": 8032, "is_parallel": true, "self": 1.1652930469998743 } } } } } } } } } } }, "trainer_advance": { "total": 1.227250789999938, "count": 1004, "self": 0.0674553749999598, "children": { "process_trajectory": { "total": 1.1597954149999783, "count": 1004, "self": 1.1597954149999783 } } } } }, "trainer_threads": { "total": 4.170000025283116e-07, "count": 1, "self": 4.170000025283116e-07 }, "TrainerController._save_models": { "total": 0.14383529199999856, "count": 1, "self": 0.0480642919999994, "children": { "RLTrainer._checkpoint": { "total": 0.09577099999999916, "count": 1, "self": 0.09577099999999916 } } } } } } }