{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.295698404312134, "min": 3.295698404312134, "max": 3.295698404312134, "count": 1 }, "SoccerTwos.Policy.Entropy.sum": { "value": 105462.3515625, "min": 105462.3515625, "max": 105462.3515625, "count": 1 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 510.3, "min": 510.3, "max": 510.3, "count": 1 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20412.0, "min": 20412.0, "max": 20412.0, "count": 1 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1198.6983882804839, "min": 1198.6983882804839, "max": 1198.6983882804839, "count": 1 }, "SoccerTwos.Self-play.ELO.sum": { "value": 16781.777435926775, "min": 16781.777435926775, "max": 16781.777435926775, "count": 1 }, "SoccerTwos.Step.mean": { "value": 9226.0, "min": 9226.0, "max": 9226.0, "count": 1 }, "SoccerTwos.Step.sum": { "value": 9226.0, "min": 9226.0, "max": 9226.0, "count": 1 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.06891250610351562, "min": 0.06891250610351562, "max": 0.06891250610351562, "count": 1 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 1.3093376159667969, "min": 1.3093376159667969, "max": 1.3093376159667969, "count": 1 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.06894762814044952, "min": 0.06894762814044952, "max": 0.06894762814044952, "count": 1 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.3100049495697021, "min": 1.3100049495697021, "max": 1.3100049495697021, "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": -0.35837894991824504, "min": -0.35837894991824504, "max": -0.35837894991824504, "count": 1 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -6.809200048446655, "min": -6.809200048446655, "max": -6.809200048446655, "count": 1 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.35837894991824504, "min": -0.35837894991824504, "max": -0.35837894991824504, "count": 1 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -6.809200048446655, "min": -6.809200048446655, "max": -6.809200048446655, "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": "1703231750", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/home/operario/anaconda3/envs/mlagents/bin/mlagents-learn SoccerTwos.yaml --run-id=Soccer", "mlagents_version": "1.0.0", "mlagents_envs_version": "1.0.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.21.2", "end_time_seconds": "1703231769" }, "total": 18.828908071000114, "count": 1, "self": 0.0038752350001232116, "children": { "run_training.setup": { "total": 0.011371966999831784, "count": 1, "self": 0.011371966999831784 }, "TrainerController.start_learning": { "total": 18.81366086900016, "count": 1, "self": 0.012658913007271622, "children": { "TrainerController._reset_env": { "total": 6.519004453999969, "count": 1, "self": 6.519004453999969 }, "TrainerController.advance": { "total": 12.224295807993258, "count": 1005, "self": 0.012754022996887215, "children": { "env_step": { "total": 11.209075801001745, "count": 1005, "self": 9.642230745010238, "children": { "SubprocessEnvManager._take_step": { "total": 1.558794789998501, "count": 1005, "self": 0.07714688002579351, "children": { "TorchPolicy.evaluate": { "total": 1.4816479099727076, "count": 2000, "self": 1.4816479099727076 } } }, "workers": { "total": 0.008050265993006178, "count": 1005, "self": 0.0, "children": { "worker_root": { "total": 18.191109271007917, "count": 1005, "is_parallel": true, "self": 9.978554264029299, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016817149999042158, "count": 2, "is_parallel": true, "self": 0.0005443020008897292, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011374129990144866, "count": 8, "is_parallel": true, "self": 0.0011374129990144866 } } }, "UnityEnvironment.step": { "total": 0.0247552379996705, "count": 1, "is_parallel": true, "self": 0.0005118170001878752, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006443479996960377, "count": 1, "is_parallel": true, "self": 0.0006443479996960377 }, "communicator.exchange": { "total": 0.02191044499977579, "count": 1, "is_parallel": true, "self": 0.02191044499977579 }, "steps_from_proto": { "total": 0.0016886280000107945, "count": 2, "is_parallel": true, "self": 0.0003622190006353776, "children": { "_process_rank_one_or_two_observation": { "total": 0.001326408999375417, "count": 8, "is_parallel": true, "self": 0.001326408999375417 } } } } } } }, "UnityEnvironment.step": { "total": 8.212555006978619, "count": 1004, "is_parallel": true, "self": 0.3458426219631292, "children": { "UnityEnvironment._generate_step_input": { "total": 0.20143538798947702, "count": 1004, "is_parallel": true, "self": 0.20143538798947702 }, "communicator.exchange": { "total": 6.67237666901201, "count": 1004, "is_parallel": true, "self": 6.67237666901201 }, "steps_from_proto": { "total": 0.9929003280140023, "count": 2008, "is_parallel": true, "self": 0.18314762201407575, "children": { "_process_rank_one_or_two_observation": { "total": 0.8097527059999265, "count": 8032, "is_parallel": true, "self": 0.8097527059999265 } } } } } } } } } } }, "trainer_advance": { "total": 1.0024659839946253, "count": 1005, "self": 0.05726587000845029, "children": { "process_trajectory": { "total": 0.945200113986175, "count": 1005, "self": 0.945200113986175 } } } } }, "trainer_threads": { "total": 6.089994712965563e-07, "count": 1, "self": 6.089994712965563e-07 }, "TrainerController._save_models": { "total": 0.05770108500018978, "count": 1, "self": 0.0008857650000209105, "children": { "RLTrainer._checkpoint": { "total": 0.05681532000016887, "count": 1, "self": 0.05681532000016887 } } } } } } }