{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2777881622314453, "min": 3.277698040008545, "max": 3.2958109378814697, "count": 10 }, "SoccerTwos.Policy.Entropy.sum": { "value": 84435.8203125, "min": 27895.205078125, "max": 105465.953125, "count": 10 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 564.4444444444445, "min": 564.4444444444445, "max": 999.0, "count": 10 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20320.0, "min": 11988.0, "max": 28036.0, "count": 10 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1200.1569488124733, "min": 1199.3839273809324, "max": 1200.1569488124733, "count": 8 }, "SoccerTwos.Self-play.ELO.sum": { "value": 12001.569488124733, "min": 2400.022827873145, "max": 12001.569488124733, "count": 8 }, "SoccerTwos.Step.mean": { "value": 99730.0, "min": 9034.0, "max": 99730.0, "count": 10 }, "SoccerTwos.Step.sum": { "value": 99730.0, "min": 9034.0, "max": 99730.0, "count": 10 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.04222764074802399, "min": -0.0968908816576004, "max": -0.04222764074802399, "count": 10 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.7600975632667542, "min": -1.0727790594100952, "max": -0.5923495888710022, "count": 10 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.04232519119977951, "min": -0.09689081460237503, "max": -0.04232519119977951, "count": 10 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.7618534564971924, "min": -1.0657989978790283, "max": -0.5932878851890564, "count": 10 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 10 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 10 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.24262222978803846, "min": -0.2301230774475978, "max": 0.2968571441514151, "count": 10 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 4.367200136184692, "min": -2.9916000068187714, "max": 4.367200136184692, "count": 10 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.24262222978803846, "min": -0.2301230774475978, "max": 0.2968571441514151, "count": 10 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 4.367200136184692, "min": -2.9916000068187714, "max": 4.367200136184692, "count": 10 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018879526696400716, "min": 0.013216279258206972, "max": 0.018879526696400716, "count": 4 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018879526696400716, "min": 0.013216279258206972, "max": 0.018879526696400716, "count": 4 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0011499579239170998, "min": 0.0011499579239170998, "max": 0.0015964658145094291, "count": 4 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0011499579239170998, "min": 0.0011499579239170998, "max": 0.0015964658145094291, "count": 4 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0011461617114643255, "min": 0.0011461617114643255, "max": 0.001617215361329727, "count": 4 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0011461617114643255, "min": 0.0011461617114643255, "max": 0.001617215361329727, "count": 4 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 4.7166084277999986e-05, "min": 4.7166084277999986e-05, "max": 0.0002341140219619999, "count": 4 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 4.7166084277999986e-05, "min": 4.7166084277999986e-05, "max": 0.0002341140219619999, "count": 4 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.11572199999999998, "min": 0.11572199999999998, "max": 0.17803799999999997, "count": 4 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.11572199999999998, "min": 0.11572199999999998, "max": 0.17803799999999997, "count": 4 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.0007945278000000002, "min": 0.0007945278000000002, "max": 0.0039040961999999998, "count": 4 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.0007945278000000002, "min": 0.0007945278000000002, "max": 0.0039040961999999998, "count": 4 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679918907", "python_version": "3.9.10 (tags/v3.9.10:f2f3f53, Jan 17 2022, 15:14:21) [MSC v.1929 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\Melon\\PycharmProjects\\huggingface\\deep-rl-course\\venv\\Scripts\\mlagents-learn .\\SoccerTwos.yaml --env=.\\training-envs-executables\\SoccerTwos\\ --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1679919060" }, "total": 152.71846240000002, "count": 1, "self": 0.4438656000000094, "children": { "run_training.setup": { "total": 0.0783541000000001, "count": 1, "self": 0.0783541000000001 }, "TrainerController.start_learning": { "total": 152.1962427, "count": 1, "self": 0.09687869999950749, "children": { "TrainerController._reset_env": { "total": 3.0567960000000003, "count": 1, "self": 3.0567960000000003 }, "TrainerController.advance": { "total": 148.9081946000005, "count": 6839, "self": 0.09801829999963729, "children": { "env_step": { "total": 70.89547440000075, "count": 6839, "self": 53.72903609999963, "children": { "SubprocessEnvManager._take_step": { "total": 17.10549290000064, "count": 6839, "self": 0.5554405000015166, "children": { "TorchPolicy.evaluate": { "total": 16.550052399999124, "count": 13610, "self": 16.550052399999124 } } }, "workers": { "total": 0.0609454000004801, "count": 6839, "self": 0.0, "children": { "worker_root": { "total": 148.57212640000017, "count": 6839, "is_parallel": true, "self": 104.62892350000091, "children": { "steps_from_proto": { "total": 0.0011726000000003012, "count": 2, "is_parallel": true, "self": 0.00022330000000003736, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009493000000002638, "count": 8, "is_parallel": true, "self": 0.0009493000000002638 } } }, "UnityEnvironment.step": { "total": 43.94203029999927, "count": 6839, "is_parallel": true, "self": 2.271892799998021, "children": { "UnityEnvironment._generate_step_input": { "total": 1.52210370000032, "count": 6839, "is_parallel": true, "self": 1.52210370000032 }, "communicator.exchange": { "total": 33.784643900000326, "count": 6839, "is_parallel": true, "self": 33.784643900000326 }, "steps_from_proto": { "total": 6.363389900000595, "count": 13678, "is_parallel": true, "self": 1.2525943000015936, "children": { "_process_rank_one_or_two_observation": { "total": 5.110795599999001, "count": 54712, "is_parallel": true, "self": 5.110795599999001 } } } } } } } } } } }, "trainer_advance": { "total": 77.91470190000014, "count": 6839, "self": 0.8459732000001594, "children": { "process_trajectory": { "total": 13.26886649999997, "count": 6839, "self": 13.26886649999997 }, "_update_policy": { "total": 63.79986220000001, "count": 4, "self": 6.665142300000127, "children": { "TorchPOCAOptimizer.update": { "total": 57.13471989999988, "count": 120, "self": 57.13471989999988 } } } } } } }, "trainer_threads": { "total": 4.999999987376214e-07, "count": 1, "self": 4.999999987376214e-07 }, "TrainerController._save_models": { "total": 0.13437289999998825, "count": 1, "self": 0.00656009999997309, "children": { "RLTrainer._checkpoint": { "total": 0.12781280000001516, "count": 1, "self": 0.12781280000001516 } } } } } } }