{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7273133993148804, "min": 1.725851058959961, "max": 3.2958192825317383, "count": 800 }, "SoccerTwos.Policy.Entropy.sum": { "value": 33551.3359375, "min": 21626.03125, "max": 105853.578125, "count": 800 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 69.73239436619718, "min": 42.728070175438596, "max": 999.0, "count": 800 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19804.0, "min": 15332.0, "max": 25020.0, "count": 800 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1399.356244407418, "min": 1194.5472810524313, "max": 1470.470844044644, "count": 795 }, "SoccerTwos.Self-play.ELO.sum": { "value": 198708.58670585335, "min": 2390.1173737667473, "max": 327335.3858416885, "count": 795 }, "SoccerTwos.Step.mean": { "value": 7999928.0, "min": 9528.0, "max": 7999928.0, "count": 800 }, "SoccerTwos.Step.sum": { "value": 7999928.0, "min": 9528.0, "max": 7999928.0, "count": 800 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.03234412148594856, "min": -0.0870576947927475, "max": 0.14418645203113556, "count": 800 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.560521125793457, "min": -14.285683631896973, "max": 15.229736328125, "count": 800 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.032624777406454086, "min": -0.08909215033054352, "max": 0.13982641696929932, "count": 800 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -4.600093364715576, "min": -14.719603538513184, "max": 15.053775787353516, "count": 800 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 800 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 800 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.11173191518648297, "min": -0.5473769238361945, "max": 0.3575615378526541, "count": 800 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -15.754200041294098, "min": -51.327200055122375, "max": 48.59420049190521, "count": 800 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.11173191518648297, "min": -0.5473769238361945, "max": 0.3575615378526541, "count": 800 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -15.754200041294098, "min": -51.327200055122375, "max": 48.59420049190521, "count": 800 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 800 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 800 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.02384740280879972, "min": 0.01476079898578367, "max": 0.027096473701143018, "count": 194 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.02384740280879972, "min": 0.01476079898578367, "max": 0.027096473701143018, "count": 194 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.057859680925806366, "min": 0.00041930236269157223, "max": 0.07084110043942929, "count": 194 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.057859680925806366, "min": 0.00041930236269157223, "max": 0.07084110043942929, "count": 194 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.061720517153541245, "min": 0.0004619299531138192, "max": 0.07488205824047327, "count": 194 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.061720517153541245, "min": 0.0004619299531138192, "max": 0.07488205824047327, "count": 194 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003000000000000001, "min": 0.0003000000000000001, "max": 0.0003000000000000001, "count": 194 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003000000000000001, "min": 0.0003000000000000001, "max": 0.0003000000000000001, "count": 194 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.19999999999999993, "min": 0.19999999999999993, "max": 0.19999999999999993, "count": 194 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.19999999999999993, "min": 0.19999999999999993, "max": 0.19999999999999993, "count": 194 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 194 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 194 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675426009", "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\\kinkp\\Envs\\deepRL\\Scripts\\mlagents-learn .\\config\\poca\\SoccerTwos.yaml --env=.\\training-envs-executables\\SoccerTwos.exe --run-id=poca-SoccerTwos --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cu117", "numpy_version": "1.21.2", "end_time_seconds": "1675441767" }, "total": 15757.6121481, "count": 1, "self": 1.6682987999975012, "children": { "run_training.setup": { "total": 0.114309, "count": 1, "self": 0.114309 }, "TrainerController.start_learning": { "total": 15755.829540300001, "count": 1, "self": 12.71333719946415, "children": { "TrainerController._reset_env": { "total": 8.956131299996445, "count": 40, "self": 8.956131299996445 }, "TrainerController.advance": { "total": 15733.829673200542, "count": 546802, "self": 12.774396700076977, "children": { "env_step": { "total": 11263.03935770082, "count": 546802, "self": 6551.67030200055, "children": { "SubprocessEnvManager._take_step": { "total": 4703.843380200144, "count": 546802, "self": 82.80920490023982, "children": { "TorchPolicy.evaluate": { "total": 4621.034175299904, "count": 1006178, "self": 4621.034175299904 } } }, "workers": { "total": 7.5256755001262015, "count": 546802, "self": 0.0, "children": { "worker_root": { "total": 15730.021454000003, "count": 546802, "is_parallel": true, "self": 10486.985418399847, "children": { "steps_from_proto": { "total": 0.07238010000435402, "count": 80, "is_parallel": true, "self": 0.014686999985126903, "children": { "_process_rank_one_or_two_observation": { "total": 0.05769310001922712, "count": 320, "is_parallel": true, "self": 0.05769310001922712 } } }, "UnityEnvironment.step": { "total": 5242.963655500153, "count": 546802, "is_parallel": true, "self": 264.74344670050505, "children": { "UnityEnvironment._generate_step_input": { "total": 203.61528599958382, "count": 546802, "is_parallel": true, "self": 203.61528599958382 }, "communicator.exchange": { "total": 3892.480514900447, "count": 546802, "is_parallel": true, "self": 3892.480514900447 }, "steps_from_proto": { "total": 882.1244078996176, "count": 1093604, "is_parallel": true, "self": 182.61879139899736, "children": { "_process_rank_one_or_two_observation": { "total": 699.5056165006202, "count": 4374416, "is_parallel": true, "self": 699.5056165006202 } } } } } } } } } } }, "trainer_advance": { "total": 4458.015918799644, "count": 546802, "self": 91.38107339960152, "children": { "process_trajectory": { "total": 2204.128150000053, "count": 546802, "self": 2199.2849700000506, "children": { "RLTrainer._checkpoint": { "total": 4.843180000002462, "count": 16, "self": 4.843180000002462 } } }, "_update_policy": { "total": 2162.5066953999894, "count": 194, "self": 1171.7026437999914, "children": { "TorchPOCAOptimizer.update": { "total": 990.804051599998, "count": 11640, "self": 990.804051599998 } } } } } } }, "trainer_threads": { "total": 5.999991117278114e-07, "count": 1, "self": 5.999991117278114e-07 }, "TrainerController._save_models": { "total": 0.33039800000005926, "count": 1, "self": 0.010598900000331923, "children": { "RLTrainer._checkpoint": { "total": 0.31979909999972733, "count": 1, "self": 0.31979909999972733 } } } } } } }