{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6473673582077026, "min": 1.5890077352523804, "max": 3.2957236766815186, "count": 1095 }, "SoccerTwos.Policy.Entropy.sum": { "value": 32736.484375, "min": 16745.82421875, "max": 105463.15625, "count": 1095 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 51.79347826086956, "min": 41.77777777777778, "max": 999.0, "count": 1095 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19060.0, "min": 3996.0, "max": 29388.0, "count": 1095 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1615.7864995531077, "min": 1197.883595492411, "max": 1637.623285441702, "count": 1088 }, "SoccerTwos.Self-play.ELO.sum": { "value": 297304.7159177718, "min": 2396.017235991407, "max": 378190.26052090013, "count": 1088 }, "SoccerTwos.Step.mean": { "value": 10949984.0, "min": 9896.0, "max": 10949984.0, "count": 1095 }, "SoccerTwos.Step.sum": { "value": 10949984.0, "min": 9896.0, "max": 10949984.0, "count": 1095 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.007928959093987942, "min": -0.11489910632371902, "max": 0.1951962113380432, "count": 1095 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.4668574333190918, "min": -21.291839599609375, "max": 28.10825538635254, "count": 1095 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.007328324485570192, "min": -0.11541522294282913, "max": 0.1981067657470703, "count": 1095 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -1.3557400703430176, "min": -21.77008819580078, "max": 28.527374267578125, "count": 1095 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1095 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1095 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.09063567470859837, "min": -0.42857142857142855, "max": 0.4200916724900405, "count": 1095 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -16.7675998210907, "min": -58.39039981365204, "max": 60.493200838565826, "count": 1095 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.09063567470859837, "min": -0.42857142857142855, "max": 0.4200916724900405, "count": 1095 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -16.7675998210907, "min": -58.39039981365204, "max": 60.493200838565826, "count": 1095 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1095 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1095 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017770308559799258, "min": 0.009530342406166407, "max": 0.024176514243784673, "count": 530 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017770308559799258, "min": 0.009530342406166407, "max": 0.024176514243784673, "count": 530 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1106264352798462, "min": 1.7331508843199117e-05, "max": 0.1259973814090093, "count": 530 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1106264352798462, "min": 1.7331508843199117e-05, "max": 0.1259973814090093, "count": 530 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11188975498080253, "min": 3.2924286657968574e-05, "max": 0.1279420557121436, "count": 530 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11188975498080253, "min": 3.2924286657968574e-05, "max": 0.1279420557121436, "count": 530 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 530 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 530 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 530 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 530 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 530 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 530 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1694371608", "python_version": "3.9.17 (main, Jul 5 2023, 20:47:11) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\adity\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn .\\config\\poca\\SoccerTwos.yaml --env .\\training-envs-executables\\SoccerTwos\\SoccerTwos.exe --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": "2.0.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1694395435" }, "total": 23826.283557400002, "count": 1, "self": 3.566927800002304, "children": { "run_training.setup": { "total": 0.08268549999999975, "count": 1, "self": 0.08268549999999975 }, "TrainerController.start_learning": { "total": 23822.6339441, "count": 1, "self": 15.298786599836603, "children": { "TrainerController._reset_env": { "total": 3.8628853000021097, "count": 55, "self": 3.8628853000021097 }, "TrainerController.advance": { "total": 23803.35610570016, "count": 756822, "self": 15.109223498788197, "children": { "env_step": { "total": 10251.448578899888, "count": 756822, "self": 8056.3651755979445, "children": { "SubprocessEnvManager._take_step": { "total": 2186.216164100905, "count": 756822, "self": 77.24165550066255, "children": { "TorchPolicy.evaluate": { "total": 2108.9745086002426, "count": 1377212, "self": 2108.9745086002426 } } }, "workers": { "total": 8.867239201039041, "count": 756821, "self": 0.0, "children": { "worker_root": { "total": 23800.52825510034, "count": 756821, "is_parallel": true, "self": 17270.801565600057, "children": { "steps_from_proto": { "total": 0.07635939998142538, "count": 110, "is_parallel": true, "self": 0.01607739998333768, "children": { "_process_rank_one_or_two_observation": { "total": 0.0602819999980877, "count": 440, "is_parallel": true, "self": 0.0602819999980877 } } }, "UnityEnvironment.step": { "total": 6529.650330100302, "count": 756821, "is_parallel": true, "self": 304.17063270086237, "children": { "UnityEnvironment._generate_step_input": { "total": 220.52574180139, "count": 756821, "is_parallel": true, "self": 220.52574180139 }, "communicator.exchange": { "total": 5030.338851199453, "count": 756821, "is_parallel": true, "self": 5030.338851199453 }, "steps_from_proto": { "total": 974.6151043985972, "count": 1513642, "is_parallel": true, "self": 208.96600710188818, "children": { "_process_rank_one_or_two_observation": { "total": 765.649097296709, "count": 6054568, "is_parallel": true, "self": 765.649097296709 } } } } } } } } } } }, "trainer_advance": { "total": 13536.798303301484, "count": 756821, "self": 111.43809630138458, "children": { "process_trajectory": { "total": 2352.561482200109, "count": 756821, "self": 2350.280817400112, "children": { "RLTrainer._checkpoint": { "total": 2.2806647999968845, "count": 21, "self": 2.2806647999968845 } } }, "_update_policy": { "total": 11072.798724799992, "count": 530, "self": 1362.297064600054, "children": { "TorchPOCAOptimizer.update": { "total": 9710.501660199938, "count": 15912, "self": 9710.501660199938 } } } } } } }, "trainer_threads": { "total": 7.999988156370819e-07, "count": 1, "self": 7.999988156370819e-07 }, "TrainerController._save_models": { "total": 0.11616570000114734, "count": 1, "self": 0.005518900001334259, "children": { "RLTrainer._checkpoint": { "total": 0.11064679999981308, "count": 1, "self": 0.11064679999981308 } } } } } } }