{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9081424474716187, "min": 1.8569482564926147, "max": 3.2957239151000977, "count": 1696 }, "SoccerTwos.Policy.Entropy.sum": { "value": 37857.546875, "min": 12016.7900390625, "max": 162516.515625, "count": 1696 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 102.60416666666667, "min": 71.71014492753623, "max": 999.0, "count": 1696 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19700.0, "min": 16304.0, "max": 23620.0, "count": 1696 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1480.762717569772, "min": 1198.49454273255, "max": 1513.5470795141598, "count": 1052 }, "SoccerTwos.Self-play.ELO.sum": { "value": 142153.2208866981, "min": 2398.4672776531243, "max": 206908.54901103445, "count": 1052 }, "SoccerTwos.Step.mean": { "value": 16959950.0, "min": 9666.0, "max": 16959950.0, "count": 1696 }, "SoccerTwos.Step.sum": { "value": 16959950.0, "min": 9666.0, "max": 16959950.0, "count": 1696 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.042484100908041, "min": -0.1209673285484314, "max": 0.08432997763156891, "count": 1696 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.0784735679626465, "min": -14.758013725280762, "max": 6.972206115722656, "count": 1696 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.04343920946121216, "min": -0.12238497287034988, "max": 0.08571578562259674, "count": 1696 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -4.170164108276367, "min": -14.9309663772583, "max": 7.411514759063721, "count": 1696 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1696 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1696 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.07420416610936324, "min": -0.6232181841676886, "max": 0.43226086575052014, "count": 1696 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -7.123599946498871, "min": -45.98939996957779, "max": 33.95600014925003, "count": 1696 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.07420416610936324, "min": -0.6232181841676886, "max": 0.43226086575052014, "count": 1696 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -7.123599946498871, "min": -45.98939996957779, "max": 33.95600014925003, "count": 1696 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1696 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1696 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015667513432951332, "min": 0.010533121827271922, "max": 0.02685099102091044, "count": 798 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015667513432951332, "min": 0.010533121827271922, "max": 0.02685099102091044, "count": 798 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.07109390248854955, "min": 3.922223305400744e-10, "max": 0.07932198345661164, "count": 798 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.07109390248854955, "min": 3.922223305400744e-10, "max": 0.07932198345661164, "count": 798 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.07201107839743297, "min": 5.209304672811517e-10, "max": 0.0802318458755811, "count": 798 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.07201107839743297, "min": 5.209304672811517e-10, "max": 0.0802318458755811, "count": 798 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 798 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 798 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 798 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 798 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 798 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 798 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1706074009", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\ProgramData\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn .\\config\\poca\\SoccerTwos.yaml --env=.\\SoccerTwos\\SoccerTwos\\SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1706109931" }, "total": 35920.1144813, "count": 1, "self": 1.6802807000203757, "children": { "run_training.setup": { "total": 0.07653599999321159, "count": 1, "self": 0.07653599999321159 }, "TrainerController.start_learning": { "total": 35918.357664599986, "count": 1, "self": 13.76135550509207, "children": { "TrainerController._reset_env": { "total": 6.697737099922961, "count": 85, "self": 6.697737099922961 }, "TrainerController.advance": { "total": 35897.799485494965, "count": 1116096, "self": 14.068040496305912, "children": { "env_step": { "total": 12341.891317795002, "count": 1116096, "self": 9352.766301088806, "children": { "SubprocessEnvManager._take_step": { "total": 2980.022104709584, "count": 1116096, "self": 97.6170436139655, "children": { "TorchPolicy.evaluate": { "total": 2882.4050610956183, "count": 2165450, "self": 2882.4050610956183 } } }, "workers": { "total": 9.10291199661151, "count": 1116096, "self": 0.0, "children": { "worker_root": { "total": 35875.48386889631, "count": 1116096, "is_parallel": true, "self": 28539.939800499997, "children": { "steps_from_proto": { "total": 0.10554500001308043, "count": 170, "is_parallel": true, "self": 0.02169160004996229, "children": { "_process_rank_one_or_two_observation": { "total": 0.08385339996311814, "count": 680, "is_parallel": true, "self": 0.08385339996311814 } } }, "UnityEnvironment.step": { "total": 7335.438523396297, "count": 1116096, "is_parallel": true, "self": 403.66893040476134, "children": { "UnityEnvironment._generate_step_input": { "total": 363.4501111073623, "count": 1116096, "is_parallel": true, "self": 363.4501111073623 }, "communicator.exchange": { "total": 5315.479628394358, "count": 1116096, "is_parallel": true, "self": 5315.479628394358 }, "steps_from_proto": { "total": 1252.8398534898151, "count": 2232192, "is_parallel": true, "self": 251.06104848264658, "children": { "_process_rank_one_or_two_observation": { "total": 1001.7788050071686, "count": 8928768, "is_parallel": true, "self": 1001.7788050071686 } } } } } } } } } } }, "trainer_advance": { "total": 23541.840127203657, "count": 1116096, "self": 137.17520250451344, "children": { "process_trajectory": { "total": 3179.262487899163, "count": 1116096, "self": 3176.297287999201, "children": { "RLTrainer._checkpoint": { "total": 2.96519989996159, "count": 33, "self": 2.96519989996159 } } }, "_update_policy": { "total": 20225.40243679998, "count": 799, "self": 1879.7964162002609, "children": { "TorchPOCAOptimizer.update": { "total": 18345.60602059972, "count": 23963, "self": 18345.60602059972 } } } } } } }, "trainer_threads": { "total": 1.00000761449337e-06, "count": 1, "self": 1.00000761449337e-06 }, "TrainerController._save_models": { "total": 0.09908549999818206, "count": 1, "self": 0.00568639999255538, "children": { "RLTrainer._checkpoint": { "total": 0.09339910000562668, "count": 1, "self": 0.09339910000562668 } } } } } } }