{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.285998582839966, "min": 3.2672150135040283, "max": 3.2957563400268555, "count": 50 }, "SoccerTwos.Policy.Entropy.sum": { "value": 88327.640625, "min": 27892.60546875, "max": 117716.6015625, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 417.3333333333333, "max": 999.0, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 15396.0, "max": 26208.0, "count": 50 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1184.0528148766145, "min": 1183.0530441429582, "max": 1199.4660672222722, "count": 43 }, "SoccerTwos.Self-play.ELO.sum": { "value": 11840.528148766145, "min": 2370.961219735413, "max": 16792.52494111181, "count": 43 }, "SoccerTwos.Step.mean": { "value": 499418.0, "min": 9126.0, "max": 499418.0, "count": 50 }, "SoccerTwos.Step.sum": { "value": 499418.0, "min": 9126.0, "max": 499418.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.013640234246850014, "min": -0.08858286589384079, "max": -0.004238549619913101, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.13640233874320984, "min": -1.5944916009902954, "max": -0.04238549619913101, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.013837648555636406, "min": -0.08846139162778854, "max": -0.005063777323812246, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.13837648928165436, "min": -1.5922682285308838, "max": -0.05234326422214508, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.014880000054836274, "min": -0.5489600010216236, "max": 0.21036922931671143, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.14880000054836273, "min": -8.234400015324354, "max": 2.7347999811172485, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.014880000054836274, "min": -0.5489600010216236, "max": 0.21036922931671143, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.14880000054836273, "min": -8.234400015324354, "max": 2.7347999811172485, "count": 50 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.02153375749476254, "min": 0.010410184945794754, "max": 0.024094702501315624, "count": 23 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.02153375749476254, "min": 0.010410184945794754, "max": 0.024094702501315624, "count": 23 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0013284804299473763, "min": 0.00024111115490086377, "max": 0.007237169751897454, "count": 23 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0013284804299473763, "min": 0.00024111115490086377, "max": 0.007237169751897454, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0013349808636121453, "min": 0.00024450847558910027, "max": 0.006368812778964639, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0013349808636121453, "min": 0.00024450847558910027, "max": 0.006368812778964639, "count": 23 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 23 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 23 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.2, "min": 0.2, "max": 0.2, "count": 23 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.2, "min": 0.2, "max": 0.2, "count": 23 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.004999999999999999, "min": 0.004999999999999999, "max": 0.004999999999999999, "count": 23 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.004999999999999999, "min": 0.004999999999999999, "max": 0.004999999999999999, "count": 23 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1731697797", "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:\\Users\\cafer\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1731698858" }, "total": 1061.392763200216, "count": 1, "self": 1.5768440002575517, "children": { "run_training.setup": { "total": 0.13145879982039332, "count": 1, "self": 0.13145879982039332 }, "TrainerController.start_learning": { "total": 1059.684460400138, "count": 1, "self": 0.9244102146476507, "children": { "TrainerController._reset_env": { "total": 6.319037399720401, "count": 3, "self": 6.319037399720401 }, "TrainerController.advance": { "total": 1052.2923052855767, "count": 33175, "self": 0.9748070519417524, "children": { "env_step": { "total": 733.6119241900742, "count": 33175, "self": 581.3141815788113, "children": { "SubprocessEnvManager._take_step": { "total": 151.68048197589815, "count": 33175, "self": 7.193980729673058, "children": { "TorchPolicy.evaluate": { "total": 144.4865012462251, "count": 65900, "self": 144.4865012462251 } } }, "workers": { "total": 0.6172606353648007, "count": 33175, "self": 0.0, "children": { "worker_root": { "total": 1053.0294138188474, "count": 33175, "is_parallel": true, "self": 601.3654705402441, "children": { "steps_from_proto": { "total": 0.007623199839144945, "count": 6, "is_parallel": true, "self": 0.0014385012909770012, "children": { "_process_rank_one_or_two_observation": { "total": 0.006184698548167944, "count": 24, "is_parallel": true, "self": 0.006184698548167944 } } }, "UnityEnvironment.step": { "total": 451.6563200787641, "count": 33175, "is_parallel": true, "self": 23.378545485436916, "children": { "UnityEnvironment._generate_step_input": { "total": 29.492051992099732, "count": 33175, "is_parallel": true, "self": 29.492051992099732 }, "communicator.exchange": { "total": 326.7904810588807, "count": 33175, "is_parallel": true, "self": 326.7904810588807 }, "steps_from_proto": { "total": 71.99524154234678, "count": 66350, "is_parallel": true, "self": 13.266702304594219, "children": { "_process_rank_one_or_two_observation": { "total": 58.72853923775256, "count": 265400, "is_parallel": true, "self": 58.72853923775256 } } } } } } } } } } }, "trainer_advance": { "total": 317.7055740435608, "count": 33175, "self": 7.006266000214964, "children": { "process_trajectory": { "total": 103.28810014342889, "count": 33175, "self": 103.04438654333353, "children": { "RLTrainer._checkpoint": { "total": 0.24371360009536147, "count": 1, "self": 0.24371360009536147 } } }, "_update_policy": { "total": 207.41120789991692, "count": 23, "self": 33.33055819943547, "children": { "TorchPOCAOptimizer.update": { "total": 174.08064970048144, "count": 230, "self": 174.08064970048144 } } } } } } }, "trainer_threads": { "total": 1.000240445137024e-06, "count": 1, "self": 1.000240445137024e-06 }, "TrainerController._save_models": { "total": 0.14870649995282292, "count": 1, "self": 0.012371799908578396, "children": { "RLTrainer._checkpoint": { "total": 0.13633470004424453, "count": 1, "self": 0.13633470004424453 } } } } } } }