{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.3613641262054443, "min": 1.3411742448806763, "max": 3.2956974506378174, "count": 3602 }, "SoccerTwos.Policy.Entropy.sum": { "value": 26965.900390625, "min": 20730.64453125, "max": 113570.3515625, "count": 3602 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 60.25925925925926, "min": 37.152671755725194, "max": 999.0, "count": 3602 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19524.0, "min": 14780.0, "max": 26264.0, "count": 3602 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1657.6884764709157, "min": 1196.935184936025, "max": 1693.6010200992766, "count": 3598 }, "SoccerTwos.Self-play.ELO.sum": { "value": 268545.53318828833, "min": 2395.503742810388, "max": 395426.28455575136, "count": 3598 }, "SoccerTwos.Step.mean": { "value": 36019996.0, "min": 9152.0, "max": 36019996.0, "count": 3602 }, "SoccerTwos.Step.sum": { "value": 36019996.0, "min": 9152.0, "max": 36019996.0, "count": 3602 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.02646617218852043, "min": -0.12825043499469757, "max": 0.16259294748306274, "count": 3602 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.287519931793213, "min": -23.33773422241211, "max": 29.429323196411133, "count": 3602 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.02755160629749298, "min": -0.12929044663906097, "max": 0.16035780310630798, "count": 3602 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -4.46336030960083, "min": -23.126182556152344, "max": 29.145509719848633, "count": 3602 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 3602 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 3602 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.06300493817270537, "min": -0.5118799969553948, "max": 0.38358182121406903, "count": 3602 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -10.206799983978271, "min": -75.341000020504, "max": 65.22119987010956, "count": 3602 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.06300493817270537, "min": -0.5118799969553948, "max": 0.38358182121406903, "count": 3602 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -10.206799983978271, "min": -75.341000020504, "max": 65.22119987010956, "count": 3602 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3602 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3602 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.024208955618087204, "min": 0.010381613879386957, "max": 0.02644906841839353, "count": 1747 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.024208955618087204, "min": 0.010381613879386957, "max": 0.02644906841839353, "count": 1747 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09502252489328385, "min": 0.0008015644780243747, "max": 0.12794513031840324, "count": 1747 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09502252489328385, "min": 0.0008015644780243747, "max": 0.12794513031840324, "count": 1747 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09575181355079015, "min": 0.0008083683215469743, "max": 0.13082094714045525, "count": 1747 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09575181355079015, "min": 0.0008083683215469743, "max": 0.13082094714045525, "count": 1747 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1747 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1747 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1747 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1747 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1747 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1747 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1678891687", "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\ProgramData\\Anaconda3\\envs\\Unit_7_v1\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/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": "1.13.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1678947339" }, "total": 55652.2723445, "count": 1, "self": 4.1539450000054785, "children": { "run_training.setup": { "total": 0.04273440000000006, "count": 1, "self": 0.04273440000000006 }, "TrainerController.start_learning": { "total": 55648.0756651, "count": 1, "self": 31.595731998357223, "children": { "TrainerController._reset_env": { "total": 2.9493974999899493, "count": 181, "self": 2.9493974999899493 }, "TrainerController.advance": { "total": 55613.45954870164, "count": 2494971, "self": 29.06726641154819, "children": { "env_step": { "total": 20888.51379739436, "count": 2494971, "self": 16634.13684089223, "children": { "SubprocessEnvManager._take_step": { "total": 4238.250976899165, "count": 2494971, "self": 167.79678639648273, "children": { "TorchPolicy.evaluate": { "total": 4070.454190502682, "count": 4523328, "self": 4070.454190502682 } } }, "workers": { "total": 16.12597960296451, "count": 2494970, "self": 0.0, "children": { "worker_root": { "total": 55605.35222459717, "count": 2494970, "is_parallel": true, "self": 41758.270943694755, "children": { "steps_from_proto": { "total": 0.16569109998207066, "count": 362, "is_parallel": true, "self": 0.03305700008893364, "children": { "_process_rank_one_or_two_observation": { "total": 0.13263409989313701, "count": 1448, "is_parallel": true, "self": 0.13263409989313701 } } }, "UnityEnvironment.step": { "total": 13846.91558980243, "count": 2494970, "is_parallel": true, "self": 665.5670276068831, "children": { "UnityEnvironment._generate_step_input": { "total": 446.81969479831116, "count": 2494970, "is_parallel": true, "self": 446.81969479831116 }, "communicator.exchange": { "total": 10669.060154700657, "count": 2494970, "is_parallel": true, "self": 10669.060154700657 }, "steps_from_proto": { "total": 2065.4687126965787, "count": 4989940, "is_parallel": true, "self": 405.50216390756873, "children": { "_process_rank_one_or_two_observation": { "total": 1659.96654878901, "count": 19959760, "is_parallel": true, "self": 1659.96654878901 } } } } } } } } } } }, "trainer_advance": { "total": 34695.87848489574, "count": 2494970, "self": 206.65146769313287, "children": { "process_trajectory": { "total": 6583.591829502495, "count": 2494970, "self": 6578.748415902507, "children": { "RLTrainer._checkpoint": { "total": 4.843413599987798, "count": 72, "self": 4.843413599987798 } } }, "_update_policy": { "total": 27905.635187700107, "count": 1748, "self": 2748.502520400274, "children": { "TorchPOCAOptimizer.update": { "total": 25157.132667299833, "count": 52440, "self": 25157.132667299833 } } } } } } }, "trainer_threads": { "total": 1.700005668681115e-06, "count": 1, "self": 1.700005668681115e-06 }, "TrainerController._save_models": { "total": 0.07098519999999553, "count": 1, "self": 0.0037606999976560473, "children": { "RLTrainer._checkpoint": { "total": 0.06722450000233948, "count": 1, "self": 0.06722450000233948 } } } } } } }