{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.0657835006713867, "min": 0.8271827101707458, "max": 1.0846834182739258, "count": 134 }, "SoccerTwos.Policy.Entropy.sum": { "value": 24521.546875, "min": 714.6858520507812, "max": 24521.546875, "count": 134 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 62.139240506329116, "min": 18.0, "max": 108.95454545454545, "count": 134 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19636.0, "min": 216.0, "max": 21180.0, "count": 134 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1199.537674055424, "min": 1141.8328850840762, "max": 1213.5387676849714, "count": 134 }, "SoccerTwos.Self-play.ELO.sum": { "value": 189526.952500757, "min": 7111.963383615639, "max": 212201.6234024732, "count": 134 }, "SoccerTwos.Step.mean": { "value": 87999985.0, "min": 86669978.0, "max": 87999985.0, "count": 134 }, "SoccerTwos.Step.sum": { "value": 87999985.0, "min": 86669978.0, "max": 87999985.0, "count": 134 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.014292377047240734, "min": -0.32840096950531006, "max": 0.040184665471315384, "count": 134 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 2.258195638656616, "min": -16.492427825927734, "max": 5.7062225341796875, "count": 134 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.013550088740885258, "min": -0.3203054964542389, "max": 0.04180605337023735, "count": 134 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 2.140913963317871, "min": -16.367063522338867, "max": 5.54995059967041, "count": 134 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 134 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 134 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.07685316627538658, "min": -1.0, "max": 0.24133232930549106, "count": 134 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 12.142800271511078, "min": -49.61899983882904, "max": 32.09719979763031, "count": 134 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.07685316627538658, "min": -1.0, "max": 0.24133232930549106, "count": 134 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 12.142800271511078, "min": -49.61899983882904, "max": 32.09719979763031, "count": 134 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 134 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 134 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01875397504772991, "min": 0.010948603112289372, "max": 0.024624802494266382, "count": 64 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01875397504772991, "min": 0.010948603112289372, "max": 0.024624802494266382, "count": 64 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08763666873176892, "min": 0.07551249091823896, "max": 0.10563173020879428, "count": 64 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08763666873176892, "min": 0.07551249091823896, "max": 0.10563173020879428, "count": 64 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08807998945315679, "min": 0.07606927181283633, "max": 0.10634580304225286, "count": 64 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08807998945315679, "min": 0.07606927181283633, "max": 0.10634580304225286, "count": 64 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 64 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 64 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 64 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 64 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 64 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 64 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1678223506", "python_version": "3.9.16 (main, Jan 11 2023, 16:16:36) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\ProgramData\\Anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/!SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "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": "1678252082" }, "total": 28576.821291, "count": 1, "self": 2.462663899998006, "children": { "run_training.setup": { "total": 0.10050110000000068, "count": 1, "self": 0.10050110000000068 }, "TrainerController.start_learning": { "total": 28574.258126, "count": 1, "self": 10.61634349949236, "children": { "TrainerController._reset_env": { "total": 15.576662500001085, "count": 8, "self": 15.576662500001085 }, "TrainerController.advance": { "total": 28547.56943230051, "count": 90880, "self": 9.851066700051888, "children": { "env_step": { "total": 5566.16805360012, "count": 90880, "self": 4335.347687000279, "children": { "SubprocessEnvManager._take_step": { "total": 1226.1228862997557, "count": 90880, "self": 48.201311400173836, "children": { "TorchPolicy.evaluate": { "total": 1177.9215748995819, "count": 167516, "self": 1177.9215748995819 } } }, "workers": { "total": 4.6974803000856795, "count": 90880, "self": 0.0, "children": { "worker_root": { "total": 28544.925808599837, "count": 90880, "is_parallel": true, "self": 25044.235386299977, "children": { "steps_from_proto": { "total": 0.0250341000033103, "count": 16, "is_parallel": true, "self": 0.010483800012170974, "children": { "_process_rank_one_or_two_observation": { "total": 0.014550299991139326, "count": 64, "is_parallel": true, "self": 0.014550299991139326 } } }, "UnityEnvironment.step": { "total": 3500.6653881998573, "count": 90880, "is_parallel": true, "self": 155.26112569943916, "children": { "UnityEnvironment._generate_step_input": { "total": 63.298819200252616, "count": 90880, "is_parallel": true, "self": 63.298819200252616 }, "communicator.exchange": { "total": 2757.479375899919, "count": 90880, "is_parallel": true, "self": 2757.479375899919 }, "steps_from_proto": { "total": 524.6260674002465, "count": 181760, "is_parallel": true, "self": 113.46512780203273, "children": { "_process_rank_one_or_two_observation": { "total": 411.16093959821376, "count": 727040, "is_parallel": true, "self": 411.16093959821376 } } } } } } } } } } }, "trainer_advance": { "total": 22971.550312000334, "count": 90880, "self": 62.63358490049359, "children": { "process_trajectory": { "total": 1549.2741931998512, "count": 90880, "self": 1544.0235150998524, "children": { "RLTrainer._checkpoint": { "total": 5.250678099998737, "count": 14, "self": 5.250678099998737 } } }, "_update_policy": { "total": 21359.64253389999, "count": 64, "self": 564.9658853000328, "children": { "TorchPOCAOptimizer.update": { "total": 20794.676648599958, "count": 1920, "self": 20794.676648599958 } } } } } } }, "trainer_threads": { "total": 2.0000006770715117e-06, "count": 1, "self": 2.0000006770715117e-06 }, "TrainerController._save_models": { "total": 0.4956856999997399, "count": 1, "self": 0.012757399999827612, "children": { "RLTrainer._checkpoint": { "total": 0.48292829999991227, "count": 1, "self": 0.48292829999991227 } } } } } } }