{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6099094152450562, "min": 1.5207527875900269, "max": 2.384139060974121, "count": 1000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 32404.255859375, "min": 27570.814453125, "max": 50887.06640625, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 63.177215189873415, "min": 37.93076923076923, "max": 77.25, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19964.0, "min": 18560.0, "max": 20964.0, "count": 1000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1630.5526151676804, "min": 1380.5516471633684, "max": 1658.2405356683296, "count": 1000 }, "SoccerTwos.Self-play.ELO.sum": { "value": 257627.31319649352, "min": 196305.03927465307, "max": 420312.2336165031, "count": 1000 }, "SoccerTwos.Step.mean": { "value": 14999989.0, "min": 5009930.0, "max": 14999989.0, "count": 1000 }, "SoccerTwos.Step.sum": { "value": 14999989.0, "min": 5009930.0, "max": 14999989.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.02849951945245266, "min": -0.10880010575056076, "max": 0.11400023102760315, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.502923965454102, "min": -19.710926055908203, "max": 22.08706283569336, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.024522004649043083, "min": -0.11366839706897736, "max": 0.10873111337423325, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.874476671218872, "min": -20.68764877319336, "max": 22.398609161376953, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.05733291069163552, "min": -0.32792437817919906, "max": 0.3206224626398341, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -9.058599889278412, "min": -65.91280001401901, "max": 59.95640051364899, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.05733291069163552, "min": -0.32792437817919906, "max": 0.3206224626398341, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -9.058599889278412, "min": -65.91280001401901, "max": 59.95640051364899, "count": 1000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.0149743233230159, "min": 0.011443423058760041, "max": 0.026090294665967424, "count": 486 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.0149743233230159, "min": 0.011443423058760041, "max": 0.026090294665967424, "count": 486 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10135304778814316, "min": 0.08815950925151507, "max": 0.12917640407880146, "count": 486 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10135304778814316, "min": 0.08815950925151507, "max": 0.12917640407880146, "count": 486 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10274179776509602, "min": 0.08971414019664128, "max": 0.13080705429116884, "count": 486 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10274179776509602, "min": 0.08971414019664128, "max": 0.13080705429116884, "count": 486 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 486 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 486 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 486 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 486 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 486 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 486 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1684779147", "python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:39:03) \n[GCC 11.3.0]", "command_line_arguments": "ml-agents/mlagents/trainers/learn.py ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume --torch-device=cuda", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu118", "numpy_version": "1.21.2", "end_time_seconds": "1684784885" }, "total": 5738.293310943998, "count": 1, "self": 0.16640525999901, "children": { "run_training.setup": { "total": 0.006291360001341673, "count": 1, "self": 0.006291360001341673 }, "TrainerController.start_learning": { "total": 5738.120614323998, "count": 1, "self": 5.686786572623532, "children": { "TrainerController._reset_env": { "total": 1.5485932720075652, "count": 51, "self": 1.5485932720075652 }, "TrainerController.advance": { "total": 5730.810328043368, "count": 700812, "self": 5.292680743667006, "children": { "env_step": { "total": 4235.785418268359, "count": 700812, "self": 3243.6642487515273, "children": { "SubprocessEnvManager._take_step": { "total": 989.048752669034, "count": 700812, "self": 36.69071319253635, "children": { "TorchPolicy.evaluate": { "total": 952.3580394764977, "count": 1253978, "self": 952.3580394764977 } } }, "workers": { "total": 3.0724168477972853, "count": 700812, "self": 0.0, "children": { "worker_root": { "total": 5730.651753197661, "count": 700812, "is_parallel": true, "self": 3042.8718115734773, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0015056480042403564, "count": 2, "is_parallel": true, "self": 0.00041794100252445787, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010877070017158985, "count": 8, "is_parallel": true, "self": 0.0010877070017158985 } } }, "UnityEnvironment.step": { "total": 0.011163593997480348, "count": 1, "is_parallel": true, "self": 0.0002702169949770905, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000198353998712264, "count": 1, "is_parallel": true, "self": 0.000198353998712264 }, "communicator.exchange": { "total": 0.009959303002688102, "count": 1, "is_parallel": true, "self": 0.009959303002688102 }, "steps_from_proto": { "total": 0.0007357200011028908, "count": 2, "is_parallel": true, "self": 0.0001429900039511267, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005927299971517641, "count": 8, "is_parallel": true, "self": 0.0005927299971517641 } } } } } } }, "steps_from_proto": { "total": 0.03402553797059227, "count": 100, "is_parallel": true, "self": 0.006169039937958587, "children": { "_process_rank_one_or_two_observation": { "total": 0.02785649803263368, "count": 400, "is_parallel": true, "self": 0.02785649803263368 } } }, "UnityEnvironment.step": { "total": 2687.7459160862127, "count": 700811, "is_parallel": true, "self": 164.7059383653468, "children": { "UnityEnvironment._generate_step_input": { "total": 87.95222477414063, "count": 700811, "is_parallel": true, "self": 87.95222477414063 }, "communicator.exchange": { "total": 2005.0622043327712, "count": 700811, "is_parallel": true, "self": 2005.0622043327712 }, "steps_from_proto": { "total": 430.025548613954, "count": 1401622, "is_parallel": true, "self": 77.20184635687838, "children": { "_process_rank_one_or_two_observation": { "total": 352.82370225707564, "count": 5606488, "is_parallel": true, "self": 352.82370225707564 } } } } } } } } } } }, "trainer_advance": { "total": 1489.7322290313423, "count": 700812, "self": 38.19949424334118, "children": { "process_trajectory": { "total": 649.0925412990582, "count": 700812, "self": 647.4561120400504, "children": { "RLTrainer._checkpoint": { "total": 1.6364292590078549, "count": 20, "self": 1.6364292590078549 } } }, "_update_policy": { "total": 802.4401934889429, "count": 486, "self": 560.5196833143345, "children": { "TorchPOCAOptimizer.update": { "total": 241.92051017460835, "count": 14580, "self": 241.92051017460835 } } } } } } }, "trainer_threads": { "total": 4.2300234781578183e-07, "count": 1, "self": 4.2300234781578183e-07 }, "TrainerController._save_models": { "total": 0.07490601299650734, "count": 1, "self": 0.0016170749950106256, "children": { "RLTrainer._checkpoint": { "total": 0.07328893800149672, "count": 1, "self": 0.07328893800149672 } } } } } } }