{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9214180707931519, "min": 1.862352967262268, "max": 2.0375585556030273, "count": 171 }, "SoccerTwos.Policy.Entropy.sum": { "value": 39473.61328125, "min": 14372.5556640625, "max": 44608.6640625, "count": 171 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 49.58585858585859, "min": 40.706896551724135, "max": 71.81428571428572, "count": 171 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19636.0, "min": 6180.0, "max": 20260.0, "count": 171 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1585.7677991109404, "min": 1553.5179580138852, "max": 1610.7972019352037, "count": 171 }, "SoccerTwos.Self-play.ELO.sum": { "value": 313982.0242239662, "min": 94213.86956426132, "max": 394536.63157583587, "count": 171 }, "SoccerTwos.Step.mean": { "value": 5139959.0, "min": 3439951.0, "max": 5139959.0, "count": 171 }, "SoccerTwos.Step.sum": { "value": 5139959.0, "min": 3439951.0, "max": 5139959.0, "count": 171 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.060572218149900436, "min": -0.08898256719112396, "max": 0.1005156859755516, "count": 171 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -12.053871154785156, "min": -17.240734100341797, "max": 17.89179229736328, "count": 171 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.05699760094285011, "min": -0.087178535759449, "max": 0.09999766200780869, "count": 171 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -11.342522621154785, "min": -16.390785217285156, "max": 17.799583435058594, "count": 171 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 171 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 171 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.1673165817356589, "min": -0.2861095484177671, "max": 0.22272921378692884, "count": 171 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -33.29599976539612, "min": -56.93580013513565, "max": 39.645800054073334, "count": 171 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.1673165817356589, "min": -0.2861095484177671, "max": 0.22272921378692884, "count": 171 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -33.29599976539612, "min": -56.93580013513565, "max": 39.645800054073334, "count": 171 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 171 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 171 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018759650674959025, "min": 0.01115469560221148, "max": 0.021448074255992346, "count": 82 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018759650674959025, "min": 0.01115469560221148, "max": 0.021448074255992346, "count": 82 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11596904620528221, "min": 0.09423803612589836, "max": 0.12632074877619742, "count": 82 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11596904620528221, "min": 0.09423803612589836, "max": 0.12632074877619742, "count": 82 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11812345335880915, "min": 0.0952321524421374, "max": 0.12842872540156047, "count": 82 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11812345335880915, "min": 0.0952321524421374, "max": 0.12842872540156047, "count": 82 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 82 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 82 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 82 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 82 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 82 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 82 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1716454994", "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\\ASUSROG\\.conda\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1716467265" }, "total": 12270.348834600001, "count": 1, "self": 1.1021543000024394, "children": { "run_training.setup": { "total": 0.3115802999996049, "count": 1, "self": 0.3115802999996049 }, "TrainerController.start_learning": { "total": 12268.935099999999, "count": 1, "self": 8.741336000073716, "children": { "TrainerController._reset_env": { "total": 24.339133400000264, "count": 10, "self": 24.339133400000264 }, "TrainerController.advance": { "total": 12235.582564599925, "count": 119838, "self": 8.518548199779616, "children": { "env_step": { "total": 6489.675793600161, "count": 119838, "self": 5023.78484800052, "children": { "SubprocessEnvManager._take_step": { "total": 1460.3441352998884, "count": 119838, "self": 46.86335090045304, "children": { "TorchPolicy.evaluate": { "total": 1413.4807843994354, "count": 214308, "self": 1413.4807843994354 } } }, "workers": { "total": 5.546810299753361, "count": 119838, "self": 0.0, "children": { "worker_root": { "total": 12204.119910299984, "count": 119838, "is_parallel": true, "self": 8252.098853600017, "children": { "steps_from_proto": { "total": 0.0566629999966608, "count": 20, "is_parallel": true, "self": 0.011537199997746939, "children": { "_process_rank_one_or_two_observation": { "total": 0.04512579999891386, "count": 80, "is_parallel": true, "self": 0.04512579999891386 } } }, "UnityEnvironment.step": { "total": 3951.9643936999705, "count": 119838, "is_parallel": true, "self": 227.40118399990342, "children": { "UnityEnvironment._generate_step_input": { "total": 221.29594099971882, "count": 119838, "is_parallel": true, "self": 221.29594099971882 }, "communicator.exchange": { "total": 2718.435361500345, "count": 119838, "is_parallel": true, "self": 2718.435361500345 }, "steps_from_proto": { "total": 784.8319072000031, "count": 239676, "is_parallel": true, "self": 154.5026458000434, "children": { "_process_rank_one_or_two_observation": { "total": 630.3292613999597, "count": 958704, "is_parallel": true, "self": 630.3292613999597 } } } } } } } } } } }, "trainer_advance": { "total": 5737.388222799984, "count": 119838, "self": 47.69191030006823, "children": { "process_trajectory": { "total": 1710.6069001999222, "count": 119838, "self": 1709.2757095999232, "children": { "RLTrainer._checkpoint": { "total": 1.3311905999989904, "count": 4, "self": 1.3311905999989904 } } }, "_update_policy": { "total": 3979.0894122999935, "count": 83, "self": 503.9244860999961, "children": { "TorchPOCAOptimizer.update": { "total": 3475.1649261999974, "count": 2480, "self": 3475.1649261999974 } } } } } } }, "trainer_threads": { "total": 2.599999788799323e-06, "count": 1, "self": 2.599999788799323e-06 }, "TrainerController._save_models": { "total": 0.2720633999997517, "count": 1, "self": 0.014902599999913946, "children": { "RLTrainer._checkpoint": { "total": 0.25716079999983776, "count": 1, "self": 0.25716079999983776 } } } } } } }