{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5931496620178223, "min": 1.5379153490066528, "max": 1.950473666191101, "count": 889 }, "SoccerTwos.Policy.Entropy.sum": { "value": 31404.166015625, "min": 12367.951171875, "max": 44546.3046875, "count": 889 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 64.57894736842105, "min": 43.3, "max": 113.0, "count": 889 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19632.0, "min": 5196.0, "max": 21736.0, "count": 889 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1686.7929876739474, "min": 1628.9054425126162, "max": 1719.1533080607512, "count": 889 }, "SoccerTwos.Self-play.ELO.sum": { "value": 256392.53412644, "min": 99161.43184951188, "max": 378840.6926137847, "count": 889 }, "SoccerTwos.Step.mean": { "value": 19999780.0, "min": 11119959.0, "max": 19999780.0, "count": 889 }, "SoccerTwos.Step.sum": { "value": 19999780.0, "min": 11119959.0, "max": 19999780.0, "count": 889 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.02013554982841015, "min": -0.13025151193141937, "max": 0.09185903519392014, "count": 889 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -3.060603618621826, "min": -21.250598907470703, "max": 17.545076370239258, "count": 889 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.02120521478354931, "min": -0.1314365267753601, "max": 0.08880048990249634, "count": 889 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.2231926918029785, "min": -20.439422607421875, "max": 16.960893630981445, "count": 889 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 889 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 889 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.13405921114118477, "min": -0.5107376808705537, "max": 0.3571549976865451, "count": 889 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 20.377000093460083, "min": -70.48179996013641, "max": 58.28660011291504, "count": 889 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.13405921114118477, "min": -0.5107376808705537, "max": 0.3571549976865451, "count": 889 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 20.377000093460083, "min": -70.48179996013641, "max": 58.28660011291504, "count": 889 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 889 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 889 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.023435101409753165, "min": 0.011006926382348563, "max": 0.023990907132004698, "count": 431 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.023435101409753165, "min": 0.011006926382348563, "max": 0.023990907132004698, "count": 431 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09929284676909447, "min": 0.07108619386951129, "max": 0.12211424360672633, "count": 431 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09929284676909447, "min": 0.07108619386951129, "max": 0.12211424360672633, "count": 431 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10040274386604627, "min": 0.07166211406389872, "max": 0.12442898328105609, "count": 431 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10040274386604627, "min": 0.07166211406389872, "max": 0.12442898328105609, "count": 431 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 431 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 431 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 431 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 431 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 431 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 431 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1686380226", "python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:38:11) \n[Clang 14.0.6 ]", "command_line_arguments": "/Users/huangxin/miniconda/envs/rl/bin/mlagents-learn ./config/poca/MySoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos --run-id=MySoccerTwos --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0", "numpy_version": "1.21.2", "end_time_seconds": "1686411784" }, "total": 31558.743268917002, "count": 1, "self": 0.18436241700328537, "children": { "run_training.setup": { "total": 0.011634582999999976, "count": 1, "self": 0.011634582999999976 }, "TrainerController.start_learning": { "total": 31558.547271917, "count": 1, "self": 6.859618200909608, "children": { "TrainerController._reset_env": { "total": 2.877357038997752, "count": 46, "self": 2.877357038997752 }, "TrainerController.advance": { "total": 31548.729604219094, "count": 612292, "self": 6.664372276431095, "children": { "env_step": { "total": 24855.031640116315, "count": 612292, "self": 23881.4058230394, "children": { "SubprocessEnvManager._take_step": { "total": 969.0804236776685, "count": 612292, "self": 28.495145847641993, "children": { "TorchPolicy.evaluate": { "total": 940.5852778300265, "count": 1115570, "self": 940.5852778300265 } } }, "workers": { "total": 4.545393399244284, "count": 612292, "self": 0.0, "children": { "worker_root": { "total": 31546.64145962295, "count": 612292, "is_parallel": true, "self": 8570.061137250581, "children": { "steps_from_proto": { "total": 0.05852121300729651, "count": 92, "is_parallel": true, "self": 0.008406461991320668, "children": { "_process_rank_one_or_two_observation": { "total": 0.050114751015975845, "count": 368, "is_parallel": true, "self": 0.050114751015975845 } } }, "UnityEnvironment.step": { "total": 22976.521801159364, "count": 612292, "is_parallel": true, "self": 62.71345968130845, "children": { "UnityEnvironment._generate_step_input": { "total": 368.9046247036486, "count": 612292, "is_parallel": true, "self": 368.9046247036486 }, "communicator.exchange": { "total": 21825.500489326132, "count": 612292, "is_parallel": true, "self": 21825.500489326132 }, "steps_from_proto": { "total": 719.4032274482732, "count": 1224584, "is_parallel": true, "self": 99.59622331908429, "children": { "_process_rank_one_or_two_observation": { "total": 619.807004129189, "count": 4898336, "is_parallel": true, "self": 619.807004129189 } } } } } } } } } } }, "trainer_advance": { "total": 6687.033591826349, "count": 612292, "self": 48.71599595516, "children": { "process_trajectory": { "total": 1710.8917903592137, "count": 612292, "self": 1709.4232704842111, "children": { "RLTrainer._checkpoint": { "total": 1.4685198750025847, "count": 18, "self": 1.4685198750025847 } } }, "_update_policy": { "total": 4927.425805511975, "count": 431, "self": 756.8673415870398, "children": { "TorchPOCAOptimizer.update": { "total": 4170.5584639249355, "count": 12930, "self": 4170.5584639249355 } } } } } } }, "trainer_threads": { "total": 3.749992174562067e-07, "count": 1, "self": 3.749992174562067e-07 }, "TrainerController._save_models": { "total": 0.08069208300003083, "count": 1, "self": 0.0018718749997788109, "children": { "RLTrainer._checkpoint": { "total": 0.07882020800025202, "count": 1, "self": 0.07882020800025202 } } } } } } }