{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.462829351425171, "min": 1.4009822607040405, "max": 1.5029096603393555, "count": 493 }, "SoccerTwos.Policy.Entropy.sum": { "value": 11843.06640625, "min": 8624.970703125, "max": 19728.86328125, "count": 493 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 62.68421052631579, "min": 50.354166666666664, "max": 138.1578947368421, "count": 493 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 9528.0, "min": 5060.0, "max": 12312.0, "count": 493 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1767.3834457654516, "min": 1746.583706536575, "max": 1804.0291415428298, "count": 493 }, "SoccerTwos.Self-play.ELO.sum": { "value": 134321.14187817433, "min": 67882.67408529173, "max": 168713.455797354, "count": 493 }, "SoccerTwos.Step.mean": { "value": 88914899.0, "min": 86454874.0, "max": 88914899.0, "count": 493 }, "SoccerTwos.Step.sum": { "value": 88914899.0, "min": 86454874.0, "max": 88914899.0, "count": 493 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0520256906747818, "min": -0.10452874004840851, "max": 0.0713474377989769, "count": 493 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.005978107452393, "min": -8.362298965454102, "max": 4.345118522644043, "count": 493 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.05622515827417374, "min": -0.10496088117361069, "max": 0.07028066366910934, "count": 493 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -4.329337120056152, "min": -8.396870613098145, "max": 4.338320255279541, "count": 493 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 493 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 493 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.11434026043136399, "min": -0.6378692273910229, "max": 0.4695058815619525, "count": 493 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -8.804200053215027, "min": -33.701199889183044, "max": 31.92639994621277, "count": 493 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.11434026043136399, "min": -0.6378692273910229, "max": 0.4695058815619525, "count": 493 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -8.804200053215027, "min": -33.701199889183044, "max": 31.92639994621277, "count": 493 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 493 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 493 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016503152671502902, "min": 0.013709111934294924, "max": 0.01911210694583133, "count": 59 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016503152671502902, "min": 0.013709111934294924, "max": 0.01911210694583133, "count": 59 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.03968265287578106, "min": 0.033692181818187235, "max": 0.03968265287578106, "count": 59 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.03968265287578106, "min": 0.033692181818187235, "max": 0.03968265287578106, "count": 59 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.04020755760371685, "min": 0.03429904207587242, "max": 0.04020755760371685, "count": 59 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.04020755760371685, "min": 0.03429904207587242, "max": 0.04020755760371685, "count": 59 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003644496484875901, "min": 0.0003644496484875901, "max": 0.00036540257864935757, "count": 59 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003644496484875901, "min": 0.0003644496484875901, "max": 0.00036540257864935757, "count": 59 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.26, "min": 0.26, "max": 0.26, "count": 59 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.26, "min": 0.26, "max": 0.26, "count": 59 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.007289881551010001, "min": 0.007289881551010001, "max": 0.007308916335749999, "count": 59 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.007289881551010001, "min": 0.007289881551010001, "max": 0.007308916335749999, "count": 59 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1687616378", "python_version": "3.9.16 (main, May 17 2023, 17:49:16) [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": "2.0.1+cpu", "numpy_version": "1.22.3", "end_time_seconds": "1687621233" }, "total": 4855.1836637, "count": 1, "self": 0.11203930000010587, "children": { "run_training.setup": { "total": 0.06094929999999987, "count": 1, "self": 0.06094929999999987 }, "TrainerController.start_learning": { "total": 4855.010675099999, "count": 1, "self": 2.591246700088959, "children": { "TrainerController._reset_env": { "total": 1.8982426999998394, "count": 14, "self": 1.8982426999998394 }, "TrainerController.advance": { "total": 4850.46030909991, "count": 168064, "self": 2.407578899942564, "children": { "env_step": { "total": 1686.2362792000536, "count": 168064, "self": 1356.7433718999523, "children": { "SubprocessEnvManager._take_step": { "total": 328.05091160003076, "count": 168064, "self": 16.409821200230226, "children": { "TorchPolicy.evaluate": { "total": 311.64109039980053, "count": 309652, "self": 311.64109039980053 } } }, "workers": { "total": 1.441995700070537, "count": 168064, "self": 0.0, "children": { "worker_root": { "total": 4801.3829403999225, "count": 168064, "is_parallel": true, "self": 3698.9537907998338, "children": { "steps_from_proto": { "total": 0.015389099999134404, "count": 28, "is_parallel": true, "self": 0.00305629999885082, "children": { "_process_rank_one_or_two_observation": { "total": 0.012332800000283584, "count": 112, "is_parallel": true, "self": 0.012332800000283584 } } }, "UnityEnvironment.step": { "total": 1102.41376050009, "count": 168064, "is_parallel": true, "self": 61.519009900300716, "children": { "UnityEnvironment._generate_step_input": { "total": 40.754522099996535, "count": 168064, "is_parallel": true, "self": 40.754522099996535 }, "communicator.exchange": { "total": 827.0594783999637, "count": 168064, "is_parallel": true, "self": 827.0594783999637 }, "steps_from_proto": { "total": 173.0807500998289, "count": 336128, "is_parallel": true, "self": 33.51694829988776, "children": { "_process_rank_one_or_two_observation": { "total": 139.56380179994113, "count": 1344512, "is_parallel": true, "self": 139.56380179994113 } } } } } } } } } } }, "trainer_advance": { "total": 3161.8164509999137, "count": 168064, "self": 18.913633199877495, "children": { "process_trajectory": { "total": 322.1973488000333, "count": 168064, "self": 321.89535020003314, "children": { "RLTrainer._checkpoint": { "total": 0.30199860000014667, "count": 5, "self": 0.30199860000014667 } } }, "_update_policy": { "total": 2820.7054690000027, "count": 60, "self": 407.2015091000044, "children": { "TorchPOCAOptimizer.update": { "total": 2413.5039598999983, "count": 2990, "self": 2413.5039598999983 } } } } } } }, "trainer_threads": { "total": 6.000000212225132e-07, "count": 1, "self": 6.000000212225132e-07 }, "TrainerController._save_models": { "total": 0.06087600000046223, "count": 1, "self": 0.0074088000001211185, "children": { "RLTrainer._checkpoint": { "total": 0.05346720000034111, "count": 1, "self": 0.05346720000034111 } } } } } } }