{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8058241605758667, "min": 1.7579253911972046, "max": 1.911346435546875, "count": 46 }, "SoccerTwos.Policy.Entropy.sum": { "value": 38774.65625, "min": 19227.70703125, "max": 41152.75390625, "count": 46 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 62.41772151898734, "min": 55.60919540229885, "max": 84.37931034482759, "count": 46 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19724.0, "min": 7768.0, "max": 20660.0, "count": 46 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1680.5489530446416, "min": 1639.7450073677105, "max": 1691.1465713203363, "count": 46 }, "SoccerTwos.Self-play.ELO.sum": { "value": 265526.7345810534, "min": 111886.37048148527, "max": 303643.6927703533, "count": 46 }, "SoccerTwos.Step.mean": { "value": 6509996.0, "min": 6059954.0, "max": 6509996.0, "count": 46 }, "SoccerTwos.Step.sum": { "value": 6509996.0, "min": 6059954.0, "max": 6509996.0, "count": 46 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.012257174588739872, "min": -0.07837150990962982, "max": 0.04054918885231018, "count": 46 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 1.936633586883545, "min": -13.088042259216309, "max": 6.974460601806641, "count": 46 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.014666596427559853, "min": -0.077060267329216, "max": 0.043719593435525894, "count": 46 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 2.317322254180908, "min": -12.869064331054688, "max": 7.51977014541626, "count": 46 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 46 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 46 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.04137594828122779, "min": -0.1951999986098588, "max": 0.3472493143930827, "count": 46 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -6.5373998284339905, "min": -31.817599773406982, "max": 50.698399901390076, "count": 46 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.04137594828122779, "min": -0.1951999986098588, "max": 0.3472493143930827, "count": 46 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -6.5373998284339905, "min": -31.817599773406982, "max": 50.698399901390076, "count": 46 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 46 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 46 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.020626439266682912, "min": 0.01387019136066859, "max": 0.022149660189946494, "count": 22 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.020626439266682912, "min": 0.01387019136066859, "max": 0.022149660189946494, "count": 22 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09354040001829465, "min": 0.087071726222833, "max": 0.1047582966585954, "count": 22 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09354040001829465, "min": 0.087071726222833, "max": 0.1047582966585954, "count": 22 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09433713282148043, "min": 0.08816391477982204, "max": 0.10674229065577188, "count": 22 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09433713282148043, "min": 0.08816391477982204, "max": 0.10674229065577188, "count": 22 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 22 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 22 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 22 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 22 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 22 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 22 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1682619847", "python_version": "3.9.13 (tags/v3.9.13:6de2ca5, May 17 2022, 16:36:42) [MSC v.1929 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\Shane\\Desktop\\ml-agents\\env\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.12.1+cu113", "numpy_version": "1.21.2", "end_time_seconds": "1682620629" }, "total": 782.6740892, "count": 1, "self": 0.04328290000000834, "children": { "run_training.setup": { "total": 0.08860310000000005, "count": 1, "self": 0.08860310000000005 }, "TrainerController.start_learning": { "total": 782.5422032, "count": 1, "self": 0.6224599999951579, "children": { "TrainerController._reset_env": { "total": 5.779618599999895, "count": 4, "self": 5.779618599999895 }, "TrainerController.advance": { "total": 775.927230300005, "count": 31572, "self": 0.5344178000094644, "children": { "env_step": { "total": 575.9990928999946, "count": 31572, "self": 356.92020419999335, "children": { "SubprocessEnvManager._take_step": { "total": 218.68193099999752, "count": 31572, "self": 3.6872831000034125, "children": { "TorchPolicy.evaluate": { "total": 214.9946478999941, "count": 57472, "self": 214.9946478999941 } } }, "workers": { "total": 0.396957700003699, "count": 31572, "self": 0.0, "children": { "worker_root": { "total": 776.8060425000017, "count": 31572, "is_parallel": true, "self": 484.6908350000008, "children": { "steps_from_proto": { "total": 0.006427000000011063, "count": 8, "is_parallel": true, "self": 0.0011145000003303096, "children": { "_process_rank_one_or_two_observation": { "total": 0.005312499999680753, "count": 32, "is_parallel": true, "self": 0.005312499999680753 } } }, "UnityEnvironment.step": { "total": 292.1087805000009, "count": 31572, "is_parallel": true, "self": 14.630607499987946, "children": { "UnityEnvironment._generate_step_input": { "total": 11.858462899994677, "count": 31572, "is_parallel": true, "self": 11.858462899994677 }, "communicator.exchange": { "total": 218.59651410000873, "count": 31572, "is_parallel": true, "self": 218.59651410000873 }, "steps_from_proto": { "total": 47.02319600000952, "count": 63144, "is_parallel": true, "self": 8.230957600017128, "children": { "_process_rank_one_or_two_observation": { "total": 38.79223839999239, "count": 252576, "is_parallel": true, "self": 38.79223839999239 } } } } } } } } } } }, "trainer_advance": { "total": 199.393719600001, "count": 31572, "self": 4.736007500007446, "children": { "process_trajectory": { "total": 95.70726739999324, "count": 31572, "self": 95.46402169999325, "children": { "RLTrainer._checkpoint": { "total": 0.24324569999998857, "count": 1, "self": 0.24324569999998857 } } }, "_update_policy": { "total": 98.95044470000029, "count": 22, "self": 61.41991180000086, "children": { "TorchPOCAOptimizer.update": { "total": 37.53053289999943, "count": 660, "self": 37.53053289999943 } } } } } } }, "trainer_threads": { "total": 1.6999999843392288e-06, "count": 1, "self": 1.6999999843392288e-06 }, "TrainerController._save_models": { "total": 0.21289259999991827, "count": 1, "self": 0.008440899999868634, "children": { "RLTrainer._checkpoint": { "total": 0.20445170000004964, "count": 1, "self": 0.20445170000004964 } } } } } } }