{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4011540412902832, "min": 1.3830610513687134, "max": 1.8234226703643799, "count": 1387 }, "SoccerTwos.Policy.Entropy.sum": { "value": 29457.86328125, "min": 24735.029296875, "max": 40224.5859375, "count": 1387 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 58.367816091954026, "min": 38.88, "max": 84.22033898305085, "count": 1387 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20312.0, "min": 16436.0, "max": 21344.0, "count": 1387 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1561.1051212072978, "min": 1534.2771543014587, "max": 1635.500014025064, "count": 1387 }, "SoccerTwos.Self-play.ELO.sum": { "value": 271632.2910900698, "min": 186546.69901904836, "max": 401449.33329243044, "count": 1387 }, "SoccerTwos.Step.mean": { "value": 20099724.0, "min": 6239878.0, "max": 20099724.0, "count": 1387 }, "SoccerTwos.Step.sum": { "value": 20099724.0, "min": 6239878.0, "max": 20099724.0, "count": 1387 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.030307073146104813, "min": -0.11720992624759674, "max": 0.09817449003458023, "count": 1387 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 5.273430824279785, "min": -24.3062744140625, "max": 19.431991577148438, "count": 1387 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.030129041522741318, "min": -0.11586025357246399, "max": 0.09992619603872299, "count": 1387 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 5.242453098297119, "min": -24.77324104309082, "max": 19.474201202392578, "count": 1387 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1387 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1387 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.10522758618168447, "min": -0.3467288472904609, "max": 0.2952673269970582, "count": 1387 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -18.309599995613098, "min": -72.11960023641586, "max": 59.64400005340576, "count": 1387 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.10522758618168447, "min": -0.3467288472904609, "max": 0.2952673269970582, "count": 1387 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -18.309599995613098, "min": -72.11960023641586, "max": 59.64400005340576, "count": 1387 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1387 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1387 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015247845936877032, "min": 0.009736820104687164, "max": 0.026066995008538166, "count": 673 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015247845936877032, "min": 0.009736820104687164, "max": 0.026066995008538166, "count": 673 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10042838230729104, "min": 0.08936696400245031, "max": 0.13043266261617342, "count": 673 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10042838230729104, "min": 0.08936696400245031, "max": 0.13043266261617342, "count": 673 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10176143199205398, "min": 0.09096879363059998, "max": 0.13310801660021146, "count": 673 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10176143199205398, "min": 0.09096879363059998, "max": 0.13310801660021146, "count": 673 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 673 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 673 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 673 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 673 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 673 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 673 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1709589208", "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\\Jye\\anaconda3\\envs\\soccer-twos\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./../SoccerTwos/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": "2.2.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1709623739" }, "total": 34531.8872847, "count": 1, "self": 5.522328399994876, "children": { "run_training.setup": { "total": 0.15610849997028708, "count": 1, "self": 0.15610849997028708 }, "TrainerController.start_learning": { "total": 34526.20884780004, "count": 1, "self": 21.874699187173974, "children": { "TrainerController._reset_env": { "total": 6.788810000056401, "count": 71, "self": 6.788810000056401 }, "TrainerController.advance": { "total": 34497.370763612795, "count": 966985, "self": 22.764213644666597, "children": { "env_step": { "total": 15801.091968905122, "count": 966985, "self": 12241.024186512746, "children": { "SubprocessEnvManager._take_step": { "total": 3546.995186906017, "count": 966985, "self": 126.5962325267028, "children": { "TorchPolicy.evaluate": { "total": 3420.398954379314, "count": 1739784, "self": 3420.398954379314 } } }, "workers": { "total": 13.072595486359205, "count": 966984, "self": 0.0, "children": { "worker_root": { "total": 34491.274311717425, "count": 966984, "is_parallel": true, "self": 24744.850100534735, "children": { "steps_from_proto": { "total": 0.11729780008317903, "count": 142, "is_parallel": true, "self": 0.02500570082338527, "children": { "_process_rank_one_or_two_observation": { "total": 0.09229209925979376, "count": 568, "is_parallel": true, "self": 0.09229209925979376 } } }, "UnityEnvironment.step": { "total": 9746.306913382607, "count": 966984, "is_parallel": true, "self": 497.49245673097903, "children": { "UnityEnvironment._generate_step_input": { "total": 417.32924795680447, "count": 966984, "is_parallel": true, "self": 417.32924795680447 }, "communicator.exchange": { "total": 7202.096342267643, "count": 966984, "is_parallel": true, "self": 7202.096342267643 }, "steps_from_proto": { "total": 1629.38886642718, "count": 1933968, "is_parallel": true, "self": 349.3434953748365, "children": { "_process_rank_one_or_two_observation": { "total": 1280.0453710523434, "count": 7735872, "is_parallel": true, "self": 1280.0453710523434 } } } } } } } } } } }, "trainer_advance": { "total": 18673.514581063006, "count": 966984, "self": 138.87641985644586, "children": { "process_trajectory": { "total": 4110.245011105493, "count": 966984, "self": 4106.549847305461, "children": { "RLTrainer._checkpoint": { "total": 3.695163800031878, "count": 28, "self": 3.695163800031878 } } }, "_update_policy": { "total": 14424.393150101067, "count": 673, "self": 1926.2894451007014, "children": { "TorchPOCAOptimizer.update": { "total": 12498.103705000365, "count": 20190, "self": 12498.103705000365 } } } } } } }, "trainer_threads": { "total": 2.300017513334751e-06, "count": 1, "self": 2.300017513334751e-06 }, "TrainerController._save_models": { "total": 0.17457269999431446, "count": 1, "self": 0.008668499940540642, "children": { "RLTrainer._checkpoint": { "total": 0.16590420005377382, "count": 1, "self": 0.16590420005377382 } } } } } } }