{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2150719165802, "min": 3.170013427734375, "max": 3.2957265377044678, "count": 88 }, "SoccerTwos.Policy.Entropy.sum": { "value": 42490.390625, "min": 16325.6259765625, "max": 105463.203125, "count": 88 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 495.2, "max": 999.0, "count": 88 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 15380.0, "max": 27320.0, "count": 88 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1200.0979941689066, "min": 1193.0671509243548, "max": 1204.4035210473291, "count": 63 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2400.195988337813, "min": 2389.9140730166932, "max": 19188.856449368337, "count": 63 }, "SoccerTwos.Step.mean": { "value": 879414.0, "min": 9676.0, "max": 879414.0, "count": 88 }, "SoccerTwos.Step.sum": { "value": 879414.0, "min": 9676.0, "max": 879414.0, "count": 88 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0022735975217074156, "min": -0.10676523298025131, "max": -0.0012080572778359056, "count": 88 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.022735975682735443, "min": -1.494713306427002, "max": -0.018120858818292618, "count": 88 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0028971494175493717, "min": -0.10677098482847214, "max": -0.00031215374474413693, "count": 88 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.028971493244171143, "min": -1.4947937726974487, "max": -0.004682306200265884, "count": 88 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 88 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 88 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.4550599992275238, "max": 0.2824857064655849, "count": 88 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -9.101199984550476, "max": 3.9547998905181885, "count": 88 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.4550599992275238, "max": 0.2824857064655849, "count": 88 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -9.101199984550476, "max": 3.9547998905181885, "count": 88 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 88 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 88 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.012585476921716084, "min": 0.011764387342069919, "max": 0.021005486588304242, "count": 40 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.012585476921716084, "min": 0.011764387342069919, "max": 0.021005486588304242, "count": 40 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0008365886198589579, "min": 1.2928697022592435e-06, "max": 0.0063222938605273764, "count": 40 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0008365886198589579, "min": 1.2928697022592435e-06, "max": 0.0063222938605273764, "count": 40 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.000837781477215079, "min": 1.555102905588986e-06, "max": 0.006354990066029131, "count": 40 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.000837781477215079, "min": 1.555102905588986e-06, "max": 0.006354990066029131, "count": 40 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 40 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 40 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 40 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 40 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 40 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1701429137", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:34:57) [MSC v.1936 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1701430801" }, "total": 1664.0088754000608, "count": 1, "self": 0.09524330007843673, "children": { "run_training.setup": { "total": 0.136288300040178, "count": 1, "self": 0.136288300040178 }, "TrainerController.start_learning": { "total": 1663.7773437999422, "count": 1, "self": 1.1845473876455799, "children": { "TrainerController._reset_env": { "total": 3.6966400999808684, "count": 5, "self": 3.6966400999808684 }, "TrainerController.advance": { "total": 1658.7602074122988, "count": 57842, "self": 1.203146017040126, "children": { "env_step": { "total": 869.9707423954969, "count": 57842, "self": 662.7599132098258, "children": { "SubprocessEnvManager._take_step": { "total": 206.47988678875845, "count": 57842, "self": 6.4427419940475374, "children": { "TorchPolicy.evaluate": { "total": 200.0371447947109, "count": 114854, "self": 200.0371447947109 } } }, "workers": { "total": 0.7309423969127238, "count": 57842, "self": 0.0, "children": { "worker_root": { "total": 1655.4266972908517, "count": 57842, "is_parallel": true, "self": 1137.4915873962454, "children": { "steps_from_proto": { "total": 0.0071546999970451, "count": 10, "is_parallel": true, "self": 0.0015663999365642667, "children": { "_process_rank_one_or_two_observation": { "total": 0.005588300060480833, "count": 40, "is_parallel": true, "self": 0.005588300060480833 } } }, "UnityEnvironment.step": { "total": 517.9279551946092, "count": 57842, "is_parallel": true, "self": 25.801930344779976, "children": { "UnityEnvironment._generate_step_input": { "total": 20.350491013145074, "count": 57842, "is_parallel": true, "self": 20.350491013145074 }, "communicator.exchange": { "total": 388.40555692638736, "count": 57842, "is_parallel": true, "self": 388.40555692638736 }, "steps_from_proto": { "total": 83.36997691029683, "count": 115684, "is_parallel": true, "self": 17.866936698090285, "children": { "_process_rank_one_or_two_observation": { "total": 65.50304021220654, "count": 462736, "is_parallel": true, "self": 65.50304021220654 } } } } } } } } } } }, "trainer_advance": { "total": 787.5863189997617, "count": 57842, "self": 8.574956009048037, "children": { "process_trajectory": { "total": 116.95183569041546, "count": 57842, "self": 116.79685379052535, "children": { "RLTrainer._checkpoint": { "total": 0.15498189989011735, "count": 1, "self": 0.15498189989011735 } } }, "_update_policy": { "total": 662.0595273002982, "count": 41, "self": 108.21700470196083, "children": { "TorchPOCAOptimizer.update": { "total": 553.8425225983374, "count": 1206, "self": 553.8425225983374 } } } } } } }, "trainer_threads": { "total": 1.100008375942707e-06, "count": 1, "self": 1.100008375942707e-06 }, "TrainerController._save_models": { "total": 0.1359478000085801, "count": 1, "self": 0.006517199915833771, "children": { "RLTrainer._checkpoint": { "total": 0.12943060009274632, "count": 1, "self": 0.12943060009274632 } } } } } } }