{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.285967230796814, "min": 1.2675200700759888, "max": 3.295814037322998, "count": 853 }, "SoccerTwos.Policy.Entropy.sum": { "value": 25966.25, "min": 22325.609375, "max": 105466.03125, "count": 853 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 97.84313725490196, "min": 49.05940594059406, "max": 925.0, "count": 853 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19960.0, "min": 5364.0, "max": 29600.0, "count": 853 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1480.4279381383674, "min": 1196.131789494324, "max": 1522.0611629451164, "count": 850 }, "SoccerTwos.Self-play.ELO.sum": { "value": 151003.64969011347, "min": 2392.263578988648, "max": 295950.4051838331, "count": 850 }, "SoccerTwos.Step.mean": { "value": 8529926.0, "min": 9816.0, "max": 8529926.0, "count": 853 }, "SoccerTwos.Step.sum": { "value": 8529926.0, "min": 9816.0, "max": 8529926.0, "count": 853 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.020283233374357224, "min": -0.1126069724559784, "max": 0.12560239434242249, "count": 853 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 2.0486066341400146, "min": -15.31454849243164, "max": 15.44909381866455, "count": 853 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.01970083825290203, "min": -0.11717960238456726, "max": 0.12388100475072861, "count": 853 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.9897847175598145, "min": -15.936426162719727, "max": 15.237363815307617, "count": 853 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 853 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 853 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.055607922006361554, "min": -0.5, "max": 0.500690323203021, "count": 853 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 5.616400122642517, "min": -51.106799960136414, "max": 50.08020043373108, "count": 853 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.055607922006361554, "min": -0.5, "max": 0.500690323203021, "count": 853 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 5.616400122642517, "min": -51.106799960136414, "max": 50.08020043373108, "count": 853 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 853 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 853 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.0493208258546656, "min": 0.0114828991171089, "max": 0.0493208258546656, "count": 170 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.0493208258546656, "min": 0.0114828991171089, "max": 0.0493208258546656, "count": 170 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.029093711879104377, "min": 0.0011735607974696905, "max": 0.03776841139420867, "count": 170 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.029093711879104377, "min": 0.0011735607974696905, "max": 0.03776841139420867, "count": 170 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.031326058581471444, "min": 0.0011769584967987613, "max": 0.04217576038092375, "count": 170 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.031326058581471444, "min": 0.0011769584967987613, "max": 0.04217576038092375, "count": 170 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0009957384654261535, "min": 0.0009957384654261535, "max": 0.0009999748010025198, "count": 170 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0009957384654261535, "min": 0.0009957384654261535, "max": 0.0009999748010025198, "count": 170 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.2493607697499999, "min": 0.2493607697499999, "max": 0.2499962201499999, "count": 170 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.2493607697499999, "min": 0.2493607697499999, "max": 0.2499962201499999, "count": 170 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.004978734940349999, "min": 0.004978734940349999, "max": 0.00499987425699, "count": 170 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.004978734940349999, "min": 0.004978734940349999, "max": 0.00499987425699, "count": 170 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1699147128", "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\\JoshC\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos/SoccerTwos.exe --run-id=Match3X --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1699162773" }, "total": 15644.935624699996, "count": 1, "self": 4.19003050000174, "children": { "run_training.setup": { "total": 0.14043479999236297, "count": 1, "self": 0.14043479999236297 }, "TrainerController.start_learning": { "total": 15640.605159400002, "count": 1, "self": 8.876793300325517, "children": { "TrainerController._reset_env": { "total": 8.399447100047837, "count": 423, "self": 8.399447100047837 }, "TrainerController.advance": { "total": 15623.215789099617, "count": 605029, "self": 9.197971106797922, "children": { "env_step": { "total": 8817.819561292636, "count": 605029, "self": 4854.33211369683, "children": { "SubprocessEnvManager._take_step": { "total": 3957.8022943981923, "count": 605029, "self": 63.435529397349455, "children": { "TorchPolicy.evaluate": { "total": 3894.366765000843, "count": 1127378, "self": 3894.366765000843 } } }, "workers": { "total": 5.685153197613545, "count": 605028, "self": 0.0, "children": { "worker_root": { "total": 15625.389314606888, "count": 605028, "is_parallel": true, "self": 11742.094659000679, "children": { "steps_from_proto": { "total": 0.4215285999234766, "count": 846, "is_parallel": true, "self": 0.07961020030779764, "children": { "_process_rank_one_or_two_observation": { "total": 0.34191839961567894, "count": 3384, "is_parallel": true, "self": 0.34191839961567894 } } }, "UnityEnvironment.step": { "total": 3882.8731270062854, "count": 605028, "is_parallel": true, "self": 195.46075548956287, "children": { "UnityEnvironment._generate_step_input": { "total": 156.97058519966959, "count": 605028, "is_parallel": true, "self": 156.97058519966959 }, "communicator.exchange": { "total": 2948.478467908775, "count": 605028, "is_parallel": true, "self": 2948.478467908775 }, "steps_from_proto": { "total": 581.9633184082777, "count": 1210056, "is_parallel": true, "self": 112.42234582995297, "children": { "_process_rank_one_or_two_observation": { "total": 469.5409725783247, "count": 4840224, "is_parallel": true, "self": 469.5409725783247 } } } } } } } } } } }, "trainer_advance": { "total": 6796.198256700183, "count": 605028, "self": 61.92319880602008, "children": { "process_trajectory": { "total": 2843.9778707941587, "count": 605028, "self": 2842.233458594157, "children": { "RLTrainer._checkpoint": { "total": 1.744412200001534, "count": 17, "self": 1.744412200001534 } } }, "_update_policy": { "total": 3890.2971871000045, "count": 170, "self": 2448.599131897863, "children": { "TorchPOCAOptimizer.update": { "total": 1441.6980552021414, "count": 17000, "self": 1441.6980552021414 } } } } } } }, "trainer_threads": { "total": 7.00005330145359e-07, "count": 1, "self": 7.00005330145359e-07 }, "TrainerController._save_models": { "total": 0.1131292000063695, "count": 1, "self": 0.004963100014720112, "children": { "RLTrainer._checkpoint": { "total": 0.10816609999164939, "count": 1, "self": 0.10816609999164939 } } } } } } }