{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.060180902481079, "min": 2.0366084575653076, "max": 3.2957489490509033, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 37775.4765625, "min": 25640.1796875, "max": 124540.796875, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 64.23684210526316, "min": 43.41228070175438, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19528.0, "min": 16252.0, "max": 23688.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1568.1828422437923, "min": 1184.8733249128697, "max": 1591.4549585676755, "count": 490 }, "SoccerTwos.Self-play.ELO.sum": { "value": 238363.79202105643, "min": 2369.7466498257395, "max": 354290.0691976056, "count": 490 }, "SoccerTwos.Step.mean": { "value": 4999996.0, "min": 9488.0, "max": 4999996.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999996.0, "min": 9488.0, "max": 4999996.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.022454505786299706, "min": -0.08605106920003891, "max": 0.17248587310314178, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -3.4355392456054688, "min": -16.349702835083008, "max": 21.856319427490234, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.024616263806819916, "min": -0.08110318332910538, "max": 0.16757957637310028, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.7662882804870605, "min": -15.08519172668457, "max": 22.9644718170166, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.054274510713963726, "min": -0.5384615384615384, "max": 0.37619402426392284, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -8.30400013923645, "min": -54.3367999792099, "max": 61.355800092220306, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.054274510713963726, "min": -0.5384615384615384, "max": 0.37619402426392284, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -8.30400013923645, "min": -54.3367999792099, "max": 61.355800092220306, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.012937161442823707, "min": 0.010601800406584516, "max": 0.023501068291564783, "count": 240 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.012937161442823707, "min": 0.010601800406584516, "max": 0.023501068291564783, "count": 240 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10735289230942727, "min": 0.00017051689076955274, "max": 0.11434300442536673, "count": 240 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10735289230942727, "min": 0.00017051689076955274, "max": 0.11434300442536673, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.1099305289487044, "min": 0.0001683511588150092, "max": 0.11686786686380704, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.1099305289487044, "min": 0.0001683511588150092, "max": 0.11686786686380704, "count": 240 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 240 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 240 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1727369591", "python_version": "3.10.12 (main, Aug 16 2023, 05:39:07) [GCC 12.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos.x86_64 --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": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1727388678" }, "total": 19087.34006651299, "count": 1, "self": 0.27230525598861277, "children": { "run_training.setup": { "total": 0.02452742398600094, "count": 1, "self": 0.02452742398600094 }, "TrainerController.start_learning": { "total": 19087.043233833014, "count": 1, "self": 9.329972284089308, "children": { "TrainerController._reset_env": { "total": 2.7176319319405593, "count": 25, "self": 2.7176319319405593 }, "TrainerController.advance": { "total": 19074.795949301973, "count": 339797, "self": 9.569373899052152, "children": { "env_step": { "total": 7215.81410285164, "count": 339797, "self": 5645.826248357742, "children": { "SubprocessEnvManager._take_step": { "total": 1564.5003681878443, "count": 339797, "self": 58.23159076765296, "children": { "TorchPolicy.evaluate": { "total": 1506.2687774201913, "count": 631724, "self": 1506.2687774201913 } } }, "workers": { "total": 5.487486306054052, "count": 339797, "self": 0.0, "children": { "worker_root": { "total": 19073.511663525744, "count": 339797, "is_parallel": true, "self": 14493.58961916584, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0033430790062993765, "count": 2, "is_parallel": true, "self": 0.0014058079686947167, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019372710376046598, "count": 8, "is_parallel": true, "self": 0.0019372710376046598 } } }, "UnityEnvironment.step": { "total": 0.022890007006935775, "count": 1, "is_parallel": true, "self": 0.0005640779854729772, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005011320172343403, "count": 1, "is_parallel": true, "self": 0.0005011320172343403 }, "communicator.exchange": { "total": 0.020044882025104016, "count": 1, "is_parallel": true, "self": 0.020044882025104016 }, "steps_from_proto": { "total": 0.0017799149791244417, "count": 2, "is_parallel": true, "self": 0.0004491359868552536, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013307789922691882, "count": 8, "is_parallel": true, "self": 0.0013307789922691882 } } } } } } }, "UnityEnvironment.step": { "total": 4579.874745954963, "count": 339796, "is_parallel": true, "self": 271.2976286878402, "children": { "UnityEnvironment._generate_step_input": { "total": 216.71171673206845, "count": 339796, "is_parallel": true, "self": 216.71171673206845 }, "communicator.exchange": { "total": 3261.8513107775652, "count": 339796, "is_parallel": true, "self": 3261.8513107775652 }, "steps_from_proto": { "total": 830.0140897574893, "count": 679592, "is_parallel": true, "self": 166.4034510877682, "children": { "_process_rank_one_or_two_observation": { "total": 663.6106386697211, "count": 2718368, "is_parallel": true, "self": 663.6106386697211 } } } } }, "steps_from_proto": { "total": 0.04729840494110249, "count": 48, "is_parallel": true, "self": 0.009920554468408227, "children": { "_process_rank_one_or_two_observation": { "total": 0.03737785047269426, "count": 192, "is_parallel": true, "self": 0.03737785047269426 } } } } } } } } }, "trainer_advance": { "total": 11849.412472551281, "count": 339797, "self": 67.42974598979345, "children": { "process_trajectory": { "total": 1605.39068581225, "count": 339797, "self": 1603.2557784811943, "children": { "RLTrainer._checkpoint": { "total": 2.1349073310557287, "count": 10, "self": 2.1349073310557287 } } }, "_update_policy": { "total": 10176.592040749238, "count": 240, "self": 823.4263972544286, "children": { "TorchPOCAOptimizer.update": { "total": 9353.165643494809, "count": 7203, "self": 9353.165643494809 } } } } } } }, "trainer_threads": { "total": 1.381005859002471e-06, "count": 1, "self": 1.381005859002471e-06 }, "TrainerController._save_models": { "total": 0.19967893400462344, "count": 1, "self": 0.001612991007277742, "children": { "RLTrainer._checkpoint": { "total": 0.1980659429973457, "count": 1, "self": 0.1980659429973457 } } } } } } }