{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 0.7528050541877747, "min": 0.744097113609314, "max": 3.2958080768585205, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 15875.1533203125, "min": 13482.884765625, "max": 145545.296875, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 72.8840579710145, "min": 46.714285714285715, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20116.0, "min": 14468.0, "max": 29368.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1521.6200062848854, "min": 1197.6965959407885, "max": 1542.2184162523804, "count": 4962 }, "SoccerTwos.Self-play.ELO.sum": { "value": 209983.5608673142, "min": 2397.2224862700255, "max": 305839.4694683634, "count": 4962 }, "SoccerTwos.Step.mean": { "value": 49999984.0, "min": 9700.0, "max": 49999984.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999984.0, "min": 9700.0, "max": 49999984.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.03433554247021675, "min": -0.1411672830581665, "max": 0.1276848018169403, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.703969478607178, "min": -17.780824661254883, "max": 16.854393005371094, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03536888584494591, "min": -0.14170502126216888, "max": 0.12184350937604904, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -4.845537185668945, "min": -18.577476501464844, "max": 16.083343505859375, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.13587883049554197, "min": -0.676000000834465, "max": 0.41523007432320963, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -18.61539977788925, "min": -59.55239975452423, "max": 60.76680016517639, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.13587883049554197, "min": -0.676000000834465, "max": 0.41523007432320963, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -18.61539977788925, "min": -59.55239975452423, "max": 60.76680016517639, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014076471507238845, "min": 0.010697605286259204, "max": 0.03338661268353462, "count": 2417 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014076471507238845, "min": 0.010697605286259204, "max": 0.03338661268353462, "count": 2417 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10066431562105814, "min": 3.947502089355718e-07, "max": 0.11748221243421236, "count": 2417 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10066431562105814, "min": 3.947502089355718e-07, "max": 0.11748221243421236, "count": 2417 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10089455048243205, "min": 4.6868527050492046e-07, "max": 0.11859208767612775, "count": 2417 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10089455048243205, "min": 4.6868527050492046e-07, "max": 0.11859208767612775, "count": 2417 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 2.312199743199514e-07, "min": 2.312199743199514e-07, "max": 0.0008996049360438962, "count": 2417 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 2.312199743199514e-07, "min": 2.312199743199514e-07, "max": 0.0008996049360438962, "count": 2417 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.10002567999999998, "min": 0.10002567999999998, "max": 0.19995610400000002, "count": 2417 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.10002567999999998, "min": 0.10002567999999998, "max": 0.19995610400000002, "count": 2417 }, "SoccerTwos.Policy.Beta.mean": { "value": 1.1281431999999728e-05, "min": 1.1281431999999728e-05, "max": 0.0049978095896000005, "count": 2417 }, "SoccerTwos.Policy.Beta.sum": { "value": 1.1281431999999728e-05, "min": 1.1281431999999728e-05, "max": 0.0049978095896000005, "count": 2417 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1683497116", "python_version": "3.10.9 (main, Mar 8 2023, 10:47:38) [GCC 11.2.0]", "command_line_arguments": "/home/carlos/miniconda3/envs/textgen/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.0+cu117", "numpy_version": "1.21.2", "end_time_seconds": "1683597241" }, "total": 100126.71848519999, "count": 1, "self": 0.21982578100869432, "children": { "run_training.setup": { "total": 0.015976239000337955, "count": 1, "self": 0.015976239000337955 }, "TrainerController.start_learning": { "total": 100126.48268317999, "count": 1, "self": 60.53738365323807, "children": { "TrainerController._reset_env": { "total": 7.498064547096419, "count": 250, "self": 7.498064547096419 }, "TrainerController.advance": { "total": 100058.25947812066, "count": 3393920, "self": 53.90755338271265, "children": { "env_step": { "total": 81884.61852085213, "count": 3393920, "self": 60674.191123298355, "children": { "SubprocessEnvManager._take_step": { "total": 21168.547460421425, "count": 3393920, "self": 324.84548636215914, "children": { "TorchPolicy.evaluate": { "total": 20843.701974059266, "count": 6294770, "self": 20843.701974059266 } } }, "workers": { "total": 41.87993713234982, "count": 3393920, "self": 0.0, "children": { "worker_root": { "total": 99973.0472672242, "count": 3393920, "is_parallel": true, "self": 46078.17114818673, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00195840800051883, "count": 2, "is_parallel": true, "self": 0.0005004350000490376, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014579730004697922, "count": 8, "is_parallel": true, "self": 0.0014579730004697922 } } }, "UnityEnvironment.step": { "total": 0.027323311000145623, "count": 1, "is_parallel": true, "self": 0.0005018440001549607, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047084499965421855, "count": 1, "is_parallel": true, "self": 0.00047084499965421855 }, "communicator.exchange": { "total": 0.02492631400036771, "count": 1, "is_parallel": true, "self": 0.02492631400036771 }, "steps_from_proto": { "total": 0.0014243079999687325, "count": 2, "is_parallel": true, "self": 0.0002603189996079891, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011639890003607434, "count": 8, "is_parallel": true, "self": 0.0011639890003607434 } } } } } } }, "UnityEnvironment.step": { "total": 53894.52075054261, "count": 3393919, "is_parallel": true, "self": 1622.7739945919457, "children": { "UnityEnvironment._generate_step_input": { "total": 1132.0179813537943, "count": 3393919, "is_parallel": true, "self": 1132.0179813537943 }, "communicator.exchange": { "total": 46619.90814841098, "count": 3393919, "is_parallel": true, "self": 46619.90814841098 }, "steps_from_proto": { "total": 4519.820626185885, "count": 6787838, "is_parallel": true, "self": 808.7526396262397, "children": { "_process_rank_one_or_two_observation": { "total": 3711.0679865596453, "count": 27151352, "is_parallel": true, "self": 3711.0679865596453 } } } } }, "steps_from_proto": { "total": 0.355368494862887, "count": 498, "is_parallel": true, "self": 0.0627699819551708, "children": { "_process_rank_one_or_two_observation": { "total": 0.2925985129077162, "count": 1992, "is_parallel": true, "self": 0.2925985129077162 } } } } } } } } }, "trainer_advance": { "total": 18119.733403885803, "count": 3393920, "self": 509.5392241690279, "children": { "process_trajectory": { "total": 7896.541462817081, "count": 3393920, "self": 7877.550474918095, "children": { "RLTrainer._checkpoint": { "total": 18.990987898986532, "count": 100, "self": 18.990987898986532 } } }, "_update_policy": { "total": 9713.652716899693, "count": 2417, "self": 6110.9646856947, "children": { "TorchPOCAOptimizer.update": { "total": 3602.688031204992, "count": 72510, "self": 3602.688031204992 } } } } } } }, "trainer_threads": { "total": 5.809997674077749e-07, "count": 1, "self": 5.809997674077749e-07 }, "TrainerController._save_models": { "total": 0.18775627799914218, "count": 1, "self": 0.001825260987970978, "children": { "RLTrainer._checkpoint": { "total": 0.1859310170111712, "count": 1, "self": 0.1859310170111712 } } } } } } }