{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4686238765716553, "min": 1.4124062061309814, "max": 3.2957513332366943, "count": 1918 }, "SoccerTwos.Policy.Entropy.sum": { "value": 26646.7109375, "min": 25450.26953125, "max": 115394.265625, "count": 1918 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 52.287234042553195, "min": 38.208, "max": 999.0, "count": 1918 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19660.0, "min": 13836.0, "max": 26264.0, "count": 1918 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1789.9904293150914, "min": 1190.989605084076, "max": 1798.454766607555, "count": 1912 }, "SoccerTwos.Self-play.ELO.sum": { "value": 336518.2007112372, "min": 2386.3474062038426, "max": 448126.2799177739, "count": 1912 }, "SoccerTwos.Step.mean": { "value": 19179990.0, "min": 9150.0, "max": 19179990.0, "count": 1918 }, "SoccerTwos.Step.sum": { "value": 19179990.0, "min": 9150.0, "max": 19179990.0, "count": 1918 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.02112666517496109, "min": -0.12706585228443146, "max": 0.2018619030714035, "count": 1918 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 3.971813201904297, "min": -28.73523712158203, "max": 27.736572265625, "count": 1918 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0276110228151083, "min": -0.12947994470596313, "max": 0.20456001162528992, "count": 1918 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 5.1908721923828125, "min": -28.175561904907227, "max": 28.968101501464844, "count": 1918 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1918 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1918 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.2413936155907651, "min": -0.6370285712182522, "max": 0.4357126222073453, "count": 1918 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 45.38199973106384, "min": -69.23000001907349, "max": 57.187599539756775, "count": 1918 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.2413936155907651, "min": -0.6370285712182522, "max": 0.4357126222073453, "count": 1918 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 45.38199973106384, "min": -69.23000001907349, "max": 57.187599539756775, "count": 1918 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1918 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1918 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.02269799134034353, "min": 0.009474151117804771, "max": 0.02723043248455118, "count": 930 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.02269799134034353, "min": 0.009474151117804771, "max": 0.02723043248455118, "count": 930 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11184387827912966, "min": 0.0007547088331193663, "max": 0.12730500722924867, "count": 930 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11184387827912966, "min": 0.0007547088331193663, "max": 0.12730500722924867, "count": 930 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11342640891671181, "min": 0.0007653566640025626, "max": 0.13085049639145532, "count": 930 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11342640891671181, "min": 0.0007653566640025626, "max": 0.13085049639145532, "count": 930 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 930 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 930 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 930 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 930 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 930 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 930 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1707445094", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos/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": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1707489081" }, "total": 43987.138019727005, "count": 1, "self": 10.011347937004757, "children": { "run_training.setup": { "total": 0.12375941599998441, "count": 1, "self": 0.12375941599998441 }, "TrainerController.start_learning": { "total": 43977.002912374, "count": 1, "self": 31.654629751596076, "children": { "TrainerController._reset_env": { "total": 7.057183964995659, "count": 96, "self": 7.057183964995659 }, "TrainerController.advance": { "total": 43938.09238910042, "count": 1332763, "self": 35.38949171025888, "children": { "env_step": { "total": 34021.78582067748, "count": 1332763, "self": 26111.781371965386, "children": { "SubprocessEnvManager._take_step": { "total": 7891.1215795483895, "count": 1332763, "self": 210.708865721429, "children": { "TorchPolicy.evaluate": { "total": 7680.4127138269605, "count": 2408840, "self": 7680.4127138269605 } } }, "workers": { "total": 18.88286916370629, "count": 1332762, "self": 0.0, "children": { "worker_root": { "total": 43899.37106761412, "count": 1332762, "is_parallel": true, "self": 21887.230890617033, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.010409866000031798, "count": 2, "is_parallel": true, "self": 0.005038005000074008, "children": { "_process_rank_one_or_two_observation": { "total": 0.005371860999957789, "count": 8, "is_parallel": true, "self": 0.005371860999957789 } } }, "UnityEnvironment.step": { "total": 0.0414876090000007, "count": 1, "is_parallel": true, "self": 0.001229048999960014, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0009126200000082463, "count": 1, "is_parallel": true, "self": 0.0009126200000082463 }, "communicator.exchange": { "total": 0.03575425499997209, "count": 1, "is_parallel": true, "self": 0.03575425499997209 }, "steps_from_proto": { "total": 0.0035916850000603517, "count": 2, "is_parallel": true, "self": 0.0006635470001015165, "children": { "_process_rank_one_or_two_observation": { "total": 0.0029281379999588353, "count": 8, "is_parallel": true, "self": 0.0029281379999588353 } } } } } } }, "UnityEnvironment.step": { "total": 22011.927295866117, "count": 1332761, "is_parallel": true, "self": 1458.431733110956, "children": { "UnityEnvironment._generate_step_input": { "total": 944.730512323051, "count": 1332761, "is_parallel": true, "self": 944.730512323051 }, "communicator.exchange": { "total": 15099.590473116243, "count": 1332761, "is_parallel": true, "self": 15099.590473116243 }, "steps_from_proto": { "total": 4509.174577315867, "count": 2665522, "is_parallel": true, "self": 746.4641492398005, "children": { "_process_rank_one_or_two_observation": { "total": 3762.710428076067, "count": 10662088, "is_parallel": true, "self": 3762.710428076067 } } } } }, "steps_from_proto": { "total": 0.21288113097114092, "count": 190, "is_parallel": true, "self": 0.043240759022978636, "children": { "_process_rank_one_or_two_observation": { "total": 0.16964037194816228, "count": 760, "is_parallel": true, "self": 0.16964037194816228 } } } } } } } } }, "trainer_advance": { "total": 9880.91707671268, "count": 1332762, "self": 250.2854035456603, "children": { "process_trajectory": { "total": 4646.082872691048, "count": 1332762, "self": 4637.307923756058, "children": { "RLTrainer._checkpoint": { "total": 8.774948934989652, "count": 38, "self": 8.774948934989652 } } }, "_update_policy": { "total": 4984.548800475973, "count": 930, "self": 2867.820134074186, "children": { "TorchPOCAOptimizer.update": { "total": 2116.7286664017865, "count": 27900, "self": 2116.7286664017865 } } } } } } }, "trainer_threads": { "total": 1.2669988791458309e-06, "count": 1, "self": 1.2669988791458309e-06 }, "TrainerController._save_models": { "total": 0.1987082899941015, "count": 1, "self": 0.0018980379900312982, "children": { "RLTrainer._checkpoint": { "total": 0.1968102520040702, "count": 1, "self": 0.1968102520040702 } } } } } } }