{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.0170891284942627, "min": 1.8789044618606567, "max": 3.295760154724121, "count": 496 }, "SoccerTwos.Policy.Entropy.sum": { "value": 44408.234375, "min": 21455.42578125, "max": 154475.640625, "count": 496 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 67.27777777777777, "min": 44.81651376146789, "max": 999.0, "count": 496 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19376.0, "min": 16228.0, "max": 23912.0, "count": 496 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1508.1163604947023, "min": 1182.8421708455958, "max": 1519.6095622292594, "count": 487 }, "SoccerTwos.Self-play.ELO.sum": { "value": 217168.75591123712, "min": 2369.2644624010436, "max": 323656.72171062784, "count": 487 }, "SoccerTwos.Step.mean": { "value": 4959977.0, "min": 9972.0, "max": 4959977.0, "count": 496 }, "SoccerTwos.Step.sum": { "value": 4959977.0, "min": 9972.0, "max": 4959977.0, "count": 496 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.015529231168329716, "min": -0.16310332715511322, "max": 0.27335065603256226, "count": 496 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 2.2517385482788086, "min": -25.770326614379883, "max": 31.36713409423828, "count": 496 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.010477464646100998, "min": -0.1623694747686386, "max": 0.2630256414413452, "count": 496 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.5192323923110962, "min": -25.654376983642578, "max": 31.72089385986328, "count": 496 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 496 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 496 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.1311737927897223, "min": -0.55129166568319, "max": 0.4727384608525496, "count": 496 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -19.020199954509735, "min": -48.20039987564087, "max": 62.700600147247314, "count": 496 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.1311737927897223, "min": -0.55129166568319, "max": 0.4727384608525496, "count": 496 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -19.020199954509735, "min": -48.20039987564087, "max": 62.700600147247314, "count": 496 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 496 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 496 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.02880678440108871, "min": 0.019772288502038767, "max": 0.031095777271548285, "count": 238 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.02880678440108871, "min": 0.019772288502038767, "max": 0.031095777271548285, "count": 238 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.07831853032112121, "min": 0.00012128652103874918, "max": 0.11398706659674644, "count": 238 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.07831853032112121, "min": 0.00012128652103874918, "max": 0.11398706659674644, "count": 238 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0830160591751337, "min": 0.0001215280617182702, "max": 0.12332418784499169, "count": 238 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0830160591751337, "min": 0.0001215280617182702, "max": 0.12332418784499169, "count": 238 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0006000000000000002, "min": 0.0006000000000000002, "max": 0.0006000000000000004, "count": 238 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0006000000000000002, "min": 0.0006000000000000002, "max": 0.0006000000000000004, "count": 238 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.19999999999999993, "min": 0.1999999999999999, "max": 0.19999999999999993, "count": 238 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.19999999999999993, "min": 0.1999999999999999, "max": 0.19999999999999993, "count": 238 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 238 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 238 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1696221287", "python_version": "3.9.13 (main, Aug 25 2022, 18:29:29) \n[Clang 12.0.0 ]", "command_line_arguments": "/Users/min/opt/anaconda3/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=impatientSoccerPlayer --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0", "numpy_version": "1.21.5", "end_time_seconds": "1696243759" }, "total": 22472.209734666, "count": 1, "self": 0.8138606240027002, "children": { "run_training.setup": { "total": 0.05455804200000003, "count": 1, "self": 0.05455804200000003 }, "TrainerController.start_learning": { "total": 22471.341316, "count": 1, "self": 5.888035890762694, "children": { "TrainerController._reset_env": { "total": 12.478927579004504, "count": 245, "self": 12.478927579004504 }, "TrainerController.advance": { "total": 22452.74893290523, "count": 369444, "self": 5.0823435700185655, "children": { "env_step": { "total": 5304.438053194684, "count": 369444, "self": 4300.56540087665, "children": { "SubprocessEnvManager._take_step": { "total": 1000.1727141657639, "count": 369444, "self": 26.993620021142306, "children": { "TorchPolicy.evaluate": { "total": 973.1790941446216, "count": 694912, "self": 973.1790941446216 } } }, "workers": { "total": 3.6999381522700503, "count": 369444, "self": 0.0, "children": { "worker_root": { "total": 22397.987685314532, "count": 369444, "is_parallel": true, "self": 18728.82446173286, "children": { "steps_from_proto": { "total": 0.3672039240000524, "count": 490, "is_parallel": true, "self": 0.06699814807154514, "children": { "_process_rank_one_or_two_observation": { "total": 0.3002057759285073, "count": 1960, "is_parallel": true, "self": 0.3002057759285073 } } }, "UnityEnvironment.step": { "total": 3668.796019657671, "count": 369444, "is_parallel": true, "self": 287.1529651292035, "children": { "UnityEnvironment._generate_step_input": { "total": 120.71345707751362, "count": 369444, "is_parallel": true, "self": 120.71345707751362 }, "communicator.exchange": { "total": 2755.4013959973745, "count": 369444, "is_parallel": true, "self": 2755.4013959973745 }, "steps_from_proto": { "total": 505.52820145357924, "count": 738888, "is_parallel": true, "self": 86.93492432616353, "children": { "_process_rank_one_or_two_observation": { "total": 418.5932771274157, "count": 2955552, "is_parallel": true, "self": 418.5932771274157 } } } } } } } } } } }, "trainer_advance": { "total": 17143.228536140527, "count": 369444, "self": 44.14212389020031, "children": { "process_trajectory": { "total": 2110.2125743713127, "count": 369444, "self": 2108.1162062453136, "children": { "RLTrainer._checkpoint": { "total": 2.0963681259991063, "count": 9, "self": 2.0963681259991063 } } }, "_update_policy": { "total": 14988.873837879013, "count": 239, "self": 655.389815831033, "children": { "TorchPOCAOptimizer.update": { "total": 14333.48402204798, "count": 14402, "self": 14333.48402204798 } } } } } } }, "trainer_threads": { "total": 1.2080017768312246e-06, "count": 1, "self": 1.2080017768312246e-06 }, "TrainerController._save_models": { "total": 0.22541841699785437, "count": 1, "self": 0.0033028759971784893, "children": { "RLTrainer._checkpoint": { "total": 0.22211554100067588, "count": 1, "self": 0.22211554100067588 } } } } } } }