{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.676177501678467, "min": 2.598740339279175, "max": 3.295732021331787, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 65855.375, "min": 18855.1015625, "max": 122805.3046875, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 435.8333333333333, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 10460.0, "max": 31968.0, "count": 500 }, "SoccerTwos.Step.mean": { "value": 4999276.0, "min": 9000.0, "max": 4999276.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999276.0, "min": 9000.0, "max": 4999276.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -4.848902790399734e-07, "min": -0.012399966828525066, "max": 0.10119228065013885, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.848902790399734e-06, "min": -0.1487995982170105, "max": 1.720268726348877, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -1.571019993207301e-06, "min": -0.012112118303775787, "max": 0.10118485242128372, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -1.571020038682036e-05, "min": -0.14534541964530945, "max": 1.7201424837112427, "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": 0.0, "min": -0.4666666666666667, "max": 0.21615385092221773, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -7.715399980545044, "max": 2.8100000619888306, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.4666666666666667, "max": 0.21615385092221773, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -7.715399980545044, "max": 2.8100000619888306, "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.Self-play.ELO.mean": { "value": 1183.047677848624, "min": 1183.047677848624, "max": 1203.94634974305, "count": 148 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2366.095355697248, "min": 2366.095355697248, "max": 14400.0, "count": 148 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016676351289970626, "min": 0.01073535617027422, "max": 0.024217968597076832, "count": 229 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016676351289970626, "min": 0.01073535617027422, "max": 0.024217968597076832, "count": 229 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 1.5972951405984758e-09, "min": 1.405121607955806e-09, "max": 0.005868740465181569, "count": 229 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 1.5972951405984758e-09, "min": 1.405121607955806e-09, "max": 0.005868740465181569, "count": 229 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 2.154069829914581e-09, "min": 1.990526439972958e-09, "max": 0.005896581600730618, "count": 229 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 2.154069829914581e-09, "min": 1.990526439972958e-09, "max": 0.005896581600730618, "count": 229 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 229 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 229 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 229 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 229 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 229 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 229 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1692521085", "python_version": "3.9.17 (main, Jul 5 2023, 15:35:09) \n[Clang 14.0.6 ]", "command_line_arguments": "/Users/saudi/anaconda3/envs/deep-rl-class/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/CODE_OF_CONDUCT/SoccerTwos.exe --run-id=SoccerTwos --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": "1.21.2", "end_time_seconds": "1692541305" }, "total": 20219.925531292, "count": 1, "self": 0.24657999999908498, "children": { "run_training.setup": { "total": 0.012521166999999167, "count": 1, "self": 0.012521166999999167 }, "TrainerController.start_learning": { "total": 20219.666430125002, "count": 1, "self": 3.3699819468420174, "children": { "TrainerController._reset_env": { "total": 3.7819047049947443, "count": 25, "self": 3.7819047049947443 }, "TrainerController.advance": { "total": 20212.416194723162, "count": 325056, "self": 3.4083157107997977, "children": { "env_step": { "total": 16284.679422255322, "count": 325056, "self": 15695.868954123802, "children": { "SubprocessEnvManager._take_step": { "total": 586.434282944386, "count": 325056, "self": 18.290819188387786, "children": { "TorchPolicy.evaluate": { "total": 568.1434637559983, "count": 646530, "self": 568.1434637559983 } } }, "workers": { "total": 2.3761851871328883, "count": 325056, "self": 0.0, "children": { "worker_root": { "total": 20211.157416639457, "count": 325056, "is_parallel": true, "self": 5105.002463181883, "children": { "steps_from_proto": { "total": 0.03824129200130888, "count": 50, "is_parallel": true, "self": 0.00618012300261106, "children": { "_process_rank_one_or_two_observation": { "total": 0.03206116899869782, "count": 200, "is_parallel": true, "self": 0.03206116899869782 } } }, "UnityEnvironment.step": { "total": 15106.116712165573, "count": 325056, "is_parallel": true, "self": 39.546201843559174, "children": { "UnityEnvironment._generate_step_input": { "total": 227.2118996418793, "count": 325056, "is_parallel": true, "self": 227.2118996418793 }, "communicator.exchange": { "total": 14383.597966565889, "count": 325056, "is_parallel": true, "self": 14383.597966565889 }, "steps_from_proto": { "total": 455.76064411424545, "count": 650112, "is_parallel": true, "self": 60.1256898787924, "children": { "_process_rank_one_or_two_observation": { "total": 395.63495423545305, "count": 2600448, "is_parallel": true, "self": 395.63495423545305 } } } } } } } } } } }, "trainer_advance": { "total": 3924.3284567570417, "count": 325056, "self": 37.91353336326529, "children": { "process_trajectory": { "total": 622.8786449337781, "count": 325056, "self": 621.7951958087797, "children": { "RLTrainer._checkpoint": { "total": 1.083449124998424, "count": 10, "self": 1.083449124998424 } } }, "_update_policy": { "total": 3263.5362784599984, "count": 229, "self": 490.0581290929895, "children": { "TorchPOCAOptimizer.update": { "total": 2773.478149367009, "count": 6870, "self": 2773.478149367009 } } } } } } }, "trainer_threads": { "total": 5.000001692678779e-07, "count": 1, "self": 5.000001692678779e-07 }, "TrainerController._save_models": { "total": 0.0983482500014361, "count": 1, "self": 0.0022057500027585775, "children": { "RLTrainer._checkpoint": { "total": 0.09614249999867752, "count": 1, "self": 0.09614249999867752 } } } } } } }