{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6470953226089478, "min": 1.5953850746154785, "max": 2.3093199729919434, "count": 479 }, "SoccerTwos.Policy.Entropy.sum": { "value": 34523.1171875, "min": 29625.490234375, "max": 51072.29296875, "count": 479 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 51.21649484536083, "min": 41.720338983050844, "max": 83.73770491803279, "count": 479 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19872.0, "min": 14200.0, "max": 20692.0, "count": 479 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1608.7605317785462, "min": 1472.4185017158015, "max": 1627.1288522807756, "count": 479 }, "SoccerTwos.Self-play.ELO.sum": { "value": 312099.543165038, "min": 139141.5329085182, "max": 377112.46624928806, "count": 479 }, "SoccerTwos.Step.mean": { "value": 6829854.0, "min": 2049932.0, "max": 6829854.0, "count": 479 }, "SoccerTwos.Step.sum": { "value": 6829854.0, "min": 2049932.0, "max": 6829854.0, "count": 479 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.013270261697471142, "min": -0.14858590066432953, "max": 0.10823917388916016, "count": 479 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.5611605644226074, "min": -24.516674041748047, "max": 15.802919387817383, "count": 479 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.010980118997395039, "min": -0.1502770185470581, "max": 0.11209087818861008, "count": 479 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.1191630363464355, "min": -24.79570770263672, "max": 16.36526870727539, "count": 479 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 479 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 479 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.016830051501180224, "min": -0.4204434791336889, "max": 0.27019212658949726, "count": 479 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 3.248199939727783, "min": -55.13759970664978, "max": 49.95380002260208, "count": 479 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.016830051501180224, "min": -0.4204434791336889, "max": 0.27019212658949726, "count": 479 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 3.248199939727783, "min": -55.13759970664978, "max": 49.95380002260208, "count": 479 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 479 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 479 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01711671534285415, "min": 0.011406772219925188, "max": 0.023807225172640757, "count": 232 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01711671534285415, "min": 0.011406772219925188, "max": 0.023807225172640757, "count": 232 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11728582382202149, "min": 0.07979752396543821, "max": 0.12634022161364555, "count": 232 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11728582382202149, "min": 0.07979752396543821, "max": 0.12634022161364555, "count": 232 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11893877113858858, "min": 0.08056673184037208, "max": 0.12834935064117114, "count": 232 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11893877113858858, "min": 0.08056673184037208, "max": 0.12834935064117114, "count": 232 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 232 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 232 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 232 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 232 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 232 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 232 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1734805267", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/ez/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-env-executables/SoccerTwo/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1734812675" }, "total": 7407.930592285993, "count": 1, "self": 0.0830988860107027, "children": { "run_training.setup": { "total": 0.014124214998446405, "count": 1, "self": 0.014124214998446405 }, "TrainerController.start_learning": { "total": 7407.833369184984, "count": 1, "self": 4.557064374006586, "children": { "TrainerController._reset_env": { "total": 1.5468581588647794, "count": 25, "self": 1.5468581588647794 }, "TrainerController.advance": { "total": 7401.59500303914, "count": 333334, "self": 3.933105544099817, "children": { "env_step": { "total": 5963.718467488739, "count": 333334, "self": 4762.2044231270265, "children": { "SubprocessEnvManager._take_step": { "total": 1198.8402411262214, "count": 333334, "self": 22.965649539168226, "children": { "TorchPolicy.evaluate": { "total": 1175.8745915870531, "count": 601966, "self": 1175.8745915870531 } } }, "workers": { "total": 2.673803235491505, "count": 333334, "self": 0.0, "children": { "worker_root": { "total": 7396.952812148578, "count": 333334, "is_parallel": true, "self": 3185.231254872866, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018544579797890037, "count": 2, "is_parallel": true, "self": 0.00043329395703040063, "children": { "_process_rank_one_or_two_observation": { "total": 0.001421164022758603, "count": 8, "is_parallel": true, "self": 0.001421164022758603 } } }, "UnityEnvironment.step": { "total": 0.018671988014830276, "count": 1, "is_parallel": true, "self": 0.0004823860072065145, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006805970042478293, "count": 1, "is_parallel": true, "self": 0.0006805970042478293 }, "communicator.exchange": { "total": 0.016217303986195475, "count": 1, "is_parallel": true, "self": 0.016217303986195475 }, "steps_from_proto": { "total": 0.0012917010171804577, "count": 2, "is_parallel": true, "self": 0.00022089105914346874, "children": { "_process_rank_one_or_two_observation": { "total": 0.001070809958036989, "count": 8, "is_parallel": true, "self": 0.001070809958036989 } } } } } } }, "steps_from_proto": { "total": 0.057611184020061046, "count": 48, "is_parallel": true, "self": 0.008995019015856087, "children": { "_process_rank_one_or_two_observation": { "total": 0.04861616500420496, "count": 192, "is_parallel": true, "self": 0.04861616500420496 } } }, "UnityEnvironment.step": { "total": 4211.663946091692, "count": 333333, "is_parallel": true, "self": 283.66528311476577, "children": { "UnityEnvironment._generate_step_input": { "total": 173.266821395664, "count": 333333, "is_parallel": true, "self": 173.266821395664 }, "communicator.exchange": { "total": 3011.904557889997, "count": 333333, "is_parallel": true, "self": 3011.904557889997 }, "steps_from_proto": { "total": 742.8272836912656, "count": 666666, "is_parallel": true, "self": 117.61646822033799, "children": { "_process_rank_one_or_two_observation": { "total": 625.2108154709276, "count": 2666664, "is_parallel": true, "self": 625.2108154709276 } } } } } } } } } } }, "trainer_advance": { "total": 1433.9434300063003, "count": 333334, "self": 32.3608399060322, "children": { "process_trajectory": { "total": 698.8355939066096, "count": 333334, "self": 697.6233816336025, "children": { "RLTrainer._checkpoint": { "total": 1.212212273007026, "count": 9, "self": 1.212212273007026 } } }, "_update_policy": { "total": 702.7469961936586, "count": 233, "self": 445.06726305090706, "children": { "TorchPOCAOptimizer.update": { "total": 257.6797331427515, "count": 6960, "self": 257.6797331427515 } } } } } } }, "trainer_threads": { "total": 9.899958968162537e-07, "count": 1, "self": 9.899958968162537e-07 }, "TrainerController._save_models": { "total": 0.1344426229770761, "count": 1, "self": 0.002314659970579669, "children": { "RLTrainer._checkpoint": { "total": 0.13212796300649643, "count": 1, "self": 0.13212796300649643 } } } } } } }