{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.80917227268219, "min": 1.730055570602417, "max": 3.295778512954712, "count": 1000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 35720.296875, "min": 12192.248046875, "max": 109020.8203125, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 64.36708860759494, "min": 38.248, "max": 999.0, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20340.0, "min": 14736.0, "max": 26152.0, "count": 1000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1578.2808316500339, "min": 1193.0141342541017, "max": 1586.0312939484315, "count": 980 }, "SoccerTwos.Self-play.ELO.sum": { "value": 249368.37140070533, "min": 2386.9973856665797, "max": 389807.9867272342, "count": 980 }, "SoccerTwos.Step.mean": { "value": 9999750.0, "min": 9092.0, "max": 9999750.0, "count": 1000 }, "SoccerTwos.Step.sum": { "value": 9999750.0, "min": 9092.0, "max": 9999750.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.005977350287139416, "min": -0.11456811428070068, "max": 0.1724340319633484, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.9384440183639526, "min": -20.085418701171875, "max": 29.1413516998291, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.006567197386175394, "min": -0.11627768725156784, "max": 0.17000749707221985, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.0310499668121338, "min": -20.390769958496094, "max": 29.903545379638672, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.10700636988232849, "min": -0.5458181825551119, "max": 0.44800625182688236, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -16.800000071525574, "min": -50.67199981212616, "max": 63.750800013542175, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.10700636988232849, "min": -0.5458181825551119, "max": 0.44800625182688236, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -16.800000071525574, "min": -50.67199981212616, "max": 63.750800013542175, "count": 1000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014692272393828414, "min": 0.010675552282676411, "max": 0.024100505871077378, "count": 482 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014692272393828414, "min": 0.010675552282676411, "max": 0.024100505871077378, "count": 482 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10919131437937418, "min": 9.562355929422968e-06, "max": 0.1290760229031245, "count": 482 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10919131437937418, "min": 9.562355929422968e-06, "max": 0.1290760229031245, "count": 482 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11076388855775197, "min": 8.26342475193087e-06, "max": 0.13235595524311067, "count": 482 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11076388855775197, "min": 8.26342475193087e-06, "max": 0.13235595524311067, "count": 482 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 482 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 482 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 482 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 482 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 482 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 482 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1715440878", "python_version": "3.10.11 (v3.10.11:7d4cc5aa85, Apr 4 2023, 19:05:19) [Clang 13.0.0 (clang-1300.0.29.30)]", "command_line_arguments": "/Users/davidmoczar/Desktop/MuJoCo_Playground/ml_agents_test/.venv/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --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": "2.3.0", "numpy_version": "1.23.5", "end_time_seconds": "1715538213" }, "total": 29450.230693334, "count": 1, "self": 0.17530304299725685, "children": { "run_training.setup": { "total": 0.2869752500009781, "count": 1, "self": 0.2869752500009781 }, "TrainerController.start_learning": { "total": 29449.768415041002, "count": 1, "self": 5.809039876585302, "children": { "TrainerController._reset_env": { "total": 4.78903316400465, "count": 50, "self": 4.78903316400465 }, "TrainerController.advance": { "total": 29439.091661667415, "count": 685396, "self": 5.235877136932686, "children": { "env_step": { "total": 23899.509375383976, "count": 685396, "self": 23121.6960295936, "children": { "SubprocessEnvManager._take_step": { "total": 774.0431406713506, "count": 685396, "self": 26.688623408957937, "children": { "TorchPolicy.evaluate": { "total": 747.3545172623926, "count": 1259772, "self": 747.3545172623926 } } }, "workers": { "total": 3.7702051190262864, "count": 685396, "self": 0.0, "children": { "worker_root": { "total": 29438.501148043146, "count": 685396, "is_parallel": true, "self": 7035.530549869305, "children": { "steps_from_proto": { "total": 0.06415762100368738, "count": 100, "is_parallel": true, "self": 0.007805785919117625, "children": { "_process_rank_one_or_two_observation": { "total": 0.05635183508456976, "count": 400, "is_parallel": true, "self": 0.05635183508456976 } } }, "UnityEnvironment.step": { "total": 22402.906440552837, "count": 685396, "is_parallel": true, "self": 61.18230664405928, "children": { "UnityEnvironment._generate_step_input": { "total": 405.7803917880028, "count": 685396, "is_parallel": true, "self": 405.7803917880028 }, "communicator.exchange": { "total": 21143.28687191561, "count": 685396, "is_parallel": true, "self": 21143.28687191561 }, "steps_from_proto": { "total": 792.6568702051645, "count": 1370792, "is_parallel": true, "self": 91.67796033556442, "children": { "_process_rank_one_or_two_observation": { "total": 700.9789098696001, "count": 5483168, "is_parallel": true, "self": 700.9789098696001 } } } } } } } } } } }, "trainer_advance": { "total": 5534.346409146508, "count": 685396, "self": 47.53942243489837, "children": { "process_trajectory": { "total": 1037.6773498515613, "count": 685396, "self": 1036.0619220175558, "children": { "RLTrainer._checkpoint": { "total": 1.6154278340054589, "count": 20, "self": 1.6154278340054589 } } }, "_update_policy": { "total": 4449.129636860049, "count": 482, "self": 507.21281981039465, "children": { "TorchPOCAOptimizer.update": { "total": 3941.916817049654, "count": 14460, "self": 3941.916817049654 } } } } } } }, "trainer_threads": { "total": 3.3299875212833285e-07, "count": 1, "self": 3.3299875212833285e-07 }, "TrainerController._save_models": { "total": 0.07867999999871245, "count": 1, "self": 0.0013584999978775159, "children": { "RLTrainer._checkpoint": { "total": 0.07732150000083493, "count": 1, "self": 0.07732150000083493 } } } } } } }