{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7120624780654907, "min": 1.6752153635025024, "max": 3.295743703842163, "count": 800 }, "SoccerTwos.Policy.Entropy.sum": { "value": 34022.10546875, "min": 23056.83984375, "max": 132146.140625, "count": 800 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 71.07142857142857, "min": 47.14563106796116, "max": 999.0, "count": 800 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19900.0, "min": 11700.0, "max": 29732.0, "count": 800 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1636.939504410227, "min": 1187.7780098675032, "max": 1639.39625700252, "count": 704 }, "SoccerTwos.Self-play.ELO.sum": { "value": 229171.5306174318, "min": 2376.8265762762753, "max": 319879.45122049504, "count": 704 }, "SoccerTwos.Step.mean": { "value": 7999976.0, "min": 9887.0, "max": 7999976.0, "count": 800 }, "SoccerTwos.Step.sum": { "value": 7999976.0, "min": 9887.0, "max": 7999976.0, "count": 800 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.026560766622424126, "min": -0.15737122297286987, "max": 0.18703752756118774, "count": 800 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -3.691946506500244, "min": -19.671401977539062, "max": 23.208147048950195, "count": 800 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.02333911508321762, "min": -0.16499941051006317, "max": 0.1860237866640091, "count": 800 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.2441370487213135, "min": -20.62492561340332, "max": 23.47559928894043, "count": 800 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 800 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 800 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.08235971190088945, "min": -0.6275818212465807, "max": 0.5646181834208501, "count": 800 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -11.447999954223633, "min": -57.163999915122986, "max": 46.37959957122803, "count": 800 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.08235971190088945, "min": -0.6275818212465807, "max": 0.5646181834208501, "count": 800 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -11.447999954223633, "min": -57.163999915122986, "max": 46.37959957122803, "count": 800 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 800 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 800 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.032967403337048985, "min": 0.02366156485691641, "max": 0.047298097182647325, "count": 799 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.032967403337048985, "min": 0.02366156485691641, "max": 0.08833755592220566, "count": 799 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.044130529639207654, "min": 7.133955895157998e-09, "max": 0.06697994998345773, "count": 799 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.044130529639207654, "min": 7.133955895157998e-09, "max": 0.11953396774414513, "count": 799 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.04712000551323096, "min": 9.061594309479738e-09, "max": 0.07186874074654447, "count": 799 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.04712000551323096, "min": 9.061594309479738e-09, "max": 0.13117384041349092, "count": 799 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003000000000000001, "count": 799 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0006, "count": 799 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000004, "min": 0.19999999999999993, "max": 0.20000000000000004, "count": 799 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000004, "min": 0.19999999999999993, "max": 0.4000000000000001, "count": 799 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 799 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.010000000000000002, "count": 799 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1732570473", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\V:\\ANACONDA\\envs\\MARL\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1732592411" }, "total": 21937.200009100008, "count": 1, "self": 0.29581590000452707, "children": { "run_training.setup": { "total": 0.08974570000282256, "count": 1, "self": 0.08974570000282256 }, "TrainerController.start_learning": { "total": 21936.8144475, "count": 1, "self": 12.929385196781368, "children": { "TrainerController._reset_env": { "total": 8.304657699976815, "count": 40, "self": 8.304657699976815 }, "TrainerController.advance": { "total": 21915.47576830325, "count": 539612, "self": 12.730081307832734, "children": { "env_step": { "total": 9690.569411797682, "count": 539612, "self": 7637.877279600281, "children": { "SubprocessEnvManager._take_step": { "total": 2044.9682655006618, "count": 539613, "self": 71.9575318003408, "children": { "TorchPolicy.evaluate": { "total": 1973.010733700321, "count": 1011376, "self": 1973.010733700321 } } }, "workers": { "total": 7.723866696738696, "count": 539612, "self": 0.0, "children": { "worker_root": { "total": 21908.103088694617, "count": 539612, "is_parallel": true, "self": 15825.960818394851, "children": { "steps_from_proto": { "total": 0.06807190001563868, "count": 82, "is_parallel": true, "self": 0.014305900032923091, "children": { "_process_rank_one_or_two_observation": { "total": 0.053765999982715584, "count": 328, "is_parallel": true, "self": 0.053765999982715584 } } }, "UnityEnvironment.step": { "total": 6082.0741983997505, "count": 539612, "is_parallel": true, "self": 257.43906669433636, "children": { "UnityEnvironment._generate_step_input": { "total": 234.81601379493804, "count": 539612, "is_parallel": true, "self": 234.81601379493804 }, "communicator.exchange": { "total": 4746.347336301478, "count": 539612, "is_parallel": true, "self": 4746.347336301478 }, "steps_from_proto": { "total": 843.4717816089978, "count": 1079224, "is_parallel": true, "self": 180.56753821792518, "children": { "_process_rank_one_or_two_observation": { "total": 662.9042433910727, "count": 4316896, "is_parallel": true, "self": 662.9042433910727 } } } } } } } } } } }, "trainer_advance": { "total": 12212.176275197737, "count": 539612, "self": 81.58882319513214, "children": { "process_trajectory": { "total": 1681.1291229024064, "count": 539612, "self": 1679.1809420024001, "children": { "RLTrainer._checkpoint": { "total": 1.948180900006264, "count": 16, "self": 1.948180900006264 } } }, "_update_policy": { "total": 10449.458329100198, "count": 1225, "self": 1115.510473299175, "children": { "TorchPOCAOptimizer.update": { "total": 9333.947855801023, "count": 45765, "self": 9333.947855801023 } } } } } } }, "trainer_threads": { "total": 1.4999968698248267e-06, "count": 1, "self": 1.4999968698248267e-06 }, "TrainerController._save_models": { "total": 0.1046347999945283, "count": 1, "self": 0.0016571999876759946, "children": { "RLTrainer._checkpoint": { "total": 0.1029776000068523, "count": 1, "self": 0.1029776000068523 } } } } } } }