{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7693387269973755, "min": 1.6698956489562988, "max": 3.295759439468384, "count": 1000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 35783.10546875, "min": 16838.9921875, "max": 132726.640625, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 46.21153846153846, "min": 39.392, "max": 999.0, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19224.0, "min": 13396.0, "max": 25944.0, "count": 1000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1599.5533707690754, "min": 1190.9725721183304, "max": 1645.2840475202256, "count": 823 }, "SoccerTwos.Self-play.ELO.sum": { "value": 332707.1011199677, "min": 2381.945144236661, "max": 395237.1358031364, "count": 823 }, "SoccerTwos.Step.mean": { "value": 9999945.0, "min": 9978.0, "max": 9999945.0, "count": 1000 }, "SoccerTwos.Step.sum": { "value": 9999945.0, "min": 9978.0, "max": 9999945.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.021001819521188736, "min": -0.12387946993112564, "max": 0.17120541632175446, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -4.38938045501709, "min": -26.01468849182129, "max": 27.032238006591797, "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": -0.07473110040409144, "min": -0.6303999986913469, "max": 0.5784631559723302, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -15.618799984455109, "min": -52.1120001077652, "max": 75.82220029830933, "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": 0.01917786959093064, "min": 0.010777857618328805, "max": 0.02597189780790359, "count": 477 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01917786959093064, "min": 0.010777857618328805, "max": 0.02597189780790359, "count": 477 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11877927159269651, "min": 1.5434958246866396e-05, "max": 0.14347270578145982, "count": 477 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11877927159269651, "min": 1.5434958246866396e-05, "max": 0.14347270578145982, "count": 477 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 477 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 477 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 477 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 477 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 477 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 477 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1713913050", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/home/luyijie/anaconda3/envs/rl/bin/mlagents-learn ./config/SoccerTwos/ppo.yaml --env=../test_env/SoccerTwos.x86_64 --run-id=ppo_default_run0 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1713920882" }, "total": 7832.6669030470075, "count": 1, "self": 0.21771723801793996, "children": { "run_training.setup": { "total": 0.015953310998156667, "count": 1, "self": 0.015953310998156667 }, "TrainerController.start_learning": { "total": 7832.433232497991, "count": 1, "self": 7.572927598434035, "children": { "TrainerController._reset_env": { "total": 2.0095456790731987, "count": 50, "self": 2.0095456790731987 }, "TrainerController.advance": { "total": 7822.796976582482, "count": 679616, "self": 8.074539636581903, "children": { "env_step": { "total": 6480.472914928396, "count": 679616, "self": 4938.859413687649, "children": { "SubprocessEnvManager._take_step": { "total": 1536.4154619876062, "count": 679616, "self": 53.173565854289336, "children": { "TorchPolicy.evaluate": { "total": 1483.241896133317, "count": 1267618, "self": 1483.241896133317 } } }, "workers": { "total": 5.1980392531404505, "count": 679616, "self": 0.0, "children": { "worker_root": { "total": 7822.1544387560425, "count": 679616, "is_parallel": true, "self": 3838.3403712371946, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0013324350002221763, "count": 2, "is_parallel": true, "self": 0.00030599100864492357, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010264439915772527, "count": 8, "is_parallel": true, "self": 0.0010264439915772527 } } }, "UnityEnvironment.step": { "total": 0.01668741600587964, "count": 1, "is_parallel": true, "self": 0.0003859650023514405, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002358269994147122, "count": 1, "is_parallel": true, "self": 0.0002358269994147122 }, "communicator.exchange": { "total": 0.015114890004042536, "count": 1, "is_parallel": true, "self": 0.015114890004042536 }, "steps_from_proto": { "total": 0.0009507340000709519, "count": 2, "is_parallel": true, "self": 0.00019624900596681982, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007544849941041321, "count": 8, "is_parallel": true, "self": 0.0007544849941041321 } } } } } } }, "UnityEnvironment.step": { "total": 3983.770027508828, "count": 679615, "is_parallel": true, "self": 223.88906603705254, "children": { "UnityEnvironment._generate_step_input": { "total": 133.03361019992735, "count": 679615, "is_parallel": true, "self": 133.03361019992735 }, "communicator.exchange": { "total": 3027.3254374588723, "count": 679615, "is_parallel": true, "self": 3027.3254374588723 }, "steps_from_proto": { "total": 599.521913812976, "count": 1359230, "is_parallel": true, "self": 111.78756611495919, "children": { "_process_rank_one_or_two_observation": { "total": 487.7343476980168, "count": 5436920, "is_parallel": true, "self": 487.7343476980168 } } } } }, "steps_from_proto": { "total": 0.04404001001967117, "count": 98, "is_parallel": true, "self": 0.008472020010231063, "children": { "_process_rank_one_or_two_observation": { "total": 0.03556799000944011, "count": 392, "is_parallel": true, "self": 0.03556799000944011 } } } } } } } } }, "trainer_advance": { "total": 1334.2495220175042, "count": 679616, "self": 62.39744327936205, "children": { "process_trajectory": { "total": 398.02675184133113, "count": 679616, "self": 396.7832723913307, "children": { "RLTrainer._checkpoint": { "total": 1.24347945000045, "count": 20, "self": 1.24347945000045 } } }, "_update_policy": { "total": 873.825326896811, "count": 477, "self": 659.4169314454048, "children": { "TorchPPOOptimizer.update": { "total": 214.40839545140625, "count": 14313, "self": 214.40839545140625 } } } } } } }, "trainer_threads": { "total": 6.150075932964683e-07, "count": 1, "self": 6.150075932964683e-07 }, "TrainerController._save_models": { "total": 0.05378202299471013, "count": 1, "self": 0.0008823869866319001, "children": { "RLTrainer._checkpoint": { "total": 0.05289963600807823, "count": 1, "self": 0.05289963600807823 } } } } } } }