Hinova's picture
Second Push
8ec5710
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 3.233672857284546,
"min": 3.22583270072937,
"max": 3.2957563400268555,
"count": 50
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 65087.3671875,
"min": 15354.1748046875,
"max": 112034.8515625,
"count": 50
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 999.0,
"min": 493.1111111111111,
"max": 999.0,
"count": 50
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19980.0,
"min": 11276.0,
"max": 29660.0,
"count": 50
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1193.3721645523224,
"min": 1193.3721645523224,
"max": 1200.0797527907453,
"count": 32
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 2386.7443291046447,
"min": 2386.7443291046447,
"max": 9577.186690112787,
"count": 32
},
"SoccerTwos.Step.mean": {
"value": 499470.0,
"min": 9848.0,
"max": 499470.0,
"count": 50
},
"SoccerTwos.Step.sum": {
"value": 499470.0,
"min": 9848.0,
"max": 499470.0,
"count": 50
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.0031131296418607235,
"min": -0.0031131296418607235,
"max": 0.04542664438486099,
"count": 50
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -0.03113129734992981,
"min": -0.03113129734992981,
"max": 0.6318801641464233,
"count": 50
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.0038255066610872746,
"min": -0.0038255066610872746,
"max": 0.041037287563085556,
"count": 50
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -0.03825506567955017,
"min": -0.03825506567955017,
"max": 0.5745220184326172,
"count": 50
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 50
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 50
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": 0.0,
"min": -0.46153846153846156,
"max": 0.21603077191572922,
"count": 50
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": 0.0,
"min": -6.0,
"max": 2.80840003490448,
"count": 50
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": 0.0,
"min": -0.46153846153846156,
"max": 0.21603077191572922,
"count": 50
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": 0.0,
"min": -6.0,
"max": 2.80840003490448,
"count": 50
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.014357396599370987,
"min": 0.013364207791164517,
"max": 0.021163785768051942,
"count": 23
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.014357396599370987,
"min": 0.013364207791164517,
"max": 0.021163785768051942,
"count": 23
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.001597303138502563,
"min": 1.3475353474253401e-05,
"max": 0.005773242943299313,
"count": 23
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.001597303138502563,
"min": 1.3475353474253401e-05,
"max": 0.005773242943299313,
"count": 23
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.001598834787728265,
"min": 1.3690317412814087e-05,
"max": 0.005346031254157424,
"count": 23
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.001598834787728265,
"min": 1.3690317412814087e-05,
"max": 0.005346031254157424,
"count": 23
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 23
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 23
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.2,
"max": 0.20000000000000007,
"count": 23
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.2,
"max": 0.20000000000000007,
"count": 23
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005,
"max": 0.005000000000000001,
"count": 23
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005,
"max": 0.005000000000000001,
"count": 23
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1687350472",
"python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:38:11) \n[Clang 14.0.6 ]",
"command_line_arguments": "/Users/hinova/miniconda3/envs/drl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwosMps --no-graphics --force",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.0.0",
"numpy_version": "1.21.2",
"end_time_seconds": "1687353526"
},
"total": 3054.774062209,
"count": 1,
"self": 0.24040079200040054,
"children": {
"run_training.setup": {
"total": 0.027766291999999915,
"count": 1,
"self": 0.027766291999999915
},
"TrainerController.start_learning": {
"total": 3054.505895125,
"count": 1,
"self": 0.48156175300300674,
"children": {
"TrainerController._reset_env": {
"total": 2.9118101250003274,
"count": 3,
"self": 2.9118101250003274
},
"TrainerController.advance": {
"total": 3050.858510538997,
"count": 32716,
"self": 0.4315882450086974,
"children": {
"env_step": {
"total": 2763.6579373589884,
"count": 32716,
"self": 1873.2906480149368,
"children": {
"SubprocessEnvManager._take_step": {
"total": 890.0393871580209,
"count": 32716,
"self": 2.949738248970448,
"children": {
"TorchPolicy.evaluate": {
"total": 887.0896489090504,
"count": 64988,
"self": 887.0896489090504
}
}
},
"workers": {
"total": 0.3279021860308706,
"count": 32716,
"self": 0.0,
"children": {
"worker_root": {
"total": 3049.100819417003,
"count": 32716,
"is_parallel": true,
"self": 1232.053774705992,
"children": {
"steps_from_proto": {
"total": 0.005620666999630597,
"count": 6,
"is_parallel": true,
"self": 0.0010053319991629728,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004615335000467624,
"count": 24,
"is_parallel": true,
"self": 0.004615335000467624
}
}
},
"UnityEnvironment.step": {
"total": 1817.0414240440114,
"count": 32716,
"is_parallel": true,
"self": 4.633772936008654,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 28.213531115970742,
"count": 32716,
"is_parallel": true,
"self": 28.213531115970742
},
"communicator.exchange": {
"total": 1729.8886375140496,
"count": 32716,
"is_parallel": true,
"self": 1729.8886375140496
},
"steps_from_proto": {
"total": 54.30548247798243,
"count": 65432,
"is_parallel": true,
"self": 7.845784742923698,
"children": {
"_process_rank_one_or_two_observation": {
"total": 46.45969773505873,
"count": 261728,
"is_parallel": true,
"self": 46.45969773505873
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 286.76898493499976,
"count": 32716,
"self": 4.91265759401449,
"children": {
"process_trajectory": {
"total": 118.21020459198506,
"count": 32716,
"self": 116.45898279998526,
"children": {
"RLTrainer._checkpoint": {
"total": 1.7512217919997966,
"count": 1,
"self": 1.7512217919997966
}
}
},
"_update_policy": {
"total": 163.64612274900023,
"count": 23,
"self": 56.49899599799923,
"children": {
"TorchPOCAOptimizer.update": {
"total": 107.147126751001,
"count": 696,
"self": 107.147126751001
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.2540127079996637,
"count": 1,
"self": 3.229100002499763e-05,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2539804169996387,
"count": 1,
"self": 0.2539804169996387
}
}
}
}
}
}
}