KoRiF's picture
First Push: run 00 commit
d0be23d
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8750593066215515,
"min": 0.8750593066215515,
"max": 2.8706209659576416,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8355.06640625,
"min": 8355.06640625,
"max": 29398.029296875,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.032539367675781,
"min": 0.29029911756515503,
"max": 13.032539367675781,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2541.34521484375,
"min": 56.318031311035156,
"max": 2658.46826171875,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06340845064508305,
"min": 0.0615499073475161,
"max": 0.07313500791953594,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2536338025803322,
"min": 0.2536338025803322,
"max": 0.3612626324250538,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21173716701713263,
"min": 0.11499877018150964,
"max": 0.2913417992200337,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8469486680685305,
"min": 0.45999508072603856,
"max": 1.394705377080861,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.09090909090909,
"min": 3.1363636363636362,
"max": 26.236363636363638,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1104.0,
"min": 138.0,
"max": 1443.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.09090909090909,
"min": 3.1363636363636362,
"max": 26.236363636363638,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1104.0,
"min": 138.0,
"max": 1443.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1674982548",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1674982997"
},
"total": 448.58515835000003,
"count": 1,
"self": 0.3856453469998087,
"children": {
"run_training.setup": {
"total": 0.10320770900011667,
"count": 1,
"self": 0.10320770900011667
},
"TrainerController.start_learning": {
"total": 448.0963052940001,
"count": 1,
"self": 0.5503306029850137,
"children": {
"TrainerController._reset_env": {
"total": 9.736419137999974,
"count": 1,
"self": 9.736419137999974
},
"TrainerController.advance": {
"total": 437.6904138350151,
"count": 18204,
"self": 0.2798578720198748,
"children": {
"env_step": {
"total": 437.4105559629952,
"count": 18204,
"self": 285.9590844410093,
"children": {
"SubprocessEnvManager._take_step": {
"total": 151.1773891479777,
"count": 18204,
"self": 1.47580428797869,
"children": {
"TorchPolicy.evaluate": {
"total": 149.701584859999,
"count": 18204,
"self": 33.90134413198916,
"children": {
"TorchPolicy.sample_actions": {
"total": 115.80024072800984,
"count": 18204,
"self": 115.80024072800984
}
}
}
}
},
"workers": {
"total": 0.27408237400823054,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 446.8266784209907,
"count": 18204,
"is_parallel": true,
"self": 215.64516987399998,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006530804000021817,
"count": 1,
"is_parallel": true,
"self": 0.0039503279997461505,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0025804760002756666,
"count": 10,
"is_parallel": true,
"self": 0.0025804760002756666
}
}
},
"UnityEnvironment.step": {
"total": 0.03322613800014551,
"count": 1,
"is_parallel": true,
"self": 0.0003569240002434526,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003068129999519442,
"count": 1,
"is_parallel": true,
"self": 0.0003068129999519442
},
"communicator.exchange": {
"total": 0.030679942999995546,
"count": 1,
"is_parallel": true,
"self": 0.030679942999995546
},
"steps_from_proto": {
"total": 0.0018824579999545676,
"count": 1,
"is_parallel": true,
"self": 0.0004410599997299869,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014413980002245808,
"count": 10,
"is_parallel": true,
"self": 0.0014413980002245808
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 231.1815085469907,
"count": 18203,
"is_parallel": true,
"self": 8.562461825964647,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.274769551012696,
"count": 18203,
"is_parallel": true,
"self": 5.274769551012696
},
"communicator.exchange": {
"total": 185.22780114102488,
"count": 18203,
"is_parallel": true,
"self": 185.22780114102488
},
"steps_from_proto": {
"total": 32.11647602898847,
"count": 18203,
"is_parallel": true,
"self": 6.955008385945348,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.161467643043125,
"count": 182030,
"is_parallel": true,
"self": 25.161467643043125
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.803999993579055e-05,
"count": 1,
"self": 3.803999993579055e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 434.4178079680514,
"count": 352055,
"is_parallel": true,
"self": 9.772135885984426,
"children": {
"process_trajectory": {
"total": 250.80169016506716,
"count": 352055,
"is_parallel": true,
"self": 249.92666266806737,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8750274969997918,
"count": 4,
"is_parallel": true,
"self": 0.8750274969997918
}
}
},
"_update_policy": {
"total": 173.84398191699984,
"count": 90,
"is_parallel": true,
"self": 41.0052180689936,
"children": {
"TorchPPOOptimizer.update": {
"total": 132.83876384800624,
"count": 4587,
"is_parallel": true,
"self": 132.83876384800624
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11910367800010135,
"count": 1,
"self": 0.0008878810001533566,
"children": {
"RLTrainer._checkpoint": {
"total": 0.118215796999948,
"count": 1,
"self": 0.118215796999948
}
}
}
}
}
}
}