pratsy's picture
First Push
68a3b7b
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.968576967716217,
"min": 0.968576967716217,
"max": 2.8754141330718994,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9258.626953125,
"min": 9258.626953125,
"max": 29415.486328125,
"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": 12.973041534423828,
"min": 0.4000825881958008,
"max": 12.973041534423828,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2529.7431640625,
"min": 77.61602020263672,
"max": 2628.8359375,
"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": 0.06908381303041025,
"min": 0.06512874117321973,
"max": 0.07770480015959966,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.276335252121641,
"min": 0.26108650436999237,
"max": 0.37159698836359323,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17939072105960518,
"min": 0.10795861113172792,
"max": 0.2610465970109491,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7175628842384207,
"min": 0.43183444452691166,
"max": 1.3052329850547455,
"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": 25.84090909090909,
"min": 3.0,
"max": 25.84090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1137.0,
"min": 132.0,
"max": 1393.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.84090909090909,
"min": 3.0,
"max": 25.84090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1137.0,
"min": 132.0,
"max": 1393.0,
"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": "1690691499",
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1690691989"
},
"total": 490.331943187,
"count": 1,
"self": 0.436267378000025,
"children": {
"run_training.setup": {
"total": 0.036318134999987706,
"count": 1,
"self": 0.036318134999987706
},
"TrainerController.start_learning": {
"total": 489.85935767399997,
"count": 1,
"self": 0.5764790490043197,
"children": {
"TrainerController._reset_env": {
"total": 6.210442552999979,
"count": 1,
"self": 6.210442552999979
},
"TrainerController.advance": {
"total": 482.9288815149956,
"count": 18202,
"self": 0.27425429299967163,
"children": {
"env_step": {
"total": 482.65462722199595,
"count": 18202,
"self": 349.85547828799304,
"children": {
"SubprocessEnvManager._take_step": {
"total": 132.50338851600455,
"count": 18202,
"self": 1.8620630440040031,
"children": {
"TorchPolicy.evaluate": {
"total": 130.64132547200055,
"count": 18202,
"self": 130.64132547200055
}
}
},
"workers": {
"total": 0.29576041799836617,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 487.8925919919975,
"count": 18202,
"is_parallel": true,
"self": 233.4235324389926,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0057346019999897635,
"count": 1,
"is_parallel": true,
"self": 0.004261501999963002,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014731000000267613,
"count": 10,
"is_parallel": true,
"self": 0.0014731000000267613
}
}
},
"UnityEnvironment.step": {
"total": 0.0782287699999813,
"count": 1,
"is_parallel": true,
"self": 0.00045747799995865535,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003149300000018229,
"count": 1,
"is_parallel": true,
"self": 0.0003149300000018229
},
"communicator.exchange": {
"total": 0.07520840300000486,
"count": 1,
"is_parallel": true,
"self": 0.07520840300000486
},
"steps_from_proto": {
"total": 0.0022479590000159533,
"count": 1,
"is_parallel": true,
"self": 0.0004081589999316293,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001839800000084324,
"count": 10,
"is_parallel": true,
"self": 0.001839800000084324
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 254.4690595530049,
"count": 18201,
"is_parallel": true,
"self": 10.977699339986799,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.377518150003937,
"count": 18201,
"is_parallel": true,
"self": 5.377518150003937
},
"communicator.exchange": {
"total": 201.68366236600858,
"count": 18201,
"is_parallel": true,
"self": 201.68366236600858
},
"steps_from_proto": {
"total": 36.4301796970056,
"count": 18201,
"is_parallel": true,
"self": 6.883902509972984,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.546277187032615,
"count": 182010,
"is_parallel": true,
"self": 29.546277187032615
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0002592929999991611,
"count": 1,
"self": 0.0002592929999991611,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 478.9993254049697,
"count": 463380,
"is_parallel": true,
"self": 10.624862764967702,
"children": {
"process_trajectory": {
"total": 261.0939736650026,
"count": 463380,
"is_parallel": true,
"self": 259.90616082700257,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1878128380000135,
"count": 4,
"is_parallel": true,
"self": 1.1878128380000135
}
}
},
"_update_policy": {
"total": 207.2804889749994,
"count": 90,
"is_parallel": true,
"self": 85.07862988699864,
"children": {
"TorchPPOOptimizer.update": {
"total": 122.20185908800076,
"count": 4587,
"is_parallel": true,
"self": 122.20185908800076
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1432952640000167,
"count": 1,
"self": 0.0008182939999414884,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1424769700000752,
"count": 1,
"self": 0.1424769700000752
}
}
}
}
}
}
}