jwright94's picture
First Version
7f98b1e
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.30137303471565247,
"min": 0.28194016218185425,
"max": 1.462998867034912,
"count": 38
},
"Pyramids.Policy.Entropy.sum": {
"value": 8949.5732421875,
"min": 8417.60546875,
"max": 44381.53515625,
"count": 38
},
"Pyramids.Step.mean": {
"value": 1139879.0,
"min": 29952.0,
"max": 1139879.0,
"count": 38
},
"Pyramids.Step.sum": {
"value": 1139879.0,
"min": 29952.0,
"max": 1139879.0,
"count": 38
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7385226488113403,
"min": -0.10890169441699982,
"max": 0.7635995745658875,
"count": 38
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 214.91009521484375,
"min": -26.24530792236328,
"max": 226.02548217773438,
"count": 38
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.0059921215288341045,
"min": -0.020112870261073112,
"max": 0.3811810612678528,
"count": 38
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 1.7437074184417725,
"min": -5.551152229309082,
"max": 91.48345184326172,
"count": 38
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06758994502264874,
"min": 0.06575554041619118,
"max": 0.07426582175789267,
"count": 38
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9462592303170824,
"min": 0.4862367310797081,
"max": 1.0880257441655405,
"count": 38
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015740875233729766,
"min": 0.0010942598402561867,
"max": 0.017464276381707305,
"count": 38
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.22037225327221674,
"min": 0.010296031405797013,
"max": 0.24755473498325778,
"count": 38
},
"Pyramids.Policy.LearningRate.mean": {
"value": 0.0001875712446191214,
"min": 0.0001875712446191214,
"max": 0.00029838354339596195,
"count": 38
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0026259974246676996,
"min": 0.0020691136102954665,
"max": 0.003927869090710333,
"count": 38
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.16252373571428572,
"min": 0.16252373571428572,
"max": 0.19946118095238097,
"count": 38
},
"Pyramids.Policy.Epsilon.sum": {
"value": 2.2753323,
"min": 1.3897045333333333,
"max": 2.782550666666667,
"count": 38
},
"Pyramids.Policy.Beta.mean": {
"value": 0.006256121197857143,
"min": 0.006256121197857143,
"max": 0.009946171977142856,
"count": 38
},
"Pyramids.Policy.Beta.sum": {
"value": 0.08758569677,
"min": 0.06897148288,
"max": 0.13093803770000004,
"count": 38
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.0124094532802701,
"min": 0.010984128341078758,
"max": 0.40785735845565796,
"count": 38
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.17373234033584595,
"min": 0.15377779304981232,
"max": 2.855001449584961,
"count": 38
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 268.84166666666664,
"min": 229.41860465116278,
"max": 999.0,
"count": 38
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 32261.0,
"min": 15984.0,
"max": 33428.0,
"count": 38
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6973630123529113,
"min": -1.0000000521540642,
"max": 1.7550713054893552,
"count": 38
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 201.98619846999645,
"min": -32.000001668930054,
"max": 226.40419840812683,
"count": 38
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6973630123529113,
"min": -1.0000000521540642,
"max": 1.7550713054893552,
"count": 38
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 201.98619846999645,
"min": -32.000001668930054,
"max": 226.40419840812683,
"count": 38
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.033704481174569666,
"min": 0.0285461096984448,
"max": 7.8781257681548595,
"count": 38
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.01083325977379,
"min": 3.442089660966303,
"max": 126.05001229047775,
"count": 38
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 38
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 38
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1675136468",
"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/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1675138785"
},
"total": 2317.574583199,
"count": 1,
"self": 0.3651109139991604,
"children": {
"run_training.setup": {
"total": 0.09633537800004888,
"count": 1,
"self": 0.09633537800004888
},
"TrainerController.start_learning": {
"total": 2317.1131369070004,
"count": 1,
"self": 1.2570142969925655,
"children": {
"TrainerController._reset_env": {
"total": 6.064585103999889,
"count": 1,
"self": 6.064585103999889
},
"TrainerController.advance": {
"total": 2309.637065582008,
"count": 74025,
"self": 1.2961100769930454,
"children": {
"env_step": {
"total": 1576.8907674129828,
"count": 74025,
"self": 1466.4407406310684,
"children": {
"SubprocessEnvManager._take_step": {
"total": 109.65119824798262,
"count": 74025,
"self": 4.630598815972689,
"children": {
"TorchPolicy.evaluate": {
"total": 105.02059943200993,
"count": 72194,
"self": 35.670480280011134,
"children": {
"TorchPolicy.sample_actions": {
"total": 69.3501191519988,
"count": 72194,
"self": 69.3501191519988
}
}
}
}
},
"workers": {
"total": 0.7988285339317827,
"count": 74024,
"self": 0.0,
"children": {
"worker_root": {
"total": 2314.0605300530765,
"count": 74024,
"is_parallel": true,
"self": 952.0054890430133,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001754022999875815,
"count": 1,
"is_parallel": true,
"self": 0.0006151239997507219,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011388990001250932,
"count": 8,
"is_parallel": true,
"self": 0.0011388990001250932
}
}
},
"UnityEnvironment.step": {
"total": 0.04334960999995019,
"count": 1,
"is_parallel": true,
"self": 0.0005076370000551833,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00045765400000163936,
"count": 1,
"is_parallel": true,
"self": 0.00045765400000163936
},
"communicator.exchange": {
"total": 0.04078492400003597,
"count": 1,
"is_parallel": true,
"self": 0.04078492400003597
},
"steps_from_proto": {
"total": 0.0015993949998573953,
"count": 1,
"is_parallel": true,
"self": 0.00040947899992715975,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011899159999302356,
"count": 8,
"is_parallel": true,
"self": 0.0011899159999302356
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1362.0550410100632,
"count": 74023,
"is_parallel": true,
"self": 30.393406646037647,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.204881174987804,
"count": 74023,
"is_parallel": true,
"self": 24.204881174987804
},
"communicator.exchange": {
"total": 1208.0889757490224,
"count": 74023,
"is_parallel": true,
"self": 1208.0889757490224
},
"steps_from_proto": {
"total": 99.36777744001529,
"count": 74023,
"is_parallel": true,
"self": 23.039123961724272,
"children": {
"_process_rank_one_or_two_observation": {
"total": 76.32865347829102,
"count": 592184,
"is_parallel": true,
"self": 76.32865347829102
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 731.4501880920322,
"count": 74024,
"self": 2.420142123964524,
"children": {
"process_trajectory": {
"total": 159.51538411506544,
"count": 74024,
"self": 159.33482016406515,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18056395100029476,
"count": 2,
"self": 0.18056395100029476
}
}
},
"_update_policy": {
"total": 569.5146618530023,
"count": 521,
"self": 214.97468131899927,
"children": {
"TorchPPOOptimizer.update": {
"total": 354.539980534003,
"count": 26331,
"self": 354.539980534003
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3310000213095918e-06,
"count": 1,
"self": 1.3310000213095918e-06
},
"TrainerController._save_models": {
"total": 0.15447059300004184,
"count": 1,
"self": 0.0018904530006693676,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15258013999937248,
"count": 1,
"self": 0.15258013999937248
}
}
}
}
}
}
}