micheljperez's picture
Second Pyramids
fff71d7
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.26107534766197205,
"min": 0.26107534766197205,
"max": 1.4664194583892822,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 7794.666015625,
"min": 7794.666015625,
"max": 44485.30078125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989956.0,
"min": 29952.0,
"max": 989956.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989956.0,
"min": 29952.0,
"max": 989956.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 1.6054641008377075,
"min": -0.48449644446372986,
"max": 1.6569384336471558,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 462.3736572265625,
"min": -116.76364135742188,
"max": 482.1690673828125,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.04423460736870766,
"min": -0.004755581263452768,
"max": 0.8728349208831787,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 12.739566802978516,
"min": -1.3838741779327393,
"max": 210.35321044921875,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.046251159782210984,
"min": 0.045696529173645625,
"max": 0.0540908072627867,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.6937673967331648,
"min": 0.3786356508395069,
"max": 0.7710272762851673,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.002084497260026789,
"min": 0.0014826393429548117,
"max": 0.010252225601366913,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.031267458900401834,
"min": 0.013343754086593305,
"max": 0.14353115841913677,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.495037501686666e-06,
"min": 7.495037501686666e-06,
"max": 0.00029515063018788564,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011242556252529999,
"min": 0.00011242556252529999,
"max": 0.003506866131044699,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10249831333333333,
"min": 0.10249831333333333,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5374747,
"min": 1.3886848,
"max": 2.6169431,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.000259581502,
"min": 0.000259581502,
"max": 0.009838515931428574,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0038937225299999997,
"min": 0.0038937225299999997,
"max": 0.11691863447,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.007819236256182194,
"min": 0.007819236256182194,
"max": 0.401153028011322,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.11728853732347488,
"min": 0.10960745066404343,
"max": 2.8080711364746094,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 260.31531531531533,
"min": 257.5245901639344,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28895.0,
"min": 15984.0,
"max": 32676.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7213374855262893,
"min": -1.0000000521540642,
"max": 1.7420796322084107,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 192.7897983789444,
"min": -30.629201717674732,
"max": 208.78019827604294,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7213374855262893,
"min": -1.0000000521540642,
"max": 1.7420796322084107,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 192.7897983789444,
"min": -30.629201717674732,
"max": 208.78019827604294,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.021774777754606994,
"min": 0.02151474995689343,
"max": 8.353349308483303,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.4387751085159834,
"min": 2.4387751085159834,
"max": 133.65358893573284,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1658028918",
"python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force",
"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": "1658032003"
},
"total": 3084.9860942680007,
"count": 1,
"self": 0.430274886000916,
"children": {
"run_training.setup": {
"total": 0.048925633000180824,
"count": 1,
"self": 0.048925633000180824
},
"TrainerController.start_learning": {
"total": 3084.5068937489996,
"count": 1,
"self": 1.5831082699178296,
"children": {
"TrainerController._reset_env": {
"total": 7.35815438300051,
"count": 1,
"self": 7.35815438300051
},
"TrainerController.advance": {
"total": 3075.4721377410815,
"count": 64691,
"self": 1.6771062848183647,
"children": {
"env_step": {
"total": 1588.5231937400622,
"count": 64691,
"self": 1471.5532497830336,
"children": {
"SubprocessEnvManager._take_step": {
"total": 116.14517533213893,
"count": 64691,
"self": 4.991721288186454,
"children": {
"TorchPolicy.evaluate": {
"total": 111.15345404395248,
"count": 62570,
"self": 37.7865800209147,
"children": {
"TorchPolicy.sample_actions": {
"total": 73.36687402303778,
"count": 62570,
"self": 73.36687402303778
}
}
}
}
},
"workers": {
"total": 0.8247686248896571,
"count": 64691,
"self": 0.0,
"children": {
"worker_root": {
"total": 3080.1595899310223,
"count": 64691,
"is_parallel": true,
"self": 1721.4867742550214,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019354169999132864,
"count": 1,
"is_parallel": true,
"self": 0.0007688039986533113,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011666130012599751,
"count": 8,
"is_parallel": true,
"self": 0.0011666130012599751
}
}
},
"UnityEnvironment.step": {
"total": 0.04867720800029929,
"count": 1,
"is_parallel": true,
"self": 0.0005122329994264874,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047852399984549265,
"count": 1,
"is_parallel": true,
"self": 0.00047852399984549265
},
"communicator.exchange": {
"total": 0.046026797000195074,
"count": 1,
"is_parallel": true,
"self": 0.046026797000195074
},
"steps_from_proto": {
"total": 0.0016596540008322336,
"count": 1,
"is_parallel": true,
"self": 0.0004727280011138646,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001186925999718369,
"count": 8,
"is_parallel": true,
"self": 0.001186925999718369
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1358.672815676001,
"count": 64690,
"is_parallel": true,
"self": 30.14013462017465,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 25.49354818697975,
"count": 64690,
"is_parallel": true,
"self": 25.49354818697975
},
"communicator.exchange": {
"total": 1202.0809343339015,
"count": 64690,
"is_parallel": true,
"self": 1202.0809343339015
},
"steps_from_proto": {
"total": 100.95819853494504,
"count": 64690,
"is_parallel": true,
"self": 25.135631938998813,
"children": {
"_process_rank_one_or_two_observation": {
"total": 75.82256659594623,
"count": 517520,
"is_parallel": true,
"self": 75.82256659594623
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1485.271837716201,
"count": 64691,
"self": 2.9798812501694556,
"children": {
"process_trajectory": {
"total": 183.20917830903363,
"count": 64691,
"self": 183.00248284303325,
"children": {
"RLTrainer._checkpoint": {
"total": 0.20669546600038302,
"count": 2,
"self": 0.20669546600038302
}
}
},
"_update_policy": {
"total": 1299.0827781569978,
"count": 454,
"self": 633.4596136449909,
"children": {
"TorchPPOOptimizer.update": {
"total": 665.623164512007,
"count": 30272,
"self": 665.623164512007
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3869994290871546e-06,
"count": 1,
"self": 1.3869994290871546e-06
},
"TrainerController._save_models": {
"total": 0.09349196800030768,
"count": 1,
"self": 0.001884271000562876,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0916076969997448,
"count": 1,
"self": 0.0916076969997448
}
}
}
}
}
}
}