ppo-PyramidsRND / run_logs /timers.json
mjschock's picture
First Push
2772db2
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.432206392288208,
"min": 0.432206392288208,
"max": 1.4730149507522583,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 12848.6318359375,
"min": 12848.6318359375,
"max": 44685.3828125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989920.0,
"min": 29952.0,
"max": 989920.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989920.0,
"min": 29952.0,
"max": 989920.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.46615034341812134,
"min": -0.15150484442710876,
"max": 0.48049354553222656,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 126.32674407958984,
"min": -35.906646728515625,
"max": 129.73326110839844,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.004022940993309021,
"min": -0.01697673089802265,
"max": 0.42778825759887695,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 1.0902169942855835,
"min": -4.583717346191406,
"max": 101.38581848144531,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07025942367986458,
"min": 0.06441083694654474,
"max": 0.07634530807987229,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9836319315181041,
"min": 0.534417156559106,
"max": 1.0185675451060638,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.013918780163676427,
"min": 0.00027117087841156364,
"max": 0.01404069789818355,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.19486292229146998,
"min": 0.0031040734473766454,
"max": 0.19816185142068815,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.606383178857143e-06,
"min": 7.606383178857143e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.000106489364504,
"min": 0.000106489364504,
"max": 0.0032240200253266993,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1025354285714286,
"min": 0.1025354285714286,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4354960000000003,
"min": 1.3886848,
"max": 2.3599716999999996,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026328931428571425,
"min": 0.00026328931428571425,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036860503999999994,
"min": 0.0036860503999999994,
"max": 0.10747986267000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.006543363910168409,
"min": 0.006543363910168409,
"max": 0.4691660702228546,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.09160709381103516,
"min": 0.09160709381103516,
"max": 3.2841625213623047,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 406.7887323943662,
"min": 396.6388888888889,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28882.0,
"min": 15984.0,
"max": 34650.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4804816689919418,
"min": -1.0000000521540642,
"max": 1.5200138630138502,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 105.11419849842787,
"min": -31.99480165541172,
"max": 114.9943981692195,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4804816689919418,
"min": -1.0000000521540642,
"max": 1.5200138630138502,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 105.11419849842787,
"min": -31.99480165541172,
"max": 114.9943981692195,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.027698535902153463,
"min": 0.027698535902153463,
"max": 9.6401991173625,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 1.966596049052896,
"min": 1.966596049052896,
"max": 154.2431858778,
"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": "1675548662",
"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": "1675550977"
},
"total": 2314.564682952,
"count": 1,
"self": 0.49108289500054525,
"children": {
"run_training.setup": {
"total": 0.10712699100008649,
"count": 1,
"self": 0.10712699100008649
},
"TrainerController.start_learning": {
"total": 2313.9664730659997,
"count": 1,
"self": 1.5147602249653573,
"children": {
"TrainerController._reset_env": {
"total": 6.936558383000147,
"count": 1,
"self": 6.936558383000147
},
"TrainerController.advance": {
"total": 2305.423361138033,
"count": 63591,
"self": 1.4745091750774009,
"children": {
"env_step": {
"total": 1540.6930787249762,
"count": 63591,
"self": 1418.5517137349798,
"children": {
"SubprocessEnvManager._take_step": {
"total": 121.20565162596881,
"count": 63591,
"self": 4.8942804219555,
"children": {
"TorchPolicy.evaluate": {
"total": 116.31137120401331,
"count": 62564,
"self": 38.59636141303531,
"children": {
"TorchPolicy.sample_actions": {
"total": 77.715009790978,
"count": 62564,
"self": 77.715009790978
}
}
}
}
},
"workers": {
"total": 0.9357133640276061,
"count": 63591,
"self": 0.0,
"children": {
"worker_root": {
"total": 2308.3186362929036,
"count": 63591,
"is_parallel": true,
"self": 1008.9289815168961,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001851342999998451,
"count": 1,
"is_parallel": true,
"self": 0.0006784439999591996,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011728990000392514,
"count": 8,
"is_parallel": true,
"self": 0.0011728990000392514
}
}
},
"UnityEnvironment.step": {
"total": 0.09949328200013952,
"count": 1,
"is_parallel": true,
"self": 0.0004994800001441035,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005259130000467849,
"count": 1,
"is_parallel": true,
"self": 0.0005259130000467849
},
"communicator.exchange": {
"total": 0.09669451900003878,
"count": 1,
"is_parallel": true,
"self": 0.09669451900003878
},
"steps_from_proto": {
"total": 0.0017733699999098462,
"count": 1,
"is_parallel": true,
"self": 0.00043244099992989504,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013409289999799512,
"count": 8,
"is_parallel": true,
"self": 0.0013409289999799512
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1299.3896547760075,
"count": 63590,
"is_parallel": true,
"self": 28.632702366042622,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.65935295797226,
"count": 63590,
"is_parallel": true,
"self": 23.65935295797226
},
"communicator.exchange": {
"total": 1140.3609726659784,
"count": 63590,
"is_parallel": true,
"self": 1140.3609726659784
},
"steps_from_proto": {
"total": 106.73662678601431,
"count": 63590,
"is_parallel": true,
"self": 24.1413972509431,
"children": {
"_process_rank_one_or_two_observation": {
"total": 82.59522953507121,
"count": 508720,
"is_parallel": true,
"self": 82.59522953507121
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 763.2557732379798,
"count": 63591,
"self": 2.551895961899845,
"children": {
"process_trajectory": {
"total": 172.18199050708427,
"count": 63591,
"self": 171.9869582320839,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1950322750003579,
"count": 2,
"self": 0.1950322750003579
}
}
},
"_update_policy": {
"total": 588.5218867689957,
"count": 443,
"self": 231.8582354679911,
"children": {
"TorchPPOOptimizer.update": {
"total": 356.6636513010046,
"count": 22788,
"self": 356.6636513010046
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.900004442897625e-07,
"count": 1,
"self": 9.900004442897625e-07
},
"TrainerController._save_models": {
"total": 0.09179233000031672,
"count": 1,
"self": 0.0014256370004659402,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09036669299985078,
"count": 1,
"self": 0.09036669299985078
}
}
}
}
}
}
}