ppo-Pyramids / run_logs /timers.json
mjkim0928's picture
First Push
5da4cc8 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4027997553348541,
"min": 0.4027997553348541,
"max": 1.4343562126159668,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 12019.544921875,
"min": 12019.544921875,
"max": 43512.62890625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989873.0,
"min": 29952.0,
"max": 989873.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989873.0,
"min": 29952.0,
"max": 989873.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.536551833152771,
"min": -0.11401091516017914,
"max": 0.6212583780288696,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 149.16140747070312,
"min": -27.47663116455078,
"max": 174.5736083984375,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.014315195381641388,
"min": -0.00030912665533833206,
"max": 0.3096245229244232,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 3.9796242713928223,
"min": -0.08470070362091064,
"max": 74.6195068359375,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06890531469188216,
"min": 0.0640647734949553,
"max": 0.07341675332468116,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0335797203782324,
"min": 0.5139172732727681,
"max": 1.0371465390096146,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015860375400128152,
"min": 0.0009943202910716266,
"max": 0.017657518174798627,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2379056310019223,
"min": 0.013920484075002773,
"max": 0.2472052544471808,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.442617519160001e-06,
"min": 7.442617519160001e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011163926278740001,
"min": 0.00011163926278740001,
"max": 0.0035081954306015995,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10248084,
"min": 0.10248084,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5372126000000002,
"min": 1.3886848,
"max": 2.5693984,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.000257835916,
"min": 0.000257835916,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0038675387400000003,
"min": 0.0038675387400000003,
"max": 0.11696290016,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.009087380953133106,
"min": 0.009087380953133106,
"max": 0.3771204650402069,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.13631071150302887,
"min": 0.13631071150302887,
"max": 2.639843225479126,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 341.14772727272725,
"min": 320.22340425531917,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30021.0,
"min": 15984.0,
"max": 33087.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5474516658970479,
"min": -1.0000000521540642,
"max": 1.5988329475397591,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 137.72319826483727,
"min": -30.475601695477962,
"max": 152.919798001647,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5474516658970479,
"min": -1.0000000521540642,
"max": 1.5988329475397591,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 137.72319826483727,
"min": -30.475601695477962,
"max": 152.919798001647,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03307639237383238,
"min": 0.03307639237383238,
"max": 7.429623998701572,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.943798921271082,
"min": 2.943798921271082,
"max": 118.87398397922516,
"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": "1738574995",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1738577308"
},
"total": 2313.0557430199997,
"count": 1,
"self": 0.4764227659993594,
"children": {
"run_training.setup": {
"total": 0.01983663200007868,
"count": 1,
"self": 0.01983663200007868
},
"TrainerController.start_learning": {
"total": 2312.5594836220002,
"count": 1,
"self": 1.354617482017602,
"children": {
"TrainerController._reset_env": {
"total": 2.105676241999845,
"count": 1,
"self": 2.105676241999845
},
"TrainerController.advance": {
"total": 2309.0069774789827,
"count": 63889,
"self": 1.3784180908928647,
"children": {
"env_step": {
"total": 1607.7396915389504,
"count": 63889,
"self": 1447.8375723189638,
"children": {
"SubprocessEnvManager._take_step": {
"total": 159.10443604997954,
"count": 63889,
"self": 4.793551470850616,
"children": {
"TorchPolicy.evaluate": {
"total": 154.31088457912892,
"count": 62561,
"self": 154.31088457912892
}
}
},
"workers": {
"total": 0.7976831700070761,
"count": 63889,
"self": 0.0,
"children": {
"worker_root": {
"total": 2307.04189735501,
"count": 63889,
"is_parallel": true,
"self": 973.2597713390296,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019966509998994297,
"count": 1,
"is_parallel": true,
"self": 0.0006754909991286695,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013211600007707602,
"count": 8,
"is_parallel": true,
"self": 0.0013211600007707602
}
}
},
"UnityEnvironment.step": {
"total": 0.05157556700032728,
"count": 1,
"is_parallel": true,
"self": 0.0005359140004657093,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0006352049999804876,
"count": 1,
"is_parallel": true,
"self": 0.0006352049999804876
},
"communicator.exchange": {
"total": 0.04630184899997403,
"count": 1,
"is_parallel": true,
"self": 0.04630184899997403
},
"steps_from_proto": {
"total": 0.004102598999907059,
"count": 1,
"is_parallel": true,
"self": 0.0004629080012819031,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0036396909986251558,
"count": 8,
"is_parallel": true,
"self": 0.0036396909986251558
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1333.7821260159803,
"count": 63888,
"is_parallel": true,
"self": 31.616955611805224,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.307319588102928,
"count": 63888,
"is_parallel": true,
"self": 23.307319588102928
},
"communicator.exchange": {
"total": 1182.144339918063,
"count": 63888,
"is_parallel": true,
"self": 1182.144339918063
},
"steps_from_proto": {
"total": 96.71351089800919,
"count": 63888,
"is_parallel": true,
"self": 19.390343191490956,
"children": {
"_process_rank_one_or_two_observation": {
"total": 77.32316770651823,
"count": 511104,
"is_parallel": true,
"self": 77.32316770651823
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 699.8888678491394,
"count": 63889,
"self": 2.7116423762945487,
"children": {
"process_trajectory": {
"total": 133.36949172484492,
"count": 63889,
"self": 133.15142243184437,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21806929300055344,
"count": 2,
"self": 0.21806929300055344
}
}
},
"_update_policy": {
"total": 563.8077337479999,
"count": 454,
"self": 308.0816017970037,
"children": {
"TorchPPOOptimizer.update": {
"total": 255.7261319509962,
"count": 22800,
"self": 255.7261319509962
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.750004442641512e-07,
"count": 1,
"self": 7.750004442641512e-07
},
"TrainerController._save_models": {
"total": 0.09221164399968984,
"count": 1,
"self": 0.0013181749991417746,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09089346900054807,
"count": 1,
"self": 0.09089346900054807
}
}
}
}
}
}
}