ppo-Pyramids / run_logs /timers.json
mviano's picture
First Push
f81cea0 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3301348090171814,
"min": 0.3301348090171814,
"max": 1.4909651279449463,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 9914.6083984375,
"min": 9914.6083984375,
"max": 45229.91796875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989887.0,
"min": 29952.0,
"max": 989887.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989887.0,
"min": 29952.0,
"max": 989887.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6729474067687988,
"min": -0.0858224406838417,
"max": 0.6729474067687988,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 193.1359100341797,
"min": -20.769031524658203,
"max": 193.1359100341797,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.03691047430038452,
"min": -0.03242198005318642,
"max": 0.5937733054161072,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 10.593306541442871,
"min": -8.429715156555176,
"max": 140.72427368164062,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07009360415589375,
"min": 0.06577560376043788,
"max": 0.07354520476942772,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0514040623384062,
"min": 0.514816433385994,
"max": 1.0657340850060184,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.018025814964332518,
"min": 0.0010192231638315229,
"max": 0.018961556263983454,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.27038722446498775,
"min": 0.013249901129809796,
"max": 0.27038722446498775,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.474837508419997e-06,
"min": 7.474837508419997e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011212256262629995,
"min": 0.00011212256262629995,
"max": 0.0035101040299654,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10249158,
"min": 0.10249158,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5373737,
"min": 1.3886848,
"max": 2.6173269,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002589088419999999,
"min": 0.0002589088419999999,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003883632629999999,
"min": 0.003883632629999999,
"max": 0.11702645653999999,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.016223954036831856,
"min": 0.01585986278951168,
"max": 0.5980637669563293,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.2433592975139618,
"min": 0.22626979649066925,
"max": 4.186446189880371,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 268.0373831775701,
"min": 268.0373831775701,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28680.0,
"min": 15984.0,
"max": 32697.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7334259167589523,
"min": -1.0000000521540642,
"max": 1.7334259167589523,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 187.20999900996685,
"min": -30.9928015768528,
"max": 187.20999900996685,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7334259167589523,
"min": -1.0000000521540642,
"max": 1.7334259167589523,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 187.20999900996685,
"min": -30.9928015768528,
"max": 187.20999900996685,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.044414734847291755,
"min": 0.044414734847291755,
"max": 13.824727034196258,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.796791363507509,
"min": 4.796791363507509,
"max": 221.19563254714012,
"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": "1729810934",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1729812681"
},
"total": 1747.5811398410005,
"count": 1,
"self": 0.32643172899952333,
"children": {
"run_training.setup": {
"total": 0.05606421300035436,
"count": 1,
"self": 0.05606421300035436
},
"TrainerController.start_learning": {
"total": 1747.1986438990007,
"count": 1,
"self": 1.3995315429301627,
"children": {
"TrainerController._reset_env": {
"total": 2.1889615370000683,
"count": 1,
"self": 2.1889615370000683
},
"TrainerController.advance": {
"total": 1743.5279341880714,
"count": 64195,
"self": 1.326919759350858,
"children": {
"env_step": {
"total": 1100.064448106903,
"count": 64195,
"self": 955.8784302557151,
"children": {
"SubprocessEnvManager._take_step": {
"total": 143.34183748708074,
"count": 64195,
"self": 4.663799701333119,
"children": {
"TorchPolicy.evaluate": {
"total": 138.67803778574762,
"count": 62573,
"self": 138.67803778574762
}
}
},
"workers": {
"total": 0.8441803641071601,
"count": 64195,
"self": 0.0,
"children": {
"worker_root": {
"total": 1745.0284688413076,
"count": 64195,
"is_parallel": true,
"self": 883.6689650754251,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021438940002553863,
"count": 1,
"is_parallel": true,
"self": 0.0006751569999323692,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014687370003230171,
"count": 8,
"is_parallel": true,
"self": 0.0014687370003230171
}
}
},
"UnityEnvironment.step": {
"total": 0.03539983099926758,
"count": 1,
"is_parallel": true,
"self": 0.0004517309989751084,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00030624999999417923,
"count": 1,
"is_parallel": true,
"self": 0.00030624999999417923
},
"communicator.exchange": {
"total": 0.03335601700018742,
"count": 1,
"is_parallel": true,
"self": 0.03335601700018742
},
"steps_from_proto": {
"total": 0.0012858330001108698,
"count": 1,
"is_parallel": true,
"self": 0.000312189999021939,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009736430010889308,
"count": 8,
"is_parallel": true,
"self": 0.0009736430010889308
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 861.3595037658824,
"count": 64194,
"is_parallel": true,
"self": 21.831434710897156,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 13.767708518088511,
"count": 64194,
"is_parallel": true,
"self": 13.767708518088511
},
"communicator.exchange": {
"total": 762.4688790630125,
"count": 64194,
"is_parallel": true,
"self": 762.4688790630125
},
"steps_from_proto": {
"total": 63.29148147388423,
"count": 64194,
"is_parallel": true,
"self": 13.772601158365433,
"children": {
"_process_rank_one_or_two_observation": {
"total": 49.5188803155188,
"count": 513552,
"is_parallel": true,
"self": 49.5188803155188
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 642.1365663218176,
"count": 64195,
"self": 2.752761771062069,
"children": {
"process_trajectory": {
"total": 121.07463003774865,
"count": 64195,
"self": 120.87994148074904,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1946885569996084,
"count": 2,
"self": 0.1946885569996084
}
}
},
"_update_policy": {
"total": 518.3091745130068,
"count": 455,
"self": 286.3558637539918,
"children": {
"TorchPPOOptimizer.update": {
"total": 231.95331075901504,
"count": 22806,
"self": 231.95331075901504
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1339998309267685e-06,
"count": 1,
"self": 1.1339998309267685e-06
},
"TrainerController._save_models": {
"total": 0.08221549699919706,
"count": 1,
"self": 0.0014834779976808932,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08073201900151616,
"count": 1,
"self": 0.08073201900151616
}
}
}
}
}
}
}