ptoloudis's picture
First Push
869823d verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4185730218887329,
"min": 0.4185730218887329,
"max": 1.4671629667282104,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 12530.40234375,
"min": 12530.40234375,
"max": 44507.85546875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989878.0,
"min": 29958.0,
"max": 989878.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989878.0,
"min": 29958.0,
"max": 989878.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.3910575211048126,
"min": -0.10510184615850449,
"max": 0.453395813703537,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 103.23918914794922,
"min": -25.329544067382812,
"max": 121.05667877197266,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.0540316179394722,
"min": 0.003430201904848218,
"max": 0.3303825259208679,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 14.264347076416016,
"min": 0.8541202545166016,
"max": 78.63104248046875,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0682032393757254,
"min": 0.06511108100763849,
"max": 0.07294659902871892,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0230485906358808,
"min": 0.5033261976238266,
"max": 1.04888244275935,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.011619496290546118,
"min": 0.0001541237208678819,
"max": 0.013019459746240447,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.17429244435819177,
"min": 0.0016953609295467008,
"max": 0.18227243644736627,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.512477495873334e-06,
"min": 7.512477495873334e-06,
"max": 0.00029523814444442855,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011268716243810001,
"min": 0.00011268716243810001,
"max": 0.0035078573307143,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10250412666666667,
"min": 0.10250412666666667,
"max": 0.1984127142857143,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5375619,
"min": 1.388889,
"max": 2.5692857,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002601622540000001,
"min": 0.0002601622540000001,
"max": 0.009841430157142856,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0039024338100000014,
"min": 0.0039024338100000014,
"max": 0.11695164143000003,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.008226909674704075,
"min": 0.0077830529771745205,
"max": 0.3760862350463867,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1234036386013031,
"min": 0.10896274447441101,
"max": 2.632603645324707,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 457.87301587301585,
"min": 425.95454545454544,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28846.0,
"min": 16629.0,
"max": 32849.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.3516126726827924,
"min": -0.999987552408129,
"max": 1.513433309441263,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 85.15159837901592,
"min": -31.999601677060127,
"max": 99.88659842312336,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.3516126726827924,
"min": -0.999987552408129,
"max": 1.513433309441263,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 85.15159837901592,
"min": -31.999601677060127,
"max": 99.88659842312336,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.038956941581942836,
"min": 0.03660548727423178,
"max": 7.139599466586814,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.4542873196623987,
"min": 2.4159621600992978,
"max": 121.37319093197584,
"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": "1743759009",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/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": "1743761347"
},
"total": 2337.638979544,
"count": 1,
"self": 0.5282870290002393,
"children": {
"run_training.setup": {
"total": 0.02148465799996302,
"count": 1,
"self": 0.02148465799996302
},
"TrainerController.start_learning": {
"total": 2337.089207857,
"count": 1,
"self": 1.7447182810287813,
"children": {
"TrainerController._reset_env": {
"total": 2.217395534000161,
"count": 1,
"self": 2.217395534000161
},
"TrainerController.advance": {
"total": 2333.03642901297,
"count": 63548,
"self": 1.7562227760517999,
"children": {
"env_step": {
"total": 1623.807898671966,
"count": 63548,
"self": 1449.3243318319292,
"children": {
"SubprocessEnvManager._take_step": {
"total": 173.49551099905784,
"count": 63548,
"self": 5.108520826031054,
"children": {
"TorchPolicy.evaluate": {
"total": 168.3869901730268,
"count": 62559,
"self": 168.3869901730268
}
}
},
"workers": {
"total": 0.9880558409790865,
"count": 63548,
"self": 0.0,
"children": {
"worker_root": {
"total": 2331.193917635074,
"count": 63548,
"is_parallel": true,
"self": 1007.0058721200915,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021125519999714015,
"count": 1,
"is_parallel": true,
"self": 0.0007440310002948536,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001368520999676548,
"count": 8,
"is_parallel": true,
"self": 0.001368520999676548
}
}
},
"UnityEnvironment.step": {
"total": 0.0462365299999874,
"count": 1,
"is_parallel": true,
"self": 0.0005140380001193989,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004523210000115796,
"count": 1,
"is_parallel": true,
"self": 0.0004523210000115796
},
"communicator.exchange": {
"total": 0.04370984499996666,
"count": 1,
"is_parallel": true,
"self": 0.04370984499996666
},
"steps_from_proto": {
"total": 0.0015603259998897556,
"count": 1,
"is_parallel": true,
"self": 0.00034945299989885825,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012108729999908974,
"count": 8,
"is_parallel": true,
"self": 0.0012108729999908974
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1324.1880455149824,
"count": 63547,
"is_parallel": true,
"self": 33.25807361885995,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.59699563102322,
"count": 63547,
"is_parallel": true,
"self": 23.59699563102322
},
"communicator.exchange": {
"total": 1168.5220084760015,
"count": 63547,
"is_parallel": true,
"self": 1168.5220084760015
},
"steps_from_proto": {
"total": 98.81096778909773,
"count": 63547,
"is_parallel": true,
"self": 20.68582852319537,
"children": {
"_process_rank_one_or_two_observation": {
"total": 78.12513926590236,
"count": 508376,
"is_parallel": true,
"self": 78.12513926590236
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 707.4723075649524,
"count": 63548,
"self": 3.284575679875843,
"children": {
"process_trajectory": {
"total": 132.1079465690807,
"count": 63548,
"self": 131.90172395208106,
"children": {
"RLTrainer._checkpoint": {
"total": 0.20622261699963929,
"count": 2,
"self": 0.20622261699963929
}
}
},
"_update_policy": {
"total": 572.0797853159959,
"count": 444,
"self": 313.71299598194514,
"children": {
"TorchPPOOptimizer.update": {
"total": 258.36678933405074,
"count": 22806,
"self": 258.36678933405074
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1890006135217845e-06,
"count": 1,
"self": 1.1890006135217845e-06
},
"TrainerController._save_models": {
"total": 0.09066384000016114,
"count": 1,
"self": 0.001569393999488966,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08909444600067218,
"count": 1,
"self": 0.08909444600067218
}
}
}
}
}
}
}