Adilbai's picture
First commit
c0f187d verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.34709692001342773,
"min": 0.34709692001342773,
"max": 1.3772199153900146,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 10390.693359375,
"min": 10390.693359375,
"max": 41779.34375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989964.0,
"min": 29929.0,
"max": 989964.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989964.0,
"min": 29929.0,
"max": 989964.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5435134768486023,
"min": -0.14447298645973206,
"max": 0.638748824596405,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 152.727294921875,
"min": -34.24009704589844,
"max": 185.23715209960938,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.02685640938580036,
"min": -0.005096071865409613,
"max": 0.42292797565460205,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 7.5466508865356445,
"min": -1.4778608083724976,
"max": 100.23393249511719,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06706119823751024,
"min": 0.06480447375919238,
"max": 0.07554008456437648,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9388567753251433,
"min": 0.5489559323764759,
"max": 1.0575611839012709,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.02001704709458945,
"min": 0.0003918369340308651,
"max": 0.02001704709458945,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2802386593242523,
"min": 0.005485717076432111,
"max": 0.2802386593242523,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.537318916164284e-06,
"min": 7.537318916164284e-06,
"max": 0.0002948425892191375,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010552246482629998,
"min": 0.00010552246482629998,
"max": 0.0036355327881558,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10251240714285716,
"min": 0.10251240714285716,
"max": 0.1982808625,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4351737000000002,
"min": 1.4351737000000002,
"max": 2.6118442,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002609894735714286,
"min": 0.0002609894735714286,
"max": 0.009828258163749999,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036538526300000005,
"min": 0.0036538526300000005,
"max": 0.12120323558000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.010533587075769901,
"min": 0.010533587075769901,
"max": 0.38407689332962036,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.14747022092342377,
"min": 0.14747022092342377,
"max": 3.072615146636963,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 308.67021276595744,
"min": 284.375,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29015.0,
"min": 16472.0,
"max": 32947.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6482340273387888,
"min": -0.9997290836707238,
"max": 1.6771538246136446,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 154.93399856984615,
"min": -30.99160159379244,
"max": 174.42399775981903,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6482340273387888,
"min": -0.9997290836707238,
"max": 1.6771538246136446,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 154.93399856984615,
"min": -30.99160159379244,
"max": 174.42399775981903,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03420959581977668,
"min": 0.03371683187707766,
"max": 7.7171577460625596,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.215702007059008,
"min": 3.215702007059008,
"max": 131.1916816830635,
"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": "1749632864",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn --force ./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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1749635270"
},
"total": 2406.2906839360003,
"count": 1,
"self": 0.4845137860002069,
"children": {
"run_training.setup": {
"total": 0.020860632999983864,
"count": 1,
"self": 0.020860632999983864
},
"TrainerController.start_learning": {
"total": 2405.7853095170003,
"count": 1,
"self": 1.601997605041106,
"children": {
"TrainerController._reset_env": {
"total": 2.2697864730000674,
"count": 1,
"self": 2.2697864730000674
},
"TrainerController.advance": {
"total": 2401.825112346959,
"count": 64027,
"self": 1.6322849109128583,
"children": {
"env_step": {
"total": 1698.2700127610228,
"count": 64027,
"self": 1530.7088281619642,
"children": {
"SubprocessEnvManager._take_step": {
"total": 166.6351843210398,
"count": 64027,
"self": 5.254397206975,
"children": {
"TorchPolicy.evaluate": {
"total": 161.3807871140648,
"count": 62547,
"self": 161.3807871140648
}
}
},
"workers": {
"total": 0.9260002780188188,
"count": 64027,
"self": 0.0,
"children": {
"worker_root": {
"total": 2400.200380381991,
"count": 64027,
"is_parallel": true,
"self": 993.9651638779801,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021290639999733685,
"count": 1,
"is_parallel": true,
"self": 0.0007669850001548184,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00136207899981855,
"count": 8,
"is_parallel": true,
"self": 0.00136207899981855
}
}
},
"UnityEnvironment.step": {
"total": 0.0523250950000147,
"count": 1,
"is_parallel": true,
"self": 0.0006155080000098678,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005076680001820932,
"count": 1,
"is_parallel": true,
"self": 0.0005076680001820932
},
"communicator.exchange": {
"total": 0.04938620599978094,
"count": 1,
"is_parallel": true,
"self": 0.04938620599978094
},
"steps_from_proto": {
"total": 0.0018157130000417965,
"count": 1,
"is_parallel": true,
"self": 0.0003686520003611804,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001447060999680616,
"count": 8,
"is_parallel": true,
"self": 0.001447060999680616
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1406.235216504011,
"count": 64026,
"is_parallel": true,
"self": 33.44424187610889,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 25.21370678194444,
"count": 64026,
"is_parallel": true,
"self": 25.21370678194444
},
"communicator.exchange": {
"total": 1243.4155479730066,
"count": 64026,
"is_parallel": true,
"self": 1243.4155479730066
},
"steps_from_proto": {
"total": 104.16171987295115,
"count": 64026,
"is_parallel": true,
"self": 21.326765515980924,
"children": {
"_process_rank_one_or_two_observation": {
"total": 82.83495435697023,
"count": 512208,
"is_parallel": true,
"self": 82.83495435697023
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 701.9228146750236,
"count": 64027,
"self": 2.9798679860271022,
"children": {
"process_trajectory": {
"total": 139.95392378299516,
"count": 64027,
"self": 139.67806338699552,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2758603959996435,
"count": 2,
"self": 0.2758603959996435
}
}
},
"_update_policy": {
"total": 558.9890229060013,
"count": 460,
"self": 311.0371156200017,
"children": {
"TorchPPOOptimizer.update": {
"total": 247.9519072859996,
"count": 22776,
"self": 247.9519072859996
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.032999989547534e-06,
"count": 1,
"self": 1.032999989547534e-06
},
"TrainerController._save_models": {
"total": 0.08841205900034765,
"count": 1,
"self": 0.0018383490000815073,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08657371000026615,
"count": 1,
"self": 0.08657371000026615
}
}
}
}
}
}
}