ppo-Pyramids / run_logs /timers.json
ataunal's picture
First Push
2fd25a6
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.9148204922676086,
"min": 0.9148204922676086,
"max": 1.5012378692626953,
"count": 3
},
"Pyramids.Policy.Entropy.sum": {
"value": 27400.703125,
"min": 27400.703125,
"max": 45541.55078125,
"count": 3
},
"Pyramids.Step.mean": {
"value": 89970.0,
"min": 29952.0,
"max": 89970.0,
"count": 3
},
"Pyramids.Step.sum": {
"value": 89970.0,
"min": 29952.0,
"max": 89970.0,
"count": 3
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.10244161635637283,
"min": -0.10244161635637283,
"max": -0.07576289772987366,
"count": 3
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -24.585987091064453,
"min": -24.585987091064453,
"max": -17.955806732177734,
"count": 3
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.2163112610578537,
"min": 0.2163112610578537,
"max": 0.378736287355423,
"count": 3
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 51.914703369140625,
"min": 51.914703369140625,
"max": 91.27544403076172,
"count": 3
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07296046107898836,
"min": 0.07094076145861845,
"max": 0.07440731547689407,
"count": 3
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.7296046107898836,
"min": 0.49658533021032913,
"max": 0.7296046107898836,
"count": 3
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.0008105346256205457,
"min": 0.0008105346256205457,
"max": 0.009002897662479038,
"count": 3
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.008105346256205457,
"min": 0.008105346256205457,
"max": 0.06302028363735326,
"count": 3
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.91406736198e-05,
"min": 7.91406736198e-05,
"max": 0.0002515063018788571,
"count": 3
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0007914067361980001,
"min": 0.0007914067361980001,
"max": 0.0017605441131519997,
"count": 3
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1263802,
"min": 0.1263802,
"max": 0.1838354285714286,
"count": 3
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.263802,
"min": 1.263802,
"max": 1.398523,
"count": 3
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0026453819800000005,
"min": 0.0026453819800000005,
"max": 0.008385159314285713,
"count": 3
},
"Pyramids.Policy.Beta.sum": {
"value": 0.026453819800000004,
"min": 0.026453819800000004,
"max": 0.058696115199999996,
"count": 3
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.1369694173336029,
"min": 0.1369694173336029,
"max": 0.5733288526535034,
"count": 3
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 1.3696941137313843,
"min": 1.3696941137313843,
"max": 4.013301849365234,
"count": 3
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 987.71875,
"min": 983.0909090909091,
"max": 999.0,
"count": 3
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31607.0,
"min": 15984.0,
"max": 32442.0,
"count": 3
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -0.9261813028715551,
"min": -1.0000000521540642,
"max": -0.9234545975923538,
"count": 3
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -29.637801691889763,
"min": -30.474001720547676,
"max": -16.000000834465027,
"count": 3
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -0.9261813028715551,
"min": -1.0000000521540642,
"max": -0.9234545975923538,
"count": 3
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -29.637801691889763,
"min": -30.474001720547676,
"max": -16.000000834465027,
"count": 3
},
"Pyramids.Policy.RndReward.mean": {
"value": 1.5837116080801934,
"min": 1.5837116080801934,
"max": 11.688033819198608,
"count": 3
},
"Pyramids.Policy.RndReward.sum": {
"value": 50.67877145856619,
"min": 50.67877145856619,
"max": 187.00854110717773,
"count": 3
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 3
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 3
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1686237566",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1686237765"
},
"total": 198.76117317600006,
"count": 1,
"self": 1.0465921420000086,
"children": {
"run_training.setup": {
"total": 0.07062023200001022,
"count": 1,
"self": 0.07062023200001022
},
"TrainerController.start_learning": {
"total": 197.64396080200004,
"count": 1,
"self": 0.13004797299549864,
"children": {
"TrainerController._reset_env": {
"total": 5.304961340000091,
"count": 1,
"self": 5.304961340000091
},
"TrainerController.advance": {
"total": 192.0415421810044,
"count": 6260,
"self": 0.13544875801153466,
"children": {
"env_step": {
"total": 128.23672941699033,
"count": 6260,
"self": 117.26518526598056,
"children": {
"SubprocessEnvManager._take_step": {
"total": 10.894160795004609,
"count": 6260,
"self": 0.459610031016382,
"children": {
"TorchPolicy.evaluate": {
"total": 10.434550763988227,
"count": 6256,
"self": 10.434550763988227
}
}
},
"workers": {
"total": 0.07738335600515711,
"count": 6260,
"self": 0.0,
"children": {
"worker_root": {
"total": 196.95379087500555,
"count": 6260,
"is_parallel": true,
"self": 90.27220173399951,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002955956000050719,
"count": 1,
"is_parallel": true,
"self": 0.0011241299998800969,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018318260001706221,
"count": 8,
"is_parallel": true,
"self": 0.0018318260001706221
}
}
},
"UnityEnvironment.step": {
"total": 0.04859236199990846,
"count": 1,
"is_parallel": true,
"self": 0.0005935849999332277,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004961219999586319,
"count": 1,
"is_parallel": true,
"self": 0.0004961219999586319
},
"communicator.exchange": {
"total": 0.045592117000069265,
"count": 1,
"is_parallel": true,
"self": 0.045592117000069265
},
"steps_from_proto": {
"total": 0.001910537999947337,
"count": 1,
"is_parallel": true,
"self": 0.00042213999995510676,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014883979999922303,
"count": 8,
"is_parallel": true,
"self": 0.0014883979999922303
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 106.68158914100604,
"count": 6259,
"is_parallel": true,
"self": 3.3133003700245354,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.257042258004958,
"count": 6259,
"is_parallel": true,
"self": 2.257042258004958
},
"communicator.exchange": {
"total": 91.00068138698066,
"count": 6259,
"is_parallel": true,
"self": 91.00068138698066
},
"steps_from_proto": {
"total": 10.11056512599589,
"count": 6259,
"is_parallel": true,
"self": 2.003080381963855,
"children": {
"_process_rank_one_or_two_observation": {
"total": 8.107484744032035,
"count": 50072,
"is_parallel": true,
"self": 8.107484744032035
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 63.669364006002525,
"count": 6260,
"self": 0.16679451799495837,
"children": {
"process_trajectory": {
"total": 9.814462238007309,
"count": 6260,
"self": 9.814462238007309
},
"_update_policy": {
"total": 53.68810725000026,
"count": 29,
"self": 34.5890388290004,
"children": {
"TorchPPOOptimizer.update": {
"total": 19.099068420999856,
"count": 2289,
"self": 19.099068420999856
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0060000477096764e-06,
"count": 1,
"self": 1.0060000477096764e-06
},
"TrainerController._save_models": {
"total": 0.16740830200001255,
"count": 1,
"self": 0.0017958620001081727,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16561243999990438,
"count": 1,
"self": 0.16561243999990438
}
}
}
}
}
}
}