testpyramidsrnd / run_logs /timers.json
Shivus's picture
First Pyramids
d257d90
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.7374254465103149,
"min": 0.7354739308357239,
"max": 1.4544875621795654,
"count": 16
},
"Pyramids.Policy.Entropy.sum": {
"value": 22158.16015625,
"min": 22028.916015625,
"max": 44123.3359375,
"count": 16
},
"Pyramids.Step.mean": {
"value": 479904.0,
"min": 29952.0,
"max": 479904.0,
"count": 16
},
"Pyramids.Step.sum": {
"value": 479904.0,
"min": 29952.0,
"max": 479904.0,
"count": 16
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.07202206552028656,
"min": -0.1915508210659027,
"max": -0.058979619294404984,
"count": 16
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -17.357316970825195,
"min": -45.397544860839844,
"max": -14.273067474365234,
"count": 16
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.030214279890060425,
"min": 0.030214279890060425,
"max": 0.248300701379776,
"count": 16
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 7.281641483306885,
"min": 7.281641483306885,
"max": 59.84046936035156,
"count": 16
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06815784465211751,
"min": 0.06471886275593185,
"max": 0.07315375409840674,
"count": 16
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.954209825129645,
"min": 0.4878393394284449,
"max": 1.0241525573776944,
"count": 16
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.0015370902591845903,
"min": 7.581922957380537e-05,
"max": 0.00687960320847226,
"count": 16
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.021519263628584265,
"min": 0.0010614692140332753,
"max": 0.04815722245930582,
"count": 16
},
"Pyramids.Policy.LearningRate.mean": {
"value": 2.131470718084286e-05,
"min": 2.131470718084286e-05,
"max": 0.00029030126037577137,
"count": 16
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0002984059005318,
"min": 0.0002984059005318,
"max": 0.0030856706714432,
"count": 16
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10710487142857143,
"min": 0.10710487142857143,
"max": 0.19676708571428575,
"count": 16
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4994682000000001,
"min": 1.3773696000000002,
"max": 2.4215096,
"count": 16
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0007197766557142858,
"min": 0.0007197766557142858,
"max": 0.00967703186285714,
"count": 16
},
"Pyramids.Policy.Beta.sum": {
"value": 0.010076873180000001,
"min": 0.010076873180000001,
"max": 0.10288282432000001,
"count": 16
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.027275118976831436,
"min": 0.027275118976831436,
"max": 0.43215733766555786,
"count": 16
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.3818516731262207,
"min": 0.3818516731262207,
"max": 3.02510142326355,
"count": 16
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 935.3870967741935,
"min": 930.8,
"max": 999.0,
"count": 16
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28997.0,
"min": 15984.0,
"max": 33014.0,
"count": 16
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -0.6780258549317237,
"min": -1.0000000521540642,
"max": -0.6359188007190824,
"count": 16
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -21.018801502883434,
"min": -31.994401648640633,
"max": -16.000000834465027,
"count": 16
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -0.6780258549317237,
"min": -1.0000000521540642,
"max": -0.6359188007190824,
"count": 16
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -21.018801502883434,
"min": -31.994401648640633,
"max": -16.000000834465027,
"count": 16
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.26671038736258784,
"min": 0.26671038736258784,
"max": 8.87466505356133,
"count": 16
},
"Pyramids.Policy.RndReward.sum": {
"value": 8.268022008240223,
"min": 8.268022008240223,
"max": 141.99464085698128,
"count": 16
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 16
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 16
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1661858401",
"python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1661859348"
},
"total": 946.029204316,
"count": 1,
"self": 0.44270347799999854,
"children": {
"run_training.setup": {
"total": 0.0413421709999966,
"count": 1,
"self": 0.0413421709999966
},
"TrainerController.start_learning": {
"total": 945.545158667,
"count": 1,
"self": 0.6378445290051786,
"children": {
"TrainerController._reset_env": {
"total": 9.865291363999972,
"count": 1,
"self": 9.865291363999972
},
"TrainerController.advance": {
"total": 934.949883445995,
"count": 31481,
"self": 0.6858694119654274,
"children": {
"env_step": {
"total": 585.5114319600027,
"count": 31481,
"self": 534.0456407629998,
"children": {
"SubprocessEnvManager._take_step": {
"total": 51.11960112999259,
"count": 31481,
"self": 2.2609074709754395,
"children": {
"TorchPolicy.evaluate": {
"total": 48.85869365901715,
"count": 31320,
"self": 16.88868105400661,
"children": {
"TorchPolicy.sample_actions": {
"total": 31.970012605010538,
"count": 31320,
"self": 31.970012605010538
}
}
}
}
},
"workers": {
"total": 0.34619006701029775,
"count": 31481,
"self": 0.0,
"children": {
"worker_root": {
"total": 943.5903271929965,
"count": 31481,
"is_parallel": true,
"self": 459.0316374479854,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005366275000028509,
"count": 1,
"is_parallel": true,
"self": 0.0040551060000098005,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013111690000187082,
"count": 8,
"is_parallel": true,
"self": 0.0013111690000187082
}
}
},
"UnityEnvironment.step": {
"total": 0.048166655999921204,
"count": 1,
"is_parallel": true,
"self": 0.0005082090000314565,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004575739999381767,
"count": 1,
"is_parallel": true,
"self": 0.0004575739999381767
},
"communicator.exchange": {
"total": 0.045587065999939114,
"count": 1,
"is_parallel": true,
"self": 0.045587065999939114
},
"steps_from_proto": {
"total": 0.0016138070000124571,
"count": 1,
"is_parallel": true,
"self": 0.0004308680000804088,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011829389999320483,
"count": 8,
"is_parallel": true,
"self": 0.0011829389999320483
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 484.55868974501107,
"count": 31480,
"is_parallel": true,
"self": 13.670741169995267,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 11.401649876998817,
"count": 31480,
"is_parallel": true,
"self": 11.401649876998817
},
"communicator.exchange": {
"total": 414.32225709800605,
"count": 31480,
"is_parallel": true,
"self": 414.32225709800605
},
"steps_from_proto": {
"total": 45.16404160001093,
"count": 31480,
"is_parallel": true,
"self": 11.042640836076998,
"children": {
"_process_rank_one_or_two_observation": {
"total": 34.121400763933934,
"count": 251840,
"is_parallel": true,
"self": 34.121400763933934
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 348.7525820740269,
"count": 31481,
"self": 1.0544240560280969,
"children": {
"process_trajectory": {
"total": 78.59101642799726,
"count": 31481,
"self": 78.48874995799713,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10226647000013145,
"count": 1,
"self": 0.10226647000013145
}
}
},
"_update_policy": {
"total": 269.10714159000156,
"count": 214,
"self": 106.10256095698958,
"children": {
"TorchPPOOptimizer.update": {
"total": 163.00458063301198,
"count": 11415,
"self": 163.00458063301198
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0659998679329874e-06,
"count": 1,
"self": 1.0659998679329874e-06
},
"TrainerController._save_models": {
"total": 0.09213826199993491,
"count": 1,
"self": 0.0015783630001351412,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09055989899979977,
"count": 1,
"self": 0.09055989899979977
}
}
}
}
}
}
}