ppo-PyramidsRnd / run_logs /timers.json
Iamvincent's picture
one more Push
e3b17bb
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.23605553805828094,
"min": 0.22889655828475952,
"max": 0.2508504390716553,
"count": 20
},
"Pyramids.Policy.Entropy.sum": {
"value": 11866.984375,
"min": 11540.048828125,
"max": 12598.7119140625,
"count": 20
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 221.39285714285714,
"min": 214.3047210300429,
"max": 246.60487804878048,
"count": 20
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 49592.0,
"min": 47598.0,
"max": 51116.0,
"count": 20
},
"Pyramids.Step.mean": {
"value": 3999893.0,
"min": 3049970.0,
"max": 3999893.0,
"count": 20
},
"Pyramids.Step.sum": {
"value": 3999893.0,
"min": 3049970.0,
"max": 3999893.0,
"count": 20
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7989347577095032,
"min": 0.7467613220214844,
"max": 0.8410912752151489,
"count": 20
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 402.6631164550781,
"min": 365.1662902832031,
"max": 425.52984619140625,
"count": 20
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.018077602609992027,
"min": -0.018844055011868477,
"max": 0.03128303959965706,
"count": 20
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 9.111111640930176,
"min": -9.459715843200684,
"max": 15.391256332397461,
"count": 20
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.778559988339742,
"min": 1.7143580370559925,
"max": 1.7826771168831752,
"count": 20
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 400.17599737644196,
"min": 345.80099721997976,
"max": 415.8387972712517,
"count": 20
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.778559988339742,
"min": 1.7143580370559925,
"max": 1.7826771168831752,
"count": 20
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 400.17599737644196,
"min": 345.80099721997976,
"max": 415.8387972712517,
"count": 20
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.016336062841033304,
"min": 0.015823443759496188,
"max": 0.018775434206428715,
"count": 20
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.6756141392324935,
"min": 3.577199833627674,
"max": 4.036718354382174,
"count": 20
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.05028897351095159,
"min": 0.044386929340840306,
"max": 0.05093259401619434,
"count": 20
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.5028897351095158,
"min": 0.43735607840905066,
"max": 0.5093259401619434,
"count": 20
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015452114992627974,
"min": 0.013820333611220124,
"max": 0.01625803027653315,
"count": 20
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.15452114992627974,
"min": 0.1338562767070375,
"max": 0.1625803027653315,
"count": 20
},
"Pyramids.Policy.LearningRate.mean": {
"value": 6.303993696999993e-07,
"min": 6.303993696999993e-07,
"max": 2.4363486747700004e-05,
"count": 20
},
"Pyramids.Policy.LearningRate.sum": {
"value": 6.303993696999993e-06,
"min": 6.303993696999993e-06,
"max": 0.00023160281839795002,
"count": 20
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10063029999999999,
"min": 0.10063029999999999,
"max": 0.12436341111111113,
"count": 20
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.006303,
"min": 0.95066775,
"max": 1.2316020500000002,
"count": 20
},
"Pyramids.Policy.Beta.mean": {
"value": 7.296696999999992e-05,
"min": 7.296696999999992e-05,
"max": 0.00244390477,
"count": 20
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0007296696999999992,
"min": 0.0007296696999999992,
"max": 0.023237044794999998,
"count": 20
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.007169483695179224,
"min": 0.007084073964506388,
"max": 0.007771213073283434,
"count": 20
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.07169483602046967,
"min": 0.0658775344491005,
"max": 0.07668492197990417,
"count": 20
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1673878002",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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 --resume",
"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": "1673880441"
},
"total": 2439.451575113999,
"count": 1,
"self": 0.47513688399703824,
"children": {
"run_training.setup": {
"total": 0.10879467500126339,
"count": 1,
"self": 0.10879467500126339
},
"TrainerController.start_learning": {
"total": 2438.8676435550005,
"count": 1,
"self": 1.3225082348362776,
"children": {
"TrainerController._reset_env": {
"total": 6.430154832998596,
"count": 1,
"self": 6.430154832998596
},
"TrainerController.advance": {
"total": 2431.016472615165,
"count": 66028,
"self": 1.3931733894696663,
"children": {
"env_step": {
"total": 1845.8382917009858,
"count": 66028,
"self": 1736.3696118349399,
"children": {
"SubprocessEnvManager._take_step": {
"total": 108.60705801098266,
"count": 66028,
"self": 4.634580640986314,
"children": {
"TorchPolicy.evaluate": {
"total": 103.97247736999634,
"count": 62564,
"self": 34.94328856557695,
"children": {
"TorchPolicy.sample_actions": {
"total": 69.02918880441939,
"count": 62564,
"self": 69.02918880441939
}
}
}
}
},
"workers": {
"total": 0.8616218550632766,
"count": 66028,
"self": 0.0,
"children": {
"worker_root": {
"total": 2433.8066512827736,
"count": 66028,
"is_parallel": true,
"self": 804.9885571905961,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017686219998722663,
"count": 1,
"is_parallel": true,
"self": 0.0006370989976858255,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011315230021864409,
"count": 8,
"is_parallel": true,
"self": 0.0011315230021864409
}
}
},
"UnityEnvironment.step": {
"total": 0.04684086100132845,
"count": 1,
"is_parallel": true,
"self": 0.000536315999852377,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004777410013048211,
"count": 1,
"is_parallel": true,
"self": 0.0004777410013048211
},
"communicator.exchange": {
"total": 0.0439741000009235,
"count": 1,
"is_parallel": true,
"self": 0.0439741000009235
},
"steps_from_proto": {
"total": 0.0018527039992477512,
"count": 1,
"is_parallel": true,
"self": 0.000489846994241816,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013628570050059352,
"count": 8,
"is_parallel": true,
"self": 0.0013628570050059352
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1628.8180940921775,
"count": 66027,
"is_parallel": true,
"self": 28.99446016211914,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.90630173813588,
"count": 66027,
"is_parallel": true,
"self": 24.90630173813588
},
"communicator.exchange": {
"total": 1462.9814383609246,
"count": 66027,
"is_parallel": true,
"self": 1462.9814383609246
},
"steps_from_proto": {
"total": 111.93589383099788,
"count": 66027,
"is_parallel": true,
"self": 24.77005182310313,
"children": {
"_process_rank_one_or_two_observation": {
"total": 87.16584200789475,
"count": 528216,
"is_parallel": true,
"self": 87.16584200789475
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 583.7850075247097,
"count": 66028,
"self": 2.5765204733215796,
"children": {
"process_trajectory": {
"total": 162.21185930240972,
"count": 66028,
"self": 161.99728351340855,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2145757890011737,
"count": 2,
"self": 0.2145757890011737
}
}
},
"_update_policy": {
"total": 418.9966277489784,
"count": 197,
"self": 200.26165303204834,
"children": {
"TorchPPOOptimizer.update": {
"total": 218.73497471693008,
"count": 11280,
"self": 218.73497471693008
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.140003385255113e-07,
"count": 1,
"self": 9.140003385255113e-07
},
"TrainerController._save_models": {
"total": 0.09850695800014364,
"count": 1,
"self": 0.0018503079991205595,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09665665000102308,
"count": 1,
"self": 0.09665665000102308
}
}
}
}
}
}
}