ppo-Pyramids / run_logs /timers.json
luhx's picture
First Push
890bf9a
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.43832945823669434,
"min": 0.43832945823669434,
"max": 1.4628087282180786,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 13128.84375,
"min": 13128.84375,
"max": 44375.765625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989988.0,
"min": 29952.0,
"max": 989988.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989988.0,
"min": 29952.0,
"max": 989988.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6132928729057312,
"min": -0.10015010088682175,
"max": 0.6266399025917053,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 175.40176391601562,
"min": -24.236324310302734,
"max": 175.45916748046875,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.023999838158488274,
"min": -0.003972286824136972,
"max": 0.34887760877609253,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 6.863953590393066,
"min": -1.1201848983764648,
"max": 83.73062896728516,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06798766111329438,
"min": 0.06404964961291712,
"max": 0.07348389571139012,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9518272555861212,
"min": 0.48643107202366376,
"max": 1.0834310679581225,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014419864009322625,
"min": 0.0003430252197074589,
"max": 0.01605907480558674,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.20187809613051674,
"min": 0.003773277416782048,
"max": 0.2360785340179242,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.579211759342858e-06,
"min": 7.579211759342858e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010610896463080001,
"min": 0.00010610896463080001,
"max": 0.0032588504137165994,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10252637142857143,
"min": 0.10252637142857143,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4353692,
"min": 1.3691136000000002,
"max": 2.4014311000000004,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002623845057142857,
"min": 0.0002623845057142857,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036733830800000002,
"min": 0.0036733830800000002,
"max": 0.10864971166,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.006914176046848297,
"min": 0.006914176046848297,
"max": 0.48632293939590454,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.09679846465587616,
"min": 0.09679846465587616,
"max": 3.4042606353759766,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 326.4193548387097,
"min": 308.0,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30357.0,
"min": 15984.0,
"max": 32845.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.65206879906116,
"min": -1.0000000521540642,
"max": 1.65206879906116,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 153.64239831268787,
"min": -32.000001668930054,
"max": 163.1983978226781,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.65206879906116,
"min": -1.0000000521540642,
"max": 1.65206879906116,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 153.64239831268787,
"min": -32.000001668930054,
"max": 163.1983978226781,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.02372391973493836,
"min": 0.023198974832303064,
"max": 10.726053665857762,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.2063245353492675,
"min": 2.169671970885247,
"max": 171.6168586537242,
"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": "1689137925",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1689140178"
},
"total": 2252.492898943,
"count": 1,
"self": 0.7932429680004134,
"children": {
"run_training.setup": {
"total": 0.05918699399990146,
"count": 1,
"self": 0.05918699399990146
},
"TrainerController.start_learning": {
"total": 2251.6404689809997,
"count": 1,
"self": 1.2916739240145034,
"children": {
"TrainerController._reset_env": {
"total": 5.361450402999935,
"count": 1,
"self": 5.361450402999935
},
"TrainerController.advance": {
"total": 2244.8316718599845,
"count": 63948,
"self": 1.3637981789370315,
"children": {
"env_step": {
"total": 1597.0205703580739,
"count": 63948,
"self": 1490.3011556649735,
"children": {
"SubprocessEnvManager._take_step": {
"total": 105.91953611002623,
"count": 63948,
"self": 4.515852487098982,
"children": {
"TorchPolicy.evaluate": {
"total": 101.40368362292725,
"count": 62555,
"self": 101.40368362292725
}
}
},
"workers": {
"total": 0.7998785830741326,
"count": 63948,
"self": 0.0,
"children": {
"worker_root": {
"total": 2246.3993664579534,
"count": 63948,
"is_parallel": true,
"self": 867.4671020769476,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0025366820000272128,
"count": 1,
"is_parallel": true,
"self": 0.0006541980003476056,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018824839996796072,
"count": 8,
"is_parallel": true,
"self": 0.0018824839996796072
}
}
},
"UnityEnvironment.step": {
"total": 0.051748916999940775,
"count": 1,
"is_parallel": true,
"self": 0.0005963870000869065,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047919499979798275,
"count": 1,
"is_parallel": true,
"self": 0.00047919499979798275
},
"communicator.exchange": {
"total": 0.04874918699988484,
"count": 1,
"is_parallel": true,
"self": 0.04874918699988484
},
"steps_from_proto": {
"total": 0.0019241480001710443,
"count": 1,
"is_parallel": true,
"self": 0.0003700980003031873,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001554049999867857,
"count": 8,
"is_parallel": true,
"self": 0.001554049999867857
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1378.9322643810058,
"count": 63947,
"is_parallel": true,
"self": 33.12619355191532,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.150209046027385,
"count": 63947,
"is_parallel": true,
"self": 22.150209046027385
},
"communicator.exchange": {
"total": 1221.78748679103,
"count": 63947,
"is_parallel": true,
"self": 1221.78748679103
},
"steps_from_proto": {
"total": 101.86837499203307,
"count": 63947,
"is_parallel": true,
"self": 19.52485533988829,
"children": {
"_process_rank_one_or_two_observation": {
"total": 82.34351965214478,
"count": 511576,
"is_parallel": true,
"self": 82.34351965214478
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 646.4473033229735,
"count": 63948,
"self": 2.5332588870235213,
"children": {
"process_trajectory": {
"total": 109.3374546679529,
"count": 63948,
"self": 109.07950605095266,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2579486170002383,
"count": 2,
"self": 0.2579486170002383
}
}
},
"_update_policy": {
"total": 534.5765897679971,
"count": 442,
"self": 344.67942141896333,
"children": {
"TorchPPOOptimizer.update": {
"total": 189.8971683490338,
"count": 22854,
"self": 189.8971683490338
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3310000213095918e-06,
"count": 1,
"self": 1.3310000213095918e-06
},
"TrainerController._save_models": {
"total": 0.15567146300054446,
"count": 1,
"self": 0.0019372189999558032,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15373424400058866,
"count": 1,
"self": 0.15373424400058866
}
}
}
}
}
}
}