ppo-pyramids / run_logs /timers.json
mcaoun's picture
first
a3cf9e8
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4117347300052643,
"min": 0.40967363119125366,
"max": 1.4416874647140503,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 12312.515625,
"min": 12292.5078125,
"max": 43735.03125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989995.0,
"min": 29952.0,
"max": 989995.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989995.0,
"min": 29952.0,
"max": 989995.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.4429982006549835,
"min": -0.11300461739301682,
"max": 0.4429982006549835,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 120.93850708007812,
"min": -27.121109008789062,
"max": 120.93850708007812,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.009348861873149872,
"min": -0.0007346700876951218,
"max": 0.3121086657047272,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 2.552239179611206,
"min": -0.1873408704996109,
"max": 73.96975708007812,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.068063630750018,
"min": 0.06512978557429251,
"max": 0.07327509979448896,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9528908305002521,
"min": 0.4839507439673875,
"max": 1.0532503229361623,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01598655992864285,
"min": 0.000131386373719577,
"max": 0.01598655992864285,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2238118390009999,
"min": 0.0017080228583545012,
"max": 0.2238118390009999,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.318490417678567e-06,
"min": 7.318490417678567e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010245886584749994,
"min": 0.00010245886584749994,
"max": 0.0035077613307462996,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10243946428571427,
"min": 0.10243946428571427,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4341524999999997,
"min": 1.3886848,
"max": 2.5692537000000004,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002537024821428571,
"min": 0.0002537024821428571,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0035518347499999994,
"min": 0.0035518347499999994,
"max": 0.11694844463,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.009764452464878559,
"min": 0.009548386558890343,
"max": 0.38033929467201233,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.13670232892036438,
"min": 0.1336774080991745,
"max": 2.662374973297119,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 414.0,
"min": 414.0,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31050.0,
"min": 15984.0,
"max": 32637.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4526346375544865,
"min": -1.0000000521540642,
"max": 1.4988953637389035,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 108.9475978165865,
"min": -30.998601615428925,
"max": 108.9475978165865,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4526346375544865,
"min": -1.0000000521540642,
"max": 1.4988953637389035,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 108.9475978165865,
"min": -30.998601615428925,
"max": 108.9475978165865,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04224840864480939,
"min": 0.04224840864480939,
"max": 8.080033687874675,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.168630648360704,
"min": 3.0305288865056355,
"max": 129.2805390059948,
"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": "1678321573",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"command_line_arguments": "/home/michel/Desktop/env/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-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": "1.19.0",
"end_time_seconds": "1678322607"
},
"total": 1033.976035886,
"count": 1,
"self": 0.21928045000004204,
"children": {
"run_training.setup": {
"total": 0.0512899870000183,
"count": 1,
"self": 0.0512899870000183
},
"TrainerController.start_learning": {
"total": 1033.705465449,
"count": 1,
"self": 0.9291809480232587,
"children": {
"TrainerController._reset_env": {
"total": 2.142328912000039,
"count": 1,
"self": 2.142328912000039
},
"TrainerController.advance": {
"total": 1030.578141104977,
"count": 63596,
"self": 0.9213676960846442,
"children": {
"env_step": {
"total": 572.6218864469404,
"count": 63596,
"self": 500.35717842394706,
"children": {
"SubprocessEnvManager._take_step": {
"total": 71.66216238300399,
"count": 63596,
"self": 2.639973263061165,
"children": {
"TorchPolicy.evaluate": {
"total": 69.02218911994282,
"count": 62568,
"self": 24.11859495302815,
"children": {
"TorchPolicy.sample_actions": {
"total": 44.90359416691467,
"count": 62568,
"self": 44.90359416691467
}
}
}
}
},
"workers": {
"total": 0.6025456399893301,
"count": 63596,
"self": 0.0,
"children": {
"worker_root": {
"total": 1032.3054974279935,
"count": 63596,
"is_parallel": true,
"self": 591.6611436340193,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011750630001188256,
"count": 1,
"is_parallel": true,
"self": 0.0002814680001392844,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008935949999795412,
"count": 8,
"is_parallel": true,
"self": 0.0008935949999795412
}
}
},
"UnityEnvironment.step": {
"total": 0.02086268600010044,
"count": 1,
"is_parallel": true,
"self": 0.00035697799989975465,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003421290000460431,
"count": 1,
"is_parallel": true,
"self": 0.0003421290000460431
},
"communicator.exchange": {
"total": 0.018538490000082675,
"count": 1,
"is_parallel": true,
"self": 0.018538490000082675
},
"steps_from_proto": {
"total": 0.0016250890000719664,
"count": 1,
"is_parallel": true,
"self": 0.00026331399999435234,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001361775000077614,
"count": 8,
"is_parallel": true,
"self": 0.001361775000077614
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 440.64435379397423,
"count": 63595,
"is_parallel": true,
"self": 12.7546080440693,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 9.33707120498002,
"count": 63595,
"is_parallel": true,
"self": 9.33707120498002
},
"communicator.exchange": {
"total": 365.23446450993197,
"count": 63595,
"is_parallel": true,
"self": 365.23446450993197
},
"steps_from_proto": {
"total": 53.318210034992944,
"count": 63595,
"is_parallel": true,
"self": 9.363350655966315,
"children": {
"_process_rank_one_or_two_observation": {
"total": 43.95485937902663,
"count": 508760,
"is_parallel": true,
"self": 43.95485937902663
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 457.034886961952,
"count": 63596,
"self": 1.6884432689805635,
"children": {
"process_trajectory": {
"total": 94.15615678996755,
"count": 63596,
"self": 94.04345088496757,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11270590499998434,
"count": 2,
"self": 0.11270590499998434
}
}
},
"_update_policy": {
"total": 361.1902869030039,
"count": 452,
"self": 143.36543787304208,
"children": {
"TorchPPOOptimizer.update": {
"total": 217.8248490299618,
"count": 22788,
"self": 217.8248490299618
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.089997779985424e-07,
"count": 1,
"self": 7.089997779985424e-07
},
"TrainerController._save_models": {
"total": 0.05581377499993323,
"count": 1,
"self": 0.0006925789998604159,
"children": {
"RLTrainer._checkpoint": {
"total": 0.055121196000072814,
"count": 1,
"self": 0.055121196000072814
}
}
}
}
}
}
}