testpyramidsrnd / run_logs /timers.json
SimingSiming's picture
First Pyramids
d953af4
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.14780670404434204,
"min": 0.1300026774406433,
"max": 1.4495569467544556,
"count": 100
},
"Pyramids.Policy.Entropy.sum": {
"value": 4464.94482421875,
"min": 3966.641845703125,
"max": 43973.7578125,
"count": 100
},
"Pyramids.Step.mean": {
"value": 2999952.0,
"min": 29952.0,
"max": 2999952.0,
"count": 100
},
"Pyramids.Step.sum": {
"value": 2999952.0,
"min": 29952.0,
"max": 2999952.0,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.821334719657898,
"min": -0.20435258746147156,
"max": 0.9054329991340637,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 243.93641662597656,
"min": -48.43156433105469,
"max": 274.34619140625,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.004226795397698879,
"min": -0.10785798728466034,
"max": 0.3109534680843353,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 1.2553582191467285,
"min": -31.27881622314453,
"max": 73.69596862792969,
"count": 100
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06664926032695519,
"min": 0.06253593953234875,
"max": 0.0732787603650327,
"count": 100
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9997389049043277,
"min": 0.5129513225552289,
"max": 1.0785635088686831,
"count": 100
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01626021498513676,
"min": 0.00041446184006542594,
"max": 0.016462732440794794,
"count": 100
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.24390322477705137,
"min": 0.004973542080785111,
"max": 0.24390322477705137,
"count": 100
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.4953595015800004e-06,
"min": 1.4953595015800004e-06,
"max": 0.00029838354339596195,
"count": 100
},
"Pyramids.Policy.LearningRate.sum": {
"value": 2.2430392523700006e-05,
"min": 2.2430392523700006e-05,
"max": 0.0039683919772027,
"count": 100
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10049842,
"min": 0.10049842,
"max": 0.19946118095238097,
"count": 100
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5074763,
"min": 1.3962282666666668,
"max": 2.7825003000000006,
"count": 100
},
"Pyramids.Policy.Beta.mean": {
"value": 5.9792158000000025e-05,
"min": 5.9792158000000025e-05,
"max": 0.009946171977142856,
"count": 100
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0008968823700000004,
"min": 0.0008968823700000004,
"max": 0.13228745027,
"count": 100
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.006872964091598988,
"min": 0.0065099922940135,
"max": 0.4194892346858978,
"count": 100
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.10309445858001709,
"min": 0.09113989025354385,
"max": 2.936424732208252,
"count": 100
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 224.7153846153846,
"min": 207.14583333333334,
"max": 999.0,
"count": 100
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29213.0,
"min": 15984.0,
"max": 33351.0,
"count": 100
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.728604641764663,
"min": -1.0000000521540642,
"max": 1.7874428391456605,
"count": 100
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 222.98999878764153,
"min": -30.253401719033718,
"max": 259.41359812021255,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.728604641764663,
"min": -1.0000000521540642,
"max": 1.7874428391456605,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 222.98999878764153,
"min": -30.253401719033718,
"max": 259.41359812021255,
"count": 100
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.015897272022706348,
"min": 0.015238432568551523,
"max": 7.7207092912867665,
"count": 100
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.050748090929119,
"min": 1.928862558867877,
"max": 123.53134866058826,
"count": 100
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1658204471",
"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": "1658211091"
},
"total": 6619.339343733,
"count": 1,
"self": 0.4455976740000551,
"children": {
"run_training.setup": {
"total": 0.0417078609998498,
"count": 1,
"self": 0.0417078609998498
},
"TrainerController.start_learning": {
"total": 6618.852038198,
"count": 1,
"self": 4.646784417229355,
"children": {
"TrainerController._reset_env": {
"total": 9.543732030999763,
"count": 1,
"self": 9.543732030999763
},
"TrainerController.advance": {
"total": 6604.567609156771,
"count": 195569,
"self": 4.677121330864793,
"children": {
"env_step": {
"total": 4497.229145775065,
"count": 195569,
"self": 4182.462279413201,
"children": {
"SubprocessEnvManager._take_step": {
"total": 312.33302780383065,
"count": 195569,
"self": 14.033170330889789,
"children": {
"TorchPolicy.evaluate": {
"total": 298.29985747294086,
"count": 187564,
"self": 104.41294495768534,
"children": {
"TorchPolicy.sample_actions": {
"total": 193.88691251525552,
"count": 187564,
"self": 193.88691251525552
}
}
}
}
},
"workers": {
"total": 2.43383855803404,
"count": 195569,
"self": 0.0,
"children": {
"worker_root": {
"total": 6606.560772887889,
"count": 195569,
"is_parallel": true,
"self": 2736.6898178318575,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005123976000049879,
"count": 1,
"is_parallel": true,
"self": 0.0039225249993251055,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012014510007247736,
"count": 8,
"is_parallel": true,
"self": 0.0012014510007247736
}
}
},
"UnityEnvironment.step": {
"total": 0.04863662599973395,
"count": 1,
"is_parallel": true,
"self": 0.0005545299995901587,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00044044900005246745,
"count": 1,
"is_parallel": true,
"self": 0.00044044900005246745
},
"communicator.exchange": {
"total": 0.04568512200012265,
"count": 1,
"is_parallel": true,
"self": 0.04568512200012265
},
"steps_from_proto": {
"total": 0.0019565249999686785,
"count": 1,
"is_parallel": true,
"self": 0.0005145639997863327,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014419610001823457,
"count": 8,
"is_parallel": true,
"self": 0.0014419610001823457
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 3869.870955056031,
"count": 195568,
"is_parallel": true,
"self": 83.7177419824643,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 68.53912556888645,
"count": 195568,
"is_parallel": true,
"self": 68.53912556888645
},
"communicator.exchange": {
"total": 3439.12510016423,
"count": 195568,
"is_parallel": true,
"self": 3439.12510016423
},
"steps_from_proto": {
"total": 278.4889873404504,
"count": 195568,
"is_parallel": true,
"self": 70.12867599588662,
"children": {
"_process_rank_one_or_two_observation": {
"total": 208.3603113445638,
"count": 1564544,
"is_parallel": true,
"self": 208.3603113445638
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 2102.661342050841,
"count": 195569,
"self": 8.810323025499656,
"children": {
"process_trajectory": {
"total": 491.46664152335325,
"count": 195569,
"self": 490.8849757753528,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5816657480004324,
"count": 6,
"self": 0.5816657480004324
}
}
},
"_update_policy": {
"total": 1602.3843775019882,
"count": 1401,
"self": 643.413863815907,
"children": {
"TorchPPOOptimizer.update": {
"total": 958.9705136860812,
"count": 68376,
"self": 958.9705136860812
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.859995770966634e-07,
"count": 1,
"self": 9.859995770966634e-07
},
"TrainerController._save_models": {
"total": 0.09391160700033652,
"count": 1,
"self": 0.0015927120002743322,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09231889500006218,
"count": 1,
"self": 0.09231889500006218
}
}
}
}
}
}
}