ppo-Pyramids / run_logs /timers.json
WimStraetemans's picture
First Pyramids model
ca972ba
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.27275049686431885,
"min": 0.27275049686431885,
"max": 1.5233992338180542,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 8230.5185546875,
"min": 8230.5185546875,
"max": 46213.83984375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989957.0,
"min": 29952.0,
"max": 989957.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989957.0,
"min": 29952.0,
"max": 989957.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5973702073097229,
"min": -0.08120010793209076,
"max": 0.66926509141922,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 167.86102294921875,
"min": -19.569225311279297,
"max": 188.06349182128906,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.015019497834146023,
"min": 0.005141410976648331,
"max": 0.38139477372169495,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 4.2204790115356445,
"min": 1.4293122291564941,
"max": 91.53474426269531,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.04674690813262714,
"min": 0.046383668735922715,
"max": 0.05598472705874662,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.37397526506101714,
"min": 0.22393890823498647,
"max": 0.40185193612123843,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.013970617746963399,
"min": 0.0001130391297209082,
"max": 0.016499955373417054,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.11176494197570719,
"min": 0.000565195648604541,
"max": 0.12566556133097037,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.829999974225004e-06,
"min": 7.829999974225004e-06,
"max": 0.00030529792151680004,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 6.263999979380003e-05,
"min": 6.263999979380003e-05,
"max": 0.0019212611402384,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.102525775,
"min": 0.102525775,
"max": 0.19848319999999997,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 0.8202062,
"min": 0.7395068,
"max": 1.4197616000000002,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026232492250000014,
"min": 0.00026232492250000014,
"max": 0.009848471680000002,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.002098599380000001,
"min": 0.002098599380000001,
"max": 0.061994183839999994,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.00826144777238369,
"min": 0.00826144777238369,
"max": 0.5609574317932129,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.06609158217906952,
"min": 0.06352592259645462,
"max": 2.2438297271728516,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 338.1573033707865,
"min": 289.421568627451,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30096.0,
"min": 15984.0,
"max": 31968.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5269460516531816,
"min": -1.0000000521540642,
"max": 1.671347043166558,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 135.89819859713316,
"min": -32.000001668930054,
"max": 170.4773984029889,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5269460516531816,
"min": -1.0000000521540642,
"max": 1.671347043166558,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 135.89819859713316,
"min": -32.000001668930054,
"max": 170.4773984029889,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.02969808062620911,
"min": 0.027656672863254333,
"max": 11.479000383988023,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.6431291757326107,
"min": 2.6431291757326107,
"max": 183.66400614380836,
"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": "1674211902",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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": "0.29.0.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": "1674214225"
},
"total": 2323.459274552,
"count": 1,
"self": 0.4912877930000832,
"children": {
"run_training.setup": {
"total": 0.0973076420000325,
"count": 1,
"self": 0.0973076420000325
},
"TrainerController.start_learning": {
"total": 2322.870679117,
"count": 1,
"self": 1.5131976930088058,
"children": {
"TrainerController._reset_env": {
"total": 6.0401756369999475,
"count": 1,
"self": 6.0401756369999475
},
"TrainerController.advance": {
"total": 2315.197495050991,
"count": 64060,
"self": 1.522172445936576,
"children": {
"env_step": {
"total": 1468.1517604910719,
"count": 64060,
"self": 1346.1891477358806,
"children": {
"SubprocessEnvManager._take_step": {
"total": 121.0175561861347,
"count": 64060,
"self": 4.83624378015088,
"children": {
"TorchPolicy.evaluate": {
"total": 116.18131240598382,
"count": 62571,
"self": 37.27013758698786,
"children": {
"TorchPolicy.sample_actions": {
"total": 78.91117481899596,
"count": 62571,
"self": 78.91117481899596
}
}
}
}
},
"workers": {
"total": 0.9450565690565327,
"count": 64060,
"self": 0.0,
"children": {
"worker_root": {
"total": 2317.6208418410038,
"count": 64060,
"is_parallel": true,
"self": 1082.5254259690175,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001797456000076636,
"count": 1,
"is_parallel": true,
"self": 0.0006494180008758121,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011480379992008238,
"count": 8,
"is_parallel": true,
"self": 0.0011480379992008238
}
}
},
"UnityEnvironment.step": {
"total": 0.04834823099986352,
"count": 1,
"is_parallel": true,
"self": 0.0005332480000106443,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004544109999642387,
"count": 1,
"is_parallel": true,
"self": 0.0004544109999642387
},
"communicator.exchange": {
"total": 0.04566610199981369,
"count": 1,
"is_parallel": true,
"self": 0.04566610199981369
},
"steps_from_proto": {
"total": 0.0016944700000749435,
"count": 1,
"is_parallel": true,
"self": 0.0004545280000911589,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012399419999837846,
"count": 8,
"is_parallel": true,
"self": 0.0012399419999837846
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1235.0954158719862,
"count": 64059,
"is_parallel": true,
"self": 29.457366580865255,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.451536234017794,
"count": 64059,
"is_parallel": true,
"self": 23.451536234017794
},
"communicator.exchange": {
"total": 1075.3685513970315,
"count": 64059,
"is_parallel": true,
"self": 1075.3685513970315
},
"steps_from_proto": {
"total": 106.81796166007166,
"count": 64059,
"is_parallel": true,
"self": 24.29914819807641,
"children": {
"_process_rank_one_or_two_observation": {
"total": 82.51881346199525,
"count": 512472,
"is_parallel": true,
"self": 82.51881346199525
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 845.5235621139827,
"count": 64060,
"self": 2.878031457000816,
"children": {
"process_trajectory": {
"total": 150.72795471597829,
"count": 64060,
"self": 150.3704709379781,
"children": {
"RLTrainer._checkpoint": {
"total": 0.35748377800018716,
"count": 2,
"self": 0.35748377800018716
}
}
},
"_update_policy": {
"total": 691.9175759410036,
"count": 231,
"self": 314.5846155929901,
"children": {
"TorchPPOOptimizer.update": {
"total": 377.33296034801356,
"count": 19180,
"self": 377.33296034801356
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.049999789567664e-07,
"count": 1,
"self": 9.049999789567664e-07
},
"TrainerController._save_models": {
"total": 0.1198098309996567,
"count": 1,
"self": 0.002358720000302128,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11745111099935457,
"count": 1,
"self": 0.11745111099935457
}
}
}
}
}
}
}