ppo-PyramidsRND / run_logs /timers.json
Lakshya2k's picture
First
2e1077c
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4785943925380707,
"min": 0.47159531712532043,
"max": 1.116101622581482,
"count": 31
},
"Pyramids.Policy.Entropy.sum": {
"value": 14350.173828125,
"min": 2103.439208984375,
"max": 33429.4765625,
"count": 31
},
"Pyramids.Step.mean": {
"value": 989954.0,
"min": 89878.0,
"max": 989954.0,
"count": 31
},
"Pyramids.Step.sum": {
"value": 989954.0,
"min": 89878.0,
"max": 989954.0,
"count": 31
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.4250779449939728,
"min": -0.10707823187112808,
"max": 0.4596061408519745,
"count": 31
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 114.77104187011719,
"min": -25.544355392456055,
"max": 125.47247314453125,
"count": 31
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.10168644785881042,
"min": -0.19839252531528473,
"max": 0.1588427722454071,
"count": 31
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 27.455341339111328,
"min": -52.970802307128906,
"max": 42.09333419799805,
"count": 31
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 31
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 31
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.069038539259523,
"min": 0.06600921479028848,
"max": 0.07283664380208522,
"count": 30
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9665395496333219,
"min": 0.652202222592913,
"max": 1.0629840530067063,
"count": 30
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.02027683650022464,
"min": 0.0005738195980875657,
"max": 0.02027683650022464,
"count": 30
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.28387571100314496,
"min": 0.007459654775138355,
"max": 0.28387571100314496,
"count": 30
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.4790760784357145e-06,
"min": 7.4790760784357145e-06,
"max": 0.0002678656107114667,
"count": 30
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001047070650981,
"min": 0.0001047070650981,
"max": 0.0030035605988131997,
"count": 30
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10249299285714288,
"min": 0.10249299285714288,
"max": 0.18928853333333334,
"count": 30
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4349019000000003,
"min": 1.4349019000000003,
"max": 2.4006878,
"count": 30
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025904998642857144,
"min": 0.00025904998642857144,
"max": 0.00892992448,
"count": 30
},
"Pyramids.Policy.Beta.sum": {
"value": 0.00362669981,
"min": 0.00362669981,
"max": 0.10013856131999999,
"count": 30
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.010669345036149025,
"min": 0.010669345036149025,
"max": 0.061842747032642365,
"count": 30
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.14937083423137665,
"min": 0.14937083423137665,
"max": 0.5565847158432007,
"count": 30
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 394.0405405405405,
"min": 394.0405405405405,
"max": 999.0,
"count": 30
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29159.0,
"min": 18366.0,
"max": 33509.0,
"count": 30
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.497821596828667,
"min": -0.9999290848931959,
"max": 1.549450681348082,
"count": 30
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 110.83879816532135,
"min": -30.99780163168907,
"max": 110.83879816532135,
"count": 30
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.497821596828667,
"min": -0.9999290848931959,
"max": 1.549450681348082,
"count": 30
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 110.83879816532135,
"min": -30.99780163168907,
"max": 110.83879816532135,
"count": 30
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.043452983139817464,
"min": 0.043452983139817464,
"max": 0.6680420862267846,
"count": 30
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.2155207523464924,
"min": 3.2155207523464924,
"max": 15.364967983216047,
"count": 30
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1677769274",
"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 --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": "1.19.3",
"end_time_seconds": "1677771715"
},
"total": 2440.8562752231956,
"count": 1,
"self": 0.4843339314684272,
"children": {
"run_training.setup": {
"total": 0.04219593806192279,
"count": 1,
"self": 0.04219593806192279
},
"TrainerController.start_learning": {
"total": 2440.329745353665,
"count": 1,
"self": 2.004777515307069,
"children": {
"TrainerController._reset_env": {
"total": 4.372910663951188,
"count": 1,
"self": 4.372910663951188
},
"TrainerController.advance": {
"total": 2433.825947108213,
"count": 57961,
"self": 1.890930352266878,
"children": {
"env_step": {
"total": 1483.2487869774923,
"count": 57961,
"self": 1336.1901531065814,
"children": {
"SubprocessEnvManager._take_step": {
"total": 145.71801492664963,
"count": 57961,
"self": 5.478747155983001,
"children": {
"TorchPolicy.evaluate": {
"total": 140.23926777066663,
"count": 57016,
"self": 48.64909548172727,
"children": {
"TorchPolicy.sample_actions": {
"total": 91.59017228893936,
"count": 57016,
"self": 91.59017228893936
}
}
}
}
},
"workers": {
"total": 1.340618944261223,
"count": 57961,
"self": 0.0,
"children": {
"worker_root": {
"total": 2436.0561608159915,
"count": 57961,
"is_parallel": true,
"self": 1236.2111965408549,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021593128331005573,
"count": 1,
"is_parallel": true,
"self": 0.0005121328867971897,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016471799463033676,
"count": 8,
"is_parallel": true,
"self": 0.0016471799463033676
}
}
},
"UnityEnvironment.step": {
"total": 0.05017649196088314,
"count": 1,
"is_parallel": true,
"self": 0.0004150751046836376,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00036114174872636795,
"count": 1,
"is_parallel": true,
"self": 0.00036114174872636795
},
"communicator.exchange": {
"total": 0.04770693788304925,
"count": 1,
"is_parallel": true,
"self": 0.04770693788304925
},
"steps_from_proto": {
"total": 0.0016933372244238853,
"count": 1,
"is_parallel": true,
"self": 0.0003586597740650177,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013346774503588676,
"count": 8,
"is_parallel": true,
"self": 0.0013346774503588676
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1199.8449642751366,
"count": 57960,
"is_parallel": true,
"self": 29.221174432896078,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 20.987894147168845,
"count": 57960,
"is_parallel": true,
"self": 20.987894147168845
},
"communicator.exchange": {
"total": 1034.4738610158674,
"count": 57960,
"is_parallel": true,
"self": 1034.4738610158674
},
"steps_from_proto": {
"total": 115.16203467920423,
"count": 57960,
"is_parallel": true,
"self": 21.261384571436793,
"children": {
"_process_rank_one_or_two_observation": {
"total": 93.90065010776743,
"count": 463680,
"is_parallel": true,
"self": 93.90065010776743
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 948.6862297784537,
"count": 57961,
"self": 4.0497002536430955,
"children": {
"process_trajectory": {
"total": 189.01093625603244,
"count": 57961,
"self": 188.51984816091135,
"children": {
"RLTrainer._checkpoint": {
"total": 0.49108809512108564,
"count": 2,
"self": 0.49108809512108564
}
}
},
"_update_policy": {
"total": 755.6255932687782,
"count": 411,
"self": 286.9416079763323,
"children": {
"TorchPPOOptimizer.update": {
"total": 468.68398529244587,
"count": 20748,
"self": 468.68398529244587
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.5660189092159271e-06,
"count": 1,
"self": 1.5660189092159271e-06
},
"TrainerController._save_models": {
"total": 0.12610850017517805,
"count": 1,
"self": 0.009289463516324759,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11681903665885329,
"count": 1,
"self": 0.11681903665885329
}
}
}
}
}
}
}