testpyramidsrnd / run_logs /timers.json
curt-tigges's picture
First Pyramids
42d98d2
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.44389885663986206,
"min": 0.4429570138454437,
"max": 1.466874361038208,
"count": 50
},
"Pyramids.Policy.Entropy.sum": {
"value": 13295.658203125,
"min": 13295.658203125,
"max": 44499.1015625,
"count": 50
},
"Pyramids.Step.mean": {
"value": 1499935.0,
"min": 29909.0,
"max": 1499935.0,
"count": 50
},
"Pyramids.Step.sum": {
"value": 1499935.0,
"min": 29909.0,
"max": 1499935.0,
"count": 50
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7310246229171753,
"min": -0.10883622616529465,
"max": 0.780449628829956,
"count": 50
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 213.4591827392578,
"min": -26.229530334472656,
"max": 231.79354858398438,
"count": 50
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.003801656188443303,
"min": -0.02046757936477661,
"max": 0.4144503176212311,
"count": 50
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -1.1100835800170898,
"min": -5.32157039642334,
"max": 98.22472381591797,
"count": 50
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07093477098581692,
"min": 0.06488527835329476,
"max": 0.07267788270643603,
"count": 50
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0640215647872537,
"min": 0.4744797794154347,
"max": 1.0901682405965405,
"count": 50
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01536192101031904,
"min": 9.669598815068191e-05,
"max": 0.017008988528340565,
"count": 50
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.23042881515478558,
"min": 0.0012570478459588649,
"max": 0.23812583939676793,
"count": 50
},
"Pyramids.Policy.LearningRate.mean": {
"value": 3.001725666124444e-06,
"min": 3.001725666124444e-06,
"max": 0.0002968231724875142,
"count": 50
},
"Pyramids.Policy.LearningRate.sum": {
"value": 4.502588499186666e-05,
"min": 4.502588499186666e-05,
"max": 0.0037061768646077333,
"count": 50
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10100054222222224,
"min": 0.10100054222222224,
"max": 0.19894105714285718,
"count": 50
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5150081333333336,
"min": 1.3925874000000003,
"max": 2.6183329333333334,
"count": 50
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00010995416799999998,
"min": 0.00010995416799999998,
"max": 0.00989421160857143,
"count": 50
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0016493125199999997,
"min": 0.0016493125199999997,
"max": 0.12354568744000002,
"count": 50
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.006000143475830555,
"min": 0.006000143475830555,
"max": 0.43413084745407104,
"count": 50
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.0900021493434906,
"min": 0.0850573256611824,
"max": 3.0389158725738525,
"count": 50
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 260.6475409836066,
"min": 242.83870967741936,
"max": 999.0,
"count": 50
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31799.0,
"min": 16708.0,
"max": 33023.0,
"count": 50
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7232861631527179,
"min": -0.9999226326903989,
"max": 1.7571612806810486,
"count": 50
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 211.9641980677843,
"min": -30.997601613402367,
"max": 217.88799880445004,
"count": 50
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7232861631527179,
"min": -0.9999226326903989,
"max": 1.7571612806810486,
"count": 50
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 211.9641980677843,
"min": -30.997601613402367,
"max": 217.88799880445004,
"count": 50
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.01608496457191631,
"min": 0.015336832706276666,
"max": 8.486839855418486,
"count": 50
},
"Pyramids.Policy.RndReward.sum": {
"value": 1.978450642345706,
"min": 1.733607194837532,
"max": 144.27627754211426,
"count": 50
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1662399637",
"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": "1662402715"
},
"total": 3077.788285257,
"count": 1,
"self": 0.43036782200033485,
"children": {
"run_training.setup": {
"total": 0.04394579499989959,
"count": 1,
"self": 0.04394579499989959
},
"TrainerController.start_learning": {
"total": 3077.31397164,
"count": 1,
"self": 2.136831337013973,
"children": {
"TrainerController._reset_env": {
"total": 9.182996784000125,
"count": 1,
"self": 9.182996784000125
},
"TrainerController.advance": {
"total": 3065.9042919479857,
"count": 96310,
"self": 2.184833859130322,
"children": {
"env_step": {
"total": 2013.6734765389017,
"count": 96310,
"self": 1857.4008511689572,
"children": {
"SubprocessEnvManager._take_step": {
"total": 155.15193579401216,
"count": 96310,
"self": 6.822911933089699,
"children": {
"TorchPolicy.evaluate": {
"total": 148.32902386092246,
"count": 93810,
"self": 52.403997892915186,
"children": {
"TorchPolicy.sample_actions": {
"total": 95.92502596800728,
"count": 93810,
"self": 95.92502596800728
}
}
}
}
},
"workers": {
"total": 1.1206895759323743,
"count": 96310,
"self": 0.0,
"children": {
"worker_root": {
"total": 3071.4742740630336,
"count": 96310,
"is_parallel": true,
"self": 1366.19907004606,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008565696999994543,
"count": 1,
"is_parallel": true,
"self": 0.0034624649999841495,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.005103232000010394,
"count": 8,
"is_parallel": true,
"self": 0.005103232000010394
}
}
},
"UnityEnvironment.step": {
"total": 0.04740006500014715,
"count": 1,
"is_parallel": true,
"self": 0.0005839370003286604,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004570389999116742,
"count": 1,
"is_parallel": true,
"self": 0.0004570389999116742
},
"communicator.exchange": {
"total": 0.04469502500000999,
"count": 1,
"is_parallel": true,
"self": 0.04469502500000999
},
"steps_from_proto": {
"total": 0.0016640639998968254,
"count": 1,
"is_parallel": true,
"self": 0.00048067899979287176,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011833850001039536,
"count": 8,
"is_parallel": true,
"self": 0.0011833850001039536
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1705.2752040169737,
"count": 96309,
"is_parallel": true,
"self": 41.235679040122704,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 33.987226408951756,
"count": 96309,
"is_parallel": true,
"self": 33.987226408951756
},
"communicator.exchange": {
"total": 1492.7428819050608,
"count": 96309,
"is_parallel": true,
"self": 1492.7428819050608
},
"steps_from_proto": {
"total": 137.30941666283843,
"count": 96309,
"is_parallel": true,
"self": 34.05759684784812,
"children": {
"_process_rank_one_or_two_observation": {
"total": 103.25181981499031,
"count": 770472,
"is_parallel": true,
"self": 103.25181981499031
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1050.0459815499537,
"count": 96310,
"self": 4.0948472109603244,
"children": {
"process_trajectory": {
"total": 241.16208699599724,
"count": 96310,
"self": 240.86859932199673,
"children": {
"RLTrainer._checkpoint": {
"total": 0.29348767400051656,
"count": 3,
"self": 0.29348767400051656
}
}
},
"_update_policy": {
"total": 804.7890473429961,
"count": 690,
"self": 320.0053215850396,
"children": {
"TorchPPOOptimizer.update": {
"total": 484.7837257579565,
"count": 34251,
"self": 484.7837257579565
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0730000212788582e-06,
"count": 1,
"self": 1.0730000212788582e-06
},
"TrainerController._save_models": {
"total": 0.08985049800048728,
"count": 1,
"self": 0.0016160260001925053,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08823447200029477,
"count": 1,
"self": 0.08823447200029477
}
}
}
}
}
}
}